License cleanup: add SPDX GPL-2.0 license identifier to files with no license
Many source files in the tree are missing licensing information, which
makes it harder for compliance tools to determine the correct license.
By default all files without license information are under the default
license of the kernel, which is GPL version 2.
Update the files which contain no license information with the 'GPL-2.0'
SPDX license identifier. The SPDX identifier is a legally binding
shorthand, which can be used instead of the full boiler plate text.
This patch is based on work done by Thomas Gleixner and Kate Stewart and
Philippe Ombredanne.
How this work was done:
Patches were generated and checked against linux-4.14-rc6 for a subset of
the use cases:
- file had no licensing information it it.
- file was a */uapi/* one with no licensing information in it,
- file was a */uapi/* one with existing licensing information,
Further patches will be generated in subsequent months to fix up cases
where non-standard license headers were used, and references to license
had to be inferred by heuristics based on keywords.
The analysis to determine which SPDX License Identifier to be applied to
a file was done in a spreadsheet of side by side results from of the
output of two independent scanners (ScanCode & Windriver) producing SPDX
tag:value files created by Philippe Ombredanne. Philippe prepared the
base worksheet, and did an initial spot review of a few 1000 files.
The 4.13 kernel was the starting point of the analysis with 60,537 files
assessed. Kate Stewart did a file by file comparison of the scanner
results in the spreadsheet to determine which SPDX license identifier(s)
to be applied to the file. She confirmed any determination that was not
immediately clear with lawyers working with the Linux Foundation.
Criteria used to select files for SPDX license identifier tagging was:
- Files considered eligible had to be source code files.
- Make and config files were included as candidates if they contained >5
lines of source
- File already had some variant of a license header in it (even if <5
lines).
All documentation files were explicitly excluded.
The following heuristics were used to determine which SPDX license
identifiers to apply.
- when both scanners couldn't find any license traces, file was
considered to have no license information in it, and the top level
COPYING file license applied.
For non */uapi/* files that summary was:
SPDX license identifier # files
---------------------------------------------------|-------
GPL-2.0 11139
and resulted in the first patch in this series.
If that file was a */uapi/* path one, it was "GPL-2.0 WITH
Linux-syscall-note" otherwise it was "GPL-2.0". Results of that was:
SPDX license identifier # files
---------------------------------------------------|-------
GPL-2.0 WITH Linux-syscall-note 930
and resulted in the second patch in this series.
- if a file had some form of licensing information in it, and was one
of the */uapi/* ones, it was denoted with the Linux-syscall-note if
any GPL family license was found in the file or had no licensing in
it (per prior point). Results summary:
SPDX license identifier # files
---------------------------------------------------|------
GPL-2.0 WITH Linux-syscall-note 270
GPL-2.0+ WITH Linux-syscall-note 169
((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) 21
((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) 17
LGPL-2.1+ WITH Linux-syscall-note 15
GPL-1.0+ WITH Linux-syscall-note 14
((GPL-2.0+ WITH Linux-syscall-note) OR BSD-3-Clause) 5
LGPL-2.0+ WITH Linux-syscall-note 4
LGPL-2.1 WITH Linux-syscall-note 3
((GPL-2.0 WITH Linux-syscall-note) OR MIT) 3
((GPL-2.0 WITH Linux-syscall-note) AND MIT) 1
and that resulted in the third patch in this series.
- when the two scanners agreed on the detected license(s), that became
the concluded license(s).
- when there was disagreement between the two scanners (one detected a
license but the other didn't, or they both detected different
licenses) a manual inspection of the file occurred.
- In most cases a manual inspection of the information in the file
resulted in a clear resolution of the license that should apply (and
which scanner probably needed to revisit its heuristics).
- When it was not immediately clear, the license identifier was
confirmed with lawyers working with the Linux Foundation.
- If there was any question as to the appropriate license identifier,
the file was flagged for further research and to be revisited later
in time.
In total, over 70 hours of logged manual review was done on the
spreadsheet to determine the SPDX license identifiers to apply to the
source files by Kate, Philippe, Thomas and, in some cases, confirmation
by lawyers working with the Linux Foundation.
Kate also obtained a third independent scan of the 4.13 code base from
FOSSology, and compared selected files where the other two scanners
disagreed against that SPDX file, to see if there was new insights. The
Windriver scanner is based on an older version of FOSSology in part, so
they are related.
Thomas did random spot checks in about 500 files from the spreadsheets
for the uapi headers and agreed with SPDX license identifier in the
files he inspected. For the non-uapi files Thomas did random spot checks
in about 15000 files.
In initial set of patches against 4.14-rc6, 3 files were found to have
copy/paste license identifier errors, and have been fixed to reflect the
correct identifier.
Additionally Philippe spent 10 hours this week doing a detailed manual
inspection and review of the 12,461 patched files from the initial patch
version early this week with:
- a full scancode scan run, collecting the matched texts, detected
license ids and scores
- reviewing anything where there was a license detected (about 500+
files) to ensure that the applied SPDX license was correct
- reviewing anything where there was no detection but the patch license
was not GPL-2.0 WITH Linux-syscall-note to ensure that the applied
SPDX license was correct
This produced a worksheet with 20 files needing minor correction. This
worksheet was then exported into 3 different .csv files for the
different types of files to be modified.
These .csv files were then reviewed by Greg. Thomas wrote a script to
parse the csv files and add the proper SPDX tag to the file, in the
format that the file expected. This script was further refined by Greg
based on the output to detect more types of files automatically and to
distinguish between header and source .c files (which need different
comment types.) Finally Greg ran the script using the .csv files to
generate the patches.
Reviewed-by: Kate Stewart <kstewart@linuxfoundation.org>
Reviewed-by: Philippe Ombredanne <pombredanne@nexb.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2017-11-01 15:07:57 +01:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-04-29 22:54:51 -07:00
|
|
|
|
2011-06-01 12:25:53 -05:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2008-07-04 09:59:22 -07:00
|
|
|
|
2011-06-01 12:25:53 -05:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-04-13 10:40:34 +00:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-06-15 18:23:39 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
2012-07-06 15:25:11 -05:00
|
|
|
|
2008-10-06 02:42:17 +04:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2015-02-13 14:39:38 -08:00
|
|
|
|
2022-09-15 17:03:49 +02:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-07-07 18:07:47 -07:00
|
|
|
|
2008-04-30 00:55:01 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2021-02-25 17:19:16 -08:00
|
|
|
|
2007-10-21 16:41:37 -07:00
|
|
|
|
2008-05-01 04:34:31 -07:00
|
|
|
|
2008-12-23 19:37:01 +09:00
|
|
|
|
2023-10-03 11:57:45 +02:00
|
|
|
|
2011-07-07 22:47:01 +03:00
|
|
|
|
2012-01-30 15:53:51 -06:00
|
|
|
|
2012-12-18 14:22:34 -08:00
|
|
|
|
2017-09-06 16:19:18 -07:00
|
|
|
|
2021-06-28 19:34:33 -07:00
|
|
|
|
2022-11-25 16:43:06 +08:00
|
|
|
|
2021-05-21 14:11:26 +02:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2021-06-28 19:34:55 -07:00
|
|
|
|
2010-10-21 10:29:19 +01:00
|
|
|
|
|
|
|
|
|
mm: sl[au]b: add knowledge of PFMEMALLOC reserve pages
When a user or administrator requires swap for their application, they
create a swap partition and file, format it with mkswap and activate it
with swapon. Swap over the network is considered as an option in diskless
systems. The two likely scenarios are when blade servers are used as part
of a cluster where the form factor or maintenance costs do not allow the
use of disks and thin clients.
The Linux Terminal Server Project recommends the use of the Network Block
Device (NBD) for swap according to the manual at
https://sourceforge.net/projects/ltsp/files/Docs-Admin-Guide/LTSPManual.pdf/download
There is also documentation and tutorials on how to setup swap over NBD at
places like https://help.ubuntu.com/community/UbuntuLTSP/EnableNBDSWAP The
nbd-client also documents the use of NBD as swap. Despite this, the fact
is that a machine using NBD for swap can deadlock within minutes if swap
is used intensively. This patch series addresses the problem.
The core issue is that network block devices do not use mempools like
normal block devices do. As the host cannot control where they receive
packets from, they cannot reliably work out in advance how much memory
they might need. Some years ago, Peter Zijlstra developed a series of
patches that supported swap over an NFS that at least one distribution is
carrying within their kernels. This patch series borrows very heavily
from Peter's work to support swapping over NBD as a pre-requisite to
supporting swap-over-NFS. The bulk of the complexity is concerned with
preserving memory that is allocated from the PFMEMALLOC reserves for use
by the network layer which is needed for both NBD and NFS.
Patch 1 adds knowledge of the PFMEMALLOC reserves to SLAB and SLUB to
preserve access to pages allocated under low memory situations
to callers that are freeing memory.
Patch 2 optimises the SLUB fast path to avoid pfmemalloc checks
Patch 3 introduces __GFP_MEMALLOC to allow access to the PFMEMALLOC
reserves without setting PFMEMALLOC.
Patch 4 opens the possibility for softirqs to use PFMEMALLOC reserves
for later use by network packet processing.
Patch 5 only sets page->pfmemalloc when ALLOC_NO_WATERMARKS was required
Patch 6 ignores memory policies when ALLOC_NO_WATERMARKS is set.
Patches 7-12 allows network processing to use PFMEMALLOC reserves when
the socket has been marked as being used by the VM to clean pages. If
packets are received and stored in pages that were allocated under
low-memory situations and are unrelated to the VM, the packets
are dropped.
Patch 11 reintroduces __skb_alloc_page which the networking
folk may object to but is needed in some cases to propogate
pfmemalloc from a newly allocated page to an skb. If there is a
strong objection, this patch can be dropped with the impact being
that swap-over-network will be slower in some cases but it should
not fail.
Patch 13 is a micro-optimisation to avoid a function call in the
common case.
Patch 14 tags NBD sockets as being SOCK_MEMALLOC so they can use
PFMEMALLOC if necessary.
Patch 15 notes that it is still possible for the PFMEMALLOC reserve
to be depleted. To prevent this, direct reclaimers get throttled on
a waitqueue if 50% of the PFMEMALLOC reserves are depleted. It is
expected that kswapd and the direct reclaimers already running
will clean enough pages for the low watermark to be reached and
the throttled processes are woken up.
Patch 16 adds a statistic to track how often processes get throttled
Some basic performance testing was run using kernel builds, netperf on
loopback for UDP and TCP, hackbench (pipes and sockets), iozone and
sysbench. Each of them were expected to use the sl*b allocators
reasonably heavily but there did not appear to be significant performance
variances.
For testing swap-over-NBD, a machine was booted with 2G of RAM with a
swapfile backed by NBD. 8*NUM_CPU processes were started that create
anonymous memory mappings and read them linearly in a loop. The total
size of the mappings were 4*PHYSICAL_MEMORY to use swap heavily under
memory pressure.
Without the patches and using SLUB, the machine locks up within minutes
and runs to completion with them applied. With SLAB, the story is
different as an unpatched kernel run to completion. However, the patched
kernel completed the test 45% faster.
MICRO
3.5.0-rc2 3.5.0-rc2
vanilla swapnbd
Unrecognised test vmscan-anon-mmap-write
MMTests Statistics: duration
Sys Time Running Test (seconds) 197.80 173.07
User+Sys Time Running Test (seconds) 206.96 182.03
Total Elapsed Time (seconds) 3240.70 1762.09
This patch: mm: sl[au]b: add knowledge of PFMEMALLOC reserve pages
Allocations of pages below the min watermark run a risk of the machine
hanging due to a lack of memory. To prevent this, only callers who have
PF_MEMALLOC or TIF_MEMDIE set and are not processing an interrupt are
allowed to allocate with ALLOC_NO_WATERMARKS. Once they are allocated to
a slab though, nothing prevents other callers consuming free objects
within those slabs. This patch limits access to slab pages that were
alloced from the PFMEMALLOC reserves.
When this patch is applied, pages allocated from below the low watermark
are returned with page->pfmemalloc set and it is up to the caller to
determine how the page should be protected. SLAB restricts access to any
page with page->pfmemalloc set to callers which are known to able to
access the PFMEMALLOC reserve. If one is not available, an attempt is
made to allocate a new page rather than use a reserve. SLUB is a bit more
relaxed in that it only records if the current per-CPU page was allocated
from PFMEMALLOC reserve and uses another partial slab if the caller does
not have the necessary GFP or process flags. This was found to be
sufficient in tests to avoid hangs due to SLUB generally maintaining
smaller lists than SLAB.
In low-memory conditions it does mean that !PFMEMALLOC allocators can fail
a slab allocation even though free objects are available because they are
being preserved for callers that are freeing pages.
[a.p.zijlstra@chello.nl: Original implementation]
[sebastian@breakpoint.cc: Correct order of page flag clearing]
Signed-off-by: Mel Gorman <mgorman@suse.de>
Cc: David Miller <davem@davemloft.net>
Cc: Neil Brown <neilb@suse.de>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Mike Christie <michaelc@cs.wisc.edu>
Cc: Eric B Munson <emunson@mgebm.net>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Sebastian Andrzej Siewior <sebastian@breakpoint.cc>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Christoph Lameter <cl@linux.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-07-31 16:43:58 -07:00
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
2012-07-06 15:25:12 -05:00
|
|
|
|
2021-05-22 01:59:38 +02:00
|
|
|
|
|
|
|
|
|
2022-08-23 19:03:58 +02:00
|
|
|
|
2021-05-22 01:59:38 +02:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2012-07-06 15:25:12 -05:00
|
|
|
|
2011-06-01 12:25:53 -05:00
|
|
|
|
2012-07-06 15:25:12 -05:00
|
|
|
|
2011-06-01 12:25:53 -05:00
|
|
|
|
2021-05-22 01:59:38 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-06-01 12:25:53 -05:00
|
|
|
|
2022-08-23 19:03:58 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-11-15 16:55:15 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-06-01 12:25:53 -05:00
|
|
|
|
2021-05-22 01:59:38 +02:00
|
|
|
|
|
|
|
|
|
2023-11-02 03:23:30 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-11-15 16:55:15 +01:00
|
|
|
|
2019-05-13 17:16:28 -07:00
|
|
|
|
|
|
|
|
|
2021-11-15 16:55:15 +01:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2023-11-02 03:23:30 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-05-22 01:59:38 +02:00
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-05-22 01:59:38 +02:00
|
|
|
|
2022-08-23 19:03:58 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-05-22 01:59:38 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-08-25 09:51:36 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-05-22 01:59:38 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-09 02:32:39 -07:00
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2007-05-09 02:32:39 -07:00
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-11-15 16:55:15 +01:00
|
|
|
|
2007-05-16 22:10:53 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-10-16 01:26:05 -07:00
|
|
|
|
2007-05-10 03:15:16 -07:00
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2019-11-30 17:49:34 -08:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2007-05-10 03:15:16 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
2021-05-21 14:03:23 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-08-25 09:51:36 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-05-21 14:03:23 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-08-25 09:51:36 +02:00
|
|
|
|
2021-05-21 14:03:23 +02:00
|
|
|
|
|
|
|
|
|
2022-11-21 16:58:39 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-08-06 23:18:51 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-06-28 19:34:52 -07:00
|
|
|
|
2020-08-06 23:18:51 -07:00
|
|
|
|
2024-10-01 12:08:06 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
mm/slub: enable debugging memory wasting of kmalloc
kmalloc's API family is critical for mm, with one nature that it will
round up the request size to a fixed one (mostly power of 2). Say
when user requests memory for '2^n + 1' bytes, actually 2^(n+1) bytes
could be allocated, so in worst case, there is around 50% memory
space waste.
The wastage is not a big issue for requests that get allocated/freed
quickly, but may cause problems with objects that have longer life
time.
We've met a kernel boot OOM panic (v5.10), and from the dumped slab
info:
[ 26.062145] kmalloc-2k 814056KB 814056KB
From debug we found there are huge number of 'struct iova_magazine',
whose size is 1032 bytes (1024 + 8), so each allocation will waste
1016 bytes. Though the issue was solved by giving the right (bigger)
size of RAM, it is still nice to optimize the size (either use a
kmalloc friendly size or create a dedicated slab for it).
And from lkml archive, there was another crash kernel OOM case [1]
back in 2019, which seems to be related with the similar slab waste
situation, as the log is similar:
[ 4.332648] iommu: Adding device 0000:20:02.0 to group 16
[ 4.338946] swapper/0 invoked oom-killer: gfp_mask=0x6040c0(GFP_KERNEL|__GFP_COMP), nodemask=(null), order=0, oom_score_adj=0
...
[ 4.857565] kmalloc-2048 59164KB 59164KB
The crash kernel only has 256M memory, and 59M is pretty big here.
(Note: the related code has been changed and optimised in recent
kernel [2], these logs are just picked to demo the problem, also
a patch changing its size to 1024 bytes has been merged)
So add an way to track each kmalloc's memory waste info, and
leverage the existing SLUB debug framework (specifically
SLUB_STORE_USER) to show its call stack of original allocation,
so that user can evaluate the waste situation, identify some hot
spots and optimize accordingly, for a better utilization of memory.
The waste info is integrated into existing interface:
'/sys/kernel/debug/slab/kmalloc-xx/alloc_traces', one example of
'kmalloc-4k' after boot is:
126 ixgbe_alloc_q_vector+0xbe/0x830 [ixgbe] waste=233856/1856 age=280763/281414/282065 pid=1330 cpus=32 nodes=1
__kmem_cache_alloc_node+0x11f/0x4e0
__kmalloc_node+0x4e/0x140
ixgbe_alloc_q_vector+0xbe/0x830 [ixgbe]
ixgbe_init_interrupt_scheme+0x2ae/0xc90 [ixgbe]
ixgbe_probe+0x165f/0x1d20 [ixgbe]
local_pci_probe+0x78/0xc0
work_for_cpu_fn+0x26/0x40
...
which means in 'kmalloc-4k' slab, there are 126 requests of
2240 bytes which got a 4KB space (wasting 1856 bytes each
and 233856 bytes in total), from ixgbe_alloc_q_vector().
And when system starts some real workload like multiple docker
instances, there could are more severe waste.
[1]. https://lkml.org/lkml/2019/8/12/266
[2]. https://lore.kernel.org/lkml/2920df89-9975-5785-f79b-257d3052dfaf@huawei.com/
[Thanks Hyeonggon for pointing out several bugs about sorting/format]
[Thanks Vlastimil for suggesting way to reduce memory usage of
orig_size and keep it only for kmalloc objects]
Signed-off-by: Feng Tang <feng.tang@intel.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Robin Murphy <robin.murphy@arm.com>
Cc: John Garry <john.garry@huawei.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2022-09-13 14:54:20 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-11-02 03:23:23 +00:00
|
|
|
|
mm/slub: enable debugging memory wasting of kmalloc
kmalloc's API family is critical for mm, with one nature that it will
round up the request size to a fixed one (mostly power of 2). Say
when user requests memory for '2^n + 1' bytes, actually 2^(n+1) bytes
could be allocated, so in worst case, there is around 50% memory
space waste.
The wastage is not a big issue for requests that get allocated/freed
quickly, but may cause problems with objects that have longer life
time.
We've met a kernel boot OOM panic (v5.10), and from the dumped slab
info:
[ 26.062145] kmalloc-2k 814056KB 814056KB
From debug we found there are huge number of 'struct iova_magazine',
whose size is 1032 bytes (1024 + 8), so each allocation will waste
1016 bytes. Though the issue was solved by giving the right (bigger)
size of RAM, it is still nice to optimize the size (either use a
kmalloc friendly size or create a dedicated slab for it).
And from lkml archive, there was another crash kernel OOM case [1]
back in 2019, which seems to be related with the similar slab waste
situation, as the log is similar:
[ 4.332648] iommu: Adding device 0000:20:02.0 to group 16
[ 4.338946] swapper/0 invoked oom-killer: gfp_mask=0x6040c0(GFP_KERNEL|__GFP_COMP), nodemask=(null), order=0, oom_score_adj=0
...
[ 4.857565] kmalloc-2048 59164KB 59164KB
The crash kernel only has 256M memory, and 59M is pretty big here.
(Note: the related code has been changed and optimised in recent
kernel [2], these logs are just picked to demo the problem, also
a patch changing its size to 1024 bytes has been merged)
So add an way to track each kmalloc's memory waste info, and
leverage the existing SLUB debug framework (specifically
SLUB_STORE_USER) to show its call stack of original allocation,
so that user can evaluate the waste situation, identify some hot
spots and optimize accordingly, for a better utilization of memory.
The waste info is integrated into existing interface:
'/sys/kernel/debug/slab/kmalloc-xx/alloc_traces', one example of
'kmalloc-4k' after boot is:
126 ixgbe_alloc_q_vector+0xbe/0x830 [ixgbe] waste=233856/1856 age=280763/281414/282065 pid=1330 cpus=32 nodes=1
__kmem_cache_alloc_node+0x11f/0x4e0
__kmalloc_node+0x4e/0x140
ixgbe_alloc_q_vector+0xbe/0x830 [ixgbe]
ixgbe_init_interrupt_scheme+0x2ae/0xc90 [ixgbe]
ixgbe_probe+0x165f/0x1d20 [ixgbe]
local_pci_probe+0x78/0xc0
work_for_cpu_fn+0x26/0x40
...
which means in 'kmalloc-4k' slab, there are 126 requests of
2240 bytes which got a 4KB space (wasting 1856 bytes each
and 233856 bytes in total), from ixgbe_alloc_q_vector().
And when system starts some real workload like multiple docker
instances, there could are more severe waste.
[1]. https://lkml.org/lkml/2019/8/12/266
[2]. https://lore.kernel.org/lkml/2920df89-9975-5785-f79b-257d3052dfaf@huawei.com/
[Thanks Hyeonggon for pointing out several bugs about sorting/format]
[Thanks Vlastimil for suggesting way to reduce memory usage of
orig_size and keep it only for kmalloc objects]
Signed-off-by: Feng Tang <feng.tang@intel.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Robin Murphy <robin.murphy@arm.com>
Cc: John Garry <john.garry@huawei.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2022-09-13 14:54:20 +08:00
|
|
|
|
|
|
|
|
|
2020-08-06 23:18:55 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2010-07-09 14:07:14 -05:00
|
|
|
|
2007-05-16 22:10:56 -07:00
|
|
|
|
2016-08-04 15:31:55 -07:00
|
|
|
|
2016-03-15 14:55:12 -07:00
|
|
|
|
2020-08-06 23:18:55 -07:00
|
|
|
|
2016-03-15 14:55:12 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-06-19 14:05:52 +09:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-06-01 12:25:49 -05:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-11-15 10:50:28 +01:00
|
|
|
|
2007-05-06 14:49:46 -07:00
|
|
|
|
2021-04-29 22:54:51 -07:00
|
|
|
|
2007-05-06 14:49:46 -07:00
|
|
|
|
|
|
|
|
|
2007-12-21 14:37:37 -08:00
|
|
|
|
2007-05-06 14:49:44 -07:00
|
|
|
|
2007-05-06 14:49:46 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-11-08 20:47:37 +08:00
|
|
|
|
2007-05-06 14:49:46 -07:00
|
|
|
|
|
|
|
|
|
2022-11-15 10:50:28 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:46 -07:00
|
|
|
|
2016-03-15 14:55:06 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2007-05-09 02:32:39 -07:00
|
|
|
|
2016-03-15 14:55:09 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2009-07-07 00:14:14 -07:00
|
|
|
|
2009-07-27 18:30:35 -07:00
|
|
|
|
2023-12-15 11:41:48 +08:00
|
|
|
|
2009-07-27 18:30:35 -07:00
|
|
|
|
2009-07-07 00:14:14 -07:00
|
|
|
|
2009-07-27 18:30:35 -07:00
|
|
|
|
2009-07-07 00:14:14 -07:00
|
|
|
|
2008-10-22 23:00:38 +04:00
|
|
|
|
|
|
|
|
|
2021-11-15 16:55:15 +01:00
|
|
|
|
2008-10-22 23:00:38 +04:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2017-11-15 17:32:18 -08:00
|
|
|
|
2024-02-23 19:27:18 +01:00
|
|
|
|
2017-11-15 17:32:18 -08:00
|
|
|
|
2023-05-31 15:08:43 +02:00
|
|
|
|
|
|
|
|
|
2024-02-23 19:27:18 +01:00
|
|
|
|
2023-05-31 15:08:43 +02:00
|
|
|
|
2024-02-23 19:27:18 +01:00
|
|
|
|
2023-05-31 15:08:43 +02:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2007-05-09 02:32:43 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-07-07 11:36:36 -07:00
|
|
|
|
2007-05-09 02:32:43 -07:00
|
|
|
|
2008-08-19 20:43:25 +03:00
|
|
|
|
2021-07-07 18:07:47 -07:00
|
|
|
|
|
|
|
|
|
2011-07-07 11:36:36 -07:00
|
|
|
|
2007-05-09 02:32:43 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-11-14 18:18:39 +01:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-07-17 04:03:24 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
2021-06-28 19:34:55 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-10-03 09:54:15 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-02-21 12:12:54 +00:00
|
|
|
|
2023-10-03 09:54:15 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-03-22 13:35:00 -05:00
|
|
|
|
2008-02-07 17:47:41 -08:00
|
|
|
|
|
|
|
|
|
2014-04-07 15:39:42 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-02-07 17:47:41 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-08-07 20:50:44 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-10-03 14:57:49 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
mm, slab, slub: stop taking memory hotplug lock
Since commit 03afc0e25f7f ("slab: get_online_mems for
kmem_cache_{create,destroy,shrink}") we are taking memory hotplug lock for
SLAB and SLUB when creating, destroying or shrinking a cache. It is quite
a heavy lock and it's best to avoid it if possible, as we had several
issues with lockdep complaining about ordering in the past, see e.g.
e4f8e513c3d3 ("mm/slub: fix a deadlock in show_slab_objects()").
The problem scenario in 03afc0e25f7f (solved by the memory hotplug lock)
can be summarized as follows: while there's slab_mutex synchronizing new
kmem cache creation and SLUB's MEM_GOING_ONLINE callback
slab_mem_going_online_callback(), we may miss creation of kmem_cache_node
for the hotplugged node in the new kmem cache, because the hotplug
callback doesn't yet see the new cache, and cache creation in
init_kmem_cache_nodes() only inits kmem_cache_node for nodes in the
N_NORMAL_MEMORY nodemask, which however may not yet include the new node,
as that happens only later after the MEM_GOING_ONLINE callback.
Instead of using get/put_online_mems(), the problem can be solved by SLUB
maintaining its own nodemask of nodes for which it has allocated the
per-node kmem_cache_node structures. This nodemask would generally mirror
the N_NORMAL_MEMORY nodemask, but would be updated only in under SLUB's
control in its memory hotplug callbacks under the slab_mutex. This patch
adds such nodemask and its handling.
Commit 03afc0e25f7f mentiones "issues like [the one above]", but there
don't appear to be further issues. All the paths (shared for SLAB and
SLUB) taking the memory hotplug locks are also taking the slab_mutex,
except kmem_cache_shrink() where 03afc0e25f7f replaced slab_mutex with
get/put_online_mems().
We however cannot simply restore slab_mutex in kmem_cache_shrink(), as
SLUB can enters the function from a write to sysfs 'shrink' file, thus
holding kernfs lock, and in kmem_cache_create() the kernfs lock is nested
within slab_mutex. But on closer inspection we don't actually need to
protect kmem_cache_shrink() from hotplug callbacks: While SLUB's
__kmem_cache_shrink() does for_each_kmem_cache_node(), missing a new node
added in parallel hotplug is not fatal, and parallel hotremove does not
free kmem_cache_node's anymore after the previous patch, so use-after free
cannot happen. The per-node shrinking itself is protected by
n->list_lock. Same is true for SLAB, and SLOB is no-op.
SLAB also doesn't need the memory hotplug locking, which it only gained by
03afc0e25f7f through the shared paths in slab_common.c. Its memory
hotplug callbacks are also protected by slab_mutex against races with
these paths. The problem of SLUB relying on N_NORMAL_MEMORY doesn't apply
to SLAB, as its setup_kmem_cache_nodes relies on N_ONLINE, and the new
node is already set there during the MEM_GOING_ONLINE callback, so no
special care is needed for SLAB.
As such, this patch removes all get/put_online_mems() usage by the slab
subsystem.
Link: https://lkml.kernel.org/r/20210113131634.3671-3-vbabka@suse.cz
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Christoph Lameter <cl@linux.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Qian Cai <cai@redhat.com>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-02-24 12:01:12 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-11-15 18:14:31 +01:00
|
|
|
|
2022-09-19 18:39:29 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-11-15 18:14:31 +01:00
|
|
|
|
2022-09-19 18:39:29 +02:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-09-06 16:19:18 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-07-04 13:58:34 +00:00
|
|
|
|
|
|
|
|
|
2017-09-06 16:19:18 -07:00
|
|
|
|
2023-07-11 12:24:59 +02:00
|
|
|
|
|
|
|
|
|
2017-09-06 16:19:18 -07:00
|
|
|
|
2023-07-11 12:24:59 +02:00
|
|
|
|
2017-09-06 16:19:18 -07:00
|
|
|
|
2023-07-11 12:24:59 +02:00
|
|
|
|
2017-09-06 16:19:18 -07:00
|
|
|
|
2023-07-11 12:24:59 +02:00
|
|
|
|
2017-09-06 16:19:18 -07:00
|
|
|
|
|
|
|
|
|
2023-07-04 13:58:34 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-07-11 12:24:59 +02:00
|
|
|
|
2023-07-04 13:58:34 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-09 02:32:40 -07:00
|
|
|
|
|
|
|
|
|
2023-07-11 15:35:33 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-12-22 12:02:17 -08:00
|
|
|
|
2023-07-11 15:35:33 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-09 02:32:40 -07:00
|
|
|
|
|
|
|
|
|
2022-11-15 18:14:31 +01:00
|
|
|
|
slub: prefetch next freelist pointer in slab_alloc()
Recycling a page is a problem, since freelist link chain is hot on
cpu(s) which freed objects, and possibly very cold on cpu currently
owning slab.
Adding a prefetch of cache line containing the pointer to next object in
slab_alloc() helps a lot in many workloads, in particular on assymetric
ones (allocations done on one cpu, frees on another cpus). Added cost is
three machine instructions only.
Examples on my dual socket quad core ht machine (Intel CPU E5540
@2.53GHz) (16 logical cpus, 2 memory nodes), 64bit kernel.
Before patch :
# perf stat -r 32 hackbench 50 process 4000 >/dev/null
Performance counter stats for 'hackbench 50 process 4000' (32 runs):
327577,471718 task-clock # 15,821 CPUs utilized ( +- 0,64% )
28 866 491 context-switches # 0,088 M/sec ( +- 1,80% )
1 506 929 CPU-migrations # 0,005 M/sec ( +- 3,24% )
127 151 page-faults # 0,000 M/sec ( +- 0,16% )
829 399 813 448 cycles # 2,532 GHz ( +- 0,64% )
580 664 691 740 stalled-cycles-frontend # 70,01% frontend cycles idle ( +- 0,71% )
197 431 700 448 stalled-cycles-backend # 23,80% backend cycles idle ( +- 1,03% )
503 548 648 975 instructions # 0,61 insns per cycle
# 1,15 stalled cycles per insn ( +- 0,46% )
95 780 068 471 branches # 292,389 M/sec ( +- 0,48% )
1 426 407 916 branch-misses # 1,49% of all branches ( +- 1,35% )
20,705679994 seconds time elapsed ( +- 0,64% )
After patch :
# perf stat -r 32 hackbench 50 process 4000 >/dev/null
Performance counter stats for 'hackbench 50 process 4000' (32 runs):
286236,542804 task-clock # 15,786 CPUs utilized ( +- 1,32% )
19 703 372 context-switches # 0,069 M/sec ( +- 4,99% )
1 658 249 CPU-migrations # 0,006 M/sec ( +- 6,62% )
126 776 page-faults # 0,000 M/sec ( +- 0,12% )
724 636 593 213 cycles # 2,532 GHz ( +- 1,32% )
499 320 714 837 stalled-cycles-frontend # 68,91% frontend cycles idle ( +- 1,47% )
156 555 126 809 stalled-cycles-backend # 21,60% backend cycles idle ( +- 2,22% )
463 897 792 661 instructions # 0,64 insns per cycle
# 1,08 stalled cycles per insn ( +- 0,94% )
87 717 352 563 branches # 306,451 M/sec ( +- 0,99% )
941 738 280 branch-misses # 1,07% of all branches ( +- 3,35% )
18,132070670 seconds time elapsed ( +- 1,30% )
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Acked-by: Christoph Lameter <cl@linux.com>
CC: Matt Mackall <mpm@selenic.com>
CC: David Rientjes <rientjes@google.com>
CC: "Alex,Shi" <alex.shi@intel.com>
CC: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Pekka Enberg <penberg@kernel.org>
2011-12-16 16:25:34 +01:00
|
|
|
|
|
|
|
|
|
2021-11-05 13:35:24 -07:00
|
|
|
|
slub: prefetch next freelist pointer in slab_alloc()
Recycling a page is a problem, since freelist link chain is hot on
cpu(s) which freed objects, and possibly very cold on cpu currently
owning slab.
Adding a prefetch of cache line containing the pointer to next object in
slab_alloc() helps a lot in many workloads, in particular on assymetric
ones (allocations done on one cpu, frees on another cpus). Added cost is
three machine instructions only.
Examples on my dual socket quad core ht machine (Intel CPU E5540
@2.53GHz) (16 logical cpus, 2 memory nodes), 64bit kernel.
Before patch :
# perf stat -r 32 hackbench 50 process 4000 >/dev/null
Performance counter stats for 'hackbench 50 process 4000' (32 runs):
327577,471718 task-clock # 15,821 CPUs utilized ( +- 0,64% )
28 866 491 context-switches # 0,088 M/sec ( +- 1,80% )
1 506 929 CPU-migrations # 0,005 M/sec ( +- 3,24% )
127 151 page-faults # 0,000 M/sec ( +- 0,16% )
829 399 813 448 cycles # 2,532 GHz ( +- 0,64% )
580 664 691 740 stalled-cycles-frontend # 70,01% frontend cycles idle ( +- 0,71% )
197 431 700 448 stalled-cycles-backend # 23,80% backend cycles idle ( +- 1,03% )
503 548 648 975 instructions # 0,61 insns per cycle
# 1,15 stalled cycles per insn ( +- 0,46% )
95 780 068 471 branches # 292,389 M/sec ( +- 0,48% )
1 426 407 916 branch-misses # 1,49% of all branches ( +- 1,35% )
20,705679994 seconds time elapsed ( +- 0,64% )
After patch :
# perf stat -r 32 hackbench 50 process 4000 >/dev/null
Performance counter stats for 'hackbench 50 process 4000' (32 runs):
286236,542804 task-clock # 15,786 CPUs utilized ( +- 1,32% )
19 703 372 context-switches # 0,069 M/sec ( +- 4,99% )
1 658 249 CPU-migrations # 0,006 M/sec ( +- 6,62% )
126 776 page-faults # 0,000 M/sec ( +- 0,12% )
724 636 593 213 cycles # 2,532 GHz ( +- 1,32% )
499 320 714 837 stalled-cycles-frontend # 68,91% frontend cycles idle ( +- 1,47% )
156 555 126 809 stalled-cycles-backend # 21,60% backend cycles idle ( +- 2,22% )
463 897 792 661 instructions # 0,64 insns per cycle
# 1,08 stalled cycles per insn ( +- 0,94% )
87 717 352 563 branches # 306,451 M/sec ( +- 0,99% )
941 738 280 branch-misses # 1,07% of all branches ( +- 3,35% )
18,132070670 seconds time elapsed ( +- 1,30% )
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Acked-by: Christoph Lameter <cl@linux.com>
CC: Matt Mackall <mpm@selenic.com>
CC: David Rientjes <rientjes@google.com>
CC: "Alex,Shi" <alex.shi@intel.com>
CC: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Pekka Enberg <penberg@kernel.org>
2011-12-16 16:25:34 +01:00
|
|
|
|
2022-11-15 18:14:31 +01:00
|
|
|
|
slub: prefetch next freelist pointer in slab_alloc()
Recycling a page is a problem, since freelist link chain is hot on
cpu(s) which freed objects, and possibly very cold on cpu currently
owning slab.
Adding a prefetch of cache line containing the pointer to next object in
slab_alloc() helps a lot in many workloads, in particular on assymetric
ones (allocations done on one cpu, frees on another cpus). Added cost is
three machine instructions only.
Examples on my dual socket quad core ht machine (Intel CPU E5540
@2.53GHz) (16 logical cpus, 2 memory nodes), 64bit kernel.
Before patch :
# perf stat -r 32 hackbench 50 process 4000 >/dev/null
Performance counter stats for 'hackbench 50 process 4000' (32 runs):
327577,471718 task-clock # 15,821 CPUs utilized ( +- 0,64% )
28 866 491 context-switches # 0,088 M/sec ( +- 1,80% )
1 506 929 CPU-migrations # 0,005 M/sec ( +- 3,24% )
127 151 page-faults # 0,000 M/sec ( +- 0,16% )
829 399 813 448 cycles # 2,532 GHz ( +- 0,64% )
580 664 691 740 stalled-cycles-frontend # 70,01% frontend cycles idle ( +- 0,71% )
197 431 700 448 stalled-cycles-backend # 23,80% backend cycles idle ( +- 1,03% )
503 548 648 975 instructions # 0,61 insns per cycle
# 1,15 stalled cycles per insn ( +- 0,46% )
95 780 068 471 branches # 292,389 M/sec ( +- 0,48% )
1 426 407 916 branch-misses # 1,49% of all branches ( +- 1,35% )
20,705679994 seconds time elapsed ( +- 0,64% )
After patch :
# perf stat -r 32 hackbench 50 process 4000 >/dev/null
Performance counter stats for 'hackbench 50 process 4000' (32 runs):
286236,542804 task-clock # 15,786 CPUs utilized ( +- 1,32% )
19 703 372 context-switches # 0,069 M/sec ( +- 4,99% )
1 658 249 CPU-migrations # 0,006 M/sec ( +- 6,62% )
126 776 page-faults # 0,000 M/sec ( +- 0,12% )
724 636 593 213 cycles # 2,532 GHz ( +- 1,32% )
499 320 714 837 stalled-cycles-frontend # 68,91% frontend cycles idle ( +- 1,47% )
156 555 126 809 stalled-cycles-backend # 21,60% backend cycles idle ( +- 2,22% )
463 897 792 661 instructions # 0,64 insns per cycle
# 1,08 stalled cycles per insn ( +- 0,94% )
87 717 352 563 branches # 306,451 M/sec ( +- 0,99% )
941 738 280 branch-misses # 1,07% of all branches ( +- 3,35% )
18,132070670 seconds time elapsed ( +- 1,30% )
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Acked-by: Christoph Lameter <cl@linux.com>
CC: Matt Mackall <mpm@selenic.com>
CC: David Rientjes <rientjes@google.com>
CC: "Alex,Shi" <alex.shi@intel.com>
CC: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Pekka Enberg <penberg@kernel.org>
2011-12-16 16:25:34 +01:00
|
|
|
|
2022-09-15 17:03:49 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-05-16 15:26:08 -05:00
|
|
|
|
|
|
|
|
|
2017-09-06 16:19:18 -07:00
|
|
|
|
2023-07-04 13:58:34 +00:00
|
|
|
|
2011-05-16 15:26:08 -05:00
|
|
|
|
mm, debug_pagealloc: don't rely on static keys too early
Commit 96a2b03f281d ("mm, debug_pagelloc: use static keys to enable
debugging") has introduced a static key to reduce overhead when
debug_pagealloc is compiled in but not enabled. It relied on the
assumption that jump_label_init() is called before parse_early_param()
as in start_kernel(), so when the "debug_pagealloc=on" option is parsed,
it is safe to enable the static key.
However, it turns out multiple architectures call parse_early_param()
earlier from their setup_arch(). x86 also calls jump_label_init() even
earlier, so no issue was found while testing the commit, but same is not
true for e.g. ppc64 and s390 where the kernel would not boot with
debug_pagealloc=on as found by our QA.
To fix this without tricky changes to init code of multiple
architectures, this patch partially reverts the static key conversion
from 96a2b03f281d. Init-time and non-fastpath calls (such as in arch
code) of debug_pagealloc_enabled() will again test a simple bool
variable. Fastpath mm code is converted to a new
debug_pagealloc_enabled_static() variant that relies on the static key,
which is enabled in a well-defined point in mm_init() where it's
guaranteed that jump_label_init() has been called, regardless of
architecture.
[sfr@canb.auug.org.au: export _debug_pagealloc_enabled_early]
Link: http://lkml.kernel.org/r/20200106164944.063ac07b@canb.auug.org.au
Link: http://lkml.kernel.org/r/20191219130612.23171-1-vbabka@suse.cz
Fixes: 96a2b03f281d ("mm, debug_pagelloc: use static keys to enable debugging")
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Qian Cai <cai@lca.pw>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-01-13 16:29:20 -08:00
|
|
|
|
2016-03-17 14:17:53 -07:00
|
|
|
|
|
|
|
|
|
2021-05-22 17:41:56 -07:00
|
|
|
|
2017-09-06 16:19:18 -07:00
|
|
|
|
2023-07-04 13:58:34 +00:00
|
|
|
|
|
|
|
|
|
2011-05-16 15:26:08 -05:00
|
|
|
|
|
|
|
|
|
2007-05-09 02:32:40 -07:00
|
|
|
|
|
|
|
|
|
2017-09-06 16:19:18 -07:00
|
|
|
|
|
|
|
|
|
2017-09-06 16:19:22 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-12-22 12:02:17 -08:00
|
|
|
|
2023-07-04 13:58:34 +00:00
|
|
|
|
2007-05-09 02:32:40 -07:00
|
|
|
|
|
|
|
|
|
2024-04-30 13:34:59 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-09 02:32:40 -07:00
|
|
|
|
2008-04-14 19:11:31 +03:00
|
|
|
|
2016-03-15 14:55:12 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-09 02:32:40 -07:00
|
|
|
|
2018-06-07 17:09:10 -07:00
|
|
|
|
2011-03-10 15:21:48 +08:00
|
|
|
|
2018-06-07 17:09:10 -07:00
|
|
|
|
2011-03-10 15:21:48 +08:00
|
|
|
|
|
|
|
|
|
2018-04-05 16:21:39 -07:00
|
|
|
|
2018-06-07 17:09:10 -07:00
|
|
|
|
2008-04-14 19:11:31 +03:00
|
|
|
|
|
|
|
|
|
2018-06-07 17:09:10 -07:00
|
|
|
|
2008-04-14 19:11:31 +03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-04-05 16:21:39 -07:00
|
|
|
|
2008-04-14 19:11:31 +03:00
|
|
|
|
2008-10-22 23:00:38 +04:00
|
|
|
|
2008-04-14 19:11:31 +03:00
|
|
|
|
|
|
|
|
|
2018-04-05 16:21:39 -07:00
|
|
|
|
2008-04-14 19:11:31 +03:00
|
|
|
|
2008-10-22 23:00:38 +04:00
|
|
|
|
2008-04-14 19:11:31 +03:00
|
|
|
|
|
|
|
|
|
mm, slub: change percpu partial accounting from objects to pages
With CONFIG_SLUB_CPU_PARTIAL enabled, SLUB keeps a percpu list of
partial slabs that can be promoted to cpu slab when the previous one is
depleted, without accessing the shared partial list. A slab can be
added to this list by 1) refill of an empty list from get_partial_node()
- once we really have to access the shared partial list, we acquire
multiple slabs to amortize the cost of locking, and 2) first free to a
previously full slab - instead of putting the slab on a shared partial
list, we can more cheaply freeze it and put it on the per-cpu list.
To control how large a percpu partial list can grow for a kmem cache,
set_cpu_partial() calculates a target number of free objects on each
cpu's percpu partial list, and this can be also set by the sysfs file
cpu_partial.
However, the tracking of actual number of objects is imprecise, in order
to limit overhead from cpu X freeing an objects to a slab on percpu
partial list of cpu Y. Basically, the percpu partial slabs form a
single linked list, and when we add a new slab to the list with current
head "oldpage", we set in the struct page of the slab we're adding:
page->pages = oldpage->pages + 1; // this is precise
page->pobjects = oldpage->pobjects + (page->objects - page->inuse);
page->next = oldpage;
Thus the real number of free objects in the slab (objects - inuse) is
only determined at the moment of adding the slab to the percpu partial
list, and further freeing doesn't update the pobjects counter nor
propagate it to the current list head. As Jann reports [1], this can
easily lead to large inaccuracies, where the target number of objects
(up to 30 by default) can translate to the same number of (empty) slab
pages on the list. In case 2) above, we put a slab with 1 free object
on the list, thus only increase page->pobjects by 1, even if there are
subsequent frees on the same slab. Jann has noticed this in practice
and so did we [2] when investigating significant increase of kmemcg
usage after switching from SLAB to SLUB.
While this is no longer a problem in kmemcg context thanks to the
accounting rewrite in 5.9, the memory waste is still not ideal and it's
questionable whether it makes sense to perform free object count based
control when object counts can easily become so much inaccurate. So
this patch converts the accounting to be based on number of pages only
(which is precise) and removes the page->pobjects field completely.
This is also ultimately simpler.
To retain the existing set_cpu_partial() heuristic, first calculate the
target number of objects as previously, but then convert it to target
number of pages by assuming the pages will be half-filled on average.
This assumption might obviously also be inaccurate in practice, but
cannot degrade to actual number of pages being equal to the target
number of objects.
We could also skip the intermediate step with target number of objects
and rewrite the heuristic in terms of pages. However we still have the
sysfs file cpu_partial which uses number of objects and could break
existing users if it suddenly becomes number of pages, so this patch
doesn't do that.
In practice, after this patch the heuristics limit the size of percpu
partial list up to 2 pages. In case of a reported regression (which
would mean some workload has benefited from the previous imprecise
object based counting), we can tune the heuristics to get a better
compromise within the new scheme, while still avoid the unexpectedly
long percpu partial lists.
[1] https://lore.kernel.org/linux-mm/CAG48ez2Qx5K1Cab-m8BdSibp6wLTip6ro4=-umR7BLsEgjEYzA@mail.gmail.com/
[2] https://lore.kernel.org/all/2f0f46e8-2535-410a-1859-e9cfa4e57c18@suse.cz/
==========
Evaluation
==========
Mel was kind enough to run v1 through mmtests machinery for netperf
(localhost) and hackbench and, for most significant results see below.
So there are some apparent regressions, especially with hackbench, which
I think ultimately boils down to having shorter percpu partial lists on
average and some benchmarks benefiting from longer ones. Monitoring
slab usage also indicated less memory usage by slab. Based on that, the
following patch will bump the defaults to allow longer percpu partial
lists than after this patch.
However the goal is certainly not such that we would limit the percpu
partial lists to 30 pages just because previously a specific alloc/free
pattern could lead to the limit of 30 objects translate to a limit to 30
pages - that would make little sense. This is a correctness patch, and
if a workload benefits from larger lists, the sysfs tuning knobs are
still there to allow that.
Netperf
2-socket Intel(R) Xeon(R) Gold 5218R CPU @ 2.10GHz (20 cores, 40 threads per socket), 384GB RAM
TCP-RR:
hmean before 127045.79 after 121092.94 (-4.69%, worse)
stddev before 2634.37 after 1254.08
UDP-RR:
hmean before 166985.45 after 160668.94 ( -3.78%, worse)
stddev before 4059.69 after 1943.63
2-socket Intel(R) Xeon(R) CPU E5-2698 v4 @ 2.20GHz (20 cores, 40 threads per socket), 512GB RAM
TCP-RR:
hmean before 84173.25 after 76914.72 ( -8.62%, worse)
UDP-RR:
hmean before 93571.12 after 96428.69 ( 3.05%, better)
stddev before 23118.54 after 16828.14
2-socket Intel(R) Xeon(R) CPU E5-2670 v3 @ 2.30GHz (12 cores, 24 threads per socket), 64GB RAM
TCP-RR:
hmean before 49984.92 after 48922.27 ( -2.13%, worse)
stddev before 6248.15 after 4740.51
UDP-RR:
hmean before 61854.31 after 68761.81 ( 11.17%, better)
stddev before 4093.54 after 5898.91
other machines - within 2%
Hackbench
(results before and after the patch, negative % means worse)
2-socket AMD EPYC 7713 (64 cores, 128 threads per core), 256GB RAM
hackbench-process-sockets
Amean 1 0.5380 0.5583 ( -3.78%)
Amean 4 0.7510 0.8150 ( -8.52%)
Amean 7 0.7930 0.9533 ( -20.22%)
Amean 12 0.7853 1.1313 ( -44.06%)
Amean 21 1.1520 1.4993 ( -30.15%)
Amean 30 1.6223 1.9237 ( -18.57%)
Amean 48 2.6767 2.9903 ( -11.72%)
Amean 79 4.0257 5.1150 ( -27.06%)
Amean 110 5.5193 7.4720 ( -35.38%)
Amean 141 7.2207 9.9840 ( -38.27%)
Amean 172 8.4770 12.1963 ( -43.88%)
Amean 203 9.6473 14.3137 ( -48.37%)
Amean 234 11.3960 18.7917 ( -64.90%)
Amean 265 13.9627 22.4607 ( -60.86%)
Amean 296 14.9163 26.0483 ( -74.63%)
hackbench-thread-sockets
Amean 1 0.5597 0.5877 ( -5.00%)
Amean 4 0.7913 0.8960 ( -13.23%)
Amean 7 0.8190 1.0017 ( -22.30%)
Amean 12 0.9560 1.1727 ( -22.66%)
Amean 21 1.7587 1.5660 ( 10.96%)
Amean 30 2.4477 1.9807 ( 19.08%)
Amean 48 3.4573 3.0630 ( 11.41%)
Amean 79 4.7903 5.1733 ( -8.00%)
Amean 110 6.1370 7.4220 ( -20.94%)
Amean 141 7.5777 9.2617 ( -22.22%)
Amean 172 9.2280 11.0907 ( -20.18%)
Amean 203 10.2793 13.3470 ( -29.84%)
Amean 234 11.2410 17.1070 ( -52.18%)
Amean 265 12.5970 23.3323 ( -85.22%)
Amean 296 17.1540 24.2857 ( -41.57%)
2-socket Intel(R) Xeon(R) Gold 5218R CPU @ 2.10GHz (20 cores, 40 threads
per socket), 384GB RAM
hackbench-process-sockets
Amean 1 0.5760 0.4793 ( 16.78%)
Amean 4 0.9430 0.9707 ( -2.93%)
Amean 7 1.5517 1.8843 ( -21.44%)
Amean 12 2.4903 2.7267 ( -9.49%)
Amean 21 3.9560 4.2877 ( -8.38%)
Amean 30 5.4613 5.8343 ( -6.83%)
Amean 48 8.5337 9.2937 ( -8.91%)
Amean 79 14.0670 15.2630 ( -8.50%)
Amean 110 19.2253 21.2467 ( -10.51%)
Amean 141 23.7557 25.8550 ( -8.84%)
Amean 172 28.4407 29.7603 ( -4.64%)
Amean 203 33.3407 33.9927 ( -1.96%)
Amean 234 38.3633 39.1150 ( -1.96%)
Amean 265 43.4420 43.8470 ( -0.93%)
Amean 296 48.3680 48.9300 ( -1.16%)
hackbench-thread-sockets
Amean 1 0.6080 0.6493 ( -6.80%)
Amean 4 1.0000 1.0513 ( -5.13%)
Amean 7 1.6607 2.0260 ( -22.00%)
Amean 12 2.7637 2.9273 ( -5.92%)
Amean 21 5.0613 4.5153 ( 10.79%)
Amean 30 6.3340 6.1140 ( 3.47%)
Amean 48 9.0567 9.5577 ( -5.53%)
Amean 79 14.5657 15.7983 ( -8.46%)
Amean 110 19.6213 21.6333 ( -10.25%)
Amean 141 24.1563 26.2697 ( -8.75%)
Amean 172 28.9687 30.2187 ( -4.32%)
Amean 203 33.9763 34.6970 ( -2.12%)
Amean 234 38.8647 39.3207 ( -1.17%)
Amean 265 44.0813 44.1507 ( -0.16%)
Amean 296 49.2040 49.4330 ( -0.47%)
2-socket Intel(R) Xeon(R) CPU E5-2698 v4 @ 2.20GHz (20 cores, 40 threads
per socket), 512GB RAM
hackbench-process-sockets
Amean 1 0.5027 0.5017 ( 0.20%)
Amean 4 1.1053 1.2033 ( -8.87%)
Amean 7 1.8760 2.1820 ( -16.31%)
Amean 12 2.9053 3.1810 ( -9.49%)
Amean 21 4.6777 4.9920 ( -6.72%)
Amean 30 6.5180 6.7827 ( -4.06%)
Amean 48 10.0710 10.5227 ( -4.48%)
Amean 79 16.4250 17.5053 ( -6.58%)
Amean 110 22.6203 24.4617 ( -8.14%)
Amean 141 28.0967 31.0363 ( -10.46%)
Amean 172 34.4030 36.9233 ( -7.33%)
Amean 203 40.5933 43.0850 ( -6.14%)
Amean 234 46.6477 48.7220 ( -4.45%)
Amean 265 53.0530 53.9597 ( -1.71%)
Amean 296 59.2760 59.9213 ( -1.09%)
hackbench-thread-sockets
Amean 1 0.5363 0.5330 ( 0.62%)
Amean 4 1.1647 1.2157 ( -4.38%)
Amean 7 1.9237 2.2833 ( -18.70%)
Amean 12 2.9943 3.3110 ( -10.58%)
Amean 21 4.9987 5.1880 ( -3.79%)
Amean 30 6.7583 7.0043 ( -3.64%)
Amean 48 10.4547 10.8353 ( -3.64%)
Amean 79 16.6707 17.6790 ( -6.05%)
Amean 110 22.8207 24.4403 ( -7.10%)
Amean 141 28.7090 31.0533 ( -8.17%)
Amean 172 34.9387 36.8260 ( -5.40%)
Amean 203 41.1567 43.0450 ( -4.59%)
Amean 234 47.3790 48.5307 ( -2.43%)
Amean 265 53.9543 54.6987 ( -1.38%)
Amean 296 60.0820 60.2163 ( -0.22%)
1-socket Intel(R) Xeon(R) CPU E3-1240 v5 @ 3.50GHz (4 cores, 8 threads),
32 GB RAM
hackbench-process-sockets
Amean 1 1.4760 1.5773 ( -6.87%)
Amean 3 3.9370 4.0910 ( -3.91%)
Amean 5 6.6797 6.9357 ( -3.83%)
Amean 7 9.3367 9.7150 ( -4.05%)
Amean 12 15.7627 16.1400 ( -2.39%)
Amean 18 23.5360 23.6890 ( -0.65%)
Amean 24 31.0663 31.3137 ( -0.80%)
Amean 30 38.7283 39.0037 ( -0.71%)
Amean 32 41.3417 41.6097 ( -0.65%)
hackbench-thread-sockets
Amean 1 1.5250 1.6043 ( -5.20%)
Amean 3 4.0897 4.2603 ( -4.17%)
Amean 5 6.7760 7.0933 ( -4.68%)
Amean 7 9.4817 9.9157 ( -4.58%)
Amean 12 15.9610 16.3937 ( -2.71%)
Amean 18 23.9543 24.3417 ( -1.62%)
Amean 24 31.4400 31.7217 ( -0.90%)
Amean 30 39.2457 39.5467 ( -0.77%)
Amean 32 41.8267 42.1230 ( -0.71%)
2-socket Intel(R) Xeon(R) CPU E5-2670 v3 @ 2.30GHz (12 cores, 24 threads
per socket), 64GB RAM
hackbench-process-sockets
Amean 1 1.0347 1.0880 ( -5.15%)
Amean 4 1.7267 1.8527 ( -7.30%)
Amean 7 2.6707 2.8110 ( -5.25%)
Amean 12 4.1617 4.3383 ( -4.25%)
Amean 21 7.0070 7.2600 ( -3.61%)
Amean 30 9.9187 10.2397 ( -3.24%)
Amean 48 15.6710 16.3923 ( -4.60%)
Amean 79 24.7743 26.1247 ( -5.45%)
Amean 110 34.3000 35.9307 ( -4.75%)
Amean 141 44.2043 44.8010 ( -1.35%)
Amean 172 54.2430 54.7260 ( -0.89%)
Amean 192 60.6557 60.9777 ( -0.53%)
hackbench-thread-sockets
Amean 1 1.0610 1.1353 ( -7.01%)
Amean 4 1.7543 1.9140 ( -9.10%)
Amean 7 2.7840 2.9573 ( -6.23%)
Amean 12 4.3813 4.4937 ( -2.56%)
Amean 21 7.3460 7.5350 ( -2.57%)
Amean 30 10.2313 10.5190 ( -2.81%)
Amean 48 15.9700 16.5940 ( -3.91%)
Amean 79 25.3973 26.6637 ( -4.99%)
Amean 110 35.1087 36.4797 ( -3.91%)
Amean 141 45.8220 46.3053 ( -1.05%)
Amean 172 55.4917 55.7320 ( -0.43%)
Amean 192 62.7490 62.5410 ( 0.33%)
Link: https://lkml.kernel.org/r/20211012134651.11258-1-vbabka@suse.cz
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reported-by: Jann Horn <jannh@google.com>
Cc: Roman Gushchin <guro@fb.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-11-05 13:35:17 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
mm, slub: change percpu partial accounting from objects to pages
With CONFIG_SLUB_CPU_PARTIAL enabled, SLUB keeps a percpu list of
partial slabs that can be promoted to cpu slab when the previous one is
depleted, without accessing the shared partial list. A slab can be
added to this list by 1) refill of an empty list from get_partial_node()
- once we really have to access the shared partial list, we acquire
multiple slabs to amortize the cost of locking, and 2) first free to a
previously full slab - instead of putting the slab on a shared partial
list, we can more cheaply freeze it and put it on the per-cpu list.
To control how large a percpu partial list can grow for a kmem cache,
set_cpu_partial() calculates a target number of free objects on each
cpu's percpu partial list, and this can be also set by the sysfs file
cpu_partial.
However, the tracking of actual number of objects is imprecise, in order
to limit overhead from cpu X freeing an objects to a slab on percpu
partial list of cpu Y. Basically, the percpu partial slabs form a
single linked list, and when we add a new slab to the list with current
head "oldpage", we set in the struct page of the slab we're adding:
page->pages = oldpage->pages + 1; // this is precise
page->pobjects = oldpage->pobjects + (page->objects - page->inuse);
page->next = oldpage;
Thus the real number of free objects in the slab (objects - inuse) is
only determined at the moment of adding the slab to the percpu partial
list, and further freeing doesn't update the pobjects counter nor
propagate it to the current list head. As Jann reports [1], this can
easily lead to large inaccuracies, where the target number of objects
(up to 30 by default) can translate to the same number of (empty) slab
pages on the list. In case 2) above, we put a slab with 1 free object
on the list, thus only increase page->pobjects by 1, even if there are
subsequent frees on the same slab. Jann has noticed this in practice
and so did we [2] when investigating significant increase of kmemcg
usage after switching from SLAB to SLUB.
While this is no longer a problem in kmemcg context thanks to the
accounting rewrite in 5.9, the memory waste is still not ideal and it's
questionable whether it makes sense to perform free object count based
control when object counts can easily become so much inaccurate. So
this patch converts the accounting to be based on number of pages only
(which is precise) and removes the page->pobjects field completely.
This is also ultimately simpler.
To retain the existing set_cpu_partial() heuristic, first calculate the
target number of objects as previously, but then convert it to target
number of pages by assuming the pages will be half-filled on average.
This assumption might obviously also be inaccurate in practice, but
cannot degrade to actual number of pages being equal to the target
number of objects.
We could also skip the intermediate step with target number of objects
and rewrite the heuristic in terms of pages. However we still have the
sysfs file cpu_partial which uses number of objects and could break
existing users if it suddenly becomes number of pages, so this patch
doesn't do that.
In practice, after this patch the heuristics limit the size of percpu
partial list up to 2 pages. In case of a reported regression (which
would mean some workload has benefited from the previous imprecise
object based counting), we can tune the heuristics to get a better
compromise within the new scheme, while still avoid the unexpectedly
long percpu partial lists.
[1] https://lore.kernel.org/linux-mm/CAG48ez2Qx5K1Cab-m8BdSibp6wLTip6ro4=-umR7BLsEgjEYzA@mail.gmail.com/
[2] https://lore.kernel.org/all/2f0f46e8-2535-410a-1859-e9cfa4e57c18@suse.cz/
==========
Evaluation
==========
Mel was kind enough to run v1 through mmtests machinery for netperf
(localhost) and hackbench and, for most significant results see below.
So there are some apparent regressions, especially with hackbench, which
I think ultimately boils down to having shorter percpu partial lists on
average and some benchmarks benefiting from longer ones. Monitoring
slab usage also indicated less memory usage by slab. Based on that, the
following patch will bump the defaults to allow longer percpu partial
lists than after this patch.
However the goal is certainly not such that we would limit the percpu
partial lists to 30 pages just because previously a specific alloc/free
pattern could lead to the limit of 30 objects translate to a limit to 30
pages - that would make little sense. This is a correctness patch, and
if a workload benefits from larger lists, the sysfs tuning knobs are
still there to allow that.
Netperf
2-socket Intel(R) Xeon(R) Gold 5218R CPU @ 2.10GHz (20 cores, 40 threads per socket), 384GB RAM
TCP-RR:
hmean before 127045.79 after 121092.94 (-4.69%, worse)
stddev before 2634.37 after 1254.08
UDP-RR:
hmean before 166985.45 after 160668.94 ( -3.78%, worse)
stddev before 4059.69 after 1943.63
2-socket Intel(R) Xeon(R) CPU E5-2698 v4 @ 2.20GHz (20 cores, 40 threads per socket), 512GB RAM
TCP-RR:
hmean before 84173.25 after 76914.72 ( -8.62%, worse)
UDP-RR:
hmean before 93571.12 after 96428.69 ( 3.05%, better)
stddev before 23118.54 after 16828.14
2-socket Intel(R) Xeon(R) CPU E5-2670 v3 @ 2.30GHz (12 cores, 24 threads per socket), 64GB RAM
TCP-RR:
hmean before 49984.92 after 48922.27 ( -2.13%, worse)
stddev before 6248.15 after 4740.51
UDP-RR:
hmean before 61854.31 after 68761.81 ( 11.17%, better)
stddev before 4093.54 after 5898.91
other machines - within 2%
Hackbench
(results before and after the patch, negative % means worse)
2-socket AMD EPYC 7713 (64 cores, 128 threads per core), 256GB RAM
hackbench-process-sockets
Amean 1 0.5380 0.5583 ( -3.78%)
Amean 4 0.7510 0.8150 ( -8.52%)
Amean 7 0.7930 0.9533 ( -20.22%)
Amean 12 0.7853 1.1313 ( -44.06%)
Amean 21 1.1520 1.4993 ( -30.15%)
Amean 30 1.6223 1.9237 ( -18.57%)
Amean 48 2.6767 2.9903 ( -11.72%)
Amean 79 4.0257 5.1150 ( -27.06%)
Amean 110 5.5193 7.4720 ( -35.38%)
Amean 141 7.2207 9.9840 ( -38.27%)
Amean 172 8.4770 12.1963 ( -43.88%)
Amean 203 9.6473 14.3137 ( -48.37%)
Amean 234 11.3960 18.7917 ( -64.90%)
Amean 265 13.9627 22.4607 ( -60.86%)
Amean 296 14.9163 26.0483 ( -74.63%)
hackbench-thread-sockets
Amean 1 0.5597 0.5877 ( -5.00%)
Amean 4 0.7913 0.8960 ( -13.23%)
Amean 7 0.8190 1.0017 ( -22.30%)
Amean 12 0.9560 1.1727 ( -22.66%)
Amean 21 1.7587 1.5660 ( 10.96%)
Amean 30 2.4477 1.9807 ( 19.08%)
Amean 48 3.4573 3.0630 ( 11.41%)
Amean 79 4.7903 5.1733 ( -8.00%)
Amean 110 6.1370 7.4220 ( -20.94%)
Amean 141 7.5777 9.2617 ( -22.22%)
Amean 172 9.2280 11.0907 ( -20.18%)
Amean 203 10.2793 13.3470 ( -29.84%)
Amean 234 11.2410 17.1070 ( -52.18%)
Amean 265 12.5970 23.3323 ( -85.22%)
Amean 296 17.1540 24.2857 ( -41.57%)
2-socket Intel(R) Xeon(R) Gold 5218R CPU @ 2.10GHz (20 cores, 40 threads
per socket), 384GB RAM
hackbench-process-sockets
Amean 1 0.5760 0.4793 ( 16.78%)
Amean 4 0.9430 0.9707 ( -2.93%)
Amean 7 1.5517 1.8843 ( -21.44%)
Amean 12 2.4903 2.7267 ( -9.49%)
Amean 21 3.9560 4.2877 ( -8.38%)
Amean 30 5.4613 5.8343 ( -6.83%)
Amean 48 8.5337 9.2937 ( -8.91%)
Amean 79 14.0670 15.2630 ( -8.50%)
Amean 110 19.2253 21.2467 ( -10.51%)
Amean 141 23.7557 25.8550 ( -8.84%)
Amean 172 28.4407 29.7603 ( -4.64%)
Amean 203 33.3407 33.9927 ( -1.96%)
Amean 234 38.3633 39.1150 ( -1.96%)
Amean 265 43.4420 43.8470 ( -0.93%)
Amean 296 48.3680 48.9300 ( -1.16%)
hackbench-thread-sockets
Amean 1 0.6080 0.6493 ( -6.80%)
Amean 4 1.0000 1.0513 ( -5.13%)
Amean 7 1.6607 2.0260 ( -22.00%)
Amean 12 2.7637 2.9273 ( -5.92%)
Amean 21 5.0613 4.5153 ( 10.79%)
Amean 30 6.3340 6.1140 ( 3.47%)
Amean 48 9.0567 9.5577 ( -5.53%)
Amean 79 14.5657 15.7983 ( -8.46%)
Amean 110 19.6213 21.6333 ( -10.25%)
Amean 141 24.1563 26.2697 ( -8.75%)
Amean 172 28.9687 30.2187 ( -4.32%)
Amean 203 33.9763 34.6970 ( -2.12%)
Amean 234 38.8647 39.3207 ( -1.17%)
Amean 265 44.0813 44.1507 ( -0.16%)
Amean 296 49.2040 49.4330 ( -0.47%)
2-socket Intel(R) Xeon(R) CPU E5-2698 v4 @ 2.20GHz (20 cores, 40 threads
per socket), 512GB RAM
hackbench-process-sockets
Amean 1 0.5027 0.5017 ( 0.20%)
Amean 4 1.1053 1.2033 ( -8.87%)
Amean 7 1.8760 2.1820 ( -16.31%)
Amean 12 2.9053 3.1810 ( -9.49%)
Amean 21 4.6777 4.9920 ( -6.72%)
Amean 30 6.5180 6.7827 ( -4.06%)
Amean 48 10.0710 10.5227 ( -4.48%)
Amean 79 16.4250 17.5053 ( -6.58%)
Amean 110 22.6203 24.4617 ( -8.14%)
Amean 141 28.0967 31.0363 ( -10.46%)
Amean 172 34.4030 36.9233 ( -7.33%)
Amean 203 40.5933 43.0850 ( -6.14%)
Amean 234 46.6477 48.7220 ( -4.45%)
Amean 265 53.0530 53.9597 ( -1.71%)
Amean 296 59.2760 59.9213 ( -1.09%)
hackbench-thread-sockets
Amean 1 0.5363 0.5330 ( 0.62%)
Amean 4 1.1647 1.2157 ( -4.38%)
Amean 7 1.9237 2.2833 ( -18.70%)
Amean 12 2.9943 3.3110 ( -10.58%)
Amean 21 4.9987 5.1880 ( -3.79%)
Amean 30 6.7583 7.0043 ( -3.64%)
Amean 48 10.4547 10.8353 ( -3.64%)
Amean 79 16.6707 17.6790 ( -6.05%)
Amean 110 22.8207 24.4403 ( -7.10%)
Amean 141 28.7090 31.0533 ( -8.17%)
Amean 172 34.9387 36.8260 ( -5.40%)
Amean 203 41.1567 43.0450 ( -4.59%)
Amean 234 47.3790 48.5307 ( -2.43%)
Amean 265 53.9543 54.6987 ( -1.38%)
Amean 296 60.0820 60.2163 ( -0.22%)
1-socket Intel(R) Xeon(R) CPU E3-1240 v5 @ 3.50GHz (4 cores, 8 threads),
32 GB RAM
hackbench-process-sockets
Amean 1 1.4760 1.5773 ( -6.87%)
Amean 3 3.9370 4.0910 ( -3.91%)
Amean 5 6.6797 6.9357 ( -3.83%)
Amean 7 9.3367 9.7150 ( -4.05%)
Amean 12 15.7627 16.1400 ( -2.39%)
Amean 18 23.5360 23.6890 ( -0.65%)
Amean 24 31.0663 31.3137 ( -0.80%)
Amean 30 38.7283 39.0037 ( -0.71%)
Amean 32 41.3417 41.6097 ( -0.65%)
hackbench-thread-sockets
Amean 1 1.5250 1.6043 ( -5.20%)
Amean 3 4.0897 4.2603 ( -4.17%)
Amean 5 6.7760 7.0933 ( -4.68%)
Amean 7 9.4817 9.9157 ( -4.58%)
Amean 12 15.9610 16.3937 ( -2.71%)
Amean 18 23.9543 24.3417 ( -1.62%)
Amean 24 31.4400 31.7217 ( -0.90%)
Amean 30 39.2457 39.5467 ( -0.77%)
Amean 32 41.8267 42.1230 ( -0.71%)
2-socket Intel(R) Xeon(R) CPU E5-2670 v3 @ 2.30GHz (12 cores, 24 threads
per socket), 64GB RAM
hackbench-process-sockets
Amean 1 1.0347 1.0880 ( -5.15%)
Amean 4 1.7267 1.8527 ( -7.30%)
Amean 7 2.6707 2.8110 ( -5.25%)
Amean 12 4.1617 4.3383 ( -4.25%)
Amean 21 7.0070 7.2600 ( -3.61%)
Amean 30 9.9187 10.2397 ( -3.24%)
Amean 48 15.6710 16.3923 ( -4.60%)
Amean 79 24.7743 26.1247 ( -5.45%)
Amean 110 34.3000 35.9307 ( -4.75%)
Amean 141 44.2043 44.8010 ( -1.35%)
Amean 172 54.2430 54.7260 ( -0.89%)
Amean 192 60.6557 60.9777 ( -0.53%)
hackbench-thread-sockets
Amean 1 1.0610 1.1353 ( -7.01%)
Amean 4 1.7543 1.9140 ( -9.10%)
Amean 7 2.7840 2.9573 ( -6.23%)
Amean 12 4.3813 4.4937 ( -2.56%)
Amean 21 7.3460 7.5350 ( -2.57%)
Amean 30 10.2313 10.5190 ( -2.81%)
Amean 48 15.9700 16.5940 ( -3.91%)
Amean 79 25.3973 26.6637 ( -4.99%)
Amean 110 35.1087 36.4797 ( -3.91%)
Amean 141 45.8220 46.3053 ( -1.05%)
Amean 172 55.4917 55.7320 ( -0.43%)
Amean 192 62.7490 62.5410 ( 0.33%)
Link: https://lkml.kernel.org/r/20211012134651.11258-1-vbabka@suse.cz
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reported-by: Jann Horn <jannh@google.com>
Cc: Roman Gushchin <guro@fb.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-11-05 13:35:17 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-11-15 16:55:15 +01:00
|
|
|
|
|
|
|
|
|
mm, slub: change percpu partial accounting from objects to pages
With CONFIG_SLUB_CPU_PARTIAL enabled, SLUB keeps a percpu list of
partial slabs that can be promoted to cpu slab when the previous one is
depleted, without accessing the shared partial list. A slab can be
added to this list by 1) refill of an empty list from get_partial_node()
- once we really have to access the shared partial list, we acquire
multiple slabs to amortize the cost of locking, and 2) first free to a
previously full slab - instead of putting the slab on a shared partial
list, we can more cheaply freeze it and put it on the per-cpu list.
To control how large a percpu partial list can grow for a kmem cache,
set_cpu_partial() calculates a target number of free objects on each
cpu's percpu partial list, and this can be also set by the sysfs file
cpu_partial.
However, the tracking of actual number of objects is imprecise, in order
to limit overhead from cpu X freeing an objects to a slab on percpu
partial list of cpu Y. Basically, the percpu partial slabs form a
single linked list, and when we add a new slab to the list with current
head "oldpage", we set in the struct page of the slab we're adding:
page->pages = oldpage->pages + 1; // this is precise
page->pobjects = oldpage->pobjects + (page->objects - page->inuse);
page->next = oldpage;
Thus the real number of free objects in the slab (objects - inuse) is
only determined at the moment of adding the slab to the percpu partial
list, and further freeing doesn't update the pobjects counter nor
propagate it to the current list head. As Jann reports [1], this can
easily lead to large inaccuracies, where the target number of objects
(up to 30 by default) can translate to the same number of (empty) slab
pages on the list. In case 2) above, we put a slab with 1 free object
on the list, thus only increase page->pobjects by 1, even if there are
subsequent frees on the same slab. Jann has noticed this in practice
and so did we [2] when investigating significant increase of kmemcg
usage after switching from SLAB to SLUB.
While this is no longer a problem in kmemcg context thanks to the
accounting rewrite in 5.9, the memory waste is still not ideal and it's
questionable whether it makes sense to perform free object count based
control when object counts can easily become so much inaccurate. So
this patch converts the accounting to be based on number of pages only
(which is precise) and removes the page->pobjects field completely.
This is also ultimately simpler.
To retain the existing set_cpu_partial() heuristic, first calculate the
target number of objects as previously, but then convert it to target
number of pages by assuming the pages will be half-filled on average.
This assumption might obviously also be inaccurate in practice, but
cannot degrade to actual number of pages being equal to the target
number of objects.
We could also skip the intermediate step with target number of objects
and rewrite the heuristic in terms of pages. However we still have the
sysfs file cpu_partial which uses number of objects and could break
existing users if it suddenly becomes number of pages, so this patch
doesn't do that.
In practice, after this patch the heuristics limit the size of percpu
partial list up to 2 pages. In case of a reported regression (which
would mean some workload has benefited from the previous imprecise
object based counting), we can tune the heuristics to get a better
compromise within the new scheme, while still avoid the unexpectedly
long percpu partial lists.
[1] https://lore.kernel.org/linux-mm/CAG48ez2Qx5K1Cab-m8BdSibp6wLTip6ro4=-umR7BLsEgjEYzA@mail.gmail.com/
[2] https://lore.kernel.org/all/2f0f46e8-2535-410a-1859-e9cfa4e57c18@suse.cz/
==========
Evaluation
==========
Mel was kind enough to run v1 through mmtests machinery for netperf
(localhost) and hackbench and, for most significant results see below.
So there are some apparent regressions, especially with hackbench, which
I think ultimately boils down to having shorter percpu partial lists on
average and some benchmarks benefiting from longer ones. Monitoring
slab usage also indicated less memory usage by slab. Based on that, the
following patch will bump the defaults to allow longer percpu partial
lists than after this patch.
However the goal is certainly not such that we would limit the percpu
partial lists to 30 pages just because previously a specific alloc/free
pattern could lead to the limit of 30 objects translate to a limit to 30
pages - that would make little sense. This is a correctness patch, and
if a workload benefits from larger lists, the sysfs tuning knobs are
still there to allow that.
Netperf
2-socket Intel(R) Xeon(R) Gold 5218R CPU @ 2.10GHz (20 cores, 40 threads per socket), 384GB RAM
TCP-RR:
hmean before 127045.79 after 121092.94 (-4.69%, worse)
stddev before 2634.37 after 1254.08
UDP-RR:
hmean before 166985.45 after 160668.94 ( -3.78%, worse)
stddev before 4059.69 after 1943.63
2-socket Intel(R) Xeon(R) CPU E5-2698 v4 @ 2.20GHz (20 cores, 40 threads per socket), 512GB RAM
TCP-RR:
hmean before 84173.25 after 76914.72 ( -8.62%, worse)
UDP-RR:
hmean before 93571.12 after 96428.69 ( 3.05%, better)
stddev before 23118.54 after 16828.14
2-socket Intel(R) Xeon(R) CPU E5-2670 v3 @ 2.30GHz (12 cores, 24 threads per socket), 64GB RAM
TCP-RR:
hmean before 49984.92 after 48922.27 ( -2.13%, worse)
stddev before 6248.15 after 4740.51
UDP-RR:
hmean before 61854.31 after 68761.81 ( 11.17%, better)
stddev before 4093.54 after 5898.91
other machines - within 2%
Hackbench
(results before and after the patch, negative % means worse)
2-socket AMD EPYC 7713 (64 cores, 128 threads per core), 256GB RAM
hackbench-process-sockets
Amean 1 0.5380 0.5583 ( -3.78%)
Amean 4 0.7510 0.8150 ( -8.52%)
Amean 7 0.7930 0.9533 ( -20.22%)
Amean 12 0.7853 1.1313 ( -44.06%)
Amean 21 1.1520 1.4993 ( -30.15%)
Amean 30 1.6223 1.9237 ( -18.57%)
Amean 48 2.6767 2.9903 ( -11.72%)
Amean 79 4.0257 5.1150 ( -27.06%)
Amean 110 5.5193 7.4720 ( -35.38%)
Amean 141 7.2207 9.9840 ( -38.27%)
Amean 172 8.4770 12.1963 ( -43.88%)
Amean 203 9.6473 14.3137 ( -48.37%)
Amean 234 11.3960 18.7917 ( -64.90%)
Amean 265 13.9627 22.4607 ( -60.86%)
Amean 296 14.9163 26.0483 ( -74.63%)
hackbench-thread-sockets
Amean 1 0.5597 0.5877 ( -5.00%)
Amean 4 0.7913 0.8960 ( -13.23%)
Amean 7 0.8190 1.0017 ( -22.30%)
Amean 12 0.9560 1.1727 ( -22.66%)
Amean 21 1.7587 1.5660 ( 10.96%)
Amean 30 2.4477 1.9807 ( 19.08%)
Amean 48 3.4573 3.0630 ( 11.41%)
Amean 79 4.7903 5.1733 ( -8.00%)
Amean 110 6.1370 7.4220 ( -20.94%)
Amean 141 7.5777 9.2617 ( -22.22%)
Amean 172 9.2280 11.0907 ( -20.18%)
Amean 203 10.2793 13.3470 ( -29.84%)
Amean 234 11.2410 17.1070 ( -52.18%)
Amean 265 12.5970 23.3323 ( -85.22%)
Amean 296 17.1540 24.2857 ( -41.57%)
2-socket Intel(R) Xeon(R) Gold 5218R CPU @ 2.10GHz (20 cores, 40 threads
per socket), 384GB RAM
hackbench-process-sockets
Amean 1 0.5760 0.4793 ( 16.78%)
Amean 4 0.9430 0.9707 ( -2.93%)
Amean 7 1.5517 1.8843 ( -21.44%)
Amean 12 2.4903 2.7267 ( -9.49%)
Amean 21 3.9560 4.2877 ( -8.38%)
Amean 30 5.4613 5.8343 ( -6.83%)
Amean 48 8.5337 9.2937 ( -8.91%)
Amean 79 14.0670 15.2630 ( -8.50%)
Amean 110 19.2253 21.2467 ( -10.51%)
Amean 141 23.7557 25.8550 ( -8.84%)
Amean 172 28.4407 29.7603 ( -4.64%)
Amean 203 33.3407 33.9927 ( -1.96%)
Amean 234 38.3633 39.1150 ( -1.96%)
Amean 265 43.4420 43.8470 ( -0.93%)
Amean 296 48.3680 48.9300 ( -1.16%)
hackbench-thread-sockets
Amean 1 0.6080 0.6493 ( -6.80%)
Amean 4 1.0000 1.0513 ( -5.13%)
Amean 7 1.6607 2.0260 ( -22.00%)
Amean 12 2.7637 2.9273 ( -5.92%)
Amean 21 5.0613 4.5153 ( 10.79%)
Amean 30 6.3340 6.1140 ( 3.47%)
Amean 48 9.0567 9.5577 ( -5.53%)
Amean 79 14.5657 15.7983 ( -8.46%)
Amean 110 19.6213 21.6333 ( -10.25%)
Amean 141 24.1563 26.2697 ( -8.75%)
Amean 172 28.9687 30.2187 ( -4.32%)
Amean 203 33.9763 34.6970 ( -2.12%)
Amean 234 38.8647 39.3207 ( -1.17%)
Amean 265 44.0813 44.1507 ( -0.16%)
Amean 296 49.2040 49.4330 ( -0.47%)
2-socket Intel(R) Xeon(R) CPU E5-2698 v4 @ 2.20GHz (20 cores, 40 threads
per socket), 512GB RAM
hackbench-process-sockets
Amean 1 0.5027 0.5017 ( 0.20%)
Amean 4 1.1053 1.2033 ( -8.87%)
Amean 7 1.8760 2.1820 ( -16.31%)
Amean 12 2.9053 3.1810 ( -9.49%)
Amean 21 4.6777 4.9920 ( -6.72%)
Amean 30 6.5180 6.7827 ( -4.06%)
Amean 48 10.0710 10.5227 ( -4.48%)
Amean 79 16.4250 17.5053 ( -6.58%)
Amean 110 22.6203 24.4617 ( -8.14%)
Amean 141 28.0967 31.0363 ( -10.46%)
Amean 172 34.4030 36.9233 ( -7.33%)
Amean 203 40.5933 43.0850 ( -6.14%)
Amean 234 46.6477 48.7220 ( -4.45%)
Amean 265 53.0530 53.9597 ( -1.71%)
Amean 296 59.2760 59.9213 ( -1.09%)
hackbench-thread-sockets
Amean 1 0.5363 0.5330 ( 0.62%)
Amean 4 1.1647 1.2157 ( -4.38%)
Amean 7 1.9237 2.2833 ( -18.70%)
Amean 12 2.9943 3.3110 ( -10.58%)
Amean 21 4.9987 5.1880 ( -3.79%)
Amean 30 6.7583 7.0043 ( -3.64%)
Amean 48 10.4547 10.8353 ( -3.64%)
Amean 79 16.6707 17.6790 ( -6.05%)
Amean 110 22.8207 24.4403 ( -7.10%)
Amean 141 28.7090 31.0533 ( -8.17%)
Amean 172 34.9387 36.8260 ( -5.40%)
Amean 203 41.1567 43.0450 ( -4.59%)
Amean 234 47.3790 48.5307 ( -2.43%)
Amean 265 53.9543 54.6987 ( -1.38%)
Amean 296 60.0820 60.2163 ( -0.22%)
1-socket Intel(R) Xeon(R) CPU E3-1240 v5 @ 3.50GHz (4 cores, 8 threads),
32 GB RAM
hackbench-process-sockets
Amean 1 1.4760 1.5773 ( -6.87%)
Amean 3 3.9370 4.0910 ( -3.91%)
Amean 5 6.6797 6.9357 ( -3.83%)
Amean 7 9.3367 9.7150 ( -4.05%)
Amean 12 15.7627 16.1400 ( -2.39%)
Amean 18 23.5360 23.6890 ( -0.65%)
Amean 24 31.0663 31.3137 ( -0.80%)
Amean 30 38.7283 39.0037 ( -0.71%)
Amean 32 41.3417 41.6097 ( -0.65%)
hackbench-thread-sockets
Amean 1 1.5250 1.6043 ( -5.20%)
Amean 3 4.0897 4.2603 ( -4.17%)
Amean 5 6.7760 7.0933 ( -4.68%)
Amean 7 9.4817 9.9157 ( -4.58%)
Amean 12 15.9610 16.3937 ( -2.71%)
Amean 18 23.9543 24.3417 ( -1.62%)
Amean 24 31.4400 31.7217 ( -0.90%)
Amean 30 39.2457 39.5467 ( -0.77%)
Amean 32 41.8267 42.1230 ( -0.71%)
2-socket Intel(R) Xeon(R) CPU E5-2670 v3 @ 2.30GHz (12 cores, 24 threads
per socket), 64GB RAM
hackbench-process-sockets
Amean 1 1.0347 1.0880 ( -5.15%)
Amean 4 1.7267 1.8527 ( -7.30%)
Amean 7 2.6707 2.8110 ( -5.25%)
Amean 12 4.1617 4.3383 ( -4.25%)
Amean 21 7.0070 7.2600 ( -3.61%)
Amean 30 9.9187 10.2397 ( -3.24%)
Amean 48 15.6710 16.3923 ( -4.60%)
Amean 79 24.7743 26.1247 ( -5.45%)
Amean 110 34.3000 35.9307 ( -4.75%)
Amean 141 44.2043 44.8010 ( -1.35%)
Amean 172 54.2430 54.7260 ( -0.89%)
Amean 192 60.6557 60.9777 ( -0.53%)
hackbench-thread-sockets
Amean 1 1.0610 1.1353 ( -7.01%)
Amean 4 1.7543 1.9140 ( -9.10%)
Amean 7 2.7840 2.9573 ( -6.23%)
Amean 12 4.3813 4.4937 ( -2.56%)
Amean 21 7.3460 7.5350 ( -2.57%)
Amean 30 10.2313 10.5190 ( -2.81%)
Amean 48 15.9700 16.5940 ( -3.91%)
Amean 79 25.3973 26.6637 ( -4.99%)
Amean 110 35.1087 36.4797 ( -3.91%)
Amean 141 45.8220 46.3053 ( -1.05%)
Amean 172 55.4917 55.7320 ( -0.43%)
Amean 192 62.7490 62.5410 ( 0.33%)
Link: https://lkml.kernel.org/r/20211012134651.11258-1-vbabka@suse.cz
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reported-by: Jann Horn <jannh@google.com>
Cc: Roman Gushchin <guro@fb.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-11-05 13:35:17 -07:00
|
|
|
|
|
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
|
|
|
|
|
mm, slub: change percpu partial accounting from objects to pages
With CONFIG_SLUB_CPU_PARTIAL enabled, SLUB keeps a percpu list of
partial slabs that can be promoted to cpu slab when the previous one is
depleted, without accessing the shared partial list. A slab can be
added to this list by 1) refill of an empty list from get_partial_node()
- once we really have to access the shared partial list, we acquire
multiple slabs to amortize the cost of locking, and 2) first free to a
previously full slab - instead of putting the slab on a shared partial
list, we can more cheaply freeze it and put it on the per-cpu list.
To control how large a percpu partial list can grow for a kmem cache,
set_cpu_partial() calculates a target number of free objects on each
cpu's percpu partial list, and this can be also set by the sysfs file
cpu_partial.
However, the tracking of actual number of objects is imprecise, in order
to limit overhead from cpu X freeing an objects to a slab on percpu
partial list of cpu Y. Basically, the percpu partial slabs form a
single linked list, and when we add a new slab to the list with current
head "oldpage", we set in the struct page of the slab we're adding:
page->pages = oldpage->pages + 1; // this is precise
page->pobjects = oldpage->pobjects + (page->objects - page->inuse);
page->next = oldpage;
Thus the real number of free objects in the slab (objects - inuse) is
only determined at the moment of adding the slab to the percpu partial
list, and further freeing doesn't update the pobjects counter nor
propagate it to the current list head. As Jann reports [1], this can
easily lead to large inaccuracies, where the target number of objects
(up to 30 by default) can translate to the same number of (empty) slab
pages on the list. In case 2) above, we put a slab with 1 free object
on the list, thus only increase page->pobjects by 1, even if there are
subsequent frees on the same slab. Jann has noticed this in practice
and so did we [2] when investigating significant increase of kmemcg
usage after switching from SLAB to SLUB.
While this is no longer a problem in kmemcg context thanks to the
accounting rewrite in 5.9, the memory waste is still not ideal and it's
questionable whether it makes sense to perform free object count based
control when object counts can easily become so much inaccurate. So
this patch converts the accounting to be based on number of pages only
(which is precise) and removes the page->pobjects field completely.
This is also ultimately simpler.
To retain the existing set_cpu_partial() heuristic, first calculate the
target number of objects as previously, but then convert it to target
number of pages by assuming the pages will be half-filled on average.
This assumption might obviously also be inaccurate in practice, but
cannot degrade to actual number of pages being equal to the target
number of objects.
We could also skip the intermediate step with target number of objects
and rewrite the heuristic in terms of pages. However we still have the
sysfs file cpu_partial which uses number of objects and could break
existing users if it suddenly becomes number of pages, so this patch
doesn't do that.
In practice, after this patch the heuristics limit the size of percpu
partial list up to 2 pages. In case of a reported regression (which
would mean some workload has benefited from the previous imprecise
object based counting), we can tune the heuristics to get a better
compromise within the new scheme, while still avoid the unexpectedly
long percpu partial lists.
[1] https://lore.kernel.org/linux-mm/CAG48ez2Qx5K1Cab-m8BdSibp6wLTip6ro4=-umR7BLsEgjEYzA@mail.gmail.com/
[2] https://lore.kernel.org/all/2f0f46e8-2535-410a-1859-e9cfa4e57c18@suse.cz/
==========
Evaluation
==========
Mel was kind enough to run v1 through mmtests machinery for netperf
(localhost) and hackbench and, for most significant results see below.
So there are some apparent regressions, especially with hackbench, which
I think ultimately boils down to having shorter percpu partial lists on
average and some benchmarks benefiting from longer ones. Monitoring
slab usage also indicated less memory usage by slab. Based on that, the
following patch will bump the defaults to allow longer percpu partial
lists than after this patch.
However the goal is certainly not such that we would limit the percpu
partial lists to 30 pages just because previously a specific alloc/free
pattern could lead to the limit of 30 objects translate to a limit to 30
pages - that would make little sense. This is a correctness patch, and
if a workload benefits from larger lists, the sysfs tuning knobs are
still there to allow that.
Netperf
2-socket Intel(R) Xeon(R) Gold 5218R CPU @ 2.10GHz (20 cores, 40 threads per socket), 384GB RAM
TCP-RR:
hmean before 127045.79 after 121092.94 (-4.69%, worse)
stddev before 2634.37 after 1254.08
UDP-RR:
hmean before 166985.45 after 160668.94 ( -3.78%, worse)
stddev before 4059.69 after 1943.63
2-socket Intel(R) Xeon(R) CPU E5-2698 v4 @ 2.20GHz (20 cores, 40 threads per socket), 512GB RAM
TCP-RR:
hmean before 84173.25 after 76914.72 ( -8.62%, worse)
UDP-RR:
hmean before 93571.12 after 96428.69 ( 3.05%, better)
stddev before 23118.54 after 16828.14
2-socket Intel(R) Xeon(R) CPU E5-2670 v3 @ 2.30GHz (12 cores, 24 threads per socket), 64GB RAM
TCP-RR:
hmean before 49984.92 after 48922.27 ( -2.13%, worse)
stddev before 6248.15 after 4740.51
UDP-RR:
hmean before 61854.31 after 68761.81 ( 11.17%, better)
stddev before 4093.54 after 5898.91
other machines - within 2%
Hackbench
(results before and after the patch, negative % means worse)
2-socket AMD EPYC 7713 (64 cores, 128 threads per core), 256GB RAM
hackbench-process-sockets
Amean 1 0.5380 0.5583 ( -3.78%)
Amean 4 0.7510 0.8150 ( -8.52%)
Amean 7 0.7930 0.9533 ( -20.22%)
Amean 12 0.7853 1.1313 ( -44.06%)
Amean 21 1.1520 1.4993 ( -30.15%)
Amean 30 1.6223 1.9237 ( -18.57%)
Amean 48 2.6767 2.9903 ( -11.72%)
Amean 79 4.0257 5.1150 ( -27.06%)
Amean 110 5.5193 7.4720 ( -35.38%)
Amean 141 7.2207 9.9840 ( -38.27%)
Amean 172 8.4770 12.1963 ( -43.88%)
Amean 203 9.6473 14.3137 ( -48.37%)
Amean 234 11.3960 18.7917 ( -64.90%)
Amean 265 13.9627 22.4607 ( -60.86%)
Amean 296 14.9163 26.0483 ( -74.63%)
hackbench-thread-sockets
Amean 1 0.5597 0.5877 ( -5.00%)
Amean 4 0.7913 0.8960 ( -13.23%)
Amean 7 0.8190 1.0017 ( -22.30%)
Amean 12 0.9560 1.1727 ( -22.66%)
Amean 21 1.7587 1.5660 ( 10.96%)
Amean 30 2.4477 1.9807 ( 19.08%)
Amean 48 3.4573 3.0630 ( 11.41%)
Amean 79 4.7903 5.1733 ( -8.00%)
Amean 110 6.1370 7.4220 ( -20.94%)
Amean 141 7.5777 9.2617 ( -22.22%)
Amean 172 9.2280 11.0907 ( -20.18%)
Amean 203 10.2793 13.3470 ( -29.84%)
Amean 234 11.2410 17.1070 ( -52.18%)
Amean 265 12.5970 23.3323 ( -85.22%)
Amean 296 17.1540 24.2857 ( -41.57%)
2-socket Intel(R) Xeon(R) Gold 5218R CPU @ 2.10GHz (20 cores, 40 threads
per socket), 384GB RAM
hackbench-process-sockets
Amean 1 0.5760 0.4793 ( 16.78%)
Amean 4 0.9430 0.9707 ( -2.93%)
Amean 7 1.5517 1.8843 ( -21.44%)
Amean 12 2.4903 2.7267 ( -9.49%)
Amean 21 3.9560 4.2877 ( -8.38%)
Amean 30 5.4613 5.8343 ( -6.83%)
Amean 48 8.5337 9.2937 ( -8.91%)
Amean 79 14.0670 15.2630 ( -8.50%)
Amean 110 19.2253 21.2467 ( -10.51%)
Amean 141 23.7557 25.8550 ( -8.84%)
Amean 172 28.4407 29.7603 ( -4.64%)
Amean 203 33.3407 33.9927 ( -1.96%)
Amean 234 38.3633 39.1150 ( -1.96%)
Amean 265 43.4420 43.8470 ( -0.93%)
Amean 296 48.3680 48.9300 ( -1.16%)
hackbench-thread-sockets
Amean 1 0.6080 0.6493 ( -6.80%)
Amean 4 1.0000 1.0513 ( -5.13%)
Amean 7 1.6607 2.0260 ( -22.00%)
Amean 12 2.7637 2.9273 ( -5.92%)
Amean 21 5.0613 4.5153 ( 10.79%)
Amean 30 6.3340 6.1140 ( 3.47%)
Amean 48 9.0567 9.5577 ( -5.53%)
Amean 79 14.5657 15.7983 ( -8.46%)
Amean 110 19.6213 21.6333 ( -10.25%)
Amean 141 24.1563 26.2697 ( -8.75%)
Amean 172 28.9687 30.2187 ( -4.32%)
Amean 203 33.9763 34.6970 ( -2.12%)
Amean 234 38.8647 39.3207 ( -1.17%)
Amean 265 44.0813 44.1507 ( -0.16%)
Amean 296 49.2040 49.4330 ( -0.47%)
2-socket Intel(R) Xeon(R) CPU E5-2698 v4 @ 2.20GHz (20 cores, 40 threads
per socket), 512GB RAM
hackbench-process-sockets
Amean 1 0.5027 0.5017 ( 0.20%)
Amean 4 1.1053 1.2033 ( -8.87%)
Amean 7 1.8760 2.1820 ( -16.31%)
Amean 12 2.9053 3.1810 ( -9.49%)
Amean 21 4.6777 4.9920 ( -6.72%)
Amean 30 6.5180 6.7827 ( -4.06%)
Amean 48 10.0710 10.5227 ( -4.48%)
Amean 79 16.4250 17.5053 ( -6.58%)
Amean 110 22.6203 24.4617 ( -8.14%)
Amean 141 28.0967 31.0363 ( -10.46%)
Amean 172 34.4030 36.9233 ( -7.33%)
Amean 203 40.5933 43.0850 ( -6.14%)
Amean 234 46.6477 48.7220 ( -4.45%)
Amean 265 53.0530 53.9597 ( -1.71%)
Amean 296 59.2760 59.9213 ( -1.09%)
hackbench-thread-sockets
Amean 1 0.5363 0.5330 ( 0.62%)
Amean 4 1.1647 1.2157 ( -4.38%)
Amean 7 1.9237 2.2833 ( -18.70%)
Amean 12 2.9943 3.3110 ( -10.58%)
Amean 21 4.9987 5.1880 ( -3.79%)
Amean 30 6.7583 7.0043 ( -3.64%)
Amean 48 10.4547 10.8353 ( -3.64%)
Amean 79 16.6707 17.6790 ( -6.05%)
Amean 110 22.8207 24.4403 ( -7.10%)
Amean 141 28.7090 31.0533 ( -8.17%)
Amean 172 34.9387 36.8260 ( -5.40%)
Amean 203 41.1567 43.0450 ( -4.59%)
Amean 234 47.3790 48.5307 ( -2.43%)
Amean 265 53.9543 54.6987 ( -1.38%)
Amean 296 60.0820 60.2163 ( -0.22%)
1-socket Intel(R) Xeon(R) CPU E3-1240 v5 @ 3.50GHz (4 cores, 8 threads),
32 GB RAM
hackbench-process-sockets
Amean 1 1.4760 1.5773 ( -6.87%)
Amean 3 3.9370 4.0910 ( -3.91%)
Amean 5 6.6797 6.9357 ( -3.83%)
Amean 7 9.3367 9.7150 ( -4.05%)
Amean 12 15.7627 16.1400 ( -2.39%)
Amean 18 23.5360 23.6890 ( -0.65%)
Amean 24 31.0663 31.3137 ( -0.80%)
Amean 30 38.7283 39.0037 ( -0.71%)
Amean 32 41.3417 41.6097 ( -0.65%)
hackbench-thread-sockets
Amean 1 1.5250 1.6043 ( -5.20%)
Amean 3 4.0897 4.2603 ( -4.17%)
Amean 5 6.7760 7.0933 ( -4.68%)
Amean 7 9.4817 9.9157 ( -4.58%)
Amean 12 15.9610 16.3937 ( -2.71%)
Amean 18 23.9543 24.3417 ( -1.62%)
Amean 24 31.4400 31.7217 ( -0.90%)
Amean 30 39.2457 39.5467 ( -0.77%)
Amean 32 41.8267 42.1230 ( -0.71%)
2-socket Intel(R) Xeon(R) CPU E5-2670 v3 @ 2.30GHz (12 cores, 24 threads
per socket), 64GB RAM
hackbench-process-sockets
Amean 1 1.0347 1.0880 ( -5.15%)
Amean 4 1.7267 1.8527 ( -7.30%)
Amean 7 2.6707 2.8110 ( -5.25%)
Amean 12 4.1617 4.3383 ( -4.25%)
Amean 21 7.0070 7.2600 ( -3.61%)
Amean 30 9.9187 10.2397 ( -3.24%)
Amean 48 15.6710 16.3923 ( -4.60%)
Amean 79 24.7743 26.1247 ( -5.45%)
Amean 110 34.3000 35.9307 ( -4.75%)
Amean 141 44.2043 44.8010 ( -1.35%)
Amean 172 54.2430 54.7260 ( -0.89%)
Amean 192 60.6557 60.9777 ( -0.53%)
hackbench-thread-sockets
Amean 1 1.0610 1.1353 ( -7.01%)
Amean 4 1.7543 1.9140 ( -9.10%)
Amean 7 2.7840 2.9573 ( -6.23%)
Amean 12 4.3813 4.4937 ( -2.56%)
Amean 21 7.3460 7.5350 ( -2.57%)
Amean 30 10.2313 10.5190 ( -2.81%)
Amean 48 15.9700 16.5940 ( -3.91%)
Amean 79 25.3973 26.6637 ( -4.99%)
Amean 110 35.1087 36.4797 ( -3.91%)
Amean 141 45.8220 46.3053 ( -1.05%)
Amean 172 55.4917 55.7320 ( -0.43%)
Amean 192 62.7490 62.5410 ( 0.33%)
Link: https://lkml.kernel.org/r/20211012134651.11258-1-vbabka@suse.cz
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reported-by: Jann Horn <jannh@google.com>
Cc: Roman Gushchin <guro@fb.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-11-05 13:35:17 -07:00
|
|
|
|
2024-04-04 13:58:25 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
mm, slub: change percpu partial accounting from objects to pages
With CONFIG_SLUB_CPU_PARTIAL enabled, SLUB keeps a percpu list of
partial slabs that can be promoted to cpu slab when the previous one is
depleted, without accessing the shared partial list. A slab can be
added to this list by 1) refill of an empty list from get_partial_node()
- once we really have to access the shared partial list, we acquire
multiple slabs to amortize the cost of locking, and 2) first free to a
previously full slab - instead of putting the slab on a shared partial
list, we can more cheaply freeze it and put it on the per-cpu list.
To control how large a percpu partial list can grow for a kmem cache,
set_cpu_partial() calculates a target number of free objects on each
cpu's percpu partial list, and this can be also set by the sysfs file
cpu_partial.
However, the tracking of actual number of objects is imprecise, in order
to limit overhead from cpu X freeing an objects to a slab on percpu
partial list of cpu Y. Basically, the percpu partial slabs form a
single linked list, and when we add a new slab to the list with current
head "oldpage", we set in the struct page of the slab we're adding:
page->pages = oldpage->pages + 1; // this is precise
page->pobjects = oldpage->pobjects + (page->objects - page->inuse);
page->next = oldpage;
Thus the real number of free objects in the slab (objects - inuse) is
only determined at the moment of adding the slab to the percpu partial
list, and further freeing doesn't update the pobjects counter nor
propagate it to the current list head. As Jann reports [1], this can
easily lead to large inaccuracies, where the target number of objects
(up to 30 by default) can translate to the same number of (empty) slab
pages on the list. In case 2) above, we put a slab with 1 free object
on the list, thus only increase page->pobjects by 1, even if there are
subsequent frees on the same slab. Jann has noticed this in practice
and so did we [2] when investigating significant increase of kmemcg
usage after switching from SLAB to SLUB.
While this is no longer a problem in kmemcg context thanks to the
accounting rewrite in 5.9, the memory waste is still not ideal and it's
questionable whether it makes sense to perform free object count based
control when object counts can easily become so much inaccurate. So
this patch converts the accounting to be based on number of pages only
(which is precise) and removes the page->pobjects field completely.
This is also ultimately simpler.
To retain the existing set_cpu_partial() heuristic, first calculate the
target number of objects as previously, but then convert it to target
number of pages by assuming the pages will be half-filled on average.
This assumption might obviously also be inaccurate in practice, but
cannot degrade to actual number of pages being equal to the target
number of objects.
We could also skip the intermediate step with target number of objects
and rewrite the heuristic in terms of pages. However we still have the
sysfs file cpu_partial which uses number of objects and could break
existing users if it suddenly becomes number of pages, so this patch
doesn't do that.
In practice, after this patch the heuristics limit the size of percpu
partial list up to 2 pages. In case of a reported regression (which
would mean some workload has benefited from the previous imprecise
object based counting), we can tune the heuristics to get a better
compromise within the new scheme, while still avoid the unexpectedly
long percpu partial lists.
[1] https://lore.kernel.org/linux-mm/CAG48ez2Qx5K1Cab-m8BdSibp6wLTip6ro4=-umR7BLsEgjEYzA@mail.gmail.com/
[2] https://lore.kernel.org/all/2f0f46e8-2535-410a-1859-e9cfa4e57c18@suse.cz/
==========
Evaluation
==========
Mel was kind enough to run v1 through mmtests machinery for netperf
(localhost) and hackbench and, for most significant results see below.
So there are some apparent regressions, especially with hackbench, which
I think ultimately boils down to having shorter percpu partial lists on
average and some benchmarks benefiting from longer ones. Monitoring
slab usage also indicated less memory usage by slab. Based on that, the
following patch will bump the defaults to allow longer percpu partial
lists than after this patch.
However the goal is certainly not such that we would limit the percpu
partial lists to 30 pages just because previously a specific alloc/free
pattern could lead to the limit of 30 objects translate to a limit to 30
pages - that would make little sense. This is a correctness patch, and
if a workload benefits from larger lists, the sysfs tuning knobs are
still there to allow that.
Netperf
2-socket Intel(R) Xeon(R) Gold 5218R CPU @ 2.10GHz (20 cores, 40 threads per socket), 384GB RAM
TCP-RR:
hmean before 127045.79 after 121092.94 (-4.69%, worse)
stddev before 2634.37 after 1254.08
UDP-RR:
hmean before 166985.45 after 160668.94 ( -3.78%, worse)
stddev before 4059.69 after 1943.63
2-socket Intel(R) Xeon(R) CPU E5-2698 v4 @ 2.20GHz (20 cores, 40 threads per socket), 512GB RAM
TCP-RR:
hmean before 84173.25 after 76914.72 ( -8.62%, worse)
UDP-RR:
hmean before 93571.12 after 96428.69 ( 3.05%, better)
stddev before 23118.54 after 16828.14
2-socket Intel(R) Xeon(R) CPU E5-2670 v3 @ 2.30GHz (12 cores, 24 threads per socket), 64GB RAM
TCP-RR:
hmean before 49984.92 after 48922.27 ( -2.13%, worse)
stddev before 6248.15 after 4740.51
UDP-RR:
hmean before 61854.31 after 68761.81 ( 11.17%, better)
stddev before 4093.54 after 5898.91
other machines - within 2%
Hackbench
(results before and after the patch, negative % means worse)
2-socket AMD EPYC 7713 (64 cores, 128 threads per core), 256GB RAM
hackbench-process-sockets
Amean 1 0.5380 0.5583 ( -3.78%)
Amean 4 0.7510 0.8150 ( -8.52%)
Amean 7 0.7930 0.9533 ( -20.22%)
Amean 12 0.7853 1.1313 ( -44.06%)
Amean 21 1.1520 1.4993 ( -30.15%)
Amean 30 1.6223 1.9237 ( -18.57%)
Amean 48 2.6767 2.9903 ( -11.72%)
Amean 79 4.0257 5.1150 ( -27.06%)
Amean 110 5.5193 7.4720 ( -35.38%)
Amean 141 7.2207 9.9840 ( -38.27%)
Amean 172 8.4770 12.1963 ( -43.88%)
Amean 203 9.6473 14.3137 ( -48.37%)
Amean 234 11.3960 18.7917 ( -64.90%)
Amean 265 13.9627 22.4607 ( -60.86%)
Amean 296 14.9163 26.0483 ( -74.63%)
hackbench-thread-sockets
Amean 1 0.5597 0.5877 ( -5.00%)
Amean 4 0.7913 0.8960 ( -13.23%)
Amean 7 0.8190 1.0017 ( -22.30%)
Amean 12 0.9560 1.1727 ( -22.66%)
Amean 21 1.7587 1.5660 ( 10.96%)
Amean 30 2.4477 1.9807 ( 19.08%)
Amean 48 3.4573 3.0630 ( 11.41%)
Amean 79 4.7903 5.1733 ( -8.00%)
Amean 110 6.1370 7.4220 ( -20.94%)
Amean 141 7.5777 9.2617 ( -22.22%)
Amean 172 9.2280 11.0907 ( -20.18%)
Amean 203 10.2793 13.3470 ( -29.84%)
Amean 234 11.2410 17.1070 ( -52.18%)
Amean 265 12.5970 23.3323 ( -85.22%)
Amean 296 17.1540 24.2857 ( -41.57%)
2-socket Intel(R) Xeon(R) Gold 5218R CPU @ 2.10GHz (20 cores, 40 threads
per socket), 384GB RAM
hackbench-process-sockets
Amean 1 0.5760 0.4793 ( 16.78%)
Amean 4 0.9430 0.9707 ( -2.93%)
Amean 7 1.5517 1.8843 ( -21.44%)
Amean 12 2.4903 2.7267 ( -9.49%)
Amean 21 3.9560 4.2877 ( -8.38%)
Amean 30 5.4613 5.8343 ( -6.83%)
Amean 48 8.5337 9.2937 ( -8.91%)
Amean 79 14.0670 15.2630 ( -8.50%)
Amean 110 19.2253 21.2467 ( -10.51%)
Amean 141 23.7557 25.8550 ( -8.84%)
Amean 172 28.4407 29.7603 ( -4.64%)
Amean 203 33.3407 33.9927 ( -1.96%)
Amean 234 38.3633 39.1150 ( -1.96%)
Amean 265 43.4420 43.8470 ( -0.93%)
Amean 296 48.3680 48.9300 ( -1.16%)
hackbench-thread-sockets
Amean 1 0.6080 0.6493 ( -6.80%)
Amean 4 1.0000 1.0513 ( -5.13%)
Amean 7 1.6607 2.0260 ( -22.00%)
Amean 12 2.7637 2.9273 ( -5.92%)
Amean 21 5.0613 4.5153 ( 10.79%)
Amean 30 6.3340 6.1140 ( 3.47%)
Amean 48 9.0567 9.5577 ( -5.53%)
Amean 79 14.5657 15.7983 ( -8.46%)
Amean 110 19.6213 21.6333 ( -10.25%)
Amean 141 24.1563 26.2697 ( -8.75%)
Amean 172 28.9687 30.2187 ( -4.32%)
Amean 203 33.9763 34.6970 ( -2.12%)
Amean 234 38.8647 39.3207 ( -1.17%)
Amean 265 44.0813 44.1507 ( -0.16%)
Amean 296 49.2040 49.4330 ( -0.47%)
2-socket Intel(R) Xeon(R) CPU E5-2698 v4 @ 2.20GHz (20 cores, 40 threads
per socket), 512GB RAM
hackbench-process-sockets
Amean 1 0.5027 0.5017 ( 0.20%)
Amean 4 1.1053 1.2033 ( -8.87%)
Amean 7 1.8760 2.1820 ( -16.31%)
Amean 12 2.9053 3.1810 ( -9.49%)
Amean 21 4.6777 4.9920 ( -6.72%)
Amean 30 6.5180 6.7827 ( -4.06%)
Amean 48 10.0710 10.5227 ( -4.48%)
Amean 79 16.4250 17.5053 ( -6.58%)
Amean 110 22.6203 24.4617 ( -8.14%)
Amean 141 28.0967 31.0363 ( -10.46%)
Amean 172 34.4030 36.9233 ( -7.33%)
Amean 203 40.5933 43.0850 ( -6.14%)
Amean 234 46.6477 48.7220 ( -4.45%)
Amean 265 53.0530 53.9597 ( -1.71%)
Amean 296 59.2760 59.9213 ( -1.09%)
hackbench-thread-sockets
Amean 1 0.5363 0.5330 ( 0.62%)
Amean 4 1.1647 1.2157 ( -4.38%)
Amean 7 1.9237 2.2833 ( -18.70%)
Amean 12 2.9943 3.3110 ( -10.58%)
Amean 21 4.9987 5.1880 ( -3.79%)
Amean 30 6.7583 7.0043 ( -3.64%)
Amean 48 10.4547 10.8353 ( -3.64%)
Amean 79 16.6707 17.6790 ( -6.05%)
Amean 110 22.8207 24.4403 ( -7.10%)
Amean 141 28.7090 31.0533 ( -8.17%)
Amean 172 34.9387 36.8260 ( -5.40%)
Amean 203 41.1567 43.0450 ( -4.59%)
Amean 234 47.3790 48.5307 ( -2.43%)
Amean 265 53.9543 54.6987 ( -1.38%)
Amean 296 60.0820 60.2163 ( -0.22%)
1-socket Intel(R) Xeon(R) CPU E3-1240 v5 @ 3.50GHz (4 cores, 8 threads),
32 GB RAM
hackbench-process-sockets
Amean 1 1.4760 1.5773 ( -6.87%)
Amean 3 3.9370 4.0910 ( -3.91%)
Amean 5 6.6797 6.9357 ( -3.83%)
Amean 7 9.3367 9.7150 ( -4.05%)
Amean 12 15.7627 16.1400 ( -2.39%)
Amean 18 23.5360 23.6890 ( -0.65%)
Amean 24 31.0663 31.3137 ( -0.80%)
Amean 30 38.7283 39.0037 ( -0.71%)
Amean 32 41.3417 41.6097 ( -0.65%)
hackbench-thread-sockets
Amean 1 1.5250 1.6043 ( -5.20%)
Amean 3 4.0897 4.2603 ( -4.17%)
Amean 5 6.7760 7.0933 ( -4.68%)
Amean 7 9.4817 9.9157 ( -4.58%)
Amean 12 15.9610 16.3937 ( -2.71%)
Amean 18 23.9543 24.3417 ( -1.62%)
Amean 24 31.4400 31.7217 ( -0.90%)
Amean 30 39.2457 39.5467 ( -0.77%)
Amean 32 41.8267 42.1230 ( -0.71%)
2-socket Intel(R) Xeon(R) CPU E5-2670 v3 @ 2.30GHz (12 cores, 24 threads
per socket), 64GB RAM
hackbench-process-sockets
Amean 1 1.0347 1.0880 ( -5.15%)
Amean 4 1.7267 1.8527 ( -7.30%)
Amean 7 2.6707 2.8110 ( -5.25%)
Amean 12 4.1617 4.3383 ( -4.25%)
Amean 21 7.0070 7.2600 ( -3.61%)
Amean 30 9.9187 10.2397 ( -3.24%)
Amean 48 15.6710 16.3923 ( -4.60%)
Amean 79 24.7743 26.1247 ( -5.45%)
Amean 110 34.3000 35.9307 ( -4.75%)
Amean 141 44.2043 44.8010 ( -1.35%)
Amean 172 54.2430 54.7260 ( -0.89%)
Amean 192 60.6557 60.9777 ( -0.53%)
hackbench-thread-sockets
Amean 1 1.0610 1.1353 ( -7.01%)
Amean 4 1.7543 1.9140 ( -9.10%)
Amean 7 2.7840 2.9573 ( -6.23%)
Amean 12 4.3813 4.4937 ( -2.56%)
Amean 21 7.3460 7.5350 ( -2.57%)
Amean 30 10.2313 10.5190 ( -2.81%)
Amean 48 15.9700 16.5940 ( -3.91%)
Amean 79 25.3973 26.6637 ( -4.99%)
Amean 110 35.1087 36.4797 ( -3.91%)
Amean 141 45.8220 46.3053 ( -1.05%)
Amean 172 55.4917 55.7320 ( -0.43%)
Amean 192 62.7490 62.5410 ( 0.33%)
Link: https://lkml.kernel.org/r/20211012134651.11258-1-vbabka@suse.cz
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reported-by: Jann Horn <jannh@google.com>
Cc: Roman Gushchin <guro@fb.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-11-05 13:35:17 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-04-04 13:58:25 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
mm, slub: change percpu partial accounting from objects to pages
With CONFIG_SLUB_CPU_PARTIAL enabled, SLUB keeps a percpu list of
partial slabs that can be promoted to cpu slab when the previous one is
depleted, without accessing the shared partial list. A slab can be
added to this list by 1) refill of an empty list from get_partial_node()
- once we really have to access the shared partial list, we acquire
multiple slabs to amortize the cost of locking, and 2) first free to a
previously full slab - instead of putting the slab on a shared partial
list, we can more cheaply freeze it and put it on the per-cpu list.
To control how large a percpu partial list can grow for a kmem cache,
set_cpu_partial() calculates a target number of free objects on each
cpu's percpu partial list, and this can be also set by the sysfs file
cpu_partial.
However, the tracking of actual number of objects is imprecise, in order
to limit overhead from cpu X freeing an objects to a slab on percpu
partial list of cpu Y. Basically, the percpu partial slabs form a
single linked list, and when we add a new slab to the list with current
head "oldpage", we set in the struct page of the slab we're adding:
page->pages = oldpage->pages + 1; // this is precise
page->pobjects = oldpage->pobjects + (page->objects - page->inuse);
page->next = oldpage;
Thus the real number of free objects in the slab (objects - inuse) is
only determined at the moment of adding the slab to the percpu partial
list, and further freeing doesn't update the pobjects counter nor
propagate it to the current list head. As Jann reports [1], this can
easily lead to large inaccuracies, where the target number of objects
(up to 30 by default) can translate to the same number of (empty) slab
pages on the list. In case 2) above, we put a slab with 1 free object
on the list, thus only increase page->pobjects by 1, even if there are
subsequent frees on the same slab. Jann has noticed this in practice
and so did we [2] when investigating significant increase of kmemcg
usage after switching from SLAB to SLUB.
While this is no longer a problem in kmemcg context thanks to the
accounting rewrite in 5.9, the memory waste is still not ideal and it's
questionable whether it makes sense to perform free object count based
control when object counts can easily become so much inaccurate. So
this patch converts the accounting to be based on number of pages only
(which is precise) and removes the page->pobjects field completely.
This is also ultimately simpler.
To retain the existing set_cpu_partial() heuristic, first calculate the
target number of objects as previously, but then convert it to target
number of pages by assuming the pages will be half-filled on average.
This assumption might obviously also be inaccurate in practice, but
cannot degrade to actual number of pages being equal to the target
number of objects.
We could also skip the intermediate step with target number of objects
and rewrite the heuristic in terms of pages. However we still have the
sysfs file cpu_partial which uses number of objects and could break
existing users if it suddenly becomes number of pages, so this patch
doesn't do that.
In practice, after this patch the heuristics limit the size of percpu
partial list up to 2 pages. In case of a reported regression (which
would mean some workload has benefited from the previous imprecise
object based counting), we can tune the heuristics to get a better
compromise within the new scheme, while still avoid the unexpectedly
long percpu partial lists.
[1] https://lore.kernel.org/linux-mm/CAG48ez2Qx5K1Cab-m8BdSibp6wLTip6ro4=-umR7BLsEgjEYzA@mail.gmail.com/
[2] https://lore.kernel.org/all/2f0f46e8-2535-410a-1859-e9cfa4e57c18@suse.cz/
==========
Evaluation
==========
Mel was kind enough to run v1 through mmtests machinery for netperf
(localhost) and hackbench and, for most significant results see below.
So there are some apparent regressions, especially with hackbench, which
I think ultimately boils down to having shorter percpu partial lists on
average and some benchmarks benefiting from longer ones. Monitoring
slab usage also indicated less memory usage by slab. Based on that, the
following patch will bump the defaults to allow longer percpu partial
lists than after this patch.
However the goal is certainly not such that we would limit the percpu
partial lists to 30 pages just because previously a specific alloc/free
pattern could lead to the limit of 30 objects translate to a limit to 30
pages - that would make little sense. This is a correctness patch, and
if a workload benefits from larger lists, the sysfs tuning knobs are
still there to allow that.
Netperf
2-socket Intel(R) Xeon(R) Gold 5218R CPU @ 2.10GHz (20 cores, 40 threads per socket), 384GB RAM
TCP-RR:
hmean before 127045.79 after 121092.94 (-4.69%, worse)
stddev before 2634.37 after 1254.08
UDP-RR:
hmean before 166985.45 after 160668.94 ( -3.78%, worse)
stddev before 4059.69 after 1943.63
2-socket Intel(R) Xeon(R) CPU E5-2698 v4 @ 2.20GHz (20 cores, 40 threads per socket), 512GB RAM
TCP-RR:
hmean before 84173.25 after 76914.72 ( -8.62%, worse)
UDP-RR:
hmean before 93571.12 after 96428.69 ( 3.05%, better)
stddev before 23118.54 after 16828.14
2-socket Intel(R) Xeon(R) CPU E5-2670 v3 @ 2.30GHz (12 cores, 24 threads per socket), 64GB RAM
TCP-RR:
hmean before 49984.92 after 48922.27 ( -2.13%, worse)
stddev before 6248.15 after 4740.51
UDP-RR:
hmean before 61854.31 after 68761.81 ( 11.17%, better)
stddev before 4093.54 after 5898.91
other machines - within 2%
Hackbench
(results before and after the patch, negative % means worse)
2-socket AMD EPYC 7713 (64 cores, 128 threads per core), 256GB RAM
hackbench-process-sockets
Amean 1 0.5380 0.5583 ( -3.78%)
Amean 4 0.7510 0.8150 ( -8.52%)
Amean 7 0.7930 0.9533 ( -20.22%)
Amean 12 0.7853 1.1313 ( -44.06%)
Amean 21 1.1520 1.4993 ( -30.15%)
Amean 30 1.6223 1.9237 ( -18.57%)
Amean 48 2.6767 2.9903 ( -11.72%)
Amean 79 4.0257 5.1150 ( -27.06%)
Amean 110 5.5193 7.4720 ( -35.38%)
Amean 141 7.2207 9.9840 ( -38.27%)
Amean 172 8.4770 12.1963 ( -43.88%)
Amean 203 9.6473 14.3137 ( -48.37%)
Amean 234 11.3960 18.7917 ( -64.90%)
Amean 265 13.9627 22.4607 ( -60.86%)
Amean 296 14.9163 26.0483 ( -74.63%)
hackbench-thread-sockets
Amean 1 0.5597 0.5877 ( -5.00%)
Amean 4 0.7913 0.8960 ( -13.23%)
Amean 7 0.8190 1.0017 ( -22.30%)
Amean 12 0.9560 1.1727 ( -22.66%)
Amean 21 1.7587 1.5660 ( 10.96%)
Amean 30 2.4477 1.9807 ( 19.08%)
Amean 48 3.4573 3.0630 ( 11.41%)
Amean 79 4.7903 5.1733 ( -8.00%)
Amean 110 6.1370 7.4220 ( -20.94%)
Amean 141 7.5777 9.2617 ( -22.22%)
Amean 172 9.2280 11.0907 ( -20.18%)
Amean 203 10.2793 13.3470 ( -29.84%)
Amean 234 11.2410 17.1070 ( -52.18%)
Amean 265 12.5970 23.3323 ( -85.22%)
Amean 296 17.1540 24.2857 ( -41.57%)
2-socket Intel(R) Xeon(R) Gold 5218R CPU @ 2.10GHz (20 cores, 40 threads
per socket), 384GB RAM
hackbench-process-sockets
Amean 1 0.5760 0.4793 ( 16.78%)
Amean 4 0.9430 0.9707 ( -2.93%)
Amean 7 1.5517 1.8843 ( -21.44%)
Amean 12 2.4903 2.7267 ( -9.49%)
Amean 21 3.9560 4.2877 ( -8.38%)
Amean 30 5.4613 5.8343 ( -6.83%)
Amean 48 8.5337 9.2937 ( -8.91%)
Amean 79 14.0670 15.2630 ( -8.50%)
Amean 110 19.2253 21.2467 ( -10.51%)
Amean 141 23.7557 25.8550 ( -8.84%)
Amean 172 28.4407 29.7603 ( -4.64%)
Amean 203 33.3407 33.9927 ( -1.96%)
Amean 234 38.3633 39.1150 ( -1.96%)
Amean 265 43.4420 43.8470 ( -0.93%)
Amean 296 48.3680 48.9300 ( -1.16%)
hackbench-thread-sockets
Amean 1 0.6080 0.6493 ( -6.80%)
Amean 4 1.0000 1.0513 ( -5.13%)
Amean 7 1.6607 2.0260 ( -22.00%)
Amean 12 2.7637 2.9273 ( -5.92%)
Amean 21 5.0613 4.5153 ( 10.79%)
Amean 30 6.3340 6.1140 ( 3.47%)
Amean 48 9.0567 9.5577 ( -5.53%)
Amean 79 14.5657 15.7983 ( -8.46%)
Amean 110 19.6213 21.6333 ( -10.25%)
Amean 141 24.1563 26.2697 ( -8.75%)
Amean 172 28.9687 30.2187 ( -4.32%)
Amean 203 33.9763 34.6970 ( -2.12%)
Amean 234 38.8647 39.3207 ( -1.17%)
Amean 265 44.0813 44.1507 ( -0.16%)
Amean 296 49.2040 49.4330 ( -0.47%)
2-socket Intel(R) Xeon(R) CPU E5-2698 v4 @ 2.20GHz (20 cores, 40 threads
per socket), 512GB RAM
hackbench-process-sockets
Amean 1 0.5027 0.5017 ( 0.20%)
Amean 4 1.1053 1.2033 ( -8.87%)
Amean 7 1.8760 2.1820 ( -16.31%)
Amean 12 2.9053 3.1810 ( -9.49%)
Amean 21 4.6777 4.9920 ( -6.72%)
Amean 30 6.5180 6.7827 ( -4.06%)
Amean 48 10.0710 10.5227 ( -4.48%)
Amean 79 16.4250 17.5053 ( -6.58%)
Amean 110 22.6203 24.4617 ( -8.14%)
Amean 141 28.0967 31.0363 ( -10.46%)
Amean 172 34.4030 36.9233 ( -7.33%)
Amean 203 40.5933 43.0850 ( -6.14%)
Amean 234 46.6477 48.7220 ( -4.45%)
Amean 265 53.0530 53.9597 ( -1.71%)
Amean 296 59.2760 59.9213 ( -1.09%)
hackbench-thread-sockets
Amean 1 0.5363 0.5330 ( 0.62%)
Amean 4 1.1647 1.2157 ( -4.38%)
Amean 7 1.9237 2.2833 ( -18.70%)
Amean 12 2.9943 3.3110 ( -10.58%)
Amean 21 4.9987 5.1880 ( -3.79%)
Amean 30 6.7583 7.0043 ( -3.64%)
Amean 48 10.4547 10.8353 ( -3.64%)
Amean 79 16.6707 17.6790 ( -6.05%)
Amean 110 22.8207 24.4403 ( -7.10%)
Amean 141 28.7090 31.0533 ( -8.17%)
Amean 172 34.9387 36.8260 ( -5.40%)
Amean 203 41.1567 43.0450 ( -4.59%)
Amean 234 47.3790 48.5307 ( -2.43%)
Amean 265 53.9543 54.6987 ( -1.38%)
Amean 296 60.0820 60.2163 ( -0.22%)
1-socket Intel(R) Xeon(R) CPU E3-1240 v5 @ 3.50GHz (4 cores, 8 threads),
32 GB RAM
hackbench-process-sockets
Amean 1 1.4760 1.5773 ( -6.87%)
Amean 3 3.9370 4.0910 ( -3.91%)
Amean 5 6.6797 6.9357 ( -3.83%)
Amean 7 9.3367 9.7150 ( -4.05%)
Amean 12 15.7627 16.1400 ( -2.39%)
Amean 18 23.5360 23.6890 ( -0.65%)
Amean 24 31.0663 31.3137 ( -0.80%)
Amean 30 38.7283 39.0037 ( -0.71%)
Amean 32 41.3417 41.6097 ( -0.65%)
hackbench-thread-sockets
Amean 1 1.5250 1.6043 ( -5.20%)
Amean 3 4.0897 4.2603 ( -4.17%)
Amean 5 6.7760 7.0933 ( -4.68%)
Amean 7 9.4817 9.9157 ( -4.58%)
Amean 12 15.9610 16.3937 ( -2.71%)
Amean 18 23.9543 24.3417 ( -1.62%)
Amean 24 31.4400 31.7217 ( -0.90%)
Amean 30 39.2457 39.5467 ( -0.77%)
Amean 32 41.8267 42.1230 ( -0.71%)
2-socket Intel(R) Xeon(R) CPU E5-2670 v3 @ 2.30GHz (12 cores, 24 threads
per socket), 64GB RAM
hackbench-process-sockets
Amean 1 1.0347 1.0880 ( -5.15%)
Amean 4 1.7267 1.8527 ( -7.30%)
Amean 7 2.6707 2.8110 ( -5.25%)
Amean 12 4.1617 4.3383 ( -4.25%)
Amean 21 7.0070 7.2600 ( -3.61%)
Amean 30 9.9187 10.2397 ( -3.24%)
Amean 48 15.6710 16.3923 ( -4.60%)
Amean 79 24.7743 26.1247 ( -5.45%)
Amean 110 34.3000 35.9307 ( -4.75%)
Amean 141 44.2043 44.8010 ( -1.35%)
Amean 172 54.2430 54.7260 ( -0.89%)
Amean 192 60.6557 60.9777 ( -0.53%)
hackbench-thread-sockets
Amean 1 1.0610 1.1353 ( -7.01%)
Amean 4 1.7543 1.9140 ( -9.10%)
Amean 7 2.7840 2.9573 ( -6.23%)
Amean 12 4.3813 4.4937 ( -2.56%)
Amean 21 7.3460 7.5350 ( -2.57%)
Amean 30 10.2313 10.5190 ( -2.81%)
Amean 48 15.9700 16.5940 ( -3.91%)
Amean 79 25.3973 26.6637 ( -4.99%)
Amean 110 35.1087 36.4797 ( -3.91%)
Amean 141 45.8220 46.3053 ( -1.05%)
Amean 172 55.4917 55.7320 ( -0.43%)
Amean 192 62.7490 62.5410 ( 0.33%)
Link: https://lkml.kernel.org/r/20211012134651.11258-1-vbabka@suse.cz
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reported-by: Jann Horn <jannh@google.com>
Cc: Roman Gushchin <guro@fb.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-11-05 13:35:17 -07:00
|
|
|
|
|
|
|
|
|
2011-06-01 12:25:53 -05:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-08-23 19:04:00 +02:00
|
|
|
|
2011-06-01 12:25:53 -05:00
|
|
|
|
2024-03-26 17:10:30 +00:00
|
|
|
|
2011-06-01 12:25:53 -05:00
|
|
|
|
|
|
|
|
|
2022-08-23 19:04:00 +02:00
|
|
|
|
2011-06-01 12:25:53 -05:00
|
|
|
|
2024-03-26 17:10:30 +00:00
|
|
|
|
2011-06-01 12:25:53 -05:00
|
|
|
|
|
|
|
|
|
2023-05-31 15:08:43 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
mm, slub: make slab_lock() disable irqs with PREEMPT_RT
We need to disable irqs around slab_lock() (a bit spinlock) to make it
irq-safe. Most calls to slab_lock() are nested under spin_lock_irqsave() which
doesn't disable irqs on PREEMPT_RT, so add explicit disabling with PREEMPT_RT.
The exception is cmpxchg_double_slab() which already disables irqs, so use a
__slab_[un]lock() variant without irq disable there.
slab_[un]lock() thus needs a flags pointer parameter, which is unused on !RT.
free_debug_processing() now has two flags variables, which looks odd, but only
one is actually used - the one used in spin_lock_irqsave() on !RT and the one
used in slab_lock() on RT.
As a result, __cmpxchg_double_slab() and cmpxchg_double_slab() become
effectively identical on RT, as both will disable irqs, which is necessary on
RT as most callers of this function also rely on irqsaving lock operations.
Thus, assert that irqs are already disabled in __cmpxchg_double_slab() only on
!RT and also change the VM_BUG_ON assertion to the more standard lockdep_assert
one.
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2021-06-04 12:55:55 +02:00
|
|
|
|
|
|
|
|
|
2022-08-23 19:04:00 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
mm, slub: make slab_lock() disable irqs with PREEMPT_RT
We need to disable irqs around slab_lock() (a bit spinlock) to make it
irq-safe. Most calls to slab_lock() are nested under spin_lock_irqsave() which
doesn't disable irqs on PREEMPT_RT, so add explicit disabling with PREEMPT_RT.
The exception is cmpxchg_double_slab() which already disables irqs, so use a
__slab_[un]lock() variant without irq disable there.
slab_[un]lock() thus needs a flags pointer parameter, which is unused on !RT.
free_debug_processing() now has two flags variables, which looks odd, but only
one is actually used - the one used in spin_lock_irqsave() on !RT and the one
used in slab_lock() on RT.
As a result, __cmpxchg_double_slab() and cmpxchg_double_slab() become
effectively identical on RT, as both will disable irqs, which is necessary on
RT as most callers of this function also rely on irqsaving lock operations.
Thus, assert that irqs are already disabled in __cmpxchg_double_slab() only on
!RT and also change the VM_BUG_ON assertion to the more standard lockdep_assert
one.
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2021-06-04 12:55:55 +02:00
|
|
|
|
2023-05-31 15:08:43 +02:00
|
|
|
|
2011-06-01 12:25:49 -05:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-05-31 15:08:43 +02:00
|
|
|
|
|
|
|
|
|
2022-08-25 09:51:36 +02:00
|
|
|
|
mm, slub: make slab_lock() disable irqs with PREEMPT_RT
We need to disable irqs around slab_lock() (a bit spinlock) to make it
irq-safe. Most calls to slab_lock() are nested under spin_lock_irqsave() which
doesn't disable irqs on PREEMPT_RT, so add explicit disabling with PREEMPT_RT.
The exception is cmpxchg_double_slab() which already disables irqs, so use a
__slab_[un]lock() variant without irq disable there.
slab_[un]lock() thus needs a flags pointer parameter, which is unused on !RT.
free_debug_processing() now has two flags variables, which looks odd, but only
one is actually used - the one used in spin_lock_irqsave() on !RT and the one
used in slab_lock() on RT.
As a result, __cmpxchg_double_slab() and cmpxchg_double_slab() become
effectively identical on RT, as both will disable irqs, which is necessary on
RT as most callers of this function also rely on irqsaving lock operations.
Thus, assert that irqs are already disabled in __cmpxchg_double_slab() only on
!RT and also change the VM_BUG_ON assertion to the more standard lockdep_assert
one.
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2021-06-04 12:55:55 +02:00
|
|
|
|
2023-05-31 15:08:43 +02:00
|
|
|
|
2011-06-01 12:25:49 -05:00
|
|
|
|
2023-05-31 15:08:43 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-06-01 12:25:49 -05:00
|
|
|
|
2023-05-31 15:08:43 +02:00
|
|
|
|
|
|
|
|
|
2011-06-01 12:25:49 -05:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2014-06-04 16:06:34 -07:00
|
|
|
|
2011-06-01 12:25:49 -05:00
|
|
|
|
|
|
|
|
|
2015-04-14 15:44:31 -07:00
|
|
|
|
2011-06-01 12:25:49 -05:00
|
|
|
|
|
|
|
|
|
2023-05-31 15:08:43 +02:00
|
|
|
|
2011-07-14 12:49:12 -05:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-05-31 15:08:43 +02:00
|
|
|
|
|
|
|
|
|
2011-07-14 12:49:12 -05:00
|
|
|
|
2023-05-31 15:08:43 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-07-14 12:49:12 -05:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-05-31 15:08:43 +02:00
|
|
|
|
|
|
|
|
|
2011-07-14 12:49:12 -05:00
|
|
|
|
|
|
|
|
|
2023-05-31 15:08:43 +02:00
|
|
|
|
|
|
|
|
|
2011-07-14 12:49:12 -05:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2014-06-04 16:06:34 -07:00
|
|
|
|
2011-07-14 12:49:12 -05:00
|
|
|
|
|
|
|
|
|
2015-04-14 15:44:31 -07:00
|
|
|
|
2011-07-14 12:49:12 -05:00
|
|
|
|
|
|
|
|
|
mm, slub: avoid zeroing kmalloc redzone
Since commit 946fa0dbf2d8 ("mm/slub: extend redzone check to extra
allocated kmalloc space than requested"), setting orig_size treats
the wasted space (object_size - orig_size) as a redzone. However with
init_on_free=1 we clear the full object->size, including the redzone.
Additionally we clear the object metadata, including the stored orig_size,
making it zero, which makes check_object() treat the whole object as a
redzone.
These issues lead to the following BUG report with "slub_debug=FUZ
init_on_free=1":
[ 0.000000] =============================================================================
[ 0.000000] BUG kmalloc-8 (Not tainted): kmalloc Redzone overwritten
[ 0.000000] -----------------------------------------------------------------------------
[ 0.000000]
[ 0.000000] 0xffff000010032858-0xffff00001003285f @offset=2136. First byte 0x0 instead of 0xcc
[ 0.000000] FIX kmalloc-8: Restoring kmalloc Redzone 0xffff000010032858-0xffff00001003285f=0xcc
[ 0.000000] Slab 0xfffffdffc0400c80 objects=36 used=23 fp=0xffff000010032a18 flags=0x3fffe0000000200(workingset|node=0|zone=0|lastcpupid=0x1ffff)
[ 0.000000] Object 0xffff000010032858 @offset=2136 fp=0xffff0000100328c8
[ 0.000000]
[ 0.000000] Redzone ffff000010032850: cc cc cc cc cc cc cc cc ........
[ 0.000000] Object ffff000010032858: cc cc cc cc cc cc cc cc ........
[ 0.000000] Redzone ffff000010032860: cc cc cc cc cc cc cc cc ........
[ 0.000000] Padding ffff0000100328b4: 00 00 00 00 00 00 00 00 00 00 00 00 ............
[ 0.000000] CPU: 0 UID: 0 PID: 0 Comm: swapper/0 Not tainted 6.11.0-rc3-next-20240814-00004-g61844c55c3f4 #144
[ 0.000000] Hardware name: NXP i.MX95 19X19 board (DT)
[ 0.000000] Call trace:
[ 0.000000] dump_backtrace+0x90/0xe8
[ 0.000000] show_stack+0x18/0x24
[ 0.000000] dump_stack_lvl+0x74/0x8c
[ 0.000000] dump_stack+0x18/0x24
[ 0.000000] print_trailer+0x150/0x218
[ 0.000000] check_object+0xe4/0x454
[ 0.000000] free_to_partial_list+0x2f8/0x5ec
To address the issue, use orig_size to clear the used area. And restore
the value of orig_size after clear the remaining area.
When CONFIG_SLUB_DEBUG not defined, (get_orig_size()' directly returns
s->object_size. So when using memset to init the area, the size can simply
be orig_size, as orig_size returns object_size when CONFIG_SLUB_DEBUG not
enabled. And orig_size can never be bigger than object_size.
Fixes: 946fa0dbf2d8 ("mm/slub: extend redzone check to extra allocated kmalloc space than requested")
Cc: <stable@vger.kernel.org>
Reviewed-by: Feng Tang <feng.tang@intel.com>
Acked-by: David Rientjes <rientjes@google.com>
Signed-off-by: Peng Fan <peng.fan@nxp.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2024-08-29 11:29:11 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-10-16 23:41:50 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
mm, slub: avoid zeroing kmalloc redzone
Since commit 946fa0dbf2d8 ("mm/slub: extend redzone check to extra
allocated kmalloc space than requested"), setting orig_size treats
the wasted space (object_size - orig_size) as a redzone. However with
init_on_free=1 we clear the full object->size, including the redzone.
Additionally we clear the object metadata, including the stored orig_size,
making it zero, which makes check_object() treat the whole object as a
redzone.
These issues lead to the following BUG report with "slub_debug=FUZ
init_on_free=1":
[ 0.000000] =============================================================================
[ 0.000000] BUG kmalloc-8 (Not tainted): kmalloc Redzone overwritten
[ 0.000000] -----------------------------------------------------------------------------
[ 0.000000]
[ 0.000000] 0xffff000010032858-0xffff00001003285f @offset=2136. First byte 0x0 instead of 0xcc
[ 0.000000] FIX kmalloc-8: Restoring kmalloc Redzone 0xffff000010032858-0xffff00001003285f=0xcc
[ 0.000000] Slab 0xfffffdffc0400c80 objects=36 used=23 fp=0xffff000010032a18 flags=0x3fffe0000000200(workingset|node=0|zone=0|lastcpupid=0x1ffff)
[ 0.000000] Object 0xffff000010032858 @offset=2136 fp=0xffff0000100328c8
[ 0.000000]
[ 0.000000] Redzone ffff000010032850: cc cc cc cc cc cc cc cc ........
[ 0.000000] Object ffff000010032858: cc cc cc cc cc cc cc cc ........
[ 0.000000] Redzone ffff000010032860: cc cc cc cc cc cc cc cc ........
[ 0.000000] Padding ffff0000100328b4: 00 00 00 00 00 00 00 00 00 00 00 00 ............
[ 0.000000] CPU: 0 UID: 0 PID: 0 Comm: swapper/0 Not tainted 6.11.0-rc3-next-20240814-00004-g61844c55c3f4 #144
[ 0.000000] Hardware name: NXP i.MX95 19X19 board (DT)
[ 0.000000] Call trace:
[ 0.000000] dump_backtrace+0x90/0xe8
[ 0.000000] show_stack+0x18/0x24
[ 0.000000] dump_stack_lvl+0x74/0x8c
[ 0.000000] dump_stack+0x18/0x24
[ 0.000000] print_trailer+0x150/0x218
[ 0.000000] check_object+0xe4/0x454
[ 0.000000] free_to_partial_list+0x2f8/0x5ec
To address the issue, use orig_size to clear the used area. And restore
the value of orig_size after clear the remaining area.
When CONFIG_SLUB_DEBUG not defined, (get_orig_size()' directly returns
s->object_size. So when using memset to init the area, the size can simply
be orig_size, as orig_size returns object_size when CONFIG_SLUB_DEBUG not
enabled. And orig_size can never be bigger than object_size.
Fixes: 946fa0dbf2d8 ("mm/slub: extend redzone check to extra allocated kmalloc space than requested")
Cc: <stable@vger.kernel.org>
Reviewed-by: Feng Tang <feng.tang@intel.com>
Acked-by: David Rientjes <rientjes@google.com>
Signed-off-by: Peng Fan <peng.fan@nxp.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2024-08-29 11:29:11 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-09 02:32:44 -07:00
|
|
|
|
2020-01-30 22:11:57 -08:00
|
|
|
|
2022-08-23 19:03:59 +02:00
|
|
|
|
2020-01-30 22:11:57 -08:00
|
|
|
|
2021-05-23 01:28:37 +02:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2021-05-23 01:28:37 +02:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2021-05-23 01:28:37 +02:00
|
|
|
|
|
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2021-05-23 01:28:37 +02:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2021-05-23 01:28:37 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-06-28 19:34:33 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-11-25 16:43:06 +08:00
|
|
|
|
2021-06-28 19:34:33 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-06-07 16:40:12 +08:00
|
|
|
|
2024-10-01 18:20:48 +02:00
|
|
|
|
2024-06-07 16:40:12 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-06-28 19:34:33 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-04-05 16:21:43 -07:00
|
|
|
|
2016-03-15 14:55:12 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-09 02:32:44 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-11-05 18:51:23 -08:00
|
|
|
|
2017-11-15 17:32:18 -08:00
|
|
|
|
2007-07-15 23:38:14 -07:00
|
|
|
|
2017-11-15 17:32:18 -08:00
|
|
|
|
2007-07-15 23:38:14 -07:00
|
|
|
|
2007-05-09 02:32:44 -07:00
|
|
|
|
2020-08-06 23:18:35 -07:00
|
|
|
|
2009-07-07 00:14:14 -07:00
|
|
|
|
2007-05-09 02:32:44 -07:00
|
|
|
|
2015-02-13 14:39:38 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-06-21 13:35:01 +02:00
|
|
|
|
2015-02-13 14:39:38 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-06-21 13:35:01 +02:00
|
|
|
|
2015-02-13 14:39:38 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-03-15 14:55:12 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2016-03-15 14:55:12 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2019-02-20 22:19:36 -08:00
|
|
|
|
2016-03-15 14:55:12 -07:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2016-03-15 14:55:12 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-01-24 15:18:02 -08:00
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2015-02-13 14:39:38 -08:00
|
|
|
|
2021-08-13 16:54:27 -07:00
|
|
|
|
|
|
|
|
|
2015-02-13 14:39:38 -08:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-05-07 18:36:06 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2020-12-22 12:02:17 -08:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
2021-07-07 18:07:47 -07:00
|
|
|
|
2022-06-07 17:20:10 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-07-07 18:07:47 -07:00
|
|
|
|
2022-02-04 17:44:40 +01:00
|
|
|
|
2021-07-17 13:27:00 -07:00
|
|
|
|
2021-07-07 18:07:47 -07:00
|
|
|
|
2022-06-07 17:20:10 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-07-07 11:36:36 -07:00
|
|
|
|
2021-07-07 18:07:47 -07:00
|
|
|
|
2022-06-07 17:20:10 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-02-04 17:44:40 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
2022-06-07 17:20:10 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
2022-02-04 17:44:40 +01:00
|
|
|
|
|
|
|
|
|
2007-07-17 04:03:18 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-02-04 17:44:40 +01:00
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
2018-04-05 16:20:15 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2021-07-07 18:07:47 -07:00
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-03-19 18:12:45 +08:00
|
|
|
|
2018-04-05 16:20:15 -07:00
|
|
|
|
2021-07-07 18:07:47 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-07-07 11:36:36 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
2020-08-06 23:19:05 -07:00
|
|
|
|
2007-07-17 04:03:18 -07:00
|
|
|
|
2018-04-05 16:20:15 -07:00
|
|
|
|
2007-07-17 04:03:18 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-04-05 16:20:15 -07:00
|
|
|
|
|
|
|
|
|
2007-07-17 04:03:18 -07:00
|
|
|
|
|
|
|
|
|
2021-10-04 14:46:34 +01:00
|
|
|
|
2007-07-17 04:03:18 -07:00
|
|
|
|
2021-10-04 14:46:34 +01:00
|
|
|
|
|
|
|
|
|
2024-05-31 13:29:02 +01:00
|
|
|
|
2007-07-17 04:03:18 -07:00
|
|
|
|
|
|
|
|
|
mm/slub: extend redzone check to extra allocated kmalloc space than requested
kmalloc will round up the request size to a fixed size (mostly power
of 2), so there could be a extra space than what is requested, whose
size is the actual buffer size minus original request size.
To better detect out of bound access or abuse of this space, add
redzone sanity check for it.
In current kernel, some kmalloc user already knows the existence of
the space and utilizes it after calling 'ksize()' to know the real
size of the allocated buffer. So we skip the sanity check for objects
which have been called with ksize(), as treating them as legitimate
users. Kees Cook is working on sanitizing all these user cases,
by using kmalloc_size_roundup() to avoid ambiguous usages. And after
this is done, this special handling for ksize() can be removed.
In some cases, the free pointer could be saved inside the latter
part of object data area, which may overlap the redzone part(for
small sizes of kmalloc objects). As suggested by Hyeonggon Yoo,
force the free pointer to be in meta data area when kmalloc redzone
debug is enabled, to make all kmalloc objects covered by redzone
check.
Suggested-by: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Feng Tang <feng.tang@intel.com>
Acked-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2022-10-21 11:24:05 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-07-17 04:03:18 -07:00
|
|
|
|
|
|
|
|
|
2014-06-04 16:06:35 -07:00
|
|
|
|
2007-07-17 04:03:18 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2014-06-04 16:06:35 -07:00
|
|
|
|
|
|
|
|
|
2014-06-04 16:06:34 -07:00
|
|
|
|
2014-06-04 16:06:35 -07:00
|
|
|
|
2014-06-04 16:06:34 -07:00
|
|
|
|
2014-06-04 16:06:35 -07:00
|
|
|
|
2007-07-17 04:03:18 -07:00
|
|
|
|
|
|
|
|
|
2021-06-28 19:34:49 -07:00
|
|
|
|
2007-07-17 04:03:18 -07:00
|
|
|
|
|
|
|
|
|
2014-06-04 16:06:35 -07:00
|
|
|
|
2007-07-17 04:03:18 -07:00
|
|
|
|
|
|
|
|
|
2021-06-28 19:34:33 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-07-17 04:03:18 -07:00
|
|
|
|
2014-06-04 16:06:35 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-07-17 04:03:18 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2007-07-17 04:03:18 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2007-07-17 04:03:18 -07:00
|
|
|
|
2021-03-19 18:12:45 +08:00
|
|
|
|
2014-06-04 16:06:34 -07:00
|
|
|
|
2007-07-17 04:03:18 -07:00
|
|
|
|
2016-03-15 14:55:12 -07:00
|
|
|
|
2021-06-15 18:23:19 -07:00
|
|
|
|
2017-01-24 15:18:02 -08:00
|
|
|
|
2016-03-15 14:55:12 -07:00
|
|
|
|
2017-01-24 15:18:02 -08:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2021-06-15 18:23:19 -07:00
|
|
|
|
2018-04-05 16:21:17 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2021-06-15 18:23:19 -07:00
|
|
|
|
2012-06-13 10:24:57 -05:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2020-05-07 18:36:06 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2007-07-17 04:03:18 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
mm/slub: enable debugging memory wasting of kmalloc
kmalloc's API family is critical for mm, with one nature that it will
round up the request size to a fixed one (mostly power of 2). Say
when user requests memory for '2^n + 1' bytes, actually 2^(n+1) bytes
could be allocated, so in worst case, there is around 50% memory
space waste.
The wastage is not a big issue for requests that get allocated/freed
quickly, but may cause problems with objects that have longer life
time.
We've met a kernel boot OOM panic (v5.10), and from the dumped slab
info:
[ 26.062145] kmalloc-2k 814056KB 814056KB
From debug we found there are huge number of 'struct iova_magazine',
whose size is 1032 bytes (1024 + 8), so each allocation will waste
1016 bytes. Though the issue was solved by giving the right (bigger)
size of RAM, it is still nice to optimize the size (either use a
kmalloc friendly size or create a dedicated slab for it).
And from lkml archive, there was another crash kernel OOM case [1]
back in 2019, which seems to be related with the similar slab waste
situation, as the log is similar:
[ 4.332648] iommu: Adding device 0000:20:02.0 to group 16
[ 4.338946] swapper/0 invoked oom-killer: gfp_mask=0x6040c0(GFP_KERNEL|__GFP_COMP), nodemask=(null), order=0, oom_score_adj=0
...
[ 4.857565] kmalloc-2048 59164KB 59164KB
The crash kernel only has 256M memory, and 59M is pretty big here.
(Note: the related code has been changed and optimised in recent
kernel [2], these logs are just picked to demo the problem, also
a patch changing its size to 1024 bytes has been merged)
So add an way to track each kmalloc's memory waste info, and
leverage the existing SLUB debug framework (specifically
SLUB_STORE_USER) to show its call stack of original allocation,
so that user can evaluate the waste situation, identify some hot
spots and optimize accordingly, for a better utilization of memory.
The waste info is integrated into existing interface:
'/sys/kernel/debug/slab/kmalloc-xx/alloc_traces', one example of
'kmalloc-4k' after boot is:
126 ixgbe_alloc_q_vector+0xbe/0x830 [ixgbe] waste=233856/1856 age=280763/281414/282065 pid=1330 cpus=32 nodes=1
__kmem_cache_alloc_node+0x11f/0x4e0
__kmalloc_node+0x4e/0x140
ixgbe_alloc_q_vector+0xbe/0x830 [ixgbe]
ixgbe_init_interrupt_scheme+0x2ae/0xc90 [ixgbe]
ixgbe_probe+0x165f/0x1d20 [ixgbe]
local_pci_probe+0x78/0xc0
work_for_cpu_fn+0x26/0x40
...
which means in 'kmalloc-4k' slab, there are 126 requests of
2240 bytes which got a 4KB space (wasting 1856 bytes each
and 233856 bytes in total), from ixgbe_alloc_q_vector().
And when system starts some real workload like multiple docker
instances, there could are more severe waste.
[1]. https://lkml.org/lkml/2019/8/12/266
[2]. https://lore.kernel.org/lkml/2920df89-9975-5785-f79b-257d3052dfaf@huawei.com/
[Thanks Hyeonggon for pointing out several bugs about sorting/format]
[Thanks Vlastimil for suggesting way to reduce memory usage of
orig_size and keep it only for kmalloc objects]
Signed-off-by: Feng Tang <feng.tang@intel.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Robin Murphy <robin.murphy@arm.com>
Cc: John Garry <john.garry@huawei.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2022-09-13 14:54:20 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-10-21 11:24:04 +08:00
|
|
|
|
2016-07-28 15:49:07 -07:00
|
|
|
|
2016-03-15 14:55:12 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2021-06-15 18:23:19 -07:00
|
|
|
|
2017-01-24 15:18:02 -08:00
|
|
|
|
2007-07-17 04:03:18 -07:00
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
2021-06-28 19:34:33 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-04-23 12:28:01 -07:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2021-06-28 19:34:58 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2021-10-26 18:22:44 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
|
|
|
|
|
2021-10-26 18:22:44 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2013-07-15 09:05:29 +08:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-06-28 19:34:33 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-07-17 04:03:18 -07:00
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2008-04-23 12:28:01 -07:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2021-06-28 19:34:58 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
2010-09-29 07:15:01 -05:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2020-12-22 12:02:17 -08:00
|
|
|
|
mm/slub: extend redzone check to extra allocated kmalloc space than requested
kmalloc will round up the request size to a fixed size (mostly power
of 2), so there could be a extra space than what is requested, whose
size is the actual buffer size minus original request size.
To better detect out of bound access or abuse of this space, add
redzone sanity check for it.
In current kernel, some kmalloc user already knows the existence of
the space and utilizes it after calling 'ksize()' to know the real
size of the allocated buffer. So we skip the sanity check for objects
which have been called with ksize(), as treating them as legitimate
users. Kees Cook is working on sanitizing all these user cases,
by using kmalloc_size_roundup() to avoid ambiguous usages. And after
this is done, this special handling for ksize() can be removed.
In some cases, the free pointer could be saved inside the latter
part of object data area, which may overlap the redzone part(for
small sizes of kmalloc objects). As suggested by Hyeonggon Yoo,
force the free pointer to be in meta data area when kmalloc redzone
debug is enabled, to make all kmalloc objects covered by redzone
check.
Suggested-by: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Feng Tang <feng.tang@intel.com>
Acked-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2022-10-21 11:24:05 +08:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
mm/slub: extend redzone check to extra allocated kmalloc space than requested
kmalloc will round up the request size to a fixed size (mostly power
of 2), so there could be a extra space than what is requested, whose
size is the actual buffer size minus original request size.
To better detect out of bound access or abuse of this space, add
redzone sanity check for it.
In current kernel, some kmalloc user already knows the existence of
the space and utilizes it after calling 'ksize()' to know the real
size of the allocated buffer. So we skip the sanity check for objects
which have been called with ksize(), as treating them as legitimate
users. Kees Cook is working on sanitizing all these user cases,
by using kmalloc_size_roundup() to avoid ambiguous usages. And after
this is done, this special handling for ksize() can be removed.
In some cases, the free pointer could be saved inside the latter
part of object data area, which may overlap the redzone part(for
small sizes of kmalloc objects). As suggested by Hyeonggon Yoo,
force the free pointer to be in meta data area when kmalloc redzone
debug is enabled, to make all kmalloc objects covered by redzone
check.
Suggested-by: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Feng Tang <feng.tang@intel.com>
Acked-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2022-10-21 11:24:05 +08:00
|
|
|
|
2024-06-21 13:34:57 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-03-15 14:55:12 -07:00
|
|
|
|
mm/slub: extend redzone check to extra allocated kmalloc space than requested
kmalloc will round up the request size to a fixed size (mostly power
of 2), so there could be a extra space than what is requested, whose
size is the actual buffer size minus original request size.
To better detect out of bound access or abuse of this space, add
redzone sanity check for it.
In current kernel, some kmalloc user already knows the existence of
the space and utilizes it after calling 'ksize()' to know the real
size of the allocated buffer. So we skip the sanity check for objects
which have been called with ksize(), as treating them as legitimate
users. Kees Cook is working on sanitizing all these user cases,
by using kmalloc_size_roundup() to avoid ambiguous usages. And after
this is done, this special handling for ksize() can be removed.
In some cases, the free pointer could be saved inside the latter
part of object data area, which may overlap the redzone part(for
small sizes of kmalloc objects). As suggested by Hyeonggon Yoo,
force the free pointer to be in meta data area when kmalloc redzone
debug is enabled, to make all kmalloc objects covered by redzone
check.
Suggested-by: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Feng Tang <feng.tang@intel.com>
Acked-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2022-10-21 11:24:05 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2024-06-21 13:34:57 +02:00
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-06-21 13:34:57 +02:00
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
2007-07-17 04:03:18 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-06-28 19:34:49 -07:00
|
|
|
|
2007-07-17 04:03:18 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-06-21 13:35:02 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-07-17 04:03:18 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2007-07-17 04:03:18 -07:00
|
|
|
|
2015-02-13 14:39:38 -08:00
|
|
|
|
2020-12-22 12:02:17 -08:00
|
|
|
|
2015-02-13 14:39:38 -08:00
|
|
|
|
2007-07-17 04:03:18 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-06-28 19:34:33 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-07-17 04:03:18 -07:00
|
|
|
|
2021-03-19 18:12:45 +08:00
|
|
|
|
2019-11-30 17:49:31 -08:00
|
|
|
|
|
|
|
|
|
2007-07-17 04:03:18 -07:00
|
|
|
|
2021-06-28 19:34:33 -07:00
|
|
|
|
2007-07-17 04:03:18 -07:00
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-05-07 18:36:06 -07:00
|
|
|
|
2007-05-09 02:32:39 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-06-13 10:24:57 -05:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2007-05-09 02:32:39 -07:00
|
|
|
|
2012-06-13 10:24:57 -05:00
|
|
|
|
2007-05-09 02:32:39 -07:00
|
|
|
|
2024-06-07 16:40:14 +08:00
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
2007-05-09 02:32:39 -07:00
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
mm/slub: enable debugging memory wasting of kmalloc
kmalloc's API family is critical for mm, with one nature that it will
round up the request size to a fixed one (mostly power of 2). Say
when user requests memory for '2^n + 1' bytes, actually 2^(n+1) bytes
could be allocated, so in worst case, there is around 50% memory
space waste.
The wastage is not a big issue for requests that get allocated/freed
quickly, but may cause problems with objects that have longer life
time.
We've met a kernel boot OOM panic (v5.10), and from the dumped slab
info:
[ 26.062145] kmalloc-2k 814056KB 814056KB
From debug we found there are huge number of 'struct iova_magazine',
whose size is 1032 bytes (1024 + 8), so each allocation will waste
1016 bytes. Though the issue was solved by giving the right (bigger)
size of RAM, it is still nice to optimize the size (either use a
kmalloc friendly size or create a dedicated slab for it).
And from lkml archive, there was another crash kernel OOM case [1]
back in 2019, which seems to be related with the similar slab waste
situation, as the log is similar:
[ 4.332648] iommu: Adding device 0000:20:02.0 to group 16
[ 4.338946] swapper/0 invoked oom-killer: gfp_mask=0x6040c0(GFP_KERNEL|__GFP_COMP), nodemask=(null), order=0, oom_score_adj=0
...
[ 4.857565] kmalloc-2048 59164KB 59164KB
The crash kernel only has 256M memory, and 59M is pretty big here.
(Note: the related code has been changed and optimised in recent
kernel [2], these logs are just picked to demo the problem, also
a patch changing its size to 1024 bytes has been merged)
So add an way to track each kmalloc's memory waste info, and
leverage the existing SLUB debug framework (specifically
SLUB_STORE_USER) to show its call stack of original allocation,
so that user can evaluate the waste situation, identify some hot
spots and optimize accordingly, for a better utilization of memory.
The waste info is integrated into existing interface:
'/sys/kernel/debug/slab/kmalloc-xx/alloc_traces', one example of
'kmalloc-4k' after boot is:
126 ixgbe_alloc_q_vector+0xbe/0x830 [ixgbe] waste=233856/1856 age=280763/281414/282065 pid=1330 cpus=32 nodes=1
__kmem_cache_alloc_node+0x11f/0x4e0
__kmalloc_node+0x4e/0x140
ixgbe_alloc_q_vector+0xbe/0x830 [ixgbe]
ixgbe_init_interrupt_scheme+0x2ae/0xc90 [ixgbe]
ixgbe_probe+0x165f/0x1d20 [ixgbe]
local_pci_probe+0x78/0xc0
work_for_cpu_fn+0x26/0x40
...
which means in 'kmalloc-4k' slab, there are 126 requests of
2240 bytes which got a 4KB space (wasting 1856 bytes each
and 233856 bytes in total), from ixgbe_alloc_q_vector().
And when system starts some real workload like multiple docker
instances, there could are more severe waste.
[1]. https://lkml.org/lkml/2019/8/12/266
[2]. https://lore.kernel.org/lkml/2920df89-9975-5785-f79b-257d3052dfaf@huawei.com/
[Thanks Hyeonggon for pointing out several bugs about sorting/format]
[Thanks Vlastimil for suggesting way to reduce memory usage of
orig_size and keep it only for kmalloc objects]
Signed-off-by: Feng Tang <feng.tang@intel.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Robin Murphy <robin.murphy@arm.com>
Cc: John Garry <john.garry@huawei.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2022-09-13 14:54:20 +08:00
|
|
|
|
|
|
|
|
|
2008-02-15 23:45:26 -08:00
|
|
|
|
2007-05-09 02:32:39 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
2007-05-09 02:32:39 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2012-06-13 10:24:57 -05:00
|
|
|
|
2007-05-09 02:32:39 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2020-05-07 18:36:06 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
mm/slub: enable debugging memory wasting of kmalloc
kmalloc's API family is critical for mm, with one nature that it will
round up the request size to a fixed one (mostly power of 2). Say
when user requests memory for '2^n + 1' bytes, actually 2^(n+1) bytes
could be allocated, so in worst case, there is around 50% memory
space waste.
The wastage is not a big issue for requests that get allocated/freed
quickly, but may cause problems with objects that have longer life
time.
We've met a kernel boot OOM panic (v5.10), and from the dumped slab
info:
[ 26.062145] kmalloc-2k 814056KB 814056KB
From debug we found there are huge number of 'struct iova_magazine',
whose size is 1032 bytes (1024 + 8), so each allocation will waste
1016 bytes. Though the issue was solved by giving the right (bigger)
size of RAM, it is still nice to optimize the size (either use a
kmalloc friendly size or create a dedicated slab for it).
And from lkml archive, there was another crash kernel OOM case [1]
back in 2019, which seems to be related with the similar slab waste
situation, as the log is similar:
[ 4.332648] iommu: Adding device 0000:20:02.0 to group 16
[ 4.338946] swapper/0 invoked oom-killer: gfp_mask=0x6040c0(GFP_KERNEL|__GFP_COMP), nodemask=(null), order=0, oom_score_adj=0
...
[ 4.857565] kmalloc-2048 59164KB 59164KB
The crash kernel only has 256M memory, and 59M is pretty big here.
(Note: the related code has been changed and optimised in recent
kernel [2], these logs are just picked to demo the problem, also
a patch changing its size to 1024 bytes has been merged)
So add an way to track each kmalloc's memory waste info, and
leverage the existing SLUB debug framework (specifically
SLUB_STORE_USER) to show its call stack of original allocation,
so that user can evaluate the waste situation, identify some hot
spots and optimize accordingly, for a better utilization of memory.
The waste info is integrated into existing interface:
'/sys/kernel/debug/slab/kmalloc-xx/alloc_traces', one example of
'kmalloc-4k' after boot is:
126 ixgbe_alloc_q_vector+0xbe/0x830 [ixgbe] waste=233856/1856 age=280763/281414/282065 pid=1330 cpus=32 nodes=1
__kmem_cache_alloc_node+0x11f/0x4e0
__kmalloc_node+0x4e/0x140
ixgbe_alloc_q_vector+0xbe/0x830 [ixgbe]
ixgbe_init_interrupt_scheme+0x2ae/0xc90 [ixgbe]
ixgbe_probe+0x165f/0x1d20 [ixgbe]
local_pci_probe+0x78/0xc0
work_for_cpu_fn+0x26/0x40
...
which means in 'kmalloc-4k' slab, there are 126 requests of
2240 bytes which got a 4KB space (wasting 1856 bytes each
and 233856 bytes in total), from ixgbe_alloc_q_vector().
And when system starts some real workload like multiple docker
instances, there could are more severe waste.
[1]. https://lkml.org/lkml/2019/8/12/266
[2]. https://lore.kernel.org/lkml/2920df89-9975-5785-f79b-257d3052dfaf@huawei.com/
[Thanks Hyeonggon for pointing out several bugs about sorting/format]
[Thanks Vlastimil for suggesting way to reduce memory usage of
orig_size and keep it only for kmalloc objects]
Signed-off-by: Feng Tang <feng.tang@intel.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Robin Murphy <robin.murphy@arm.com>
Cc: John Garry <john.garry@huawei.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2022-09-13 14:54:20 +08:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
mm/slub: enable debugging memory wasting of kmalloc
kmalloc's API family is critical for mm, with one nature that it will
round up the request size to a fixed one (mostly power of 2). Say
when user requests memory for '2^n + 1' bytes, actually 2^(n+1) bytes
could be allocated, so in worst case, there is around 50% memory
space waste.
The wastage is not a big issue for requests that get allocated/freed
quickly, but may cause problems with objects that have longer life
time.
We've met a kernel boot OOM panic (v5.10), and from the dumped slab
info:
[ 26.062145] kmalloc-2k 814056KB 814056KB
From debug we found there are huge number of 'struct iova_magazine',
whose size is 1032 bytes (1024 + 8), so each allocation will waste
1016 bytes. Though the issue was solved by giving the right (bigger)
size of RAM, it is still nice to optimize the size (either use a
kmalloc friendly size or create a dedicated slab for it).
And from lkml archive, there was another crash kernel OOM case [1]
back in 2019, which seems to be related with the similar slab waste
situation, as the log is similar:
[ 4.332648] iommu: Adding device 0000:20:02.0 to group 16
[ 4.338946] swapper/0 invoked oom-killer: gfp_mask=0x6040c0(GFP_KERNEL|__GFP_COMP), nodemask=(null), order=0, oom_score_adj=0
...
[ 4.857565] kmalloc-2048 59164KB 59164KB
The crash kernel only has 256M memory, and 59M is pretty big here.
(Note: the related code has been changed and optimised in recent
kernel [2], these logs are just picked to demo the problem, also
a patch changing its size to 1024 bytes has been merged)
So add an way to track each kmalloc's memory waste info, and
leverage the existing SLUB debug framework (specifically
SLUB_STORE_USER) to show its call stack of original allocation,
so that user can evaluate the waste situation, identify some hot
spots and optimize accordingly, for a better utilization of memory.
The waste info is integrated into existing interface:
'/sys/kernel/debug/slab/kmalloc-xx/alloc_traces', one example of
'kmalloc-4k' after boot is:
126 ixgbe_alloc_q_vector+0xbe/0x830 [ixgbe] waste=233856/1856 age=280763/281414/282065 pid=1330 cpus=32 nodes=1
__kmem_cache_alloc_node+0x11f/0x4e0
__kmalloc_node+0x4e/0x140
ixgbe_alloc_q_vector+0xbe/0x830 [ixgbe]
ixgbe_init_interrupt_scheme+0x2ae/0xc90 [ixgbe]
ixgbe_probe+0x165f/0x1d20 [ixgbe]
local_pci_probe+0x78/0xc0
work_for_cpu_fn+0x26/0x40
...
which means in 'kmalloc-4k' slab, there are 126 requests of
2240 bytes which got a 4KB space (wasting 1856 bytes each
and 233856 bytes in total), from ixgbe_alloc_q_vector().
And when system starts some real workload like multiple docker
instances, there could are more severe waste.
[1]. https://lkml.org/lkml/2019/8/12/266
[2]. https://lore.kernel.org/lkml/2920df89-9975-5785-f79b-257d3052dfaf@huawei.com/
[Thanks Hyeonggon for pointing out several bugs about sorting/format]
[Thanks Vlastimil for suggesting way to reduce memory usage of
orig_size and keep it only for kmalloc objects]
Signed-off-by: Feng Tang <feng.tang@intel.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Robin Murphy <robin.murphy@arm.com>
Cc: John Garry <john.garry@huawei.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2022-09-13 14:54:20 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-10-21 11:24:04 +08:00
|
|
|
|
2016-07-28 15:49:07 -07:00
|
|
|
|
2016-03-15 14:55:12 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2016-03-15 14:55:12 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
2008-04-14 19:11:30 +03:00
|
|
|
|
2024-06-21 13:35:02 +02:00
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2007-07-17 04:03:18 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-01-31 16:15:43 -08:00
|
|
|
|
2007-07-17 04:03:18 -07:00
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
2022-04-19 20:03:52 +08:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
|
|
|
|
|
2008-04-14 19:11:30 +03:00
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2022-04-19 20:03:52 +08:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2018-01-31 16:15:43 -08:00
|
|
|
|
2015-02-13 14:39:38 -08:00
|
|
|
|
2020-12-22 12:02:17 -08:00
|
|
|
|
2015-02-13 14:39:38 -08:00
|
|
|
|
2007-07-17 04:03:18 -07:00
|
|
|
|
2022-04-19 20:03:52 +08:00
|
|
|
|
2007-07-17 04:03:18 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2019-11-30 17:49:31 -08:00
|
|
|
|
2018-01-31 16:15:43 -08:00
|
|
|
|
2007-07-17 04:03:18 -07:00
|
|
|
|
2018-01-31 16:15:43 -08:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2010-09-29 07:15:01 -05:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
2012-06-13 10:24:57 -05:00
|
|
|
|
slub, kasan: improve interaction of KASAN and slub_debug poisoning
When both KASAN and slub_debug are enabled, when a free object is being
prepared in setup_object, slub_debug poisons the object data before KASAN
initializes its per-object metadata.
Right now, in setup_object, KASAN only initializes the alloc metadata,
which is always stored outside of the object. slub_debug is aware of this
and it skips poisoning and checking that memory area.
However, with the following patch in this series, KASAN also starts
initializing its free medata in setup_object. As this metadata might be
stored within the object, this initialization might overwrite the
slub_debug poisoning. This leads to slub_debug reports.
Thus, skip checking slub_debug poisoning of the object data area that
overlaps with the in-object KASAN free metadata.
Also make slub_debug poisoning of tail kmalloc redzones more precise when
KASAN is enabled: slub_debug can still poison and check the tail kmalloc
allocation area that comes after the KASAN free metadata.
Link: https://lkml.kernel.org/r/20231122231202.121277-1-andrey.konovalov@linux.dev
Signed-off-by: Andrey Konovalov <andreyknvl@google.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Evgenii Stepanov <eugenis@google.com>
Cc: Feng Tang <feng.tang@intel.com>
Cc: Marco Elver <elver@google.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-11-23 00:12:02 +01:00
|
|
|
|
2024-06-07 16:40:12 +08:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2016-03-15 14:55:12 -07:00
|
|
|
|
2024-06-07 16:40:12 +08:00
|
|
|
|
2016-03-15 14:55:12 -07:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2012-06-13 10:24:57 -05:00
|
|
|
|
2024-06-07 16:40:12 +08:00
|
|
|
|
mm/slub: extend redzone check to extra allocated kmalloc space than requested
kmalloc will round up the request size to a fixed size (mostly power
of 2), so there could be a extra space than what is requested, whose
size is the actual buffer size minus original request size.
To better detect out of bound access or abuse of this space, add
redzone sanity check for it.
In current kernel, some kmalloc user already knows the existence of
the space and utilizes it after calling 'ksize()' to know the real
size of the allocated buffer. So we skip the sanity check for objects
which have been called with ksize(), as treating them as legitimate
users. Kees Cook is working on sanitizing all these user cases,
by using kmalloc_size_roundup() to avoid ambiguous usages. And after
this is done, this special handling for ksize() can be removed.
In some cases, the free pointer could be saved inside the latter
part of object data area, which may overlap the redzone part(for
small sizes of kmalloc objects). As suggested by Hyeonggon Yoo,
force the free pointer to be in meta data area when kmalloc redzone
debug is enabled, to make all kmalloc objects covered by redzone
check.
Suggested-by: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Feng Tang <feng.tang@intel.com>
Acked-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2022-10-21 11:24:05 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-06-07 16:40:12 +08:00
|
|
|
|
mm/slub: extend redzone check to extra allocated kmalloc space than requested
kmalloc will round up the request size to a fixed size (mostly power
of 2), so there could be a extra space than what is requested, whose
size is the actual buffer size minus original request size.
To better detect out of bound access or abuse of this space, add
redzone sanity check for it.
In current kernel, some kmalloc user already knows the existence of
the space and utilizes it after calling 'ksize()' to know the real
size of the allocated buffer. So we skip the sanity check for objects
which have been called with ksize(), as treating them as legitimate
users. Kees Cook is working on sanitizing all these user cases,
by using kmalloc_size_roundup() to avoid ambiguous usages. And after
this is done, this special handling for ksize() can be removed.
In some cases, the free pointer could be saved inside the latter
part of object data area, which may overlap the redzone part(for
small sizes of kmalloc objects). As suggested by Hyeonggon Yoo,
force the free pointer to be in meta data area when kmalloc redzone
debug is enabled, to make all kmalloc objects covered by redzone
check.
Suggested-by: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Feng Tang <feng.tang@intel.com>
Acked-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2022-10-21 11:24:05 +08:00
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2012-06-13 10:24:57 -05:00
|
|
|
|
2024-06-07 16:40:12 +08:00
|
|
|
|
2013-07-15 09:05:29 +08:00
|
|
|
|
2024-06-07 16:40:12 +08:00
|
|
|
|
|
|
|
|
|
2008-02-05 17:57:39 -08:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
slub, kasan: improve interaction of KASAN and slub_debug poisoning
When both KASAN and slub_debug are enabled, when a free object is being
prepared in setup_object, slub_debug poisons the object data before KASAN
initializes its per-object metadata.
Right now, in setup_object, KASAN only initializes the alloc metadata,
which is always stored outside of the object. slub_debug is aware of this
and it skips poisoning and checking that memory area.
However, with the following patch in this series, KASAN also starts
initializing its free medata in setup_object. As this metadata might be
stored within the object, this initialization might overwrite the
slub_debug poisoning. This leads to slub_debug reports.
Thus, skip checking slub_debug poisoning of the object data area that
overlaps with the in-object KASAN free metadata.
Also make slub_debug poisoning of tail kmalloc redzones more precise when
KASAN is enabled: slub_debug can still poison and check the tail kmalloc
allocation area that comes after the KASAN free metadata.
Link: https://lkml.kernel.org/r/20231122231202.121277-1-andrey.konovalov@linux.dev
Signed-off-by: Andrey Konovalov <andreyknvl@google.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Evgenii Stepanov <eugenis@google.com>
Cc: Feng Tang <feng.tang@intel.com>
Cc: Marco Elver <elver@google.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-11-23 00:12:02 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-06-07 16:40:12 +08:00
|
|
|
|
slub, kasan: improve interaction of KASAN and slub_debug poisoning
When both KASAN and slub_debug are enabled, when a free object is being
prepared in setup_object, slub_debug poisons the object data before KASAN
initializes its per-object metadata.
Right now, in setup_object, KASAN only initializes the alloc metadata,
which is always stored outside of the object. slub_debug is aware of this
and it skips poisoning and checking that memory area.
However, with the following patch in this series, KASAN also starts
initializing its free medata in setup_object. As this metadata might be
stored within the object, this initialization might overwrite the
slub_debug poisoning. This leads to slub_debug reports.
Thus, skip checking slub_debug poisoning of the object data area that
overlaps with the in-object KASAN free metadata.
Also make slub_debug poisoning of tail kmalloc redzones more precise when
KASAN is enabled: slub_debug can still poison and check the tail kmalloc
allocation area that comes after the KASAN free metadata.
Link: https://lkml.kernel.org/r/20231122231202.121277-1-andrey.konovalov@linux.dev
Signed-off-by: Andrey Konovalov <andreyknvl@google.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Evgenii Stepanov <eugenis@google.com>
Cc: Feng Tang <feng.tang@intel.com>
Cc: Marco Elver <elver@google.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-11-23 00:12:02 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-06-07 16:40:12 +08:00
|
|
|
|
slub, kasan: improve interaction of KASAN and slub_debug poisoning
When both KASAN and slub_debug are enabled, when a free object is being
prepared in setup_object, slub_debug poisons the object data before KASAN
initializes its per-object metadata.
Right now, in setup_object, KASAN only initializes the alloc metadata,
which is always stored outside of the object. slub_debug is aware of this
and it skips poisoning and checking that memory area.
However, with the following patch in this series, KASAN also starts
initializing its free medata in setup_object. As this metadata might be
stored within the object, this initialization might overwrite the
slub_debug poisoning. This leads to slub_debug reports.
Thus, skip checking slub_debug poisoning of the object data area that
overlaps with the in-object KASAN free metadata.
Also make slub_debug poisoning of tail kmalloc redzones more precise when
KASAN is enabled: slub_debug can still poison and check the tail kmalloc
allocation area that comes after the KASAN free metadata.
Link: https://lkml.kernel.org/r/20231122231202.121277-1-andrey.konovalov@linux.dev
Signed-off-by: Andrey Konovalov <andreyknvl@google.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Evgenii Stepanov <eugenis@google.com>
Cc: Feng Tang <feng.tang@intel.com>
Cc: Marco Elver <elver@google.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-11-23 00:12:02 +01:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-06-07 16:40:12 +08:00
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
2024-06-07 16:40:12 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2008-12-05 14:08:08 +11:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2007-05-09 02:32:39 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2008-03-01 13:40:44 -08:00
|
|
|
|
2024-06-07 16:40:12 +08:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2024-06-07 16:40:12 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2008-04-14 19:11:30 +03:00
|
|
|
|
|
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
2008-04-14 19:11:30 +03:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-04-14 19:11:30 +03:00
|
|
|
|
|
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
2024-10-18 14:44:35 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-11-15 16:55:15 +01:00
|
|
|
|
2007-05-09 02:32:39 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
2011-06-01 12:25:53 -05:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
mm: slub: fix format mismatches in slab_err() callers
Adding __printf(3, 4) to slab_err exposed following:
mm/slub.c: In function `check_slab':
mm/slub.c:852:4: warning: format `%u' expects argument of type `unsigned int', but argument 4 has type `const char *' [-Wformat=]
s->name, page->objects, maxobj);
^
mm/slub.c:852:4: warning: too many arguments for format [-Wformat-extra-args]
mm/slub.c:857:4: warning: format `%u' expects argument of type `unsigned int', but argument 4 has type `const char *' [-Wformat=]
s->name, page->inuse, page->objects);
^
mm/slub.c:857:4: warning: too many arguments for format [-Wformat-extra-args]
mm/slub.c: In function `on_freelist':
mm/slub.c:905:4: warning: format `%d' expects argument of type `int', but argument 5 has type `long unsigned int' [-Wformat=]
"should be %d", page->objects, max_objects);
Fix first two warnings by removing redundant s->name.
Fix the last by changing type of max_object from unsigned long to int.
Signed-off-by: Andrey Ryabinin <a.ryabinin@samsung.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Acked-by: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-12-10 15:42:22 -08:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2008-03-01 13:40:44 -08:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-07-17 04:03:18 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2008-10-22 23:00:38 +04:00
|
|
|
|
|
|
|
|
|
2008-04-14 19:11:31 +03:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-06-28 19:34:49 -07:00
|
|
|
|
2008-04-14 19:11:31 +03:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-06-28 19:34:49 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2008-04-29 16:11:12 -07:00
|
|
|
|
2007-05-16 22:11:00 -07:00
|
|
|
|
|
|
|
|
|
2014-06-04 16:06:34 -07:00
|
|
|
|
2007-05-16 22:11:00 -07:00
|
|
|
|
|
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
|
|
|
|
|
2007-05-16 22:11:00 -07:00
|
|
|
|
|
|
|
|
|
2017-01-24 15:18:02 -08:00
|
|
|
|
2013-07-15 09:05:29 +08:00
|
|
|
|
2007-05-16 22:11:00 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:42 -07:00
|
|
|
|
2007-05-09 02:32:39 -07:00
|
|
|
|
2007-05-06 14:49:42 -07:00
|
|
|
|
2011-06-01 12:25:50 -05:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2007-05-06 14:49:42 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2014-02-10 14:25:39 -08:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2011-06-01 12:25:50 -05:00
|
|
|
|
|
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2011-06-01 12:25:50 -05:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:42 -07:00
|
|
|
|
2014-02-10 14:25:39 -08:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2007-05-06 14:49:42 -07:00
|
|
|
|
|
|
|
|
|
2009-06-11 14:08:48 +04:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-04-14 19:11:40 +03:00
|
|
|
|
2008-04-14 18:53:02 +03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-02-22 13:02:33 +00:00
|
|
|
|
|
|
|
|
|
2008-04-14 18:53:02 +03:00
|
|
|
|
2008-04-14 19:11:40 +03:00
|
|
|
|
2008-04-14 18:53:02 +03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-04-14 19:11:40 +03:00
|
|
|
|
2008-04-14 18:53:02 +03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-04-11 16:25:34 +09:00
|
|
|
|
2007-05-16 22:11:00 -07:00
|
|
|
|
2020-08-06 23:18:58 -07:00
|
|
|
|
2007-05-16 22:11:00 -07:00
|
|
|
|
|
|
|
|
|
2010-09-29 07:15:01 -05:00
|
|
|
|
2007-05-16 22:11:00 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2019-09-23 15:34:25 -07:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2019-02-20 22:19:23 -08:00
|
|
|
|
2020-08-06 23:18:58 -07:00
|
|
|
|
2019-02-20 22:19:23 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2019-02-20 22:19:23 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-03-15 14:55:06 -07:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2016-03-15 14:55:06 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
|
|
|
|
|
2016-03-15 14:55:06 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2016-03-15 14:55:06 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-11-21 16:06:38 +01:00
|
|
|
|
mm/slub: enable debugging memory wasting of kmalloc
kmalloc's API family is critical for mm, with one nature that it will
round up the request size to a fixed one (mostly power of 2). Say
when user requests memory for '2^n + 1' bytes, actually 2^(n+1) bytes
could be allocated, so in worst case, there is around 50% memory
space waste.
The wastage is not a big issue for requests that get allocated/freed
quickly, but may cause problems with objects that have longer life
time.
We've met a kernel boot OOM panic (v5.10), and from the dumped slab
info:
[ 26.062145] kmalloc-2k 814056KB 814056KB
From debug we found there are huge number of 'struct iova_magazine',
whose size is 1032 bytes (1024 + 8), so each allocation will waste
1016 bytes. Though the issue was solved by giving the right (bigger)
size of RAM, it is still nice to optimize the size (either use a
kmalloc friendly size or create a dedicated slab for it).
And from lkml archive, there was another crash kernel OOM case [1]
back in 2019, which seems to be related with the similar slab waste
situation, as the log is similar:
[ 4.332648] iommu: Adding device 0000:20:02.0 to group 16
[ 4.338946] swapper/0 invoked oom-killer: gfp_mask=0x6040c0(GFP_KERNEL|__GFP_COMP), nodemask=(null), order=0, oom_score_adj=0
...
[ 4.857565] kmalloc-2048 59164KB 59164KB
The crash kernel only has 256M memory, and 59M is pretty big here.
(Note: the related code has been changed and optimised in recent
kernel [2], these logs are just picked to demo the problem, also
a patch changing its size to 1024 bytes has been merged)
So add an way to track each kmalloc's memory waste info, and
leverage the existing SLUB debug framework (specifically
SLUB_STORE_USER) to show its call stack of original allocation,
so that user can evaluate the waste situation, identify some hot
spots and optimize accordingly, for a better utilization of memory.
The waste info is integrated into existing interface:
'/sys/kernel/debug/slab/kmalloc-xx/alloc_traces', one example of
'kmalloc-4k' after boot is:
126 ixgbe_alloc_q_vector+0xbe/0x830 [ixgbe] waste=233856/1856 age=280763/281414/282065 pid=1330 cpus=32 nodes=1
__kmem_cache_alloc_node+0x11f/0x4e0
__kmalloc_node+0x4e/0x140
ixgbe_alloc_q_vector+0xbe/0x830 [ixgbe]
ixgbe_init_interrupt_scheme+0x2ae/0xc90 [ixgbe]
ixgbe_probe+0x165f/0x1d20 [ixgbe]
local_pci_probe+0x78/0xc0
work_for_cpu_fn+0x26/0x40
...
which means in 'kmalloc-4k' slab, there are 126 requests of
2240 bytes which got a 4KB space (wasting 1856 bytes each
and 233856 bytes in total), from ixgbe_alloc_q_vector().
And when system starts some real workload like multiple docker
instances, there could are more severe waste.
[1]. https://lkml.org/lkml/2019/8/12/266
[2]. https://lore.kernel.org/lkml/2920df89-9975-5785-f79b-257d3052dfaf@huawei.com/
[Thanks Hyeonggon for pointing out several bugs about sorting/format]
[Thanks Vlastimil for suggesting way to reduce memory usage of
orig_size and keep it only for kmalloc objects]
Signed-off-by: Feng Tang <feng.tang@intel.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Robin Murphy <robin.murphy@arm.com>
Cc: John Garry <john.garry@huawei.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2022-09-13 14:54:20 +08:00
|
|
|
|
2016-03-15 14:55:06 -07:00
|
|
|
|
|
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2016-03-15 14:55:06 -07:00
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
mm/slub: restrict sysfs validation to debug caches and make it safe
Rongwei Wang reports [1] that cache validation triggered by writing to
/sys/kernel/slab/<cache>/validate is racy against normal cache
operations (e.g. freeing) in a way that can cause false positive
inconsistency reports for caches with debugging enabled. The problem is
that debugging actions that mark object free or active and actual
freelist operations are not atomic, and the validation can see an
inconsistent state.
For caches that do or don't have debugging enabled, additional races
involving n->nr_slabs are possible that result in false reports of wrong
slab counts.
This patch attempts to solve these issues while not adding overhead to
normal (especially fastpath) operations for caches that do not have
debugging enabled. Such overhead would not be justified to make possible
userspace-triggered validation safe. Instead, disable the validation for
caches that don't have debugging enabled and make their sysfs validate
handler return -EINVAL.
For caches that do have debugging enabled, we can instead extend the
existing approach of not using percpu freelists to force all alloc/free
operations to the slow paths where debugging flags is checked and acted
upon. There can adjust the debug-specific paths to increase n->list_lock
coverage against concurrent validation as necessary.
The processing on free in free_debug_processing() already happens under
n->list_lock so we can extend it to actually do the freeing as well and
thus make it atomic against concurrent validation. As observed by
Hyeonggon Yoo, we do not really need to take slab_lock() anymore here
because all paths we could race with are protected by n->list_lock under
the new scheme, so drop its usage here.
The processing on alloc in alloc_debug_processing() currently doesn't
take any locks, but we have to first allocate the object from a slab on
the partial list (as debugging caches have no percpu slabs) and thus
take the n->list_lock anyway. Add a function alloc_single_from_partial()
that grabs just the allocated object instead of the whole freelist, and
does the debug processing. The n->list_lock coverage again makes it
atomic against validation and it is also ultimately more efficient than
the current grabbing of freelist immediately followed by slab
deactivation.
To prevent races on n->nr_slabs updates, make sure that for caches with
debugging enabled, inc_slabs_node() or dec_slabs_node() is called under
n->list_lock. When allocating a new slab for a debug cache, handle the
allocation by a new function alloc_single_from_new_slab() instead of the
current forced deactivation path.
Neither of these changes affect the fast paths at all. The changes in
slow paths are negligible for non-debug caches.
[1] https://lore.kernel.org/all/20220529081535.69275-1-rongwei.wang@linux.alibaba.com/
Reported-by: Rongwei Wang <rongwei.wang@linux.alibaba.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
2022-08-23 19:03:57 +02:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
mm/slub: enable debugging memory wasting of kmalloc
kmalloc's API family is critical for mm, with one nature that it will
round up the request size to a fixed one (mostly power of 2). Say
when user requests memory for '2^n + 1' bytes, actually 2^(n+1) bytes
could be allocated, so in worst case, there is around 50% memory
space waste.
The wastage is not a big issue for requests that get allocated/freed
quickly, but may cause problems with objects that have longer life
time.
We've met a kernel boot OOM panic (v5.10), and from the dumped slab
info:
[ 26.062145] kmalloc-2k 814056KB 814056KB
From debug we found there are huge number of 'struct iova_magazine',
whose size is 1032 bytes (1024 + 8), so each allocation will waste
1016 bytes. Though the issue was solved by giving the right (bigger)
size of RAM, it is still nice to optimize the size (either use a
kmalloc friendly size or create a dedicated slab for it).
And from lkml archive, there was another crash kernel OOM case [1]
back in 2019, which seems to be related with the similar slab waste
situation, as the log is similar:
[ 4.332648] iommu: Adding device 0000:20:02.0 to group 16
[ 4.338946] swapper/0 invoked oom-killer: gfp_mask=0x6040c0(GFP_KERNEL|__GFP_COMP), nodemask=(null), order=0, oom_score_adj=0
...
[ 4.857565] kmalloc-2048 59164KB 59164KB
The crash kernel only has 256M memory, and 59M is pretty big here.
(Note: the related code has been changed and optimised in recent
kernel [2], these logs are just picked to demo the problem, also
a patch changing its size to 1024 bytes has been merged)
So add an way to track each kmalloc's memory waste info, and
leverage the existing SLUB debug framework (specifically
SLUB_STORE_USER) to show its call stack of original allocation,
so that user can evaluate the waste situation, identify some hot
spots and optimize accordingly, for a better utilization of memory.
The waste info is integrated into existing interface:
'/sys/kernel/debug/slab/kmalloc-xx/alloc_traces', one example of
'kmalloc-4k' after boot is:
126 ixgbe_alloc_q_vector+0xbe/0x830 [ixgbe] waste=233856/1856 age=280763/281414/282065 pid=1330 cpus=32 nodes=1
__kmem_cache_alloc_node+0x11f/0x4e0
__kmalloc_node+0x4e/0x140
ixgbe_alloc_q_vector+0xbe/0x830 [ixgbe]
ixgbe_init_interrupt_scheme+0x2ae/0xc90 [ixgbe]
ixgbe_probe+0x165f/0x1d20 [ixgbe]
local_pci_probe+0x78/0xc0
work_for_cpu_fn+0x26/0x40
...
which means in 'kmalloc-4k' slab, there are 126 requests of
2240 bytes which got a 4KB space (wasting 1856 bytes each
and 233856 bytes in total), from ixgbe_alloc_q_vector().
And when system starts some real workload like multiple docker
instances, there could are more severe waste.
[1]. https://lkml.org/lkml/2019/8/12/266
[2]. https://lore.kernel.org/lkml/2920df89-9975-5785-f79b-257d3052dfaf@huawei.com/
[Thanks Hyeonggon for pointing out several bugs about sorting/format]
[Thanks Vlastimil for suggesting way to reduce memory usage of
orig_size and keep it only for kmalloc objects]
Signed-off-by: Feng Tang <feng.tang@intel.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Robin Murphy <robin.murphy@arm.com>
Cc: John Garry <john.garry@huawei.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2022-09-13 14:54:20 +08:00
|
|
|
|
2010-09-29 07:15:01 -05:00
|
|
|
|
2022-11-21 16:06:38 +01:00
|
|
|
|
2007-05-16 22:11:00 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-09 02:32:39 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2007-07-17 04:03:18 -07:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
|
|
|
|
|
2024-10-18 14:44:35 +08:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2022-11-21 16:06:38 +01:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
2016-03-15 14:55:06 -07:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2016-03-15 14:55:06 -07:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
|
|
|
|
|
2016-03-15 14:55:06 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
|
|
|
|
|
2016-03-15 14:55:06 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2016-03-15 14:55:06 -07:00
|
|
|
|
|
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-03-17 14:19:47 -07:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2016-03-15 14:55:06 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2016-03-15 14:55:06 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-08-06 23:18:35 -07:00
|
|
|
|
2023-12-15 11:41:48 +08:00
|
|
|
|
2020-08-06 23:18:35 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-12-15 11:41:48 +08:00
|
|
|
|
2020-08-06 23:18:35 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-09 02:32:44 -07:00
|
|
|
|
|
|
|
|
|
2020-08-06 23:18:35 -07:00
|
|
|
|
2021-08-13 16:54:34 -07:00
|
|
|
|
2020-08-06 23:18:35 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-08-13 16:54:34 -07:00
|
|
|
|
2007-07-15 23:38:14 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-09 02:32:44 -07:00
|
|
|
|
2020-08-06 23:18:35 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-07-15 23:38:14 -07:00
|
|
|
|
2020-08-06 23:18:35 -07:00
|
|
|
|
2021-08-13 16:54:34 -07:00
|
|
|
|
2020-08-06 23:18:35 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-07-07 18:07:47 -07:00
|
|
|
|
2023-02-10 22:15:51 +01:00
|
|
|
|
2007-07-15 23:38:14 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-08-06 23:18:35 -07:00
|
|
|
|
|
|
|
|
|
2021-08-13 16:54:34 -07:00
|
|
|
|
2023-12-15 11:41:48 +08:00
|
|
|
|
2021-08-13 16:54:34 -07:00
|
|
|
|
2020-08-06 23:18:35 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-08-13 16:54:34 -07:00
|
|
|
|
2020-08-06 23:18:35 -07:00
|
|
|
|
|
|
|
|
|
2007-07-15 23:38:14 -07:00
|
|
|
|
2021-08-13 16:54:34 -07:00
|
|
|
|
2021-07-07 18:07:47 -07:00
|
|
|
|
2023-02-10 22:15:51 +01:00
|
|
|
|
2020-08-06 23:18:51 -07:00
|
|
|
|
|
|
|
|
|
2021-06-28 19:34:43 -07:00
|
|
|
|
|
|
|
|
|
mm: security: introduce init_on_alloc=1 and init_on_free=1 boot options
Patch series "add init_on_alloc/init_on_free boot options", v10.
Provide init_on_alloc and init_on_free boot options.
These are aimed at preventing possible information leaks and making the
control-flow bugs that depend on uninitialized values more deterministic.
Enabling either of the options guarantees that the memory returned by the
page allocator and SL[AU]B is initialized with zeroes. SLOB allocator
isn't supported at the moment, as its emulation of kmem caches complicates
handling of SLAB_TYPESAFE_BY_RCU caches correctly.
Enabling init_on_free also guarantees that pages and heap objects are
initialized right after they're freed, so it won't be possible to access
stale data by using a dangling pointer.
As suggested by Michal Hocko, right now we don't let the heap users to
disable initialization for certain allocations. There's not enough
evidence that doing so can speed up real-life cases, and introducing ways
to opt-out may result in things going out of control.
This patch (of 2):
The new options are needed to prevent possible information leaks and make
control-flow bugs that depend on uninitialized values more deterministic.
This is expected to be on-by-default on Android and Chrome OS. And it
gives the opportunity for anyone else to use it under distros too via the
boot args. (The init_on_free feature is regularly requested by folks
where memory forensics is included in their threat models.)
init_on_alloc=1 makes the kernel initialize newly allocated pages and heap
objects with zeroes. Initialization is done at allocation time at the
places where checks for __GFP_ZERO are performed.
init_on_free=1 makes the kernel initialize freed pages and heap objects
with zeroes upon their deletion. This helps to ensure sensitive data
doesn't leak via use-after-free accesses.
Both init_on_alloc=1 and init_on_free=1 guarantee that the allocator
returns zeroed memory. The two exceptions are slab caches with
constructors and SLAB_TYPESAFE_BY_RCU flag. Those are never
zero-initialized to preserve their semantics.
Both init_on_alloc and init_on_free default to zero, but those defaults
can be overridden with CONFIG_INIT_ON_ALLOC_DEFAULT_ON and
CONFIG_INIT_ON_FREE_DEFAULT_ON.
If either SLUB poisoning or page poisoning is enabled, those options take
precedence over init_on_alloc and init_on_free: initialization is only
applied to unpoisoned allocations.
Slowdown for the new features compared to init_on_free=0, init_on_alloc=0:
hackbench, init_on_free=1: +7.62% sys time (st.err 0.74%)
hackbench, init_on_alloc=1: +7.75% sys time (st.err 2.14%)
Linux build with -j12, init_on_free=1: +8.38% wall time (st.err 0.39%)
Linux build with -j12, init_on_free=1: +24.42% sys time (st.err 0.52%)
Linux build with -j12, init_on_alloc=1: -0.13% wall time (st.err 0.42%)
Linux build with -j12, init_on_alloc=1: +0.57% sys time (st.err 0.40%)
The slowdown for init_on_free=0, init_on_alloc=0 compared to the baseline
is within the standard error.
The new features are also going to pave the way for hardware memory
tagging (e.g. arm64's MTE), which will require both on_alloc and on_free
hooks to set the tags for heap objects. With MTE, tagging will have the
same cost as memory initialization.
Although init_on_free is rather costly, there are paranoid use-cases where
in-memory data lifetime is desired to be minimized. There are various
arguments for/against the realism of the associated threat models, but
given that we'll need the infrastructure for MTE anyway, and there are
people who want wipe-on-free behavior no matter what the performance cost,
it seems reasonable to include it in this series.
[glider@google.com: v8]
Link: http://lkml.kernel.org/r/20190626121943.131390-2-glider@google.com
[glider@google.com: v9]
Link: http://lkml.kernel.org/r/20190627130316.254309-2-glider@google.com
[glider@google.com: v10]
Link: http://lkml.kernel.org/r/20190628093131.199499-2-glider@google.com
Link: http://lkml.kernel.org/r/20190617151050.92663-2-glider@google.com
Signed-off-by: Alexander Potapenko <glider@google.com>
Acked-by: Kees Cook <keescook@chromium.org>
Acked-by: Michal Hocko <mhocko@suse.cz> [page and dmapool parts
Acked-by: James Morris <jamorris@linux.microsoft.com>]
Cc: Christoph Lameter <cl@linux.com>
Cc: Masahiro Yamada <yamada.masahiro@socionext.com>
Cc: "Serge E. Hallyn" <serge@hallyn.com>
Cc: Nick Desaulniers <ndesaulniers@google.com>
Cc: Kostya Serebryany <kcc@google.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Sandeep Patil <sspatil@android.com>
Cc: Laura Abbott <labbott@redhat.com>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Jann Horn <jannh@google.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Marco Elver <elver@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-07-11 20:59:19 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-09 02:32:44 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-12-15 11:41:48 +08:00
|
|
|
|
|
|
|
|
|
2007-05-09 02:32:44 -07:00
|
|
|
|
2018-10-26 15:03:15 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-12-15 11:41:48 +08:00
|
|
|
|
2018-10-26 15:03:15 -07:00
|
|
|
|
|
|
|
|
|
2024-02-21 12:12:53 +00:00
|
|
|
|
2007-05-09 02:32:44 -07:00
|
|
|
|
2018-10-26 15:03:15 -07:00
|
|
|
|
|
|
|
|
|
2020-08-06 23:18:35 -07:00
|
|
|
|
|
|
|
|
|
2021-02-24 12:01:04 -08:00
|
|
|
|
|
|
|
|
|
2022-04-06 15:00:03 +09:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-02-24 12:01:04 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-10-26 15:03:15 -07:00
|
|
|
|
|
|
|
|
|
2020-08-06 23:18:35 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-10-26 15:03:15 -07:00
|
|
|
|
2020-08-06 23:18:35 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-10-26 15:03:15 -07:00
|
|
|
|
2020-08-06 23:18:35 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-10-26 15:03:15 -07:00
|
|
|
|
2020-08-06 23:18:35 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-10-26 15:03:15 -07:00
|
|
|
|
|
|
|
|
|
2007-09-11 15:24:11 -07:00
|
|
|
|
2021-02-24 12:01:04 -08:00
|
|
|
|
2007-05-09 02:32:44 -07:00
|
|
|
|
2015-11-20 15:57:41 -08:00
|
|
|
|
2022-04-11 16:25:34 +09:00
|
|
|
|
2019-09-23 15:34:25 -07:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2007-05-09 02:32:44 -07:00
|
|
|
|
2022-11-21 16:06:38 +01:00
|
|
|
|
|
|
|
|
|
2007-05-09 02:32:44 -07:00
|
|
|
|
2022-11-21 16:06:38 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-09 02:32:44 -07:00
|
|
|
|
2022-04-19 20:03:52 +08:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2010-09-29 07:15:01 -05:00
|
|
|
|
2022-11-21 16:06:38 +01:00
|
|
|
|
mm/slub: restrict sysfs validation to debug caches and make it safe
Rongwei Wang reports [1] that cache validation triggered by writing to
/sys/kernel/slab/<cache>/validate is racy against normal cache
operations (e.g. freeing) in a way that can cause false positive
inconsistency reports for caches with debugging enabled. The problem is
that debugging actions that mark object free or active and actual
freelist operations are not atomic, and the validation can see an
inconsistent state.
For caches that do or don't have debugging enabled, additional races
involving n->nr_slabs are possible that result in false reports of wrong
slab counts.
This patch attempts to solve these issues while not adding overhead to
normal (especially fastpath) operations for caches that do not have
debugging enabled. Such overhead would not be justified to make possible
userspace-triggered validation safe. Instead, disable the validation for
caches that don't have debugging enabled and make their sysfs validate
handler return -EINVAL.
For caches that do have debugging enabled, we can instead extend the
existing approach of not using percpu freelists to force all alloc/free
operations to the slow paths where debugging flags is checked and acted
upon. There can adjust the debug-specific paths to increase n->list_lock
coverage against concurrent validation as necessary.
The processing on free in free_debug_processing() already happens under
n->list_lock so we can extend it to actually do the freeing as well and
thus make it atomic against concurrent validation. As observed by
Hyeonggon Yoo, we do not really need to take slab_lock() anymore here
because all paths we could race with are protected by n->list_lock under
the new scheme, so drop its usage here.
The processing on alloc in alloc_debug_processing() currently doesn't
take any locks, but we have to first allocate the object from a slab on
the partial list (as debugging caches have no percpu slabs) and thus
take the n->list_lock anyway. Add a function alloc_single_from_partial()
that grabs just the allocated object instead of the whole freelist, and
does the debug processing. The n->list_lock coverage again makes it
atomic against validation and it is also ultimately more efficient than
the current grabbing of freelist immediately followed by slab
deactivation.
To prevent races on n->nr_slabs updates, make sure that for caches with
debugging enabled, inc_slabs_node() or dec_slabs_node() is called under
n->list_lock. When allocating a new slab for a debug cache, handle the
allocation by a new function alloc_single_from_new_slab() instead of the
current forced deactivation path.
Neither of these changes affect the fast paths at all. The changes in
slow paths are negligible for non-debug caches.
[1] https://lore.kernel.org/all/20220529081535.69275-1-rongwei.wang@linux.alibaba.com/
Reported-by: Rongwei Wang <rongwei.wang@linux.alibaba.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
2022-08-23 19:03:57 +02:00
|
|
|
|
|
|
|
|
|
2011-06-01 12:25:50 -05:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2014-01-10 13:23:49 +01:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2024-02-21 12:12:53 +00:00
|
|
|
|
2007-09-11 15:24:11 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-09 02:32:44 -07:00
|
|
|
|
2008-04-14 18:53:02 +03:00
|
|
|
|
2009-09-15 11:00:26 +02:00
|
|
|
|
|
|
|
|
|
2009-06-11 14:08:48 +04:00
|
|
|
|
|
|
|
|
|
2008-04-14 19:11:40 +03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-11-15 18:14:31 +01:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2020-09-04 16:35:30 -07:00
|
|
|
|
2020-06-01 21:45:47 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-11-15 18:14:31 +01:00
|
|
|
|
2014-08-06 16:04:18 -07:00
|
|
|
|
|
|
|
|
|
2024-03-21 09:36:28 -07:00
|
|
|
|
|
|
|
|
|
2024-03-21 09:36:55 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-10-03 14:52:47 +02:00
|
|
|
|
2024-03-21 09:36:55 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-10-03 14:52:47 +02:00
|
|
|
|
|
|
|
|
|
2024-03-21 09:36:57 -07:00
|
|
|
|
2023-10-03 14:52:47 +02:00
|
|
|
|
2024-03-21 09:36:57 -07:00
|
|
|
|
2023-10-03 14:52:47 +02:00
|
|
|
|
|
|
|
|
|
2024-03-21 09:36:57 -07:00
|
|
|
|
|
|
|
|
|
2023-10-03 14:52:47 +02:00
|
|
|
|
|
|
|
|
|
2024-03-21 09:36:57 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-10-03 14:52:47 +02:00
|
|
|
|
2024-03-21 09:36:57 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-10-03 14:52:47 +02:00
|
|
|
|
|
|
|
|
|
2024-03-21 09:36:55 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-03-21 09:36:57 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-03-21 09:36:55 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-10-03 14:52:47 +02:00
|
|
|
|
2024-03-21 09:36:28 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-10-03 14:52:47 +02:00
|
|
|
|
2024-03-21 09:36:28 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-03-26 11:37:39 +01:00
|
|
|
|
|
|
|
|
|
2023-10-03 14:52:47 +02:00
|
|
|
|
2024-03-21 09:36:28 -07:00
|
|
|
|
2024-03-21 09:36:57 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-10-03 14:52:47 +02:00
|
|
|
|
2024-03-21 09:36:28 -07:00
|
|
|
|
2024-03-21 09:36:29 -07:00
|
|
|
|
|
|
|
|
|
2024-03-21 09:36:28 -07:00
|
|
|
|
|
|
|
|
|
2024-03-21 09:36:57 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-10-03 14:52:47 +02:00
|
|
|
|
2024-03-21 09:36:57 -07:00
|
|
|
|
2023-10-03 14:52:47 +02:00
|
|
|
|
|
|
|
|
|
2024-03-21 09:36:57 -07:00
|
|
|
|
2024-03-21 09:36:28 -07:00
|
|
|
|
2024-03-21 09:36:57 -07:00
|
|
|
|
2024-03-21 09:36:28 -07:00
|
|
|
|
2024-05-27 15:30:06 -03:00
|
|
|
|
2024-03-21 09:36:57 -07:00
|
|
|
|
2024-03-21 09:36:28 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-03-21 09:36:57 -07:00
|
|
|
|
2024-05-27 15:30:06 -03:00
|
|
|
|
|
|
|
|
|
2024-03-21 09:36:28 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-03-21 09:36:55 -07:00
|
|
|
|
2024-03-21 09:36:28 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-10-03 14:52:47 +02:00
|
|
|
|
2024-03-21 09:36:28 -07:00
|
|
|
|
|
|
|
|
|
2023-10-03 14:52:47 +02:00
|
|
|
|
|
|
|
|
|
2024-03-21 09:36:28 -07:00
|
|
|
|
2023-11-13 18:04:05 +01:00
|
|
|
|
2024-03-21 09:36:28 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-03-21 09:36:55 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-03-21 09:36:28 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-03-21 09:36:45 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-07-01 11:31:15 -04:00
|
|
|
|
2024-03-21 09:36:45 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-07-11 10:02:16 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-03-21 09:36:45 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-04-25 13:55:23 -07:00
|
|
|
|
2024-03-21 09:36:45 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-07-04 06:59:41 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
mm/slub: add check for s->flags in the alloc_tagging_slab_free_hook
When enable CONFIG_MEMCG & CONFIG_KFENCE & CONFIG_KMEMLEAK, the following
warning always occurs,This is because the following call stack occurred:
mem_pool_alloc
kmem_cache_alloc_noprof
slab_alloc_node
kfence_alloc
Once the kfence allocation is successful,slab->obj_exts will not be empty,
because it has already been assigned a value in kfence_init_pool.
Since in the prepare_slab_obj_exts_hook function,we perform a check for
s->flags & (SLAB_NO_OBJ_EXT | SLAB_NOLEAKTRACE),the alloc_tag_add function
will not be called as a result.Therefore,ref->ct remains NULL.
However,when we call mem_pool_free,since obj_ext is not empty, it
eventually leads to the alloc_tag_sub scenario being invoked. This is
where the warning occurs.
So we should add corresponding checks in the alloc_tagging_slab_free_hook.
For __GFP_NO_OBJ_EXT case,I didn't see the specific case where it's using
kfence,so I won't add the corresponding check in
alloc_tagging_slab_free_hook for now.
[ 3.734349] ------------[ cut here ]------------
[ 3.734807] alloc_tag was not set
[ 3.735129] WARNING: CPU: 4 PID: 40 at ./include/linux/alloc_tag.h:130 kmem_cache_free+0x444/0x574
[ 3.735866] Modules linked in: autofs4
[ 3.736211] CPU: 4 UID: 0 PID: 40 Comm: ksoftirqd/4 Tainted: G W 6.11.0-rc3-dirty #1
[ 3.736969] Tainted: [W]=WARN
[ 3.737258] Hardware name: QEMU KVM Virtual Machine, BIOS unknown 2/2/2022
[ 3.737875] pstate: 60400005 (nZCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--)
[ 3.738501] pc : kmem_cache_free+0x444/0x574
[ 3.738951] lr : kmem_cache_free+0x444/0x574
[ 3.739361] sp : ffff80008357bb60
[ 3.739693] x29: ffff80008357bb70 x28: 0000000000000000 x27: 0000000000000000
[ 3.740338] x26: ffff80008207f000 x25: ffff000b2eb2fd60 x24: ffff0000c0005700
[ 3.740982] x23: ffff8000804229e4 x22: ffff800082080000 x21: ffff800081756000
[ 3.741630] x20: fffffd7ff8253360 x19: 00000000000000a8 x18: ffffffffffffffff
[ 3.742274] x17: ffff800ab327f000 x16: ffff800083398000 x15: ffff800081756df0
[ 3.742919] x14: 0000000000000000 x13: 205d344320202020 x12: 5b5d373038343337
[ 3.743560] x11: ffff80008357b650 x10: 000000000000005d x9 : 00000000ffffffd0
[ 3.744231] x8 : 7f7f7f7f7f7f7f7f x7 : ffff80008237bad0 x6 : c0000000ffff7fff
[ 3.744907] x5 : ffff80008237ba78 x4 : ffff8000820bbad0 x3 : 0000000000000001
[ 3.745580] x2 : 68d66547c09f7800 x1 : 68d66547c09f7800 x0 : 0000000000000000
[ 3.746255] Call trace:
[ 3.746530] kmem_cache_free+0x444/0x574
[ 3.746931] mem_pool_free+0x44/0xf4
[ 3.747306] free_object_rcu+0xc8/0xdc
[ 3.747693] rcu_do_batch+0x234/0x8a4
[ 3.748075] rcu_core+0x230/0x3e4
[ 3.748424] rcu_core_si+0x14/0x1c
[ 3.748780] handle_softirqs+0x134/0x378
[ 3.749189] run_ksoftirqd+0x70/0x9c
[ 3.749560] smpboot_thread_fn+0x148/0x22c
[ 3.749978] kthread+0x10c/0x118
[ 3.750323] ret_from_fork+0x10/0x20
[ 3.750696] ---[ end trace 0000000000000000 ]---
Link: https://lkml.kernel.org/r/20240816013336.17505-1-hao.ge@linux.dev
Fixes: 4b8736964640 ("mm/slab: add allocation accounting into slab allocation and free paths")
Signed-off-by: Hao Ge <gehao@kylinos.cn>
Cc: Christoph Lameter <cl@linux.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Kees Cook <kees@kernel.org>
Cc: Kent Overstreet <kent.overstreet@linux.dev>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2024-08-16 09:33:36 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-07-04 06:59:41 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-03-21 09:36:45 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-07-04 06:59:41 -07:00
|
|
|
|
|
|
|
|
|
2024-03-21 09:36:28 -07:00
|
|
|
|
2024-07-01 11:31:15 -04:00
|
|
|
|
2023-10-03 14:52:47 +02:00
|
|
|
|
2024-03-26 11:37:38 +01:00
|
|
|
|
|
|
|
|
|
2023-11-13 18:04:05 +01:00
|
|
|
|
2024-03-26 11:37:38 +01:00
|
|
|
|
|
|
|
|
|
2023-11-13 18:04:05 +01:00
|
|
|
|
2024-03-26 11:37:38 +01:00
|
|
|
|
2023-11-13 18:04:05 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-03-26 11:37:38 +01:00
|
|
|
|
|
|
|
|
|
2023-11-13 18:04:05 +01:00
|
|
|
|
2024-03-26 11:37:38 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-10-03 14:52:47 +02:00
|
|
|
|
|
|
|
|
|
2024-03-26 11:37:38 +01:00
|
|
|
|
2023-10-03 14:52:47 +02:00
|
|
|
|
2023-10-27 12:34:18 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-03-21 09:36:28 -07:00
|
|
|
|
2023-10-27 12:34:18 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-03-21 09:36:28 -07:00
|
|
|
|
|
|
|
|
|
2023-10-27 12:34:18 +02:00
|
|
|
|
|
|
|
|
|
2024-03-21 09:36:28 -07:00
|
|
|
|
2023-11-02 16:34:39 +01:00
|
|
|
|
2024-09-05 10:34:22 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-12-09 20:06:57 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-09-05 10:34:22 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-07-01 11:31:15 -04:00
|
|
|
|
2024-03-26 11:37:38 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-10-03 14:52:47 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-09-05 10:34:22 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-07-01 11:31:15 -04:00
|
|
|
|
2023-10-03 14:52:47 +02:00
|
|
|
|
2024-08-09 17:36:56 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2014-08-06 16:04:18 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-11-03 20:24:51 +01:00
|
|
|
|
|
|
|
|
|
2024-08-09 17:36:56 +02:00
|
|
|
|
|
|
|
|
|
2014-08-06 16:04:18 -07:00
|
|
|
|
2023-11-03 20:24:51 +01:00
|
|
|
|
2024-08-09 17:36:56 +02:00
|
|
|
|
|
|
|
|
|
2013-10-08 15:58:57 -07:00
|
|
|
|
2024-08-09 17:36:56 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-10-08 15:58:57 -07:00
|
|
|
|
2022-09-15 17:03:49 +02:00
|
|
|
|
2010-08-25 14:07:16 -05:00
|
|
|
|
2021-05-21 01:25:06 +02:00
|
|
|
|
2014-08-06 16:04:18 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-02-13 14:39:42 -08:00
|
|
|
|
2020-08-06 23:19:12 -07:00
|
|
|
|
2024-08-09 17:36:56 +02:00
|
|
|
|
2020-08-06 23:19:12 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-11-14 22:12:47 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-08-09 17:36:55 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-08-09 17:36:56 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-11-22 16:54:51 +01:00
|
|
|
|
2024-08-09 17:36:56 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-04-29 23:00:09 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-04-30 13:34:59 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-04-29 23:00:09 -07:00
|
|
|
|
2023-10-27 12:34:18 +02:00
|
|
|
|
2021-04-29 23:00:09 -07:00
|
|
|
|
mm, slub: avoid zeroing kmalloc redzone
Since commit 946fa0dbf2d8 ("mm/slub: extend redzone check to extra
allocated kmalloc space than requested"), setting orig_size treats
the wasted space (object_size - orig_size) as a redzone. However with
init_on_free=1 we clear the full object->size, including the redzone.
Additionally we clear the object metadata, including the stored orig_size,
making it zero, which makes check_object() treat the whole object as a
redzone.
These issues lead to the following BUG report with "slub_debug=FUZ
init_on_free=1":
[ 0.000000] =============================================================================
[ 0.000000] BUG kmalloc-8 (Not tainted): kmalloc Redzone overwritten
[ 0.000000] -----------------------------------------------------------------------------
[ 0.000000]
[ 0.000000] 0xffff000010032858-0xffff00001003285f @offset=2136. First byte 0x0 instead of 0xcc
[ 0.000000] FIX kmalloc-8: Restoring kmalloc Redzone 0xffff000010032858-0xffff00001003285f=0xcc
[ 0.000000] Slab 0xfffffdffc0400c80 objects=36 used=23 fp=0xffff000010032a18 flags=0x3fffe0000000200(workingset|node=0|zone=0|lastcpupid=0x1ffff)
[ 0.000000] Object 0xffff000010032858 @offset=2136 fp=0xffff0000100328c8
[ 0.000000]
[ 0.000000] Redzone ffff000010032850: cc cc cc cc cc cc cc cc ........
[ 0.000000] Object ffff000010032858: cc cc cc cc cc cc cc cc ........
[ 0.000000] Redzone ffff000010032860: cc cc cc cc cc cc cc cc ........
[ 0.000000] Padding ffff0000100328b4: 00 00 00 00 00 00 00 00 00 00 00 00 ............
[ 0.000000] CPU: 0 UID: 0 PID: 0 Comm: swapper/0 Not tainted 6.11.0-rc3-next-20240814-00004-g61844c55c3f4 #144
[ 0.000000] Hardware name: NXP i.MX95 19X19 board (DT)
[ 0.000000] Call trace:
[ 0.000000] dump_backtrace+0x90/0xe8
[ 0.000000] show_stack+0x18/0x24
[ 0.000000] dump_stack_lvl+0x74/0x8c
[ 0.000000] dump_stack+0x18/0x24
[ 0.000000] print_trailer+0x150/0x218
[ 0.000000] check_object+0xe4/0x454
[ 0.000000] free_to_partial_list+0x2f8/0x5ec
To address the issue, use orig_size to clear the used area. And restore
the value of orig_size after clear the remaining area.
When CONFIG_SLUB_DEBUG not defined, (get_orig_size()' directly returns
s->object_size. So when using memset to init the area, the size can simply
be orig_size, as orig_size returns object_size when CONFIG_SLUB_DEBUG not
enabled. And orig_size can never be bigger than object_size.
Fixes: 946fa0dbf2d8 ("mm/slub: extend redzone check to extra allocated kmalloc space than requested")
Cc: <stable@vger.kernel.org>
Reviewed-by: Feng Tang <feng.tang@intel.com>
Acked-by: David Rientjes <rientjes@google.com>
Signed-off-by: Peng Fan <peng.fan@nxp.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2024-08-29 11:29:11 +08:00
|
|
|
|
2021-04-29 23:00:09 -07:00
|
|
|
|
2024-04-30 13:34:59 +02:00
|
|
|
|
mm, slub: avoid zeroing kmalloc redzone
Since commit 946fa0dbf2d8 ("mm/slub: extend redzone check to extra
allocated kmalloc space than requested"), setting orig_size treats
the wasted space (object_size - orig_size) as a redzone. However with
init_on_free=1 we clear the full object->size, including the redzone.
Additionally we clear the object metadata, including the stored orig_size,
making it zero, which makes check_object() treat the whole object as a
redzone.
These issues lead to the following BUG report with "slub_debug=FUZ
init_on_free=1":
[ 0.000000] =============================================================================
[ 0.000000] BUG kmalloc-8 (Not tainted): kmalloc Redzone overwritten
[ 0.000000] -----------------------------------------------------------------------------
[ 0.000000]
[ 0.000000] 0xffff000010032858-0xffff00001003285f @offset=2136. First byte 0x0 instead of 0xcc
[ 0.000000] FIX kmalloc-8: Restoring kmalloc Redzone 0xffff000010032858-0xffff00001003285f=0xcc
[ 0.000000] Slab 0xfffffdffc0400c80 objects=36 used=23 fp=0xffff000010032a18 flags=0x3fffe0000000200(workingset|node=0|zone=0|lastcpupid=0x1ffff)
[ 0.000000] Object 0xffff000010032858 @offset=2136 fp=0xffff0000100328c8
[ 0.000000]
[ 0.000000] Redzone ffff000010032850: cc cc cc cc cc cc cc cc ........
[ 0.000000] Object ffff000010032858: cc cc cc cc cc cc cc cc ........
[ 0.000000] Redzone ffff000010032860: cc cc cc cc cc cc cc cc ........
[ 0.000000] Padding ffff0000100328b4: 00 00 00 00 00 00 00 00 00 00 00 00 ............
[ 0.000000] CPU: 0 UID: 0 PID: 0 Comm: swapper/0 Not tainted 6.11.0-rc3-next-20240814-00004-g61844c55c3f4 #144
[ 0.000000] Hardware name: NXP i.MX95 19X19 board (DT)
[ 0.000000] Call trace:
[ 0.000000] dump_backtrace+0x90/0xe8
[ 0.000000] show_stack+0x18/0x24
[ 0.000000] dump_stack_lvl+0x74/0x8c
[ 0.000000] dump_stack+0x18/0x24
[ 0.000000] print_trailer+0x150/0x218
[ 0.000000] check_object+0xe4/0x454
[ 0.000000] free_to_partial_list+0x2f8/0x5ec
To address the issue, use orig_size to clear the used area. And restore
the value of orig_size after clear the remaining area.
When CONFIG_SLUB_DEBUG not defined, (get_orig_size()' directly returns
s->object_size. So when using memset to init the area, the size can simply
be orig_size, as orig_size returns object_size when CONFIG_SLUB_DEBUG not
enabled. And orig_size can never be bigger than object_size.
Fixes: 946fa0dbf2d8 ("mm/slub: extend redzone check to extra allocated kmalloc space than requested")
Cc: <stable@vger.kernel.org>
Reviewed-by: Feng Tang <feng.tang@intel.com>
Acked-by: David Rientjes <rientjes@google.com>
Signed-off-by: Peng Fan <peng.fan@nxp.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2024-08-29 11:29:11 +08:00
|
|
|
|
2021-04-29 23:00:09 -07:00
|
|
|
|
mm, slub: avoid zeroing kmalloc redzone
Since commit 946fa0dbf2d8 ("mm/slub: extend redzone check to extra
allocated kmalloc space than requested"), setting orig_size treats
the wasted space (object_size - orig_size) as a redzone. However with
init_on_free=1 we clear the full object->size, including the redzone.
Additionally we clear the object metadata, including the stored orig_size,
making it zero, which makes check_object() treat the whole object as a
redzone.
These issues lead to the following BUG report with "slub_debug=FUZ
init_on_free=1":
[ 0.000000] =============================================================================
[ 0.000000] BUG kmalloc-8 (Not tainted): kmalloc Redzone overwritten
[ 0.000000] -----------------------------------------------------------------------------
[ 0.000000]
[ 0.000000] 0xffff000010032858-0xffff00001003285f @offset=2136. First byte 0x0 instead of 0xcc
[ 0.000000] FIX kmalloc-8: Restoring kmalloc Redzone 0xffff000010032858-0xffff00001003285f=0xcc
[ 0.000000] Slab 0xfffffdffc0400c80 objects=36 used=23 fp=0xffff000010032a18 flags=0x3fffe0000000200(workingset|node=0|zone=0|lastcpupid=0x1ffff)
[ 0.000000] Object 0xffff000010032858 @offset=2136 fp=0xffff0000100328c8
[ 0.000000]
[ 0.000000] Redzone ffff000010032850: cc cc cc cc cc cc cc cc ........
[ 0.000000] Object ffff000010032858: cc cc cc cc cc cc cc cc ........
[ 0.000000] Redzone ffff000010032860: cc cc cc cc cc cc cc cc ........
[ 0.000000] Padding ffff0000100328b4: 00 00 00 00 00 00 00 00 00 00 00 00 ............
[ 0.000000] CPU: 0 UID: 0 PID: 0 Comm: swapper/0 Not tainted 6.11.0-rc3-next-20240814-00004-g61844c55c3f4 #144
[ 0.000000] Hardware name: NXP i.MX95 19X19 board (DT)
[ 0.000000] Call trace:
[ 0.000000] dump_backtrace+0x90/0xe8
[ 0.000000] show_stack+0x18/0x24
[ 0.000000] dump_stack_lvl+0x74/0x8c
[ 0.000000] dump_stack+0x18/0x24
[ 0.000000] print_trailer+0x150/0x218
[ 0.000000] check_object+0xe4/0x454
[ 0.000000] free_to_partial_list+0x2f8/0x5ec
To address the issue, use orig_size to clear the used area. And restore
the value of orig_size after clear the remaining area.
When CONFIG_SLUB_DEBUG not defined, (get_orig_size()' directly returns
s->object_size. So when using memset to init the area, the size can simply
be orig_size, as orig_size returns object_size when CONFIG_SLUB_DEBUG not
enabled. And orig_size can never be bigger than object_size.
Fixes: 946fa0dbf2d8 ("mm/slub: extend redzone check to extra allocated kmalloc space than requested")
Cc: <stable@vger.kernel.org>
Reviewed-by: Feng Tang <feng.tang@intel.com>
Acked-by: David Rientjes <rientjes@google.com>
Signed-off-by: Peng Fan <peng.fan@nxp.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2024-08-29 11:29:11 +08:00
|
|
|
|
2021-04-29 23:00:09 -07:00
|
|
|
|
2024-04-30 13:34:59 +02:00
|
|
|
|
|
|
|
|
|
mm, slub: avoid zeroing kmalloc redzone
Since commit 946fa0dbf2d8 ("mm/slub: extend redzone check to extra
allocated kmalloc space than requested"), setting orig_size treats
the wasted space (object_size - orig_size) as a redzone. However with
init_on_free=1 we clear the full object->size, including the redzone.
Additionally we clear the object metadata, including the stored orig_size,
making it zero, which makes check_object() treat the whole object as a
redzone.
These issues lead to the following BUG report with "slub_debug=FUZ
init_on_free=1":
[ 0.000000] =============================================================================
[ 0.000000] BUG kmalloc-8 (Not tainted): kmalloc Redzone overwritten
[ 0.000000] -----------------------------------------------------------------------------
[ 0.000000]
[ 0.000000] 0xffff000010032858-0xffff00001003285f @offset=2136. First byte 0x0 instead of 0xcc
[ 0.000000] FIX kmalloc-8: Restoring kmalloc Redzone 0xffff000010032858-0xffff00001003285f=0xcc
[ 0.000000] Slab 0xfffffdffc0400c80 objects=36 used=23 fp=0xffff000010032a18 flags=0x3fffe0000000200(workingset|node=0|zone=0|lastcpupid=0x1ffff)
[ 0.000000] Object 0xffff000010032858 @offset=2136 fp=0xffff0000100328c8
[ 0.000000]
[ 0.000000] Redzone ffff000010032850: cc cc cc cc cc cc cc cc ........
[ 0.000000] Object ffff000010032858: cc cc cc cc cc cc cc cc ........
[ 0.000000] Redzone ffff000010032860: cc cc cc cc cc cc cc cc ........
[ 0.000000] Padding ffff0000100328b4: 00 00 00 00 00 00 00 00 00 00 00 00 ............
[ 0.000000] CPU: 0 UID: 0 PID: 0 Comm: swapper/0 Not tainted 6.11.0-rc3-next-20240814-00004-g61844c55c3f4 #144
[ 0.000000] Hardware name: NXP i.MX95 19X19 board (DT)
[ 0.000000] Call trace:
[ 0.000000] dump_backtrace+0x90/0xe8
[ 0.000000] show_stack+0x18/0x24
[ 0.000000] dump_stack_lvl+0x74/0x8c
[ 0.000000] dump_stack+0x18/0x24
[ 0.000000] print_trailer+0x150/0x218
[ 0.000000] check_object+0xe4/0x454
[ 0.000000] free_to_partial_list+0x2f8/0x5ec
To address the issue, use orig_size to clear the used area. And restore
the value of orig_size after clear the remaining area.
When CONFIG_SLUB_DEBUG not defined, (get_orig_size()' directly returns
s->object_size. So when using memset to init the area, the size can simply
be orig_size, as orig_size returns object_size when CONFIG_SLUB_DEBUG not
enabled. And orig_size can never be bigger than object_size.
Fixes: 946fa0dbf2d8 ("mm/slub: extend redzone check to extra allocated kmalloc space than requested")
Cc: <stable@vger.kernel.org>
Reviewed-by: Feng Tang <feng.tang@intel.com>
Acked-by: David Rientjes <rientjes@google.com>
Signed-off-by: Peng Fan <peng.fan@nxp.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2024-08-29 11:29:11 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-04-29 23:00:09 -07:00
|
|
|
|
|
|
|
|
|
2024-08-09 17:36:56 +02:00
|
|
|
|
2014-08-06 16:04:18 -07:00
|
|
|
|
2008-04-14 19:11:40 +03:00
|
|
|
|
2024-03-21 09:36:25 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-11-20 15:57:46 -08:00
|
|
|
|
mm: security: introduce init_on_alloc=1 and init_on_free=1 boot options
Patch series "add init_on_alloc/init_on_free boot options", v10.
Provide init_on_alloc and init_on_free boot options.
These are aimed at preventing possible information leaks and making the
control-flow bugs that depend on uninitialized values more deterministic.
Enabling either of the options guarantees that the memory returned by the
page allocator and SL[AU]B is initialized with zeroes. SLOB allocator
isn't supported at the moment, as its emulation of kmem caches complicates
handling of SLAB_TYPESAFE_BY_RCU caches correctly.
Enabling init_on_free also guarantees that pages and heap objects are
initialized right after they're freed, so it won't be possible to access
stale data by using a dangling pointer.
As suggested by Michal Hocko, right now we don't let the heap users to
disable initialization for certain allocations. There's not enough
evidence that doing so can speed up real-life cases, and introducing ways
to opt-out may result in things going out of control.
This patch (of 2):
The new options are needed to prevent possible information leaks and make
control-flow bugs that depend on uninitialized values more deterministic.
This is expected to be on-by-default on Android and Chrome OS. And it
gives the opportunity for anyone else to use it under distros too via the
boot args. (The init_on_free feature is regularly requested by folks
where memory forensics is included in their threat models.)
init_on_alloc=1 makes the kernel initialize newly allocated pages and heap
objects with zeroes. Initialization is done at allocation time at the
places where checks for __GFP_ZERO are performed.
init_on_free=1 makes the kernel initialize freed pages and heap objects
with zeroes upon their deletion. This helps to ensure sensitive data
doesn't leak via use-after-free accesses.
Both init_on_alloc=1 and init_on_free=1 guarantee that the allocator
returns zeroed memory. The two exceptions are slab caches with
constructors and SLAB_TYPESAFE_BY_RCU flag. Those are never
zero-initialized to preserve their semantics.
Both init_on_alloc and init_on_free default to zero, but those defaults
can be overridden with CONFIG_INIT_ON_ALLOC_DEFAULT_ON and
CONFIG_INIT_ON_FREE_DEFAULT_ON.
If either SLUB poisoning or page poisoning is enabled, those options take
precedence over init_on_alloc and init_on_free: initialization is only
applied to unpoisoned allocations.
Slowdown for the new features compared to init_on_free=0, init_on_alloc=0:
hackbench, init_on_free=1: +7.62% sys time (st.err 0.74%)
hackbench, init_on_alloc=1: +7.75% sys time (st.err 2.14%)
Linux build with -j12, init_on_free=1: +8.38% wall time (st.err 0.39%)
Linux build with -j12, init_on_free=1: +24.42% sys time (st.err 0.52%)
Linux build with -j12, init_on_alloc=1: -0.13% wall time (st.err 0.42%)
Linux build with -j12, init_on_alloc=1: +0.57% sys time (st.err 0.40%)
The slowdown for init_on_free=0, init_on_alloc=0 compared to the baseline
is within the standard error.
The new features are also going to pave the way for hardware memory
tagging (e.g. arm64's MTE), which will require both on_alloc and on_free
hooks to set the tags for heap objects. With MTE, tagging will have the
same cost as memory initialization.
Although init_on_free is rather costly, there are paranoid use-cases where
in-memory data lifetime is desired to be minimized. There are various
arguments for/against the realism of the associated threat models, but
given that we'll need the infrastructure for MTE anyway, and there are
people who want wipe-on-free behavior no matter what the performance cost,
it seems reasonable to include it in this series.
[glider@google.com: v8]
Link: http://lkml.kernel.org/r/20190626121943.131390-2-glider@google.com
[glider@google.com: v9]
Link: http://lkml.kernel.org/r/20190627130316.254309-2-glider@google.com
[glider@google.com: v10]
Link: http://lkml.kernel.org/r/20190628093131.199499-2-glider@google.com
Link: http://lkml.kernel.org/r/20190617151050.92663-2-glider@google.com
Signed-off-by: Alexander Potapenko <glider@google.com>
Acked-by: Kees Cook <keescook@chromium.org>
Acked-by: Michal Hocko <mhocko@suse.cz> [page and dmapool parts
Acked-by: James Morris <jamorris@linux.microsoft.com>]
Cc: Christoph Lameter <cl@linux.com>
Cc: Masahiro Yamada <yamada.masahiro@socionext.com>
Cc: "Serge E. Hallyn" <serge@hallyn.com>
Cc: Nick Desaulniers <ndesaulniers@google.com>
Cc: Kostya Serebryany <kcc@google.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Sandeep Patil <sspatil@android.com>
Cc: Laura Abbott <labbott@redhat.com>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Jann Horn <jannh@google.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Marco Elver <elver@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-07-11 20:59:19 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-11-03 20:24:51 +01:00
|
|
|
|
2023-11-14 22:12:47 +01:00
|
|
|
|
mm: security: introduce init_on_alloc=1 and init_on_free=1 boot options
Patch series "add init_on_alloc/init_on_free boot options", v10.
Provide init_on_alloc and init_on_free boot options.
These are aimed at preventing possible information leaks and making the
control-flow bugs that depend on uninitialized values more deterministic.
Enabling either of the options guarantees that the memory returned by the
page allocator and SL[AU]B is initialized with zeroes. SLOB allocator
isn't supported at the moment, as its emulation of kmem caches complicates
handling of SLAB_TYPESAFE_BY_RCU caches correctly.
Enabling init_on_free also guarantees that pages and heap objects are
initialized right after they're freed, so it won't be possible to access
stale data by using a dangling pointer.
As suggested by Michal Hocko, right now we don't let the heap users to
disable initialization for certain allocations. There's not enough
evidence that doing so can speed up real-life cases, and introducing ways
to opt-out may result in things going out of control.
This patch (of 2):
The new options are needed to prevent possible information leaks and make
control-flow bugs that depend on uninitialized values more deterministic.
This is expected to be on-by-default on Android and Chrome OS. And it
gives the opportunity for anyone else to use it under distros too via the
boot args. (The init_on_free feature is regularly requested by folks
where memory forensics is included in their threat models.)
init_on_alloc=1 makes the kernel initialize newly allocated pages and heap
objects with zeroes. Initialization is done at allocation time at the
places where checks for __GFP_ZERO are performed.
init_on_free=1 makes the kernel initialize freed pages and heap objects
with zeroes upon their deletion. This helps to ensure sensitive data
doesn't leak via use-after-free accesses.
Both init_on_alloc=1 and init_on_free=1 guarantee that the allocator
returns zeroed memory. The two exceptions are slab caches with
constructors and SLAB_TYPESAFE_BY_RCU flag. Those are never
zero-initialized to preserve their semantics.
Both init_on_alloc and init_on_free default to zero, but those defaults
can be overridden with CONFIG_INIT_ON_ALLOC_DEFAULT_ON and
CONFIG_INIT_ON_FREE_DEFAULT_ON.
If either SLUB poisoning or page poisoning is enabled, those options take
precedence over init_on_alloc and init_on_free: initialization is only
applied to unpoisoned allocations.
Slowdown for the new features compared to init_on_free=0, init_on_alloc=0:
hackbench, init_on_free=1: +7.62% sys time (st.err 0.74%)
hackbench, init_on_alloc=1: +7.75% sys time (st.err 2.14%)
Linux build with -j12, init_on_free=1: +8.38% wall time (st.err 0.39%)
Linux build with -j12, init_on_free=1: +24.42% sys time (st.err 0.52%)
Linux build with -j12, init_on_alloc=1: -0.13% wall time (st.err 0.42%)
Linux build with -j12, init_on_alloc=1: +0.57% sys time (st.err 0.40%)
The slowdown for init_on_free=0, init_on_alloc=0 compared to the baseline
is within the standard error.
The new features are also going to pave the way for hardware memory
tagging (e.g. arm64's MTE), which will require both on_alloc and on_free
hooks to set the tags for heap objects. With MTE, tagging will have the
same cost as memory initialization.
Although init_on_free is rather costly, there are paranoid use-cases where
in-memory data lifetime is desired to be minimized. There are various
arguments for/against the realism of the associated threat models, but
given that we'll need the infrastructure for MTE anyway, and there are
people who want wipe-on-free behavior no matter what the performance cost,
it seems reasonable to include it in this series.
[glider@google.com: v8]
Link: http://lkml.kernel.org/r/20190626121943.131390-2-glider@google.com
[glider@google.com: v9]
Link: http://lkml.kernel.org/r/20190627130316.254309-2-glider@google.com
[glider@google.com: v10]
Link: http://lkml.kernel.org/r/20190628093131.199499-2-glider@google.com
Link: http://lkml.kernel.org/r/20190617151050.92663-2-glider@google.com
Signed-off-by: Alexander Potapenko <glider@google.com>
Acked-by: Kees Cook <keescook@chromium.org>
Acked-by: Michal Hocko <mhocko@suse.cz> [page and dmapool parts
Acked-by: James Morris <jamorris@linux.microsoft.com>]
Cc: Christoph Lameter <cl@linux.com>
Cc: Masahiro Yamada <yamada.masahiro@socionext.com>
Cc: "Serge E. Hallyn" <serge@hallyn.com>
Cc: Nick Desaulniers <ndesaulniers@google.com>
Cc: Kostya Serebryany <kcc@google.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Sandeep Patil <sspatil@android.com>
Cc: Laura Abbott <labbott@redhat.com>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Jann Horn <jannh@google.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Marco Elver <elver@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-07-11 20:59:19 -07:00
|
|
|
|
2021-02-25 17:19:16 -08:00
|
|
|
|
2024-08-09 17:36:56 +02:00
|
|
|
|
2023-11-14 22:12:47 +01:00
|
|
|
|
2021-02-25 17:19:16 -08:00
|
|
|
|
|
|
|
|
|
2019-11-15 17:34:50 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2019-07-31 15:32:40 -04:00
|
|
|
|
2023-11-14 22:12:47 +01:00
|
|
|
|
|
|
|
|
|
2019-11-15 17:34:50 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-04-10 16:30:31 -07:00
|
|
|
|
2024-08-09 17:36:56 +02:00
|
|
|
|
2018-04-10 16:30:31 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-10-18 15:15:55 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-04-10 16:30:31 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-11-20 15:57:46 -08:00
|
|
|
|
|
|
|
|
|
2022-04-11 16:25:34 +09:00
|
|
|
|
2015-09-04 15:45:48 -07:00
|
|
|
|
2022-04-11 16:25:34 +09:00
|
|
|
|
2018-12-28 00:30:23 -08:00
|
|
|
|
2015-09-04 15:45:48 -07:00
|
|
|
|
2023-12-19 23:29:03 +01:00
|
|
|
|
2015-09-04 15:45:48 -07:00
|
|
|
|
2023-12-19 23:29:03 +01:00
|
|
|
|
2015-09-04 15:45:48 -07:00
|
|
|
|
2018-12-28 00:30:23 -08:00
|
|
|
|
2015-09-04 15:45:48 -07:00
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-03-10 22:07:01 +08:00
|
|
|
|
|
|
|
|
|
2008-04-14 19:11:40 +03:00
|
|
|
|
2021-10-26 16:35:02 +02:00
|
|
|
|
|
|
|
|
|
2018-04-05 16:21:39 -07:00
|
|
|
|
2008-04-14 19:11:40 +03:00
|
|
|
|
2024-08-19 11:54:05 -07:00
|
|
|
|
2024-11-25 21:01:47 +00:00
|
|
|
|
2024-08-19 11:54:05 -07:00
|
|
|
|
2024-11-25 21:01:47 +00:00
|
|
|
|
2024-08-19 11:54:05 -07:00
|
|
|
|
2021-10-26 16:35:02 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-01-06 15:52:51 -06:00
|
|
|
|
2021-10-26 16:35:02 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-04-14 19:11:40 +03:00
|
|
|
|
|
|
|
|
|
2016-07-26 15:21:59 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-04-05 16:21:39 -07:00
|
|
|
|
2016-07-26 15:21:59 -07:00
|
|
|
|
|
|
|
|
|
2017-02-08 14:30:59 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-07-26 15:21:59 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-04-05 16:21:39 -07:00
|
|
|
|
|
|
|
|
|
2016-07-26 15:21:59 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-01-23 09:33:31 +00:00
|
|
|
|
2016-07-26 15:21:59 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2016-07-26 15:21:59 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2016-07-26 15:21:59 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-10-09 20:44:02 -06:00
|
|
|
|
2016-07-26 15:21:59 -07:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
|
|
|
|
|
2016-07-26 15:21:59 -07:00
|
|
|
|
|
|
|
|
|
2024-01-23 09:33:31 +00:00
|
|
|
|
2022-04-11 16:25:34 +09:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2016-07-26 15:21:59 -07:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2024-01-23 09:33:31 +00:00
|
|
|
|
2016-07-26 15:21:59 -07:00
|
|
|
|
2022-04-11 16:25:34 +09:00
|
|
|
|
2016-07-26 15:21:59 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2016-07-26 15:21:59 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-10-03 14:52:47 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-03-21 09:36:28 -07:00
|
|
|
|
2023-10-03 14:52:47 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-03-21 09:36:45 -07:00
|
|
|
|
2024-03-21 09:36:28 -07:00
|
|
|
|
2023-10-03 14:52:47 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2008-04-14 19:11:31 +03:00
|
|
|
|
2009-06-24 21:59:51 +03:00
|
|
|
|
2018-12-28 00:30:23 -08:00
|
|
|
|
2019-09-23 15:34:25 -07:00
|
|
|
|
2016-07-26 15:21:59 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2011-06-01 12:25:44 -05:00
|
|
|
|
|
|
|
|
|
2008-02-14 14:21:32 -08:00
|
|
|
|
2007-10-16 01:25:52 -07:00
|
|
|
|
2009-06-24 21:59:51 +03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-11-06 16:28:21 -08:00
|
|
|
|
2022-04-10 00:05:37 +09:00
|
|
|
|
2009-06-24 21:59:51 +03:00
|
|
|
|
2022-03-10 22:07:01 +08:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2008-04-14 19:11:40 +03:00
|
|
|
|
2014-03-12 17:26:20 +09:00
|
|
|
|
2008-04-14 19:11:40 +03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-03-10 22:07:01 +08:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
mm/slub: restrict sysfs validation to debug caches and make it safe
Rongwei Wang reports [1] that cache validation triggered by writing to
/sys/kernel/slab/<cache>/validate is racy against normal cache
operations (e.g. freeing) in a way that can cause false positive
inconsistency reports for caches with debugging enabled. The problem is
that debugging actions that mark object free or active and actual
freelist operations are not atomic, and the validation can see an
inconsistent state.
For caches that do or don't have debugging enabled, additional races
involving n->nr_slabs are possible that result in false reports of wrong
slab counts.
This patch attempts to solve these issues while not adding overhead to
normal (especially fastpath) operations for caches that do not have
debugging enabled. Such overhead would not be justified to make possible
userspace-triggered validation safe. Instead, disable the validation for
caches that don't have debugging enabled and make their sysfs validate
handler return -EINVAL.
For caches that do have debugging enabled, we can instead extend the
existing approach of not using percpu freelists to force all alloc/free
operations to the slow paths where debugging flags is checked and acted
upon. There can adjust the debug-specific paths to increase n->list_lock
coverage against concurrent validation as necessary.
The processing on free in free_debug_processing() already happens under
n->list_lock so we can extend it to actually do the freeing as well and
thus make it atomic against concurrent validation. As observed by
Hyeonggon Yoo, we do not really need to take slab_lock() anymore here
because all paths we could race with are protected by n->list_lock under
the new scheme, so drop its usage here.
The processing on alloc in alloc_debug_processing() currently doesn't
take any locks, but we have to first allocate the object from a slab on
the partial list (as debugging caches have no percpu slabs) and thus
take the n->list_lock anyway. Add a function alloc_single_from_partial()
that grabs just the allocated object instead of the whole freelist, and
does the debug processing. The n->list_lock coverage again makes it
atomic against validation and it is also ultimately more efficient than
the current grabbing of freelist immediately followed by slab
deactivation.
To prevent races on n->nr_slabs updates, make sure that for caches with
debugging enabled, inc_slabs_node() or dec_slabs_node() is called under
n->list_lock. When allocating a new slab for a debug cache, handle the
allocation by a new function alloc_single_from_new_slab() instead of the
current forced deactivation path.
Neither of these changes affect the fast paths at all. The changes in
slow paths are negligible for non-debug caches.
[1] https://lore.kernel.org/all/20220529081535.69275-1-rongwei.wang@linux.alibaba.com/
Reported-by: Rongwei Wang <rongwei.wang@linux.alibaba.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
2022-08-23 19:03:57 +02:00
|
|
|
|
2015-09-04 15:45:48 -07:00
|
|
|
|
2008-04-14 19:11:40 +03:00
|
|
|
|
2008-04-04 00:54:48 +02:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
mm/slub: restrict sysfs validation to debug caches and make it safe
Rongwei Wang reports [1] that cache validation triggered by writing to
/sys/kernel/slab/<cache>/validate is racy against normal cache
operations (e.g. freeing) in a way that can cause false positive
inconsistency reports for caches with debugging enabled. The problem is
that debugging actions that mark object free or active and actual
freelist operations are not atomic, and the validation can see an
inconsistent state.
For caches that do or don't have debugging enabled, additional races
involving n->nr_slabs are possible that result in false reports of wrong
slab counts.
This patch attempts to solve these issues while not adding overhead to
normal (especially fastpath) operations for caches that do not have
debugging enabled. Such overhead would not be justified to make possible
userspace-triggered validation safe. Instead, disable the validation for
caches that don't have debugging enabled and make their sysfs validate
handler return -EINVAL.
For caches that do have debugging enabled, we can instead extend the
existing approach of not using percpu freelists to force all alloc/free
operations to the slow paths where debugging flags is checked and acted
upon. There can adjust the debug-specific paths to increase n->list_lock
coverage against concurrent validation as necessary.
The processing on free in free_debug_processing() already happens under
n->list_lock so we can extend it to actually do the freeing as well and
thus make it atomic against concurrent validation. As observed by
Hyeonggon Yoo, we do not really need to take slab_lock() anymore here
because all paths we could race with are protected by n->list_lock under
the new scheme, so drop its usage here.
The processing on alloc in alloc_debug_processing() currently doesn't
take any locks, but we have to first allocate the object from a slab on
the partial list (as debugging caches have no percpu slabs) and thus
take the n->list_lock anyway. Add a function alloc_single_from_partial()
that grabs just the allocated object instead of the whole freelist, and
does the debug processing. The n->list_lock coverage again makes it
atomic against validation and it is also ultimately more efficient than
the current grabbing of freelist immediately followed by slab
deactivation.
To prevent races on n->nr_slabs updates, make sure that for caches with
debugging enabled, inc_slabs_node() or dec_slabs_node() is called under
n->list_lock. When allocating a new slab for a debug cache, handle the
allocation by a new function alloc_single_from_new_slab() instead of the
current forced deactivation path.
Neither of these changes affect the fast paths at all. The changes in
slow paths are negligible for non-debug caches.
[1] https://lore.kernel.org/all/20220529081535.69275-1-rongwei.wang@linux.alibaba.com/
Reported-by: Rongwei Wang <rongwei.wang@linux.alibaba.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
2022-08-23 19:03:57 +02:00
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2020-12-29 15:15:07 -08:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2021-10-04 14:46:46 +01:00
|
|
|
|
2019-02-20 22:19:23 -08:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2015-02-13 14:39:42 -08:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2016-07-26 15:21:59 -07:00
|
|
|
|
|
|
|
|
|
2018-12-28 00:30:23 -08:00
|
|
|
|
2022-04-11 16:25:34 +09:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
|
|
|
|
|
2019-02-20 22:19:28 -08:00
|
|
|
|
2022-04-11 16:25:34 +09:00
|
|
|
|
2019-02-20 22:19:28 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2015-09-04 15:45:48 -07:00
|
|
|
|
2020-08-06 23:18:28 -07:00
|
|
|
|
|
|
|
|
|
2015-09-04 15:45:48 -07:00
|
|
|
|
2021-05-11 13:01:34 +02:00
|
|
|
|
|
|
|
|
|
2015-09-04 15:45:48 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-10-29 12:18:24 +02:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2021-10-29 12:18:24 +02:00
|
|
|
|
|
|
|
|
|
2008-04-14 19:11:31 +03:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2021-10-29 12:18:24 +02:00
|
|
|
|
|
|
|
|
|
2022-11-04 15:57:26 +01:00
|
|
|
|
2023-04-13 10:40:34 +00:00
|
|
|
|
2021-10-29 12:18:24 +02:00
|
|
|
|
2024-11-25 21:01:47 +00:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2011-03-10 15:22:00 +08:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2022-08-26 11:09:11 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2022-08-26 11:09:11 +02:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
2023-11-02 03:23:24 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-05-31 13:29:02 +01:00
|
|
|
|
2023-11-02 03:23:24 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2011-06-01 12:25:50 -05:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2014-02-10 14:25:46 -08:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2007-05-06 14:49:44 -07:00
|
|
|
|
2011-08-24 08:57:52 +08:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2008-01-07 23:20:27 -08:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2023-11-02 03:23:24 +00:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
2014-02-10 14:25:46 -08:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2014-02-10 14:25:46 -08:00
|
|
|
|
|
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2014-02-10 14:25:46 -08:00
|
|
|
|
|
|
|
|
|
2011-06-01 12:25:50 -05:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2010-09-28 08:10:28 -05:00
|
|
|
|
2014-01-10 13:23:49 +01:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2023-11-02 03:23:24 +00:00
|
|
|
|
2016-02-17 13:11:37 -08:00
|
|
|
|
2010-09-28 08:10:28 -05:00
|
|
|
|
|
|
|
|
|
mm/slub: restrict sysfs validation to debug caches and make it safe
Rongwei Wang reports [1] that cache validation triggered by writing to
/sys/kernel/slab/<cache>/validate is racy against normal cache
operations (e.g. freeing) in a way that can cause false positive
inconsistency reports for caches with debugging enabled. The problem is
that debugging actions that mark object free or active and actual
freelist operations are not atomic, and the validation can see an
inconsistent state.
For caches that do or don't have debugging enabled, additional races
involving n->nr_slabs are possible that result in false reports of wrong
slab counts.
This patch attempts to solve these issues while not adding overhead to
normal (especially fastpath) operations for caches that do not have
debugging enabled. Such overhead would not be justified to make possible
userspace-triggered validation safe. Instead, disable the validation for
caches that don't have debugging enabled and make their sysfs validate
handler return -EINVAL.
For caches that do have debugging enabled, we can instead extend the
existing approach of not using percpu freelists to force all alloc/free
operations to the slow paths where debugging flags is checked and acted
upon. There can adjust the debug-specific paths to increase n->list_lock
coverage against concurrent validation as necessary.
The processing on free in free_debug_processing() already happens under
n->list_lock so we can extend it to actually do the freeing as well and
thus make it atomic against concurrent validation. As observed by
Hyeonggon Yoo, we do not really need to take slab_lock() anymore here
because all paths we could race with are protected by n->list_lock under
the new scheme, so drop its usage here.
The processing on alloc in alloc_debug_processing() currently doesn't
take any locks, but we have to first allocate the object from a slab on
the partial list (as debugging caches have no percpu slabs) and thus
take the n->list_lock anyway. Add a function alloc_single_from_partial()
that grabs just the allocated object instead of the whole freelist, and
does the debug processing. The n->list_lock coverage again makes it
atomic against validation and it is also ultimately more efficient than
the current grabbing of freelist immediately followed by slab
deactivation.
To prevent races on n->nr_slabs updates, make sure that for caches with
debugging enabled, inc_slabs_node() or dec_slabs_node() is called under
n->list_lock. When allocating a new slab for a debug cache, handle the
allocation by a new function alloc_single_from_new_slab() instead of the
current forced deactivation path.
Neither of these changes affect the fast paths at all. The changes in
slow paths are negligible for non-debug caches.
[1] https://lore.kernel.org/all/20220529081535.69275-1-rongwei.wang@linux.alibaba.com/
Reported-by: Rongwei Wang <rongwei.wang@linux.alibaba.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
2022-08-23 19:03:57 +02:00
|
|
|
|
2023-11-02 03:23:27 +00:00
|
|
|
|
mm/slub: restrict sysfs validation to debug caches and make it safe
Rongwei Wang reports [1] that cache validation triggered by writing to
/sys/kernel/slab/<cache>/validate is racy against normal cache
operations (e.g. freeing) in a way that can cause false positive
inconsistency reports for caches with debugging enabled. The problem is
that debugging actions that mark object free or active and actual
freelist operations are not atomic, and the validation can see an
inconsistent state.
For caches that do or don't have debugging enabled, additional races
involving n->nr_slabs are possible that result in false reports of wrong
slab counts.
This patch attempts to solve these issues while not adding overhead to
normal (especially fastpath) operations for caches that do not have
debugging enabled. Such overhead would not be justified to make possible
userspace-triggered validation safe. Instead, disable the validation for
caches that don't have debugging enabled and make their sysfs validate
handler return -EINVAL.
For caches that do have debugging enabled, we can instead extend the
existing approach of not using percpu freelists to force all alloc/free
operations to the slow paths where debugging flags is checked and acted
upon. There can adjust the debug-specific paths to increase n->list_lock
coverage against concurrent validation as necessary.
The processing on free in free_debug_processing() already happens under
n->list_lock so we can extend it to actually do the freeing as well and
thus make it atomic against concurrent validation. As observed by
Hyeonggon Yoo, we do not really need to take slab_lock() anymore here
because all paths we could race with are protected by n->list_lock under
the new scheme, so drop its usage here.
The processing on alloc in alloc_debug_processing() currently doesn't
take any locks, but we have to first allocate the object from a slab on
the partial list (as debugging caches have no percpu slabs) and thus
take the n->list_lock anyway. Add a function alloc_single_from_partial()
that grabs just the allocated object instead of the whole freelist, and
does the debug processing. The n->list_lock coverage again makes it
atomic against validation and it is also ultimately more efficient than
the current grabbing of freelist immediately followed by slab
deactivation.
To prevent races on n->nr_slabs updates, make sure that for caches with
debugging enabled, inc_slabs_node() or dec_slabs_node() is called under
n->list_lock. When allocating a new slab for a debug cache, handle the
allocation by a new function alloc_single_from_new_slab() instead of the
current forced deactivation path.
Neither of these changes affect the fast paths at all. The changes in
slow paths are negligible for non-debug caches.
[1] https://lore.kernel.org/all/20220529081535.69275-1-rongwei.wang@linux.alibaba.com/
Reported-by: Rongwei Wang <rongwei.wang@linux.alibaba.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
2022-08-23 19:03:57 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
mm/slub: enable debugging memory wasting of kmalloc
kmalloc's API family is critical for mm, with one nature that it will
round up the request size to a fixed one (mostly power of 2). Say
when user requests memory for '2^n + 1' bytes, actually 2^(n+1) bytes
could be allocated, so in worst case, there is around 50% memory
space waste.
The wastage is not a big issue for requests that get allocated/freed
quickly, but may cause problems with objects that have longer life
time.
We've met a kernel boot OOM panic (v5.10), and from the dumped slab
info:
[ 26.062145] kmalloc-2k 814056KB 814056KB
From debug we found there are huge number of 'struct iova_magazine',
whose size is 1032 bytes (1024 + 8), so each allocation will waste
1016 bytes. Though the issue was solved by giving the right (bigger)
size of RAM, it is still nice to optimize the size (either use a
kmalloc friendly size or create a dedicated slab for it).
And from lkml archive, there was another crash kernel OOM case [1]
back in 2019, which seems to be related with the similar slab waste
situation, as the log is similar:
[ 4.332648] iommu: Adding device 0000:20:02.0 to group 16
[ 4.338946] swapper/0 invoked oom-killer: gfp_mask=0x6040c0(GFP_KERNEL|__GFP_COMP), nodemask=(null), order=0, oom_score_adj=0
...
[ 4.857565] kmalloc-2048 59164KB 59164KB
The crash kernel only has 256M memory, and 59M is pretty big here.
(Note: the related code has been changed and optimised in recent
kernel [2], these logs are just picked to demo the problem, also
a patch changing its size to 1024 bytes has been merged)
So add an way to track each kmalloc's memory waste info, and
leverage the existing SLUB debug framework (specifically
SLUB_STORE_USER) to show its call stack of original allocation,
so that user can evaluate the waste situation, identify some hot
spots and optimize accordingly, for a better utilization of memory.
The waste info is integrated into existing interface:
'/sys/kernel/debug/slab/kmalloc-xx/alloc_traces', one example of
'kmalloc-4k' after boot is:
126 ixgbe_alloc_q_vector+0xbe/0x830 [ixgbe] waste=233856/1856 age=280763/281414/282065 pid=1330 cpus=32 nodes=1
__kmem_cache_alloc_node+0x11f/0x4e0
__kmalloc_node+0x4e/0x140
ixgbe_alloc_q_vector+0xbe/0x830 [ixgbe]
ixgbe_init_interrupt_scheme+0x2ae/0xc90 [ixgbe]
ixgbe_probe+0x165f/0x1d20 [ixgbe]
local_pci_probe+0x78/0xc0
work_for_cpu_fn+0x26/0x40
...
which means in 'kmalloc-4k' slab, there are 126 requests of
2240 bytes which got a 4KB space (wasting 1856 bytes each
and 233856 bytes in total), from ixgbe_alloc_q_vector().
And when system starts some real workload like multiple docker
instances, there could are more severe waste.
[1]. https://lkml.org/lkml/2019/8/12/266
[2]. https://lore.kernel.org/lkml/2920df89-9975-5785-f79b-257d3052dfaf@huawei.com/
[Thanks Hyeonggon for pointing out several bugs about sorting/format]
[Thanks Vlastimil for suggesting way to reduce memory usage of
orig_size and keep it only for kmalloc objects]
Signed-off-by: Feng Tang <feng.tang@intel.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Robin Murphy <robin.murphy@arm.com>
Cc: John Garry <john.garry@huawei.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2022-09-13 14:54:20 +08:00
|
|
|
|
mm/slub: restrict sysfs validation to debug caches and make it safe
Rongwei Wang reports [1] that cache validation triggered by writing to
/sys/kernel/slab/<cache>/validate is racy against normal cache
operations (e.g. freeing) in a way that can cause false positive
inconsistency reports for caches with debugging enabled. The problem is
that debugging actions that mark object free or active and actual
freelist operations are not atomic, and the validation can see an
inconsistent state.
For caches that do or don't have debugging enabled, additional races
involving n->nr_slabs are possible that result in false reports of wrong
slab counts.
This patch attempts to solve these issues while not adding overhead to
normal (especially fastpath) operations for caches that do not have
debugging enabled. Such overhead would not be justified to make possible
userspace-triggered validation safe. Instead, disable the validation for
caches that don't have debugging enabled and make their sysfs validate
handler return -EINVAL.
For caches that do have debugging enabled, we can instead extend the
existing approach of not using percpu freelists to force all alloc/free
operations to the slow paths where debugging flags is checked and acted
upon. There can adjust the debug-specific paths to increase n->list_lock
coverage against concurrent validation as necessary.
The processing on free in free_debug_processing() already happens under
n->list_lock so we can extend it to actually do the freeing as well and
thus make it atomic against concurrent validation. As observed by
Hyeonggon Yoo, we do not really need to take slab_lock() anymore here
because all paths we could race with are protected by n->list_lock under
the new scheme, so drop its usage here.
The processing on alloc in alloc_debug_processing() currently doesn't
take any locks, but we have to first allocate the object from a slab on
the partial list (as debugging caches have no percpu slabs) and thus
take the n->list_lock anyway. Add a function alloc_single_from_partial()
that grabs just the allocated object instead of the whole freelist, and
does the debug processing. The n->list_lock coverage again makes it
atomic against validation and it is also ultimately more efficient than
the current grabbing of freelist immediately followed by slab
deactivation.
To prevent races on n->nr_slabs updates, make sure that for caches with
debugging enabled, inc_slabs_node() or dec_slabs_node() is called under
n->list_lock. When allocating a new slab for a debug cache, handle the
allocation by a new function alloc_single_from_new_slab() instead of the
current forced deactivation path.
Neither of these changes affect the fast paths at all. The changes in
slow paths are negligible for non-debug caches.
[1] https://lore.kernel.org/all/20220529081535.69275-1-rongwei.wang@linux.alibaba.com/
Reported-by: Rongwei Wang <rongwei.wang@linux.alibaba.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
2022-08-23 19:03:57 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
mm/slub: enable debugging memory wasting of kmalloc
kmalloc's API family is critical for mm, with one nature that it will
round up the request size to a fixed one (mostly power of 2). Say
when user requests memory for '2^n + 1' bytes, actually 2^(n+1) bytes
could be allocated, so in worst case, there is around 50% memory
space waste.
The wastage is not a big issue for requests that get allocated/freed
quickly, but may cause problems with objects that have longer life
time.
We've met a kernel boot OOM panic (v5.10), and from the dumped slab
info:
[ 26.062145] kmalloc-2k 814056KB 814056KB
From debug we found there are huge number of 'struct iova_magazine',
whose size is 1032 bytes (1024 + 8), so each allocation will waste
1016 bytes. Though the issue was solved by giving the right (bigger)
size of RAM, it is still nice to optimize the size (either use a
kmalloc friendly size or create a dedicated slab for it).
And from lkml archive, there was another crash kernel OOM case [1]
back in 2019, which seems to be related with the similar slab waste
situation, as the log is similar:
[ 4.332648] iommu: Adding device 0000:20:02.0 to group 16
[ 4.338946] swapper/0 invoked oom-killer: gfp_mask=0x6040c0(GFP_KERNEL|__GFP_COMP), nodemask=(null), order=0, oom_score_adj=0
...
[ 4.857565] kmalloc-2048 59164KB 59164KB
The crash kernel only has 256M memory, and 59M is pretty big here.
(Note: the related code has been changed and optimised in recent
kernel [2], these logs are just picked to demo the problem, also
a patch changing its size to 1024 bytes has been merged)
So add an way to track each kmalloc's memory waste info, and
leverage the existing SLUB debug framework (specifically
SLUB_STORE_USER) to show its call stack of original allocation,
so that user can evaluate the waste situation, identify some hot
spots and optimize accordingly, for a better utilization of memory.
The waste info is integrated into existing interface:
'/sys/kernel/debug/slab/kmalloc-xx/alloc_traces', one example of
'kmalloc-4k' after boot is:
126 ixgbe_alloc_q_vector+0xbe/0x830 [ixgbe] waste=233856/1856 age=280763/281414/282065 pid=1330 cpus=32 nodes=1
__kmem_cache_alloc_node+0x11f/0x4e0
__kmalloc_node+0x4e/0x140
ixgbe_alloc_q_vector+0xbe/0x830 [ixgbe]
ixgbe_init_interrupt_scheme+0x2ae/0xc90 [ixgbe]
ixgbe_probe+0x165f/0x1d20 [ixgbe]
local_pci_probe+0x78/0xc0
work_for_cpu_fn+0x26/0x40
...
which means in 'kmalloc-4k' slab, there are 126 requests of
2240 bytes which got a 4KB space (wasting 1856 bytes each
and 233856 bytes in total), from ixgbe_alloc_q_vector().
And when system starts some real workload like multiple docker
instances, there could are more severe waste.
[1]. https://lkml.org/lkml/2019/8/12/266
[2]. https://lore.kernel.org/lkml/2920df89-9975-5785-f79b-257d3052dfaf@huawei.com/
[Thanks Hyeonggon for pointing out several bugs about sorting/format]
[Thanks Vlastimil for suggesting way to reduce memory usage of
orig_size and keep it only for kmalloc objects]
Signed-off-by: Feng Tang <feng.tang@intel.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Robin Murphy <robin.murphy@arm.com>
Cc: John Garry <john.garry@huawei.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2022-09-13 14:54:20 +08:00
|
|
|
|
2024-10-18 14:44:35 +08:00
|
|
|
|
|
|
|
|
|
mm/slub: restrict sysfs validation to debug caches and make it safe
Rongwei Wang reports [1] that cache validation triggered by writing to
/sys/kernel/slab/<cache>/validate is racy against normal cache
operations (e.g. freeing) in a way that can cause false positive
inconsistency reports for caches with debugging enabled. The problem is
that debugging actions that mark object free or active and actual
freelist operations are not atomic, and the validation can see an
inconsistent state.
For caches that do or don't have debugging enabled, additional races
involving n->nr_slabs are possible that result in false reports of wrong
slab counts.
This patch attempts to solve these issues while not adding overhead to
normal (especially fastpath) operations for caches that do not have
debugging enabled. Such overhead would not be justified to make possible
userspace-triggered validation safe. Instead, disable the validation for
caches that don't have debugging enabled and make their sysfs validate
handler return -EINVAL.
For caches that do have debugging enabled, we can instead extend the
existing approach of not using percpu freelists to force all alloc/free
operations to the slow paths where debugging flags is checked and acted
upon. There can adjust the debug-specific paths to increase n->list_lock
coverage against concurrent validation as necessary.
The processing on free in free_debug_processing() already happens under
n->list_lock so we can extend it to actually do the freeing as well and
thus make it atomic against concurrent validation. As observed by
Hyeonggon Yoo, we do not really need to take slab_lock() anymore here
because all paths we could race with are protected by n->list_lock under
the new scheme, so drop its usage here.
The processing on alloc in alloc_debug_processing() currently doesn't
take any locks, but we have to first allocate the object from a slab on
the partial list (as debugging caches have no percpu slabs) and thus
take the n->list_lock anyway. Add a function alloc_single_from_partial()
that grabs just the allocated object instead of the whole freelist, and
does the debug processing. The n->list_lock coverage again makes it
atomic against validation and it is also ultimately more efficient than
the current grabbing of freelist immediately followed by slab
deactivation.
To prevent races on n->nr_slabs updates, make sure that for caches with
debugging enabled, inc_slabs_node() or dec_slabs_node() is called under
n->list_lock. When allocating a new slab for a debug cache, handle the
allocation by a new function alloc_single_from_new_slab() instead of the
current forced deactivation path.
Neither of these changes affect the fast paths at all. The changes in
slow paths are negligible for non-debug caches.
[1] https://lore.kernel.org/all/20220529081535.69275-1-rongwei.wang@linux.alibaba.com/
Reported-by: Rongwei Wang <rongwei.wang@linux.alibaba.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
2022-08-23 19:03:57 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
mm/slub: enable debugging memory wasting of kmalloc
kmalloc's API family is critical for mm, with one nature that it will
round up the request size to a fixed one (mostly power of 2). Say
when user requests memory for '2^n + 1' bytes, actually 2^(n+1) bytes
could be allocated, so in worst case, there is around 50% memory
space waste.
The wastage is not a big issue for requests that get allocated/freed
quickly, but may cause problems with objects that have longer life
time.
We've met a kernel boot OOM panic (v5.10), and from the dumped slab
info:
[ 26.062145] kmalloc-2k 814056KB 814056KB
From debug we found there are huge number of 'struct iova_magazine',
whose size is 1032 bytes (1024 + 8), so each allocation will waste
1016 bytes. Though the issue was solved by giving the right (bigger)
size of RAM, it is still nice to optimize the size (either use a
kmalloc friendly size or create a dedicated slab for it).
And from lkml archive, there was another crash kernel OOM case [1]
back in 2019, which seems to be related with the similar slab waste
situation, as the log is similar:
[ 4.332648] iommu: Adding device 0000:20:02.0 to group 16
[ 4.338946] swapper/0 invoked oom-killer: gfp_mask=0x6040c0(GFP_KERNEL|__GFP_COMP), nodemask=(null), order=0, oom_score_adj=0
...
[ 4.857565] kmalloc-2048 59164KB 59164KB
The crash kernel only has 256M memory, and 59M is pretty big here.
(Note: the related code has been changed and optimised in recent
kernel [2], these logs are just picked to demo the problem, also
a patch changing its size to 1024 bytes has been merged)
So add an way to track each kmalloc's memory waste info, and
leverage the existing SLUB debug framework (specifically
SLUB_STORE_USER) to show its call stack of original allocation,
so that user can evaluate the waste situation, identify some hot
spots and optimize accordingly, for a better utilization of memory.
The waste info is integrated into existing interface:
'/sys/kernel/debug/slab/kmalloc-xx/alloc_traces', one example of
'kmalloc-4k' after boot is:
126 ixgbe_alloc_q_vector+0xbe/0x830 [ixgbe] waste=233856/1856 age=280763/281414/282065 pid=1330 cpus=32 nodes=1
__kmem_cache_alloc_node+0x11f/0x4e0
__kmalloc_node+0x4e/0x140
ixgbe_alloc_q_vector+0xbe/0x830 [ixgbe]
ixgbe_init_interrupt_scheme+0x2ae/0xc90 [ixgbe]
ixgbe_probe+0x165f/0x1d20 [ixgbe]
local_pci_probe+0x78/0xc0
work_for_cpu_fn+0x26/0x40
...
which means in 'kmalloc-4k' slab, there are 126 requests of
2240 bytes which got a 4KB space (wasting 1856 bytes each
and 233856 bytes in total), from ixgbe_alloc_q_vector().
And when system starts some real workload like multiple docker
instances, there could are more severe waste.
[1]. https://lkml.org/lkml/2019/8/12/266
[2]. https://lore.kernel.org/lkml/2920df89-9975-5785-f79b-257d3052dfaf@huawei.com/
[Thanks Hyeonggon for pointing out several bugs about sorting/format]
[Thanks Vlastimil for suggesting way to reduce memory usage of
orig_size and keep it only for kmalloc objects]
Signed-off-by: Feng Tang <feng.tang@intel.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Robin Murphy <robin.murphy@arm.com>
Cc: John Garry <john.garry@huawei.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2022-09-13 14:54:20 +08:00
|
|
|
|
mm/slub: restrict sysfs validation to debug caches and make it safe
Rongwei Wang reports [1] that cache validation triggered by writing to
/sys/kernel/slab/<cache>/validate is racy against normal cache
operations (e.g. freeing) in a way that can cause false positive
inconsistency reports for caches with debugging enabled. The problem is
that debugging actions that mark object free or active and actual
freelist operations are not atomic, and the validation can see an
inconsistent state.
For caches that do or don't have debugging enabled, additional races
involving n->nr_slabs are possible that result in false reports of wrong
slab counts.
This patch attempts to solve these issues while not adding overhead to
normal (especially fastpath) operations for caches that do not have
debugging enabled. Such overhead would not be justified to make possible
userspace-triggered validation safe. Instead, disable the validation for
caches that don't have debugging enabled and make their sysfs validate
handler return -EINVAL.
For caches that do have debugging enabled, we can instead extend the
existing approach of not using percpu freelists to force all alloc/free
operations to the slow paths where debugging flags is checked and acted
upon. There can adjust the debug-specific paths to increase n->list_lock
coverage against concurrent validation as necessary.
The processing on free in free_debug_processing() already happens under
n->list_lock so we can extend it to actually do the freeing as well and
thus make it atomic against concurrent validation. As observed by
Hyeonggon Yoo, we do not really need to take slab_lock() anymore here
because all paths we could race with are protected by n->list_lock under
the new scheme, so drop its usage here.
The processing on alloc in alloc_debug_processing() currently doesn't
take any locks, but we have to first allocate the object from a slab on
the partial list (as debugging caches have no percpu slabs) and thus
take the n->list_lock anyway. Add a function alloc_single_from_partial()
that grabs just the allocated object instead of the whole freelist, and
does the debug processing. The n->list_lock coverage again makes it
atomic against validation and it is also ultimately more efficient than
the current grabbing of freelist immediately followed by slab
deactivation.
To prevent races on n->nr_slabs updates, make sure that for caches with
debugging enabled, inc_slabs_node() or dec_slabs_node() is called under
n->list_lock. When allocating a new slab for a debug cache, handle the
allocation by a new function alloc_single_from_new_slab() instead of the
current forced deactivation path.
Neither of these changes affect the fast paths at all. The changes in
slow paths are negligible for non-debug caches.
[1] https://lore.kernel.org/all/20220529081535.69275-1-rongwei.wang@linux.alibaba.com/
Reported-by: Rongwei Wang <rongwei.wang@linux.alibaba.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
2022-08-23 19:03:57 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
mm/slub: enable debugging memory wasting of kmalloc
kmalloc's API family is critical for mm, with one nature that it will
round up the request size to a fixed one (mostly power of 2). Say
when user requests memory for '2^n + 1' bytes, actually 2^(n+1) bytes
could be allocated, so in worst case, there is around 50% memory
space waste.
The wastage is not a big issue for requests that get allocated/freed
quickly, but may cause problems with objects that have longer life
time.
We've met a kernel boot OOM panic (v5.10), and from the dumped slab
info:
[ 26.062145] kmalloc-2k 814056KB 814056KB
From debug we found there are huge number of 'struct iova_magazine',
whose size is 1032 bytes (1024 + 8), so each allocation will waste
1016 bytes. Though the issue was solved by giving the right (bigger)
size of RAM, it is still nice to optimize the size (either use a
kmalloc friendly size or create a dedicated slab for it).
And from lkml archive, there was another crash kernel OOM case [1]
back in 2019, which seems to be related with the similar slab waste
situation, as the log is similar:
[ 4.332648] iommu: Adding device 0000:20:02.0 to group 16
[ 4.338946] swapper/0 invoked oom-killer: gfp_mask=0x6040c0(GFP_KERNEL|__GFP_COMP), nodemask=(null), order=0, oom_score_adj=0
...
[ 4.857565] kmalloc-2048 59164KB 59164KB
The crash kernel only has 256M memory, and 59M is pretty big here.
(Note: the related code has been changed and optimised in recent
kernel [2], these logs are just picked to demo the problem, also
a patch changing its size to 1024 bytes has been merged)
So add an way to track each kmalloc's memory waste info, and
leverage the existing SLUB debug framework (specifically
SLUB_STORE_USER) to show its call stack of original allocation,
so that user can evaluate the waste situation, identify some hot
spots and optimize accordingly, for a better utilization of memory.
The waste info is integrated into existing interface:
'/sys/kernel/debug/slab/kmalloc-xx/alloc_traces', one example of
'kmalloc-4k' after boot is:
126 ixgbe_alloc_q_vector+0xbe/0x830 [ixgbe] waste=233856/1856 age=280763/281414/282065 pid=1330 cpus=32 nodes=1
__kmem_cache_alloc_node+0x11f/0x4e0
__kmalloc_node+0x4e/0x140
ixgbe_alloc_q_vector+0xbe/0x830 [ixgbe]
ixgbe_init_interrupt_scheme+0x2ae/0xc90 [ixgbe]
ixgbe_probe+0x165f/0x1d20 [ixgbe]
local_pci_probe+0x78/0xc0
work_for_cpu_fn+0x26/0x40
...
which means in 'kmalloc-4k' slab, there are 126 requests of
2240 bytes which got a 4KB space (wasting 1856 bytes each
and 233856 bytes in total), from ixgbe_alloc_q_vector().
And when system starts some real workload like multiple docker
instances, there could are more severe waste.
[1]. https://lkml.org/lkml/2019/8/12/266
[2]. https://lore.kernel.org/lkml/2920df89-9975-5785-f79b-257d3052dfaf@huawei.com/
[Thanks Hyeonggon for pointing out several bugs about sorting/format]
[Thanks Vlastimil for suggesting way to reduce memory usage of
orig_size and keep it only for kmalloc objects]
Signed-off-by: Feng Tang <feng.tang@intel.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Robin Murphy <robin.murphy@arm.com>
Cc: John Garry <john.garry@huawei.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2022-09-13 14:54:20 +08:00
|
|
|
|
mm/slub: restrict sysfs validation to debug caches and make it safe
Rongwei Wang reports [1] that cache validation triggered by writing to
/sys/kernel/slab/<cache>/validate is racy against normal cache
operations (e.g. freeing) in a way that can cause false positive
inconsistency reports for caches with debugging enabled. The problem is
that debugging actions that mark object free or active and actual
freelist operations are not atomic, and the validation can see an
inconsistent state.
For caches that do or don't have debugging enabled, additional races
involving n->nr_slabs are possible that result in false reports of wrong
slab counts.
This patch attempts to solve these issues while not adding overhead to
normal (especially fastpath) operations for caches that do not have
debugging enabled. Such overhead would not be justified to make possible
userspace-triggered validation safe. Instead, disable the validation for
caches that don't have debugging enabled and make their sysfs validate
handler return -EINVAL.
For caches that do have debugging enabled, we can instead extend the
existing approach of not using percpu freelists to force all alloc/free
operations to the slow paths where debugging flags is checked and acted
upon. There can adjust the debug-specific paths to increase n->list_lock
coverage against concurrent validation as necessary.
The processing on free in free_debug_processing() already happens under
n->list_lock so we can extend it to actually do the freeing as well and
thus make it atomic against concurrent validation. As observed by
Hyeonggon Yoo, we do not really need to take slab_lock() anymore here
because all paths we could race with are protected by n->list_lock under
the new scheme, so drop its usage here.
The processing on alloc in alloc_debug_processing() currently doesn't
take any locks, but we have to first allocate the object from a slab on
the partial list (as debugging caches have no percpu slabs) and thus
take the n->list_lock anyway. Add a function alloc_single_from_partial()
that grabs just the allocated object instead of the whole freelist, and
does the debug processing. The n->list_lock coverage again makes it
atomic against validation and it is also ultimately more efficient than
the current grabbing of freelist immediately followed by slab
deactivation.
To prevent races on n->nr_slabs updates, make sure that for caches with
debugging enabled, inc_slabs_node() or dec_slabs_node() is called under
n->list_lock. When allocating a new slab for a debug cache, handle the
allocation by a new function alloc_single_from_new_slab() instead of the
current forced deactivation path.
Neither of these changes affect the fast paths at all. The changes in
slow paths are negligible for non-debug caches.
[1] https://lore.kernel.org/all/20220529081535.69275-1-rongwei.wang@linux.alibaba.com/
Reported-by: Rongwei Wang <rongwei.wang@linux.alibaba.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
2022-08-23 19:03:57 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
mm, slub: protect put_cpu_partial() with disabled irqs instead of cmpxchg
Jann Horn reported [1] the following theoretically possible race:
task A: put_cpu_partial() calls preempt_disable()
task A: oldpage = this_cpu_read(s->cpu_slab->partial)
interrupt: kfree() reaches unfreeze_partials() and discards the page
task B (on another CPU): reallocates page as page cache
task A: reads page->pages and page->pobjects, which are actually
halves of the pointer page->lru.prev
task B (on another CPU): frees page
interrupt: allocates page as SLUB page and places it on the percpu partial list
task A: this_cpu_cmpxchg() succeeds
which would cause page->pages and page->pobjects to end up containing
halves of pointers that would then influence when put_cpu_partial()
happens and show up in root-only sysfs files. Maybe that's acceptable,
I don't know. But there should probably at least be a comment for now
to point out that we're reading union fields of a page that might be
in a completely different state.
Additionally, the this_cpu_cmpxchg() approach in put_cpu_partial() is only safe
against s->cpu_slab->partial manipulation in ___slab_alloc() if the latter
disables irqs, otherwise a __slab_free() in an irq handler could call
put_cpu_partial() in the middle of ___slab_alloc() manipulating ->partial
and corrupt it. This becomes an issue on RT after a local_lock is introduced
in later patch. The fix means taking the local_lock also in put_cpu_partial()
on RT.
After debugging this issue, Mike Galbraith suggested [2] that to avoid
different locking schemes on RT and !RT, we can just protect put_cpu_partial()
with disabled irqs (to be converted to local_lock_irqsave() later) everywhere.
This should be acceptable as it's not a fast path, and moving the actual
partial unfreezing outside of the irq disabled section makes it short, and with
the retry loop gone the code can be also simplified. In addition, the race
reported by Jann should no longer be possible.
[1] https://lore.kernel.org/lkml/CAG48ez1mvUuXwg0YPH5ANzhQLpbphqk-ZS+jbRz+H66fvm4FcA@mail.gmail.com/
[2] https://lore.kernel.org/linux-rt-users/e3470ab357b48bccfbd1f5133b982178a7d2befb.camel@gmx.de/
Reported-by: Jann Horn <jannh@google.com>
Suggested-by: Mike Galbraith <efault@gmx.de>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2021-07-28 12:26:27 +02:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
mm, slub: protect put_cpu_partial() with disabled irqs instead of cmpxchg
Jann Horn reported [1] the following theoretically possible race:
task A: put_cpu_partial() calls preempt_disable()
task A: oldpage = this_cpu_read(s->cpu_slab->partial)
interrupt: kfree() reaches unfreeze_partials() and discards the page
task B (on another CPU): reallocates page as page cache
task A: reads page->pages and page->pobjects, which are actually
halves of the pointer page->lru.prev
task B (on another CPU): frees page
interrupt: allocates page as SLUB page and places it on the percpu partial list
task A: this_cpu_cmpxchg() succeeds
which would cause page->pages and page->pobjects to end up containing
halves of pointers that would then influence when put_cpu_partial()
happens and show up in root-only sysfs files. Maybe that's acceptable,
I don't know. But there should probably at least be a comment for now
to point out that we're reading union fields of a page that might be
in a completely different state.
Additionally, the this_cpu_cmpxchg() approach in put_cpu_partial() is only safe
against s->cpu_slab->partial manipulation in ___slab_alloc() if the latter
disables irqs, otherwise a __slab_free() in an irq handler could call
put_cpu_partial() in the middle of ___slab_alloc() manipulating ->partial
and corrupt it. This becomes an issue on RT after a local_lock is introduced
in later patch. The fix means taking the local_lock also in put_cpu_partial()
on RT.
After debugging this issue, Mike Galbraith suggested [2] that to avoid
different locking schemes on RT and !RT, we can just protect put_cpu_partial()
with disabled irqs (to be converted to local_lock_irqsave() later) everywhere.
This should be acceptable as it's not a fast path, and moving the actual
partial unfreezing outside of the irq disabled section makes it short, and with
the retry loop gone the code can be also simplified. In addition, the race
reported by Jann should no longer be possible.
[1] https://lore.kernel.org/lkml/CAG48ez1mvUuXwg0YPH5ANzhQLpbphqk-ZS+jbRz+H66fvm4FcA@mail.gmail.com/
[2] https://lore.kernel.org/linux-rt-users/e3470ab357b48bccfbd1f5133b982178a7d2befb.camel@gmx.de/
Reported-by: Jann Horn <jannh@google.com>
Suggested-by: Mike Galbraith <efault@gmx.de>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2021-07-28 12:26:27 +02:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
mm, slub: protect put_cpu_partial() with disabled irqs instead of cmpxchg
Jann Horn reported [1] the following theoretically possible race:
task A: put_cpu_partial() calls preempt_disable()
task A: oldpage = this_cpu_read(s->cpu_slab->partial)
interrupt: kfree() reaches unfreeze_partials() and discards the page
task B (on another CPU): reallocates page as page cache
task A: reads page->pages and page->pobjects, which are actually
halves of the pointer page->lru.prev
task B (on another CPU): frees page
interrupt: allocates page as SLUB page and places it on the percpu partial list
task A: this_cpu_cmpxchg() succeeds
which would cause page->pages and page->pobjects to end up containing
halves of pointers that would then influence when put_cpu_partial()
happens and show up in root-only sysfs files. Maybe that's acceptable,
I don't know. But there should probably at least be a comment for now
to point out that we're reading union fields of a page that might be
in a completely different state.
Additionally, the this_cpu_cmpxchg() approach in put_cpu_partial() is only safe
against s->cpu_slab->partial manipulation in ___slab_alloc() if the latter
disables irqs, otherwise a __slab_free() in an irq handler could call
put_cpu_partial() in the middle of ___slab_alloc() manipulating ->partial
and corrupt it. This becomes an issue on RT after a local_lock is introduced
in later patch. The fix means taking the local_lock also in put_cpu_partial()
on RT.
After debugging this issue, Mike Galbraith suggested [2] that to avoid
different locking schemes on RT and !RT, we can just protect put_cpu_partial()
with disabled irqs (to be converted to local_lock_irqsave() later) everywhere.
This should be acceptable as it's not a fast path, and moving the actual
partial unfreezing outside of the irq disabled section makes it short, and with
the retry loop gone the code can be also simplified. In addition, the race
reported by Jann should no longer be possible.
[1] https://lore.kernel.org/lkml/CAG48ez1mvUuXwg0YPH5ANzhQLpbphqk-ZS+jbRz+H66fvm4FcA@mail.gmail.com/
[2] https://lore.kernel.org/linux-rt-users/e3470ab357b48bccfbd1f5133b982178a7d2befb.camel@gmx.de/
Reported-by: Jann Horn <jannh@google.com>
Suggested-by: Mike Galbraith <efault@gmx.de>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2021-07-28 12:26:27 +02:00
|
|
|
|
|
|
|
|
|
2021-10-04 14:46:40 +01:00
|
|
|
|
2011-08-09 16:12:27 -05:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2007-05-09 02:32:39 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2023-11-02 03:23:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2023-11-02 03:23:23 +00:00
|
|
|
|
2021-05-11 17:45:26 +02:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-10-15 20:10:01 -07:00
|
|
|
|
2007-05-09 02:32:39 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-05-11 17:45:26 +02:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
mm/slub: enable debugging memory wasting of kmalloc
kmalloc's API family is critical for mm, with one nature that it will
round up the request size to a fixed one (mostly power of 2). Say
when user requests memory for '2^n + 1' bytes, actually 2^(n+1) bytes
could be allocated, so in worst case, there is around 50% memory
space waste.
The wastage is not a big issue for requests that get allocated/freed
quickly, but may cause problems with objects that have longer life
time.
We've met a kernel boot OOM panic (v5.10), and from the dumped slab
info:
[ 26.062145] kmalloc-2k 814056KB 814056KB
From debug we found there are huge number of 'struct iova_magazine',
whose size is 1032 bytes (1024 + 8), so each allocation will waste
1016 bytes. Though the issue was solved by giving the right (bigger)
size of RAM, it is still nice to optimize the size (either use a
kmalloc friendly size or create a dedicated slab for it).
And from lkml archive, there was another crash kernel OOM case [1]
back in 2019, which seems to be related with the similar slab waste
situation, as the log is similar:
[ 4.332648] iommu: Adding device 0000:20:02.0 to group 16
[ 4.338946] swapper/0 invoked oom-killer: gfp_mask=0x6040c0(GFP_KERNEL|__GFP_COMP), nodemask=(null), order=0, oom_score_adj=0
...
[ 4.857565] kmalloc-2048 59164KB 59164KB
The crash kernel only has 256M memory, and 59M is pretty big here.
(Note: the related code has been changed and optimised in recent
kernel [2], these logs are just picked to demo the problem, also
a patch changing its size to 1024 bytes has been merged)
So add an way to track each kmalloc's memory waste info, and
leverage the existing SLUB debug framework (specifically
SLUB_STORE_USER) to show its call stack of original allocation,
so that user can evaluate the waste situation, identify some hot
spots and optimize accordingly, for a better utilization of memory.
The waste info is integrated into existing interface:
'/sys/kernel/debug/slab/kmalloc-xx/alloc_traces', one example of
'kmalloc-4k' after boot is:
126 ixgbe_alloc_q_vector+0xbe/0x830 [ixgbe] waste=233856/1856 age=280763/281414/282065 pid=1330 cpus=32 nodes=1
__kmem_cache_alloc_node+0x11f/0x4e0
__kmalloc_node+0x4e/0x140
ixgbe_alloc_q_vector+0xbe/0x830 [ixgbe]
ixgbe_init_interrupt_scheme+0x2ae/0xc90 [ixgbe]
ixgbe_probe+0x165f/0x1d20 [ixgbe]
local_pci_probe+0x78/0xc0
work_for_cpu_fn+0x26/0x40
...
which means in 'kmalloc-4k' slab, there are 126 requests of
2240 bytes which got a 4KB space (wasting 1856 bytes each
and 233856 bytes in total), from ixgbe_alloc_q_vector().
And when system starts some real workload like multiple docker
instances, there could are more severe waste.
[1]. https://lkml.org/lkml/2019/8/12/266
[2]. https://lore.kernel.org/lkml/2920df89-9975-5785-f79b-257d3052dfaf@huawei.com/
[Thanks Hyeonggon for pointing out several bugs about sorting/format]
[Thanks Vlastimil for suggesting way to reduce memory usage of
orig_size and keep it only for kmalloc objects]
Signed-off-by: Feng Tang <feng.tang@intel.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Robin Murphy <robin.murphy@arm.com>
Cc: John Garry <john.garry@huawei.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2022-09-13 14:54:20 +08:00
|
|
|
|
2012-09-17 14:09:09 -07:00
|
|
|
|
|
|
|
|
|
2022-11-15 18:14:31 +01:00
|
|
|
|
2023-11-02 03:23:27 +00:00
|
|
|
|
mm/slub: enable debugging memory wasting of kmalloc
kmalloc's API family is critical for mm, with one nature that it will
round up the request size to a fixed one (mostly power of 2). Say
when user requests memory for '2^n + 1' bytes, actually 2^(n+1) bytes
could be allocated, so in worst case, there is around 50% memory
space waste.
The wastage is not a big issue for requests that get allocated/freed
quickly, but may cause problems with objects that have longer life
time.
We've met a kernel boot OOM panic (v5.10), and from the dumped slab
info:
[ 26.062145] kmalloc-2k 814056KB 814056KB
From debug we found there are huge number of 'struct iova_magazine',
whose size is 1032 bytes (1024 + 8), so each allocation will waste
1016 bytes. Though the issue was solved by giving the right (bigger)
size of RAM, it is still nice to optimize the size (either use a
kmalloc friendly size or create a dedicated slab for it).
And from lkml archive, there was another crash kernel OOM case [1]
back in 2019, which seems to be related with the similar slab waste
situation, as the log is similar:
[ 4.332648] iommu: Adding device 0000:20:02.0 to group 16
[ 4.338946] swapper/0 invoked oom-killer: gfp_mask=0x6040c0(GFP_KERNEL|__GFP_COMP), nodemask=(null), order=0, oom_score_adj=0
...
[ 4.857565] kmalloc-2048 59164KB 59164KB
The crash kernel only has 256M memory, and 59M is pretty big here.
(Note: the related code has been changed and optimised in recent
kernel [2], these logs are just picked to demo the problem, also
a patch changing its size to 1024 bytes has been merged)
So add an way to track each kmalloc's memory waste info, and
leverage the existing SLUB debug framework (specifically
SLUB_STORE_USER) to show its call stack of original allocation,
so that user can evaluate the waste situation, identify some hot
spots and optimize accordingly, for a better utilization of memory.
The waste info is integrated into existing interface:
'/sys/kernel/debug/slab/kmalloc-xx/alloc_traces', one example of
'kmalloc-4k' after boot is:
126 ixgbe_alloc_q_vector+0xbe/0x830 [ixgbe] waste=233856/1856 age=280763/281414/282065 pid=1330 cpus=32 nodes=1
__kmem_cache_alloc_node+0x11f/0x4e0
__kmalloc_node+0x4e/0x140
ixgbe_alloc_q_vector+0xbe/0x830 [ixgbe]
ixgbe_init_interrupt_scheme+0x2ae/0xc90 [ixgbe]
ixgbe_probe+0x165f/0x1d20 [ixgbe]
local_pci_probe+0x78/0xc0
work_for_cpu_fn+0x26/0x40
...
which means in 'kmalloc-4k' slab, there are 126 requests of
2240 bytes which got a 4KB space (wasting 1856 bytes each
and 233856 bytes in total), from ixgbe_alloc_q_vector().
And when system starts some real workload like multiple docker
instances, there could are more severe waste.
[1]. https://lkml.org/lkml/2019/8/12/266
[2]. https://lore.kernel.org/lkml/2920df89-9975-5785-f79b-257d3052dfaf@huawei.com/
[Thanks Hyeonggon for pointing out several bugs about sorting/format]
[Thanks Vlastimil for suggesting way to reduce memory usage of
orig_size and keep it only for kmalloc objects]
Signed-off-by: Feng Tang <feng.tang@intel.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Robin Murphy <robin.murphy@arm.com>
Cc: John Garry <john.garry@huawei.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2022-09-13 14:54:20 +08:00
|
|
|
|
2023-11-02 03:23:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
mm/slub: restrict sysfs validation to debug caches and make it safe
Rongwei Wang reports [1] that cache validation triggered by writing to
/sys/kernel/slab/<cache>/validate is racy against normal cache
operations (e.g. freeing) in a way that can cause false positive
inconsistency reports for caches with debugging enabled. The problem is
that debugging actions that mark object free or active and actual
freelist operations are not atomic, and the validation can see an
inconsistent state.
For caches that do or don't have debugging enabled, additional races
involving n->nr_slabs are possible that result in false reports of wrong
slab counts.
This patch attempts to solve these issues while not adding overhead to
normal (especially fastpath) operations for caches that do not have
debugging enabled. Such overhead would not be justified to make possible
userspace-triggered validation safe. Instead, disable the validation for
caches that don't have debugging enabled and make their sysfs validate
handler return -EINVAL.
For caches that do have debugging enabled, we can instead extend the
existing approach of not using percpu freelists to force all alloc/free
operations to the slow paths where debugging flags is checked and acted
upon. There can adjust the debug-specific paths to increase n->list_lock
coverage against concurrent validation as necessary.
The processing on free in free_debug_processing() already happens under
n->list_lock so we can extend it to actually do the freeing as well and
thus make it atomic against concurrent validation. As observed by
Hyeonggon Yoo, we do not really need to take slab_lock() anymore here
because all paths we could race with are protected by n->list_lock under
the new scheme, so drop its usage here.
The processing on alloc in alloc_debug_processing() currently doesn't
take any locks, but we have to first allocate the object from a slab on
the partial list (as debugging caches have no percpu slabs) and thus
take the n->list_lock anyway. Add a function alloc_single_from_partial()
that grabs just the allocated object instead of the whole freelist, and
does the debug processing. The n->list_lock coverage again makes it
atomic against validation and it is also ultimately more efficient than
the current grabbing of freelist immediately followed by slab
deactivation.
To prevent races on n->nr_slabs updates, make sure that for caches with
debugging enabled, inc_slabs_node() or dec_slabs_node() is called under
n->list_lock. When allocating a new slab for a debug cache, handle the
allocation by a new function alloc_single_from_new_slab() instead of the
current forced deactivation path.
Neither of these changes affect the fast paths at all. The changes in
slow paths are negligible for non-debug caches.
[1] https://lore.kernel.org/all/20220529081535.69275-1-rongwei.wang@linux.alibaba.com/
Reported-by: Rongwei Wang <rongwei.wang@linux.alibaba.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
2022-08-23 19:03:57 +02:00
|
|
|
|
2023-11-02 03:23:23 +00:00
|
|
|
|
mm/slub: restrict sysfs validation to debug caches and make it safe
Rongwei Wang reports [1] that cache validation triggered by writing to
/sys/kernel/slab/<cache>/validate is racy against normal cache
operations (e.g. freeing) in a way that can cause false positive
inconsistency reports for caches with debugging enabled. The problem is
that debugging actions that mark object free or active and actual
freelist operations are not atomic, and the validation can see an
inconsistent state.
For caches that do or don't have debugging enabled, additional races
involving n->nr_slabs are possible that result in false reports of wrong
slab counts.
This patch attempts to solve these issues while not adding overhead to
normal (especially fastpath) operations for caches that do not have
debugging enabled. Such overhead would not be justified to make possible
userspace-triggered validation safe. Instead, disable the validation for
caches that don't have debugging enabled and make their sysfs validate
handler return -EINVAL.
For caches that do have debugging enabled, we can instead extend the
existing approach of not using percpu freelists to force all alloc/free
operations to the slow paths where debugging flags is checked and acted
upon. There can adjust the debug-specific paths to increase n->list_lock
coverage against concurrent validation as necessary.
The processing on free in free_debug_processing() already happens under
n->list_lock so we can extend it to actually do the freeing as well and
thus make it atomic against concurrent validation. As observed by
Hyeonggon Yoo, we do not really need to take slab_lock() anymore here
because all paths we could race with are protected by n->list_lock under
the new scheme, so drop its usage here.
The processing on alloc in alloc_debug_processing() currently doesn't
take any locks, but we have to first allocate the object from a slab on
the partial list (as debugging caches have no percpu slabs) and thus
take the n->list_lock anyway. Add a function alloc_single_from_partial()
that grabs just the allocated object instead of the whole freelist, and
does the debug processing. The n->list_lock coverage again makes it
atomic against validation and it is also ultimately more efficient than
the current grabbing of freelist immediately followed by slab
deactivation.
To prevent races on n->nr_slabs updates, make sure that for caches with
debugging enabled, inc_slabs_node() or dec_slabs_node() is called under
n->list_lock. When allocating a new slab for a debug cache, handle the
allocation by a new function alloc_single_from_new_slab() instead of the
current forced deactivation path.
Neither of these changes affect the fast paths at all. The changes in
slow paths are negligible for non-debug caches.
[1] https://lore.kernel.org/all/20220529081535.69275-1-rongwei.wang@linux.alibaba.com/
Reported-by: Rongwei Wang <rongwei.wang@linux.alibaba.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
2022-08-23 19:03:57 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-11-02 03:23:27 +00:00
|
|
|
|
2011-08-09 16:12:27 -05:00
|
|
|
|
2023-11-02 03:23:23 +00:00
|
|
|
|
|
|
|
|
|
2011-08-09 16:12:27 -05:00
|
|
|
|
2024-04-04 13:58:26 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-08-09 16:12:27 -05:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2012-02-03 23:34:56 +08:00
|
|
|
|
2011-08-09 16:12:27 -05:00
|
|
|
|
2024-04-04 13:58:26 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-08-09 16:12:26 -05:00
|
|
|
|
2021-05-11 17:45:26 +02:00
|
|
|
|
2023-11-02 03:23:23 +00:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-11-15 16:55:15 +01:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2023-11-02 03:23:23 +00:00
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-04-28 02:12:17 -07:00
|
|
|
|
2008-04-28 02:12:16 -07:00
|
|
|
|
mm/slub: enable debugging memory wasting of kmalloc
kmalloc's API family is critical for mm, with one nature that it will
round up the request size to a fixed one (mostly power of 2). Say
when user requests memory for '2^n + 1' bytes, actually 2^(n+1) bytes
could be allocated, so in worst case, there is around 50% memory
space waste.
The wastage is not a big issue for requests that get allocated/freed
quickly, but may cause problems with objects that have longer life
time.
We've met a kernel boot OOM panic (v5.10), and from the dumped slab
info:
[ 26.062145] kmalloc-2k 814056KB 814056KB
From debug we found there are huge number of 'struct iova_magazine',
whose size is 1032 bytes (1024 + 8), so each allocation will waste
1016 bytes. Though the issue was solved by giving the right (bigger)
size of RAM, it is still nice to optimize the size (either use a
kmalloc friendly size or create a dedicated slab for it).
And from lkml archive, there was another crash kernel OOM case [1]
back in 2019, which seems to be related with the similar slab waste
situation, as the log is similar:
[ 4.332648] iommu: Adding device 0000:20:02.0 to group 16
[ 4.338946] swapper/0 invoked oom-killer: gfp_mask=0x6040c0(GFP_KERNEL|__GFP_COMP), nodemask=(null), order=0, oom_score_adj=0
...
[ 4.857565] kmalloc-2048 59164KB 59164KB
The crash kernel only has 256M memory, and 59M is pretty big here.
(Note: the related code has been changed and optimised in recent
kernel [2], these logs are just picked to demo the problem, also
a patch changing its size to 1024 bytes has been merged)
So add an way to track each kmalloc's memory waste info, and
leverage the existing SLUB debug framework (specifically
SLUB_STORE_USER) to show its call stack of original allocation,
so that user can evaluate the waste situation, identify some hot
spots and optimize accordingly, for a better utilization of memory.
The waste info is integrated into existing interface:
'/sys/kernel/debug/slab/kmalloc-xx/alloc_traces', one example of
'kmalloc-4k' after boot is:
126 ixgbe_alloc_q_vector+0xbe/0x830 [ixgbe] waste=233856/1856 age=280763/281414/282065 pid=1330 cpus=32 nodes=1
__kmem_cache_alloc_node+0x11f/0x4e0
__kmalloc_node+0x4e/0x140
ixgbe_alloc_q_vector+0xbe/0x830 [ixgbe]
ixgbe_init_interrupt_scheme+0x2ae/0xc90 [ixgbe]
ixgbe_probe+0x165f/0x1d20 [ixgbe]
local_pci_probe+0x78/0xc0
work_for_cpu_fn+0x26/0x40
...
which means in 'kmalloc-4k' slab, there are 126 requests of
2240 bytes which got a 4KB space (wasting 1856 bytes each
and 233856 bytes in total), from ixgbe_alloc_q_vector().
And when system starts some real workload like multiple docker
instances, there could are more severe waste.
[1]. https://lkml.org/lkml/2019/8/12/266
[2]. https://lore.kernel.org/lkml/2920df89-9975-5785-f79b-257d3052dfaf@huawei.com/
[Thanks Hyeonggon for pointing out several bugs about sorting/format]
[Thanks Vlastimil for suggesting way to reduce memory usage of
orig_size and keep it only for kmalloc objects]
Signed-off-by: Feng Tang <feng.tang@intel.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Robin Murphy <robin.murphy@arm.com>
Cc: John Garry <john.garry@huawei.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2022-09-13 14:54:20 +08:00
|
|
|
|
2023-11-02 03:23:23 +00:00
|
|
|
|
cpuset: mm: reduce large amounts of memory barrier related damage v3
Commit c0ff7453bb5c ("cpuset,mm: fix no node to alloc memory when
changing cpuset's mems") wins a super prize for the largest number of
memory barriers entered into fast paths for one commit.
[get|put]_mems_allowed is incredibly heavy with pairs of full memory
barriers inserted into a number of hot paths. This was detected while
investigating at large page allocator slowdown introduced some time
after 2.6.32. The largest portion of this overhead was shown by
oprofile to be at an mfence introduced by this commit into the page
allocator hot path.
For extra style points, the commit introduced the use of yield() in an
implementation of what looks like a spinning mutex.
This patch replaces the full memory barriers on both read and write
sides with a sequence counter with just read barriers on the fast path
side. This is much cheaper on some architectures, including x86. The
main bulk of the patch is the retry logic if the nodemask changes in a
manner that can cause a false failure.
While updating the nodemask, a check is made to see if a false failure
is a risk. If it is, the sequence number gets bumped and parallel
allocators will briefly stall while the nodemask update takes place.
In a page fault test microbenchmark, oprofile samples from
__alloc_pages_nodemask went from 4.53% of all samples to 1.15%. The
actual results were
3.3.0-rc3 3.3.0-rc3
rc3-vanilla nobarrier-v2r1
Clients 1 UserTime 0.07 ( 0.00%) 0.08 (-14.19%)
Clients 2 UserTime 0.07 ( 0.00%) 0.07 ( 2.72%)
Clients 4 UserTime 0.08 ( 0.00%) 0.07 ( 3.29%)
Clients 1 SysTime 0.70 ( 0.00%) 0.65 ( 6.65%)
Clients 2 SysTime 0.85 ( 0.00%) 0.82 ( 3.65%)
Clients 4 SysTime 1.41 ( 0.00%) 1.41 ( 0.32%)
Clients 1 WallTime 0.77 ( 0.00%) 0.74 ( 4.19%)
Clients 2 WallTime 0.47 ( 0.00%) 0.45 ( 3.73%)
Clients 4 WallTime 0.38 ( 0.00%) 0.37 ( 1.58%)
Clients 1 Flt/sec/cpu 497620.28 ( 0.00%) 520294.53 ( 4.56%)
Clients 2 Flt/sec/cpu 414639.05 ( 0.00%) 429882.01 ( 3.68%)
Clients 4 Flt/sec/cpu 257959.16 ( 0.00%) 258761.48 ( 0.31%)
Clients 1 Flt/sec 495161.39 ( 0.00%) 517292.87 ( 4.47%)
Clients 2 Flt/sec 820325.95 ( 0.00%) 850289.77 ( 3.65%)
Clients 4 Flt/sec 1020068.93 ( 0.00%) 1022674.06 ( 0.26%)
MMTests Statistics: duration
Sys Time Running Test (seconds) 135.68 132.17
User+Sys Time Running Test (seconds) 164.2 160.13
Total Elapsed Time (seconds) 123.46 120.87
The overall improvement is small but the System CPU time is much
improved and roughly in correlation to what oprofile reported (these
performance figures are without profiling so skew is expected). The
actual number of page faults is noticeably improved.
For benchmarks like kernel builds, the overall benefit is marginal but
the system CPU time is slightly reduced.
To test the actual bug the commit fixed I opened two terminals. The
first ran within a cpuset and continually ran a small program that
faulted 100M of anonymous data. In a second window, the nodemask of the
cpuset was continually randomised in a loop.
Without the commit, the program would fail every so often (usually
within 10 seconds) and obviously with the commit everything worked fine.
With this patch applied, it also worked fine so the fix should be
functionally equivalent.
Signed-off-by: Mel Gorman <mgorman@suse.de>
Cc: Miao Xie <miaox@cn.fujitsu.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Christoph Lameter <cl@linux.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-21 16:34:11 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
2007-05-09 02:32:39 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2007-05-09 02:32:39 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2016-05-19 17:10:43 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-09 02:32:39 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2008-01-07 23:20:26 -08:00
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
cpuset: mm: reduce large amounts of memory barrier related damage v3
Commit c0ff7453bb5c ("cpuset,mm: fix no node to alloc memory when
changing cpuset's mems") wins a super prize for the largest number of
memory barriers entered into fast paths for one commit.
[get|put]_mems_allowed is incredibly heavy with pairs of full memory
barriers inserted into a number of hot paths. This was detected while
investigating at large page allocator slowdown introduced some time
after 2.6.32. The largest portion of this overhead was shown by
oprofile to be at an mfence introduced by this commit into the page
allocator hot path.
For extra style points, the commit introduced the use of yield() in an
implementation of what looks like a spinning mutex.
This patch replaces the full memory barriers on both read and write
sides with a sequence counter with just read barriers on the fast path
side. This is much cheaper on some architectures, including x86. The
main bulk of the patch is the retry logic if the nodemask changes in a
manner that can cause a false failure.
While updating the nodemask, a check is made to see if a false failure
is a risk. If it is, the sequence number gets bumped and parallel
allocators will briefly stall while the nodemask update takes place.
In a page fault test microbenchmark, oprofile samples from
__alloc_pages_nodemask went from 4.53% of all samples to 1.15%. The
actual results were
3.3.0-rc3 3.3.0-rc3
rc3-vanilla nobarrier-v2r1
Clients 1 UserTime 0.07 ( 0.00%) 0.08 (-14.19%)
Clients 2 UserTime 0.07 ( 0.00%) 0.07 ( 2.72%)
Clients 4 UserTime 0.08 ( 0.00%) 0.07 ( 3.29%)
Clients 1 SysTime 0.70 ( 0.00%) 0.65 ( 6.65%)
Clients 2 SysTime 0.85 ( 0.00%) 0.82 ( 3.65%)
Clients 4 SysTime 1.41 ( 0.00%) 1.41 ( 0.32%)
Clients 1 WallTime 0.77 ( 0.00%) 0.74 ( 4.19%)
Clients 2 WallTime 0.47 ( 0.00%) 0.45 ( 3.73%)
Clients 4 WallTime 0.38 ( 0.00%) 0.37 ( 1.58%)
Clients 1 Flt/sec/cpu 497620.28 ( 0.00%) 520294.53 ( 4.56%)
Clients 2 Flt/sec/cpu 414639.05 ( 0.00%) 429882.01 ( 3.68%)
Clients 4 Flt/sec/cpu 257959.16 ( 0.00%) 258761.48 ( 0.31%)
Clients 1 Flt/sec 495161.39 ( 0.00%) 517292.87 ( 4.47%)
Clients 2 Flt/sec 820325.95 ( 0.00%) 850289.77 ( 3.65%)
Clients 4 Flt/sec 1020068.93 ( 0.00%) 1022674.06 ( 0.26%)
MMTests Statistics: duration
Sys Time Running Test (seconds) 135.68 132.17
User+Sys Time Running Test (seconds) 164.2 160.13
Total Elapsed Time (seconds) 123.46 120.87
The overall improvement is small but the System CPU time is much
improved and roughly in correlation to what oprofile reported (these
performance figures are without profiling so skew is expected). The
actual number of page faults is noticeably improved.
For benchmarks like kernel builds, the overall benefit is marginal but
the system CPU time is slightly reduced.
To test the actual bug the commit fixed I opened two terminals. The
first ran within a cpuset and continually ran a small program that
faulted 100M of anonymous data. In a second window, the nodemask of the
cpuset was continually randomised in a loop.
Without the commit, the program would fail every so often (usually
within 10 seconds) and obviously with the commit everything worked fine.
With this patch applied, it also worked fine so the fix should be
functionally equivalent.
Signed-off-by: Mel Gorman <mgorman@suse.de>
Cc: Miao Xie <miaox@cn.fujitsu.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Christoph Lameter <cl@linux.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-21 16:34:11 -07:00
|
|
|
|
2014-04-03 14:47:24 -07:00
|
|
|
|
mm/slub: enable debugging memory wasting of kmalloc
kmalloc's API family is critical for mm, with one nature that it will
round up the request size to a fixed one (mostly power of 2). Say
when user requests memory for '2^n + 1' bytes, actually 2^(n+1) bytes
could be allocated, so in worst case, there is around 50% memory
space waste.
The wastage is not a big issue for requests that get allocated/freed
quickly, but may cause problems with objects that have longer life
time.
We've met a kernel boot OOM panic (v5.10), and from the dumped slab
info:
[ 26.062145] kmalloc-2k 814056KB 814056KB
From debug we found there are huge number of 'struct iova_magazine',
whose size is 1032 bytes (1024 + 8), so each allocation will waste
1016 bytes. Though the issue was solved by giving the right (bigger)
size of RAM, it is still nice to optimize the size (either use a
kmalloc friendly size or create a dedicated slab for it).
And from lkml archive, there was another crash kernel OOM case [1]
back in 2019, which seems to be related with the similar slab waste
situation, as the log is similar:
[ 4.332648] iommu: Adding device 0000:20:02.0 to group 16
[ 4.338946] swapper/0 invoked oom-killer: gfp_mask=0x6040c0(GFP_KERNEL|__GFP_COMP), nodemask=(null), order=0, oom_score_adj=0
...
[ 4.857565] kmalloc-2048 59164KB 59164KB
The crash kernel only has 256M memory, and 59M is pretty big here.
(Note: the related code has been changed and optimised in recent
kernel [2], these logs are just picked to demo the problem, also
a patch changing its size to 1024 bytes has been merged)
So add an way to track each kmalloc's memory waste info, and
leverage the existing SLUB debug framework (specifically
SLUB_STORE_USER) to show its call stack of original allocation,
so that user can evaluate the waste situation, identify some hot
spots and optimize accordingly, for a better utilization of memory.
The waste info is integrated into existing interface:
'/sys/kernel/debug/slab/kmalloc-xx/alloc_traces', one example of
'kmalloc-4k' after boot is:
126 ixgbe_alloc_q_vector+0xbe/0x830 [ixgbe] waste=233856/1856 age=280763/281414/282065 pid=1330 cpus=32 nodes=1
__kmem_cache_alloc_node+0x11f/0x4e0
__kmalloc_node+0x4e/0x140
ixgbe_alloc_q_vector+0xbe/0x830 [ixgbe]
ixgbe_init_interrupt_scheme+0x2ae/0xc90 [ixgbe]
ixgbe_probe+0x165f/0x1d20 [ixgbe]
local_pci_probe+0x78/0xc0
work_for_cpu_fn+0x26/0x40
...
which means in 'kmalloc-4k' slab, there are 126 requests of
2240 bytes which got a 4KB space (wasting 1856 bytes each
and 233856 bytes in total), from ixgbe_alloc_q_vector().
And when system starts some real workload like multiple docker
instances, there could are more severe waste.
[1]. https://lkml.org/lkml/2019/8/12/266
[2]. https://lore.kernel.org/lkml/2920df89-9975-5785-f79b-257d3052dfaf@huawei.com/
[Thanks Hyeonggon for pointing out several bugs about sorting/format]
[Thanks Vlastimil for suggesting way to reduce memory usage of
orig_size and keep it only for kmalloc objects]
Signed-off-by: Feng Tang <feng.tang@intel.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Robin Murphy <robin.murphy@arm.com>
Cc: John Garry <john.garry@huawei.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2022-09-13 14:54:20 +08:00
|
|
|
|
2020-06-03 15:59:01 -07:00
|
|
|
|
cpuset: mm: reduce large amounts of memory barrier related damage v3
Commit c0ff7453bb5c ("cpuset,mm: fix no node to alloc memory when
changing cpuset's mems") wins a super prize for the largest number of
memory barriers entered into fast paths for one commit.
[get|put]_mems_allowed is incredibly heavy with pairs of full memory
barriers inserted into a number of hot paths. This was detected while
investigating at large page allocator slowdown introduced some time
after 2.6.32. The largest portion of this overhead was shown by
oprofile to be at an mfence introduced by this commit into the page
allocator hot path.
For extra style points, the commit introduced the use of yield() in an
implementation of what looks like a spinning mutex.
This patch replaces the full memory barriers on both read and write
sides with a sequence counter with just read barriers on the fast path
side. This is much cheaper on some architectures, including x86. The
main bulk of the patch is the retry logic if the nodemask changes in a
manner that can cause a false failure.
While updating the nodemask, a check is made to see if a false failure
is a risk. If it is, the sequence number gets bumped and parallel
allocators will briefly stall while the nodemask update takes place.
In a page fault test microbenchmark, oprofile samples from
__alloc_pages_nodemask went from 4.53% of all samples to 1.15%. The
actual results were
3.3.0-rc3 3.3.0-rc3
rc3-vanilla nobarrier-v2r1
Clients 1 UserTime 0.07 ( 0.00%) 0.08 (-14.19%)
Clients 2 UserTime 0.07 ( 0.00%) 0.07 ( 2.72%)
Clients 4 UserTime 0.08 ( 0.00%) 0.07 ( 3.29%)
Clients 1 SysTime 0.70 ( 0.00%) 0.65 ( 6.65%)
Clients 2 SysTime 0.85 ( 0.00%) 0.82 ( 3.65%)
Clients 4 SysTime 1.41 ( 0.00%) 1.41 ( 0.32%)
Clients 1 WallTime 0.77 ( 0.00%) 0.74 ( 4.19%)
Clients 2 WallTime 0.47 ( 0.00%) 0.45 ( 3.73%)
Clients 4 WallTime 0.38 ( 0.00%) 0.37 ( 1.58%)
Clients 1 Flt/sec/cpu 497620.28 ( 0.00%) 520294.53 ( 4.56%)
Clients 2 Flt/sec/cpu 414639.05 ( 0.00%) 429882.01 ( 3.68%)
Clients 4 Flt/sec/cpu 257959.16 ( 0.00%) 258761.48 ( 0.31%)
Clients 1 Flt/sec 495161.39 ( 0.00%) 517292.87 ( 4.47%)
Clients 2 Flt/sec 820325.95 ( 0.00%) 850289.77 ( 3.65%)
Clients 4 Flt/sec 1020068.93 ( 0.00%) 1022674.06 ( 0.26%)
MMTests Statistics: duration
Sys Time Running Test (seconds) 135.68 132.17
User+Sys Time Running Test (seconds) 164.2 160.13
Total Elapsed Time (seconds) 123.46 120.87
The overall improvement is small but the System CPU time is much
improved and roughly in correlation to what oprofile reported (these
performance figures are without profiling so skew is expected). The
actual number of page faults is noticeably improved.
For benchmarks like kernel builds, the overall benefit is marginal but
the system CPU time is slightly reduced.
To test the actual bug the commit fixed I opened two terminals. The
first ran within a cpuset and continually ran a small program that
faulted 100M of anonymous data. In a second window, the nodemask of the
cpuset was continually randomised in a loop.
Without the commit, the program would fail every so often (usually
within 10 seconds) and obviously with the commit everything worked fine.
With this patch applied, it also worked fine so the fix should be
functionally equivalent.
Signed-off-by: Mel Gorman <mgorman@suse.de>
Cc: Miao Xie <miaox@cn.fujitsu.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Christoph Lameter <cl@linux.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-21 16:34:11 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
cpuset: mm: reduce large amounts of memory barrier related damage v3
Commit c0ff7453bb5c ("cpuset,mm: fix no node to alloc memory when
changing cpuset's mems") wins a super prize for the largest number of
memory barriers entered into fast paths for one commit.
[get|put]_mems_allowed is incredibly heavy with pairs of full memory
barriers inserted into a number of hot paths. This was detected while
investigating at large page allocator slowdown introduced some time
after 2.6.32. The largest portion of this overhead was shown by
oprofile to be at an mfence introduced by this commit into the page
allocator hot path.
For extra style points, the commit introduced the use of yield() in an
implementation of what looks like a spinning mutex.
This patch replaces the full memory barriers on both read and write
sides with a sequence counter with just read barriers on the fast path
side. This is much cheaper on some architectures, including x86. The
main bulk of the patch is the retry logic if the nodemask changes in a
manner that can cause a false failure.
While updating the nodemask, a check is made to see if a false failure
is a risk. If it is, the sequence number gets bumped and parallel
allocators will briefly stall while the nodemask update takes place.
In a page fault test microbenchmark, oprofile samples from
__alloc_pages_nodemask went from 4.53% of all samples to 1.15%. The
actual results were
3.3.0-rc3 3.3.0-rc3
rc3-vanilla nobarrier-v2r1
Clients 1 UserTime 0.07 ( 0.00%) 0.08 (-14.19%)
Clients 2 UserTime 0.07 ( 0.00%) 0.07 ( 2.72%)
Clients 4 UserTime 0.08 ( 0.00%) 0.07 ( 3.29%)
Clients 1 SysTime 0.70 ( 0.00%) 0.65 ( 6.65%)
Clients 2 SysTime 0.85 ( 0.00%) 0.82 ( 3.65%)
Clients 4 SysTime 1.41 ( 0.00%) 1.41 ( 0.32%)
Clients 1 WallTime 0.77 ( 0.00%) 0.74 ( 4.19%)
Clients 2 WallTime 0.47 ( 0.00%) 0.45 ( 3.73%)
Clients 4 WallTime 0.38 ( 0.00%) 0.37 ( 1.58%)
Clients 1 Flt/sec/cpu 497620.28 ( 0.00%) 520294.53 ( 4.56%)
Clients 2 Flt/sec/cpu 414639.05 ( 0.00%) 429882.01 ( 3.68%)
Clients 4 Flt/sec/cpu 257959.16 ( 0.00%) 258761.48 ( 0.31%)
Clients 1 Flt/sec 495161.39 ( 0.00%) 517292.87 ( 4.47%)
Clients 2 Flt/sec 820325.95 ( 0.00%) 850289.77 ( 3.65%)
Clients 4 Flt/sec 1020068.93 ( 0.00%) 1022674.06 ( 0.26%)
MMTests Statistics: duration
Sys Time Running Test (seconds) 135.68 132.17
User+Sys Time Running Test (seconds) 164.2 160.13
Total Elapsed Time (seconds) 123.46 120.87
The overall improvement is small but the System CPU time is much
improved and roughly in correlation to what oprofile reported (these
performance figures are without profiling so skew is expected). The
actual number of page faults is noticeably improved.
For benchmarks like kernel builds, the overall benefit is marginal but
the system CPU time is slightly reduced.
To test the actual bug the commit fixed I opened two terminals. The
first ran within a cpuset and continually ran a small program that
faulted 100M of anonymous data. In a second window, the nodemask of the
cpuset was continually randomised in a loop.
Without the commit, the program would fail every so often (usually
within 10 seconds) and obviously with the commit everything worked fine.
With this patch applied, it also worked fine so the fix should be
functionally equivalent.
Signed-off-by: Mel Gorman <mgorman@suse.de>
Cc: Miao Xie <miaox@cn.fujitsu.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Christoph Lameter <cl@linux.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-21 16:34:11 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
mm/slub: enable debugging memory wasting of kmalloc
kmalloc's API family is critical for mm, with one nature that it will
round up the request size to a fixed one (mostly power of 2). Say
when user requests memory for '2^n + 1' bytes, actually 2^(n+1) bytes
could be allocated, so in worst case, there is around 50% memory
space waste.
The wastage is not a big issue for requests that get allocated/freed
quickly, but may cause problems with objects that have longer life
time.
We've met a kernel boot OOM panic (v5.10), and from the dumped slab
info:
[ 26.062145] kmalloc-2k 814056KB 814056KB
From debug we found there are huge number of 'struct iova_magazine',
whose size is 1032 bytes (1024 + 8), so each allocation will waste
1016 bytes. Though the issue was solved by giving the right (bigger)
size of RAM, it is still nice to optimize the size (either use a
kmalloc friendly size or create a dedicated slab for it).
And from lkml archive, there was another crash kernel OOM case [1]
back in 2019, which seems to be related with the similar slab waste
situation, as the log is similar:
[ 4.332648] iommu: Adding device 0000:20:02.0 to group 16
[ 4.338946] swapper/0 invoked oom-killer: gfp_mask=0x6040c0(GFP_KERNEL|__GFP_COMP), nodemask=(null), order=0, oom_score_adj=0
...
[ 4.857565] kmalloc-2048 59164KB 59164KB
The crash kernel only has 256M memory, and 59M is pretty big here.
(Note: the related code has been changed and optimised in recent
kernel [2], these logs are just picked to demo the problem, also
a patch changing its size to 1024 bytes has been merged)
So add an way to track each kmalloc's memory waste info, and
leverage the existing SLUB debug framework (specifically
SLUB_STORE_USER) to show its call stack of original allocation,
so that user can evaluate the waste situation, identify some hot
spots and optimize accordingly, for a better utilization of memory.
The waste info is integrated into existing interface:
'/sys/kernel/debug/slab/kmalloc-xx/alloc_traces', one example of
'kmalloc-4k' after boot is:
126 ixgbe_alloc_q_vector+0xbe/0x830 [ixgbe] waste=233856/1856 age=280763/281414/282065 pid=1330 cpus=32 nodes=1
__kmem_cache_alloc_node+0x11f/0x4e0
__kmalloc_node+0x4e/0x140
ixgbe_alloc_q_vector+0xbe/0x830 [ixgbe]
ixgbe_init_interrupt_scheme+0x2ae/0xc90 [ixgbe]
ixgbe_probe+0x165f/0x1d20 [ixgbe]
local_pci_probe+0x78/0xc0
work_for_cpu_fn+0x26/0x40
...
which means in 'kmalloc-4k' slab, there are 126 requests of
2240 bytes which got a 4KB space (wasting 1856 bytes each
and 233856 bytes in total), from ixgbe_alloc_q_vector().
And when system starts some real workload like multiple docker
instances, there could are more severe waste.
[1]. https://lkml.org/lkml/2019/8/12/266
[2]. https://lore.kernel.org/lkml/2920df89-9975-5785-f79b-257d3052dfaf@huawei.com/
[Thanks Hyeonggon for pointing out several bugs about sorting/format]
[Thanks Vlastimil for suggesting way to reduce memory usage of
orig_size and keep it only for kmalloc objects]
Signed-off-by: Feng Tang <feng.tang@intel.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Robin Murphy <robin.murphy@arm.com>
Cc: John Garry <john.garry@huawei.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2022-09-13 14:54:20 +08:00
|
|
|
|
cpuset: mm: reduce large amounts of memory barrier related damage v3
Commit c0ff7453bb5c ("cpuset,mm: fix no node to alloc memory when
changing cpuset's mems") wins a super prize for the largest number of
memory barriers entered into fast paths for one commit.
[get|put]_mems_allowed is incredibly heavy with pairs of full memory
barriers inserted into a number of hot paths. This was detected while
investigating at large page allocator slowdown introduced some time
after 2.6.32. The largest portion of this overhead was shown by
oprofile to be at an mfence introduced by this commit into the page
allocator hot path.
For extra style points, the commit introduced the use of yield() in an
implementation of what looks like a spinning mutex.
This patch replaces the full memory barriers on both read and write
sides with a sequence counter with just read barriers on the fast path
side. This is much cheaper on some architectures, including x86. The
main bulk of the patch is the retry logic if the nodemask changes in a
manner that can cause a false failure.
While updating the nodemask, a check is made to see if a false failure
is a risk. If it is, the sequence number gets bumped and parallel
allocators will briefly stall while the nodemask update takes place.
In a page fault test microbenchmark, oprofile samples from
__alloc_pages_nodemask went from 4.53% of all samples to 1.15%. The
actual results were
3.3.0-rc3 3.3.0-rc3
rc3-vanilla nobarrier-v2r1
Clients 1 UserTime 0.07 ( 0.00%) 0.08 (-14.19%)
Clients 2 UserTime 0.07 ( 0.00%) 0.07 ( 2.72%)
Clients 4 UserTime 0.08 ( 0.00%) 0.07 ( 3.29%)
Clients 1 SysTime 0.70 ( 0.00%) 0.65 ( 6.65%)
Clients 2 SysTime 0.85 ( 0.00%) 0.82 ( 3.65%)
Clients 4 SysTime 1.41 ( 0.00%) 1.41 ( 0.32%)
Clients 1 WallTime 0.77 ( 0.00%) 0.74 ( 4.19%)
Clients 2 WallTime 0.47 ( 0.00%) 0.45 ( 3.73%)
Clients 4 WallTime 0.38 ( 0.00%) 0.37 ( 1.58%)
Clients 1 Flt/sec/cpu 497620.28 ( 0.00%) 520294.53 ( 4.56%)
Clients 2 Flt/sec/cpu 414639.05 ( 0.00%) 429882.01 ( 3.68%)
Clients 4 Flt/sec/cpu 257959.16 ( 0.00%) 258761.48 ( 0.31%)
Clients 1 Flt/sec 495161.39 ( 0.00%) 517292.87 ( 4.47%)
Clients 2 Flt/sec 820325.95 ( 0.00%) 850289.77 ( 3.65%)
Clients 4 Flt/sec 1020068.93 ( 0.00%) 1022674.06 ( 0.26%)
MMTests Statistics: duration
Sys Time Running Test (seconds) 135.68 132.17
User+Sys Time Running Test (seconds) 164.2 160.13
Total Elapsed Time (seconds) 123.46 120.87
The overall improvement is small but the System CPU time is much
improved and roughly in correlation to what oprofile reported (these
performance figures are without profiling so skew is expected). The
actual number of page faults is noticeably improved.
For benchmarks like kernel builds, the overall benefit is marginal but
the system CPU time is slightly reduced.
To test the actual bug the commit fixed I opened two terminals. The
first ran within a cpuset and continually ran a small program that
faulted 100M of anonymous data. In a second window, the nodemask of the
cpuset was continually randomised in a loop.
Without the commit, the program would fail every so often (usually
within 10 seconds) and obviously with the commit everything worked fine.
With this patch applied, it also worked fine so the fix should be
functionally equivalent.
Signed-off-by: Mel Gorman <mgorman@suse.de>
Cc: Miao Xie <miaox@cn.fujitsu.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Christoph Lameter <cl@linux.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-21 16:34:11 -07:00
|
|
|
|
2023-11-02 03:23:23 +00:00
|
|
|
|
|
|
|
|
|
cpuset: mm: reduce large amounts of memory barrier related damage v3
Commit c0ff7453bb5c ("cpuset,mm: fix no node to alloc memory when
changing cpuset's mems") wins a super prize for the largest number of
memory barriers entered into fast paths for one commit.
[get|put]_mems_allowed is incredibly heavy with pairs of full memory
barriers inserted into a number of hot paths. This was detected while
investigating at large page allocator slowdown introduced some time
after 2.6.32. The largest portion of this overhead was shown by
oprofile to be at an mfence introduced by this commit into the page
allocator hot path.
For extra style points, the commit introduced the use of yield() in an
implementation of what looks like a spinning mutex.
This patch replaces the full memory barriers on both read and write
sides with a sequence counter with just read barriers on the fast path
side. This is much cheaper on some architectures, including x86. The
main bulk of the patch is the retry logic if the nodemask changes in a
manner that can cause a false failure.
While updating the nodemask, a check is made to see if a false failure
is a risk. If it is, the sequence number gets bumped and parallel
allocators will briefly stall while the nodemask update takes place.
In a page fault test microbenchmark, oprofile samples from
__alloc_pages_nodemask went from 4.53% of all samples to 1.15%. The
actual results were
3.3.0-rc3 3.3.0-rc3
rc3-vanilla nobarrier-v2r1
Clients 1 UserTime 0.07 ( 0.00%) 0.08 (-14.19%)
Clients 2 UserTime 0.07 ( 0.00%) 0.07 ( 2.72%)
Clients 4 UserTime 0.08 ( 0.00%) 0.07 ( 3.29%)
Clients 1 SysTime 0.70 ( 0.00%) 0.65 ( 6.65%)
Clients 2 SysTime 0.85 ( 0.00%) 0.82 ( 3.65%)
Clients 4 SysTime 1.41 ( 0.00%) 1.41 ( 0.32%)
Clients 1 WallTime 0.77 ( 0.00%) 0.74 ( 4.19%)
Clients 2 WallTime 0.47 ( 0.00%) 0.45 ( 3.73%)
Clients 4 WallTime 0.38 ( 0.00%) 0.37 ( 1.58%)
Clients 1 Flt/sec/cpu 497620.28 ( 0.00%) 520294.53 ( 4.56%)
Clients 2 Flt/sec/cpu 414639.05 ( 0.00%) 429882.01 ( 3.68%)
Clients 4 Flt/sec/cpu 257959.16 ( 0.00%) 258761.48 ( 0.31%)
Clients 1 Flt/sec 495161.39 ( 0.00%) 517292.87 ( 4.47%)
Clients 2 Flt/sec 820325.95 ( 0.00%) 850289.77 ( 3.65%)
Clients 4 Flt/sec 1020068.93 ( 0.00%) 1022674.06 ( 0.26%)
MMTests Statistics: duration
Sys Time Running Test (seconds) 135.68 132.17
User+Sys Time Running Test (seconds) 164.2 160.13
Total Elapsed Time (seconds) 123.46 120.87
The overall improvement is small but the System CPU time is much
improved and roughly in correlation to what oprofile reported (these
performance figures are without profiling so skew is expected). The
actual number of page faults is noticeably improved.
For benchmarks like kernel builds, the overall benefit is marginal but
the system CPU time is slightly reduced.
To test the actual bug the commit fixed I opened two terminals. The
first ran within a cpuset and continually ran a small program that
faulted 100M of anonymous data. In a second window, the nodemask of the
cpuset was continually randomised in a loop.
Without the commit, the program would fail every so often (usually
within 10 seconds) and obviously with the commit everything worked fine.
With this patch applied, it also worked fine so the fix should be
functionally equivalent.
Signed-off-by: Mel Gorman <mgorman@suse.de>
Cc: Miao Xie <miaox@cn.fujitsu.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Christoph Lameter <cl@linux.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-21 16:34:11 -07:00
|
|
|
|
2014-04-03 14:47:24 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
cpuset: mm: reduce large amounts of memory barrier related damage v3
Commit c0ff7453bb5c ("cpuset,mm: fix no node to alloc memory when
changing cpuset's mems") wins a super prize for the largest number of
memory barriers entered into fast paths for one commit.
[get|put]_mems_allowed is incredibly heavy with pairs of full memory
barriers inserted into a number of hot paths. This was detected while
investigating at large page allocator slowdown introduced some time
after 2.6.32. The largest portion of this overhead was shown by
oprofile to be at an mfence introduced by this commit into the page
allocator hot path.
For extra style points, the commit introduced the use of yield() in an
implementation of what looks like a spinning mutex.
This patch replaces the full memory barriers on both read and write
sides with a sequence counter with just read barriers on the fast path
side. This is much cheaper on some architectures, including x86. The
main bulk of the patch is the retry logic if the nodemask changes in a
manner that can cause a false failure.
While updating the nodemask, a check is made to see if a false failure
is a risk. If it is, the sequence number gets bumped and parallel
allocators will briefly stall while the nodemask update takes place.
In a page fault test microbenchmark, oprofile samples from
__alloc_pages_nodemask went from 4.53% of all samples to 1.15%. The
actual results were
3.3.0-rc3 3.3.0-rc3
rc3-vanilla nobarrier-v2r1
Clients 1 UserTime 0.07 ( 0.00%) 0.08 (-14.19%)
Clients 2 UserTime 0.07 ( 0.00%) 0.07 ( 2.72%)
Clients 4 UserTime 0.08 ( 0.00%) 0.07 ( 3.29%)
Clients 1 SysTime 0.70 ( 0.00%) 0.65 ( 6.65%)
Clients 2 SysTime 0.85 ( 0.00%) 0.82 ( 3.65%)
Clients 4 SysTime 1.41 ( 0.00%) 1.41 ( 0.32%)
Clients 1 WallTime 0.77 ( 0.00%) 0.74 ( 4.19%)
Clients 2 WallTime 0.47 ( 0.00%) 0.45 ( 3.73%)
Clients 4 WallTime 0.38 ( 0.00%) 0.37 ( 1.58%)
Clients 1 Flt/sec/cpu 497620.28 ( 0.00%) 520294.53 ( 4.56%)
Clients 2 Flt/sec/cpu 414639.05 ( 0.00%) 429882.01 ( 3.68%)
Clients 4 Flt/sec/cpu 257959.16 ( 0.00%) 258761.48 ( 0.31%)
Clients 1 Flt/sec 495161.39 ( 0.00%) 517292.87 ( 4.47%)
Clients 2 Flt/sec 820325.95 ( 0.00%) 850289.77 ( 3.65%)
Clients 4 Flt/sec 1020068.93 ( 0.00%) 1022674.06 ( 0.26%)
MMTests Statistics: duration
Sys Time Running Test (seconds) 135.68 132.17
User+Sys Time Running Test (seconds) 164.2 160.13
Total Elapsed Time (seconds) 123.46 120.87
The overall improvement is small but the System CPU time is much
improved and roughly in correlation to what oprofile reported (these
performance figures are without profiling so skew is expected). The
actual number of page faults is noticeably improved.
For benchmarks like kernel builds, the overall benefit is marginal but
the system CPU time is slightly reduced.
To test the actual bug the commit fixed I opened two terminals. The
first ran within a cpuset and continually ran a small program that
faulted 100M of anonymous data. In a second window, the nodemask of the
cpuset was continually randomised in a loop.
Without the commit, the program would fail every so often (usually
within 10 seconds) and obviously with the commit everything worked fine.
With this patch applied, it also worked fine so the fix should be
functionally equivalent.
Signed-off-by: Mel Gorman <mgorman@suse.de>
Cc: Miao Xie <miaox@cn.fujitsu.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Christoph Lameter <cl@linux.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-21 16:34:11 -07:00
|
|
|
|
2023-11-02 03:23:23 +00:00
|
|
|
|
cpuset: mm: reduce large amounts of memory barrier related damage v3
Commit c0ff7453bb5c ("cpuset,mm: fix no node to alloc memory when
changing cpuset's mems") wins a super prize for the largest number of
memory barriers entered into fast paths for one commit.
[get|put]_mems_allowed is incredibly heavy with pairs of full memory
barriers inserted into a number of hot paths. This was detected while
investigating at large page allocator slowdown introduced some time
after 2.6.32. The largest portion of this overhead was shown by
oprofile to be at an mfence introduced by this commit into the page
allocator hot path.
For extra style points, the commit introduced the use of yield() in an
implementation of what looks like a spinning mutex.
This patch replaces the full memory barriers on both read and write
sides with a sequence counter with just read barriers on the fast path
side. This is much cheaper on some architectures, including x86. The
main bulk of the patch is the retry logic if the nodemask changes in a
manner that can cause a false failure.
While updating the nodemask, a check is made to see if a false failure
is a risk. If it is, the sequence number gets bumped and parallel
allocators will briefly stall while the nodemask update takes place.
In a page fault test microbenchmark, oprofile samples from
__alloc_pages_nodemask went from 4.53% of all samples to 1.15%. The
actual results were
3.3.0-rc3 3.3.0-rc3
rc3-vanilla nobarrier-v2r1
Clients 1 UserTime 0.07 ( 0.00%) 0.08 (-14.19%)
Clients 2 UserTime 0.07 ( 0.00%) 0.07 ( 2.72%)
Clients 4 UserTime 0.08 ( 0.00%) 0.07 ( 3.29%)
Clients 1 SysTime 0.70 ( 0.00%) 0.65 ( 6.65%)
Clients 2 SysTime 0.85 ( 0.00%) 0.82 ( 3.65%)
Clients 4 SysTime 1.41 ( 0.00%) 1.41 ( 0.32%)
Clients 1 WallTime 0.77 ( 0.00%) 0.74 ( 4.19%)
Clients 2 WallTime 0.47 ( 0.00%) 0.45 ( 3.73%)
Clients 4 WallTime 0.38 ( 0.00%) 0.37 ( 1.58%)
Clients 1 Flt/sec/cpu 497620.28 ( 0.00%) 520294.53 ( 4.56%)
Clients 2 Flt/sec/cpu 414639.05 ( 0.00%) 429882.01 ( 3.68%)
Clients 4 Flt/sec/cpu 257959.16 ( 0.00%) 258761.48 ( 0.31%)
Clients 1 Flt/sec 495161.39 ( 0.00%) 517292.87 ( 4.47%)
Clients 2 Flt/sec 820325.95 ( 0.00%) 850289.77 ( 3.65%)
Clients 4 Flt/sec 1020068.93 ( 0.00%) 1022674.06 ( 0.26%)
MMTests Statistics: duration
Sys Time Running Test (seconds) 135.68 132.17
User+Sys Time Running Test (seconds) 164.2 160.13
Total Elapsed Time (seconds) 123.46 120.87
The overall improvement is small but the System CPU time is much
improved and roughly in correlation to what oprofile reported (these
performance figures are without profiling so skew is expected). The
actual number of page faults is noticeably improved.
For benchmarks like kernel builds, the overall benefit is marginal but
the system CPU time is slightly reduced.
To test the actual bug the commit fixed I opened two terminals. The
first ran within a cpuset and continually ran a small program that
faulted 100M of anonymous data. In a second window, the nodemask of the
cpuset was continually randomised in a loop.
Without the commit, the program would fail every so often (usually
within 10 seconds) and obviously with the commit everything worked fine.
With this patch applied, it also worked fine so the fix should be
functionally equivalent.
Signed-off-by: Mel Gorman <mgorman@suse.de>
Cc: Miao Xie <miaox@cn.fujitsu.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Christoph Lameter <cl@linux.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-21 16:34:11 -07:00
|
|
|
|
2010-05-24 14:32:08 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2014-04-03 14:47:24 -07:00
|
|
|
|
2019-05-13 17:16:09 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-11-15 16:55:15 +01:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2023-11-02 03:23:23 +00:00
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2023-11-02 03:23:23 +00:00
|
|
|
|
2014-10-09 15:26:15 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2023-11-02 03:23:23 +00:00
|
|
|
|
mm/slub: Reduce memory consumption in extreme scenarios
When kmalloc_node() is called without __GFP_THISNODE and the target node
lacks sufficient memory, SLUB allocates a folio from a different node
other than the requested node, instead of taking a partial slab from it.
However, since the allocated folio does not belong to the requested
node, on the following allocation it is deactivated and added to the
partial slab list of the node it belongs to.
This behavior can result in excessive memory usage when the requested
node has insufficient memory, as SLUB will repeatedly allocate folios
from other nodes without reusing the previously allocated ones.
To prevent memory wastage, when a preferred node is indicated (not
NUMA_NO_NODE) but without a prior __GFP_THISNODE constraint:
1) try to get a partial slab from target node only by having
__GFP_THISNODE in pc.flags for get_partial()
2) if 1) failed, try to allocate a new slab from target node with
GFP_NOWAIT | __GFP_THISNODE opportunistically.
3) if 2) failed, retry with original gfpflags which will allow
get_partial() try partial lists of other nodes before potentially
allocating new page from other nodes
Without a preferred node, or with __GFP_THISNODE constraint, the
behavior remains unchanged.
On qemu with 4 numa nodes and each numa has 1G memory. Write a test ko
to call kmalloc_node(196, GFP_KERNEL, 3) for (4 * 1024 + 4) * 1024 times.
cat /proc/slabinfo shows:
kmalloc-256 4200530 13519712 256 32 2 : tunables..
after this patch,
cat /proc/slabinfo shows:
kmalloc-256 4200558 4200768 256 32 2 : tunables..
Signed-off-by: Chen Jun <chenjun102@huawei.com>
Signed-off-by: Kefeng Wang <wangkefeng.wang@huawei.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2024-03-30 16:23:35 +08:00
|
|
|
|
2023-11-02 03:23:23 +00:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
mm/slub: enable debugging memory wasting of kmalloc
kmalloc's API family is critical for mm, with one nature that it will
round up the request size to a fixed one (mostly power of 2). Say
when user requests memory for '2^n + 1' bytes, actually 2^(n+1) bytes
could be allocated, so in worst case, there is around 50% memory
space waste.
The wastage is not a big issue for requests that get allocated/freed
quickly, but may cause problems with objects that have longer life
time.
We've met a kernel boot OOM panic (v5.10), and from the dumped slab
info:
[ 26.062145] kmalloc-2k 814056KB 814056KB
From debug we found there are huge number of 'struct iova_magazine',
whose size is 1032 bytes (1024 + 8), so each allocation will waste
1016 bytes. Though the issue was solved by giving the right (bigger)
size of RAM, it is still nice to optimize the size (either use a
kmalloc friendly size or create a dedicated slab for it).
And from lkml archive, there was another crash kernel OOM case [1]
back in 2019, which seems to be related with the similar slab waste
situation, as the log is similar:
[ 4.332648] iommu: Adding device 0000:20:02.0 to group 16
[ 4.338946] swapper/0 invoked oom-killer: gfp_mask=0x6040c0(GFP_KERNEL|__GFP_COMP), nodemask=(null), order=0, oom_score_adj=0
...
[ 4.857565] kmalloc-2048 59164KB 59164KB
The crash kernel only has 256M memory, and 59M is pretty big here.
(Note: the related code has been changed and optimised in recent
kernel [2], these logs are just picked to demo the problem, also
a patch changing its size to 1024 bytes has been merged)
So add an way to track each kmalloc's memory waste info, and
leverage the existing SLUB debug framework (specifically
SLUB_STORE_USER) to show its call stack of original allocation,
so that user can evaluate the waste situation, identify some hot
spots and optimize accordingly, for a better utilization of memory.
The waste info is integrated into existing interface:
'/sys/kernel/debug/slab/kmalloc-xx/alloc_traces', one example of
'kmalloc-4k' after boot is:
126 ixgbe_alloc_q_vector+0xbe/0x830 [ixgbe] waste=233856/1856 age=280763/281414/282065 pid=1330 cpus=32 nodes=1
__kmem_cache_alloc_node+0x11f/0x4e0
__kmalloc_node+0x4e/0x140
ixgbe_alloc_q_vector+0xbe/0x830 [ixgbe]
ixgbe_init_interrupt_scheme+0x2ae/0xc90 [ixgbe]
ixgbe_probe+0x165f/0x1d20 [ixgbe]
local_pci_probe+0x78/0xc0
work_for_cpu_fn+0x26/0x40
...
which means in 'kmalloc-4k' slab, there are 126 requests of
2240 bytes which got a 4KB space (wasting 1856 bytes each
and 233856 bytes in total), from ixgbe_alloc_q_vector().
And when system starts some real workload like multiple docker
instances, there could are more severe waste.
[1]. https://lkml.org/lkml/2019/8/12/266
[2]. https://lore.kernel.org/lkml/2920df89-9975-5785-f79b-257d3052dfaf@huawei.com/
[Thanks Hyeonggon for pointing out several bugs about sorting/format]
[Thanks Vlastimil for suggesting way to reduce memory usage of
orig_size and keep it only for kmalloc objects]
Signed-off-by: Feng Tang <feng.tang@intel.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Robin Murphy <robin.murphy@arm.com>
Cc: John Garry <john.garry@huawei.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2022-09-13 14:54:20 +08:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
2022-11-15 18:14:31 +01:00
|
|
|
|
|
|
|
|
|
2019-10-15 21:18:12 +02:00
|
|
|
|
2011-02-25 11:38:54 -06:00
|
|
|
|
2020-06-04 16:49:34 -07:00
|
|
|
|
2011-02-25 11:38:54 -06:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-11-15 18:14:31 +01:00
|
|
|
|
2011-02-25 11:38:54 -06:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2019-09-23 15:33:52 -07:00
|
|
|
|
2011-02-25 11:38:54 -06:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2019-09-23 15:33:52 -07:00
|
|
|
|
2011-02-25 11:38:54 -06:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2014-06-04 16:06:34 -07:00
|
|
|
|
2011-02-25 11:38:54 -06:00
|
|
|
|
2019-10-15 21:18:12 +02:00
|
|
|
|
2011-02-25 11:38:54 -06:00
|
|
|
|
2014-06-04 16:06:34 -07:00
|
|
|
|
2011-02-25 11:38:54 -06:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2014-06-04 16:06:34 -07:00
|
|
|
|
2011-02-25 11:38:54 -06:00
|
|
|
|
|
|
|
|
|
2014-06-04 16:06:34 -07:00
|
|
|
|
2011-02-25 11:38:54 -06:00
|
|
|
|
|
|
|
|
|
2011-03-22 13:35:00 -05:00
|
|
|
|
2011-02-25 11:38:54 -06:00
|
|
|
|
|
|
|
|
|
2012-09-28 16:34:05 +08:00
|
|
|
|
2011-02-25 11:38:54 -06:00
|
|
|
|
|
|
|
|
|
2021-05-22 01:59:38 +02:00
|
|
|
|
2011-02-25 11:38:54 -06:00
|
|
|
|
2021-05-22 01:59:38 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-02-25 11:38:54 -06:00
|
|
|
|
2011-06-01 12:25:52 -05:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2021-11-15 16:55:15 +01:00
|
|
|
|
2021-05-12 13:53:34 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2021-05-12 13:53:34 +02:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2022-03-07 07:40:56 +00:00
|
|
|
|
2021-02-24 12:01:19 -08:00
|
|
|
|
2011-08-24 08:57:52 +08:00
|
|
|
|
2021-05-12 13:59:58 +02:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
|
|
|
|
|
2008-02-07 17:47:41 -08:00
|
|
|
|
2024-04-27 16:51:54 +08:00
|
|
|
|
2009-12-18 16:26:23 -06:00
|
|
|
|
2011-08-24 08:57:52 +08:00
|
|
|
|
2007-05-10 03:15:16 -07:00
|
|
|
|
2011-06-01 12:25:52 -05:00
|
|
|
|
|
|
|
|
|
2021-02-24 12:01:19 -08:00
|
|
|
|
|
|
|
|
|
2011-06-01 12:25:52 -05:00
|
|
|
|
2021-02-24 12:01:19 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-06-01 12:25:52 -05:00
|
|
|
|
2020-06-01 21:45:47 -07:00
|
|
|
|
|
|
|
|
|
2021-02-24 12:01:19 -08:00
|
|
|
|
|
|
|
|
|
2020-06-01 21:45:47 -07:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2020-06-01 21:45:47 -07:00
|
|
|
|
|
|
|
|
|
2021-02-24 12:01:19 -08:00
|
|
|
|
|
|
|
|
|
2011-06-01 12:25:52 -05:00
|
|
|
|
2021-02-24 12:01:19 -08:00
|
|
|
|
2011-06-01 12:25:52 -05:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-11-15 16:55:15 +01:00
|
|
|
|
|
|
|
|
|
2011-06-01 12:25:52 -05:00
|
|
|
|
2023-11-02 03:23:28 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-06-01 12:25:52 -05:00
|
|
|
|
2023-11-02 03:23:28 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-06-01 12:25:52 -05:00
|
|
|
|
2023-11-02 03:23:28 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-03-07 07:40:56 +00:00
|
|
|
|
2011-06-01 12:25:52 -05:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2011-06-01 12:25:52 -05:00
|
|
|
|
2023-11-02 03:23:28 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-03-07 07:40:56 +00:00
|
|
|
|
2011-06-01 12:25:52 -05:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
2013-06-19 14:05:52 +09:00
|
|
|
|
2023-11-02 03:23:29 +00:00
|
|
|
|
2021-05-20 16:39:51 +02:00
|
|
|
|
slub: refactoring unfreeze_partials()
Current implementation of unfreeze_partials() is so complicated,
but benefit from it is insignificant. In addition many code in
do {} while loop have a bad influence to a fail rate of cmpxchg_double_slab.
Under current implementation which test status of cpu partial slab
and acquire list_lock in do {} while loop,
we don't need to acquire a list_lock and gain a little benefit
when front of the cpu partial slab is to be discarded, but this is a rare case.
In case that add_partial is performed and cmpxchg_double_slab is failed,
remove_partial should be called case by case.
I think that these are disadvantages of current implementation,
so I do refactoring unfreeze_partials().
Minimizing code in do {} while loop introduce a reduced fail rate
of cmpxchg_double_slab. Below is output of 'slabinfo -r kmalloc-256'
when './perf stat -r 33 hackbench 50 process 4000 > /dev/null' is done.
** before **
Cmpxchg_double Looping
------------------------
Locked Cmpxchg Double redos 182685
Unlocked Cmpxchg Double redos 0
** after **
Cmpxchg_double Looping
------------------------
Locked Cmpxchg Double redos 177995
Unlocked Cmpxchg Double redos 1
We can see cmpxchg_double_slab fail rate is improved slightly.
Bolow is output of './perf stat -r 30 hackbench 50 process 4000 > /dev/null'.
** before **
Performance counter stats for './hackbench 50 process 4000' (30 runs):
108517.190463 task-clock # 7.926 CPUs utilized ( +- 0.24% )
2,919,550 context-switches # 0.027 M/sec ( +- 3.07% )
100,774 CPU-migrations # 0.929 K/sec ( +- 4.72% )
124,201 page-faults # 0.001 M/sec ( +- 0.15% )
401,500,234,387 cycles # 3.700 GHz ( +- 0.24% )
<not supported> stalled-cycles-frontend
<not supported> stalled-cycles-backend
250,576,913,354 instructions # 0.62 insns per cycle ( +- 0.13% )
45,934,956,860 branches # 423.297 M/sec ( +- 0.14% )
188,219,787 branch-misses # 0.41% of all branches ( +- 0.56% )
13.691837307 seconds time elapsed ( +- 0.24% )
** after **
Performance counter stats for './hackbench 50 process 4000' (30 runs):
107784.479767 task-clock # 7.928 CPUs utilized ( +- 0.22% )
2,834,781 context-switches # 0.026 M/sec ( +- 2.33% )
93,083 CPU-migrations # 0.864 K/sec ( +- 3.45% )
123,967 page-faults # 0.001 M/sec ( +- 0.15% )
398,781,421,836 cycles # 3.700 GHz ( +- 0.22% )
<not supported> stalled-cycles-frontend
<not supported> stalled-cycles-backend
250,189,160,419 instructions # 0.63 insns per cycle ( +- 0.09% )
45,855,370,128 branches # 425.436 M/sec ( +- 0.10% )
169,881,248 branch-misses # 0.37% of all branches ( +- 0.43% )
13.596272341 seconds time elapsed ( +- 0.22% )
No regression is found, but rather we can see slightly better result.
Acked-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Joonsoo Kim <js1304@gmail.com>
Signed-off-by: Pekka Enberg <penberg@kernel.org>
2012-06-09 02:23:16 +09:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2021-05-21 01:16:54 +02:00
|
|
|
|
2011-08-09 16:12:27 -05:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
slub: refactoring unfreeze_partials()
Current implementation of unfreeze_partials() is so complicated,
but benefit from it is insignificant. In addition many code in
do {} while loop have a bad influence to a fail rate of cmpxchg_double_slab.
Under current implementation which test status of cpu partial slab
and acquire list_lock in do {} while loop,
we don't need to acquire a list_lock and gain a little benefit
when front of the cpu partial slab is to be discarded, but this is a rare case.
In case that add_partial is performed and cmpxchg_double_slab is failed,
remove_partial should be called case by case.
I think that these are disadvantages of current implementation,
so I do refactoring unfreeze_partials().
Minimizing code in do {} while loop introduce a reduced fail rate
of cmpxchg_double_slab. Below is output of 'slabinfo -r kmalloc-256'
when './perf stat -r 33 hackbench 50 process 4000 > /dev/null' is done.
** before **
Cmpxchg_double Looping
------------------------
Locked Cmpxchg Double redos 182685
Unlocked Cmpxchg Double redos 0
** after **
Cmpxchg_double Looping
------------------------
Locked Cmpxchg Double redos 177995
Unlocked Cmpxchg Double redos 1
We can see cmpxchg_double_slab fail rate is improved slightly.
Bolow is output of './perf stat -r 30 hackbench 50 process 4000 > /dev/null'.
** before **
Performance counter stats for './hackbench 50 process 4000' (30 runs):
108517.190463 task-clock # 7.926 CPUs utilized ( +- 0.24% )
2,919,550 context-switches # 0.027 M/sec ( +- 3.07% )
100,774 CPU-migrations # 0.929 K/sec ( +- 4.72% )
124,201 page-faults # 0.001 M/sec ( +- 0.15% )
401,500,234,387 cycles # 3.700 GHz ( +- 0.24% )
<not supported> stalled-cycles-frontend
<not supported> stalled-cycles-backend
250,576,913,354 instructions # 0.62 insns per cycle ( +- 0.13% )
45,934,956,860 branches # 423.297 M/sec ( +- 0.14% )
188,219,787 branch-misses # 0.41% of all branches ( +- 0.56% )
13.691837307 seconds time elapsed ( +- 0.24% )
** after **
Performance counter stats for './hackbench 50 process 4000' (30 runs):
107784.479767 task-clock # 7.928 CPUs utilized ( +- 0.22% )
2,834,781 context-switches # 0.026 M/sec ( +- 2.33% )
93,083 CPU-migrations # 0.864 K/sec ( +- 3.45% )
123,967 page-faults # 0.001 M/sec ( +- 0.15% )
398,781,421,836 cycles # 3.700 GHz ( +- 0.22% )
<not supported> stalled-cycles-frontend
<not supported> stalled-cycles-backend
250,189,160,419 instructions # 0.63 insns per cycle ( +- 0.09% )
45,855,370,128 branches # 425.436 M/sec ( +- 0.10% )
169,881,248 branch-misses # 0.37% of all branches ( +- 0.43% )
13.596272341 seconds time elapsed ( +- 0.22% )
No regression is found, but rather we can see slightly better result.
Acked-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Joonsoo Kim <js1304@gmail.com>
Signed-off-by: Pekka Enberg <penberg@kernel.org>
2012-06-09 02:23:16 +09:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
slub: refactoring unfreeze_partials()
Current implementation of unfreeze_partials() is so complicated,
but benefit from it is insignificant. In addition many code in
do {} while loop have a bad influence to a fail rate of cmpxchg_double_slab.
Under current implementation which test status of cpu partial slab
and acquire list_lock in do {} while loop,
we don't need to acquire a list_lock and gain a little benefit
when front of the cpu partial slab is to be discarded, but this is a rare case.
In case that add_partial is performed and cmpxchg_double_slab is failed,
remove_partial should be called case by case.
I think that these are disadvantages of current implementation,
so I do refactoring unfreeze_partials().
Minimizing code in do {} while loop introduce a reduced fail rate
of cmpxchg_double_slab. Below is output of 'slabinfo -r kmalloc-256'
when './perf stat -r 33 hackbench 50 process 4000 > /dev/null' is done.
** before **
Cmpxchg_double Looping
------------------------
Locked Cmpxchg Double redos 182685
Unlocked Cmpxchg Double redos 0
** after **
Cmpxchg_double Looping
------------------------
Locked Cmpxchg Double redos 177995
Unlocked Cmpxchg Double redos 1
We can see cmpxchg_double_slab fail rate is improved slightly.
Bolow is output of './perf stat -r 30 hackbench 50 process 4000 > /dev/null'.
** before **
Performance counter stats for './hackbench 50 process 4000' (30 runs):
108517.190463 task-clock # 7.926 CPUs utilized ( +- 0.24% )
2,919,550 context-switches # 0.027 M/sec ( +- 3.07% )
100,774 CPU-migrations # 0.929 K/sec ( +- 4.72% )
124,201 page-faults # 0.001 M/sec ( +- 0.15% )
401,500,234,387 cycles # 3.700 GHz ( +- 0.24% )
<not supported> stalled-cycles-frontend
<not supported> stalled-cycles-backend
250,576,913,354 instructions # 0.62 insns per cycle ( +- 0.13% )
45,934,956,860 branches # 423.297 M/sec ( +- 0.14% )
188,219,787 branch-misses # 0.41% of all branches ( +- 0.56% )
13.691837307 seconds time elapsed ( +- 0.24% )
** after **
Performance counter stats for './hackbench 50 process 4000' (30 runs):
107784.479767 task-clock # 7.928 CPUs utilized ( +- 0.22% )
2,834,781 context-switches # 0.026 M/sec ( +- 2.33% )
93,083 CPU-migrations # 0.864 K/sec ( +- 3.45% )
123,967 page-faults # 0.001 M/sec ( +- 0.15% )
398,781,421,836 cycles # 3.700 GHz ( +- 0.22% )
<not supported> stalled-cycles-frontend
<not supported> stalled-cycles-backend
250,189,160,419 instructions # 0.63 insns per cycle ( +- 0.09% )
45,855,370,128 branches # 425.436 M/sec ( +- 0.10% )
169,881,248 branch-misses # 0.37% of all branches ( +- 0.43% )
13.596272341 seconds time elapsed ( +- 0.22% )
No regression is found, but rather we can see slightly better result.
Acked-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Joonsoo Kim <js1304@gmail.com>
Signed-off-by: Pekka Enberg <penberg@kernel.org>
2012-06-09 02:23:16 +09:00
|
|
|
|
|
|
|
|
|
2021-05-21 01:16:54 +02:00
|
|
|
|
slub: refactoring unfreeze_partials()
Current implementation of unfreeze_partials() is so complicated,
but benefit from it is insignificant. In addition many code in
do {} while loop have a bad influence to a fail rate of cmpxchg_double_slab.
Under current implementation which test status of cpu partial slab
and acquire list_lock in do {} while loop,
we don't need to acquire a list_lock and gain a little benefit
when front of the cpu partial slab is to be discarded, but this is a rare case.
In case that add_partial is performed and cmpxchg_double_slab is failed,
remove_partial should be called case by case.
I think that these are disadvantages of current implementation,
so I do refactoring unfreeze_partials().
Minimizing code in do {} while loop introduce a reduced fail rate
of cmpxchg_double_slab. Below is output of 'slabinfo -r kmalloc-256'
when './perf stat -r 33 hackbench 50 process 4000 > /dev/null' is done.
** before **
Cmpxchg_double Looping
------------------------
Locked Cmpxchg Double redos 182685
Unlocked Cmpxchg Double redos 0
** after **
Cmpxchg_double Looping
------------------------
Locked Cmpxchg Double redos 177995
Unlocked Cmpxchg Double redos 1
We can see cmpxchg_double_slab fail rate is improved slightly.
Bolow is output of './perf stat -r 30 hackbench 50 process 4000 > /dev/null'.
** before **
Performance counter stats for './hackbench 50 process 4000' (30 runs):
108517.190463 task-clock # 7.926 CPUs utilized ( +- 0.24% )
2,919,550 context-switches # 0.027 M/sec ( +- 3.07% )
100,774 CPU-migrations # 0.929 K/sec ( +- 4.72% )
124,201 page-faults # 0.001 M/sec ( +- 0.15% )
401,500,234,387 cycles # 3.700 GHz ( +- 0.24% )
<not supported> stalled-cycles-frontend
<not supported> stalled-cycles-backend
250,576,913,354 instructions # 0.62 insns per cycle ( +- 0.13% )
45,934,956,860 branches # 423.297 M/sec ( +- 0.14% )
188,219,787 branch-misses # 0.41% of all branches ( +- 0.56% )
13.691837307 seconds time elapsed ( +- 0.24% )
** after **
Performance counter stats for './hackbench 50 process 4000' (30 runs):
107784.479767 task-clock # 7.928 CPUs utilized ( +- 0.22% )
2,834,781 context-switches # 0.026 M/sec ( +- 2.33% )
93,083 CPU-migrations # 0.864 K/sec ( +- 3.45% )
123,967 page-faults # 0.001 M/sec ( +- 0.15% )
398,781,421,836 cycles # 3.700 GHz ( +- 0.22% )
<not supported> stalled-cycles-frontend
<not supported> stalled-cycles-backend
250,189,160,419 instructions # 0.63 insns per cycle ( +- 0.09% )
45,855,370,128 branches # 425.436 M/sec ( +- 0.10% )
169,881,248 branch-misses # 0.37% of all branches ( +- 0.43% )
13.596272341 seconds time elapsed ( +- 0.22% )
No regression is found, but rather we can see slightly better result.
Acked-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Joonsoo Kim <js1304@gmail.com>
Signed-off-by: Pekka Enberg <penberg@kernel.org>
2012-06-09 02:23:16 +09:00
|
|
|
|
|
|
|
|
|
2021-05-21 01:16:54 +02:00
|
|
|
|
slub: refactoring unfreeze_partials()
Current implementation of unfreeze_partials() is so complicated,
but benefit from it is insignificant. In addition many code in
do {} while loop have a bad influence to a fail rate of cmpxchg_double_slab.
Under current implementation which test status of cpu partial slab
and acquire list_lock in do {} while loop,
we don't need to acquire a list_lock and gain a little benefit
when front of the cpu partial slab is to be discarded, but this is a rare case.
In case that add_partial is performed and cmpxchg_double_slab is failed,
remove_partial should be called case by case.
I think that these are disadvantages of current implementation,
so I do refactoring unfreeze_partials().
Minimizing code in do {} while loop introduce a reduced fail rate
of cmpxchg_double_slab. Below is output of 'slabinfo -r kmalloc-256'
when './perf stat -r 33 hackbench 50 process 4000 > /dev/null' is done.
** before **
Cmpxchg_double Looping
------------------------
Locked Cmpxchg Double redos 182685
Unlocked Cmpxchg Double redos 0
** after **
Cmpxchg_double Looping
------------------------
Locked Cmpxchg Double redos 177995
Unlocked Cmpxchg Double redos 1
We can see cmpxchg_double_slab fail rate is improved slightly.
Bolow is output of './perf stat -r 30 hackbench 50 process 4000 > /dev/null'.
** before **
Performance counter stats for './hackbench 50 process 4000' (30 runs):
108517.190463 task-clock # 7.926 CPUs utilized ( +- 0.24% )
2,919,550 context-switches # 0.027 M/sec ( +- 3.07% )
100,774 CPU-migrations # 0.929 K/sec ( +- 4.72% )
124,201 page-faults # 0.001 M/sec ( +- 0.15% )
401,500,234,387 cycles # 3.700 GHz ( +- 0.24% )
<not supported> stalled-cycles-frontend
<not supported> stalled-cycles-backend
250,576,913,354 instructions # 0.62 insns per cycle ( +- 0.13% )
45,934,956,860 branches # 423.297 M/sec ( +- 0.14% )
188,219,787 branch-misses # 0.41% of all branches ( +- 0.56% )
13.691837307 seconds time elapsed ( +- 0.24% )
** after **
Performance counter stats for './hackbench 50 process 4000' (30 runs):
107784.479767 task-clock # 7.928 CPUs utilized ( +- 0.22% )
2,834,781 context-switches # 0.026 M/sec ( +- 2.33% )
93,083 CPU-migrations # 0.864 K/sec ( +- 3.45% )
123,967 page-faults # 0.001 M/sec ( +- 0.15% )
398,781,421,836 cycles # 3.700 GHz ( +- 0.22% )
<not supported> stalled-cycles-frontend
<not supported> stalled-cycles-backend
250,189,160,419 instructions # 0.63 insns per cycle ( +- 0.09% )
45,855,370,128 branches # 425.436 M/sec ( +- 0.10% )
169,881,248 branch-misses # 0.37% of all branches ( +- 0.43% )
13.596272341 seconds time elapsed ( +- 0.22% )
No regression is found, but rather we can see slightly better result.
Acked-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Joonsoo Kim <js1304@gmail.com>
Signed-off-by: Pekka Enberg <penberg@kernel.org>
2012-06-09 02:23:16 +09:00
|
|
|
|
2011-08-09 16:12:27 -05:00
|
|
|
|
2023-11-02 03:23:27 +00:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
|
|
|
|
|
slub: refactoring unfreeze_partials()
Current implementation of unfreeze_partials() is so complicated,
but benefit from it is insignificant. In addition many code in
do {} while loop have a bad influence to a fail rate of cmpxchg_double_slab.
Under current implementation which test status of cpu partial slab
and acquire list_lock in do {} while loop,
we don't need to acquire a list_lock and gain a little benefit
when front of the cpu partial slab is to be discarded, but this is a rare case.
In case that add_partial is performed and cmpxchg_double_slab is failed,
remove_partial should be called case by case.
I think that these are disadvantages of current implementation,
so I do refactoring unfreeze_partials().
Minimizing code in do {} while loop introduce a reduced fail rate
of cmpxchg_double_slab. Below is output of 'slabinfo -r kmalloc-256'
when './perf stat -r 33 hackbench 50 process 4000 > /dev/null' is done.
** before **
Cmpxchg_double Looping
------------------------
Locked Cmpxchg Double redos 182685
Unlocked Cmpxchg Double redos 0
** after **
Cmpxchg_double Looping
------------------------
Locked Cmpxchg Double redos 177995
Unlocked Cmpxchg Double redos 1
We can see cmpxchg_double_slab fail rate is improved slightly.
Bolow is output of './perf stat -r 30 hackbench 50 process 4000 > /dev/null'.
** before **
Performance counter stats for './hackbench 50 process 4000' (30 runs):
108517.190463 task-clock # 7.926 CPUs utilized ( +- 0.24% )
2,919,550 context-switches # 0.027 M/sec ( +- 3.07% )
100,774 CPU-migrations # 0.929 K/sec ( +- 4.72% )
124,201 page-faults # 0.001 M/sec ( +- 0.15% )
401,500,234,387 cycles # 3.700 GHz ( +- 0.24% )
<not supported> stalled-cycles-frontend
<not supported> stalled-cycles-backend
250,576,913,354 instructions # 0.62 insns per cycle ( +- 0.13% )
45,934,956,860 branches # 423.297 M/sec ( +- 0.14% )
188,219,787 branch-misses # 0.41% of all branches ( +- 0.56% )
13.691837307 seconds time elapsed ( +- 0.24% )
** after **
Performance counter stats for './hackbench 50 process 4000' (30 runs):
107784.479767 task-clock # 7.928 CPUs utilized ( +- 0.22% )
2,834,781 context-switches # 0.026 M/sec ( +- 2.33% )
93,083 CPU-migrations # 0.864 K/sec ( +- 3.45% )
123,967 page-faults # 0.001 M/sec ( +- 0.15% )
398,781,421,836 cycles # 3.700 GHz ( +- 0.22% )
<not supported> stalled-cycles-frontend
<not supported> stalled-cycles-backend
250,189,160,419 instructions # 0.63 insns per cycle ( +- 0.09% )
45,855,370,128 branches # 425.436 M/sec ( +- 0.10% )
169,881,248 branch-misses # 0.37% of all branches ( +- 0.43% )
13.596272341 seconds time elapsed ( +- 0.22% )
No regression is found, but rather we can see slightly better result.
Acked-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Joonsoo Kim <js1304@gmail.com>
Signed-off-by: Pekka Enberg <penberg@kernel.org>
2012-06-09 02:23:16 +09:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
slub: refactoring unfreeze_partials()
Current implementation of unfreeze_partials() is so complicated,
but benefit from it is insignificant. In addition many code in
do {} while loop have a bad influence to a fail rate of cmpxchg_double_slab.
Under current implementation which test status of cpu partial slab
and acquire list_lock in do {} while loop,
we don't need to acquire a list_lock and gain a little benefit
when front of the cpu partial slab is to be discarded, but this is a rare case.
In case that add_partial is performed and cmpxchg_double_slab is failed,
remove_partial should be called case by case.
I think that these are disadvantages of current implementation,
so I do refactoring unfreeze_partials().
Minimizing code in do {} while loop introduce a reduced fail rate
of cmpxchg_double_slab. Below is output of 'slabinfo -r kmalloc-256'
when './perf stat -r 33 hackbench 50 process 4000 > /dev/null' is done.
** before **
Cmpxchg_double Looping
------------------------
Locked Cmpxchg Double redos 182685
Unlocked Cmpxchg Double redos 0
** after **
Cmpxchg_double Looping
------------------------
Locked Cmpxchg Double redos 177995
Unlocked Cmpxchg Double redos 1
We can see cmpxchg_double_slab fail rate is improved slightly.
Bolow is output of './perf stat -r 30 hackbench 50 process 4000 > /dev/null'.
** before **
Performance counter stats for './hackbench 50 process 4000' (30 runs):
108517.190463 task-clock # 7.926 CPUs utilized ( +- 0.24% )
2,919,550 context-switches # 0.027 M/sec ( +- 3.07% )
100,774 CPU-migrations # 0.929 K/sec ( +- 4.72% )
124,201 page-faults # 0.001 M/sec ( +- 0.15% )
401,500,234,387 cycles # 3.700 GHz ( +- 0.24% )
<not supported> stalled-cycles-frontend
<not supported> stalled-cycles-backend
250,576,913,354 instructions # 0.62 insns per cycle ( +- 0.13% )
45,934,956,860 branches # 423.297 M/sec ( +- 0.14% )
188,219,787 branch-misses # 0.41% of all branches ( +- 0.56% )
13.691837307 seconds time elapsed ( +- 0.24% )
** after **
Performance counter stats for './hackbench 50 process 4000' (30 runs):
107784.479767 task-clock # 7.928 CPUs utilized ( +- 0.22% )
2,834,781 context-switches # 0.026 M/sec ( +- 2.33% )
93,083 CPU-migrations # 0.864 K/sec ( +- 3.45% )
123,967 page-faults # 0.001 M/sec ( +- 0.15% )
398,781,421,836 cycles # 3.700 GHz ( +- 0.22% )
<not supported> stalled-cycles-frontend
<not supported> stalled-cycles-backend
250,189,160,419 instructions # 0.63 insns per cycle ( +- 0.09% )
45,855,370,128 branches # 425.436 M/sec ( +- 0.10% )
169,881,248 branch-misses # 0.37% of all branches ( +- 0.43% )
13.596272341 seconds time elapsed ( +- 0.22% )
No regression is found, but rather we can see slightly better result.
Acked-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Joonsoo Kim <js1304@gmail.com>
Signed-off-by: Pekka Enberg <penberg@kernel.org>
2012-06-09 02:23:16 +09:00
|
|
|
|
2011-08-09 16:12:27 -05:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-05-21 01:16:54 +02:00
|
|
|
|
2021-05-20 14:01:57 +02:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-11-14 13:34:13 +08:00
|
|
|
|
|
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2011-11-14 13:34:13 +08:00
|
|
|
|
|
|
|
|
|
2021-05-20 16:39:51 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-11-02 03:23:29 +00:00
|
|
|
|
2021-05-20 16:39:51 +02:00
|
|
|
|
2023-11-02 03:23:29 +00:00
|
|
|
|
2021-05-20 16:39:51 +02:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2021-05-20 16:39:51 +02:00
|
|
|
|
|
|
|
|
|
2021-05-22 01:59:38 +02:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2021-05-20 16:39:51 +02:00
|
|
|
|
2021-05-22 01:59:38 +02:00
|
|
|
|
2021-05-20 16:39:51 +02:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2023-11-02 03:23:29 +00:00
|
|
|
|
2021-05-20 16:39:51 +02:00
|
|
|
|
|
|
|
|
|
2023-11-02 03:23:29 +00:00
|
|
|
|
|
|
|
|
|
2021-05-20 16:39:51 +02:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2021-05-20 16:39:51 +02:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2021-05-20 16:39:51 +02:00
|
|
|
|
|
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2023-11-02 03:23:29 +00:00
|
|
|
|
2021-05-20 16:39:51 +02:00
|
|
|
|
|
|
|
|
|
2011-08-09 16:12:27 -05:00
|
|
|
|
2023-11-02 03:23:30 +00:00
|
|
|
|
2011-08-09 16:12:27 -05:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2011-08-09 16:12:27 -05:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2023-11-02 03:23:29 +00:00
|
|
|
|
mm, slub: protect put_cpu_partial() with disabled irqs instead of cmpxchg
Jann Horn reported [1] the following theoretically possible race:
task A: put_cpu_partial() calls preempt_disable()
task A: oldpage = this_cpu_read(s->cpu_slab->partial)
interrupt: kfree() reaches unfreeze_partials() and discards the page
task B (on another CPU): reallocates page as page cache
task A: reads page->pages and page->pobjects, which are actually
halves of the pointer page->lru.prev
task B (on another CPU): frees page
interrupt: allocates page as SLUB page and places it on the percpu partial list
task A: this_cpu_cmpxchg() succeeds
which would cause page->pages and page->pobjects to end up containing
halves of pointers that would then influence when put_cpu_partial()
happens and show up in root-only sysfs files. Maybe that's acceptable,
I don't know. But there should probably at least be a comment for now
to point out that we're reading union fields of a page that might be
in a completely different state.
Additionally, the this_cpu_cmpxchg() approach in put_cpu_partial() is only safe
against s->cpu_slab->partial manipulation in ___slab_alloc() if the latter
disables irqs, otherwise a __slab_free() in an irq handler could call
put_cpu_partial() in the middle of ___slab_alloc() manipulating ->partial
and corrupt it. This becomes an issue on RT after a local_lock is introduced
in later patch. The fix means taking the local_lock also in put_cpu_partial()
on RT.
After debugging this issue, Mike Galbraith suggested [2] that to avoid
different locking schemes on RT and !RT, we can just protect put_cpu_partial()
with disabled irqs (to be converted to local_lock_irqsave() later) everywhere.
This should be acceptable as it's not a fast path, and moving the actual
partial unfreezing outside of the irq disabled section makes it short, and with
the retry loop gone the code can be also simplified. In addition, the race
reported by Jann should no longer be possible.
[1] https://lore.kernel.org/lkml/CAG48ez1mvUuXwg0YPH5ANzhQLpbphqk-ZS+jbRz+H66fvm4FcA@mail.gmail.com/
[2] https://lore.kernel.org/linux-rt-users/e3470ab357b48bccfbd1f5133b982178a7d2befb.camel@gmx.de/
Reported-by: Jann Horn <jannh@google.com>
Suggested-by: Mike Galbraith <efault@gmx.de>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2021-07-28 12:26:27 +02:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2011-08-09 16:12:27 -05:00
|
|
|
|
2021-05-22 01:59:38 +02:00
|
|
|
|
2011-08-09 16:12:27 -05:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
mm, slub: protect put_cpu_partial() with disabled irqs instead of cmpxchg
Jann Horn reported [1] the following theoretically possible race:
task A: put_cpu_partial() calls preempt_disable()
task A: oldpage = this_cpu_read(s->cpu_slab->partial)
interrupt: kfree() reaches unfreeze_partials() and discards the page
task B (on another CPU): reallocates page as page cache
task A: reads page->pages and page->pobjects, which are actually
halves of the pointer page->lru.prev
task B (on another CPU): frees page
interrupt: allocates page as SLUB page and places it on the percpu partial list
task A: this_cpu_cmpxchg() succeeds
which would cause page->pages and page->pobjects to end up containing
halves of pointers that would then influence when put_cpu_partial()
happens and show up in root-only sysfs files. Maybe that's acceptable,
I don't know. But there should probably at least be a comment for now
to point out that we're reading union fields of a page that might be
in a completely different state.
Additionally, the this_cpu_cmpxchg() approach in put_cpu_partial() is only safe
against s->cpu_slab->partial manipulation in ___slab_alloc() if the latter
disables irqs, otherwise a __slab_free() in an irq handler could call
put_cpu_partial() in the middle of ___slab_alloc() manipulating ->partial
and corrupt it. This becomes an issue on RT after a local_lock is introduced
in later patch. The fix means taking the local_lock also in put_cpu_partial()
on RT.
After debugging this issue, Mike Galbraith suggested [2] that to avoid
different locking schemes on RT and !RT, we can just protect put_cpu_partial()
with disabled irqs (to be converted to local_lock_irqsave() later) everywhere.
This should be acceptable as it's not a fast path, and moving the actual
partial unfreezing outside of the irq disabled section makes it short, and with
the retry loop gone the code can be also simplified. In addition, the race
reported by Jann should no longer be possible.
[1] https://lore.kernel.org/lkml/CAG48ez1mvUuXwg0YPH5ANzhQLpbphqk-ZS+jbRz+H66fvm4FcA@mail.gmail.com/
[2] https://lore.kernel.org/linux-rt-users/e3470ab357b48bccfbd1f5133b982178a7d2befb.camel@gmx.de/
Reported-by: Jann Horn <jannh@google.com>
Suggested-by: Mike Galbraith <efault@gmx.de>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2021-07-28 12:26:27 +02:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
|
|
|
|
|
mm, slub: protect put_cpu_partial() with disabled irqs instead of cmpxchg
Jann Horn reported [1] the following theoretically possible race:
task A: put_cpu_partial() calls preempt_disable()
task A: oldpage = this_cpu_read(s->cpu_slab->partial)
interrupt: kfree() reaches unfreeze_partials() and discards the page
task B (on another CPU): reallocates page as page cache
task A: reads page->pages and page->pobjects, which are actually
halves of the pointer page->lru.prev
task B (on another CPU): frees page
interrupt: allocates page as SLUB page and places it on the percpu partial list
task A: this_cpu_cmpxchg() succeeds
which would cause page->pages and page->pobjects to end up containing
halves of pointers that would then influence when put_cpu_partial()
happens and show up in root-only sysfs files. Maybe that's acceptable,
I don't know. But there should probably at least be a comment for now
to point out that we're reading union fields of a page that might be
in a completely different state.
Additionally, the this_cpu_cmpxchg() approach in put_cpu_partial() is only safe
against s->cpu_slab->partial manipulation in ___slab_alloc() if the latter
disables irqs, otherwise a __slab_free() in an irq handler could call
put_cpu_partial() in the middle of ___slab_alloc() manipulating ->partial
and corrupt it. This becomes an issue on RT after a local_lock is introduced
in later patch. The fix means taking the local_lock also in put_cpu_partial()
on RT.
After debugging this issue, Mike Galbraith suggested [2] that to avoid
different locking schemes on RT and !RT, we can just protect put_cpu_partial()
with disabled irqs (to be converted to local_lock_irqsave() later) everywhere.
This should be acceptable as it's not a fast path, and moving the actual
partial unfreezing outside of the irq disabled section makes it short, and with
the retry loop gone the code can be also simplified. In addition, the race
reported by Jann should no longer be possible.
[1] https://lore.kernel.org/lkml/CAG48ez1mvUuXwg0YPH5ANzhQLpbphqk-ZS+jbRz+H66fvm4FcA@mail.gmail.com/
[2] https://lore.kernel.org/linux-rt-users/e3470ab357b48bccfbd1f5133b982178a7d2befb.camel@gmx.de/
Reported-by: Jann Horn <jannh@google.com>
Suggested-by: Mike Galbraith <efault@gmx.de>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2021-07-28 12:26:27 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-11-02 03:23:29 +00:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
mm, slub: protect put_cpu_partial() with disabled irqs instead of cmpxchg
Jann Horn reported [1] the following theoretically possible race:
task A: put_cpu_partial() calls preempt_disable()
task A: oldpage = this_cpu_read(s->cpu_slab->partial)
interrupt: kfree() reaches unfreeze_partials() and discards the page
task B (on another CPU): reallocates page as page cache
task A: reads page->pages and page->pobjects, which are actually
halves of the pointer page->lru.prev
task B (on another CPU): frees page
interrupt: allocates page as SLUB page and places it on the percpu partial list
task A: this_cpu_cmpxchg() succeeds
which would cause page->pages and page->pobjects to end up containing
halves of pointers that would then influence when put_cpu_partial()
happens and show up in root-only sysfs files. Maybe that's acceptable,
I don't know. But there should probably at least be a comment for now
to point out that we're reading union fields of a page that might be
in a completely different state.
Additionally, the this_cpu_cmpxchg() approach in put_cpu_partial() is only safe
against s->cpu_slab->partial manipulation in ___slab_alloc() if the latter
disables irqs, otherwise a __slab_free() in an irq handler could call
put_cpu_partial() in the middle of ___slab_alloc() manipulating ->partial
and corrupt it. This becomes an issue on RT after a local_lock is introduced
in later patch. The fix means taking the local_lock also in put_cpu_partial()
on RT.
After debugging this issue, Mike Galbraith suggested [2] that to avoid
different locking schemes on RT and !RT, we can just protect put_cpu_partial()
with disabled irqs (to be converted to local_lock_irqsave() later) everywhere.
This should be acceptable as it's not a fast path, and moving the actual
partial unfreezing outside of the irq disabled section makes it short, and with
the retry loop gone the code can be also simplified. In addition, the race
reported by Jann should no longer be possible.
[1] https://lore.kernel.org/lkml/CAG48ez1mvUuXwg0YPH5ANzhQLpbphqk-ZS+jbRz+H66fvm4FcA@mail.gmail.com/
[2] https://lore.kernel.org/linux-rt-users/e3470ab357b48bccfbd1f5133b982178a7d2befb.camel@gmx.de/
Reported-by: Jann Horn <jannh@google.com>
Suggested-by: Mike Galbraith <efault@gmx.de>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2021-07-28 12:26:27 +02:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2011-08-09 16:12:27 -05:00
|
|
|
|
mm, slub: protect put_cpu_partial() with disabled irqs instead of cmpxchg
Jann Horn reported [1] the following theoretically possible race:
task A: put_cpu_partial() calls preempt_disable()
task A: oldpage = this_cpu_read(s->cpu_slab->partial)
interrupt: kfree() reaches unfreeze_partials() and discards the page
task B (on another CPU): reallocates page as page cache
task A: reads page->pages and page->pobjects, which are actually
halves of the pointer page->lru.prev
task B (on another CPU): frees page
interrupt: allocates page as SLUB page and places it on the percpu partial list
task A: this_cpu_cmpxchg() succeeds
which would cause page->pages and page->pobjects to end up containing
halves of pointers that would then influence when put_cpu_partial()
happens and show up in root-only sysfs files. Maybe that's acceptable,
I don't know. But there should probably at least be a comment for now
to point out that we're reading union fields of a page that might be
in a completely different state.
Additionally, the this_cpu_cmpxchg() approach in put_cpu_partial() is only safe
against s->cpu_slab->partial manipulation in ___slab_alloc() if the latter
disables irqs, otherwise a __slab_free() in an irq handler could call
put_cpu_partial() in the middle of ___slab_alloc() manipulating ->partial
and corrupt it. This becomes an issue on RT after a local_lock is introduced
in later patch. The fix means taking the local_lock also in put_cpu_partial()
on RT.
After debugging this issue, Mike Galbraith suggested [2] that to avoid
different locking schemes on RT and !RT, we can just protect put_cpu_partial()
with disabled irqs (to be converted to local_lock_irqsave() later) everywhere.
This should be acceptable as it's not a fast path, and moving the actual
partial unfreezing outside of the irq disabled section makes it short, and with
the retry loop gone the code can be also simplified. In addition, the race
reported by Jann should no longer be possible.
[1] https://lore.kernel.org/lkml/CAG48ez1mvUuXwg0YPH5ANzhQLpbphqk-ZS+jbRz+H66fvm4FcA@mail.gmail.com/
[2] https://lore.kernel.org/linux-rt-users/e3470ab357b48bccfbd1f5133b982178a7d2befb.camel@gmx.de/
Reported-by: Jann Horn <jannh@google.com>
Suggested-by: Mike Galbraith <efault@gmx.de>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2021-07-28 12:26:27 +02:00
|
|
|
|
2011-08-09 16:12:27 -05:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2011-08-09 16:12:27 -05:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
|
|
|
|
|
2011-08-09 16:12:27 -05:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
mm, slub: protect put_cpu_partial() with disabled irqs instead of cmpxchg
Jann Horn reported [1] the following theoretically possible race:
task A: put_cpu_partial() calls preempt_disable()
task A: oldpage = this_cpu_read(s->cpu_slab->partial)
interrupt: kfree() reaches unfreeze_partials() and discards the page
task B (on another CPU): reallocates page as page cache
task A: reads page->pages and page->pobjects, which are actually
halves of the pointer page->lru.prev
task B (on another CPU): frees page
interrupt: allocates page as SLUB page and places it on the percpu partial list
task A: this_cpu_cmpxchg() succeeds
which would cause page->pages and page->pobjects to end up containing
halves of pointers that would then influence when put_cpu_partial()
happens and show up in root-only sysfs files. Maybe that's acceptable,
I don't know. But there should probably at least be a comment for now
to point out that we're reading union fields of a page that might be
in a completely different state.
Additionally, the this_cpu_cmpxchg() approach in put_cpu_partial() is only safe
against s->cpu_slab->partial manipulation in ___slab_alloc() if the latter
disables irqs, otherwise a __slab_free() in an irq handler could call
put_cpu_partial() in the middle of ___slab_alloc() manipulating ->partial
and corrupt it. This becomes an issue on RT after a local_lock is introduced
in later patch. The fix means taking the local_lock also in put_cpu_partial()
on RT.
After debugging this issue, Mike Galbraith suggested [2] that to avoid
different locking schemes on RT and !RT, we can just protect put_cpu_partial()
with disabled irqs (to be converted to local_lock_irqsave() later) everywhere.
This should be acceptable as it's not a fast path, and moving the actual
partial unfreezing outside of the irq disabled section makes it short, and with
the retry loop gone the code can be also simplified. In addition, the race
reported by Jann should no longer be possible.
[1] https://lore.kernel.org/lkml/CAG48ez1mvUuXwg0YPH5ANzhQLpbphqk-ZS+jbRz+H66fvm4FcA@mail.gmail.com/
[2] https://lore.kernel.org/linux-rt-users/e3470ab357b48bccfbd1f5133b982178a7d2befb.camel@gmx.de/
Reported-by: Jann Horn <jannh@google.com>
Suggested-by: Mike Galbraith <efault@gmx.de>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2021-07-28 12:26:27 +02:00
|
|
|
|
2021-05-22 01:59:38 +02:00
|
|
|
|
mm, slub: protect put_cpu_partial() with disabled irqs instead of cmpxchg
Jann Horn reported [1] the following theoretically possible race:
task A: put_cpu_partial() calls preempt_disable()
task A: oldpage = this_cpu_read(s->cpu_slab->partial)
interrupt: kfree() reaches unfreeze_partials() and discards the page
task B (on another CPU): reallocates page as page cache
task A: reads page->pages and page->pobjects, which are actually
halves of the pointer page->lru.prev
task B (on another CPU): frees page
interrupt: allocates page as SLUB page and places it on the percpu partial list
task A: this_cpu_cmpxchg() succeeds
which would cause page->pages and page->pobjects to end up containing
halves of pointers that would then influence when put_cpu_partial()
happens and show up in root-only sysfs files. Maybe that's acceptable,
I don't know. But there should probably at least be a comment for now
to point out that we're reading union fields of a page that might be
in a completely different state.
Additionally, the this_cpu_cmpxchg() approach in put_cpu_partial() is only safe
against s->cpu_slab->partial manipulation in ___slab_alloc() if the latter
disables irqs, otherwise a __slab_free() in an irq handler could call
put_cpu_partial() in the middle of ___slab_alloc() manipulating ->partial
and corrupt it. This becomes an issue on RT after a local_lock is introduced
in later patch. The fix means taking the local_lock also in put_cpu_partial()
on RT.
After debugging this issue, Mike Galbraith suggested [2] that to avoid
different locking schemes on RT and !RT, we can just protect put_cpu_partial()
with disabled irqs (to be converted to local_lock_irqsave() later) everywhere.
This should be acceptable as it's not a fast path, and moving the actual
partial unfreezing outside of the irq disabled section makes it short, and with
the retry loop gone the code can be also simplified. In addition, the race
reported by Jann should no longer be possible.
[1] https://lore.kernel.org/lkml/CAG48ez1mvUuXwg0YPH5ANzhQLpbphqk-ZS+jbRz+H66fvm4FcA@mail.gmail.com/
[2] https://lore.kernel.org/linux-rt-users/e3470ab357b48bccfbd1f5133b982178a7d2befb.camel@gmx.de/
Reported-by: Jann Horn <jannh@google.com>
Suggested-by: Mike Galbraith <efault@gmx.de>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2021-07-28 12:26:27 +02:00
|
|
|
|
2023-11-02 03:23:29 +00:00
|
|
|
|
|
|
|
|
|
mm, slub: protect put_cpu_partial() with disabled irqs instead of cmpxchg
Jann Horn reported [1] the following theoretically possible race:
task A: put_cpu_partial() calls preempt_disable()
task A: oldpage = this_cpu_read(s->cpu_slab->partial)
interrupt: kfree() reaches unfreeze_partials() and discards the page
task B (on another CPU): reallocates page as page cache
task A: reads page->pages and page->pobjects, which are actually
halves of the pointer page->lru.prev
task B (on another CPU): frees page
interrupt: allocates page as SLUB page and places it on the percpu partial list
task A: this_cpu_cmpxchg() succeeds
which would cause page->pages and page->pobjects to end up containing
halves of pointers that would then influence when put_cpu_partial()
happens and show up in root-only sysfs files. Maybe that's acceptable,
I don't know. But there should probably at least be a comment for now
to point out that we're reading union fields of a page that might be
in a completely different state.
Additionally, the this_cpu_cmpxchg() approach in put_cpu_partial() is only safe
against s->cpu_slab->partial manipulation in ___slab_alloc() if the latter
disables irqs, otherwise a __slab_free() in an irq handler could call
put_cpu_partial() in the middle of ___slab_alloc() manipulating ->partial
and corrupt it. This becomes an issue on RT after a local_lock is introduced
in later patch. The fix means taking the local_lock also in put_cpu_partial()
on RT.
After debugging this issue, Mike Galbraith suggested [2] that to avoid
different locking schemes on RT and !RT, we can just protect put_cpu_partial()
with disabled irqs (to be converted to local_lock_irqsave() later) everywhere.
This should be acceptable as it's not a fast path, and moving the actual
partial unfreezing outside of the irq disabled section makes it short, and with
the retry loop gone the code can be also simplified. In addition, the race
reported by Jann should no longer be possible.
[1] https://lore.kernel.org/lkml/CAG48ez1mvUuXwg0YPH5ANzhQLpbphqk-ZS+jbRz+H66fvm4FcA@mail.gmail.com/
[2] https://lore.kernel.org/linux-rt-users/e3470ab357b48bccfbd1f5133b982178a7d2befb.camel@gmx.de/
Reported-by: Jann Horn <jannh@google.com>
Suggested-by: Mike Galbraith <efault@gmx.de>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2021-07-28 12:26:27 +02:00
|
|
|
|
|
|
|
|
|
2011-08-09 16:12:27 -05:00
|
|
|
|
|
|
|
|
|
mm, slub: protect put_cpu_partial() with disabled irqs instead of cmpxchg
Jann Horn reported [1] the following theoretically possible race:
task A: put_cpu_partial() calls preempt_disable()
task A: oldpage = this_cpu_read(s->cpu_slab->partial)
interrupt: kfree() reaches unfreeze_partials() and discards the page
task B (on another CPU): reallocates page as page cache
task A: reads page->pages and page->pobjects, which are actually
halves of the pointer page->lru.prev
task B (on another CPU): frees page
interrupt: allocates page as SLUB page and places it on the percpu partial list
task A: this_cpu_cmpxchg() succeeds
which would cause page->pages and page->pobjects to end up containing
halves of pointers that would then influence when put_cpu_partial()
happens and show up in root-only sysfs files. Maybe that's acceptable,
I don't know. But there should probably at least be a comment for now
to point out that we're reading union fields of a page that might be
in a completely different state.
Additionally, the this_cpu_cmpxchg() approach in put_cpu_partial() is only safe
against s->cpu_slab->partial manipulation in ___slab_alloc() if the latter
disables irqs, otherwise a __slab_free() in an irq handler could call
put_cpu_partial() in the middle of ___slab_alloc() manipulating ->partial
and corrupt it. This becomes an issue on RT after a local_lock is introduced
in later patch. The fix means taking the local_lock also in put_cpu_partial()
on RT.
After debugging this issue, Mike Galbraith suggested [2] that to avoid
different locking schemes on RT and !RT, we can just protect put_cpu_partial()
with disabled irqs (to be converted to local_lock_irqsave() later) everywhere.
This should be acceptable as it's not a fast path, and moving the actual
partial unfreezing outside of the irq disabled section makes it short, and with
the retry loop gone the code can be also simplified. In addition, the race
reported by Jann should no longer be possible.
[1] https://lore.kernel.org/lkml/CAG48ez1mvUuXwg0YPH5ANzhQLpbphqk-ZS+jbRz+H66fvm4FcA@mail.gmail.com/
[2] https://lore.kernel.org/linux-rt-users/e3470ab357b48bccfbd1f5133b982178a7d2befb.camel@gmx.de/
Reported-by: Jann Horn <jannh@google.com>
Suggested-by: Mike Galbraith <efault@gmx.de>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2021-07-28 12:26:27 +02:00
|
|
|
|
|
|
|
|
|
2023-11-02 03:23:29 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
mm, slub: protect put_cpu_partial() with disabled irqs instead of cmpxchg
Jann Horn reported [1] the following theoretically possible race:
task A: put_cpu_partial() calls preempt_disable()
task A: oldpage = this_cpu_read(s->cpu_slab->partial)
interrupt: kfree() reaches unfreeze_partials() and discards the page
task B (on another CPU): reallocates page as page cache
task A: reads page->pages and page->pobjects, which are actually
halves of the pointer page->lru.prev
task B (on another CPU): frees page
interrupt: allocates page as SLUB page and places it on the percpu partial list
task A: this_cpu_cmpxchg() succeeds
which would cause page->pages and page->pobjects to end up containing
halves of pointers that would then influence when put_cpu_partial()
happens and show up in root-only sysfs files. Maybe that's acceptable,
I don't know. But there should probably at least be a comment for now
to point out that we're reading union fields of a page that might be
in a completely different state.
Additionally, the this_cpu_cmpxchg() approach in put_cpu_partial() is only safe
against s->cpu_slab->partial manipulation in ___slab_alloc() if the latter
disables irqs, otherwise a __slab_free() in an irq handler could call
put_cpu_partial() in the middle of ___slab_alloc() manipulating ->partial
and corrupt it. This becomes an issue on RT after a local_lock is introduced
in later patch. The fix means taking the local_lock also in put_cpu_partial()
on RT.
After debugging this issue, Mike Galbraith suggested [2] that to avoid
different locking schemes on RT and !RT, we can just protect put_cpu_partial()
with disabled irqs (to be converted to local_lock_irqsave() later) everywhere.
This should be acceptable as it's not a fast path, and moving the actual
partial unfreezing outside of the irq disabled section makes it short, and with
the retry loop gone the code can be also simplified. In addition, the race
reported by Jann should no longer be possible.
[1] https://lore.kernel.org/lkml/CAG48ez1mvUuXwg0YPH5ANzhQLpbphqk-ZS+jbRz+H66fvm4FcA@mail.gmail.com/
[2] https://lore.kernel.org/linux-rt-users/e3470ab357b48bccfbd1f5133b982178a7d2befb.camel@gmx.de/
Reported-by: Jann Horn <jannh@google.com>
Suggested-by: Mike Galbraith <efault@gmx.de>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2021-07-28 12:26:27 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-10-16 01:26:05 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2021-02-26 17:11:55 +01:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2021-02-26 17:11:55 +01:00
|
|
|
|
|
|
|
|
|
2021-05-22 01:59:38 +02:00
|
|
|
|
2021-02-26 17:11:55 +01:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2021-02-26 17:11:55 +01:00
|
|
|
|
2012-05-09 10:09:57 -05:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2021-05-12 13:53:34 +02:00
|
|
|
|
2012-05-09 10:09:57 -05:00
|
|
|
|
2021-05-12 13:53:34 +02:00
|
|
|
|
2021-05-22 01:59:38 +02:00
|
|
|
|
2021-05-12 13:53:34 +02:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
|
|
|
|
|
2021-02-26 17:11:55 +01:00
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
2007-07-17 04:03:24 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2009-12-18 16:26:20 -06:00
|
|
|
|
2021-06-03 19:17:42 +02:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2021-06-03 19:17:42 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
|
|
|
|
|
2021-06-03 19:17:42 +02:00
|
|
|
|
|
|
|
|
|
2011-08-09 16:12:27 -05:00
|
|
|
|
2023-11-02 03:23:29 +00:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
2021-02-26 17:11:55 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-05-20 16:39:51 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-02-26 17:11:55 +01:00
|
|
|
|
2021-05-20 16:39:51 +02:00
|
|
|
|
2021-02-26 17:11:55 +01:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2021-02-26 17:11:55 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2021-05-20 16:39:51 +02:00
|
|
|
|
|
|
|
|
|
2023-11-02 03:23:29 +00:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
2021-02-26 17:11:55 +01:00
|
|
|
|
2012-03-28 14:42:44 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2012-03-28 14:42:44 -07:00
|
|
|
|
|
|
|
|
|
2021-02-26 17:11:55 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-09-19 18:39:29 +02:00
|
|
|
|
2021-02-26 17:11:55 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
2021-02-26 17:11:55 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
2016-08-18 14:57:19 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-05-21 01:48:56 +02:00
|
|
|
|
2016-08-18 14:57:19 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-11-15 18:14:31 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-10-16 01:26:05 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2007-10-16 01:26:05 -07:00
|
|
|
|
|
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2007-10-16 01:26:05 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
mm, slab: suppress out of memory warning unless debug is enabled
When the slab or slub allocators cannot allocate additional slab pages,
they emit diagnostic information to the kernel log such as current
number of slabs, number of objects, active objects, etc. This is always
coupled with a page allocation failure warning since it is controlled by
!__GFP_NOWARN.
Suppress this out of memory warning if the allocator is configured
without debug supported. The page allocation failure warning will
indicate it is a failed slab allocation, the order, and the gfp mask, so
this is only useful to diagnose allocator issues.
Since CONFIG_SLUB_DEBUG is already enabled by default for the slub
allocator, there is no functional change with this patch. If debug is
disabled, however, the warnings are now suppressed.
Signed-off-by: David Rientjes <rientjes@google.com>
Cc: Pekka Enberg <penberg@kernel.org>
Acked-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-06-04 16:06:36 -07:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2009-06-10 18:50:32 +03:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2009-06-10 18:50:32 +03:00
|
|
|
|
|
|
|
|
|
mm, slab: suppress out of memory warning unless debug is enabled
When the slab or slub allocators cannot allocate additional slab pages,
they emit diagnostic information to the kernel log such as current
number of slabs, number of objects, active objects, etc. This is always
coupled with a page allocation failure warning since it is controlled by
!__GFP_NOWARN.
Suppress this out of memory warning if the allocator is configured
without debug supported. The page allocation failure warning will
indicate it is a failed slab allocation, the order, and the gfp mask, so
this is only useful to diagnose allocator issues.
Since CONFIG_SLUB_DEBUG is already enabled by default for the slub
allocator, there is no functional change with this patch. If debug is
disabled, however, the warnings are now suppressed.
Signed-off-by: David Rientjes <rientjes@google.com>
Cc: Pekka Enberg <penberg@kernel.org>
Acked-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-06-04 16:06:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-08-23 19:03:56 +02:00
|
|
|
|
|
|
|
|
|
2022-11-21 16:06:38 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-08-23 19:03:56 +02:00
|
|
|
|
2022-11-21 16:06:38 +01:00
|
|
|
|
2022-08-23 19:03:56 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-11-21 16:06:38 +01:00
|
|
|
|
mm/slub: restrict sysfs validation to debug caches and make it safe
Rongwei Wang reports [1] that cache validation triggered by writing to
/sys/kernel/slab/<cache>/validate is racy against normal cache
operations (e.g. freeing) in a way that can cause false positive
inconsistency reports for caches with debugging enabled. The problem is
that debugging actions that mark object free or active and actual
freelist operations are not atomic, and the validation can see an
inconsistent state.
For caches that do or don't have debugging enabled, additional races
involving n->nr_slabs are possible that result in false reports of wrong
slab counts.
This patch attempts to solve these issues while not adding overhead to
normal (especially fastpath) operations for caches that do not have
debugging enabled. Such overhead would not be justified to make possible
userspace-triggered validation safe. Instead, disable the validation for
caches that don't have debugging enabled and make their sysfs validate
handler return -EINVAL.
For caches that do have debugging enabled, we can instead extend the
existing approach of not using percpu freelists to force all alloc/free
operations to the slow paths where debugging flags is checked and acted
upon. There can adjust the debug-specific paths to increase n->list_lock
coverage against concurrent validation as necessary.
The processing on free in free_debug_processing() already happens under
n->list_lock so we can extend it to actually do the freeing as well and
thus make it atomic against concurrent validation. As observed by
Hyeonggon Yoo, we do not really need to take slab_lock() anymore here
because all paths we could race with are protected by n->list_lock under
the new scheme, so drop its usage here.
The processing on alloc in alloc_debug_processing() currently doesn't
take any locks, but we have to first allocate the object from a slab on
the partial list (as debugging caches have no percpu slabs) and thus
take the n->list_lock anyway. Add a function alloc_single_from_partial()
that grabs just the allocated object instead of the whole freelist, and
does the debug processing. The n->list_lock coverage again makes it
atomic against validation and it is also ultimately more efficient than
the current grabbing of freelist immediately followed by slab
deactivation.
To prevent races on n->nr_slabs updates, make sure that for caches with
debugging enabled, inc_slabs_node() or dec_slabs_node() is called under
n->list_lock. When allocating a new slab for a debug cache, handle the
allocation by a new function alloc_single_from_new_slab() instead of the
current forced deactivation path.
Neither of these changes affect the fast paths at all. The changes in
slow paths are negligible for non-debug caches.
[1] https://lore.kernel.org/all/20220529081535.69275-1-rongwei.wang@linux.alibaba.com/
Reported-by: Rongwei Wang <rongwei.wang@linux.alibaba.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
2022-08-23 19:03:57 +02:00
|
|
|
|
2022-11-21 16:06:38 +01:00
|
|
|
|
mm/slub: restrict sysfs validation to debug caches and make it safe
Rongwei Wang reports [1] that cache validation triggered by writing to
/sys/kernel/slab/<cache>/validate is racy against normal cache
operations (e.g. freeing) in a way that can cause false positive
inconsistency reports for caches with debugging enabled. The problem is
that debugging actions that mark object free or active and actual
freelist operations are not atomic, and the validation can see an
inconsistent state.
For caches that do or don't have debugging enabled, additional races
involving n->nr_slabs are possible that result in false reports of wrong
slab counts.
This patch attempts to solve these issues while not adding overhead to
normal (especially fastpath) operations for caches that do not have
debugging enabled. Such overhead would not be justified to make possible
userspace-triggered validation safe. Instead, disable the validation for
caches that don't have debugging enabled and make their sysfs validate
handler return -EINVAL.
For caches that do have debugging enabled, we can instead extend the
existing approach of not using percpu freelists to force all alloc/free
operations to the slow paths where debugging flags is checked and acted
upon. There can adjust the debug-specific paths to increase n->list_lock
coverage against concurrent validation as necessary.
The processing on free in free_debug_processing() already happens under
n->list_lock so we can extend it to actually do the freeing as well and
thus make it atomic against concurrent validation. As observed by
Hyeonggon Yoo, we do not really need to take slab_lock() anymore here
because all paths we could race with are protected by n->list_lock under
the new scheme, so drop its usage here.
The processing on alloc in alloc_debug_processing() currently doesn't
take any locks, but we have to first allocate the object from a slab on
the partial list (as debugging caches have no percpu slabs) and thus
take the n->list_lock anyway. Add a function alloc_single_from_partial()
that grabs just the allocated object instead of the whole freelist, and
does the debug processing. The n->list_lock coverage again makes it
atomic against validation and it is also ultimately more efficient than
the current grabbing of freelist immediately followed by slab
deactivation.
To prevent races on n->nr_slabs updates, make sure that for caches with
debugging enabled, inc_slabs_node() or dec_slabs_node() is called under
n->list_lock. When allocating a new slab for a debug cache, handle the
allocation by a new function alloc_single_from_new_slab() instead of the
current forced deactivation path.
Neither of these changes affect the fast paths at all. The changes in
slow paths are negligible for non-debug caches.
[1] https://lore.kernel.org/all/20220529081535.69275-1-rongwei.wang@linux.alibaba.com/
Reported-by: Rongwei Wang <rongwei.wang@linux.alibaba.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
2022-08-23 19:03:57 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-08-23 19:03:56 +02:00
|
|
|
|
mm/slub: restrict sysfs validation to debug caches and make it safe
Rongwei Wang reports [1] that cache validation triggered by writing to
/sys/kernel/slab/<cache>/validate is racy against normal cache
operations (e.g. freeing) in a way that can cause false positive
inconsistency reports for caches with debugging enabled. The problem is
that debugging actions that mark object free or active and actual
freelist operations are not atomic, and the validation can see an
inconsistent state.
For caches that do or don't have debugging enabled, additional races
involving n->nr_slabs are possible that result in false reports of wrong
slab counts.
This patch attempts to solve these issues while not adding overhead to
normal (especially fastpath) operations for caches that do not have
debugging enabled. Such overhead would not be justified to make possible
userspace-triggered validation safe. Instead, disable the validation for
caches that don't have debugging enabled and make their sysfs validate
handler return -EINVAL.
For caches that do have debugging enabled, we can instead extend the
existing approach of not using percpu freelists to force all alloc/free
operations to the slow paths where debugging flags is checked and acted
upon. There can adjust the debug-specific paths to increase n->list_lock
coverage against concurrent validation as necessary.
The processing on free in free_debug_processing() already happens under
n->list_lock so we can extend it to actually do the freeing as well and
thus make it atomic against concurrent validation. As observed by
Hyeonggon Yoo, we do not really need to take slab_lock() anymore here
because all paths we could race with are protected by n->list_lock under
the new scheme, so drop its usage here.
The processing on alloc in alloc_debug_processing() currently doesn't
take any locks, but we have to first allocate the object from a slab on
the partial list (as debugging caches have no percpu slabs) and thus
take the n->list_lock anyway. Add a function alloc_single_from_partial()
that grabs just the allocated object instead of the whole freelist, and
does the debug processing. The n->list_lock coverage again makes it
atomic against validation and it is also ultimately more efficient than
the current grabbing of freelist immediately followed by slab
deactivation.
To prevent races on n->nr_slabs updates, make sure that for caches with
debugging enabled, inc_slabs_node() or dec_slabs_node() is called under
n->list_lock. When allocating a new slab for a debug cache, handle the
allocation by a new function alloc_single_from_new_slab() instead of the
current forced deactivation path.
Neither of these changes affect the fast paths at all. The changes in
slow paths are negligible for non-debug caches.
[1] https://lore.kernel.org/all/20220529081535.69275-1-rongwei.wang@linux.alibaba.com/
Reported-by: Rongwei Wang <rongwei.wang@linux.alibaba.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
2022-08-23 19:03:57 +02:00
|
|
|
|
2022-11-21 16:06:38 +01:00
|
|
|
|
mm/slub: restrict sysfs validation to debug caches and make it safe
Rongwei Wang reports [1] that cache validation triggered by writing to
/sys/kernel/slab/<cache>/validate is racy against normal cache
operations (e.g. freeing) in a way that can cause false positive
inconsistency reports for caches with debugging enabled. The problem is
that debugging actions that mark object free or active and actual
freelist operations are not atomic, and the validation can see an
inconsistent state.
For caches that do or don't have debugging enabled, additional races
involving n->nr_slabs are possible that result in false reports of wrong
slab counts.
This patch attempts to solve these issues while not adding overhead to
normal (especially fastpath) operations for caches that do not have
debugging enabled. Such overhead would not be justified to make possible
userspace-triggered validation safe. Instead, disable the validation for
caches that don't have debugging enabled and make their sysfs validate
handler return -EINVAL.
For caches that do have debugging enabled, we can instead extend the
existing approach of not using percpu freelists to force all alloc/free
operations to the slow paths where debugging flags is checked and acted
upon. There can adjust the debug-specific paths to increase n->list_lock
coverage against concurrent validation as necessary.
The processing on free in free_debug_processing() already happens under
n->list_lock so we can extend it to actually do the freeing as well and
thus make it atomic against concurrent validation. As observed by
Hyeonggon Yoo, we do not really need to take slab_lock() anymore here
because all paths we could race with are protected by n->list_lock under
the new scheme, so drop its usage here.
The processing on alloc in alloc_debug_processing() currently doesn't
take any locks, but we have to first allocate the object from a slab on
the partial list (as debugging caches have no percpu slabs) and thus
take the n->list_lock anyway. Add a function alloc_single_from_partial()
that grabs just the allocated object instead of the whole freelist, and
does the debug processing. The n->list_lock coverage again makes it
atomic against validation and it is also ultimately more efficient than
the current grabbing of freelist immediately followed by slab
deactivation.
To prevent races on n->nr_slabs updates, make sure that for caches with
debugging enabled, inc_slabs_node() or dec_slabs_node() is called under
n->list_lock. When allocating a new slab for a debug cache, handle the
allocation by a new function alloc_single_from_new_slab() instead of the
current forced deactivation path.
Neither of these changes affect the fast paths at all. The changes in
slow paths are negligible for non-debug caches.
[1] https://lore.kernel.org/all/20220529081535.69275-1-rongwei.wang@linux.alibaba.com/
Reported-by: Rongwei Wang <rongwei.wang@linux.alibaba.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
2022-08-23 19:03:57 +02:00
|
|
|
|
2022-08-23 19:03:56 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
mm/slub: restrict sysfs validation to debug caches and make it safe
Rongwei Wang reports [1] that cache validation triggered by writing to
/sys/kernel/slab/<cache>/validate is racy against normal cache
operations (e.g. freeing) in a way that can cause false positive
inconsistency reports for caches with debugging enabled. The problem is
that debugging actions that mark object free or active and actual
freelist operations are not atomic, and the validation can see an
inconsistent state.
For caches that do or don't have debugging enabled, additional races
involving n->nr_slabs are possible that result in false reports of wrong
slab counts.
This patch attempts to solve these issues while not adding overhead to
normal (especially fastpath) operations for caches that do not have
debugging enabled. Such overhead would not be justified to make possible
userspace-triggered validation safe. Instead, disable the validation for
caches that don't have debugging enabled and make their sysfs validate
handler return -EINVAL.
For caches that do have debugging enabled, we can instead extend the
existing approach of not using percpu freelists to force all alloc/free
operations to the slow paths where debugging flags is checked and acted
upon. There can adjust the debug-specific paths to increase n->list_lock
coverage against concurrent validation as necessary.
The processing on free in free_debug_processing() already happens under
n->list_lock so we can extend it to actually do the freeing as well and
thus make it atomic against concurrent validation. As observed by
Hyeonggon Yoo, we do not really need to take slab_lock() anymore here
because all paths we could race with are protected by n->list_lock under
the new scheme, so drop its usage here.
The processing on alloc in alloc_debug_processing() currently doesn't
take any locks, but we have to first allocate the object from a slab on
the partial list (as debugging caches have no percpu slabs) and thus
take the n->list_lock anyway. Add a function alloc_single_from_partial()
that grabs just the allocated object instead of the whole freelist, and
does the debug processing. The n->list_lock coverage again makes it
atomic against validation and it is also ultimately more efficient than
the current grabbing of freelist immediately followed by slab
deactivation.
To prevent races on n->nr_slabs updates, make sure that for caches with
debugging enabled, inc_slabs_node() or dec_slabs_node() is called under
n->list_lock. When allocating a new slab for a debug cache, handle the
allocation by a new function alloc_single_from_new_slab() instead of the
current forced deactivation path.
Neither of these changes affect the fast paths at all. The changes in
slow paths are negligible for non-debug caches.
[1] https://lore.kernel.org/all/20220529081535.69275-1-rongwei.wang@linux.alibaba.com/
Reported-by: Rongwei Wang <rongwei.wang@linux.alibaba.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
2022-08-23 19:03:57 +02:00
|
|
|
|
2022-08-23 19:03:56 +02:00
|
|
|
|
mm/slub: restrict sysfs validation to debug caches and make it safe
Rongwei Wang reports [1] that cache validation triggered by writing to
/sys/kernel/slab/<cache>/validate is racy against normal cache
operations (e.g. freeing) in a way that can cause false positive
inconsistency reports for caches with debugging enabled. The problem is
that debugging actions that mark object free or active and actual
freelist operations are not atomic, and the validation can see an
inconsistent state.
For caches that do or don't have debugging enabled, additional races
involving n->nr_slabs are possible that result in false reports of wrong
slab counts.
This patch attempts to solve these issues while not adding overhead to
normal (especially fastpath) operations for caches that do not have
debugging enabled. Such overhead would not be justified to make possible
userspace-triggered validation safe. Instead, disable the validation for
caches that don't have debugging enabled and make their sysfs validate
handler return -EINVAL.
For caches that do have debugging enabled, we can instead extend the
existing approach of not using percpu freelists to force all alloc/free
operations to the slow paths where debugging flags is checked and acted
upon. There can adjust the debug-specific paths to increase n->list_lock
coverage against concurrent validation as necessary.
The processing on free in free_debug_processing() already happens under
n->list_lock so we can extend it to actually do the freeing as well and
thus make it atomic against concurrent validation. As observed by
Hyeonggon Yoo, we do not really need to take slab_lock() anymore here
because all paths we could race with are protected by n->list_lock under
the new scheme, so drop its usage here.
The processing on alloc in alloc_debug_processing() currently doesn't
take any locks, but we have to first allocate the object from a slab on
the partial list (as debugging caches have no percpu slabs) and thus
take the n->list_lock anyway. Add a function alloc_single_from_partial()
that grabs just the allocated object instead of the whole freelist, and
does the debug processing. The n->list_lock coverage again makes it
atomic against validation and it is also ultimately more efficient than
the current grabbing of freelist immediately followed by slab
deactivation.
To prevent races on n->nr_slabs updates, make sure that for caches with
debugging enabled, inc_slabs_node() or dec_slabs_node() is called under
n->list_lock. When allocating a new slab for a debug cache, handle the
allocation by a new function alloc_single_from_new_slab() instead of the
current forced deactivation path.
Neither of these changes affect the fast paths at all. The changes in
slow paths are negligible for non-debug caches.
[1] https://lore.kernel.org/all/20220529081535.69275-1-rongwei.wang@linux.alibaba.com/
Reported-by: Rongwei Wang <rongwei.wang@linux.alibaba.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
2022-08-23 19:03:57 +02:00
|
|
|
|
2022-11-21 16:06:38 +01:00
|
|
|
|
mm/slub: restrict sysfs validation to debug caches and make it safe
Rongwei Wang reports [1] that cache validation triggered by writing to
/sys/kernel/slab/<cache>/validate is racy against normal cache
operations (e.g. freeing) in a way that can cause false positive
inconsistency reports for caches with debugging enabled. The problem is
that debugging actions that mark object free or active and actual
freelist operations are not atomic, and the validation can see an
inconsistent state.
For caches that do or don't have debugging enabled, additional races
involving n->nr_slabs are possible that result in false reports of wrong
slab counts.
This patch attempts to solve these issues while not adding overhead to
normal (especially fastpath) operations for caches that do not have
debugging enabled. Such overhead would not be justified to make possible
userspace-triggered validation safe. Instead, disable the validation for
caches that don't have debugging enabled and make their sysfs validate
handler return -EINVAL.
For caches that do have debugging enabled, we can instead extend the
existing approach of not using percpu freelists to force all alloc/free
operations to the slow paths where debugging flags is checked and acted
upon. There can adjust the debug-specific paths to increase n->list_lock
coverage against concurrent validation as necessary.
The processing on free in free_debug_processing() already happens under
n->list_lock so we can extend it to actually do the freeing as well and
thus make it atomic against concurrent validation. As observed by
Hyeonggon Yoo, we do not really need to take slab_lock() anymore here
because all paths we could race with are protected by n->list_lock under
the new scheme, so drop its usage here.
The processing on alloc in alloc_debug_processing() currently doesn't
take any locks, but we have to first allocate the object from a slab on
the partial list (as debugging caches have no percpu slabs) and thus
take the n->list_lock anyway. Add a function alloc_single_from_partial()
that grabs just the allocated object instead of the whole freelist, and
does the debug processing. The n->list_lock coverage again makes it
atomic against validation and it is also ultimately more efficient than
the current grabbing of freelist immediately followed by slab
deactivation.
To prevent races on n->nr_slabs updates, make sure that for caches with
debugging enabled, inc_slabs_node() or dec_slabs_node() is called under
n->list_lock. When allocating a new slab for a debug cache, handle the
allocation by a new function alloc_single_from_new_slab() instead of the
current forced deactivation path.
Neither of these changes affect the fast paths at all. The changes in
slow paths are negligible for non-debug caches.
[1] https://lore.kernel.org/all/20220529081535.69275-1-rongwei.wang@linux.alibaba.com/
Reported-by: Rongwei Wang <rongwei.wang@linux.alibaba.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
2022-08-23 19:03:57 +02:00
|
|
|
|
2022-11-21 16:06:38 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-08-23 19:03:56 +02:00
|
|
|
|
mm/slub: restrict sysfs validation to debug caches and make it safe
Rongwei Wang reports [1] that cache validation triggered by writing to
/sys/kernel/slab/<cache>/validate is racy against normal cache
operations (e.g. freeing) in a way that can cause false positive
inconsistency reports for caches with debugging enabled. The problem is
that debugging actions that mark object free or active and actual
freelist operations are not atomic, and the validation can see an
inconsistent state.
For caches that do or don't have debugging enabled, additional races
involving n->nr_slabs are possible that result in false reports of wrong
slab counts.
This patch attempts to solve these issues while not adding overhead to
normal (especially fastpath) operations for caches that do not have
debugging enabled. Such overhead would not be justified to make possible
userspace-triggered validation safe. Instead, disable the validation for
caches that don't have debugging enabled and make their sysfs validate
handler return -EINVAL.
For caches that do have debugging enabled, we can instead extend the
existing approach of not using percpu freelists to force all alloc/free
operations to the slow paths where debugging flags is checked and acted
upon. There can adjust the debug-specific paths to increase n->list_lock
coverage against concurrent validation as necessary.
The processing on free in free_debug_processing() already happens under
n->list_lock so we can extend it to actually do the freeing as well and
thus make it atomic against concurrent validation. As observed by
Hyeonggon Yoo, we do not really need to take slab_lock() anymore here
because all paths we could race with are protected by n->list_lock under
the new scheme, so drop its usage here.
The processing on alloc in alloc_debug_processing() currently doesn't
take any locks, but we have to first allocate the object from a slab on
the partial list (as debugging caches have no percpu slabs) and thus
take the n->list_lock anyway. Add a function alloc_single_from_partial()
that grabs just the allocated object instead of the whole freelist, and
does the debug processing. The n->list_lock coverage again makes it
atomic against validation and it is also ultimately more efficient than
the current grabbing of freelist immediately followed by slab
deactivation.
To prevent races on n->nr_slabs updates, make sure that for caches with
debugging enabled, inc_slabs_node() or dec_slabs_node() is called under
n->list_lock. When allocating a new slab for a debug cache, handle the
allocation by a new function alloc_single_from_new_slab() instead of the
current forced deactivation path.
Neither of these changes affect the fast paths at all. The changes in
slow paths are negligible for non-debug caches.
[1] https://lore.kernel.org/all/20220529081535.69275-1-rongwei.wang@linux.alibaba.com/
Reported-by: Rongwei Wang <rongwei.wang@linux.alibaba.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
2022-08-23 19:03:57 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-08-23 19:03:56 +02:00
|
|
|
|
mm/slub: restrict sysfs validation to debug caches and make it safe
Rongwei Wang reports [1] that cache validation triggered by writing to
/sys/kernel/slab/<cache>/validate is racy against normal cache
operations (e.g. freeing) in a way that can cause false positive
inconsistency reports for caches with debugging enabled. The problem is
that debugging actions that mark object free or active and actual
freelist operations are not atomic, and the validation can see an
inconsistent state.
For caches that do or don't have debugging enabled, additional races
involving n->nr_slabs are possible that result in false reports of wrong
slab counts.
This patch attempts to solve these issues while not adding overhead to
normal (especially fastpath) operations for caches that do not have
debugging enabled. Such overhead would not be justified to make possible
userspace-triggered validation safe. Instead, disable the validation for
caches that don't have debugging enabled and make their sysfs validate
handler return -EINVAL.
For caches that do have debugging enabled, we can instead extend the
existing approach of not using percpu freelists to force all alloc/free
operations to the slow paths where debugging flags is checked and acted
upon. There can adjust the debug-specific paths to increase n->list_lock
coverage against concurrent validation as necessary.
The processing on free in free_debug_processing() already happens under
n->list_lock so we can extend it to actually do the freeing as well and
thus make it atomic against concurrent validation. As observed by
Hyeonggon Yoo, we do not really need to take slab_lock() anymore here
because all paths we could race with are protected by n->list_lock under
the new scheme, so drop its usage here.
The processing on alloc in alloc_debug_processing() currently doesn't
take any locks, but we have to first allocate the object from a slab on
the partial list (as debugging caches have no percpu slabs) and thus
take the n->list_lock anyway. Add a function alloc_single_from_partial()
that grabs just the allocated object instead of the whole freelist, and
does the debug processing. The n->list_lock coverage again makes it
atomic against validation and it is also ultimately more efficient than
the current grabbing of freelist immediately followed by slab
deactivation.
To prevent races on n->nr_slabs updates, make sure that for caches with
debugging enabled, inc_slabs_node() or dec_slabs_node() is called under
n->list_lock. When allocating a new slab for a debug cache, handle the
allocation by a new function alloc_single_from_new_slab() instead of the
current forced deactivation path.
Neither of these changes affect the fast paths at all. The changes in
slow paths are negligible for non-debug caches.
[1] https://lore.kernel.org/all/20220529081535.69275-1-rongwei.wang@linux.alibaba.com/
Reported-by: Rongwei Wang <rongwei.wang@linux.alibaba.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
2022-08-23 19:03:57 +02:00
|
|
|
|
2022-11-21 16:06:38 +01:00
|
|
|
|
2022-08-23 19:03:56 +02:00
|
|
|
|
mm, slab: suppress out of memory warning unless debug is enabled
When the slab or slub allocators cannot allocate additional slab pages,
they emit diagnostic information to the kernel log such as current
number of slabs, number of objects, active objects, etc. This is always
coupled with a page allocation failure warning since it is controlled by
!__GFP_NOWARN.
Suppress this out of memory warning if the allocator is configured
without debug supported. The page allocation failure warning will
indicate it is a failed slab allocation, the order, and the gfp mask, so
this is only useful to diagnose allocator issues.
Since CONFIG_SLUB_DEBUG is already enabled by default for the slub
allocator, there is no functional change with this patch. If debug is
disabled, however, the warnings are now suppressed.
Signed-off-by: David Rientjes <rientjes@google.com>
Cc: Pekka Enberg <penberg@kernel.org>
Acked-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-06-04 16:06:36 -07:00
|
|
|
|
|
|
|
|
|
2022-11-14 18:18:39 +01:00
|
|
|
|
2009-06-10 18:50:32 +03:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2009-06-10 18:50:32 +03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2009-06-10 18:50:32 +03:00
|
|
|
|
|
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
|
|
|
|
|
2009-06-10 18:50:32 +03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-11-14 18:18:39 +01:00
|
|
|
|
2009-06-11 14:08:48 +04:00
|
|
|
|
2022-11-21 16:23:50 +01:00
|
|
|
|
slub: introduce count_partial_free_approx()
When reading "/proc/slabinfo", the kernel needs to report the number
of free objects for each kmem_cache. The current implementation uses
count_partial() to get it by scanning each kmem_cache_node's partial
slab list and summing free objects from every partial slab. This
process must hold per-kmem_cache_node spinlock and disable IRQ, and
may take a long time. Consequently, it can block slab allocations on
other CPUs and cause timeouts for network devices, when the partial
list is long. In production, even NMI watchdog can be triggered due
to this matter: e.g., for "buffer_head", the number of partial slabs
was observed to be ~1M in one kmem_cache_node. This problem was also
confirmed by others [1-3].
Iterating a partial list to get the exact count of objects can cause
soft lockups for a long list with or without the lock (e.g., if
preemption is disabled), and may not be very useful: the object count
can change after the lock is released. The approach of maintaining
free-object counters requires atomic operations on the fast path [3].
So, the fix is to introduce count_partial_free_approx(). This function
can be used for getting the free object count in a kmem_cache_node's
partial list. It limits the number of slabs to scan and avoids scanning
the whole list by giving an approximation for a long list. Suppose the
limit is N. If the list's length is not greater than N, output the exact
count by traversing the list; if its length is greater than N, output an
approximated count by traversing a subset of the list. The proposed
method is to scan N/2 slabs from the list's head and N/2 slabs from
the tail. For a partial list with ~280K slabs, benchmarks show that
it performs better than just counting from the list's head, after slabs
get sorted by kmem_cache_shrink(). Default the limit to 10000, as it
produces an approximation within 1% of the exact count for both
scenarios. Then, use count_partial_free_approx() in get_slabinfo().
Benchmarks: Diff = (exact - approximated) / exact
* Normal case (w/o kmem_cache_shrink()):
| MAX_TO_SCAN | Diff (count from head)| Diff (count head+tail)|
| 1000 | 0.43 % | 1.09 % |
| 5000 | 0.06 % | 0.37 % |
| 10000 | 0.02 % | 0.16 % |
| 20000 | 0.009 % | -0.003 % |
* Skewed case (w/ kmem_cache_shrink()):
| MAX_TO_SCAN | Diff (count from head)| Diff (count head+tail)|
| 1000 | 12.46 % | 6.75 % |
| 5000 | 5.38 % | 1.27 % |
| 10000 | 4.99 % | 0.22 % |
| 20000 | 4.86 % | -0.06 % |
[1] https://lore.kernel.org/linux-mm/alpine.DEB.2.21.2003031602460.1537@www.lameter.com/T/
[2] https://lore.kernel.org/lkml/alpine.DEB.2.22.394.2008071258020.55871@www.lameter.com/T/
[3] https://lore.kernel.org/lkml/1e01092b-140d-2bab-aeba-321a74a194ee@linux.com/T/
Signed-off-by: Jianfeng Wang <jianfeng.w.wang@oracle.com>
Acked-by: David Rientjes <rientjes@google.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2024-04-22 21:55:53 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2009-06-10 18:50:32 +03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
mm, slab: suppress out of memory warning unless debug is enabled
When the slab or slub allocators cannot allocate additional slab pages,
they emit diagnostic information to the kernel log such as current
number of slabs, number of objects, active objects, etc. This is always
coupled with a page allocation failure warning since it is controlled by
!__GFP_NOWARN.
Suppress this out of memory warning if the allocator is configured
without debug supported. The page allocation failure warning will
indicate it is a failed slab allocation, the order, and the gfp mask, so
this is only useful to diagnose allocator issues.
Since CONFIG_SLUB_DEBUG is already enabled by default for the slub
allocator, there is no functional change with this patch. If debug is
disabled, however, the warnings are now suppressed.
Signed-off-by: David Rientjes <rientjes@google.com>
Cc: Pekka Enberg <penberg@kernel.org>
Acked-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-06-04 16:06:36 -07:00
|
|
|
|
|
|
|
|
|
2024-08-14 14:50:37 -07:00
|
|
|
|
2009-06-10 18:50:32 +03:00
|
|
|
|
2014-08-06 16:04:09 -07:00
|
|
|
|
2009-06-10 18:50:32 +03:00
|
|
|
|
mm, slab: suppress out of memory warning unless debug is enabled
When the slab or slub allocators cannot allocate additional slab pages,
they emit diagnostic information to the kernel log such as current
number of slabs, number of objects, active objects, etc. This is always
coupled with a page allocation failure warning since it is controlled by
!__GFP_NOWARN.
Suppress this out of memory warning if the allocator is configured
without debug supported. The page allocation failure warning will
indicate it is a failed slab allocation, the order, and the gfp mask, so
this is only useful to diagnose allocator issues.
Since CONFIG_SLUB_DEBUG is already enabled by default for the slub
allocator, there is no functional change with this patch. If debug is
disabled, however, the warnings are now suppressed.
Signed-off-by: David Rientjes <rientjes@google.com>
Cc: Pekka Enberg <penberg@kernel.org>
Acked-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-06-04 16:06:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-08-14 14:50:37 -07:00
|
|
|
|
|
|
|
|
|
2018-04-05 16:21:39 -07:00
|
|
|
|
2014-06-04 16:06:34 -07:00
|
|
|
|
|
|
|
|
|
2009-06-10 18:50:32 +03:00
|
|
|
|
2012-06-13 10:24:57 -05:00
|
|
|
|
2023-12-15 11:41:48 +08:00
|
|
|
|
2014-06-04 16:06:34 -07:00
|
|
|
|
2009-07-07 00:14:14 -07:00
|
|
|
|
2014-08-06 16:04:09 -07:00
|
|
|
|
2009-06-10 18:50:32 +03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-04-22 21:55:54 -07:00
|
|
|
|
2009-06-11 14:08:48 +04:00
|
|
|
|
|
|
|
|
|
2009-06-10 18:50:32 +03:00
|
|
|
|
2014-06-04 16:06:34 -07:00
|
|
|
|
2009-06-10 18:50:32 +03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-11-21 16:23:50 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2009-06-10 18:50:32 +03:00
|
|
|
|
2021-10-04 14:46:40 +01:00
|
|
|
|
mm: sl[au]b: add knowledge of PFMEMALLOC reserve pages
When a user or administrator requires swap for their application, they
create a swap partition and file, format it with mkswap and activate it
with swapon. Swap over the network is considered as an option in diskless
systems. The two likely scenarios are when blade servers are used as part
of a cluster where the form factor or maintenance costs do not allow the
use of disks and thin clients.
The Linux Terminal Server Project recommends the use of the Network Block
Device (NBD) for swap according to the manual at
https://sourceforge.net/projects/ltsp/files/Docs-Admin-Guide/LTSPManual.pdf/download
There is also documentation and tutorials on how to setup swap over NBD at
places like https://help.ubuntu.com/community/UbuntuLTSP/EnableNBDSWAP The
nbd-client also documents the use of NBD as swap. Despite this, the fact
is that a machine using NBD for swap can deadlock within minutes if swap
is used intensively. This patch series addresses the problem.
The core issue is that network block devices do not use mempools like
normal block devices do. As the host cannot control where they receive
packets from, they cannot reliably work out in advance how much memory
they might need. Some years ago, Peter Zijlstra developed a series of
patches that supported swap over an NFS that at least one distribution is
carrying within their kernels. This patch series borrows very heavily
from Peter's work to support swapping over NBD as a pre-requisite to
supporting swap-over-NFS. The bulk of the complexity is concerned with
preserving memory that is allocated from the PFMEMALLOC reserves for use
by the network layer which is needed for both NBD and NFS.
Patch 1 adds knowledge of the PFMEMALLOC reserves to SLAB and SLUB to
preserve access to pages allocated under low memory situations
to callers that are freeing memory.
Patch 2 optimises the SLUB fast path to avoid pfmemalloc checks
Patch 3 introduces __GFP_MEMALLOC to allow access to the PFMEMALLOC
reserves without setting PFMEMALLOC.
Patch 4 opens the possibility for softirqs to use PFMEMALLOC reserves
for later use by network packet processing.
Patch 5 only sets page->pfmemalloc when ALLOC_NO_WATERMARKS was required
Patch 6 ignores memory policies when ALLOC_NO_WATERMARKS is set.
Patches 7-12 allows network processing to use PFMEMALLOC reserves when
the socket has been marked as being used by the VM to clean pages. If
packets are received and stored in pages that were allocated under
low-memory situations and are unrelated to the VM, the packets
are dropped.
Patch 11 reintroduces __skb_alloc_page which the networking
folk may object to but is needed in some cases to propogate
pfmemalloc from a newly allocated page to an skb. If there is a
strong objection, this patch can be dropped with the impact being
that swap-over-network will be slower in some cases but it should
not fail.
Patch 13 is a micro-optimisation to avoid a function call in the
common case.
Patch 14 tags NBD sockets as being SOCK_MEMALLOC so they can use
PFMEMALLOC if necessary.
Patch 15 notes that it is still possible for the PFMEMALLOC reserve
to be depleted. To prevent this, direct reclaimers get throttled on
a waitqueue if 50% of the PFMEMALLOC reserves are depleted. It is
expected that kswapd and the direct reclaimers already running
will clean enough pages for the low watermark to be reached and
the throttled processes are woken up.
Patch 16 adds a statistic to track how often processes get throttled
Some basic performance testing was run using kernel builds, netperf on
loopback for UDP and TCP, hackbench (pipes and sockets), iozone and
sysbench. Each of them were expected to use the sl*b allocators
reasonably heavily but there did not appear to be significant performance
variances.
For testing swap-over-NBD, a machine was booted with 2G of RAM with a
swapfile backed by NBD. 8*NUM_CPU processes were started that create
anonymous memory mappings and read them linearly in a loop. The total
size of the mappings were 4*PHYSICAL_MEMORY to use swap heavily under
memory pressure.
Without the patches and using SLUB, the machine locks up within minutes
and runs to completion with them applied. With SLAB, the story is
different as an unpatched kernel run to completion. However, the patched
kernel completed the test 45% faster.
MICRO
3.5.0-rc2 3.5.0-rc2
vanilla swapnbd
Unrecognised test vmscan-anon-mmap-write
MMTests Statistics: duration
Sys Time Running Test (seconds) 197.80 173.07
User+Sys Time Running Test (seconds) 206.96 182.03
Total Elapsed Time (seconds) 3240.70 1762.09
This patch: mm: sl[au]b: add knowledge of PFMEMALLOC reserve pages
Allocations of pages below the min watermark run a risk of the machine
hanging due to a lack of memory. To prevent this, only callers who have
PF_MEMALLOC or TIF_MEMDIE set and are not processing an interrupt are
allowed to allocate with ALLOC_NO_WATERMARKS. Once they are allocated to
a slab though, nothing prevents other callers consuming free objects
within those slabs. This patch limits access to slab pages that were
alloced from the PFMEMALLOC reserves.
When this patch is applied, pages allocated from below the low watermark
are returned with page->pfmemalloc set and it is up to the caller to
determine how the page should be protected. SLAB restricts access to any
page with page->pfmemalloc set to callers which are known to able to
access the PFMEMALLOC reserve. If one is not available, an attempt is
made to allocate a new page rather than use a reserve. SLUB is a bit more
relaxed in that it only records if the current per-CPU page was allocated
from PFMEMALLOC reserve and uses another partial slab if the caller does
not have the necessary GFP or process flags. This was found to be
sufficient in tests to avoid hangs due to SLUB generally maintaining
smaller lists than SLAB.
In low-memory conditions it does mean that !PFMEMALLOC allocators can fail
a slab allocation even though free objects are available because they are
being preserved for callers that are freeing pages.
[a.p.zijlstra@chello.nl: Original implementation]
[sebastian@breakpoint.cc: Correct order of page flag clearing]
Signed-off-by: Mel Gorman <mgorman@suse.de>
Cc: David Miller <davem@davemloft.net>
Cc: Neil Brown <neilb@suse.de>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Mike Christie <michaelc@cs.wisc.edu>
Cc: Eric B Munson <emunson@mgebm.net>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Sebastian Andrzej Siewior <sebastian@breakpoint.cc>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Christoph Lameter <cl@linux.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-07-31 16:43:58 -07:00
|
|
|
|
2021-10-04 14:46:40 +01:00
|
|
|
|
2021-05-08 02:28:02 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-11-15 18:14:31 +01:00
|
|
|
|
2023-05-31 15:08:43 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-11-11 14:07:14 -06:00
|
|
|
|
2021-11-15 16:55:15 +01:00
|
|
|
|
|
|
|
|
|
2011-11-11 14:07:14 -06:00
|
|
|
|
2021-11-15 16:55:15 +01:00
|
|
|
|
2011-11-11 14:07:14 -06:00
|
|
|
|
2021-11-15 16:55:15 +01:00
|
|
|
|
2011-11-11 14:07:14 -06:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2011-11-11 14:07:14 -06:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2011-11-11 14:07:14 -06:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-05-22 01:59:38 +02:00
|
|
|
|
|
|
|
|
|
2011-11-11 14:07:14 -06:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
|
|
|
|
|
2012-05-09 10:09:51 -05:00
|
|
|
|
2011-11-11 14:07:14 -06:00
|
|
|
|
|
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2011-11-11 14:07:14 -06:00
|
|
|
|
|
|
|
|
|
2023-05-31 15:08:43 +02:00
|
|
|
|
2011-11-11 14:07:14 -06:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-11-02 03:23:26 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2007-05-10 03:15:16 -07:00
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2007-05-10 03:15:16 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2007-05-10 03:15:16 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-02-15 23:45:26 -08:00
|
|
|
|
|
|
|
|
|
2015-11-20 15:57:35 -08:00
|
|
|
|
mm, slub: move disabling/enabling irqs to ___slab_alloc()
Currently __slab_alloc() disables irqs around the whole ___slab_alloc(). This
includes cases where this is not needed, such as when the allocation ends up in
the page allocator and has to awkwardly enable irqs back based on gfp flags.
Also the whole kmem_cache_alloc_bulk() is executed with irqs disabled even when
it hits the __slab_alloc() slow path, and long periods with disabled interrupts
are undesirable.
As a first step towards reducing irq disabled periods, move irq handling into
___slab_alloc(). Callers will instead prevent the s->cpu_slab percpu pointer
from becoming invalid via get_cpu_ptr(), thus preempt_disable(). This does not
protect against modification by an irq handler, which is still done by disabled
irq for most of ___slab_alloc(). As a small immediate benefit,
slab_out_of_memory() from ___slab_alloc() is now called with irqs enabled.
kmem_cache_alloc_bulk() disables irqs for its fastpath and then re-enables them
before calling ___slab_alloc(), which then disables them at its discretion. The
whole kmem_cache_alloc_bulk() operation also disables preemption.
When ___slab_alloc() calls new_slab() to allocate a new page, re-enable
preemption, because new_slab() will re-enable interrupts in contexts that allow
blocking (this will be improved by later patches).
The patch itself will thus increase overhead a bit due to disabled preemption
(on configs where it matters) and increased disabling/enabling irqs in
kmem_cache_alloc_bulk(), but that will be gradually improved in the following
patches.
Note in __slab_alloc() we need to change the #ifdef CONFIG_PREEMPT guard to
CONFIG_PREEMPT_COUNT to make sure preempt disable/enable is properly paired in
all configurations. On configs without involuntary preemption and debugging
the re-read of kmem_cache_cpu pointer is still compiled out as it was before.
[ Mike Galbraith <efault@gmx.de>: Fix kmem_cache_alloc_bulk() error path ]
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2021-05-07 19:32:31 +02:00
|
|
|
|
2015-11-20 15:57:35 -08:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2015-11-20 15:57:35 -08:00
|
|
|
|
mm/slub: enable debugging memory wasting of kmalloc
kmalloc's API family is critical for mm, with one nature that it will
round up the request size to a fixed one (mostly power of 2). Say
when user requests memory for '2^n + 1' bytes, actually 2^(n+1) bytes
could be allocated, so in worst case, there is around 50% memory
space waste.
The wastage is not a big issue for requests that get allocated/freed
quickly, but may cause problems with objects that have longer life
time.
We've met a kernel boot OOM panic (v5.10), and from the dumped slab
info:
[ 26.062145] kmalloc-2k 814056KB 814056KB
From debug we found there are huge number of 'struct iova_magazine',
whose size is 1032 bytes (1024 + 8), so each allocation will waste
1016 bytes. Though the issue was solved by giving the right (bigger)
size of RAM, it is still nice to optimize the size (either use a
kmalloc friendly size or create a dedicated slab for it).
And from lkml archive, there was another crash kernel OOM case [1]
back in 2019, which seems to be related with the similar slab waste
situation, as the log is similar:
[ 4.332648] iommu: Adding device 0000:20:02.0 to group 16
[ 4.338946] swapper/0 invoked oom-killer: gfp_mask=0x6040c0(GFP_KERNEL|__GFP_COMP), nodemask=(null), order=0, oom_score_adj=0
...
[ 4.857565] kmalloc-2048 59164KB 59164KB
The crash kernel only has 256M memory, and 59M is pretty big here.
(Note: the related code has been changed and optimised in recent
kernel [2], these logs are just picked to demo the problem, also
a patch changing its size to 1024 bytes has been merged)
So add an way to track each kmalloc's memory waste info, and
leverage the existing SLUB debug framework (specifically
SLUB_STORE_USER) to show its call stack of original allocation,
so that user can evaluate the waste situation, identify some hot
spots and optimize accordingly, for a better utilization of memory.
The waste info is integrated into existing interface:
'/sys/kernel/debug/slab/kmalloc-xx/alloc_traces', one example of
'kmalloc-4k' after boot is:
126 ixgbe_alloc_q_vector+0xbe/0x830 [ixgbe] waste=233856/1856 age=280763/281414/282065 pid=1330 cpus=32 nodes=1
__kmem_cache_alloc_node+0x11f/0x4e0
__kmalloc_node+0x4e/0x140
ixgbe_alloc_q_vector+0xbe/0x830 [ixgbe]
ixgbe_init_interrupt_scheme+0x2ae/0xc90 [ixgbe]
ixgbe_probe+0x165f/0x1d20 [ixgbe]
local_pci_probe+0x78/0xc0
work_for_cpu_fn+0x26/0x40
...
which means in 'kmalloc-4k' slab, there are 126 requests of
2240 bytes which got a 4KB space (wasting 1856 bytes each
and 233856 bytes in total), from ixgbe_alloc_q_vector().
And when system starts some real workload like multiple docker
instances, there could are more severe waste.
[1]. https://lkml.org/lkml/2019/8/12/266
[2]. https://lore.kernel.org/lkml/2920df89-9975-5785-f79b-257d3052dfaf@huawei.com/
[Thanks Hyeonggon for pointing out several bugs about sorting/format]
[Thanks Vlastimil for suggesting way to reduce memory usage of
orig_size and keep it only for kmalloc objects]
Signed-off-by: Feng Tang <feng.tang@intel.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Robin Murphy <robin.murphy@arm.com>
Cc: John Garry <john.garry@huawei.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2022-09-13 14:54:20 +08:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2012-05-09 10:09:51 -05:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
mm, slub: move disabling/enabling irqs to ___slab_alloc()
Currently __slab_alloc() disables irqs around the whole ___slab_alloc(). This
includes cases where this is not needed, such as when the allocation ends up in
the page allocator and has to awkwardly enable irqs back based on gfp flags.
Also the whole kmem_cache_alloc_bulk() is executed with irqs disabled even when
it hits the __slab_alloc() slow path, and long periods with disabled interrupts
are undesirable.
As a first step towards reducing irq disabled periods, move irq handling into
___slab_alloc(). Callers will instead prevent the s->cpu_slab percpu pointer
from becoming invalid via get_cpu_ptr(), thus preempt_disable(). This does not
protect against modification by an irq handler, which is still done by disabled
irq for most of ___slab_alloc(). As a small immediate benefit,
slab_out_of_memory() from ___slab_alloc() is now called with irqs enabled.
kmem_cache_alloc_bulk() disables irqs for its fastpath and then re-enables them
before calling ___slab_alloc(), which then disables them at its discretion. The
whole kmem_cache_alloc_bulk() operation also disables preemption.
When ___slab_alloc() calls new_slab() to allocate a new page, re-enable
preemption, because new_slab() will re-enable interrupts in contexts that allow
blocking (this will be improved by later patches).
The patch itself will thus increase overhead a bit due to disabled preemption
(on configs where it matters) and increased disabling/enabling irqs in
kmem_cache_alloc_bulk(), but that will be gradually improved in the following
patches.
Note in __slab_alloc() we need to change the #ifdef CONFIG_PREEMPT guard to
CONFIG_PREEMPT_COUNT to make sure preempt disable/enable is properly paired in
all configurations. On configs without involuntary preemption and debugging
the re-read of kmem_cache_cpu pointer is still compiled out as it was before.
[ Mike Galbraith <efault@gmx.de>: Fix kmem_cache_alloc_bulk() error path ]
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2021-05-07 19:32:31 +02:00
|
|
|
|
mm/slub: enable debugging memory wasting of kmalloc
kmalloc's API family is critical for mm, with one nature that it will
round up the request size to a fixed one (mostly power of 2). Say
when user requests memory for '2^n + 1' bytes, actually 2^(n+1) bytes
could be allocated, so in worst case, there is around 50% memory
space waste.
The wastage is not a big issue for requests that get allocated/freed
quickly, but may cause problems with objects that have longer life
time.
We've met a kernel boot OOM panic (v5.10), and from the dumped slab
info:
[ 26.062145] kmalloc-2k 814056KB 814056KB
From debug we found there are huge number of 'struct iova_magazine',
whose size is 1032 bytes (1024 + 8), so each allocation will waste
1016 bytes. Though the issue was solved by giving the right (bigger)
size of RAM, it is still nice to optimize the size (either use a
kmalloc friendly size or create a dedicated slab for it).
And from lkml archive, there was another crash kernel OOM case [1]
back in 2019, which seems to be related with the similar slab waste
situation, as the log is similar:
[ 4.332648] iommu: Adding device 0000:20:02.0 to group 16
[ 4.338946] swapper/0 invoked oom-killer: gfp_mask=0x6040c0(GFP_KERNEL|__GFP_COMP), nodemask=(null), order=0, oom_score_adj=0
...
[ 4.857565] kmalloc-2048 59164KB 59164KB
The crash kernel only has 256M memory, and 59M is pretty big here.
(Note: the related code has been changed and optimised in recent
kernel [2], these logs are just picked to demo the problem, also
a patch changing its size to 1024 bytes has been merged)
So add an way to track each kmalloc's memory waste info, and
leverage the existing SLUB debug framework (specifically
SLUB_STORE_USER) to show its call stack of original allocation,
so that user can evaluate the waste situation, identify some hot
spots and optimize accordingly, for a better utilization of memory.
The waste info is integrated into existing interface:
'/sys/kernel/debug/slab/kmalloc-xx/alloc_traces', one example of
'kmalloc-4k' after boot is:
126 ixgbe_alloc_q_vector+0xbe/0x830 [ixgbe] waste=233856/1856 age=280763/281414/282065 pid=1330 cpus=32 nodes=1
__kmem_cache_alloc_node+0x11f/0x4e0
__kmalloc_node+0x4e/0x140
ixgbe_alloc_q_vector+0xbe/0x830 [ixgbe]
ixgbe_init_interrupt_scheme+0x2ae/0xc90 [ixgbe]
ixgbe_probe+0x165f/0x1d20 [ixgbe]
local_pci_probe+0x78/0xc0
work_for_cpu_fn+0x26/0x40
...
which means in 'kmalloc-4k' slab, there are 126 requests of
2240 bytes which got a 4KB space (wasting 1856 bytes each
and 233856 bytes in total), from ixgbe_alloc_q_vector().
And when system starts some real workload like multiple docker
instances, there could are more severe waste.
[1]. https://lkml.org/lkml/2019/8/12/266
[2]. https://lore.kernel.org/lkml/2920df89-9975-5785-f79b-257d3052dfaf@huawei.com/
[Thanks Hyeonggon for pointing out several bugs about sorting/format]
[Thanks Vlastimil for suggesting way to reduce memory usage of
orig_size and keep it only for kmalloc objects]
Signed-off-by: Feng Tang <feng.tang@intel.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Robin Murphy <robin.murphy@arm.com>
Cc: John Garry <john.garry@huawei.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2022-09-13 14:54:20 +08:00
|
|
|
|
mm/slub: Reduce memory consumption in extreme scenarios
When kmalloc_node() is called without __GFP_THISNODE and the target node
lacks sufficient memory, SLUB allocates a folio from a different node
other than the requested node, instead of taking a partial slab from it.
However, since the allocated folio does not belong to the requested
node, on the following allocation it is deactivated and added to the
partial slab list of the node it belongs to.
This behavior can result in excessive memory usage when the requested
node has insufficient memory, as SLUB will repeatedly allocate folios
from other nodes without reusing the previously allocated ones.
To prevent memory wastage, when a preferred node is indicated (not
NUMA_NO_NODE) but without a prior __GFP_THISNODE constraint:
1) try to get a partial slab from target node only by having
__GFP_THISNODE in pc.flags for get_partial()
2) if 1) failed, try to allocate a new slab from target node with
GFP_NOWAIT | __GFP_THISNODE opportunistically.
3) if 2) failed, retry with original gfpflags which will allow
get_partial() try partial lists of other nodes before potentially
allocating new page from other nodes
Without a preferred node, or with __GFP_THISNODE constraint, the
behavior remains unchanged.
On qemu with 4 numa nodes and each numa has 1G memory. Write a test ko
to call kmalloc_node(196, GFP_KERNEL, 3) for (4 * 1024 + 4) * 1024 times.
cat /proc/slabinfo shows:
kmalloc-256 4200530 13519712 256 32 2 : tunables..
after this patch,
cat /proc/slabinfo shows:
kmalloc-256 4200558 4200768 256 32 2 : tunables..
Signed-off-by: Chen Jun <chenjun102@huawei.com>
Signed-off-by: Kefeng Wang <wangkefeng.wang@huawei.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2024-03-30 16:23:35 +08:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2020-10-13 16:48:43 -07:00
|
|
|
|
|
|
|
|
|
2021-11-15 16:55:15 +01:00
|
|
|
|
2021-05-08 02:28:02 +02:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
|
|
|
|
|
mm, slub: prevent kmalloc_node crashes and memory leaks
Sachin reports [1] a crash in SLUB __slab_alloc():
BUG: Kernel NULL pointer dereference on read at 0x000073b0
Faulting instruction address: 0xc0000000003d55f4
Oops: Kernel access of bad area, sig: 11 [#1]
LE PAGE_SIZE=64K MMU=Hash SMP NR_CPUS=2048 NUMA pSeries
Modules linked in:
CPU: 19 PID: 1 Comm: systemd Not tainted 5.6.0-rc2-next-20200218-autotest #1
NIP: c0000000003d55f4 LR: c0000000003d5b94 CTR: 0000000000000000
REGS: c0000008b37836d0 TRAP: 0300 Not tainted (5.6.0-rc2-next-20200218-autotest)
MSR: 8000000000009033 <SF,EE,ME,IR,DR,RI,LE> CR: 24004844 XER: 00000000
CFAR: c00000000000dec4 DAR: 00000000000073b0 DSISR: 40000000 IRQMASK: 1
GPR00: c0000000003d5b94 c0000008b3783960 c00000000155d400 c0000008b301f500
GPR04: 0000000000000dc0 0000000000000002 c0000000003443d8 c0000008bb398620
GPR08: 00000008ba2f0000 0000000000000001 0000000000000000 0000000000000000
GPR12: 0000000024004844 c00000001ec52a00 0000000000000000 0000000000000000
GPR16: c0000008a1b20048 c000000001595898 c000000001750c18 0000000000000002
GPR20: c000000001750c28 c000000001624470 0000000fffffffe0 5deadbeef0000122
GPR24: 0000000000000001 0000000000000dc0 0000000000000002 c0000000003443d8
GPR28: c0000008b301f500 c0000008bb398620 0000000000000000 c00c000002287180
NIP ___slab_alloc+0x1f4/0x760
LR __slab_alloc+0x34/0x60
Call Trace:
___slab_alloc+0x334/0x760 (unreliable)
__slab_alloc+0x34/0x60
__kmalloc_node+0x110/0x490
kvmalloc_node+0x58/0x110
mem_cgroup_css_online+0x108/0x270
online_css+0x48/0xd0
cgroup_apply_control_enable+0x2ec/0x4d0
cgroup_mkdir+0x228/0x5f0
kernfs_iop_mkdir+0x90/0xf0
vfs_mkdir+0x110/0x230
do_mkdirat+0xb0/0x1a0
system_call+0x5c/0x68
This is a PowerPC platform with following NUMA topology:
available: 2 nodes (0-1)
node 0 cpus:
node 0 size: 0 MB
node 0 free: 0 MB
node 1 cpus: 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31
node 1 size: 35247 MB
node 1 free: 30907 MB
node distances:
node 0 1
0: 10 40
1: 40 10
possible numa nodes: 0-31
This only happens with a mmotm patch "mm/memcontrol.c: allocate
shrinker_map on appropriate NUMA node" [2] which effectively calls
kmalloc_node for each possible node. SLUB however only allocates
kmem_cache_node on online N_NORMAL_MEMORY nodes, and relies on
node_to_mem_node to return such valid node for other nodes since commit
a561ce00b09e ("slub: fall back to node_to_mem_node() node if allocating
on memoryless node"). This is however not true in this configuration
where the _node_numa_mem_ array is not initialized for nodes 0 and 2-31,
thus it contains zeroes and get_partial() ends up accessing
non-allocated kmem_cache_node.
A related issue was reported by Bharata (originally by Ramachandran) [3]
where a similar PowerPC configuration, but with mainline kernel without
patch [2] ends up allocating large amounts of pages by kmalloc-1k
kmalloc-512. This seems to have the same underlying issue with
node_to_mem_node() not behaving as expected, and might probably also
lead to an infinite loop with CONFIG_SLUB_CPU_PARTIAL [4].
This patch should fix both issues by not relying on node_to_mem_node()
anymore and instead simply falling back to NUMA_NO_NODE, when
kmalloc_node(node) is attempted for a node that's not online, or has no
usable memory. The "usable memory" condition is also changed from
node_present_pages() to N_NORMAL_MEMORY node state, as that is exactly
the condition that SLUB uses to allocate kmem_cache_node structures.
The check in get_partial() is removed completely, as the checks in
___slab_alloc() are now sufficient to prevent get_partial() being
reached with an invalid node.
[1] https://lore.kernel.org/linux-next/3381CD91-AB3D-4773-BA04-E7A072A63968@linux.vnet.ibm.com/
[2] https://lore.kernel.org/linux-mm/fff0e636-4c36-ed10-281c-8cdb0687c839@virtuozzo.com/
[3] https://lore.kernel.org/linux-mm/20200317092624.GB22538@in.ibm.com/
[4] https://lore.kernel.org/linux-mm/088b5996-faae-8a56-ef9c-5b567125ae54@suse.cz/
Fixes: a561ce00b09e ("slub: fall back to node_to_mem_node() node if allocating on memoryless node")
Reported-by: Sachin Sant <sachinp@linux.vnet.ibm.com>
Reported-by: PUVICHAKRAVARTHY RAMACHANDRAN <puvichakravarthy@in.ibm.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Tested-by: Sachin Sant <sachinp@linux.vnet.ibm.com>
Tested-by: Bharata B Rao <bharata@linux.ibm.com>
Reviewed-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Christopher Lameter <cl@linux.com>
Cc: linuxppc-dev@lists.ozlabs.org
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Kirill Tkhai <ktkhai@virtuozzo.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Nathan Lynch <nathanl@linux.ibm.com>
Cc: <stable@vger.kernel.org>
Link: http://lkml.kernel.org/r/20200320115533.9604-1-vbabka@suse.cz
Debugged-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-03-21 18:22:37 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
mm, slab, slub: stop taking memory hotplug lock
Since commit 03afc0e25f7f ("slab: get_online_mems for
kmem_cache_{create,destroy,shrink}") we are taking memory hotplug lock for
SLAB and SLUB when creating, destroying or shrinking a cache. It is quite
a heavy lock and it's best to avoid it if possible, as we had several
issues with lockdep complaining about ordering in the past, see e.g.
e4f8e513c3d3 ("mm/slub: fix a deadlock in show_slab_objects()").
The problem scenario in 03afc0e25f7f (solved by the memory hotplug lock)
can be summarized as follows: while there's slab_mutex synchronizing new
kmem cache creation and SLUB's MEM_GOING_ONLINE callback
slab_mem_going_online_callback(), we may miss creation of kmem_cache_node
for the hotplugged node in the new kmem cache, because the hotplug
callback doesn't yet see the new cache, and cache creation in
init_kmem_cache_nodes() only inits kmem_cache_node for nodes in the
N_NORMAL_MEMORY nodemask, which however may not yet include the new node,
as that happens only later after the MEM_GOING_ONLINE callback.
Instead of using get/put_online_mems(), the problem can be solved by SLUB
maintaining its own nodemask of nodes for which it has allocated the
per-node kmem_cache_node structures. This nodemask would generally mirror
the N_NORMAL_MEMORY nodemask, but would be updated only in under SLUB's
control in its memory hotplug callbacks under the slab_mutex. This patch
adds such nodemask and its handling.
Commit 03afc0e25f7f mentiones "issues like [the one above]", but there
don't appear to be further issues. All the paths (shared for SLAB and
SLUB) taking the memory hotplug locks are also taking the slab_mutex,
except kmem_cache_shrink() where 03afc0e25f7f replaced slab_mutex with
get/put_online_mems().
We however cannot simply restore slab_mutex in kmem_cache_shrink(), as
SLUB can enters the function from a write to sysfs 'shrink' file, thus
holding kernfs lock, and in kmem_cache_create() the kernfs lock is nested
within slab_mutex. But on closer inspection we don't actually need to
protect kmem_cache_shrink() from hotplug callbacks: While SLUB's
__kmem_cache_shrink() does for_each_kmem_cache_node(), missing a new node
added in parallel hotplug is not fatal, and parallel hotremove does not
free kmem_cache_node's anymore after the previous patch, so use-after free
cannot happen. The per-node shrinking itself is protected by
n->list_lock. Same is true for SLAB, and SLOB is no-op.
SLAB also doesn't need the memory hotplug locking, which it only gained by
03afc0e25f7f through the shared paths in slab_common.c. Its memory
hotplug callbacks are also protected by slab_mutex against races with
these paths. The problem of SLUB relying on N_NORMAL_MEMORY doesn't apply
to SLAB, as its setup_kmem_cache_nodes relies on N_ONLINE, and the new
node is already set there during the MEM_GOING_ONLINE callback, so no
special care is needed for SLAB.
As such, this patch removes all get/put_online_mems() usage by the slab
subsystem.
Link: https://lkml.kernel.org/r/20210113131634.3671-3-vbabka@suse.cz
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Christoph Lameter <cl@linux.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Qian Cai <cai@redhat.com>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-02-24 12:01:12 -08:00
|
|
|
|
mm, slub: prevent kmalloc_node crashes and memory leaks
Sachin reports [1] a crash in SLUB __slab_alloc():
BUG: Kernel NULL pointer dereference on read at 0x000073b0
Faulting instruction address: 0xc0000000003d55f4
Oops: Kernel access of bad area, sig: 11 [#1]
LE PAGE_SIZE=64K MMU=Hash SMP NR_CPUS=2048 NUMA pSeries
Modules linked in:
CPU: 19 PID: 1 Comm: systemd Not tainted 5.6.0-rc2-next-20200218-autotest #1
NIP: c0000000003d55f4 LR: c0000000003d5b94 CTR: 0000000000000000
REGS: c0000008b37836d0 TRAP: 0300 Not tainted (5.6.0-rc2-next-20200218-autotest)
MSR: 8000000000009033 <SF,EE,ME,IR,DR,RI,LE> CR: 24004844 XER: 00000000
CFAR: c00000000000dec4 DAR: 00000000000073b0 DSISR: 40000000 IRQMASK: 1
GPR00: c0000000003d5b94 c0000008b3783960 c00000000155d400 c0000008b301f500
GPR04: 0000000000000dc0 0000000000000002 c0000000003443d8 c0000008bb398620
GPR08: 00000008ba2f0000 0000000000000001 0000000000000000 0000000000000000
GPR12: 0000000024004844 c00000001ec52a00 0000000000000000 0000000000000000
GPR16: c0000008a1b20048 c000000001595898 c000000001750c18 0000000000000002
GPR20: c000000001750c28 c000000001624470 0000000fffffffe0 5deadbeef0000122
GPR24: 0000000000000001 0000000000000dc0 0000000000000002 c0000000003443d8
GPR28: c0000008b301f500 c0000008bb398620 0000000000000000 c00c000002287180
NIP ___slab_alloc+0x1f4/0x760
LR __slab_alloc+0x34/0x60
Call Trace:
___slab_alloc+0x334/0x760 (unreliable)
__slab_alloc+0x34/0x60
__kmalloc_node+0x110/0x490
kvmalloc_node+0x58/0x110
mem_cgroup_css_online+0x108/0x270
online_css+0x48/0xd0
cgroup_apply_control_enable+0x2ec/0x4d0
cgroup_mkdir+0x228/0x5f0
kernfs_iop_mkdir+0x90/0xf0
vfs_mkdir+0x110/0x230
do_mkdirat+0xb0/0x1a0
system_call+0x5c/0x68
This is a PowerPC platform with following NUMA topology:
available: 2 nodes (0-1)
node 0 cpus:
node 0 size: 0 MB
node 0 free: 0 MB
node 1 cpus: 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31
node 1 size: 35247 MB
node 1 free: 30907 MB
node distances:
node 0 1
0: 10 40
1: 40 10
possible numa nodes: 0-31
This only happens with a mmotm patch "mm/memcontrol.c: allocate
shrinker_map on appropriate NUMA node" [2] which effectively calls
kmalloc_node for each possible node. SLUB however only allocates
kmem_cache_node on online N_NORMAL_MEMORY nodes, and relies on
node_to_mem_node to return such valid node for other nodes since commit
a561ce00b09e ("slub: fall back to node_to_mem_node() node if allocating
on memoryless node"). This is however not true in this configuration
where the _node_numa_mem_ array is not initialized for nodes 0 and 2-31,
thus it contains zeroes and get_partial() ends up accessing
non-allocated kmem_cache_node.
A related issue was reported by Bharata (originally by Ramachandran) [3]
where a similar PowerPC configuration, but with mainline kernel without
patch [2] ends up allocating large amounts of pages by kmalloc-1k
kmalloc-512. This seems to have the same underlying issue with
node_to_mem_node() not behaving as expected, and might probably also
lead to an infinite loop with CONFIG_SLUB_CPU_PARTIAL [4].
This patch should fix both issues by not relying on node_to_mem_node()
anymore and instead simply falling back to NUMA_NO_NODE, when
kmalloc_node(node) is attempted for a node that's not online, or has no
usable memory. The "usable memory" condition is also changed from
node_present_pages() to N_NORMAL_MEMORY node state, as that is exactly
the condition that SLUB uses to allocate kmem_cache_node structures.
The check in get_partial() is removed completely, as the checks in
___slab_alloc() are now sufficient to prevent get_partial() being
reached with an invalid node.
[1] https://lore.kernel.org/linux-next/3381CD91-AB3D-4773-BA04-E7A072A63968@linux.vnet.ibm.com/
[2] https://lore.kernel.org/linux-mm/fff0e636-4c36-ed10-281c-8cdb0687c839@virtuozzo.com/
[3] https://lore.kernel.org/linux-mm/20200317092624.GB22538@in.ibm.com/
[4] https://lore.kernel.org/linux-mm/088b5996-faae-8a56-ef9c-5b567125ae54@suse.cz/
Fixes: a561ce00b09e ("slub: fall back to node_to_mem_node() node if allocating on memoryless node")
Reported-by: Sachin Sant <sachinp@linux.vnet.ibm.com>
Reported-by: PUVICHAKRAVARTHY RAMACHANDRAN <puvichakravarthy@in.ibm.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Tested-by: Sachin Sant <sachinp@linux.vnet.ibm.com>
Tested-by: Bharata B Rao <bharata@linux.ibm.com>
Reviewed-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Christopher Lameter <cl@linux.com>
Cc: linuxppc-dev@lists.ozlabs.org
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Kirill Tkhai <ktkhai@virtuozzo.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Nathan Lynch <nathanl@linux.ibm.com>
Cc: <stable@vger.kernel.org>
Link: http://lkml.kernel.org/r/20200320115533.9604-1-vbabka@suse.cz
Debugged-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-03-21 18:22:37 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
mm, slub: prevent kmalloc_node crashes and memory leaks
Sachin reports [1] a crash in SLUB __slab_alloc():
BUG: Kernel NULL pointer dereference on read at 0x000073b0
Faulting instruction address: 0xc0000000003d55f4
Oops: Kernel access of bad area, sig: 11 [#1]
LE PAGE_SIZE=64K MMU=Hash SMP NR_CPUS=2048 NUMA pSeries
Modules linked in:
CPU: 19 PID: 1 Comm: systemd Not tainted 5.6.0-rc2-next-20200218-autotest #1
NIP: c0000000003d55f4 LR: c0000000003d5b94 CTR: 0000000000000000
REGS: c0000008b37836d0 TRAP: 0300 Not tainted (5.6.0-rc2-next-20200218-autotest)
MSR: 8000000000009033 <SF,EE,ME,IR,DR,RI,LE> CR: 24004844 XER: 00000000
CFAR: c00000000000dec4 DAR: 00000000000073b0 DSISR: 40000000 IRQMASK: 1
GPR00: c0000000003d5b94 c0000008b3783960 c00000000155d400 c0000008b301f500
GPR04: 0000000000000dc0 0000000000000002 c0000000003443d8 c0000008bb398620
GPR08: 00000008ba2f0000 0000000000000001 0000000000000000 0000000000000000
GPR12: 0000000024004844 c00000001ec52a00 0000000000000000 0000000000000000
GPR16: c0000008a1b20048 c000000001595898 c000000001750c18 0000000000000002
GPR20: c000000001750c28 c000000001624470 0000000fffffffe0 5deadbeef0000122
GPR24: 0000000000000001 0000000000000dc0 0000000000000002 c0000000003443d8
GPR28: c0000008b301f500 c0000008bb398620 0000000000000000 c00c000002287180
NIP ___slab_alloc+0x1f4/0x760
LR __slab_alloc+0x34/0x60
Call Trace:
___slab_alloc+0x334/0x760 (unreliable)
__slab_alloc+0x34/0x60
__kmalloc_node+0x110/0x490
kvmalloc_node+0x58/0x110
mem_cgroup_css_online+0x108/0x270
online_css+0x48/0xd0
cgroup_apply_control_enable+0x2ec/0x4d0
cgroup_mkdir+0x228/0x5f0
kernfs_iop_mkdir+0x90/0xf0
vfs_mkdir+0x110/0x230
do_mkdirat+0xb0/0x1a0
system_call+0x5c/0x68
This is a PowerPC platform with following NUMA topology:
available: 2 nodes (0-1)
node 0 cpus:
node 0 size: 0 MB
node 0 free: 0 MB
node 1 cpus: 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31
node 1 size: 35247 MB
node 1 free: 30907 MB
node distances:
node 0 1
0: 10 40
1: 40 10
possible numa nodes: 0-31
This only happens with a mmotm patch "mm/memcontrol.c: allocate
shrinker_map on appropriate NUMA node" [2] which effectively calls
kmalloc_node for each possible node. SLUB however only allocates
kmem_cache_node on online N_NORMAL_MEMORY nodes, and relies on
node_to_mem_node to return such valid node for other nodes since commit
a561ce00b09e ("slub: fall back to node_to_mem_node() node if allocating
on memoryless node"). This is however not true in this configuration
where the _node_numa_mem_ array is not initialized for nodes 0 and 2-31,
thus it contains zeroes and get_partial() ends up accessing
non-allocated kmem_cache_node.
A related issue was reported by Bharata (originally by Ramachandran) [3]
where a similar PowerPC configuration, but with mainline kernel without
patch [2] ends up allocating large amounts of pages by kmalloc-1k
kmalloc-512. This seems to have the same underlying issue with
node_to_mem_node() not behaving as expected, and might probably also
lead to an infinite loop with CONFIG_SLUB_CPU_PARTIAL [4].
This patch should fix both issues by not relying on node_to_mem_node()
anymore and instead simply falling back to NUMA_NO_NODE, when
kmalloc_node(node) is attempted for a node that's not online, or has no
usable memory. The "usable memory" condition is also changed from
node_present_pages() to N_NORMAL_MEMORY node state, as that is exactly
the condition that SLUB uses to allocate kmem_cache_node structures.
The check in get_partial() is removed completely, as the checks in
___slab_alloc() are now sufficient to prevent get_partial() being
reached with an invalid node.
[1] https://lore.kernel.org/linux-next/3381CD91-AB3D-4773-BA04-E7A072A63968@linux.vnet.ibm.com/
[2] https://lore.kernel.org/linux-mm/fff0e636-4c36-ed10-281c-8cdb0687c839@virtuozzo.com/
[3] https://lore.kernel.org/linux-mm/20200317092624.GB22538@in.ibm.com/
[4] https://lore.kernel.org/linux-mm/088b5996-faae-8a56-ef9c-5b567125ae54@suse.cz/
Fixes: a561ce00b09e ("slub: fall back to node_to_mem_node() node if allocating on memoryless node")
Reported-by: Sachin Sant <sachinp@linux.vnet.ibm.com>
Reported-by: PUVICHAKRAVARTHY RAMACHANDRAN <puvichakravarthy@in.ibm.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Tested-by: Sachin Sant <sachinp@linux.vnet.ibm.com>
Tested-by: Bharata B Rao <bharata@linux.ibm.com>
Reviewed-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Christopher Lameter <cl@linux.com>
Cc: linuxppc-dev@lists.ozlabs.org
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Kirill Tkhai <ktkhai@virtuozzo.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Nathan Lynch <nathanl@linux.ibm.com>
Cc: <stable@vger.kernel.org>
Link: http://lkml.kernel.org/r/20200320115533.9604-1-vbabka@suse.cz
Debugged-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-03-21 18:22:37 -07:00
|
|
|
|
2012-05-09 10:09:51 -05:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
mm, slub: prevent kmalloc_node crashes and memory leaks
Sachin reports [1] a crash in SLUB __slab_alloc():
BUG: Kernel NULL pointer dereference on read at 0x000073b0
Faulting instruction address: 0xc0000000003d55f4
Oops: Kernel access of bad area, sig: 11 [#1]
LE PAGE_SIZE=64K MMU=Hash SMP NR_CPUS=2048 NUMA pSeries
Modules linked in:
CPU: 19 PID: 1 Comm: systemd Not tainted 5.6.0-rc2-next-20200218-autotest #1
NIP: c0000000003d55f4 LR: c0000000003d5b94 CTR: 0000000000000000
REGS: c0000008b37836d0 TRAP: 0300 Not tainted (5.6.0-rc2-next-20200218-autotest)
MSR: 8000000000009033 <SF,EE,ME,IR,DR,RI,LE> CR: 24004844 XER: 00000000
CFAR: c00000000000dec4 DAR: 00000000000073b0 DSISR: 40000000 IRQMASK: 1
GPR00: c0000000003d5b94 c0000008b3783960 c00000000155d400 c0000008b301f500
GPR04: 0000000000000dc0 0000000000000002 c0000000003443d8 c0000008bb398620
GPR08: 00000008ba2f0000 0000000000000001 0000000000000000 0000000000000000
GPR12: 0000000024004844 c00000001ec52a00 0000000000000000 0000000000000000
GPR16: c0000008a1b20048 c000000001595898 c000000001750c18 0000000000000002
GPR20: c000000001750c28 c000000001624470 0000000fffffffe0 5deadbeef0000122
GPR24: 0000000000000001 0000000000000dc0 0000000000000002 c0000000003443d8
GPR28: c0000008b301f500 c0000008bb398620 0000000000000000 c00c000002287180
NIP ___slab_alloc+0x1f4/0x760
LR __slab_alloc+0x34/0x60
Call Trace:
___slab_alloc+0x334/0x760 (unreliable)
__slab_alloc+0x34/0x60
__kmalloc_node+0x110/0x490
kvmalloc_node+0x58/0x110
mem_cgroup_css_online+0x108/0x270
online_css+0x48/0xd0
cgroup_apply_control_enable+0x2ec/0x4d0
cgroup_mkdir+0x228/0x5f0
kernfs_iop_mkdir+0x90/0xf0
vfs_mkdir+0x110/0x230
do_mkdirat+0xb0/0x1a0
system_call+0x5c/0x68
This is a PowerPC platform with following NUMA topology:
available: 2 nodes (0-1)
node 0 cpus:
node 0 size: 0 MB
node 0 free: 0 MB
node 1 cpus: 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31
node 1 size: 35247 MB
node 1 free: 30907 MB
node distances:
node 0 1
0: 10 40
1: 40 10
possible numa nodes: 0-31
This only happens with a mmotm patch "mm/memcontrol.c: allocate
shrinker_map on appropriate NUMA node" [2] which effectively calls
kmalloc_node for each possible node. SLUB however only allocates
kmem_cache_node on online N_NORMAL_MEMORY nodes, and relies on
node_to_mem_node to return such valid node for other nodes since commit
a561ce00b09e ("slub: fall back to node_to_mem_node() node if allocating
on memoryless node"). This is however not true in this configuration
where the _node_numa_mem_ array is not initialized for nodes 0 and 2-31,
thus it contains zeroes and get_partial() ends up accessing
non-allocated kmem_cache_node.
A related issue was reported by Bharata (originally by Ramachandran) [3]
where a similar PowerPC configuration, but with mainline kernel without
patch [2] ends up allocating large amounts of pages by kmalloc-1k
kmalloc-512. This seems to have the same underlying issue with
node_to_mem_node() not behaving as expected, and might probably also
lead to an infinite loop with CONFIG_SLUB_CPU_PARTIAL [4].
This patch should fix both issues by not relying on node_to_mem_node()
anymore and instead simply falling back to NUMA_NO_NODE, when
kmalloc_node(node) is attempted for a node that's not online, or has no
usable memory. The "usable memory" condition is also changed from
node_present_pages() to N_NORMAL_MEMORY node state, as that is exactly
the condition that SLUB uses to allocate kmem_cache_node structures.
The check in get_partial() is removed completely, as the checks in
___slab_alloc() are now sufficient to prevent get_partial() being
reached with an invalid node.
[1] https://lore.kernel.org/linux-next/3381CD91-AB3D-4773-BA04-E7A072A63968@linux.vnet.ibm.com/
[2] https://lore.kernel.org/linux-mm/fff0e636-4c36-ed10-281c-8cdb0687c839@virtuozzo.com/
[3] https://lore.kernel.org/linux-mm/20200317092624.GB22538@in.ibm.com/
[4] https://lore.kernel.org/linux-mm/088b5996-faae-8a56-ef9c-5b567125ae54@suse.cz/
Fixes: a561ce00b09e ("slub: fall back to node_to_mem_node() node if allocating on memoryless node")
Reported-by: Sachin Sant <sachinp@linux.vnet.ibm.com>
Reported-by: PUVICHAKRAVARTHY RAMACHANDRAN <puvichakravarthy@in.ibm.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Tested-by: Sachin Sant <sachinp@linux.vnet.ibm.com>
Tested-by: Bharata B Rao <bharata@linux.ibm.com>
Reviewed-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Christopher Lameter <cl@linux.com>
Cc: linuxppc-dev@lists.ozlabs.org
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Kirill Tkhai <ktkhai@virtuozzo.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Nathan Lynch <nathanl@linux.ibm.com>
Cc: <stable@vger.kernel.org>
Link: http://lkml.kernel.org/r/20200320115533.9604-1-vbabka@suse.cz
Debugged-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-03-21 18:22:37 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
mm, slab, slub: stop taking memory hotplug lock
Since commit 03afc0e25f7f ("slab: get_online_mems for
kmem_cache_{create,destroy,shrink}") we are taking memory hotplug lock for
SLAB and SLUB when creating, destroying or shrinking a cache. It is quite
a heavy lock and it's best to avoid it if possible, as we had several
issues with lockdep complaining about ordering in the past, see e.g.
e4f8e513c3d3 ("mm/slub: fix a deadlock in show_slab_objects()").
The problem scenario in 03afc0e25f7f (solved by the memory hotplug lock)
can be summarized as follows: while there's slab_mutex synchronizing new
kmem cache creation and SLUB's MEM_GOING_ONLINE callback
slab_mem_going_online_callback(), we may miss creation of kmem_cache_node
for the hotplugged node in the new kmem cache, because the hotplug
callback doesn't yet see the new cache, and cache creation in
init_kmem_cache_nodes() only inits kmem_cache_node for nodes in the
N_NORMAL_MEMORY nodemask, which however may not yet include the new node,
as that happens only later after the MEM_GOING_ONLINE callback.
Instead of using get/put_online_mems(), the problem can be solved by SLUB
maintaining its own nodemask of nodes for which it has allocated the
per-node kmem_cache_node structures. This nodemask would generally mirror
the N_NORMAL_MEMORY nodemask, but would be updated only in under SLUB's
control in its memory hotplug callbacks under the slab_mutex. This patch
adds such nodemask and its handling.
Commit 03afc0e25f7f mentiones "issues like [the one above]", but there
don't appear to be further issues. All the paths (shared for SLAB and
SLUB) taking the memory hotplug locks are also taking the slab_mutex,
except kmem_cache_shrink() where 03afc0e25f7f replaced slab_mutex with
get/put_online_mems().
We however cannot simply restore slab_mutex in kmem_cache_shrink(), as
SLUB can enters the function from a write to sysfs 'shrink' file, thus
holding kernfs lock, and in kmem_cache_create() the kernfs lock is nested
within slab_mutex. But on closer inspection we don't actually need to
protect kmem_cache_shrink() from hotplug callbacks: While SLUB's
__kmem_cache_shrink() does for_each_kmem_cache_node(), missing a new node
added in parallel hotplug is not fatal, and parallel hotremove does not
free kmem_cache_node's anymore after the previous patch, so use-after free
cannot happen. The per-node shrinking itself is protected by
n->list_lock. Same is true for SLAB, and SLOB is no-op.
SLAB also doesn't need the memory hotplug locking, which it only gained by
03afc0e25f7f through the shared paths in slab_common.c. Its memory
hotplug callbacks are also protected by slab_mutex against races with
these paths. The problem of SLUB relying on N_NORMAL_MEMORY doesn't apply
to SLAB, as its setup_kmem_cache_nodes relies on N_ONLINE, and the new
node is already set there during the MEM_GOING_ONLINE callback, so no
special care is needed for SLAB.
As such, this patch removes all get/put_online_mems() usage by the slab
subsystem.
Link: https://lkml.kernel.org/r/20210113131634.3671-3-vbabka@suse.cz
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Christoph Lameter <cl@linux.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Qian Cai <cai@redhat.com>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-02-24 12:01:12 -08:00
|
|
|
|
mm, slub: prevent kmalloc_node crashes and memory leaks
Sachin reports [1] a crash in SLUB __slab_alloc():
BUG: Kernel NULL pointer dereference on read at 0x000073b0
Faulting instruction address: 0xc0000000003d55f4
Oops: Kernel access of bad area, sig: 11 [#1]
LE PAGE_SIZE=64K MMU=Hash SMP NR_CPUS=2048 NUMA pSeries
Modules linked in:
CPU: 19 PID: 1 Comm: systemd Not tainted 5.6.0-rc2-next-20200218-autotest #1
NIP: c0000000003d55f4 LR: c0000000003d5b94 CTR: 0000000000000000
REGS: c0000008b37836d0 TRAP: 0300 Not tainted (5.6.0-rc2-next-20200218-autotest)
MSR: 8000000000009033 <SF,EE,ME,IR,DR,RI,LE> CR: 24004844 XER: 00000000
CFAR: c00000000000dec4 DAR: 00000000000073b0 DSISR: 40000000 IRQMASK: 1
GPR00: c0000000003d5b94 c0000008b3783960 c00000000155d400 c0000008b301f500
GPR04: 0000000000000dc0 0000000000000002 c0000000003443d8 c0000008bb398620
GPR08: 00000008ba2f0000 0000000000000001 0000000000000000 0000000000000000
GPR12: 0000000024004844 c00000001ec52a00 0000000000000000 0000000000000000
GPR16: c0000008a1b20048 c000000001595898 c000000001750c18 0000000000000002
GPR20: c000000001750c28 c000000001624470 0000000fffffffe0 5deadbeef0000122
GPR24: 0000000000000001 0000000000000dc0 0000000000000002 c0000000003443d8
GPR28: c0000008b301f500 c0000008bb398620 0000000000000000 c00c000002287180
NIP ___slab_alloc+0x1f4/0x760
LR __slab_alloc+0x34/0x60
Call Trace:
___slab_alloc+0x334/0x760 (unreliable)
__slab_alloc+0x34/0x60
__kmalloc_node+0x110/0x490
kvmalloc_node+0x58/0x110
mem_cgroup_css_online+0x108/0x270
online_css+0x48/0xd0
cgroup_apply_control_enable+0x2ec/0x4d0
cgroup_mkdir+0x228/0x5f0
kernfs_iop_mkdir+0x90/0xf0
vfs_mkdir+0x110/0x230
do_mkdirat+0xb0/0x1a0
system_call+0x5c/0x68
This is a PowerPC platform with following NUMA topology:
available: 2 nodes (0-1)
node 0 cpus:
node 0 size: 0 MB
node 0 free: 0 MB
node 1 cpus: 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31
node 1 size: 35247 MB
node 1 free: 30907 MB
node distances:
node 0 1
0: 10 40
1: 40 10
possible numa nodes: 0-31
This only happens with a mmotm patch "mm/memcontrol.c: allocate
shrinker_map on appropriate NUMA node" [2] which effectively calls
kmalloc_node for each possible node. SLUB however only allocates
kmem_cache_node on online N_NORMAL_MEMORY nodes, and relies on
node_to_mem_node to return such valid node for other nodes since commit
a561ce00b09e ("slub: fall back to node_to_mem_node() node if allocating
on memoryless node"). This is however not true in this configuration
where the _node_numa_mem_ array is not initialized for nodes 0 and 2-31,
thus it contains zeroes and get_partial() ends up accessing
non-allocated kmem_cache_node.
A related issue was reported by Bharata (originally by Ramachandran) [3]
where a similar PowerPC configuration, but with mainline kernel without
patch [2] ends up allocating large amounts of pages by kmalloc-1k
kmalloc-512. This seems to have the same underlying issue with
node_to_mem_node() not behaving as expected, and might probably also
lead to an infinite loop with CONFIG_SLUB_CPU_PARTIAL [4].
This patch should fix both issues by not relying on node_to_mem_node()
anymore and instead simply falling back to NUMA_NO_NODE, when
kmalloc_node(node) is attempted for a node that's not online, or has no
usable memory. The "usable memory" condition is also changed from
node_present_pages() to N_NORMAL_MEMORY node state, as that is exactly
the condition that SLUB uses to allocate kmem_cache_node structures.
The check in get_partial() is removed completely, as the checks in
___slab_alloc() are now sufficient to prevent get_partial() being
reached with an invalid node.
[1] https://lore.kernel.org/linux-next/3381CD91-AB3D-4773-BA04-E7A072A63968@linux.vnet.ibm.com/
[2] https://lore.kernel.org/linux-mm/fff0e636-4c36-ed10-281c-8cdb0687c839@virtuozzo.com/
[3] https://lore.kernel.org/linux-mm/20200317092624.GB22538@in.ibm.com/
[4] https://lore.kernel.org/linux-mm/088b5996-faae-8a56-ef9c-5b567125ae54@suse.cz/
Fixes: a561ce00b09e ("slub: fall back to node_to_mem_node() node if allocating on memoryless node")
Reported-by: Sachin Sant <sachinp@linux.vnet.ibm.com>
Reported-by: PUVICHAKRAVARTHY RAMACHANDRAN <puvichakravarthy@in.ibm.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Tested-by: Sachin Sant <sachinp@linux.vnet.ibm.com>
Tested-by: Bharata B Rao <bharata@linux.ibm.com>
Reviewed-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Christopher Lameter <cl@linux.com>
Cc: linuxppc-dev@lists.ozlabs.org
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Kirill Tkhai <ktkhai@virtuozzo.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Nathan Lynch <nathanl@linux.ibm.com>
Cc: <stable@vger.kernel.org>
Link: http://lkml.kernel.org/r/20200320115533.9604-1-vbabka@suse.cz
Debugged-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-03-21 18:22:37 -07:00
|
|
|
|
|
|
|
|
|
2014-10-09 15:26:15 -07:00
|
|
|
|
2021-05-08 02:28:02 +02:00
|
|
|
|
2014-10-09 15:26:15 -07:00
|
|
|
|
2011-06-01 12:25:56 -05:00
|
|
|
|
2008-02-15 23:45:26 -08:00
|
|
|
|
mm: sl[au]b: add knowledge of PFMEMALLOC reserve pages
When a user or administrator requires swap for their application, they
create a swap partition and file, format it with mkswap and activate it
with swapon. Swap over the network is considered as an option in diskless
systems. The two likely scenarios are when blade servers are used as part
of a cluster where the form factor or maintenance costs do not allow the
use of disks and thin clients.
The Linux Terminal Server Project recommends the use of the Network Block
Device (NBD) for swap according to the manual at
https://sourceforge.net/projects/ltsp/files/Docs-Admin-Guide/LTSPManual.pdf/download
There is also documentation and tutorials on how to setup swap over NBD at
places like https://help.ubuntu.com/community/UbuntuLTSP/EnableNBDSWAP The
nbd-client also documents the use of NBD as swap. Despite this, the fact
is that a machine using NBD for swap can deadlock within minutes if swap
is used intensively. This patch series addresses the problem.
The core issue is that network block devices do not use mempools like
normal block devices do. As the host cannot control where they receive
packets from, they cannot reliably work out in advance how much memory
they might need. Some years ago, Peter Zijlstra developed a series of
patches that supported swap over an NFS that at least one distribution is
carrying within their kernels. This patch series borrows very heavily
from Peter's work to support swapping over NBD as a pre-requisite to
supporting swap-over-NFS. The bulk of the complexity is concerned with
preserving memory that is allocated from the PFMEMALLOC reserves for use
by the network layer which is needed for both NBD and NFS.
Patch 1 adds knowledge of the PFMEMALLOC reserves to SLAB and SLUB to
preserve access to pages allocated under low memory situations
to callers that are freeing memory.
Patch 2 optimises the SLUB fast path to avoid pfmemalloc checks
Patch 3 introduces __GFP_MEMALLOC to allow access to the PFMEMALLOC
reserves without setting PFMEMALLOC.
Patch 4 opens the possibility for softirqs to use PFMEMALLOC reserves
for later use by network packet processing.
Patch 5 only sets page->pfmemalloc when ALLOC_NO_WATERMARKS was required
Patch 6 ignores memory policies when ALLOC_NO_WATERMARKS is set.
Patches 7-12 allows network processing to use PFMEMALLOC reserves when
the socket has been marked as being used by the VM to clean pages. If
packets are received and stored in pages that were allocated under
low-memory situations and are unrelated to the VM, the packets
are dropped.
Patch 11 reintroduces __skb_alloc_page which the networking
folk may object to but is needed in some cases to propogate
pfmemalloc from a newly allocated page to an skb. If there is a
strong objection, this patch can be dropped with the impact being
that swap-over-network will be slower in some cases but it should
not fail.
Patch 13 is a micro-optimisation to avoid a function call in the
common case.
Patch 14 tags NBD sockets as being SOCK_MEMALLOC so they can use
PFMEMALLOC if necessary.
Patch 15 notes that it is still possible for the PFMEMALLOC reserve
to be depleted. To prevent this, direct reclaimers get throttled on
a waitqueue if 50% of the PFMEMALLOC reserves are depleted. It is
expected that kswapd and the direct reclaimers already running
will clean enough pages for the low watermark to be reached and
the throttled processes are woken up.
Patch 16 adds a statistic to track how often processes get throttled
Some basic performance testing was run using kernel builds, netperf on
loopback for UDP and TCP, hackbench (pipes and sockets), iozone and
sysbench. Each of them were expected to use the sl*b allocators
reasonably heavily but there did not appear to be significant performance
variances.
For testing swap-over-NBD, a machine was booted with 2G of RAM with a
swapfile backed by NBD. 8*NUM_CPU processes were started that create
anonymous memory mappings and read them linearly in a loop. The total
size of the mappings were 4*PHYSICAL_MEMORY to use swap heavily under
memory pressure.
Without the patches and using SLUB, the machine locks up within minutes
and runs to completion with them applied. With SLAB, the story is
different as an unpatched kernel run to completion. However, the patched
kernel completed the test 45% faster.
MICRO
3.5.0-rc2 3.5.0-rc2
vanilla swapnbd
Unrecognised test vmscan-anon-mmap-write
MMTests Statistics: duration
Sys Time Running Test (seconds) 197.80 173.07
User+Sys Time Running Test (seconds) 206.96 182.03
Total Elapsed Time (seconds) 3240.70 1762.09
This patch: mm: sl[au]b: add knowledge of PFMEMALLOC reserve pages
Allocations of pages below the min watermark run a risk of the machine
hanging due to a lack of memory. To prevent this, only callers who have
PF_MEMALLOC or TIF_MEMDIE set and are not processing an interrupt are
allowed to allocate with ALLOC_NO_WATERMARKS. Once they are allocated to
a slab though, nothing prevents other callers consuming free objects
within those slabs. This patch limits access to slab pages that were
alloced from the PFMEMALLOC reserves.
When this patch is applied, pages allocated from below the low watermark
are returned with page->pfmemalloc set and it is up to the caller to
determine how the page should be protected. SLAB restricts access to any
page with page->pfmemalloc set to callers which are known to able to
access the PFMEMALLOC reserve. If one is not available, an attempt is
made to allocate a new page rather than use a reserve. SLUB is a bit more
relaxed in that it only records if the current per-CPU page was allocated
from PFMEMALLOC reserve and uses another partial slab if the caller does
not have the necessary GFP or process flags. This was found to be
sufficient in tests to avoid hangs due to SLUB generally maintaining
smaller lists than SLAB.
In low-memory conditions it does mean that !PFMEMALLOC allocators can fail
a slab allocation even though free objects are available because they are
being preserved for callers that are freeing pages.
[a.p.zijlstra@chello.nl: Original implementation]
[sebastian@breakpoint.cc: Correct order of page flag clearing]
Signed-off-by: Mel Gorman <mgorman@suse.de>
Cc: David Miller <davem@davemloft.net>
Cc: Neil Brown <neilb@suse.de>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Mike Christie <michaelc@cs.wisc.edu>
Cc: Eric B Munson <emunson@mgebm.net>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Sebastian Andrzej Siewior <sebastian@breakpoint.cc>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Christoph Lameter <cl@linux.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-07-31 16:43:58 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2021-05-08 02:28:02 +02:00
|
|
|
|
mm: sl[au]b: add knowledge of PFMEMALLOC reserve pages
When a user or administrator requires swap for their application, they
create a swap partition and file, format it with mkswap and activate it
with swapon. Swap over the network is considered as an option in diskless
systems. The two likely scenarios are when blade servers are used as part
of a cluster where the form factor or maintenance costs do not allow the
use of disks and thin clients.
The Linux Terminal Server Project recommends the use of the Network Block
Device (NBD) for swap according to the manual at
https://sourceforge.net/projects/ltsp/files/Docs-Admin-Guide/LTSPManual.pdf/download
There is also documentation and tutorials on how to setup swap over NBD at
places like https://help.ubuntu.com/community/UbuntuLTSP/EnableNBDSWAP The
nbd-client also documents the use of NBD as swap. Despite this, the fact
is that a machine using NBD for swap can deadlock within minutes if swap
is used intensively. This patch series addresses the problem.
The core issue is that network block devices do not use mempools like
normal block devices do. As the host cannot control where they receive
packets from, they cannot reliably work out in advance how much memory
they might need. Some years ago, Peter Zijlstra developed a series of
patches that supported swap over an NFS that at least one distribution is
carrying within their kernels. This patch series borrows very heavily
from Peter's work to support swapping over NBD as a pre-requisite to
supporting swap-over-NFS. The bulk of the complexity is concerned with
preserving memory that is allocated from the PFMEMALLOC reserves for use
by the network layer which is needed for both NBD and NFS.
Patch 1 adds knowledge of the PFMEMALLOC reserves to SLAB and SLUB to
preserve access to pages allocated under low memory situations
to callers that are freeing memory.
Patch 2 optimises the SLUB fast path to avoid pfmemalloc checks
Patch 3 introduces __GFP_MEMALLOC to allow access to the PFMEMALLOC
reserves without setting PFMEMALLOC.
Patch 4 opens the possibility for softirqs to use PFMEMALLOC reserves
for later use by network packet processing.
Patch 5 only sets page->pfmemalloc when ALLOC_NO_WATERMARKS was required
Patch 6 ignores memory policies when ALLOC_NO_WATERMARKS is set.
Patches 7-12 allows network processing to use PFMEMALLOC reserves when
the socket has been marked as being used by the VM to clean pages. If
packets are received and stored in pages that were allocated under
low-memory situations and are unrelated to the VM, the packets
are dropped.
Patch 11 reintroduces __skb_alloc_page which the networking
folk may object to but is needed in some cases to propogate
pfmemalloc from a newly allocated page to an skb. If there is a
strong objection, this patch can be dropped with the impact being
that swap-over-network will be slower in some cases but it should
not fail.
Patch 13 is a micro-optimisation to avoid a function call in the
common case.
Patch 14 tags NBD sockets as being SOCK_MEMALLOC so they can use
PFMEMALLOC if necessary.
Patch 15 notes that it is still possible for the PFMEMALLOC reserve
to be depleted. To prevent this, direct reclaimers get throttled on
a waitqueue if 50% of the PFMEMALLOC reserves are depleted. It is
expected that kswapd and the direct reclaimers already running
will clean enough pages for the low watermark to be reached and
the throttled processes are woken up.
Patch 16 adds a statistic to track how often processes get throttled
Some basic performance testing was run using kernel builds, netperf on
loopback for UDP and TCP, hackbench (pipes and sockets), iozone and
sysbench. Each of them were expected to use the sl*b allocators
reasonably heavily but there did not appear to be significant performance
variances.
For testing swap-over-NBD, a machine was booted with 2G of RAM with a
swapfile backed by NBD. 8*NUM_CPU processes were started that create
anonymous memory mappings and read them linearly in a loop. The total
size of the mappings were 4*PHYSICAL_MEMORY to use swap heavily under
memory pressure.
Without the patches and using SLUB, the machine locks up within minutes
and runs to completion with them applied. With SLAB, the story is
different as an unpatched kernel run to completion. However, the patched
kernel completed the test 45% faster.
MICRO
3.5.0-rc2 3.5.0-rc2
vanilla swapnbd
Unrecognised test vmscan-anon-mmap-write
MMTests Statistics: duration
Sys Time Running Test (seconds) 197.80 173.07
User+Sys Time Running Test (seconds) 206.96 182.03
Total Elapsed Time (seconds) 3240.70 1762.09
This patch: mm: sl[au]b: add knowledge of PFMEMALLOC reserve pages
Allocations of pages below the min watermark run a risk of the machine
hanging due to a lack of memory. To prevent this, only callers who have
PF_MEMALLOC or TIF_MEMDIE set and are not processing an interrupt are
allowed to allocate with ALLOC_NO_WATERMARKS. Once they are allocated to
a slab though, nothing prevents other callers consuming free objects
within those slabs. This patch limits access to slab pages that were
alloced from the PFMEMALLOC reserves.
When this patch is applied, pages allocated from below the low watermark
are returned with page->pfmemalloc set and it is up to the caller to
determine how the page should be protected. SLAB restricts access to any
page with page->pfmemalloc set to callers which are known to able to
access the PFMEMALLOC reserve. If one is not available, an attempt is
made to allocate a new page rather than use a reserve. SLUB is a bit more
relaxed in that it only records if the current per-CPU page was allocated
from PFMEMALLOC reserve and uses another partial slab if the caller does
not have the necessary GFP or process flags. This was found to be
sufficient in tests to avoid hangs due to SLUB generally maintaining
smaller lists than SLAB.
In low-memory conditions it does mean that !PFMEMALLOC allocators can fail
a slab allocation even though free objects are available because they are
being preserved for callers that are freeing pages.
[a.p.zijlstra@chello.nl: Original implementation]
[sebastian@breakpoint.cc: Correct order of page flag clearing]
Signed-off-by: Mel Gorman <mgorman@suse.de>
Cc: David Miller <davem@davemloft.net>
Cc: Neil Brown <neilb@suse.de>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Mike Christie <michaelc@cs.wisc.edu>
Cc: Eric B Munson <emunson@mgebm.net>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Sebastian Andrzej Siewior <sebastian@breakpoint.cc>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Christoph Lameter <cl@linux.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-07-31 16:43:58 -07:00
|
|
|
|
2021-11-15 16:55:15 +01:00
|
|
|
|
2021-05-22 01:59:38 +02:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2021-05-22 01:59:38 +02:00
|
|
|
|
2021-11-15 16:55:15 +01:00
|
|
|
|
2021-05-08 02:28:02 +02:00
|
|
|
|
2012-05-09 10:09:51 -05:00
|
|
|
|
|
|
|
|
|
2011-12-13 04:57:06 +01:00
|
|
|
|
|
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2008-02-15 23:45:26 -08:00
|
|
|
|
2012-05-09 10:09:51 -05:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
mm/slub: add missing TID updates on slab deactivation
The fastpath in slab_alloc_node() assumes that c->slab is stable as long as
the TID stays the same. However, two places in __slab_alloc() currently
don't update the TID when deactivating the CPU slab.
If multiple operations race the right way, this could lead to an object
getting lost; or, in an even more unlikely situation, it could even lead to
an object being freed onto the wrong slab's freelist, messing up the
`inuse` counter and eventually causing a page to be freed to the page
allocator while it still contains slab objects.
(I haven't actually tested these cases though, this is just based on
looking at the code. Writing testcases for this stuff seems like it'd be
a pain...)
The race leading to state inconsistency is (all operations on the same CPU
and kmem_cache):
- task A: begin do_slab_free():
- read TID
- read pcpu freelist (==NULL)
- check `slab == c->slab` (true)
- [PREEMPT A->B]
- task B: begin slab_alloc_node():
- fastpath fails (`c->freelist` is NULL)
- enter __slab_alloc()
- slub_get_cpu_ptr() (disables preemption)
- enter ___slab_alloc()
- take local_lock_irqsave()
- read c->freelist as NULL
- get_freelist() returns NULL
- write `c->slab = NULL`
- drop local_unlock_irqrestore()
- goto new_slab
- slub_percpu_partial() is NULL
- get_partial() returns NULL
- slub_put_cpu_ptr() (enables preemption)
- [PREEMPT B->A]
- task A: finish do_slab_free():
- this_cpu_cmpxchg_double() succeeds()
- [CORRUPT STATE: c->slab==NULL, c->freelist!=NULL]
From there, the object on c->freelist will get lost if task B is allowed to
continue from here: It will proceed to the retry_load_slab label,
set c->slab, then jump to load_freelist, which clobbers c->freelist.
But if we instead continue as follows, we get worse corruption:
- task A: run __slab_free() on object from other struct slab:
- CPU_PARTIAL_FREE case (slab was on no list, is now on pcpu partial)
- task A: run slab_alloc_node() with NUMA node constraint:
- fastpath fails (c->slab is NULL)
- call __slab_alloc()
- slub_get_cpu_ptr() (disables preemption)
- enter ___slab_alloc()
- c->slab is NULL: goto new_slab
- slub_percpu_partial() is non-NULL
- set c->slab to slub_percpu_partial(c)
- [CORRUPT STATE: c->slab points to slab-1, c->freelist has objects
from slab-2]
- goto redo
- node_match() fails
- goto deactivate_slab
- existing c->freelist is passed into deactivate_slab()
- inuse count of slab-1 is decremented to account for object from
slab-2
At this point, the inuse count of slab-1 is 1 lower than it should be.
This means that if we free all allocated objects in slab-1 except for one,
SLUB will think that slab-1 is completely unused, and may free its page,
leading to use-after-free.
Fixes: c17dda40a6a4e ("slub: Separate out kmem_cache_cpu processing from deactivate_slab")
Fixes: 03e404af26dc2 ("slub: fast release on full slab")
Cc: stable@vger.kernel.org
Signed-off-by: Jann Horn <jannh@google.com>
Acked-by: Christoph Lameter <cl@linux.com>
Acked-by: David Rientjes <rientjes@google.com>
Reviewed-by: Muchun Song <songmuchun@bytedance.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Link: https://lore.kernel.org/r/20220608182205.2945720-1-jannh@google.com
2022-06-08 20:22:05 +02:00
|
|
|
|
2021-05-22 01:59:38 +02:00
|
|
|
|
2011-06-01 12:25:58 -05:00
|
|
|
|
2011-06-01 12:25:56 -05:00
|
|
|
|
2011-06-01 12:25:58 -05:00
|
|
|
|
2008-02-15 23:45:26 -08:00
|
|
|
|
2009-12-18 16:26:23 -06:00
|
|
|
|
2008-02-15 23:45:26 -08:00
|
|
|
|
2007-05-10 03:15:16 -07:00
|
|
|
|
2021-05-08 02:28:02 +02:00
|
|
|
|
2021-05-22 01:59:38 +02:00
|
|
|
|
2021-05-08 02:28:02 +02:00
|
|
|
|
2012-05-09 10:09:52 -05:00
|
|
|
|
|
|
|
|
|
2021-11-15 16:55:15 +01:00
|
|
|
|
|
|
|
|
|
2012-05-09 10:09:52 -05:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2012-05-09 10:09:51 -05:00
|
|
|
|
2011-02-25 11:38:54 -06:00
|
|
|
|
2021-05-22 01:59:38 +02:00
|
|
|
|
2012-05-09 10:09:51 -05:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2021-05-08 02:28:02 +02:00
|
|
|
|
|
|
|
|
|
2021-05-22 01:59:38 +02:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2021-05-22 01:59:38 +02:00
|
|
|
|
2021-11-15 16:55:15 +01:00
|
|
|
|
2021-05-08 02:28:02 +02:00
|
|
|
|
2021-05-12 13:53:34 +02:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2021-05-12 13:53:34 +02:00
|
|
|
|
mm/slub: add missing TID updates on slab deactivation
The fastpath in slab_alloc_node() assumes that c->slab is stable as long as
the TID stays the same. However, two places in __slab_alloc() currently
don't update the TID when deactivating the CPU slab.
If multiple operations race the right way, this could lead to an object
getting lost; or, in an even more unlikely situation, it could even lead to
an object being freed onto the wrong slab's freelist, messing up the
`inuse` counter and eventually causing a page to be freed to the page
allocator while it still contains slab objects.
(I haven't actually tested these cases though, this is just based on
looking at the code. Writing testcases for this stuff seems like it'd be
a pain...)
The race leading to state inconsistency is (all operations on the same CPU
and kmem_cache):
- task A: begin do_slab_free():
- read TID
- read pcpu freelist (==NULL)
- check `slab == c->slab` (true)
- [PREEMPT A->B]
- task B: begin slab_alloc_node():
- fastpath fails (`c->freelist` is NULL)
- enter __slab_alloc()
- slub_get_cpu_ptr() (disables preemption)
- enter ___slab_alloc()
- take local_lock_irqsave()
- read c->freelist as NULL
- get_freelist() returns NULL
- write `c->slab = NULL`
- drop local_unlock_irqrestore()
- goto new_slab
- slub_percpu_partial() is NULL
- get_partial() returns NULL
- slub_put_cpu_ptr() (enables preemption)
- [PREEMPT B->A]
- task A: finish do_slab_free():
- this_cpu_cmpxchg_double() succeeds()
- [CORRUPT STATE: c->slab==NULL, c->freelist!=NULL]
From there, the object on c->freelist will get lost if task B is allowed to
continue from here: It will proceed to the retry_load_slab label,
set c->slab, then jump to load_freelist, which clobbers c->freelist.
But if we instead continue as follows, we get worse corruption:
- task A: run __slab_free() on object from other struct slab:
- CPU_PARTIAL_FREE case (slab was on no list, is now on pcpu partial)
- task A: run slab_alloc_node() with NUMA node constraint:
- fastpath fails (c->slab is NULL)
- call __slab_alloc()
- slub_get_cpu_ptr() (disables preemption)
- enter ___slab_alloc()
- c->slab is NULL: goto new_slab
- slub_percpu_partial() is non-NULL
- set c->slab to slub_percpu_partial(c)
- [CORRUPT STATE: c->slab points to slab-1, c->freelist has objects
from slab-2]
- goto redo
- node_match() fails
- goto deactivate_slab
- existing c->freelist is passed into deactivate_slab()
- inuse count of slab-1 is decremented to account for object from
slab-2
At this point, the inuse count of slab-1 is 1 lower than it should be.
This means that if we free all allocated objects in slab-1 except for one,
SLUB will think that slab-1 is completely unused, and may free its page,
leading to use-after-free.
Fixes: c17dda40a6a4e ("slub: Separate out kmem_cache_cpu processing from deactivate_slab")
Fixes: 03e404af26dc2 ("slub: fast release on full slab")
Cc: stable@vger.kernel.org
Signed-off-by: Jann Horn <jannh@google.com>
Acked-by: Christoph Lameter <cl@linux.com>
Acked-by: David Rientjes <rientjes@google.com>
Reviewed-by: Muchun Song <songmuchun@bytedance.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Link: https://lore.kernel.org/r/20220608182205.2945720-1-jannh@google.com
2022-06-08 20:22:05 +02:00
|
|
|
|
2021-05-22 01:59:38 +02:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2021-05-08 02:28:02 +02:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2011-06-01 12:25:52 -05:00
|
|
|
|
2023-11-02 03:23:27 +00:00
|
|
|
|
|
|
|
|
|
2021-05-22 01:59:38 +02:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2021-05-22 01:59:38 +02:00
|
|
|
|
2021-11-15 16:55:15 +01:00
|
|
|
|
2021-05-10 13:56:17 +02:00
|
|
|
|
2021-05-11 17:45:26 +02:00
|
|
|
|
2021-05-22 01:59:38 +02:00
|
|
|
|
2021-05-21 14:03:23 +02:00
|
|
|
|
|
|
|
|
|
2021-05-11 17:45:26 +02:00
|
|
|
|
2021-05-10 13:56:17 +02:00
|
|
|
|
2023-11-02 03:23:27 +00:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2023-11-02 03:23:27 +00:00
|
|
|
|
2024-01-23 09:33:29 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-11-02 03:23:27 +00:00
|
|
|
|
|
|
|
|
|
2024-01-23 09:33:29 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2023-11-02 03:23:27 +00:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2021-05-10 13:56:17 +02:00
|
|
|
|
|
|
|
|
|
mm/slub: enable debugging memory wasting of kmalloc
kmalloc's API family is critical for mm, with one nature that it will
round up the request size to a fixed one (mostly power of 2). Say
when user requests memory for '2^n + 1' bytes, actually 2^(n+1) bytes
could be allocated, so in worst case, there is around 50% memory
space waste.
The wastage is not a big issue for requests that get allocated/freed
quickly, but may cause problems with objects that have longer life
time.
We've met a kernel boot OOM panic (v5.10), and from the dumped slab
info:
[ 26.062145] kmalloc-2k 814056KB 814056KB
From debug we found there are huge number of 'struct iova_magazine',
whose size is 1032 bytes (1024 + 8), so each allocation will waste
1016 bytes. Though the issue was solved by giving the right (bigger)
size of RAM, it is still nice to optimize the size (either use a
kmalloc friendly size or create a dedicated slab for it).
And from lkml archive, there was another crash kernel OOM case [1]
back in 2019, which seems to be related with the similar slab waste
situation, as the log is similar:
[ 4.332648] iommu: Adding device 0000:20:02.0 to group 16
[ 4.338946] swapper/0 invoked oom-killer: gfp_mask=0x6040c0(GFP_KERNEL|__GFP_COMP), nodemask=(null), order=0, oom_score_adj=0
...
[ 4.857565] kmalloc-2048 59164KB 59164KB
The crash kernel only has 256M memory, and 59M is pretty big here.
(Note: the related code has been changed and optimised in recent
kernel [2], these logs are just picked to demo the problem, also
a patch changing its size to 1024 bytes has been merged)
So add an way to track each kmalloc's memory waste info, and
leverage the existing SLUB debug framework (specifically
SLUB_STORE_USER) to show its call stack of original allocation,
so that user can evaluate the waste situation, identify some hot
spots and optimize accordingly, for a better utilization of memory.
The waste info is integrated into existing interface:
'/sys/kernel/debug/slab/kmalloc-xx/alloc_traces', one example of
'kmalloc-4k' after boot is:
126 ixgbe_alloc_q_vector+0xbe/0x830 [ixgbe] waste=233856/1856 age=280763/281414/282065 pid=1330 cpus=32 nodes=1
__kmem_cache_alloc_node+0x11f/0x4e0
__kmalloc_node+0x4e/0x140
ixgbe_alloc_q_vector+0xbe/0x830 [ixgbe]
ixgbe_init_interrupt_scheme+0x2ae/0xc90 [ixgbe]
ixgbe_probe+0x165f/0x1d20 [ixgbe]
local_pci_probe+0x78/0xc0
work_for_cpu_fn+0x26/0x40
...
which means in 'kmalloc-4k' slab, there are 126 requests of
2240 bytes which got a 4KB space (wasting 1856 bytes each
and 233856 bytes in total), from ixgbe_alloc_q_vector().
And when system starts some real workload like multiple docker
instances, there could are more severe waste.
[1]. https://lkml.org/lkml/2019/8/12/266
[2]. https://lore.kernel.org/lkml/2920df89-9975-5785-f79b-257d3052dfaf@huawei.com/
[Thanks Hyeonggon for pointing out several bugs about sorting/format]
[Thanks Vlastimil for suggesting way to reduce memory usage of
orig_size and keep it only for kmalloc objects]
Signed-off-by: Feng Tang <feng.tang@intel.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Robin Murphy <robin.murphy@arm.com>
Cc: John Garry <john.garry@huawei.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2022-09-13 14:54:20 +08:00
|
|
|
|
mm/slub: Reduce memory consumption in extreme scenarios
When kmalloc_node() is called without __GFP_THISNODE and the target node
lacks sufficient memory, SLUB allocates a folio from a different node
other than the requested node, instead of taking a partial slab from it.
However, since the allocated folio does not belong to the requested
node, on the following allocation it is deactivated and added to the
partial slab list of the node it belongs to.
This behavior can result in excessive memory usage when the requested
node has insufficient memory, as SLUB will repeatedly allocate folios
from other nodes without reusing the previously allocated ones.
To prevent memory wastage, when a preferred node is indicated (not
NUMA_NO_NODE) but without a prior __GFP_THISNODE constraint:
1) try to get a partial slab from target node only by having
__GFP_THISNODE in pc.flags for get_partial()
2) if 1) failed, try to allocate a new slab from target node with
GFP_NOWAIT | __GFP_THISNODE opportunistically.
3) if 2) failed, retry with original gfpflags which will allow
get_partial() try partial lists of other nodes before potentially
allocating new page from other nodes
Without a preferred node, or with __GFP_THISNODE constraint, the
behavior remains unchanged.
On qemu with 4 numa nodes and each numa has 1G memory. Write a test ko
to call kmalloc_node(196, GFP_KERNEL, 3) for (4 * 1024 + 4) * 1024 times.
cat /proc/slabinfo shows:
kmalloc-256 4200530 13519712 256 32 2 : tunables..
after this patch,
cat /proc/slabinfo shows:
kmalloc-256 4200558 4200768 256 32 2 : tunables..
Signed-off-by: Chen Jun <chenjun102@huawei.com>
Signed-off-by: Kefeng Wang <wangkefeng.wang@huawei.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2024-03-30 16:23:35 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
mm/slub: enable debugging memory wasting of kmalloc
kmalloc's API family is critical for mm, with one nature that it will
round up the request size to a fixed one (mostly power of 2). Say
when user requests memory for '2^n + 1' bytes, actually 2^(n+1) bytes
could be allocated, so in worst case, there is around 50% memory
space waste.
The wastage is not a big issue for requests that get allocated/freed
quickly, but may cause problems with objects that have longer life
time.
We've met a kernel boot OOM panic (v5.10), and from the dumped slab
info:
[ 26.062145] kmalloc-2k 814056KB 814056KB
From debug we found there are huge number of 'struct iova_magazine',
whose size is 1032 bytes (1024 + 8), so each allocation will waste
1016 bytes. Though the issue was solved by giving the right (bigger)
size of RAM, it is still nice to optimize the size (either use a
kmalloc friendly size or create a dedicated slab for it).
And from lkml archive, there was another crash kernel OOM case [1]
back in 2019, which seems to be related with the similar slab waste
situation, as the log is similar:
[ 4.332648] iommu: Adding device 0000:20:02.0 to group 16
[ 4.338946] swapper/0 invoked oom-killer: gfp_mask=0x6040c0(GFP_KERNEL|__GFP_COMP), nodemask=(null), order=0, oom_score_adj=0
...
[ 4.857565] kmalloc-2048 59164KB 59164KB
The crash kernel only has 256M memory, and 59M is pretty big here.
(Note: the related code has been changed and optimised in recent
kernel [2], these logs are just picked to demo the problem, also
a patch changing its size to 1024 bytes has been merged)
So add an way to track each kmalloc's memory waste info, and
leverage the existing SLUB debug framework (specifically
SLUB_STORE_USER) to show its call stack of original allocation,
so that user can evaluate the waste situation, identify some hot
spots and optimize accordingly, for a better utilization of memory.
The waste info is integrated into existing interface:
'/sys/kernel/debug/slab/kmalloc-xx/alloc_traces', one example of
'kmalloc-4k' after boot is:
126 ixgbe_alloc_q_vector+0xbe/0x830 [ixgbe] waste=233856/1856 age=280763/281414/282065 pid=1330 cpus=32 nodes=1
__kmem_cache_alloc_node+0x11f/0x4e0
__kmalloc_node+0x4e/0x140
ixgbe_alloc_q_vector+0xbe/0x830 [ixgbe]
ixgbe_init_interrupt_scheme+0x2ae/0xc90 [ixgbe]
ixgbe_probe+0x165f/0x1d20 [ixgbe]
local_pci_probe+0x78/0xc0
work_for_cpu_fn+0x26/0x40
...
which means in 'kmalloc-4k' slab, there are 126 requests of
2240 bytes which got a 4KB space (wasting 1856 bytes each
and 233856 bytes in total), from ixgbe_alloc_q_vector().
And when system starts some real workload like multiple docker
instances, there could are more severe waste.
[1]. https://lkml.org/lkml/2019/8/12/266
[2]. https://lore.kernel.org/lkml/2920df89-9975-5785-f79b-257d3052dfaf@huawei.com/
[Thanks Hyeonggon for pointing out several bugs about sorting/format]
[Thanks Vlastimil for suggesting way to reduce memory usage of
orig_size and keep it only for kmalloc objects]
Signed-off-by: Feng Tang <feng.tang@intel.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Robin Murphy <robin.murphy@arm.com>
Cc: John Garry <john.garry@huawei.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2022-09-13 14:54:20 +08:00
|
|
|
|
2023-11-02 03:23:23 +00:00
|
|
|
|
|
|
|
|
|
2023-11-02 03:23:22 +00:00
|
|
|
|
2023-11-02 03:23:27 +00:00
|
|
|
|
2023-11-02 03:23:22 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-11-02 03:23:27 +00:00
|
|
|
|
2023-11-02 03:23:22 +00:00
|
|
|
|
|
|
|
|
|
2021-05-11 12:45:48 +02:00
|
|
|
|
2021-05-21 14:03:23 +02:00
|
|
|
|
mm/slub: Reduce memory consumption in extreme scenarios
When kmalloc_node() is called without __GFP_THISNODE and the target node
lacks sufficient memory, SLUB allocates a folio from a different node
other than the requested node, instead of taking a partial slab from it.
However, since the allocated folio does not belong to the requested
node, on the following allocation it is deactivated and added to the
partial slab list of the node it belongs to.
This behavior can result in excessive memory usage when the requested
node has insufficient memory, as SLUB will repeatedly allocate folios
from other nodes without reusing the previously allocated ones.
To prevent memory wastage, when a preferred node is indicated (not
NUMA_NO_NODE) but without a prior __GFP_THISNODE constraint:
1) try to get a partial slab from target node only by having
__GFP_THISNODE in pc.flags for get_partial()
2) if 1) failed, try to allocate a new slab from target node with
GFP_NOWAIT | __GFP_THISNODE opportunistically.
3) if 2) failed, retry with original gfpflags which will allow
get_partial() try partial lists of other nodes before potentially
allocating new page from other nodes
Without a preferred node, or with __GFP_THISNODE constraint, the
behavior remains unchanged.
On qemu with 4 numa nodes and each numa has 1G memory. Write a test ko
to call kmalloc_node(196, GFP_KERNEL, 3) for (4 * 1024 + 4) * 1024 times.
cat /proc/slabinfo shows:
kmalloc-256 4200530 13519712 256 32 2 : tunables..
after this patch,
cat /proc/slabinfo shows:
kmalloc-256 4200558 4200768 256 32 2 : tunables..
Signed-off-by: Chen Jun <chenjun102@huawei.com>
Signed-off-by: Kefeng Wang <wangkefeng.wang@huawei.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2024-03-30 16:23:35 +08:00
|
|
|
|
2021-05-21 14:03:23 +02:00
|
|
|
|
2007-10-16 23:25:51 -07:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
mm/slub: Reduce memory consumption in extreme scenarios
When kmalloc_node() is called without __GFP_THISNODE and the target node
lacks sufficient memory, SLUB allocates a folio from a different node
other than the requested node, instead of taking a partial slab from it.
However, since the allocated folio does not belong to the requested
node, on the following allocation it is deactivated and added to the
partial slab list of the node it belongs to.
This behavior can result in excessive memory usage when the requested
node has insufficient memory, as SLUB will repeatedly allocate folios
from other nodes without reusing the previously allocated ones.
To prevent memory wastage, when a preferred node is indicated (not
NUMA_NO_NODE) but without a prior __GFP_THISNODE constraint:
1) try to get a partial slab from target node only by having
__GFP_THISNODE in pc.flags for get_partial()
2) if 1) failed, try to allocate a new slab from target node with
GFP_NOWAIT | __GFP_THISNODE opportunistically.
3) if 2) failed, retry with original gfpflags which will allow
get_partial() try partial lists of other nodes before potentially
allocating new page from other nodes
Without a preferred node, or with __GFP_THISNODE constraint, the
behavior remains unchanged.
On qemu with 4 numa nodes and each numa has 1G memory. Write a test ko
to call kmalloc_node(196, GFP_KERNEL, 3) for (4 * 1024 + 4) * 1024 times.
cat /proc/slabinfo shows:
kmalloc-256 4200530 13519712 256 32 2 : tunables..
after this patch,
cat /proc/slabinfo shows:
kmalloc-256 4200558 4200768 256 32 2 : tunables..
Signed-off-by: Chen Jun <chenjun102@huawei.com>
Signed-off-by: Kefeng Wang <wangkefeng.wang@huawei.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2024-03-30 16:23:35 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
mm, slab: suppress out of memory warning unless debug is enabled
When the slab or slub allocators cannot allocate additional slab pages,
they emit diagnostic information to the kernel log such as current
number of slabs, number of objects, active objects, etc. This is always
coupled with a page allocation failure warning since it is controlled by
!__GFP_NOWARN.
Suppress this out of memory warning if the allocator is configured
without debug supported. The page allocation failure warning will
indicate it is a failed slab allocation, the order, and the gfp mask, so
this is only useful to diagnose allocator issues.
Since CONFIG_SLUB_DEBUG is already enabled by default for the slub
allocator, there is no functional change with this patch. If debug is
disabled, however, the warnings are now suppressed.
Signed-off-by: David Rientjes <rientjes@google.com>
Cc: Pekka Enberg <penberg@kernel.org>
Acked-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-06-04 16:06:36 -07:00
|
|
|
|
2012-05-09 10:09:54 -05:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2007-05-10 03:15:16 -07:00
|
|
|
|
mm/slub: restrict sysfs validation to debug caches and make it safe
Rongwei Wang reports [1] that cache validation triggered by writing to
/sys/kernel/slab/<cache>/validate is racy against normal cache
operations (e.g. freeing) in a way that can cause false positive
inconsistency reports for caches with debugging enabled. The problem is
that debugging actions that mark object free or active and actual
freelist operations are not atomic, and the validation can see an
inconsistent state.
For caches that do or don't have debugging enabled, additional races
involving n->nr_slabs are possible that result in false reports of wrong
slab counts.
This patch attempts to solve these issues while not adding overhead to
normal (especially fastpath) operations for caches that do not have
debugging enabled. Such overhead would not be justified to make possible
userspace-triggered validation safe. Instead, disable the validation for
caches that don't have debugging enabled and make their sysfs validate
handler return -EINVAL.
For caches that do have debugging enabled, we can instead extend the
existing approach of not using percpu freelists to force all alloc/free
operations to the slow paths where debugging flags is checked and acted
upon. There can adjust the debug-specific paths to increase n->list_lock
coverage against concurrent validation as necessary.
The processing on free in free_debug_processing() already happens under
n->list_lock so we can extend it to actually do the freeing as well and
thus make it atomic against concurrent validation. As observed by
Hyeonggon Yoo, we do not really need to take slab_lock() anymore here
because all paths we could race with are protected by n->list_lock under
the new scheme, so drop its usage here.
The processing on alloc in alloc_debug_processing() currently doesn't
take any locks, but we have to first allocate the object from a slab on
the partial list (as debugging caches have no percpu slabs) and thus
take the n->list_lock anyway. Add a function alloc_single_from_partial()
that grabs just the allocated object instead of the whole freelist, and
does the debug processing. The n->list_lock coverage again makes it
atomic against validation and it is also ultimately more efficient than
the current grabbing of freelist immediately followed by slab
deactivation.
To prevent races on n->nr_slabs updates, make sure that for caches with
debugging enabled, inc_slabs_node() or dec_slabs_node() is called under
n->list_lock. When allocating a new slab for a debug cache, handle the
allocation by a new function alloc_single_from_new_slab() instead of the
current forced deactivation path.
Neither of these changes affect the fast paths at all. The changes in
slow paths are negligible for non-debug caches.
[1] https://lore.kernel.org/all/20220529081535.69275-1-rongwei.wang@linux.alibaba.com/
Reported-by: Rongwei Wang <rongwei.wang@linux.alibaba.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
2022-08-23 19:03:57 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
mm/slub: enable debugging memory wasting of kmalloc
kmalloc's API family is critical for mm, with one nature that it will
round up the request size to a fixed one (mostly power of 2). Say
when user requests memory for '2^n + 1' bytes, actually 2^(n+1) bytes
could be allocated, so in worst case, there is around 50% memory
space waste.
The wastage is not a big issue for requests that get allocated/freed
quickly, but may cause problems with objects that have longer life
time.
We've met a kernel boot OOM panic (v5.10), and from the dumped slab
info:
[ 26.062145] kmalloc-2k 814056KB 814056KB
From debug we found there are huge number of 'struct iova_magazine',
whose size is 1032 bytes (1024 + 8), so each allocation will waste
1016 bytes. Though the issue was solved by giving the right (bigger)
size of RAM, it is still nice to optimize the size (either use a
kmalloc friendly size or create a dedicated slab for it).
And from lkml archive, there was another crash kernel OOM case [1]
back in 2019, which seems to be related with the similar slab waste
situation, as the log is similar:
[ 4.332648] iommu: Adding device 0000:20:02.0 to group 16
[ 4.338946] swapper/0 invoked oom-killer: gfp_mask=0x6040c0(GFP_KERNEL|__GFP_COMP), nodemask=(null), order=0, oom_score_adj=0
...
[ 4.857565] kmalloc-2048 59164KB 59164KB
The crash kernel only has 256M memory, and 59M is pretty big here.
(Note: the related code has been changed and optimised in recent
kernel [2], these logs are just picked to demo the problem, also
a patch changing its size to 1024 bytes has been merged)
So add an way to track each kmalloc's memory waste info, and
leverage the existing SLUB debug framework (specifically
SLUB_STORE_USER) to show its call stack of original allocation,
so that user can evaluate the waste situation, identify some hot
spots and optimize accordingly, for a better utilization of memory.
The waste info is integrated into existing interface:
'/sys/kernel/debug/slab/kmalloc-xx/alloc_traces', one example of
'kmalloc-4k' after boot is:
126 ixgbe_alloc_q_vector+0xbe/0x830 [ixgbe] waste=233856/1856 age=280763/281414/282065 pid=1330 cpus=32 nodes=1
__kmem_cache_alloc_node+0x11f/0x4e0
__kmalloc_node+0x4e/0x140
ixgbe_alloc_q_vector+0xbe/0x830 [ixgbe]
ixgbe_init_interrupt_scheme+0x2ae/0xc90 [ixgbe]
ixgbe_probe+0x165f/0x1d20 [ixgbe]
local_pci_probe+0x78/0xc0
work_for_cpu_fn+0x26/0x40
...
which means in 'kmalloc-4k' slab, there are 126 requests of
2240 bytes which got a 4KB space (wasting 1856 bytes each
and 233856 bytes in total), from ixgbe_alloc_q_vector().
And when system starts some real workload like multiple docker
instances, there could are more severe waste.
[1]. https://lkml.org/lkml/2019/8/12/266
[2]. https://lore.kernel.org/lkml/2920df89-9975-5785-f79b-257d3052dfaf@huawei.com/
[Thanks Hyeonggon for pointing out several bugs about sorting/format]
[Thanks Vlastimil for suggesting way to reduce memory usage of
orig_size and keep it only for kmalloc objects]
Signed-off-by: Feng Tang <feng.tang@intel.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Robin Murphy <robin.murphy@arm.com>
Cc: John Garry <john.garry@huawei.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2022-09-13 14:54:20 +08:00
|
|
|
|
mm/slub: restrict sysfs validation to debug caches and make it safe
Rongwei Wang reports [1] that cache validation triggered by writing to
/sys/kernel/slab/<cache>/validate is racy against normal cache
operations (e.g. freeing) in a way that can cause false positive
inconsistency reports for caches with debugging enabled. The problem is
that debugging actions that mark object free or active and actual
freelist operations are not atomic, and the validation can see an
inconsistent state.
For caches that do or don't have debugging enabled, additional races
involving n->nr_slabs are possible that result in false reports of wrong
slab counts.
This patch attempts to solve these issues while not adding overhead to
normal (especially fastpath) operations for caches that do not have
debugging enabled. Such overhead would not be justified to make possible
userspace-triggered validation safe. Instead, disable the validation for
caches that don't have debugging enabled and make their sysfs validate
handler return -EINVAL.
For caches that do have debugging enabled, we can instead extend the
existing approach of not using percpu freelists to force all alloc/free
operations to the slow paths where debugging flags is checked and acted
upon. There can adjust the debug-specific paths to increase n->list_lock
coverage against concurrent validation as necessary.
The processing on free in free_debug_processing() already happens under
n->list_lock so we can extend it to actually do the freeing as well and
thus make it atomic against concurrent validation. As observed by
Hyeonggon Yoo, we do not really need to take slab_lock() anymore here
because all paths we could race with are protected by n->list_lock under
the new scheme, so drop its usage here.
The processing on alloc in alloc_debug_processing() currently doesn't
take any locks, but we have to first allocate the object from a slab on
the partial list (as debugging caches have no percpu slabs) and thus
take the n->list_lock anyway. Add a function alloc_single_from_partial()
that grabs just the allocated object instead of the whole freelist, and
does the debug processing. The n->list_lock coverage again makes it
atomic against validation and it is also ultimately more efficient than
the current grabbing of freelist immediately followed by slab
deactivation.
To prevent races on n->nr_slabs updates, make sure that for caches with
debugging enabled, inc_slabs_node() or dec_slabs_node() is called under
n->list_lock. When allocating a new slab for a debug cache, handle the
allocation by a new function alloc_single_from_new_slab() instead of the
current forced deactivation path.
Neither of these changes affect the fast paths at all. The changes in
slow paths are negligible for non-debug caches.
[1] https://lore.kernel.org/all/20220529081535.69275-1-rongwei.wang@linux.alibaba.com/
Reported-by: Rongwei Wang <rongwei.wang@linux.alibaba.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
2022-08-23 19:03:57 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-05-11 13:01:34 +02:00
|
|
|
|
2021-11-15 16:55:15 +01:00
|
|
|
|
2021-05-11 13:01:34 +02:00
|
|
|
|
|
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
|
|
|
|
|
mm/slub: restrict sysfs validation to debug caches and make it safe
Rongwei Wang reports [1] that cache validation triggered by writing to
/sys/kernel/slab/<cache>/validate is racy against normal cache
operations (e.g. freeing) in a way that can cause false positive
inconsistency reports for caches with debugging enabled. The problem is
that debugging actions that mark object free or active and actual
freelist operations are not atomic, and the validation can see an
inconsistent state.
For caches that do or don't have debugging enabled, additional races
involving n->nr_slabs are possible that result in false reports of wrong
slab counts.
This patch attempts to solve these issues while not adding overhead to
normal (especially fastpath) operations for caches that do not have
debugging enabled. Such overhead would not be justified to make possible
userspace-triggered validation safe. Instead, disable the validation for
caches that don't have debugging enabled and make their sysfs validate
handler return -EINVAL.
For caches that do have debugging enabled, we can instead extend the
existing approach of not using percpu freelists to force all alloc/free
operations to the slow paths where debugging flags is checked and acted
upon. There can adjust the debug-specific paths to increase n->list_lock
coverage against concurrent validation as necessary.
The processing on free in free_debug_processing() already happens under
n->list_lock so we can extend it to actually do the freeing as well and
thus make it atomic against concurrent validation. As observed by
Hyeonggon Yoo, we do not really need to take slab_lock() anymore here
because all paths we could race with are protected by n->list_lock under
the new scheme, so drop its usage here.
The processing on alloc in alloc_debug_processing() currently doesn't
take any locks, but we have to first allocate the object from a slab on
the partial list (as debugging caches have no percpu slabs) and thus
take the n->list_lock anyway. Add a function alloc_single_from_partial()
that grabs just the allocated object instead of the whole freelist, and
does the debug processing. The n->list_lock coverage again makes it
atomic against validation and it is also ultimately more efficient than
the current grabbing of freelist immediately followed by slab
deactivation.
To prevent races on n->nr_slabs updates, make sure that for caches with
debugging enabled, inc_slabs_node() or dec_slabs_node() is called under
n->list_lock. When allocating a new slab for a debug cache, handle the
allocation by a new function alloc_single_from_new_slab() instead of the
current forced deactivation path.
Neither of these changes affect the fast paths at all. The changes in
slow paths are negligible for non-debug caches.
[1] https://lore.kernel.org/all/20220529081535.69275-1-rongwei.wang@linux.alibaba.com/
Reported-by: Rongwei Wang <rongwei.wang@linux.alibaba.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
2022-08-23 19:03:57 +02:00
|
|
|
|
|
|
|
|
|
2021-05-11 13:01:34 +02:00
|
|
|
|
mm/slub: restrict sysfs validation to debug caches and make it safe
Rongwei Wang reports [1] that cache validation triggered by writing to
/sys/kernel/slab/<cache>/validate is racy against normal cache
operations (e.g. freeing) in a way that can cause false positive
inconsistency reports for caches with debugging enabled. The problem is
that debugging actions that mark object free or active and actual
freelist operations are not atomic, and the validation can see an
inconsistent state.
For caches that do or don't have debugging enabled, additional races
involving n->nr_slabs are possible that result in false reports of wrong
slab counts.
This patch attempts to solve these issues while not adding overhead to
normal (especially fastpath) operations for caches that do not have
debugging enabled. Such overhead would not be justified to make possible
userspace-triggered validation safe. Instead, disable the validation for
caches that don't have debugging enabled and make their sysfs validate
handler return -EINVAL.
For caches that do have debugging enabled, we can instead extend the
existing approach of not using percpu freelists to force all alloc/free
operations to the slow paths where debugging flags is checked and acted
upon. There can adjust the debug-specific paths to increase n->list_lock
coverage against concurrent validation as necessary.
The processing on free in free_debug_processing() already happens under
n->list_lock so we can extend it to actually do the freeing as well and
thus make it atomic against concurrent validation. As observed by
Hyeonggon Yoo, we do not really need to take slab_lock() anymore here
because all paths we could race with are protected by n->list_lock under
the new scheme, so drop its usage here.
The processing on alloc in alloc_debug_processing() currently doesn't
take any locks, but we have to first allocate the object from a slab on
the partial list (as debugging caches have no percpu slabs) and thus
take the n->list_lock anyway. Add a function alloc_single_from_partial()
that grabs just the allocated object instead of the whole freelist, and
does the debug processing. The n->list_lock coverage again makes it
atomic against validation and it is also ultimately more efficient than
the current grabbing of freelist immediately followed by slab
deactivation.
To prevent races on n->nr_slabs updates, make sure that for caches with
debugging enabled, inc_slabs_node() or dec_slabs_node() is called under
n->list_lock. When allocating a new slab for a debug cache, handle the
allocation by a new function alloc_single_from_new_slab() instead of the
current forced deactivation path.
Neither of these changes affect the fast paths at all. The changes in
slow paths are negligible for non-debug caches.
[1] https://lore.kernel.org/all/20220529081535.69275-1-rongwei.wang@linux.alibaba.com/
Reported-by: Rongwei Wang <rongwei.wang@linux.alibaba.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
2022-08-23 19:03:57 +02:00
|
|
|
|
2021-05-11 13:01:34 +02:00
|
|
|
|
mm/slub: restrict sysfs validation to debug caches and make it safe
Rongwei Wang reports [1] that cache validation triggered by writing to
/sys/kernel/slab/<cache>/validate is racy against normal cache
operations (e.g. freeing) in a way that can cause false positive
inconsistency reports for caches with debugging enabled. The problem is
that debugging actions that mark object free or active and actual
freelist operations are not atomic, and the validation can see an
inconsistent state.
For caches that do or don't have debugging enabled, additional races
involving n->nr_slabs are possible that result in false reports of wrong
slab counts.
This patch attempts to solve these issues while not adding overhead to
normal (especially fastpath) operations for caches that do not have
debugging enabled. Such overhead would not be justified to make possible
userspace-triggered validation safe. Instead, disable the validation for
caches that don't have debugging enabled and make their sysfs validate
handler return -EINVAL.
For caches that do have debugging enabled, we can instead extend the
existing approach of not using percpu freelists to force all alloc/free
operations to the slow paths where debugging flags is checked and acted
upon. There can adjust the debug-specific paths to increase n->list_lock
coverage against concurrent validation as necessary.
The processing on free in free_debug_processing() already happens under
n->list_lock so we can extend it to actually do the freeing as well and
thus make it atomic against concurrent validation. As observed by
Hyeonggon Yoo, we do not really need to take slab_lock() anymore here
because all paths we could race with are protected by n->list_lock under
the new scheme, so drop its usage here.
The processing on alloc in alloc_debug_processing() currently doesn't
take any locks, but we have to first allocate the object from a slab on
the partial list (as debugging caches have no percpu slabs) and thus
take the n->list_lock anyway. Add a function alloc_single_from_partial()
that grabs just the allocated object instead of the whole freelist, and
does the debug processing. The n->list_lock coverage again makes it
atomic against validation and it is also ultimately more efficient than
the current grabbing of freelist immediately followed by slab
deactivation.
To prevent races on n->nr_slabs updates, make sure that for caches with
debugging enabled, inc_slabs_node() or dec_slabs_node() is called under
n->list_lock. When allocating a new slab for a debug cache, handle the
allocation by a new function alloc_single_from_new_slab() instead of the
current forced deactivation path.
Neither of these changes affect the fast paths at all. The changes in
slow paths are negligible for non-debug caches.
[1] https://lore.kernel.org/all/20220529081535.69275-1-rongwei.wang@linux.alibaba.com/
Reported-by: Rongwei Wang <rongwei.wang@linux.alibaba.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
2022-08-23 19:03:57 +02:00
|
|
|
|
2021-05-11 18:25:09 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
mm/slub: restrict sysfs validation to debug caches and make it safe
Rongwei Wang reports [1] that cache validation triggered by writing to
/sys/kernel/slab/<cache>/validate is racy against normal cache
operations (e.g. freeing) in a way that can cause false positive
inconsistency reports for caches with debugging enabled. The problem is
that debugging actions that mark object free or active and actual
freelist operations are not atomic, and the validation can see an
inconsistent state.
For caches that do or don't have debugging enabled, additional races
involving n->nr_slabs are possible that result in false reports of wrong
slab counts.
This patch attempts to solve these issues while not adding overhead to
normal (especially fastpath) operations for caches that do not have
debugging enabled. Such overhead would not be justified to make possible
userspace-triggered validation safe. Instead, disable the validation for
caches that don't have debugging enabled and make their sysfs validate
handler return -EINVAL.
For caches that do have debugging enabled, we can instead extend the
existing approach of not using percpu freelists to force all alloc/free
operations to the slow paths where debugging flags is checked and acted
upon. There can adjust the debug-specific paths to increase n->list_lock
coverage against concurrent validation as necessary.
The processing on free in free_debug_processing() already happens under
n->list_lock so we can extend it to actually do the freeing as well and
thus make it atomic against concurrent validation. As observed by
Hyeonggon Yoo, we do not really need to take slab_lock() anymore here
because all paths we could race with are protected by n->list_lock under
the new scheme, so drop its usage here.
The processing on alloc in alloc_debug_processing() currently doesn't
take any locks, but we have to first allocate the object from a slab on
the partial list (as debugging caches have no percpu slabs) and thus
take the n->list_lock anyway. Add a function alloc_single_from_partial()
that grabs just the allocated object instead of the whole freelist, and
does the debug processing. The n->list_lock coverage again makes it
atomic against validation and it is also ultimately more efficient than
the current grabbing of freelist immediately followed by slab
deactivation.
To prevent races on n->nr_slabs updates, make sure that for caches with
debugging enabled, inc_slabs_node() or dec_slabs_node() is called under
n->list_lock. When allocating a new slab for a debug cache, handle the
allocation by a new function alloc_single_from_new_slab() instead of the
current forced deactivation path.
Neither of these changes affect the fast paths at all. The changes in
slow paths are negligible for non-debug caches.
[1] https://lore.kernel.org/all/20220529081535.69275-1-rongwei.wang@linux.alibaba.com/
Reported-by: Rongwei Wang <rongwei.wang@linux.alibaba.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
2022-08-23 19:03:57 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-05-11 18:25:09 +02:00
|
|
|
|
2021-11-15 16:55:15 +01:00
|
|
|
|
2021-05-12 14:04:43 +02:00
|
|
|
|
2021-05-22 01:59:38 +02:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2021-05-12 14:04:43 +02:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2021-05-12 14:04:43 +02:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2021-05-12 14:04:43 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-05-22 01:59:38 +02:00
|
|
|
|
2021-05-12 14:04:43 +02:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2021-05-12 14:04:43 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-11-15 16:55:15 +01:00
|
|
|
|
2021-05-12 14:04:43 +02:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2021-05-11 16:37:51 +02:00
|
|
|
|
2021-05-11 18:25:09 +02:00
|
|
|
|
2007-05-10 03:15:16 -07:00
|
|
|
|
|
|
|
|
|
2015-11-20 15:57:35 -08:00
|
|
|
|
mm, slub: move disabling/enabling irqs to ___slab_alloc()
Currently __slab_alloc() disables irqs around the whole ___slab_alloc(). This
includes cases where this is not needed, such as when the allocation ends up in
the page allocator and has to awkwardly enable irqs back based on gfp flags.
Also the whole kmem_cache_alloc_bulk() is executed with irqs disabled even when
it hits the __slab_alloc() slow path, and long periods with disabled interrupts
are undesirable.
As a first step towards reducing irq disabled periods, move irq handling into
___slab_alloc(). Callers will instead prevent the s->cpu_slab percpu pointer
from becoming invalid via get_cpu_ptr(), thus preempt_disable(). This does not
protect against modification by an irq handler, which is still done by disabled
irq for most of ___slab_alloc(). As a small immediate benefit,
slab_out_of_memory() from ___slab_alloc() is now called with irqs enabled.
kmem_cache_alloc_bulk() disables irqs for its fastpath and then re-enables them
before calling ___slab_alloc(), which then disables them at its discretion. The
whole kmem_cache_alloc_bulk() operation also disables preemption.
When ___slab_alloc() calls new_slab() to allocate a new page, re-enable
preemption, because new_slab() will re-enable interrupts in contexts that allow
blocking (this will be improved by later patches).
The patch itself will thus increase overhead a bit due to disabled preemption
(on configs where it matters) and increased disabling/enabling irqs in
kmem_cache_alloc_bulk(), but that will be gradually improved in the following
patches.
Note in __slab_alloc() we need to change the #ifdef CONFIG_PREEMPT guard to
CONFIG_PREEMPT_COUNT to make sure preempt disable/enable is properly paired in
all configurations. On configs without involuntary preemption and debugging
the re-read of kmem_cache_cpu pointer is still compiled out as it was before.
[ Mike Galbraith <efault@gmx.de>: Fix kmem_cache_alloc_bulk() error path ]
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2021-05-07 19:32:31 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-11-20 15:57:35 -08:00
|
|
|
|
|
|
|
|
|
mm/slub: enable debugging memory wasting of kmalloc
kmalloc's API family is critical for mm, with one nature that it will
round up the request size to a fixed one (mostly power of 2). Say
when user requests memory for '2^n + 1' bytes, actually 2^(n+1) bytes
could be allocated, so in worst case, there is around 50% memory
space waste.
The wastage is not a big issue for requests that get allocated/freed
quickly, but may cause problems with objects that have longer life
time.
We've met a kernel boot OOM panic (v5.10), and from the dumped slab
info:
[ 26.062145] kmalloc-2k 814056KB 814056KB
From debug we found there are huge number of 'struct iova_magazine',
whose size is 1032 bytes (1024 + 8), so each allocation will waste
1016 bytes. Though the issue was solved by giving the right (bigger)
size of RAM, it is still nice to optimize the size (either use a
kmalloc friendly size or create a dedicated slab for it).
And from lkml archive, there was another crash kernel OOM case [1]
back in 2019, which seems to be related with the similar slab waste
situation, as the log is similar:
[ 4.332648] iommu: Adding device 0000:20:02.0 to group 16
[ 4.338946] swapper/0 invoked oom-killer: gfp_mask=0x6040c0(GFP_KERNEL|__GFP_COMP), nodemask=(null), order=0, oom_score_adj=0
...
[ 4.857565] kmalloc-2048 59164KB 59164KB
The crash kernel only has 256M memory, and 59M is pretty big here.
(Note: the related code has been changed and optimised in recent
kernel [2], these logs are just picked to demo the problem, also
a patch changing its size to 1024 bytes has been merged)
So add an way to track each kmalloc's memory waste info, and
leverage the existing SLUB debug framework (specifically
SLUB_STORE_USER) to show its call stack of original allocation,
so that user can evaluate the waste situation, identify some hot
spots and optimize accordingly, for a better utilization of memory.
The waste info is integrated into existing interface:
'/sys/kernel/debug/slab/kmalloc-xx/alloc_traces', one example of
'kmalloc-4k' after boot is:
126 ixgbe_alloc_q_vector+0xbe/0x830 [ixgbe] waste=233856/1856 age=280763/281414/282065 pid=1330 cpus=32 nodes=1
__kmem_cache_alloc_node+0x11f/0x4e0
__kmalloc_node+0x4e/0x140
ixgbe_alloc_q_vector+0xbe/0x830 [ixgbe]
ixgbe_init_interrupt_scheme+0x2ae/0xc90 [ixgbe]
ixgbe_probe+0x165f/0x1d20 [ixgbe]
local_pci_probe+0x78/0xc0
work_for_cpu_fn+0x26/0x40
...
which means in 'kmalloc-4k' slab, there are 126 requests of
2240 bytes which got a 4KB space (wasting 1856 bytes each
and 233856 bytes in total), from ixgbe_alloc_q_vector().
And when system starts some real workload like multiple docker
instances, there could are more severe waste.
[1]. https://lkml.org/lkml/2019/8/12/266
[2]. https://lore.kernel.org/lkml/2920df89-9975-5785-f79b-257d3052dfaf@huawei.com/
[Thanks Hyeonggon for pointing out several bugs about sorting/format]
[Thanks Vlastimil for suggesting way to reduce memory usage of
orig_size and keep it only for kmalloc objects]
Signed-off-by: Feng Tang <feng.tang@intel.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Robin Murphy <robin.murphy@arm.com>
Cc: John Garry <john.garry@huawei.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2022-09-13 14:54:20 +08:00
|
|
|
|
2015-11-20 15:57:35 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
mm, slub: move disabling/enabling irqs to ___slab_alloc()
Currently __slab_alloc() disables irqs around the whole ___slab_alloc(). This
includes cases where this is not needed, such as when the allocation ends up in
the page allocator and has to awkwardly enable irqs back based on gfp flags.
Also the whole kmem_cache_alloc_bulk() is executed with irqs disabled even when
it hits the __slab_alloc() slow path, and long periods with disabled interrupts
are undesirable.
As a first step towards reducing irq disabled periods, move irq handling into
___slab_alloc(). Callers will instead prevent the s->cpu_slab percpu pointer
from becoming invalid via get_cpu_ptr(), thus preempt_disable(). This does not
protect against modification by an irq handler, which is still done by disabled
irq for most of ___slab_alloc(). As a small immediate benefit,
slab_out_of_memory() from ___slab_alloc() is now called with irqs enabled.
kmem_cache_alloc_bulk() disables irqs for its fastpath and then re-enables them
before calling ___slab_alloc(), which then disables them at its discretion. The
whole kmem_cache_alloc_bulk() operation also disables preemption.
When ___slab_alloc() calls new_slab() to allocate a new page, re-enable
preemption, because new_slab() will re-enable interrupts in contexts that allow
blocking (this will be improved by later patches).
The patch itself will thus increase overhead a bit due to disabled preemption
(on configs where it matters) and increased disabling/enabling irqs in
kmem_cache_alloc_bulk(), but that will be gradually improved in the following
patches.
Note in __slab_alloc() we need to change the #ifdef CONFIG_PREEMPT guard to
CONFIG_PREEMPT_COUNT to make sure preempt disable/enable is properly paired in
all configurations. On configs without involuntary preemption and debugging
the re-read of kmem_cache_cpu pointer is still compiled out as it was before.
[ Mike Galbraith <efault@gmx.de>: Fix kmem_cache_alloc_bulk() error path ]
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2021-05-07 19:32:31 +02:00
|
|
|
|
2015-11-20 15:57:35 -08:00
|
|
|
|
|
|
|
|
|
mm, slub: move disabling/enabling irqs to ___slab_alloc()
Currently __slab_alloc() disables irqs around the whole ___slab_alloc(). This
includes cases where this is not needed, such as when the allocation ends up in
the page allocator and has to awkwardly enable irqs back based on gfp flags.
Also the whole kmem_cache_alloc_bulk() is executed with irqs disabled even when
it hits the __slab_alloc() slow path, and long periods with disabled interrupts
are undesirable.
As a first step towards reducing irq disabled periods, move irq handling into
___slab_alloc(). Callers will instead prevent the s->cpu_slab percpu pointer
from becoming invalid via get_cpu_ptr(), thus preempt_disable(). This does not
protect against modification by an irq handler, which is still done by disabled
irq for most of ___slab_alloc(). As a small immediate benefit,
slab_out_of_memory() from ___slab_alloc() is now called with irqs enabled.
kmem_cache_alloc_bulk() disables irqs for its fastpath and then re-enables them
before calling ___slab_alloc(), which then disables them at its discretion. The
whole kmem_cache_alloc_bulk() operation also disables preemption.
When ___slab_alloc() calls new_slab() to allocate a new page, re-enable
preemption, because new_slab() will re-enable interrupts in contexts that allow
blocking (this will be improved by later patches).
The patch itself will thus increase overhead a bit due to disabled preemption
(on configs where it matters) and increased disabling/enabling irqs in
kmem_cache_alloc_bulk(), but that will be gradually improved in the following
patches.
Note in __slab_alloc() we need to change the #ifdef CONFIG_PREEMPT guard to
CONFIG_PREEMPT_COUNT to make sure preempt disable/enable is properly paired in
all configurations. On configs without involuntary preemption and debugging
the re-read of kmem_cache_cpu pointer is still compiled out as it was before.
[ Mike Galbraith <efault@gmx.de>: Fix kmem_cache_alloc_bulk() error path ]
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2021-05-07 19:32:31 +02:00
|
|
|
|
2015-11-20 15:57:35 -08:00
|
|
|
|
|
|
|
|
|
2021-05-21 14:03:23 +02:00
|
|
|
|
2015-11-20 15:57:35 -08:00
|
|
|
|
|
|
|
|
|
mm/slub: enable debugging memory wasting of kmalloc
kmalloc's API family is critical for mm, with one nature that it will
round up the request size to a fixed one (mostly power of 2). Say
when user requests memory for '2^n + 1' bytes, actually 2^(n+1) bytes
could be allocated, so in worst case, there is around 50% memory
space waste.
The wastage is not a big issue for requests that get allocated/freed
quickly, but may cause problems with objects that have longer life
time.
We've met a kernel boot OOM panic (v5.10), and from the dumped slab
info:
[ 26.062145] kmalloc-2k 814056KB 814056KB
From debug we found there are huge number of 'struct iova_magazine',
whose size is 1032 bytes (1024 + 8), so each allocation will waste
1016 bytes. Though the issue was solved by giving the right (bigger)
size of RAM, it is still nice to optimize the size (either use a
kmalloc friendly size or create a dedicated slab for it).
And from lkml archive, there was another crash kernel OOM case [1]
back in 2019, which seems to be related with the similar slab waste
situation, as the log is similar:
[ 4.332648] iommu: Adding device 0000:20:02.0 to group 16
[ 4.338946] swapper/0 invoked oom-killer: gfp_mask=0x6040c0(GFP_KERNEL|__GFP_COMP), nodemask=(null), order=0, oom_score_adj=0
...
[ 4.857565] kmalloc-2048 59164KB 59164KB
The crash kernel only has 256M memory, and 59M is pretty big here.
(Note: the related code has been changed and optimised in recent
kernel [2], these logs are just picked to demo the problem, also
a patch changing its size to 1024 bytes has been merged)
So add an way to track each kmalloc's memory waste info, and
leverage the existing SLUB debug framework (specifically
SLUB_STORE_USER) to show its call stack of original allocation,
so that user can evaluate the waste situation, identify some hot
spots and optimize accordingly, for a better utilization of memory.
The waste info is integrated into existing interface:
'/sys/kernel/debug/slab/kmalloc-xx/alloc_traces', one example of
'kmalloc-4k' after boot is:
126 ixgbe_alloc_q_vector+0xbe/0x830 [ixgbe] waste=233856/1856 age=280763/281414/282065 pid=1330 cpus=32 nodes=1
__kmem_cache_alloc_node+0x11f/0x4e0
__kmalloc_node+0x4e/0x140
ixgbe_alloc_q_vector+0xbe/0x830 [ixgbe]
ixgbe_init_interrupt_scheme+0x2ae/0xc90 [ixgbe]
ixgbe_probe+0x165f/0x1d20 [ixgbe]
local_pci_probe+0x78/0xc0
work_for_cpu_fn+0x26/0x40
...
which means in 'kmalloc-4k' slab, there are 126 requests of
2240 bytes which got a 4KB space (wasting 1856 bytes each
and 233856 bytes in total), from ixgbe_alloc_q_vector().
And when system starts some real workload like multiple docker
instances, there could are more severe waste.
[1]. https://lkml.org/lkml/2019/8/12/266
[2]. https://lore.kernel.org/lkml/2920df89-9975-5785-f79b-257d3052dfaf@huawei.com/
[Thanks Hyeonggon for pointing out several bugs about sorting/format]
[Thanks Vlastimil for suggesting way to reduce memory usage of
orig_size and keep it only for kmalloc objects]
Signed-off-by: Feng Tang <feng.tang@intel.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Robin Murphy <robin.murphy@arm.com>
Cc: John Garry <john.garry@huawei.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2022-09-13 14:54:20 +08:00
|
|
|
|
mm, slub: move disabling/enabling irqs to ___slab_alloc()
Currently __slab_alloc() disables irqs around the whole ___slab_alloc(). This
includes cases where this is not needed, such as when the allocation ends up in
the page allocator and has to awkwardly enable irqs back based on gfp flags.
Also the whole kmem_cache_alloc_bulk() is executed with irqs disabled even when
it hits the __slab_alloc() slow path, and long periods with disabled interrupts
are undesirable.
As a first step towards reducing irq disabled periods, move irq handling into
___slab_alloc(). Callers will instead prevent the s->cpu_slab percpu pointer
from becoming invalid via get_cpu_ptr(), thus preempt_disable(). This does not
protect against modification by an irq handler, which is still done by disabled
irq for most of ___slab_alloc(). As a small immediate benefit,
slab_out_of_memory() from ___slab_alloc() is now called with irqs enabled.
kmem_cache_alloc_bulk() disables irqs for its fastpath and then re-enables them
before calling ___slab_alloc(), which then disables them at its discretion. The
whole kmem_cache_alloc_bulk() operation also disables preemption.
When ___slab_alloc() calls new_slab() to allocate a new page, re-enable
preemption, because new_slab() will re-enable interrupts in contexts that allow
blocking (this will be improved by later patches).
The patch itself will thus increase overhead a bit due to disabled preemption
(on configs where it matters) and increased disabling/enabling irqs in
kmem_cache_alloc_bulk(), but that will be gradually improved in the following
patches.
Note in __slab_alloc() we need to change the #ifdef CONFIG_PREEMPT guard to
CONFIG_PREEMPT_COUNT to make sure preempt disable/enable is properly paired in
all configurations. On configs without involuntary preemption and debugging
the re-read of kmem_cache_cpu pointer is still compiled out as it was before.
[ Mike Galbraith <efault@gmx.de>: Fix kmem_cache_alloc_bulk() error path ]
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2021-05-07 19:32:31 +02:00
|
|
|
|
2021-05-21 14:03:23 +02:00
|
|
|
|
mm, slub: move disabling/enabling irqs to ___slab_alloc()
Currently __slab_alloc() disables irqs around the whole ___slab_alloc(). This
includes cases where this is not needed, such as when the allocation ends up in
the page allocator and has to awkwardly enable irqs back based on gfp flags.
Also the whole kmem_cache_alloc_bulk() is executed with irqs disabled even when
it hits the __slab_alloc() slow path, and long periods with disabled interrupts
are undesirable.
As a first step towards reducing irq disabled periods, move irq handling into
___slab_alloc(). Callers will instead prevent the s->cpu_slab percpu pointer
from becoming invalid via get_cpu_ptr(), thus preempt_disable(). This does not
protect against modification by an irq handler, which is still done by disabled
irq for most of ___slab_alloc(). As a small immediate benefit,
slab_out_of_memory() from ___slab_alloc() is now called with irqs enabled.
kmem_cache_alloc_bulk() disables irqs for its fastpath and then re-enables them
before calling ___slab_alloc(), which then disables them at its discretion. The
whole kmem_cache_alloc_bulk() operation also disables preemption.
When ___slab_alloc() calls new_slab() to allocate a new page, re-enable
preemption, because new_slab() will re-enable interrupts in contexts that allow
blocking (this will be improved by later patches).
The patch itself will thus increase overhead a bit due to disabled preemption
(on configs where it matters) and increased disabling/enabling irqs in
kmem_cache_alloc_bulk(), but that will be gradually improved in the following
patches.
Note in __slab_alloc() we need to change the #ifdef CONFIG_PREEMPT guard to
CONFIG_PREEMPT_COUNT to make sure preempt disable/enable is properly paired in
all configurations. On configs without involuntary preemption and debugging
the re-read of kmem_cache_cpu pointer is still compiled out as it was before.
[ Mike Galbraith <efault@gmx.de>: Fix kmem_cache_alloc_bulk() error path ]
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2021-05-07 19:32:31 +02:00
|
|
|
|
2015-11-20 15:57:35 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-11-21 16:23:50 +01:00
|
|
|
|
2021-02-25 17:19:16 -08:00
|
|
|
|
2007-05-10 03:15:16 -07:00
|
|
|
|
2007-10-16 01:26:05 -07:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2011-02-25 11:38:54 -06:00
|
|
|
|
2022-11-21 16:23:50 +01:00
|
|
|
|
2021-02-25 17:19:16 -08:00
|
|
|
|
2011-02-25 11:38:54 -06:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-01-23 21:45:48 +00:00
|
|
|
|
2021-05-18 02:01:39 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-02-25 11:38:54 -06:00
|
|
|
|
2021-05-18 02:01:39 +02:00
|
|
|
|
|
|
|
|
|
2015-02-10 14:09:32 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-11-15 16:55:15 +01:00
|
|
|
|
2015-02-10 14:09:32 -08:00
|
|
|
|
2021-11-15 16:55:15 +01:00
|
|
|
|
2015-02-10 14:09:32 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-02-25 11:38:54 -06:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2009-12-18 16:26:20 -06:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2022-08-25 09:51:36 +02:00
|
|
|
|
2024-10-01 12:08:06 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-08-25 09:51:36 +02:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
mm/slub: enable debugging memory wasting of kmalloc
kmalloc's API family is critical for mm, with one nature that it will
round up the request size to a fixed one (mostly power of 2). Say
when user requests memory for '2^n + 1' bytes, actually 2^(n+1) bytes
could be allocated, so in worst case, there is around 50% memory
space waste.
The wastage is not a big issue for requests that get allocated/freed
quickly, but may cause problems with objects that have longer life
time.
We've met a kernel boot OOM panic (v5.10), and from the dumped slab
info:
[ 26.062145] kmalloc-2k 814056KB 814056KB
From debug we found there are huge number of 'struct iova_magazine',
whose size is 1032 bytes (1024 + 8), so each allocation will waste
1016 bytes. Though the issue was solved by giving the right (bigger)
size of RAM, it is still nice to optimize the size (either use a
kmalloc friendly size or create a dedicated slab for it).
And from lkml archive, there was another crash kernel OOM case [1]
back in 2019, which seems to be related with the similar slab waste
situation, as the log is similar:
[ 4.332648] iommu: Adding device 0000:20:02.0 to group 16
[ 4.338946] swapper/0 invoked oom-killer: gfp_mask=0x6040c0(GFP_KERNEL|__GFP_COMP), nodemask=(null), order=0, oom_score_adj=0
...
[ 4.857565] kmalloc-2048 59164KB 59164KB
The crash kernel only has 256M memory, and 59M is pretty big here.
(Note: the related code has been changed and optimised in recent
kernel [2], these logs are just picked to demo the problem, also
a patch changing its size to 1024 bytes has been merged)
So add an way to track each kmalloc's memory waste info, and
leverage the existing SLUB debug framework (specifically
SLUB_STORE_USER) to show its call stack of original allocation,
so that user can evaluate the waste situation, identify some hot
spots and optimize accordingly, for a better utilization of memory.
The waste info is integrated into existing interface:
'/sys/kernel/debug/slab/kmalloc-xx/alloc_traces', one example of
'kmalloc-4k' after boot is:
126 ixgbe_alloc_q_vector+0xbe/0x830 [ixgbe] waste=233856/1856 age=280763/281414/282065 pid=1330 cpus=32 nodes=1
__kmem_cache_alloc_node+0x11f/0x4e0
__kmalloc_node+0x4e/0x140
ixgbe_alloc_q_vector+0xbe/0x830 [ixgbe]
ixgbe_init_interrupt_scheme+0x2ae/0xc90 [ixgbe]
ixgbe_probe+0x165f/0x1d20 [ixgbe]
local_pci_probe+0x78/0xc0
work_for_cpu_fn+0x26/0x40
...
which means in 'kmalloc-4k' slab, there are 126 requests of
2240 bytes which got a 4KB space (wasting 1856 bytes each
and 233856 bytes in total), from ixgbe_alloc_q_vector().
And when system starts some real workload like multiple docker
instances, there could are more severe waste.
[1]. https://lkml.org/lkml/2019/8/12/266
[2]. https://lore.kernel.org/lkml/2920df89-9975-5785-f79b-257d3052dfaf@huawei.com/
[Thanks Hyeonggon for pointing out several bugs about sorting/format]
[Thanks Vlastimil for suggesting way to reduce memory usage of
orig_size and keep it only for kmalloc objects]
Signed-off-by: Feng Tang <feng.tang@intel.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Robin Murphy <robin.murphy@arm.com>
Cc: John Garry <john.garry@huawei.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2022-09-13 14:54:20 +08:00
|
|
|
|
mm: slub: fix ALLOC_SLOWPATH stat
There used to be only one path out of __slab_alloc(), and ALLOC_SLOWPATH
got bumped in that exit path. Now there are two, and a bunch of gotos.
ALLOC_SLOWPATH can now get set more than once during a single call to
__slab_alloc() which is pretty bogus. Here's the sequence:
1. Enter __slab_alloc(), fall through all the way to the
stat(s, ALLOC_SLOWPATH);
2. hit 'if (!freelist)', and bump DEACTIVATE_BYPASS, jump to
new_slab (goto #1)
3. Hit 'if (c->partial)', bump CPU_PARTIAL_ALLOC, goto redo
(goto #2)
4. Fall through in the same path we did before all the way to
stat(s, ALLOC_SLOWPATH)
5. bump ALLOC_REFILL stat, then return
Doing this is obviously bogus. It keeps us from being able to
accurately compare ALLOC_SLOWPATH vs. ALLOC_FASTPATH. It also means
that the total number of allocs always exceeds the total number of
frees.
This patch moves stat(s, ALLOC_SLOWPATH) to be called from the same
place that __slab_alloc() is. This makes it much less likely that
ALLOC_SLOWPATH will get botched again in the spaghetti-code inside
__slab_alloc().
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Acked-by: Christoph Lameter <cl@linux.com>
Acked-by: David Rientjes <rientjes@google.com>
Cc: Pekka Enberg <penberg@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-06-04 16:06:37 -07:00
|
|
|
|
slub: prefetch next freelist pointer in slab_alloc()
Recycling a page is a problem, since freelist link chain is hot on
cpu(s) which freed objects, and possibly very cold on cpu currently
owning slab.
Adding a prefetch of cache line containing the pointer to next object in
slab_alloc() helps a lot in many workloads, in particular on assymetric
ones (allocations done on one cpu, frees on another cpus). Added cost is
three machine instructions only.
Examples on my dual socket quad core ht machine (Intel CPU E5540
@2.53GHz) (16 logical cpus, 2 memory nodes), 64bit kernel.
Before patch :
# perf stat -r 32 hackbench 50 process 4000 >/dev/null
Performance counter stats for 'hackbench 50 process 4000' (32 runs):
327577,471718 task-clock # 15,821 CPUs utilized ( +- 0,64% )
28 866 491 context-switches # 0,088 M/sec ( +- 1,80% )
1 506 929 CPU-migrations # 0,005 M/sec ( +- 3,24% )
127 151 page-faults # 0,000 M/sec ( +- 0,16% )
829 399 813 448 cycles # 2,532 GHz ( +- 0,64% )
580 664 691 740 stalled-cycles-frontend # 70,01% frontend cycles idle ( +- 0,71% )
197 431 700 448 stalled-cycles-backend # 23,80% backend cycles idle ( +- 1,03% )
503 548 648 975 instructions # 0,61 insns per cycle
# 1,15 stalled cycles per insn ( +- 0,46% )
95 780 068 471 branches # 292,389 M/sec ( +- 0,48% )
1 426 407 916 branch-misses # 1,49% of all branches ( +- 1,35% )
20,705679994 seconds time elapsed ( +- 0,64% )
After patch :
# perf stat -r 32 hackbench 50 process 4000 >/dev/null
Performance counter stats for 'hackbench 50 process 4000' (32 runs):
286236,542804 task-clock # 15,786 CPUs utilized ( +- 1,32% )
19 703 372 context-switches # 0,069 M/sec ( +- 4,99% )
1 658 249 CPU-migrations # 0,006 M/sec ( +- 6,62% )
126 776 page-faults # 0,000 M/sec ( +- 0,12% )
724 636 593 213 cycles # 2,532 GHz ( +- 1,32% )
499 320 714 837 stalled-cycles-frontend # 68,91% frontend cycles idle ( +- 1,47% )
156 555 126 809 stalled-cycles-backend # 21,60% backend cycles idle ( +- 2,22% )
463 897 792 661 instructions # 0,64 insns per cycle
# 1,08 stalled cycles per insn ( +- 0,94% )
87 717 352 563 branches # 306,451 M/sec ( +- 0,99% )
941 738 280 branch-misses # 1,07% of all branches ( +- 3,35% )
18,132070670 seconds time elapsed ( +- 1,30% )
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Acked-by: Christoph Lameter <cl@linux.com>
CC: Matt Mackall <mpm@selenic.com>
CC: David Rientjes <rientjes@google.com>
CC: "Alex,Shi" <alex.shi@intel.com>
CC: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Pekka Enberg <penberg@kernel.org>
2011-12-16 16:25:34 +01:00
|
|
|
|
|
|
|
|
|
2011-02-25 11:38:54 -06:00
|
|
|
|
2011-03-30 22:57:33 -03:00
|
|
|
|
2011-02-25 11:38:54 -06:00
|
|
|
|
|
|
|
|
|
2013-07-15 09:05:29 +08:00
|
|
|
|
|
|
|
|
|
2011-02-25 11:38:54 -06:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-07-15 09:05:29 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-02-25 11:38:54 -06:00
|
|
|
|
2023-05-31 15:08:43 +02:00
|
|
|
|
2011-02-25 11:38:54 -06:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
slub: prefetch next freelist pointer in slab_alloc()
Recycling a page is a problem, since freelist link chain is hot on
cpu(s) which freed objects, and possibly very cold on cpu currently
owning slab.
Adding a prefetch of cache line containing the pointer to next object in
slab_alloc() helps a lot in many workloads, in particular on assymetric
ones (allocations done on one cpu, frees on another cpus). Added cost is
three machine instructions only.
Examples on my dual socket quad core ht machine (Intel CPU E5540
@2.53GHz) (16 logical cpus, 2 memory nodes), 64bit kernel.
Before patch :
# perf stat -r 32 hackbench 50 process 4000 >/dev/null
Performance counter stats for 'hackbench 50 process 4000' (32 runs):
327577,471718 task-clock # 15,821 CPUs utilized ( +- 0,64% )
28 866 491 context-switches # 0,088 M/sec ( +- 1,80% )
1 506 929 CPU-migrations # 0,005 M/sec ( +- 3,24% )
127 151 page-faults # 0,000 M/sec ( +- 0,16% )
829 399 813 448 cycles # 2,532 GHz ( +- 0,64% )
580 664 691 740 stalled-cycles-frontend # 70,01% frontend cycles idle ( +- 0,71% )
197 431 700 448 stalled-cycles-backend # 23,80% backend cycles idle ( +- 1,03% )
503 548 648 975 instructions # 0,61 insns per cycle
# 1,15 stalled cycles per insn ( +- 0,46% )
95 780 068 471 branches # 292,389 M/sec ( +- 0,48% )
1 426 407 916 branch-misses # 1,49% of all branches ( +- 1,35% )
20,705679994 seconds time elapsed ( +- 0,64% )
After patch :
# perf stat -r 32 hackbench 50 process 4000 >/dev/null
Performance counter stats for 'hackbench 50 process 4000' (32 runs):
286236,542804 task-clock # 15,786 CPUs utilized ( +- 1,32% )
19 703 372 context-switches # 0,069 M/sec ( +- 4,99% )
1 658 249 CPU-migrations # 0,006 M/sec ( +- 6,62% )
126 776 page-faults # 0,000 M/sec ( +- 0,12% )
724 636 593 213 cycles # 2,532 GHz ( +- 1,32% )
499 320 714 837 stalled-cycles-frontend # 68,91% frontend cycles idle ( +- 1,47% )
156 555 126 809 stalled-cycles-backend # 21,60% backend cycles idle ( +- 2,22% )
463 897 792 661 instructions # 0,64 insns per cycle
# 1,08 stalled cycles per insn ( +- 0,94% )
87 717 352 563 branches # 306,451 M/sec ( +- 0,99% )
941 738 280 branch-misses # 1,07% of all branches ( +- 3,35% )
18,132070670 seconds time elapsed ( +- 1,30% )
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Acked-by: Christoph Lameter <cl@linux.com>
CC: Matt Mackall <mpm@selenic.com>
CC: David Rientjes <rientjes@google.com>
CC: "Alex,Shi" <alex.shi@intel.com>
CC: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Pekka Enberg <penberg@kernel.org>
2011-12-16 16:25:34 +01:00
|
|
|
|
2009-12-18 16:26:23 -06:00
|
|
|
|
2007-05-10 03:15:16 -07:00
|
|
|
|
2019-10-14 14:11:57 -07:00
|
|
|
|
2022-11-21 16:23:50 +01:00
|
|
|
|
|
|
|
|
|
2022-11-15 18:14:31 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-11-02 03:23:23 +00:00
|
|
|
|
2022-11-15 18:14:31 +01:00
|
|
|
|
2023-11-02 03:23:23 +00:00
|
|
|
|
|
|
|
|
|
2022-11-15 18:14:31 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-11-21 16:23:50 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-08-28 12:56:24 +02:00
|
|
|
|
2024-09-05 09:56:52 +02:00
|
|
|
|
2022-11-21 16:23:50 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-04-30 13:34:59 +02:00
|
|
|
|
|
|
|
|
|
2022-11-21 16:23:50 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-11-13 18:04:05 +01:00
|
|
|
|
2024-03-26 11:37:38 +01:00
|
|
|
|
2023-10-03 11:57:45 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-11-13 18:04:05 +01:00
|
|
|
|
2023-10-03 11:57:45 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-11-13 18:04:05 +01:00
|
|
|
|
2024-03-26 11:37:38 +01:00
|
|
|
|
2023-11-13 18:04:05 +01:00
|
|
|
|
|
|
|
|
|
2023-10-03 11:57:45 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-11-13 18:04:05 +01:00
|
|
|
|
2023-10-03 11:57:45 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-12-15 11:41:48 +08:00
|
|
|
|
2023-10-03 11:57:45 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-12-15 11:41:48 +08:00
|
|
|
|
2023-10-03 11:57:45 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-11-13 18:04:05 +01:00
|
|
|
|
2023-10-03 11:57:45 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-11-13 18:04:05 +01:00
|
|
|
|
|
|
|
|
|
2024-07-04 06:59:41 -07:00
|
|
|
|
2023-10-03 11:57:45 +02:00
|
|
|
|
|
|
|
|
|
2024-03-26 11:37:38 +01:00
|
|
|
|
2023-10-03 11:57:45 +02:00
|
|
|
|
|
|
|
|
|
2022-11-21 16:23:50 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-11-21 16:58:39 +01:00
|
|
|
|
2022-11-21 16:23:50 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-03-26 11:37:38 +01:00
|
|
|
|
2023-11-13 18:04:05 +01:00
|
|
|
|
2022-11-21 16:23:50 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-01-23 21:01:38 -08:00
|
|
|
|
2021-04-29 23:00:06 -07:00
|
|
|
|
2007-07-17 04:03:23 -07:00
|
|
|
|
2021-02-25 17:19:16 -08:00
|
|
|
|
2022-10-21 11:24:03 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-03-26 11:37:38 +01:00
|
|
|
|
|
|
|
|
|
2022-10-21 11:24:03 +08:00
|
|
|
|
2024-03-26 11:37:38 +01:00
|
|
|
|
2008-04-04 00:54:48 +02:00
|
|
|
|
2007-05-10 03:15:16 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
2024-03-21 09:36:47 -07:00
|
|
|
|
2012-09-08 17:47:58 -03:00
|
|
|
|
2023-10-26 17:45:42 +02:00
|
|
|
|
|
|
|
|
|
2008-08-19 20:43:26 +03:00
|
|
|
|
2022-08-17 19:18:24 +09:00
|
|
|
|
2008-08-19 20:43:26 +03:00
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2024-03-21 09:36:47 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2024-03-21 09:36:47 -07:00
|
|
|
|
2022-03-22 14:40:56 -07:00
|
|
|
|
|
|
|
|
|
2023-10-26 17:45:42 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-03-22 14:40:56 -07:00
|
|
|
|
2024-03-21 09:36:47 -07:00
|
|
|
|
2022-03-22 14:40:56 -07:00
|
|
|
|
2024-09-05 10:34:22 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-11-20 17:11:10 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-03-21 09:36:47 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2022-03-22 14:40:56 -07:00
|
|
|
|
2008-08-19 20:43:26 +03:00
|
|
|
|
2022-08-17 19:18:24 +09:00
|
|
|
|
2008-08-19 20:43:26 +03:00
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2024-03-21 09:36:47 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2023-10-03 16:57:59 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-05-27 11:01:28 +02:00
|
|
|
|
2023-10-03 16:57:59 +02:00
|
|
|
|
Many singleton patches against the MM code. The patch series which
are included in this merge do the following:
- Peng Zhang has done some mapletree maintainance work in the
series
"maple_tree: add mt_free_one() and mt_attr() helpers"
"Some cleanups of maple tree"
- In the series "mm: use memmap_on_memory semantics for dax/kmem"
Vishal Verma has altered the interworking between memory-hotplug
and dax/kmem so that newly added 'device memory' can more easily
have its memmap placed within that newly added memory.
- Matthew Wilcox continues folio-related work (including a few
fixes) in the patch series
"Add folio_zero_tail() and folio_fill_tail()"
"Make folio_start_writeback return void"
"Fix fault handler's handling of poisoned tail pages"
"Convert aops->error_remove_page to ->error_remove_folio"
"Finish two folio conversions"
"More swap folio conversions"
- Kefeng Wang has also contributed folio-related work in the series
"mm: cleanup and use more folio in page fault"
- Jim Cromie has improved the kmemleak reporting output in the
series "tweak kmemleak report format".
- In the series "stackdepot: allow evicting stack traces" Andrey
Konovalov to permits clients (in this case KASAN) to cause
eviction of no longer needed stack traces.
- Charan Teja Kalla has fixed some accounting issues in the page
allocator's atomic reserve calculations in the series "mm:
page_alloc: fixes for high atomic reserve caluculations".
- Dmitry Rokosov has added to the samples/ dorectory some sample
code for a userspace memcg event listener application. See the
series "samples: introduce cgroup events listeners".
- Some mapletree maintanance work from Liam Howlett in the series
"maple_tree: iterator state changes".
- Nhat Pham has improved zswap's approach to writeback in the
series "workload-specific and memory pressure-driven zswap
writeback".
- DAMON/DAMOS feature and maintenance work from SeongJae Park in
the series
"mm/damon: let users feed and tame/auto-tune DAMOS"
"selftests/damon: add Python-written DAMON functionality tests"
"mm/damon: misc updates for 6.8"
- Yosry Ahmed has improved memcg's stats flushing in the series
"mm: memcg: subtree stats flushing and thresholds".
- In the series "Multi-size THP for anonymous memory" Ryan Roberts
has added a runtime opt-in feature to transparent hugepages which
improves performance by allocating larger chunks of memory during
anonymous page faults.
- Matthew Wilcox has also contributed some cleanup and maintenance
work against eh buffer_head code int he series "More buffer_head
cleanups".
- Suren Baghdasaryan has done work on Andrea Arcangeli's series
"userfaultfd move option". UFFDIO_MOVE permits userspace heap
compaction algorithms to move userspace's pages around rather than
UFFDIO_COPY'a alloc/copy/free.
- Stefan Roesch has developed a "KSM Advisor", in the series
"mm/ksm: Add ksm advisor". This is a governor which tunes KSM's
scanning aggressiveness in response to userspace's current needs.
- Chengming Zhou has optimized zswap's temporary working memory
use in the series "mm/zswap: dstmem reuse optimizations and
cleanups".
- Matthew Wilcox has performed some maintenance work on the
writeback code, both code and within filesystems. The series is
"Clean up the writeback paths".
- Andrey Konovalov has optimized KASAN's handling of alloc and
free stack traces for secondary-level allocators, in the series
"kasan: save mempool stack traces".
- Andrey also performed some KASAN maintenance work in the series
"kasan: assorted clean-ups".
- David Hildenbrand has gone to town on the rmap code. Cleanups,
more pte batching, folio conversions and more. See the series
"mm/rmap: interface overhaul".
- Kinsey Ho has contributed some maintenance work on the MGLRU
code in the series "mm/mglru: Kconfig cleanup".
- Matthew Wilcox has contributed lruvec page accounting code
cleanups in the series "Remove some lruvec page accounting
functions".
-----BEGIN PGP SIGNATURE-----
iHUEABYIAB0WIQTTMBEPP41GrTpTJgfdBJ7gKXxAjgUCZZyF2wAKCRDdBJ7gKXxA
jjWjAP42LHvGSjp5M+Rs2rKFL0daBQsrlvy6/jCHUequSdWjSgEAmOx7bc5fbF27
Oa8+DxGM9C+fwqZ/7YxU2w/WuUmLPgU=
=0NHs
-----END PGP SIGNATURE-----
Merge tag 'mm-stable-2024-01-08-15-31' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Pull MM updates from Andrew Morton:
"Many singleton patches against the MM code. The patch series which are
included in this merge do the following:
- Peng Zhang has done some mapletree maintainance work in the series
'maple_tree: add mt_free_one() and mt_attr() helpers'
'Some cleanups of maple tree'
- In the series 'mm: use memmap_on_memory semantics for dax/kmem'
Vishal Verma has altered the interworking between memory-hotplug
and dax/kmem so that newly added 'device memory' can more easily
have its memmap placed within that newly added memory.
- Matthew Wilcox continues folio-related work (including a few fixes)
in the patch series
'Add folio_zero_tail() and folio_fill_tail()'
'Make folio_start_writeback return void'
'Fix fault handler's handling of poisoned tail pages'
'Convert aops->error_remove_page to ->error_remove_folio'
'Finish two folio conversions'
'More swap folio conversions'
- Kefeng Wang has also contributed folio-related work in the series
'mm: cleanup and use more folio in page fault'
- Jim Cromie has improved the kmemleak reporting output in the series
'tweak kmemleak report format'.
- In the series 'stackdepot: allow evicting stack traces' Andrey
Konovalov to permits clients (in this case KASAN) to cause eviction
of no longer needed stack traces.
- Charan Teja Kalla has fixed some accounting issues in the page
allocator's atomic reserve calculations in the series 'mm:
page_alloc: fixes for high atomic reserve caluculations'.
- Dmitry Rokosov has added to the samples/ dorectory some sample code
for a userspace memcg event listener application. See the series
'samples: introduce cgroup events listeners'.
- Some mapletree maintanance work from Liam Howlett in the series
'maple_tree: iterator state changes'.
- Nhat Pham has improved zswap's approach to writeback in the series
'workload-specific and memory pressure-driven zswap writeback'.
- DAMON/DAMOS feature and maintenance work from SeongJae Park in the
series
'mm/damon: let users feed and tame/auto-tune DAMOS'
'selftests/damon: add Python-written DAMON functionality tests'
'mm/damon: misc updates for 6.8'
- Yosry Ahmed has improved memcg's stats flushing in the series 'mm:
memcg: subtree stats flushing and thresholds'.
- In the series 'Multi-size THP for anonymous memory' Ryan Roberts
has added a runtime opt-in feature to transparent hugepages which
improves performance by allocating larger chunks of memory during
anonymous page faults.
- Matthew Wilcox has also contributed some cleanup and maintenance
work against eh buffer_head code int he series 'More buffer_head
cleanups'.
- Suren Baghdasaryan has done work on Andrea Arcangeli's series
'userfaultfd move option'. UFFDIO_MOVE permits userspace heap
compaction algorithms to move userspace's pages around rather than
UFFDIO_COPY'a alloc/copy/free.
- Stefan Roesch has developed a 'KSM Advisor', in the series 'mm/ksm:
Add ksm advisor'. This is a governor which tunes KSM's scanning
aggressiveness in response to userspace's current needs.
- Chengming Zhou has optimized zswap's temporary working memory use
in the series 'mm/zswap: dstmem reuse optimizations and cleanups'.
- Matthew Wilcox has performed some maintenance work on the writeback
code, both code and within filesystems. The series is 'Clean up the
writeback paths'.
- Andrey Konovalov has optimized KASAN's handling of alloc and free
stack traces for secondary-level allocators, in the series 'kasan:
save mempool stack traces'.
- Andrey also performed some KASAN maintenance work in the series
'kasan: assorted clean-ups'.
- David Hildenbrand has gone to town on the rmap code. Cleanups, more
pte batching, folio conversions and more. See the series 'mm/rmap:
interface overhaul'.
- Kinsey Ho has contributed some maintenance work on the MGLRU code
in the series 'mm/mglru: Kconfig cleanup'.
- Matthew Wilcox has contributed lruvec page accounting code cleanups
in the series 'Remove some lruvec page accounting functions'"
* tag 'mm-stable-2024-01-08-15-31' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (361 commits)
mm, treewide: rename MAX_ORDER to MAX_PAGE_ORDER
mm, treewide: introduce NR_PAGE_ORDERS
selftests/mm: add separate UFFDIO_MOVE test for PMD splitting
selftests/mm: skip test if application doesn't has root privileges
selftests/mm: conform test to TAP format output
selftests: mm: hugepage-mmap: conform to TAP format output
selftests/mm: gup_test: conform test to TAP format output
mm/selftests: hugepage-mremap: conform test to TAP format output
mm/vmstat: move pgdemote_* out of CONFIG_NUMA_BALANCING
mm: zsmalloc: return -ENOSPC rather than -EINVAL in zs_malloc while size is too large
mm/memcontrol: remove __mod_lruvec_page_state()
mm/khugepaged: use a folio more in collapse_file()
slub: use a folio in __kmalloc_large_node
slub: use folio APIs in free_large_kmalloc()
slub: use alloc_pages_node() in alloc_slab_page()
mm: remove inc/dec lruvec page state functions
mm: ratelimit stat flush from workingset shrinker
kasan: stop leaking stack trace handles
mm/mglru: remove CONFIG_TRANSPARENT_HUGEPAGE
mm/mglru: add dummy pmd_dirty()
...
2024-01-09 11:18:47 -08:00
|
|
|
|
2023-10-03 16:57:59 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-03-21 09:36:47 -07:00
|
|
|
|
Many singleton patches against the MM code. The patch series which
are included in this merge do the following:
- Peng Zhang has done some mapletree maintainance work in the
series
"maple_tree: add mt_free_one() and mt_attr() helpers"
"Some cleanups of maple tree"
- In the series "mm: use memmap_on_memory semantics for dax/kmem"
Vishal Verma has altered the interworking between memory-hotplug
and dax/kmem so that newly added 'device memory' can more easily
have its memmap placed within that newly added memory.
- Matthew Wilcox continues folio-related work (including a few
fixes) in the patch series
"Add folio_zero_tail() and folio_fill_tail()"
"Make folio_start_writeback return void"
"Fix fault handler's handling of poisoned tail pages"
"Convert aops->error_remove_page to ->error_remove_folio"
"Finish two folio conversions"
"More swap folio conversions"
- Kefeng Wang has also contributed folio-related work in the series
"mm: cleanup and use more folio in page fault"
- Jim Cromie has improved the kmemleak reporting output in the
series "tweak kmemleak report format".
- In the series "stackdepot: allow evicting stack traces" Andrey
Konovalov to permits clients (in this case KASAN) to cause
eviction of no longer needed stack traces.
- Charan Teja Kalla has fixed some accounting issues in the page
allocator's atomic reserve calculations in the series "mm:
page_alloc: fixes for high atomic reserve caluculations".
- Dmitry Rokosov has added to the samples/ dorectory some sample
code for a userspace memcg event listener application. See the
series "samples: introduce cgroup events listeners".
- Some mapletree maintanance work from Liam Howlett in the series
"maple_tree: iterator state changes".
- Nhat Pham has improved zswap's approach to writeback in the
series "workload-specific and memory pressure-driven zswap
writeback".
- DAMON/DAMOS feature and maintenance work from SeongJae Park in
the series
"mm/damon: let users feed and tame/auto-tune DAMOS"
"selftests/damon: add Python-written DAMON functionality tests"
"mm/damon: misc updates for 6.8"
- Yosry Ahmed has improved memcg's stats flushing in the series
"mm: memcg: subtree stats flushing and thresholds".
- In the series "Multi-size THP for anonymous memory" Ryan Roberts
has added a runtime opt-in feature to transparent hugepages which
improves performance by allocating larger chunks of memory during
anonymous page faults.
- Matthew Wilcox has also contributed some cleanup and maintenance
work against eh buffer_head code int he series "More buffer_head
cleanups".
- Suren Baghdasaryan has done work on Andrea Arcangeli's series
"userfaultfd move option". UFFDIO_MOVE permits userspace heap
compaction algorithms to move userspace's pages around rather than
UFFDIO_COPY'a alloc/copy/free.
- Stefan Roesch has developed a "KSM Advisor", in the series
"mm/ksm: Add ksm advisor". This is a governor which tunes KSM's
scanning aggressiveness in response to userspace's current needs.
- Chengming Zhou has optimized zswap's temporary working memory
use in the series "mm/zswap: dstmem reuse optimizations and
cleanups".
- Matthew Wilcox has performed some maintenance work on the
writeback code, both code and within filesystems. The series is
"Clean up the writeback paths".
- Andrey Konovalov has optimized KASAN's handling of alloc and
free stack traces for secondary-level allocators, in the series
"kasan: save mempool stack traces".
- Andrey also performed some KASAN maintenance work in the series
"kasan: assorted clean-ups".
- David Hildenbrand has gone to town on the rmap code. Cleanups,
more pte batching, folio conversions and more. See the series
"mm/rmap: interface overhaul".
- Kinsey Ho has contributed some maintenance work on the MGLRU
code in the series "mm/mglru: Kconfig cleanup".
- Matthew Wilcox has contributed lruvec page accounting code
cleanups in the series "Remove some lruvec page accounting
functions".
-----BEGIN PGP SIGNATURE-----
iHUEABYIAB0WIQTTMBEPP41GrTpTJgfdBJ7gKXxAjgUCZZyF2wAKCRDdBJ7gKXxA
jjWjAP42LHvGSjp5M+Rs2rKFL0daBQsrlvy6/jCHUequSdWjSgEAmOx7bc5fbF27
Oa8+DxGM9C+fwqZ/7YxU2w/WuUmLPgU=
=0NHs
-----END PGP SIGNATURE-----
Merge tag 'mm-stable-2024-01-08-15-31' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Pull MM updates from Andrew Morton:
"Many singleton patches against the MM code. The patch series which are
included in this merge do the following:
- Peng Zhang has done some mapletree maintainance work in the series
'maple_tree: add mt_free_one() and mt_attr() helpers'
'Some cleanups of maple tree'
- In the series 'mm: use memmap_on_memory semantics for dax/kmem'
Vishal Verma has altered the interworking between memory-hotplug
and dax/kmem so that newly added 'device memory' can more easily
have its memmap placed within that newly added memory.
- Matthew Wilcox continues folio-related work (including a few fixes)
in the patch series
'Add folio_zero_tail() and folio_fill_tail()'
'Make folio_start_writeback return void'
'Fix fault handler's handling of poisoned tail pages'
'Convert aops->error_remove_page to ->error_remove_folio'
'Finish two folio conversions'
'More swap folio conversions'
- Kefeng Wang has also contributed folio-related work in the series
'mm: cleanup and use more folio in page fault'
- Jim Cromie has improved the kmemleak reporting output in the series
'tweak kmemleak report format'.
- In the series 'stackdepot: allow evicting stack traces' Andrey
Konovalov to permits clients (in this case KASAN) to cause eviction
of no longer needed stack traces.
- Charan Teja Kalla has fixed some accounting issues in the page
allocator's atomic reserve calculations in the series 'mm:
page_alloc: fixes for high atomic reserve caluculations'.
- Dmitry Rokosov has added to the samples/ dorectory some sample code
for a userspace memcg event listener application. See the series
'samples: introduce cgroup events listeners'.
- Some mapletree maintanance work from Liam Howlett in the series
'maple_tree: iterator state changes'.
- Nhat Pham has improved zswap's approach to writeback in the series
'workload-specific and memory pressure-driven zswap writeback'.
- DAMON/DAMOS feature and maintenance work from SeongJae Park in the
series
'mm/damon: let users feed and tame/auto-tune DAMOS'
'selftests/damon: add Python-written DAMON functionality tests'
'mm/damon: misc updates for 6.8'
- Yosry Ahmed has improved memcg's stats flushing in the series 'mm:
memcg: subtree stats flushing and thresholds'.
- In the series 'Multi-size THP for anonymous memory' Ryan Roberts
has added a runtime opt-in feature to transparent hugepages which
improves performance by allocating larger chunks of memory during
anonymous page faults.
- Matthew Wilcox has also contributed some cleanup and maintenance
work against eh buffer_head code int he series 'More buffer_head
cleanups'.
- Suren Baghdasaryan has done work on Andrea Arcangeli's series
'userfaultfd move option'. UFFDIO_MOVE permits userspace heap
compaction algorithms to move userspace's pages around rather than
UFFDIO_COPY'a alloc/copy/free.
- Stefan Roesch has developed a 'KSM Advisor', in the series 'mm/ksm:
Add ksm advisor'. This is a governor which tunes KSM's scanning
aggressiveness in response to userspace's current needs.
- Chengming Zhou has optimized zswap's temporary working memory use
in the series 'mm/zswap: dstmem reuse optimizations and cleanups'.
- Matthew Wilcox has performed some maintenance work on the writeback
code, both code and within filesystems. The series is 'Clean up the
writeback paths'.
- Andrey Konovalov has optimized KASAN's handling of alloc and free
stack traces for secondary-level allocators, in the series 'kasan:
save mempool stack traces'.
- Andrey also performed some KASAN maintenance work in the series
'kasan: assorted clean-ups'.
- David Hildenbrand has gone to town on the rmap code. Cleanups, more
pte batching, folio conversions and more. See the series 'mm/rmap:
interface overhaul'.
- Kinsey Ho has contributed some maintenance work on the MGLRU code
in the series 'mm/mglru: Kconfig cleanup'.
- Matthew Wilcox has contributed lruvec page accounting code cleanups
in the series 'Remove some lruvec page accounting functions'"
* tag 'mm-stable-2024-01-08-15-31' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (361 commits)
mm, treewide: rename MAX_ORDER to MAX_PAGE_ORDER
mm, treewide: introduce NR_PAGE_ORDERS
selftests/mm: add separate UFFDIO_MOVE test for PMD splitting
selftests/mm: skip test if application doesn't has root privileges
selftests/mm: conform test to TAP format output
selftests: mm: hugepage-mmap: conform to TAP format output
selftests/mm: gup_test: conform test to TAP format output
mm/selftests: hugepage-mremap: conform test to TAP format output
mm/vmstat: move pgdemote_* out of CONFIG_NUMA_BALANCING
mm: zsmalloc: return -ENOSPC rather than -EINVAL in zs_malloc while size is too large
mm/memcontrol: remove __mod_lruvec_page_state()
mm/khugepaged: use a folio more in collapse_file()
slub: use a folio in __kmalloc_large_node
slub: use folio APIs in free_large_kmalloc()
slub: use alloc_pages_node() in alloc_slab_page()
mm: remove inc/dec lruvec page state functions
mm: ratelimit stat flush from workingset shrinker
kasan: stop leaking stack trace handles
mm/mglru: remove CONFIG_TRANSPARENT_HUGEPAGE
mm/mglru: add dummy pmd_dirty()
...
2024-01-09 11:18:47 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-10-03 16:57:59 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-05-27 11:01:28 +02:00
|
|
|
|
2023-10-03 16:57:59 +02:00
|
|
|
|
2024-05-27 11:01:28 +02:00
|
|
|
|
2023-10-03 16:57:59 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-05-27 11:01:28 +02:00
|
|
|
|
2023-10-03 16:57:59 +02:00
|
|
|
|
2024-05-27 11:01:28 +02:00
|
|
|
|
2023-10-03 16:57:59 +02:00
|
|
|
|
2024-05-27 11:01:28 +02:00
|
|
|
|
2023-10-03 16:57:59 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-05-27 11:01:28 +02:00
|
|
|
|
2023-10-03 16:57:59 +02:00
|
|
|
|
|
|
|
|
|
2024-07-01 12:12:59 -07:00
|
|
|
|
2023-10-03 16:57:59 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-05-27 11:01:28 +02:00
|
|
|
|
2023-10-03 16:57:59 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-07-01 12:12:59 -07:00
|
|
|
|
2023-10-03 16:57:59 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-07-01 12:12:59 -07:00
|
|
|
|
2023-10-03 16:57:59 +02:00
|
|
|
|
2024-07-01 12:12:59 -07:00
|
|
|
|
2023-10-03 16:57:59 +02:00
|
|
|
|
2024-03-21 09:36:47 -07:00
|
|
|
|
2023-10-03 16:57:59 +02:00
|
|
|
|
2024-03-21 09:36:47 -07:00
|
|
|
|
2023-10-03 16:57:59 +02:00
|
|
|
|
2024-07-01 12:12:59 -07:00
|
|
|
|
2023-10-03 16:57:59 +02:00
|
|
|
|
2024-03-21 09:36:47 -07:00
|
|
|
|
2023-10-03 16:57:59 +02:00
|
|
|
|
2024-07-01 12:12:59 -07:00
|
|
|
|
|
|
|
|
|
2023-10-03 16:57:59 +02:00
|
|
|
|
2024-07-01 12:12:59 -07:00
|
|
|
|
2023-10-03 16:57:59 +02:00
|
|
|
|
|
|
|
|
|
2024-07-01 12:12:59 -07:00
|
|
|
|
2023-10-03 16:57:59 +02:00
|
|
|
|
2024-05-27 11:01:28 +02:00
|
|
|
|
2023-10-03 16:57:59 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-05-27 11:01:28 +02:00
|
|
|
|
2023-10-03 16:57:59 +02:00
|
|
|
|
2024-05-27 11:01:28 +02:00
|
|
|
|
|
|
|
|
|
2023-10-03 16:57:59 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-05-27 11:01:28 +02:00
|
|
|
|
2023-10-03 16:57:59 +02:00
|
|
|
|
2022-11-21 16:06:38 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2015-02-10 14:09:37 -08:00
|
|
|
|
2007-05-10 03:15:16 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2007-05-10 03:15:16 -07:00
|
|
|
|
2021-11-15 16:55:15 +01:00
|
|
|
|
2007-05-10 03:15:16 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2015-11-20 15:57:46 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
2011-06-01 12:25:52 -05:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2011-06-01 12:25:52 -05:00
|
|
|
|
|
|
|
|
|
treewide: Remove uninitialized_var() usage
Using uninitialized_var() is dangerous as it papers over real bugs[1]
(or can in the future), and suppresses unrelated compiler warnings
(e.g. "unused variable"). If the compiler thinks it is uninitialized,
either simply initialize the variable or make compiler changes.
In preparation for removing[2] the[3] macro[4], remove all remaining
needless uses with the following script:
git grep '\buninitialized_var\b' | cut -d: -f1 | sort -u | \
xargs perl -pi -e \
's/\buninitialized_var\(([^\)]+)\)/\1/g;
s:\s*/\* (GCC be quiet|to make compiler happy) \*/$::g;'
drivers/video/fbdev/riva/riva_hw.c was manually tweaked to avoid
pathological white-space.
No outstanding warnings were found building allmodconfig with GCC 9.3.0
for x86_64, i386, arm64, arm, powerpc, powerpc64le, s390x, mips, sparc64,
alpha, and m68k.
[1] https://lore.kernel.org/lkml/20200603174714.192027-1-glider@google.com/
[2] https://lore.kernel.org/lkml/CA+55aFw+Vbj0i=1TGqCR5vQkCzWJ0QxK6CernOU6eedsudAixw@mail.gmail.com/
[3] https://lore.kernel.org/lkml/CA+55aFwgbgqhbp1fkxvRKEpzyR5J8n1vKT1VZdz9knmPuXhOeg@mail.gmail.com/
[4] https://lore.kernel.org/lkml/CA+55aFz2500WfbKXAx8s67wrm9=yVJu65TpLgN_ybYNv0VEOKA@mail.gmail.com/
Reviewed-by: Leon Romanovsky <leonro@mellanox.com> # drivers/infiniband and mlx4/mlx5
Acked-by: Jason Gunthorpe <jgg@mellanox.com> # IB
Acked-by: Kalle Valo <kvalo@codeaurora.org> # wireless drivers
Reviewed-by: Chao Yu <yuchao0@huawei.com> # erofs
Signed-off-by: Kees Cook <keescook@chromium.org>
2020-06-03 13:09:38 -07:00
|
|
|
|
2023-11-02 03:23:25 +00:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2011-02-25 11:38:54 -06:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2022-11-15 18:14:31 +01:00
|
|
|
|
2022-11-21 16:06:38 +01:00
|
|
|
|
2011-06-01 12:25:55 -05:00
|
|
|
|
mm/slub: restrict sysfs validation to debug caches and make it safe
Rongwei Wang reports [1] that cache validation triggered by writing to
/sys/kernel/slab/<cache>/validate is racy against normal cache
operations (e.g. freeing) in a way that can cause false positive
inconsistency reports for caches with debugging enabled. The problem is
that debugging actions that mark object free or active and actual
freelist operations are not atomic, and the validation can see an
inconsistent state.
For caches that do or don't have debugging enabled, additional races
involving n->nr_slabs are possible that result in false reports of wrong
slab counts.
This patch attempts to solve these issues while not adding overhead to
normal (especially fastpath) operations for caches that do not have
debugging enabled. Such overhead would not be justified to make possible
userspace-triggered validation safe. Instead, disable the validation for
caches that don't have debugging enabled and make their sysfs validate
handler return -EINVAL.
For caches that do have debugging enabled, we can instead extend the
existing approach of not using percpu freelists to force all alloc/free
operations to the slow paths where debugging flags is checked and acted
upon. There can adjust the debug-specific paths to increase n->list_lock
coverage against concurrent validation as necessary.
The processing on free in free_debug_processing() already happens under
n->list_lock so we can extend it to actually do the freeing as well and
thus make it atomic against concurrent validation. As observed by
Hyeonggon Yoo, we do not really need to take slab_lock() anymore here
because all paths we could race with are protected by n->list_lock under
the new scheme, so drop its usage here.
The processing on alloc in alloc_debug_processing() currently doesn't
take any locks, but we have to first allocate the object from a slab on
the partial list (as debugging caches have no percpu slabs) and thus
take the n->list_lock anyway. Add a function alloc_single_from_partial()
that grabs just the allocated object instead of the whole freelist, and
does the debug processing. The n->list_lock coverage again makes it
atomic against validation and it is also ultimately more efficient than
the current grabbing of freelist immediately followed by slab
deactivation.
To prevent races on n->nr_slabs updates, make sure that for caches with
debugging enabled, inc_slabs_node() or dec_slabs_node() is called under
n->list_lock. When allocating a new slab for a debug cache, handle the
allocation by a new function alloc_single_from_new_slab() instead of the
current forced deactivation path.
Neither of these changes affect the fast paths at all. The changes in
slow paths are negligible for non-debug caches.
[1] https://lore.kernel.org/all/20220529081535.69275-1-rongwei.wang@linux.alibaba.com/
Reported-by: Rongwei Wang <rongwei.wang@linux.alibaba.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
2022-08-23 19:03:57 +02:00
|
|
|
|
2008-02-15 23:45:26 -08:00
|
|
|
|
2011-06-01 12:25:52 -05:00
|
|
|
|
slub: remove one code path and reduce lock contention in __slab_free()
When we try to free object, there is some of case that we need
to take a node lock. This is the necessary step for preventing a race.
After taking a lock, then we try to cmpxchg_double_slab().
But, there is a possible scenario that cmpxchg_double_slab() is failed
with taking a lock. Following example explains it.
CPU A CPU B
need lock
... need lock
... lock!!
lock..but spin free success
spin... unlock
lock!!
free fail
In this case, retry with taking a lock is occured in CPU A.
I think that in this case for CPU A,
"release a lock first, and re-take a lock if necessary" is preferable way.
There are two reasons for this.
First, this makes __slab_free()'s logic somehow simple.
With this patch, 'was_frozen = 1' is "always" handled without taking a lock.
So we can remove one code path.
Second, it may reduce lock contention.
When we do retrying, status of slab is already changed,
so we don't need a lock anymore in almost every case.
"release a lock first, and re-take a lock if necessary" policy is
helpful to this.
Signed-off-by: Joonsoo Kim <js1304@gmail.com>
Acked-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Pekka Enberg <penberg@kernel.org>
2012-08-16 00:02:40 +09:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
|
|
|
|
|
2015-11-20 15:57:46 -08:00
|
|
|
|
2011-06-01 12:25:52 -05:00
|
|
|
|
|
|
|
|
|
2015-11-20 15:57:46 -08:00
|
|
|
|
slub: remove one code path and reduce lock contention in __slab_free()
When we try to free object, there is some of case that we need
to take a node lock. This is the necessary step for preventing a race.
After taking a lock, then we try to cmpxchg_double_slab().
But, there is a possible scenario that cmpxchg_double_slab() is failed
with taking a lock. Following example explains it.
CPU A CPU B
need lock
... need lock
... lock!!
lock..but spin free success
spin... unlock
lock!!
free fail
In this case, retry with taking a lock is occured in CPU A.
I think that in this case for CPU A,
"release a lock first, and re-take a lock if necessary" is preferable way.
There are two reasons for this.
First, this makes __slab_free()'s logic somehow simple.
With this patch, 'was_frozen = 1' is "always" handled without taking a lock.
So we can remove one code path.
Second, it may reduce lock contention.
When we do retrying, status of slab is already changed,
so we don't need a lock anymore in almost every case.
"release a lock first, and re-take a lock if necessary" policy is
helpful to this.
Signed-off-by: Joonsoo Kim <js1304@gmail.com>
Acked-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Pekka Enberg <penberg@kernel.org>
2012-08-16 00:02:40 +09:00
|
|
|
|
2023-11-02 03:23:27 +00:00
|
|
|
|
|
|
|
|
|
2011-08-09 16:12:27 -05:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2011-08-09 16:12:27 -05:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-11-02 03:23:25 +00:00
|
|
|
|
2011-08-09 16:12:27 -05:00
|
|
|
|
2011-06-01 12:25:52 -05:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2023-05-31 15:08:43 +02:00
|
|
|
|
2011-06-01 12:25:52 -05:00
|
|
|
|
2015-11-20 15:57:46 -08:00
|
|
|
|
2011-06-01 12:25:52 -05:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2011-06-01 12:25:52 -05:00
|
|
|
|
2011-08-09 16:12:27 -05:00
|
|
|
|
2020-10-13 16:48:40 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-11-02 03:23:27 +00:00
|
|
|
|
2020-10-13 16:48:40 -07:00
|
|
|
|
2023-11-02 03:23:27 +00:00
|
|
|
|
2020-10-13 16:48:40 -07:00
|
|
|
|
|
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2012-02-03 23:34:56 +08:00
|
|
|
|
|
|
|
|
|
2020-10-13 16:48:40 -07:00
|
|
|
|
2014-12-10 15:42:13 -08:00
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2023-11-02 03:23:25 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2014-07-02 15:22:35 -07:00
|
|
|
|
slub: remove one code path and reduce lock contention in __slab_free()
When we try to free object, there is some of case that we need
to take a node lock. This is the necessary step for preventing a race.
After taking a lock, then we try to cmpxchg_double_slab().
But, there is a possible scenario that cmpxchg_double_slab() is failed
with taking a lock. Following example explains it.
CPU A CPU B
need lock
... need lock
... lock!!
lock..but spin free success
spin... unlock
lock!!
free fail
In this case, retry with taking a lock is occured in CPU A.
I think that in this case for CPU A,
"release a lock first, and re-take a lock if necessary" is preferable way.
There are two reasons for this.
First, this makes __slab_free()'s logic somehow simple.
With this patch, 'was_frozen = 1' is "always" handled without taking a lock.
So we can remove one code path.
Second, it may reduce lock contention.
When we do retrying, status of slab is already changed,
so we don't need a lock anymore in almost every case.
"release a lock first, and re-take a lock if necessary" policy is
helpful to this.
Signed-off-by: Joonsoo Kim <js1304@gmail.com>
Acked-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Pekka Enberg <penberg@kernel.org>
2012-08-16 00:02:40 +09:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
slub: remove one code path and reduce lock contention in __slab_free()
When we try to free object, there is some of case that we need
to take a node lock. This is the necessary step for preventing a race.
After taking a lock, then we try to cmpxchg_double_slab().
But, there is a possible scenario that cmpxchg_double_slab() is failed
with taking a lock. Following example explains it.
CPU A CPU B
need lock
... need lock
... lock!!
lock..but spin free success
spin... unlock
lock!!
free fail
In this case, retry with taking a lock is occured in CPU A.
I think that in this case for CPU A,
"release a lock first, and re-take a lock if necessary" is preferable way.
There are two reasons for this.
First, this makes __slab_free()'s logic somehow simple.
With this patch, 'was_frozen = 1' is "always" handled without taking a lock.
So we can remove one code path.
Second, it may reduce lock contention.
When we do retrying, status of slab is already changed,
so we don't need a lock anymore in almost every case.
"release a lock first, and re-take a lock if necessary" policy is
helpful to this.
Signed-off-by: Joonsoo Kim <js1304@gmail.com>
Acked-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Pekka Enberg <penberg@kernel.org>
2012-08-16 00:02:40 +09:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-06-19 14:05:52 +09:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
slub: remove one code path and reduce lock contention in __slab_free()
When we try to free object, there is some of case that we need
to take a node lock. This is the necessary step for preventing a race.
After taking a lock, then we try to cmpxchg_double_slab().
But, there is a possible scenario that cmpxchg_double_slab() is failed
with taking a lock. Following example explains it.
CPU A CPU B
need lock
... need lock
... lock!!
lock..but spin free success
spin... unlock
lock!!
free fail
In this case, retry with taking a lock is occured in CPU A.
I think that in this case for CPU A,
"release a lock first, and re-take a lock if necessary" is preferable way.
There are two reasons for this.
First, this makes __slab_free()'s logic somehow simple.
With this patch, 'was_frozen = 1' is "always" handled without taking a lock.
So we can remove one code path.
Second, it may reduce lock contention.
When we do retrying, status of slab is already changed,
so we don't need a lock anymore in almost every case.
"release a lock first, and re-take a lock if necessary" policy is
helpful to this.
Signed-off-by: Joonsoo Kim <js1304@gmail.com>
Acked-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Pekka Enberg <penberg@kernel.org>
2012-08-16 00:02:40 +09:00
|
|
|
|
2008-02-07 17:47:41 -08:00
|
|
|
|
2011-06-01 12:25:55 -05:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-03-01 13:40:44 -08:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2011-08-08 11:16:56 -05:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2009-12-18 16:26:23 -06:00
|
|
|
|
2014-01-10 13:23:49 +01:00
|
|
|
|
2011-06-01 12:25:52 -05:00
|
|
|
|
2011-06-01 12:25:55 -05:00
|
|
|
|
2009-12-18 16:26:23 -06:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
2022-11-15 18:14:31 +01:00
|
|
|
|
2007-05-10 03:15:16 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-11-20 15:57:46 -08:00
|
|
|
|
|
|
|
|
|
2021-11-15 16:55:15 +01:00
|
|
|
|
2015-11-20 15:57:46 -08:00
|
|
|
|
2007-05-10 03:15:16 -07:00
|
|
|
|
2016-07-28 15:49:07 -07:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2016-07-28 15:49:07 -07:00
|
|
|
|
2007-05-10 03:15:16 -07:00
|
|
|
|
2007-10-16 01:26:05 -07:00
|
|
|
|
2011-02-25 11:38:54 -06:00
|
|
|
|
2022-08-25 09:51:36 +02:00
|
|
|
|
2020-08-06 23:20:56 -07:00
|
|
|
|
2011-03-15 12:45:21 -05:00
|
|
|
|
2011-02-25 11:38:54 -06:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-09-04 15:45:31 -07:00
|
|
|
|
2011-02-25 11:38:54 -06:00
|
|
|
|
2021-05-18 02:01:39 +02:00
|
|
|
|
|
|
|
|
|
2010-08-20 12:37:16 -05:00
|
|
|
|
2024-03-25 12:22:17 +00:00
|
|
|
|
2015-02-10 14:09:32 -08:00
|
|
|
|
2010-08-20 12:37:16 -05:00
|
|
|
|
2022-08-25 09:51:36 +02:00
|
|
|
|
2023-11-03 20:24:51 +01:00
|
|
|
|
2022-08-25 09:51:36 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-03-17 11:04:09 -07:00
|
|
|
|
2023-11-03 20:24:51 +01:00
|
|
|
|
2011-02-25 11:38:54 -06:00
|
|
|
|
2023-05-31 15:08:43 +02:00
|
|
|
|
2011-02-25 11:38:54 -06:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-08-25 09:51:36 +02:00
|
|
|
|
|
|
|
|
|
2021-05-22 01:59:38 +02:00
|
|
|
|
|
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2021-05-22 01:59:38 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-11-03 20:24:51 +01:00
|
|
|
|
2021-05-22 01:59:38 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-08-25 09:51:36 +02:00
|
|
|
|
2023-08-07 20:50:44 +02:00
|
|
|
|
2007-05-10 03:15:16 -07:00
|
|
|
|
2022-11-15 18:14:31 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-11-03 20:24:51 +01:00
|
|
|
|
2022-11-15 18:14:31 +01:00
|
|
|
|
|
|
|
|
|
2007-05-10 03:15:16 -07:00
|
|
|
|
2023-11-03 20:24:51 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-03-21 09:36:45 -07:00
|
|
|
|
2023-11-03 20:24:51 +01:00
|
|
|
|
2024-08-09 17:36:56 +02:00
|
|
|
|
2023-11-03 20:24:51 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-07-01 11:31:15 -04:00
|
|
|
|
2024-03-26 11:37:38 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-08-09 17:36:56 +02:00
|
|
|
|
2024-03-26 11:37:38 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-11-03 20:24:51 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-07-28 15:49:07 -07:00
|
|
|
|
2022-04-29 20:30:44 +08:00
|
|
|
|
2024-03-21 09:36:45 -07:00
|
|
|
|
2016-07-28 15:49:07 -07:00
|
|
|
|
2018-04-10 16:30:31 -07:00
|
|
|
|
|
|
|
|
|
2016-07-28 15:49:07 -07:00
|
|
|
|
2023-10-27 12:34:18 +02:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2016-07-28 15:49:07 -07:00
|
|
|
|
|
|
|
|
|
2024-08-09 17:36:56 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-12-28 00:29:53 -08:00
|
|
|
|
2016-07-28 15:49:07 -07:00
|
|
|
|
|
|
|
|
|
2023-11-03 20:24:51 +01:00
|
|
|
|
2016-07-28 15:49:07 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-10-03 14:52:47 +02:00
|
|
|
|
2022-08-17 19:18:20 +09:00
|
|
|
|
2023-10-03 14:52:47 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-08-17 19:18:20 +09:00
|
|
|
|
|
|
|
|
|
2023-10-03 14:52:47 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-11-20 17:11:10 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
2012-12-18 14:22:46 -08:00
|
|
|
|
|
|
|
|
|
2012-09-04 23:06:14 +00:00
|
|
|
|
2022-08-17 19:18:24 +09:00
|
|
|
|
2023-11-03 20:24:51 +01:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-10-03 15:27:11 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Many singleton patches against the MM code. The patch series which
are included in this merge do the following:
- Peng Zhang has done some mapletree maintainance work in the
series
"maple_tree: add mt_free_one() and mt_attr() helpers"
"Some cleanups of maple tree"
- In the series "mm: use memmap_on_memory semantics for dax/kmem"
Vishal Verma has altered the interworking between memory-hotplug
and dax/kmem so that newly added 'device memory' can more easily
have its memmap placed within that newly added memory.
- Matthew Wilcox continues folio-related work (including a few
fixes) in the patch series
"Add folio_zero_tail() and folio_fill_tail()"
"Make folio_start_writeback return void"
"Fix fault handler's handling of poisoned tail pages"
"Convert aops->error_remove_page to ->error_remove_folio"
"Finish two folio conversions"
"More swap folio conversions"
- Kefeng Wang has also contributed folio-related work in the series
"mm: cleanup and use more folio in page fault"
- Jim Cromie has improved the kmemleak reporting output in the
series "tweak kmemleak report format".
- In the series "stackdepot: allow evicting stack traces" Andrey
Konovalov to permits clients (in this case KASAN) to cause
eviction of no longer needed stack traces.
- Charan Teja Kalla has fixed some accounting issues in the page
allocator's atomic reserve calculations in the series "mm:
page_alloc: fixes for high atomic reserve caluculations".
- Dmitry Rokosov has added to the samples/ dorectory some sample
code for a userspace memcg event listener application. See the
series "samples: introduce cgroup events listeners".
- Some mapletree maintanance work from Liam Howlett in the series
"maple_tree: iterator state changes".
- Nhat Pham has improved zswap's approach to writeback in the
series "workload-specific and memory pressure-driven zswap
writeback".
- DAMON/DAMOS feature and maintenance work from SeongJae Park in
the series
"mm/damon: let users feed and tame/auto-tune DAMOS"
"selftests/damon: add Python-written DAMON functionality tests"
"mm/damon: misc updates for 6.8"
- Yosry Ahmed has improved memcg's stats flushing in the series
"mm: memcg: subtree stats flushing and thresholds".
- In the series "Multi-size THP for anonymous memory" Ryan Roberts
has added a runtime opt-in feature to transparent hugepages which
improves performance by allocating larger chunks of memory during
anonymous page faults.
- Matthew Wilcox has also contributed some cleanup and maintenance
work against eh buffer_head code int he series "More buffer_head
cleanups".
- Suren Baghdasaryan has done work on Andrea Arcangeli's series
"userfaultfd move option". UFFDIO_MOVE permits userspace heap
compaction algorithms to move userspace's pages around rather than
UFFDIO_COPY'a alloc/copy/free.
- Stefan Roesch has developed a "KSM Advisor", in the series
"mm/ksm: Add ksm advisor". This is a governor which tunes KSM's
scanning aggressiveness in response to userspace's current needs.
- Chengming Zhou has optimized zswap's temporary working memory
use in the series "mm/zswap: dstmem reuse optimizations and
cleanups".
- Matthew Wilcox has performed some maintenance work on the
writeback code, both code and within filesystems. The series is
"Clean up the writeback paths".
- Andrey Konovalov has optimized KASAN's handling of alloc and
free stack traces for secondary-level allocators, in the series
"kasan: save mempool stack traces".
- Andrey also performed some KASAN maintenance work in the series
"kasan: assorted clean-ups".
- David Hildenbrand has gone to town on the rmap code. Cleanups,
more pte batching, folio conversions and more. See the series
"mm/rmap: interface overhaul".
- Kinsey Ho has contributed some maintenance work on the MGLRU
code in the series "mm/mglru: Kconfig cleanup".
- Matthew Wilcox has contributed lruvec page accounting code
cleanups in the series "Remove some lruvec page accounting
functions".
-----BEGIN PGP SIGNATURE-----
iHUEABYIAB0WIQTTMBEPP41GrTpTJgfdBJ7gKXxAjgUCZZyF2wAKCRDdBJ7gKXxA
jjWjAP42LHvGSjp5M+Rs2rKFL0daBQsrlvy6/jCHUequSdWjSgEAmOx7bc5fbF27
Oa8+DxGM9C+fwqZ/7YxU2w/WuUmLPgU=
=0NHs
-----END PGP SIGNATURE-----
Merge tag 'mm-stable-2024-01-08-15-31' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Pull MM updates from Andrew Morton:
"Many singleton patches against the MM code. The patch series which are
included in this merge do the following:
- Peng Zhang has done some mapletree maintainance work in the series
'maple_tree: add mt_free_one() and mt_attr() helpers'
'Some cleanups of maple tree'
- In the series 'mm: use memmap_on_memory semantics for dax/kmem'
Vishal Verma has altered the interworking between memory-hotplug
and dax/kmem so that newly added 'device memory' can more easily
have its memmap placed within that newly added memory.
- Matthew Wilcox continues folio-related work (including a few fixes)
in the patch series
'Add folio_zero_tail() and folio_fill_tail()'
'Make folio_start_writeback return void'
'Fix fault handler's handling of poisoned tail pages'
'Convert aops->error_remove_page to ->error_remove_folio'
'Finish two folio conversions'
'More swap folio conversions'
- Kefeng Wang has also contributed folio-related work in the series
'mm: cleanup and use more folio in page fault'
- Jim Cromie has improved the kmemleak reporting output in the series
'tweak kmemleak report format'.
- In the series 'stackdepot: allow evicting stack traces' Andrey
Konovalov to permits clients (in this case KASAN) to cause eviction
of no longer needed stack traces.
- Charan Teja Kalla has fixed some accounting issues in the page
allocator's atomic reserve calculations in the series 'mm:
page_alloc: fixes for high atomic reserve caluculations'.
- Dmitry Rokosov has added to the samples/ dorectory some sample code
for a userspace memcg event listener application. See the series
'samples: introduce cgroup events listeners'.
- Some mapletree maintanance work from Liam Howlett in the series
'maple_tree: iterator state changes'.
- Nhat Pham has improved zswap's approach to writeback in the series
'workload-specific and memory pressure-driven zswap writeback'.
- DAMON/DAMOS feature and maintenance work from SeongJae Park in the
series
'mm/damon: let users feed and tame/auto-tune DAMOS'
'selftests/damon: add Python-written DAMON functionality tests'
'mm/damon: misc updates for 6.8'
- Yosry Ahmed has improved memcg's stats flushing in the series 'mm:
memcg: subtree stats flushing and thresholds'.
- In the series 'Multi-size THP for anonymous memory' Ryan Roberts
has added a runtime opt-in feature to transparent hugepages which
improves performance by allocating larger chunks of memory during
anonymous page faults.
- Matthew Wilcox has also contributed some cleanup and maintenance
work against eh buffer_head code int he series 'More buffer_head
cleanups'.
- Suren Baghdasaryan has done work on Andrea Arcangeli's series
'userfaultfd move option'. UFFDIO_MOVE permits userspace heap
compaction algorithms to move userspace's pages around rather than
UFFDIO_COPY'a alloc/copy/free.
- Stefan Roesch has developed a 'KSM Advisor', in the series 'mm/ksm:
Add ksm advisor'. This is a governor which tunes KSM's scanning
aggressiveness in response to userspace's current needs.
- Chengming Zhou has optimized zswap's temporary working memory use
in the series 'mm/zswap: dstmem reuse optimizations and cleanups'.
- Matthew Wilcox has performed some maintenance work on the writeback
code, both code and within filesystems. The series is 'Clean up the
writeback paths'.
- Andrey Konovalov has optimized KASAN's handling of alloc and free
stack traces for secondary-level allocators, in the series 'kasan:
save mempool stack traces'.
- Andrey also performed some KASAN maintenance work in the series
'kasan: assorted clean-ups'.
- David Hildenbrand has gone to town on the rmap code. Cleanups, more
pte batching, folio conversions and more. See the series 'mm/rmap:
interface overhaul'.
- Kinsey Ho has contributed some maintenance work on the MGLRU code
in the series 'mm/mglru: Kconfig cleanup'.
- Matthew Wilcox has contributed lruvec page accounting code cleanups
in the series 'Remove some lruvec page accounting functions'"
* tag 'mm-stable-2024-01-08-15-31' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (361 commits)
mm, treewide: rename MAX_ORDER to MAX_PAGE_ORDER
mm, treewide: introduce NR_PAGE_ORDERS
selftests/mm: add separate UFFDIO_MOVE test for PMD splitting
selftests/mm: skip test if application doesn't has root privileges
selftests/mm: conform test to TAP format output
selftests: mm: hugepage-mmap: conform to TAP format output
selftests/mm: gup_test: conform test to TAP format output
mm/selftests: hugepage-mremap: conform test to TAP format output
mm/vmstat: move pgdemote_* out of CONFIG_NUMA_BALANCING
mm: zsmalloc: return -ENOSPC rather than -EINVAL in zs_malloc while size is too large
mm/memcontrol: remove __mod_lruvec_page_state()
mm/khugepaged: use a folio more in collapse_file()
slub: use a folio in __kmalloc_large_node
slub: use folio APIs in free_large_kmalloc()
slub: use alloc_pages_node() in alloc_slab_page()
mm: remove inc/dec lruvec page state functions
mm: ratelimit stat flush from workingset shrinker
kasan: stop leaking stack trace handles
mm/mglru: remove CONFIG_TRANSPARENT_HUGEPAGE
mm/mglru: add dummy pmd_dirty()
...
2024-01-09 11:18:47 -08:00
|
|
|
|
2023-10-03 15:27:11 +02:00
|
|
|
|
Many singleton patches against the MM code. The patch series which
are included in this merge do the following:
- Peng Zhang has done some mapletree maintainance work in the
series
"maple_tree: add mt_free_one() and mt_attr() helpers"
"Some cleanups of maple tree"
- In the series "mm: use memmap_on_memory semantics for dax/kmem"
Vishal Verma has altered the interworking between memory-hotplug
and dax/kmem so that newly added 'device memory' can more easily
have its memmap placed within that newly added memory.
- Matthew Wilcox continues folio-related work (including a few
fixes) in the patch series
"Add folio_zero_tail() and folio_fill_tail()"
"Make folio_start_writeback return void"
"Fix fault handler's handling of poisoned tail pages"
"Convert aops->error_remove_page to ->error_remove_folio"
"Finish two folio conversions"
"More swap folio conversions"
- Kefeng Wang has also contributed folio-related work in the series
"mm: cleanup and use more folio in page fault"
- Jim Cromie has improved the kmemleak reporting output in the
series "tweak kmemleak report format".
- In the series "stackdepot: allow evicting stack traces" Andrey
Konovalov to permits clients (in this case KASAN) to cause
eviction of no longer needed stack traces.
- Charan Teja Kalla has fixed some accounting issues in the page
allocator's atomic reserve calculations in the series "mm:
page_alloc: fixes for high atomic reserve caluculations".
- Dmitry Rokosov has added to the samples/ dorectory some sample
code for a userspace memcg event listener application. See the
series "samples: introduce cgroup events listeners".
- Some mapletree maintanance work from Liam Howlett in the series
"maple_tree: iterator state changes".
- Nhat Pham has improved zswap's approach to writeback in the
series "workload-specific and memory pressure-driven zswap
writeback".
- DAMON/DAMOS feature and maintenance work from SeongJae Park in
the series
"mm/damon: let users feed and tame/auto-tune DAMOS"
"selftests/damon: add Python-written DAMON functionality tests"
"mm/damon: misc updates for 6.8"
- Yosry Ahmed has improved memcg's stats flushing in the series
"mm: memcg: subtree stats flushing and thresholds".
- In the series "Multi-size THP for anonymous memory" Ryan Roberts
has added a runtime opt-in feature to transparent hugepages which
improves performance by allocating larger chunks of memory during
anonymous page faults.
- Matthew Wilcox has also contributed some cleanup and maintenance
work against eh buffer_head code int he series "More buffer_head
cleanups".
- Suren Baghdasaryan has done work on Andrea Arcangeli's series
"userfaultfd move option". UFFDIO_MOVE permits userspace heap
compaction algorithms to move userspace's pages around rather than
UFFDIO_COPY'a alloc/copy/free.
- Stefan Roesch has developed a "KSM Advisor", in the series
"mm/ksm: Add ksm advisor". This is a governor which tunes KSM's
scanning aggressiveness in response to userspace's current needs.
- Chengming Zhou has optimized zswap's temporary working memory
use in the series "mm/zswap: dstmem reuse optimizations and
cleanups".
- Matthew Wilcox has performed some maintenance work on the
writeback code, both code and within filesystems. The series is
"Clean up the writeback paths".
- Andrey Konovalov has optimized KASAN's handling of alloc and
free stack traces for secondary-level allocators, in the series
"kasan: save mempool stack traces".
- Andrey also performed some KASAN maintenance work in the series
"kasan: assorted clean-ups".
- David Hildenbrand has gone to town on the rmap code. Cleanups,
more pte batching, folio conversions and more. See the series
"mm/rmap: interface overhaul".
- Kinsey Ho has contributed some maintenance work on the MGLRU
code in the series "mm/mglru: Kconfig cleanup".
- Matthew Wilcox has contributed lruvec page accounting code
cleanups in the series "Remove some lruvec page accounting
functions".
-----BEGIN PGP SIGNATURE-----
iHUEABYIAB0WIQTTMBEPP41GrTpTJgfdBJ7gKXxAjgUCZZyF2wAKCRDdBJ7gKXxA
jjWjAP42LHvGSjp5M+Rs2rKFL0daBQsrlvy6/jCHUequSdWjSgEAmOx7bc5fbF27
Oa8+DxGM9C+fwqZ/7YxU2w/WuUmLPgU=
=0NHs
-----END PGP SIGNATURE-----
Merge tag 'mm-stable-2024-01-08-15-31' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Pull MM updates from Andrew Morton:
"Many singleton patches against the MM code. The patch series which are
included in this merge do the following:
- Peng Zhang has done some mapletree maintainance work in the series
'maple_tree: add mt_free_one() and mt_attr() helpers'
'Some cleanups of maple tree'
- In the series 'mm: use memmap_on_memory semantics for dax/kmem'
Vishal Verma has altered the interworking between memory-hotplug
and dax/kmem so that newly added 'device memory' can more easily
have its memmap placed within that newly added memory.
- Matthew Wilcox continues folio-related work (including a few fixes)
in the patch series
'Add folio_zero_tail() and folio_fill_tail()'
'Make folio_start_writeback return void'
'Fix fault handler's handling of poisoned tail pages'
'Convert aops->error_remove_page to ->error_remove_folio'
'Finish two folio conversions'
'More swap folio conversions'
- Kefeng Wang has also contributed folio-related work in the series
'mm: cleanup and use more folio in page fault'
- Jim Cromie has improved the kmemleak reporting output in the series
'tweak kmemleak report format'.
- In the series 'stackdepot: allow evicting stack traces' Andrey
Konovalov to permits clients (in this case KASAN) to cause eviction
of no longer needed stack traces.
- Charan Teja Kalla has fixed some accounting issues in the page
allocator's atomic reserve calculations in the series 'mm:
page_alloc: fixes for high atomic reserve caluculations'.
- Dmitry Rokosov has added to the samples/ dorectory some sample code
for a userspace memcg event listener application. See the series
'samples: introduce cgroup events listeners'.
- Some mapletree maintanance work from Liam Howlett in the series
'maple_tree: iterator state changes'.
- Nhat Pham has improved zswap's approach to writeback in the series
'workload-specific and memory pressure-driven zswap writeback'.
- DAMON/DAMOS feature and maintenance work from SeongJae Park in the
series
'mm/damon: let users feed and tame/auto-tune DAMOS'
'selftests/damon: add Python-written DAMON functionality tests'
'mm/damon: misc updates for 6.8'
- Yosry Ahmed has improved memcg's stats flushing in the series 'mm:
memcg: subtree stats flushing and thresholds'.
- In the series 'Multi-size THP for anonymous memory' Ryan Roberts
has added a runtime opt-in feature to transparent hugepages which
improves performance by allocating larger chunks of memory during
anonymous page faults.
- Matthew Wilcox has also contributed some cleanup and maintenance
work against eh buffer_head code int he series 'More buffer_head
cleanups'.
- Suren Baghdasaryan has done work on Andrea Arcangeli's series
'userfaultfd move option'. UFFDIO_MOVE permits userspace heap
compaction algorithms to move userspace's pages around rather than
UFFDIO_COPY'a alloc/copy/free.
- Stefan Roesch has developed a 'KSM Advisor', in the series 'mm/ksm:
Add ksm advisor'. This is a governor which tunes KSM's scanning
aggressiveness in response to userspace's current needs.
- Chengming Zhou has optimized zswap's temporary working memory use
in the series 'mm/zswap: dstmem reuse optimizations and cleanups'.
- Matthew Wilcox has performed some maintenance work on the writeback
code, both code and within filesystems. The series is 'Clean up the
writeback paths'.
- Andrey Konovalov has optimized KASAN's handling of alloc and free
stack traces for secondary-level allocators, in the series 'kasan:
save mempool stack traces'.
- Andrey also performed some KASAN maintenance work in the series
'kasan: assorted clean-ups'.
- David Hildenbrand has gone to town on the rmap code. Cleanups, more
pte batching, folio conversions and more. See the series 'mm/rmap:
interface overhaul'.
- Kinsey Ho has contributed some maintenance work on the MGLRU code
in the series 'mm/mglru: Kconfig cleanup'.
- Matthew Wilcox has contributed lruvec page accounting code cleanups
in the series 'Remove some lruvec page accounting functions'"
* tag 'mm-stable-2024-01-08-15-31' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (361 commits)
mm, treewide: rename MAX_ORDER to MAX_PAGE_ORDER
mm, treewide: introduce NR_PAGE_ORDERS
selftests/mm: add separate UFFDIO_MOVE test for PMD splitting
selftests/mm: skip test if application doesn't has root privileges
selftests/mm: conform test to TAP format output
selftests: mm: hugepage-mmap: conform to TAP format output
selftests/mm: gup_test: conform test to TAP format output
mm/selftests: hugepage-mremap: conform test to TAP format output
mm/vmstat: move pgdemote_* out of CONFIG_NUMA_BALANCING
mm: zsmalloc: return -ENOSPC rather than -EINVAL in zs_malloc while size is too large
mm/memcontrol: remove __mod_lruvec_page_state()
mm/khugepaged: use a folio more in collapse_file()
slub: use a folio in __kmalloc_large_node
slub: use folio APIs in free_large_kmalloc()
slub: use alloc_pages_node() in alloc_slab_page()
mm: remove inc/dec lruvec page state functions
mm: ratelimit stat flush from workingset shrinker
kasan: stop leaking stack trace handles
mm/mglru: remove CONFIG_TRANSPARENT_HUGEPAGE
mm/mglru: add dummy pmd_dirty()
...
2024-01-09 11:18:47 -08:00
|
|
|
|
2023-10-03 15:27:11 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-11-03 20:24:51 +01:00
|
|
|
|
2023-10-03 15:27:11 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-09-11 14:45:33 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-10-16 23:41:51 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-09-11 14:45:33 +08:00
|
|
|
|
2024-10-16 23:41:51 +08:00
|
|
|
|
|
|
|
|
|
2024-09-11 14:45:33 +08:00
|
|
|
|
2024-10-16 23:41:51 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-09-11 14:45:33 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-10-16 23:41:51 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-09-11 14:45:33 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-10-16 23:41:51 +08:00
|
|
|
|
2024-09-11 14:45:33 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-10-16 23:41:51 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-09-11 14:45:33 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-10-16 23:41:51 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-09-11 14:45:33 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
slub: optimize bulk slowpath free by detached freelist
This change focus on improving the speed of object freeing in the
"slowpath" of kmem_cache_free_bulk.
The calls slab_free (fastpath) and __slab_free (slowpath) have been
extended with support for bulk free, which amortize the overhead of
the (locked) cmpxchg_double.
To use the new bulking feature, we build what I call a detached
freelist. The detached freelist takes advantage of three properties:
1) the free function call owns the object that is about to be freed,
thus writing into this memory is synchronization-free.
2) many freelist's can co-exist side-by-side in the same slab-page
each with a separate head pointer.
3) it is the visibility of the head pointer that needs synchronization.
Given these properties, the brilliant part is that the detached
freelist can be constructed without any need for synchronization. The
freelist is constructed directly in the page objects, without any
synchronization needed. The detached freelist is allocated on the
stack of the function call kmem_cache_free_bulk. Thus, the freelist
head pointer is not visible to other CPUs.
All objects in a SLUB freelist must belong to the same slab-page.
Thus, constructing the detached freelist is about matching objects
that belong to the same slab-page. The bulk free array is scanned is
a progressive manor with a limited look-ahead facility.
Kmem debug support is handled in call of slab_free().
Notice kmem_cache_free_bulk no longer need to disable IRQs. This
only slowed down single free bulk with approx 3 cycles.
Performance data:
Benchmarked[1] obj size 256 bytes on CPU i7-4790K @ 4.00GHz
SLUB fastpath single object quick reuse: 47 cycles(tsc) 11.931 ns
To get stable and comparable numbers, the kernel have been booted with
"slab_merge" (this also improve performance for larger bulk sizes).
Performance data, compared against fallback bulking:
bulk - fallback bulk - improvement with this patch
1 - 62 cycles(tsc) 15.662 ns - 49 cycles(tsc) 12.407 ns- improved 21.0%
2 - 55 cycles(tsc) 13.935 ns - 30 cycles(tsc) 7.506 ns - improved 45.5%
3 - 53 cycles(tsc) 13.341 ns - 23 cycles(tsc) 5.865 ns - improved 56.6%
4 - 52 cycles(tsc) 13.081 ns - 20 cycles(tsc) 5.048 ns - improved 61.5%
8 - 50 cycles(tsc) 12.627 ns - 18 cycles(tsc) 4.659 ns - improved 64.0%
16 - 49 cycles(tsc) 12.412 ns - 17 cycles(tsc) 4.495 ns - improved 65.3%
30 - 49 cycles(tsc) 12.484 ns - 18 cycles(tsc) 4.533 ns - improved 63.3%
32 - 50 cycles(tsc) 12.627 ns - 18 cycles(tsc) 4.707 ns - improved 64.0%
34 - 96 cycles(tsc) 24.243 ns - 23 cycles(tsc) 5.976 ns - improved 76.0%
48 - 83 cycles(tsc) 20.818 ns - 21 cycles(tsc) 5.329 ns - improved 74.7%
64 - 74 cycles(tsc) 18.700 ns - 20 cycles(tsc) 5.127 ns - improved 73.0%
128 - 90 cycles(tsc) 22.734 ns - 27 cycles(tsc) 6.833 ns - improved 70.0%
158 - 99 cycles(tsc) 24.776 ns - 30 cycles(tsc) 7.583 ns - improved 69.7%
250 - 104 cycles(tsc) 26.089 ns - 37 cycles(tsc) 9.280 ns - improved 64.4%
Performance data, compared current in-kernel bulking:
bulk - curr in-kernel - improvement with this patch
1 - 46 cycles(tsc) - 49 cycles(tsc) - improved (cycles:-3) -6.5%
2 - 27 cycles(tsc) - 30 cycles(tsc) - improved (cycles:-3) -11.1%
3 - 21 cycles(tsc) - 23 cycles(tsc) - improved (cycles:-2) -9.5%
4 - 18 cycles(tsc) - 20 cycles(tsc) - improved (cycles:-2) -11.1%
8 - 17 cycles(tsc) - 18 cycles(tsc) - improved (cycles:-1) -5.9%
16 - 18 cycles(tsc) - 17 cycles(tsc) - improved (cycles: 1) 5.6%
30 - 18 cycles(tsc) - 18 cycles(tsc) - improved (cycles: 0) 0.0%
32 - 18 cycles(tsc) - 18 cycles(tsc) - improved (cycles: 0) 0.0%
34 - 78 cycles(tsc) - 23 cycles(tsc) - improved (cycles:55) 70.5%
48 - 60 cycles(tsc) - 21 cycles(tsc) - improved (cycles:39) 65.0%
64 - 49 cycles(tsc) - 20 cycles(tsc) - improved (cycles:29) 59.2%
128 - 69 cycles(tsc) - 27 cycles(tsc) - improved (cycles:42) 60.9%
158 - 79 cycles(tsc) - 30 cycles(tsc) - improved (cycles:49) 62.0%
250 - 86 cycles(tsc) - 37 cycles(tsc) - improved (cycles:49) 57.0%
Performance with normal SLUB merging is significantly slower for
larger bulking. This is believed to (primarily) be an effect of not
having to share the per-CPU data-structures, as tuning per-CPU size
can achieve similar performance.
bulk - slab_nomerge - normal SLUB merge
1 - 49 cycles(tsc) - 49 cycles(tsc) - merge slower with cycles:0
2 - 30 cycles(tsc) - 30 cycles(tsc) - merge slower with cycles:0
3 - 23 cycles(tsc) - 23 cycles(tsc) - merge slower with cycles:0
4 - 20 cycles(tsc) - 20 cycles(tsc) - merge slower with cycles:0
8 - 18 cycles(tsc) - 18 cycles(tsc) - merge slower with cycles:0
16 - 17 cycles(tsc) - 17 cycles(tsc) - merge slower with cycles:0
30 - 18 cycles(tsc) - 23 cycles(tsc) - merge slower with cycles:5
32 - 18 cycles(tsc) - 22 cycles(tsc) - merge slower with cycles:4
34 - 23 cycles(tsc) - 22 cycles(tsc) - merge slower with cycles:-1
48 - 21 cycles(tsc) - 22 cycles(tsc) - merge slower with cycles:1
64 - 20 cycles(tsc) - 48 cycles(tsc) - merge slower with cycles:28
128 - 27 cycles(tsc) - 57 cycles(tsc) - merge slower with cycles:30
158 - 30 cycles(tsc) - 59 cycles(tsc) - merge slower with cycles:29
250 - 37 cycles(tsc) - 56 cycles(tsc) - merge slower with cycles:19
Joint work with Alexander Duyck.
[1] https://github.com/netoptimizer/prototype-kernel/blob/master/kernel/mm/slab_bulk_test01.c
[akpm@linux-foundation.org: BUG_ON -> WARN_ON;return]
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Acked-by: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-11-20 15:57:49 -08:00
|
|
|
|
2021-10-04 14:45:58 +01:00
|
|
|
|
slub: optimize bulk slowpath free by detached freelist
This change focus on improving the speed of object freeing in the
"slowpath" of kmem_cache_free_bulk.
The calls slab_free (fastpath) and __slab_free (slowpath) have been
extended with support for bulk free, which amortize the overhead of
the (locked) cmpxchg_double.
To use the new bulking feature, we build what I call a detached
freelist. The detached freelist takes advantage of three properties:
1) the free function call owns the object that is about to be freed,
thus writing into this memory is synchronization-free.
2) many freelist's can co-exist side-by-side in the same slab-page
each with a separate head pointer.
3) it is the visibility of the head pointer that needs synchronization.
Given these properties, the brilliant part is that the detached
freelist can be constructed without any need for synchronization. The
freelist is constructed directly in the page objects, without any
synchronization needed. The detached freelist is allocated on the
stack of the function call kmem_cache_free_bulk. Thus, the freelist
head pointer is not visible to other CPUs.
All objects in a SLUB freelist must belong to the same slab-page.
Thus, constructing the detached freelist is about matching objects
that belong to the same slab-page. The bulk free array is scanned is
a progressive manor with a limited look-ahead facility.
Kmem debug support is handled in call of slab_free().
Notice kmem_cache_free_bulk no longer need to disable IRQs. This
only slowed down single free bulk with approx 3 cycles.
Performance data:
Benchmarked[1] obj size 256 bytes on CPU i7-4790K @ 4.00GHz
SLUB fastpath single object quick reuse: 47 cycles(tsc) 11.931 ns
To get stable and comparable numbers, the kernel have been booted with
"slab_merge" (this also improve performance for larger bulk sizes).
Performance data, compared against fallback bulking:
bulk - fallback bulk - improvement with this patch
1 - 62 cycles(tsc) 15.662 ns - 49 cycles(tsc) 12.407 ns- improved 21.0%
2 - 55 cycles(tsc) 13.935 ns - 30 cycles(tsc) 7.506 ns - improved 45.5%
3 - 53 cycles(tsc) 13.341 ns - 23 cycles(tsc) 5.865 ns - improved 56.6%
4 - 52 cycles(tsc) 13.081 ns - 20 cycles(tsc) 5.048 ns - improved 61.5%
8 - 50 cycles(tsc) 12.627 ns - 18 cycles(tsc) 4.659 ns - improved 64.0%
16 - 49 cycles(tsc) 12.412 ns - 17 cycles(tsc) 4.495 ns - improved 65.3%
30 - 49 cycles(tsc) 12.484 ns - 18 cycles(tsc) 4.533 ns - improved 63.3%
32 - 50 cycles(tsc) 12.627 ns - 18 cycles(tsc) 4.707 ns - improved 64.0%
34 - 96 cycles(tsc) 24.243 ns - 23 cycles(tsc) 5.976 ns - improved 76.0%
48 - 83 cycles(tsc) 20.818 ns - 21 cycles(tsc) 5.329 ns - improved 74.7%
64 - 74 cycles(tsc) 18.700 ns - 20 cycles(tsc) 5.127 ns - improved 73.0%
128 - 90 cycles(tsc) 22.734 ns - 27 cycles(tsc) 6.833 ns - improved 70.0%
158 - 99 cycles(tsc) 24.776 ns - 30 cycles(tsc) 7.583 ns - improved 69.7%
250 - 104 cycles(tsc) 26.089 ns - 37 cycles(tsc) 9.280 ns - improved 64.4%
Performance data, compared current in-kernel bulking:
bulk - curr in-kernel - improvement with this patch
1 - 46 cycles(tsc) - 49 cycles(tsc) - improved (cycles:-3) -6.5%
2 - 27 cycles(tsc) - 30 cycles(tsc) - improved (cycles:-3) -11.1%
3 - 21 cycles(tsc) - 23 cycles(tsc) - improved (cycles:-2) -9.5%
4 - 18 cycles(tsc) - 20 cycles(tsc) - improved (cycles:-2) -11.1%
8 - 17 cycles(tsc) - 18 cycles(tsc) - improved (cycles:-1) -5.9%
16 - 18 cycles(tsc) - 17 cycles(tsc) - improved (cycles: 1) 5.6%
30 - 18 cycles(tsc) - 18 cycles(tsc) - improved (cycles: 0) 0.0%
32 - 18 cycles(tsc) - 18 cycles(tsc) - improved (cycles: 0) 0.0%
34 - 78 cycles(tsc) - 23 cycles(tsc) - improved (cycles:55) 70.5%
48 - 60 cycles(tsc) - 21 cycles(tsc) - improved (cycles:39) 65.0%
64 - 49 cycles(tsc) - 20 cycles(tsc) - improved (cycles:29) 59.2%
128 - 69 cycles(tsc) - 27 cycles(tsc) - improved (cycles:42) 60.9%
158 - 79 cycles(tsc) - 30 cycles(tsc) - improved (cycles:49) 62.0%
250 - 86 cycles(tsc) - 37 cycles(tsc) - improved (cycles:49) 57.0%
Performance with normal SLUB merging is significantly slower for
larger bulking. This is believed to (primarily) be an effect of not
having to share the per-CPU data-structures, as tuning per-CPU size
can achieve similar performance.
bulk - slab_nomerge - normal SLUB merge
1 - 49 cycles(tsc) - 49 cycles(tsc) - merge slower with cycles:0
2 - 30 cycles(tsc) - 30 cycles(tsc) - merge slower with cycles:0
3 - 23 cycles(tsc) - 23 cycles(tsc) - merge slower with cycles:0
4 - 20 cycles(tsc) - 20 cycles(tsc) - merge slower with cycles:0
8 - 18 cycles(tsc) - 18 cycles(tsc) - merge slower with cycles:0
16 - 17 cycles(tsc) - 17 cycles(tsc) - merge slower with cycles:0
30 - 18 cycles(tsc) - 23 cycles(tsc) - merge slower with cycles:5
32 - 18 cycles(tsc) - 22 cycles(tsc) - merge slower with cycles:4
34 - 23 cycles(tsc) - 22 cycles(tsc) - merge slower with cycles:-1
48 - 21 cycles(tsc) - 22 cycles(tsc) - merge slower with cycles:1
64 - 20 cycles(tsc) - 48 cycles(tsc) - merge slower with cycles:28
128 - 27 cycles(tsc) - 57 cycles(tsc) - merge slower with cycles:30
158 - 30 cycles(tsc) - 59 cycles(tsc) - merge slower with cycles:29
250 - 37 cycles(tsc) - 56 cycles(tsc) - merge slower with cycles:19
Joint work with Alexander Duyck.
[1] https://github.com/netoptimizer/prototype-kernel/blob/master/kernel/mm/slab_bulk_test01.c
[akpm@linux-foundation.org: BUG_ON -> WARN_ON;return]
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Acked-by: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-11-20 15:57:49 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-03-15 14:53:32 -07:00
|
|
|
|
slub: optimize bulk slowpath free by detached freelist
This change focus on improving the speed of object freeing in the
"slowpath" of kmem_cache_free_bulk.
The calls slab_free (fastpath) and __slab_free (slowpath) have been
extended with support for bulk free, which amortize the overhead of
the (locked) cmpxchg_double.
To use the new bulking feature, we build what I call a detached
freelist. The detached freelist takes advantage of three properties:
1) the free function call owns the object that is about to be freed,
thus writing into this memory is synchronization-free.
2) many freelist's can co-exist side-by-side in the same slab-page
each with a separate head pointer.
3) it is the visibility of the head pointer that needs synchronization.
Given these properties, the brilliant part is that the detached
freelist can be constructed without any need for synchronization. The
freelist is constructed directly in the page objects, without any
synchronization needed. The detached freelist is allocated on the
stack of the function call kmem_cache_free_bulk. Thus, the freelist
head pointer is not visible to other CPUs.
All objects in a SLUB freelist must belong to the same slab-page.
Thus, constructing the detached freelist is about matching objects
that belong to the same slab-page. The bulk free array is scanned is
a progressive manor with a limited look-ahead facility.
Kmem debug support is handled in call of slab_free().
Notice kmem_cache_free_bulk no longer need to disable IRQs. This
only slowed down single free bulk with approx 3 cycles.
Performance data:
Benchmarked[1] obj size 256 bytes on CPU i7-4790K @ 4.00GHz
SLUB fastpath single object quick reuse: 47 cycles(tsc) 11.931 ns
To get stable and comparable numbers, the kernel have been booted with
"slab_merge" (this also improve performance for larger bulk sizes).
Performance data, compared against fallback bulking:
bulk - fallback bulk - improvement with this patch
1 - 62 cycles(tsc) 15.662 ns - 49 cycles(tsc) 12.407 ns- improved 21.0%
2 - 55 cycles(tsc) 13.935 ns - 30 cycles(tsc) 7.506 ns - improved 45.5%
3 - 53 cycles(tsc) 13.341 ns - 23 cycles(tsc) 5.865 ns - improved 56.6%
4 - 52 cycles(tsc) 13.081 ns - 20 cycles(tsc) 5.048 ns - improved 61.5%
8 - 50 cycles(tsc) 12.627 ns - 18 cycles(tsc) 4.659 ns - improved 64.0%
16 - 49 cycles(tsc) 12.412 ns - 17 cycles(tsc) 4.495 ns - improved 65.3%
30 - 49 cycles(tsc) 12.484 ns - 18 cycles(tsc) 4.533 ns - improved 63.3%
32 - 50 cycles(tsc) 12.627 ns - 18 cycles(tsc) 4.707 ns - improved 64.0%
34 - 96 cycles(tsc) 24.243 ns - 23 cycles(tsc) 5.976 ns - improved 76.0%
48 - 83 cycles(tsc) 20.818 ns - 21 cycles(tsc) 5.329 ns - improved 74.7%
64 - 74 cycles(tsc) 18.700 ns - 20 cycles(tsc) 5.127 ns - improved 73.0%
128 - 90 cycles(tsc) 22.734 ns - 27 cycles(tsc) 6.833 ns - improved 70.0%
158 - 99 cycles(tsc) 24.776 ns - 30 cycles(tsc) 7.583 ns - improved 69.7%
250 - 104 cycles(tsc) 26.089 ns - 37 cycles(tsc) 9.280 ns - improved 64.4%
Performance data, compared current in-kernel bulking:
bulk - curr in-kernel - improvement with this patch
1 - 46 cycles(tsc) - 49 cycles(tsc) - improved (cycles:-3) -6.5%
2 - 27 cycles(tsc) - 30 cycles(tsc) - improved (cycles:-3) -11.1%
3 - 21 cycles(tsc) - 23 cycles(tsc) - improved (cycles:-2) -9.5%
4 - 18 cycles(tsc) - 20 cycles(tsc) - improved (cycles:-2) -11.1%
8 - 17 cycles(tsc) - 18 cycles(tsc) - improved (cycles:-1) -5.9%
16 - 18 cycles(tsc) - 17 cycles(tsc) - improved (cycles: 1) 5.6%
30 - 18 cycles(tsc) - 18 cycles(tsc) - improved (cycles: 0) 0.0%
32 - 18 cycles(tsc) - 18 cycles(tsc) - improved (cycles: 0) 0.0%
34 - 78 cycles(tsc) - 23 cycles(tsc) - improved (cycles:55) 70.5%
48 - 60 cycles(tsc) - 21 cycles(tsc) - improved (cycles:39) 65.0%
64 - 49 cycles(tsc) - 20 cycles(tsc) - improved (cycles:29) 59.2%
128 - 69 cycles(tsc) - 27 cycles(tsc) - improved (cycles:42) 60.9%
158 - 79 cycles(tsc) - 30 cycles(tsc) - improved (cycles:49) 62.0%
250 - 86 cycles(tsc) - 37 cycles(tsc) - improved (cycles:49) 57.0%
Performance with normal SLUB merging is significantly slower for
larger bulking. This is believed to (primarily) be an effect of not
having to share the per-CPU data-structures, as tuning per-CPU size
can achieve similar performance.
bulk - slab_nomerge - normal SLUB merge
1 - 49 cycles(tsc) - 49 cycles(tsc) - merge slower with cycles:0
2 - 30 cycles(tsc) - 30 cycles(tsc) - merge slower with cycles:0
3 - 23 cycles(tsc) - 23 cycles(tsc) - merge slower with cycles:0
4 - 20 cycles(tsc) - 20 cycles(tsc) - merge slower with cycles:0
8 - 18 cycles(tsc) - 18 cycles(tsc) - merge slower with cycles:0
16 - 17 cycles(tsc) - 17 cycles(tsc) - merge slower with cycles:0
30 - 18 cycles(tsc) - 23 cycles(tsc) - merge slower with cycles:5
32 - 18 cycles(tsc) - 22 cycles(tsc) - merge slower with cycles:4
34 - 23 cycles(tsc) - 22 cycles(tsc) - merge slower with cycles:-1
48 - 21 cycles(tsc) - 22 cycles(tsc) - merge slower with cycles:1
64 - 20 cycles(tsc) - 48 cycles(tsc) - merge slower with cycles:28
128 - 27 cycles(tsc) - 57 cycles(tsc) - merge slower with cycles:30
158 - 30 cycles(tsc) - 59 cycles(tsc) - merge slower with cycles:29
250 - 37 cycles(tsc) - 56 cycles(tsc) - merge slower with cycles:19
Joint work with Alexander Duyck.
[1] https://github.com/netoptimizer/prototype-kernel/blob/master/kernel/mm/slab_bulk_test01.c
[akpm@linux-foundation.org: BUG_ON -> WARN_ON;return]
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Acked-by: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-11-20 15:57:49 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-10-04 14:45:58 +01:00
|
|
|
|
|
|
|
|
|
slub: optimize bulk slowpath free by detached freelist
This change focus on improving the speed of object freeing in the
"slowpath" of kmem_cache_free_bulk.
The calls slab_free (fastpath) and __slab_free (slowpath) have been
extended with support for bulk free, which amortize the overhead of
the (locked) cmpxchg_double.
To use the new bulking feature, we build what I call a detached
freelist. The detached freelist takes advantage of three properties:
1) the free function call owns the object that is about to be freed,
thus writing into this memory is synchronization-free.
2) many freelist's can co-exist side-by-side in the same slab-page
each with a separate head pointer.
3) it is the visibility of the head pointer that needs synchronization.
Given these properties, the brilliant part is that the detached
freelist can be constructed without any need for synchronization. The
freelist is constructed directly in the page objects, without any
synchronization needed. The detached freelist is allocated on the
stack of the function call kmem_cache_free_bulk. Thus, the freelist
head pointer is not visible to other CPUs.
All objects in a SLUB freelist must belong to the same slab-page.
Thus, constructing the detached freelist is about matching objects
that belong to the same slab-page. The bulk free array is scanned is
a progressive manor with a limited look-ahead facility.
Kmem debug support is handled in call of slab_free().
Notice kmem_cache_free_bulk no longer need to disable IRQs. This
only slowed down single free bulk with approx 3 cycles.
Performance data:
Benchmarked[1] obj size 256 bytes on CPU i7-4790K @ 4.00GHz
SLUB fastpath single object quick reuse: 47 cycles(tsc) 11.931 ns
To get stable and comparable numbers, the kernel have been booted with
"slab_merge" (this also improve performance for larger bulk sizes).
Performance data, compared against fallback bulking:
bulk - fallback bulk - improvement with this patch
1 - 62 cycles(tsc) 15.662 ns - 49 cycles(tsc) 12.407 ns- improved 21.0%
2 - 55 cycles(tsc) 13.935 ns - 30 cycles(tsc) 7.506 ns - improved 45.5%
3 - 53 cycles(tsc) 13.341 ns - 23 cycles(tsc) 5.865 ns - improved 56.6%
4 - 52 cycles(tsc) 13.081 ns - 20 cycles(tsc) 5.048 ns - improved 61.5%
8 - 50 cycles(tsc) 12.627 ns - 18 cycles(tsc) 4.659 ns - improved 64.0%
16 - 49 cycles(tsc) 12.412 ns - 17 cycles(tsc) 4.495 ns - improved 65.3%
30 - 49 cycles(tsc) 12.484 ns - 18 cycles(tsc) 4.533 ns - improved 63.3%
32 - 50 cycles(tsc) 12.627 ns - 18 cycles(tsc) 4.707 ns - improved 64.0%
34 - 96 cycles(tsc) 24.243 ns - 23 cycles(tsc) 5.976 ns - improved 76.0%
48 - 83 cycles(tsc) 20.818 ns - 21 cycles(tsc) 5.329 ns - improved 74.7%
64 - 74 cycles(tsc) 18.700 ns - 20 cycles(tsc) 5.127 ns - improved 73.0%
128 - 90 cycles(tsc) 22.734 ns - 27 cycles(tsc) 6.833 ns - improved 70.0%
158 - 99 cycles(tsc) 24.776 ns - 30 cycles(tsc) 7.583 ns - improved 69.7%
250 - 104 cycles(tsc) 26.089 ns - 37 cycles(tsc) 9.280 ns - improved 64.4%
Performance data, compared current in-kernel bulking:
bulk - curr in-kernel - improvement with this patch
1 - 46 cycles(tsc) - 49 cycles(tsc) - improved (cycles:-3) -6.5%
2 - 27 cycles(tsc) - 30 cycles(tsc) - improved (cycles:-3) -11.1%
3 - 21 cycles(tsc) - 23 cycles(tsc) - improved (cycles:-2) -9.5%
4 - 18 cycles(tsc) - 20 cycles(tsc) - improved (cycles:-2) -11.1%
8 - 17 cycles(tsc) - 18 cycles(tsc) - improved (cycles:-1) -5.9%
16 - 18 cycles(tsc) - 17 cycles(tsc) - improved (cycles: 1) 5.6%
30 - 18 cycles(tsc) - 18 cycles(tsc) - improved (cycles: 0) 0.0%
32 - 18 cycles(tsc) - 18 cycles(tsc) - improved (cycles: 0) 0.0%
34 - 78 cycles(tsc) - 23 cycles(tsc) - improved (cycles:55) 70.5%
48 - 60 cycles(tsc) - 21 cycles(tsc) - improved (cycles:39) 65.0%
64 - 49 cycles(tsc) - 20 cycles(tsc) - improved (cycles:29) 59.2%
128 - 69 cycles(tsc) - 27 cycles(tsc) - improved (cycles:42) 60.9%
158 - 79 cycles(tsc) - 30 cycles(tsc) - improved (cycles:49) 62.0%
250 - 86 cycles(tsc) - 37 cycles(tsc) - improved (cycles:49) 57.0%
Performance with normal SLUB merging is significantly slower for
larger bulking. This is believed to (primarily) be an effect of not
having to share the per-CPU data-structures, as tuning per-CPU size
can achieve similar performance.
bulk - slab_nomerge - normal SLUB merge
1 - 49 cycles(tsc) - 49 cycles(tsc) - merge slower with cycles:0
2 - 30 cycles(tsc) - 30 cycles(tsc) - merge slower with cycles:0
3 - 23 cycles(tsc) - 23 cycles(tsc) - merge slower with cycles:0
4 - 20 cycles(tsc) - 20 cycles(tsc) - merge slower with cycles:0
8 - 18 cycles(tsc) - 18 cycles(tsc) - merge slower with cycles:0
16 - 17 cycles(tsc) - 17 cycles(tsc) - merge slower with cycles:0
30 - 18 cycles(tsc) - 23 cycles(tsc) - merge slower with cycles:5
32 - 18 cycles(tsc) - 22 cycles(tsc) - merge slower with cycles:4
34 - 23 cycles(tsc) - 22 cycles(tsc) - merge slower with cycles:-1
48 - 21 cycles(tsc) - 22 cycles(tsc) - merge slower with cycles:1
64 - 20 cycles(tsc) - 48 cycles(tsc) - merge slower with cycles:28
128 - 27 cycles(tsc) - 57 cycles(tsc) - merge slower with cycles:30
158 - 30 cycles(tsc) - 59 cycles(tsc) - merge slower with cycles:29
250 - 37 cycles(tsc) - 56 cycles(tsc) - merge slower with cycles:19
Joint work with Alexander Duyck.
[1] https://github.com/netoptimizer/prototype-kernel/blob/master/kernel/mm/slab_bulk_test01.c
[akpm@linux-foundation.org: BUG_ON -> WARN_ON;return]
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Acked-by: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-11-20 15:57:49 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-03-15 14:53:32 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
slub: optimize bulk slowpath free by detached freelist
This change focus on improving the speed of object freeing in the
"slowpath" of kmem_cache_free_bulk.
The calls slab_free (fastpath) and __slab_free (slowpath) have been
extended with support for bulk free, which amortize the overhead of
the (locked) cmpxchg_double.
To use the new bulking feature, we build what I call a detached
freelist. The detached freelist takes advantage of three properties:
1) the free function call owns the object that is about to be freed,
thus writing into this memory is synchronization-free.
2) many freelist's can co-exist side-by-side in the same slab-page
each with a separate head pointer.
3) it is the visibility of the head pointer that needs synchronization.
Given these properties, the brilliant part is that the detached
freelist can be constructed without any need for synchronization. The
freelist is constructed directly in the page objects, without any
synchronization needed. The detached freelist is allocated on the
stack of the function call kmem_cache_free_bulk. Thus, the freelist
head pointer is not visible to other CPUs.
All objects in a SLUB freelist must belong to the same slab-page.
Thus, constructing the detached freelist is about matching objects
that belong to the same slab-page. The bulk free array is scanned is
a progressive manor with a limited look-ahead facility.
Kmem debug support is handled in call of slab_free().
Notice kmem_cache_free_bulk no longer need to disable IRQs. This
only slowed down single free bulk with approx 3 cycles.
Performance data:
Benchmarked[1] obj size 256 bytes on CPU i7-4790K @ 4.00GHz
SLUB fastpath single object quick reuse: 47 cycles(tsc) 11.931 ns
To get stable and comparable numbers, the kernel have been booted with
"slab_merge" (this also improve performance for larger bulk sizes).
Performance data, compared against fallback bulking:
bulk - fallback bulk - improvement with this patch
1 - 62 cycles(tsc) 15.662 ns - 49 cycles(tsc) 12.407 ns- improved 21.0%
2 - 55 cycles(tsc) 13.935 ns - 30 cycles(tsc) 7.506 ns - improved 45.5%
3 - 53 cycles(tsc) 13.341 ns - 23 cycles(tsc) 5.865 ns - improved 56.6%
4 - 52 cycles(tsc) 13.081 ns - 20 cycles(tsc) 5.048 ns - improved 61.5%
8 - 50 cycles(tsc) 12.627 ns - 18 cycles(tsc) 4.659 ns - improved 64.0%
16 - 49 cycles(tsc) 12.412 ns - 17 cycles(tsc) 4.495 ns - improved 65.3%
30 - 49 cycles(tsc) 12.484 ns - 18 cycles(tsc) 4.533 ns - improved 63.3%
32 - 50 cycles(tsc) 12.627 ns - 18 cycles(tsc) 4.707 ns - improved 64.0%
34 - 96 cycles(tsc) 24.243 ns - 23 cycles(tsc) 5.976 ns - improved 76.0%
48 - 83 cycles(tsc) 20.818 ns - 21 cycles(tsc) 5.329 ns - improved 74.7%
64 - 74 cycles(tsc) 18.700 ns - 20 cycles(tsc) 5.127 ns - improved 73.0%
128 - 90 cycles(tsc) 22.734 ns - 27 cycles(tsc) 6.833 ns - improved 70.0%
158 - 99 cycles(tsc) 24.776 ns - 30 cycles(tsc) 7.583 ns - improved 69.7%
250 - 104 cycles(tsc) 26.089 ns - 37 cycles(tsc) 9.280 ns - improved 64.4%
Performance data, compared current in-kernel bulking:
bulk - curr in-kernel - improvement with this patch
1 - 46 cycles(tsc) - 49 cycles(tsc) - improved (cycles:-3) -6.5%
2 - 27 cycles(tsc) - 30 cycles(tsc) - improved (cycles:-3) -11.1%
3 - 21 cycles(tsc) - 23 cycles(tsc) - improved (cycles:-2) -9.5%
4 - 18 cycles(tsc) - 20 cycles(tsc) - improved (cycles:-2) -11.1%
8 - 17 cycles(tsc) - 18 cycles(tsc) - improved (cycles:-1) -5.9%
16 - 18 cycles(tsc) - 17 cycles(tsc) - improved (cycles: 1) 5.6%
30 - 18 cycles(tsc) - 18 cycles(tsc) - improved (cycles: 0) 0.0%
32 - 18 cycles(tsc) - 18 cycles(tsc) - improved (cycles: 0) 0.0%
34 - 78 cycles(tsc) - 23 cycles(tsc) - improved (cycles:55) 70.5%
48 - 60 cycles(tsc) - 21 cycles(tsc) - improved (cycles:39) 65.0%
64 - 49 cycles(tsc) - 20 cycles(tsc) - improved (cycles:29) 59.2%
128 - 69 cycles(tsc) - 27 cycles(tsc) - improved (cycles:42) 60.9%
158 - 79 cycles(tsc) - 30 cycles(tsc) - improved (cycles:49) 62.0%
250 - 86 cycles(tsc) - 37 cycles(tsc) - improved (cycles:49) 57.0%
Performance with normal SLUB merging is significantly slower for
larger bulking. This is believed to (primarily) be an effect of not
having to share the per-CPU data-structures, as tuning per-CPU size
can achieve similar performance.
bulk - slab_nomerge - normal SLUB merge
1 - 49 cycles(tsc) - 49 cycles(tsc) - merge slower with cycles:0
2 - 30 cycles(tsc) - 30 cycles(tsc) - merge slower with cycles:0
3 - 23 cycles(tsc) - 23 cycles(tsc) - merge slower with cycles:0
4 - 20 cycles(tsc) - 20 cycles(tsc) - merge slower with cycles:0
8 - 18 cycles(tsc) - 18 cycles(tsc) - merge slower with cycles:0
16 - 17 cycles(tsc) - 17 cycles(tsc) - merge slower with cycles:0
30 - 18 cycles(tsc) - 23 cycles(tsc) - merge slower with cycles:5
32 - 18 cycles(tsc) - 22 cycles(tsc) - merge slower with cycles:4
34 - 23 cycles(tsc) - 22 cycles(tsc) - merge slower with cycles:-1
48 - 21 cycles(tsc) - 22 cycles(tsc) - merge slower with cycles:1
64 - 20 cycles(tsc) - 48 cycles(tsc) - merge slower with cycles:28
128 - 27 cycles(tsc) - 57 cycles(tsc) - merge slower with cycles:30
158 - 30 cycles(tsc) - 59 cycles(tsc) - merge slower with cycles:29
250 - 37 cycles(tsc) - 56 cycles(tsc) - merge slower with cycles:19
Joint work with Alexander Duyck.
[1] https://github.com/netoptimizer/prototype-kernel/blob/master/kernel/mm/slab_bulk_test01.c
[akpm@linux-foundation.org: BUG_ON -> WARN_ON;return]
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Acked-by: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-11-20 15:57:49 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-10-04 14:45:58 +01:00
|
|
|
|
2022-04-29 20:30:44 +08:00
|
|
|
|
slub: optimize bulk slowpath free by detached freelist
This change focus on improving the speed of object freeing in the
"slowpath" of kmem_cache_free_bulk.
The calls slab_free (fastpath) and __slab_free (slowpath) have been
extended with support for bulk free, which amortize the overhead of
the (locked) cmpxchg_double.
To use the new bulking feature, we build what I call a detached
freelist. The detached freelist takes advantage of three properties:
1) the free function call owns the object that is about to be freed,
thus writing into this memory is synchronization-free.
2) many freelist's can co-exist side-by-side in the same slab-page
each with a separate head pointer.
3) it is the visibility of the head pointer that needs synchronization.
Given these properties, the brilliant part is that the detached
freelist can be constructed without any need for synchronization. The
freelist is constructed directly in the page objects, without any
synchronization needed. The detached freelist is allocated on the
stack of the function call kmem_cache_free_bulk. Thus, the freelist
head pointer is not visible to other CPUs.
All objects in a SLUB freelist must belong to the same slab-page.
Thus, constructing the detached freelist is about matching objects
that belong to the same slab-page. The bulk free array is scanned is
a progressive manor with a limited look-ahead facility.
Kmem debug support is handled in call of slab_free().
Notice kmem_cache_free_bulk no longer need to disable IRQs. This
only slowed down single free bulk with approx 3 cycles.
Performance data:
Benchmarked[1] obj size 256 bytes on CPU i7-4790K @ 4.00GHz
SLUB fastpath single object quick reuse: 47 cycles(tsc) 11.931 ns
To get stable and comparable numbers, the kernel have been booted with
"slab_merge" (this also improve performance for larger bulk sizes).
Performance data, compared against fallback bulking:
bulk - fallback bulk - improvement with this patch
1 - 62 cycles(tsc) 15.662 ns - 49 cycles(tsc) 12.407 ns- improved 21.0%
2 - 55 cycles(tsc) 13.935 ns - 30 cycles(tsc) 7.506 ns - improved 45.5%
3 - 53 cycles(tsc) 13.341 ns - 23 cycles(tsc) 5.865 ns - improved 56.6%
4 - 52 cycles(tsc) 13.081 ns - 20 cycles(tsc) 5.048 ns - improved 61.5%
8 - 50 cycles(tsc) 12.627 ns - 18 cycles(tsc) 4.659 ns - improved 64.0%
16 - 49 cycles(tsc) 12.412 ns - 17 cycles(tsc) 4.495 ns - improved 65.3%
30 - 49 cycles(tsc) 12.484 ns - 18 cycles(tsc) 4.533 ns - improved 63.3%
32 - 50 cycles(tsc) 12.627 ns - 18 cycles(tsc) 4.707 ns - improved 64.0%
34 - 96 cycles(tsc) 24.243 ns - 23 cycles(tsc) 5.976 ns - improved 76.0%
48 - 83 cycles(tsc) 20.818 ns - 21 cycles(tsc) 5.329 ns - improved 74.7%
64 - 74 cycles(tsc) 18.700 ns - 20 cycles(tsc) 5.127 ns - improved 73.0%
128 - 90 cycles(tsc) 22.734 ns - 27 cycles(tsc) 6.833 ns - improved 70.0%
158 - 99 cycles(tsc) 24.776 ns - 30 cycles(tsc) 7.583 ns - improved 69.7%
250 - 104 cycles(tsc) 26.089 ns - 37 cycles(tsc) 9.280 ns - improved 64.4%
Performance data, compared current in-kernel bulking:
bulk - curr in-kernel - improvement with this patch
1 - 46 cycles(tsc) - 49 cycles(tsc) - improved (cycles:-3) -6.5%
2 - 27 cycles(tsc) - 30 cycles(tsc) - improved (cycles:-3) -11.1%
3 - 21 cycles(tsc) - 23 cycles(tsc) - improved (cycles:-2) -9.5%
4 - 18 cycles(tsc) - 20 cycles(tsc) - improved (cycles:-2) -11.1%
8 - 17 cycles(tsc) - 18 cycles(tsc) - improved (cycles:-1) -5.9%
16 - 18 cycles(tsc) - 17 cycles(tsc) - improved (cycles: 1) 5.6%
30 - 18 cycles(tsc) - 18 cycles(tsc) - improved (cycles: 0) 0.0%
32 - 18 cycles(tsc) - 18 cycles(tsc) - improved (cycles: 0) 0.0%
34 - 78 cycles(tsc) - 23 cycles(tsc) - improved (cycles:55) 70.5%
48 - 60 cycles(tsc) - 21 cycles(tsc) - improved (cycles:39) 65.0%
64 - 49 cycles(tsc) - 20 cycles(tsc) - improved (cycles:29) 59.2%
128 - 69 cycles(tsc) - 27 cycles(tsc) - improved (cycles:42) 60.9%
158 - 79 cycles(tsc) - 30 cycles(tsc) - improved (cycles:49) 62.0%
250 - 86 cycles(tsc) - 37 cycles(tsc) - improved (cycles:49) 57.0%
Performance with normal SLUB merging is significantly slower for
larger bulking. This is believed to (primarily) be an effect of not
having to share the per-CPU data-structures, as tuning per-CPU size
can achieve similar performance.
bulk - slab_nomerge - normal SLUB merge
1 - 49 cycles(tsc) - 49 cycles(tsc) - merge slower with cycles:0
2 - 30 cycles(tsc) - 30 cycles(tsc) - merge slower with cycles:0
3 - 23 cycles(tsc) - 23 cycles(tsc) - merge slower with cycles:0
4 - 20 cycles(tsc) - 20 cycles(tsc) - merge slower with cycles:0
8 - 18 cycles(tsc) - 18 cycles(tsc) - merge slower with cycles:0
16 - 17 cycles(tsc) - 17 cycles(tsc) - merge slower with cycles:0
30 - 18 cycles(tsc) - 23 cycles(tsc) - merge slower with cycles:5
32 - 18 cycles(tsc) - 22 cycles(tsc) - merge slower with cycles:4
34 - 23 cycles(tsc) - 22 cycles(tsc) - merge slower with cycles:-1
48 - 21 cycles(tsc) - 22 cycles(tsc) - merge slower with cycles:1
64 - 20 cycles(tsc) - 48 cycles(tsc) - merge slower with cycles:28
128 - 27 cycles(tsc) - 57 cycles(tsc) - merge slower with cycles:30
158 - 30 cycles(tsc) - 59 cycles(tsc) - merge slower with cycles:29
250 - 37 cycles(tsc) - 56 cycles(tsc) - merge slower with cycles:19
Joint work with Alexander Duyck.
[1] https://github.com/netoptimizer/prototype-kernel/blob/master/kernel/mm/slab_bulk_test01.c
[akpm@linux-foundation.org: BUG_ON -> WARN_ON;return]
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Acked-by: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-11-20 15:57:49 -08:00
|
|
|
|
2022-04-29 20:30:44 +08:00
|
|
|
|
2021-10-04 14:45:58 +01:00
|
|
|
|
2016-03-15 14:54:00 -07:00
|
|
|
|
|
|
|
|
|
2021-10-04 14:45:58 +01:00
|
|
|
|
2021-10-04 14:45:59 +01:00
|
|
|
|
2022-04-29 20:30:44 +08:00
|
|
|
|
2016-03-15 14:54:00 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-04-29 20:30:44 +08:00
|
|
|
|
|
|
|
|
|
2016-03-15 14:54:00 -07:00
|
|
|
|
2022-04-29 20:30:44 +08:00
|
|
|
|
2016-03-15 14:54:00 -07:00
|
|
|
|
|
|
|
|
|
2016-03-15 14:53:32 -07:00
|
|
|
|
slub: optimize bulk slowpath free by detached freelist
This change focus on improving the speed of object freeing in the
"slowpath" of kmem_cache_free_bulk.
The calls slab_free (fastpath) and __slab_free (slowpath) have been
extended with support for bulk free, which amortize the overhead of
the (locked) cmpxchg_double.
To use the new bulking feature, we build what I call a detached
freelist. The detached freelist takes advantage of three properties:
1) the free function call owns the object that is about to be freed,
thus writing into this memory is synchronization-free.
2) many freelist's can co-exist side-by-side in the same slab-page
each with a separate head pointer.
3) it is the visibility of the head pointer that needs synchronization.
Given these properties, the brilliant part is that the detached
freelist can be constructed without any need for synchronization. The
freelist is constructed directly in the page objects, without any
synchronization needed. The detached freelist is allocated on the
stack of the function call kmem_cache_free_bulk. Thus, the freelist
head pointer is not visible to other CPUs.
All objects in a SLUB freelist must belong to the same slab-page.
Thus, constructing the detached freelist is about matching objects
that belong to the same slab-page. The bulk free array is scanned is
a progressive manor with a limited look-ahead facility.
Kmem debug support is handled in call of slab_free().
Notice kmem_cache_free_bulk no longer need to disable IRQs. This
only slowed down single free bulk with approx 3 cycles.
Performance data:
Benchmarked[1] obj size 256 bytes on CPU i7-4790K @ 4.00GHz
SLUB fastpath single object quick reuse: 47 cycles(tsc) 11.931 ns
To get stable and comparable numbers, the kernel have been booted with
"slab_merge" (this also improve performance for larger bulk sizes).
Performance data, compared against fallback bulking:
bulk - fallback bulk - improvement with this patch
1 - 62 cycles(tsc) 15.662 ns - 49 cycles(tsc) 12.407 ns- improved 21.0%
2 - 55 cycles(tsc) 13.935 ns - 30 cycles(tsc) 7.506 ns - improved 45.5%
3 - 53 cycles(tsc) 13.341 ns - 23 cycles(tsc) 5.865 ns - improved 56.6%
4 - 52 cycles(tsc) 13.081 ns - 20 cycles(tsc) 5.048 ns - improved 61.5%
8 - 50 cycles(tsc) 12.627 ns - 18 cycles(tsc) 4.659 ns - improved 64.0%
16 - 49 cycles(tsc) 12.412 ns - 17 cycles(tsc) 4.495 ns - improved 65.3%
30 - 49 cycles(tsc) 12.484 ns - 18 cycles(tsc) 4.533 ns - improved 63.3%
32 - 50 cycles(tsc) 12.627 ns - 18 cycles(tsc) 4.707 ns - improved 64.0%
34 - 96 cycles(tsc) 24.243 ns - 23 cycles(tsc) 5.976 ns - improved 76.0%
48 - 83 cycles(tsc) 20.818 ns - 21 cycles(tsc) 5.329 ns - improved 74.7%
64 - 74 cycles(tsc) 18.700 ns - 20 cycles(tsc) 5.127 ns - improved 73.0%
128 - 90 cycles(tsc) 22.734 ns - 27 cycles(tsc) 6.833 ns - improved 70.0%
158 - 99 cycles(tsc) 24.776 ns - 30 cycles(tsc) 7.583 ns - improved 69.7%
250 - 104 cycles(tsc) 26.089 ns - 37 cycles(tsc) 9.280 ns - improved 64.4%
Performance data, compared current in-kernel bulking:
bulk - curr in-kernel - improvement with this patch
1 - 46 cycles(tsc) - 49 cycles(tsc) - improved (cycles:-3) -6.5%
2 - 27 cycles(tsc) - 30 cycles(tsc) - improved (cycles:-3) -11.1%
3 - 21 cycles(tsc) - 23 cycles(tsc) - improved (cycles:-2) -9.5%
4 - 18 cycles(tsc) - 20 cycles(tsc) - improved (cycles:-2) -11.1%
8 - 17 cycles(tsc) - 18 cycles(tsc) - improved (cycles:-1) -5.9%
16 - 18 cycles(tsc) - 17 cycles(tsc) - improved (cycles: 1) 5.6%
30 - 18 cycles(tsc) - 18 cycles(tsc) - improved (cycles: 0) 0.0%
32 - 18 cycles(tsc) - 18 cycles(tsc) - improved (cycles: 0) 0.0%
34 - 78 cycles(tsc) - 23 cycles(tsc) - improved (cycles:55) 70.5%
48 - 60 cycles(tsc) - 21 cycles(tsc) - improved (cycles:39) 65.0%
64 - 49 cycles(tsc) - 20 cycles(tsc) - improved (cycles:29) 59.2%
128 - 69 cycles(tsc) - 27 cycles(tsc) - improved (cycles:42) 60.9%
158 - 79 cycles(tsc) - 30 cycles(tsc) - improved (cycles:49) 62.0%
250 - 86 cycles(tsc) - 37 cycles(tsc) - improved (cycles:49) 57.0%
Performance with normal SLUB merging is significantly slower for
larger bulking. This is believed to (primarily) be an effect of not
having to share the per-CPU data-structures, as tuning per-CPU size
can achieve similar performance.
bulk - slab_nomerge - normal SLUB merge
1 - 49 cycles(tsc) - 49 cycles(tsc) - merge slower with cycles:0
2 - 30 cycles(tsc) - 30 cycles(tsc) - merge slower with cycles:0
3 - 23 cycles(tsc) - 23 cycles(tsc) - merge slower with cycles:0
4 - 20 cycles(tsc) - 20 cycles(tsc) - merge slower with cycles:0
8 - 18 cycles(tsc) - 18 cycles(tsc) - merge slower with cycles:0
16 - 17 cycles(tsc) - 17 cycles(tsc) - merge slower with cycles:0
30 - 18 cycles(tsc) - 23 cycles(tsc) - merge slower with cycles:5
32 - 18 cycles(tsc) - 22 cycles(tsc) - merge slower with cycles:4
34 - 23 cycles(tsc) - 22 cycles(tsc) - merge slower with cycles:-1
48 - 21 cycles(tsc) - 22 cycles(tsc) - merge slower with cycles:1
64 - 20 cycles(tsc) - 48 cycles(tsc) - merge slower with cycles:28
128 - 27 cycles(tsc) - 57 cycles(tsc) - merge slower with cycles:30
158 - 30 cycles(tsc) - 59 cycles(tsc) - merge slower with cycles:29
250 - 37 cycles(tsc) - 56 cycles(tsc) - merge slower with cycles:19
Joint work with Alexander Duyck.
[1] https://github.com/netoptimizer/prototype-kernel/blob/master/kernel/mm/slab_bulk_test01.c
[akpm@linux-foundation.org: BUG_ON -> WARN_ON;return]
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Acked-by: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-11-20 15:57:49 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-04-29 20:30:44 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
slub: optimize bulk slowpath free by detached freelist
This change focus on improving the speed of object freeing in the
"slowpath" of kmem_cache_free_bulk.
The calls slab_free (fastpath) and __slab_free (slowpath) have been
extended with support for bulk free, which amortize the overhead of
the (locked) cmpxchg_double.
To use the new bulking feature, we build what I call a detached
freelist. The detached freelist takes advantage of three properties:
1) the free function call owns the object that is about to be freed,
thus writing into this memory is synchronization-free.
2) many freelist's can co-exist side-by-side in the same slab-page
each with a separate head pointer.
3) it is the visibility of the head pointer that needs synchronization.
Given these properties, the brilliant part is that the detached
freelist can be constructed without any need for synchronization. The
freelist is constructed directly in the page objects, without any
synchronization needed. The detached freelist is allocated on the
stack of the function call kmem_cache_free_bulk. Thus, the freelist
head pointer is not visible to other CPUs.
All objects in a SLUB freelist must belong to the same slab-page.
Thus, constructing the detached freelist is about matching objects
that belong to the same slab-page. The bulk free array is scanned is
a progressive manor with a limited look-ahead facility.
Kmem debug support is handled in call of slab_free().
Notice kmem_cache_free_bulk no longer need to disable IRQs. This
only slowed down single free bulk with approx 3 cycles.
Performance data:
Benchmarked[1] obj size 256 bytes on CPU i7-4790K @ 4.00GHz
SLUB fastpath single object quick reuse: 47 cycles(tsc) 11.931 ns
To get stable and comparable numbers, the kernel have been booted with
"slab_merge" (this also improve performance for larger bulk sizes).
Performance data, compared against fallback bulking:
bulk - fallback bulk - improvement with this patch
1 - 62 cycles(tsc) 15.662 ns - 49 cycles(tsc) 12.407 ns- improved 21.0%
2 - 55 cycles(tsc) 13.935 ns - 30 cycles(tsc) 7.506 ns - improved 45.5%
3 - 53 cycles(tsc) 13.341 ns - 23 cycles(tsc) 5.865 ns - improved 56.6%
4 - 52 cycles(tsc) 13.081 ns - 20 cycles(tsc) 5.048 ns - improved 61.5%
8 - 50 cycles(tsc) 12.627 ns - 18 cycles(tsc) 4.659 ns - improved 64.0%
16 - 49 cycles(tsc) 12.412 ns - 17 cycles(tsc) 4.495 ns - improved 65.3%
30 - 49 cycles(tsc) 12.484 ns - 18 cycles(tsc) 4.533 ns - improved 63.3%
32 - 50 cycles(tsc) 12.627 ns - 18 cycles(tsc) 4.707 ns - improved 64.0%
34 - 96 cycles(tsc) 24.243 ns - 23 cycles(tsc) 5.976 ns - improved 76.0%
48 - 83 cycles(tsc) 20.818 ns - 21 cycles(tsc) 5.329 ns - improved 74.7%
64 - 74 cycles(tsc) 18.700 ns - 20 cycles(tsc) 5.127 ns - improved 73.0%
128 - 90 cycles(tsc) 22.734 ns - 27 cycles(tsc) 6.833 ns - improved 70.0%
158 - 99 cycles(tsc) 24.776 ns - 30 cycles(tsc) 7.583 ns - improved 69.7%
250 - 104 cycles(tsc) 26.089 ns - 37 cycles(tsc) 9.280 ns - improved 64.4%
Performance data, compared current in-kernel bulking:
bulk - curr in-kernel - improvement with this patch
1 - 46 cycles(tsc) - 49 cycles(tsc) - improved (cycles:-3) -6.5%
2 - 27 cycles(tsc) - 30 cycles(tsc) - improved (cycles:-3) -11.1%
3 - 21 cycles(tsc) - 23 cycles(tsc) - improved (cycles:-2) -9.5%
4 - 18 cycles(tsc) - 20 cycles(tsc) - improved (cycles:-2) -11.1%
8 - 17 cycles(tsc) - 18 cycles(tsc) - improved (cycles:-1) -5.9%
16 - 18 cycles(tsc) - 17 cycles(tsc) - improved (cycles: 1) 5.6%
30 - 18 cycles(tsc) - 18 cycles(tsc) - improved (cycles: 0) 0.0%
32 - 18 cycles(tsc) - 18 cycles(tsc) - improved (cycles: 0) 0.0%
34 - 78 cycles(tsc) - 23 cycles(tsc) - improved (cycles:55) 70.5%
48 - 60 cycles(tsc) - 21 cycles(tsc) - improved (cycles:39) 65.0%
64 - 49 cycles(tsc) - 20 cycles(tsc) - improved (cycles:29) 59.2%
128 - 69 cycles(tsc) - 27 cycles(tsc) - improved (cycles:42) 60.9%
158 - 79 cycles(tsc) - 30 cycles(tsc) - improved (cycles:49) 62.0%
250 - 86 cycles(tsc) - 37 cycles(tsc) - improved (cycles:49) 57.0%
Performance with normal SLUB merging is significantly slower for
larger bulking. This is believed to (primarily) be an effect of not
having to share the per-CPU data-structures, as tuning per-CPU size
can achieve similar performance.
bulk - slab_nomerge - normal SLUB merge
1 - 49 cycles(tsc) - 49 cycles(tsc) - merge slower with cycles:0
2 - 30 cycles(tsc) - 30 cycles(tsc) - merge slower with cycles:0
3 - 23 cycles(tsc) - 23 cycles(tsc) - merge slower with cycles:0
4 - 20 cycles(tsc) - 20 cycles(tsc) - merge slower with cycles:0
8 - 18 cycles(tsc) - 18 cycles(tsc) - merge slower with cycles:0
16 - 17 cycles(tsc) - 17 cycles(tsc) - merge slower with cycles:0
30 - 18 cycles(tsc) - 23 cycles(tsc) - merge slower with cycles:5
32 - 18 cycles(tsc) - 22 cycles(tsc) - merge slower with cycles:4
34 - 23 cycles(tsc) - 22 cycles(tsc) - merge slower with cycles:-1
48 - 21 cycles(tsc) - 22 cycles(tsc) - merge slower with cycles:1
64 - 20 cycles(tsc) - 48 cycles(tsc) - merge slower with cycles:28
128 - 27 cycles(tsc) - 57 cycles(tsc) - merge slower with cycles:30
158 - 30 cycles(tsc) - 59 cycles(tsc) - merge slower with cycles:29
250 - 37 cycles(tsc) - 56 cycles(tsc) - merge slower with cycles:19
Joint work with Alexander Duyck.
[1] https://github.com/netoptimizer/prototype-kernel/blob/master/kernel/mm/slab_bulk_test01.c
[akpm@linux-foundation.org: BUG_ON -> WARN_ON;return]
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Acked-by: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-11-20 15:57:49 -08:00
|
|
|
|
|
|
|
|
|
2021-10-04 14:45:58 +01:00
|
|
|
|
|
|
|
|
|
slub: optimize bulk slowpath free by detached freelist
This change focus on improving the speed of object freeing in the
"slowpath" of kmem_cache_free_bulk.
The calls slab_free (fastpath) and __slab_free (slowpath) have been
extended with support for bulk free, which amortize the overhead of
the (locked) cmpxchg_double.
To use the new bulking feature, we build what I call a detached
freelist. The detached freelist takes advantage of three properties:
1) the free function call owns the object that is about to be freed,
thus writing into this memory is synchronization-free.
2) many freelist's can co-exist side-by-side in the same slab-page
each with a separate head pointer.
3) it is the visibility of the head pointer that needs synchronization.
Given these properties, the brilliant part is that the detached
freelist can be constructed without any need for synchronization. The
freelist is constructed directly in the page objects, without any
synchronization needed. The detached freelist is allocated on the
stack of the function call kmem_cache_free_bulk. Thus, the freelist
head pointer is not visible to other CPUs.
All objects in a SLUB freelist must belong to the same slab-page.
Thus, constructing the detached freelist is about matching objects
that belong to the same slab-page. The bulk free array is scanned is
a progressive manor with a limited look-ahead facility.
Kmem debug support is handled in call of slab_free().
Notice kmem_cache_free_bulk no longer need to disable IRQs. This
only slowed down single free bulk with approx 3 cycles.
Performance data:
Benchmarked[1] obj size 256 bytes on CPU i7-4790K @ 4.00GHz
SLUB fastpath single object quick reuse: 47 cycles(tsc) 11.931 ns
To get stable and comparable numbers, the kernel have been booted with
"slab_merge" (this also improve performance for larger bulk sizes).
Performance data, compared against fallback bulking:
bulk - fallback bulk - improvement with this patch
1 - 62 cycles(tsc) 15.662 ns - 49 cycles(tsc) 12.407 ns- improved 21.0%
2 - 55 cycles(tsc) 13.935 ns - 30 cycles(tsc) 7.506 ns - improved 45.5%
3 - 53 cycles(tsc) 13.341 ns - 23 cycles(tsc) 5.865 ns - improved 56.6%
4 - 52 cycles(tsc) 13.081 ns - 20 cycles(tsc) 5.048 ns - improved 61.5%
8 - 50 cycles(tsc) 12.627 ns - 18 cycles(tsc) 4.659 ns - improved 64.0%
16 - 49 cycles(tsc) 12.412 ns - 17 cycles(tsc) 4.495 ns - improved 65.3%
30 - 49 cycles(tsc) 12.484 ns - 18 cycles(tsc) 4.533 ns - improved 63.3%
32 - 50 cycles(tsc) 12.627 ns - 18 cycles(tsc) 4.707 ns - improved 64.0%
34 - 96 cycles(tsc) 24.243 ns - 23 cycles(tsc) 5.976 ns - improved 76.0%
48 - 83 cycles(tsc) 20.818 ns - 21 cycles(tsc) 5.329 ns - improved 74.7%
64 - 74 cycles(tsc) 18.700 ns - 20 cycles(tsc) 5.127 ns - improved 73.0%
128 - 90 cycles(tsc) 22.734 ns - 27 cycles(tsc) 6.833 ns - improved 70.0%
158 - 99 cycles(tsc) 24.776 ns - 30 cycles(tsc) 7.583 ns - improved 69.7%
250 - 104 cycles(tsc) 26.089 ns - 37 cycles(tsc) 9.280 ns - improved 64.4%
Performance data, compared current in-kernel bulking:
bulk - curr in-kernel - improvement with this patch
1 - 46 cycles(tsc) - 49 cycles(tsc) - improved (cycles:-3) -6.5%
2 - 27 cycles(tsc) - 30 cycles(tsc) - improved (cycles:-3) -11.1%
3 - 21 cycles(tsc) - 23 cycles(tsc) - improved (cycles:-2) -9.5%
4 - 18 cycles(tsc) - 20 cycles(tsc) - improved (cycles:-2) -11.1%
8 - 17 cycles(tsc) - 18 cycles(tsc) - improved (cycles:-1) -5.9%
16 - 18 cycles(tsc) - 17 cycles(tsc) - improved (cycles: 1) 5.6%
30 - 18 cycles(tsc) - 18 cycles(tsc) - improved (cycles: 0) 0.0%
32 - 18 cycles(tsc) - 18 cycles(tsc) - improved (cycles: 0) 0.0%
34 - 78 cycles(tsc) - 23 cycles(tsc) - improved (cycles:55) 70.5%
48 - 60 cycles(tsc) - 21 cycles(tsc) - improved (cycles:39) 65.0%
64 - 49 cycles(tsc) - 20 cycles(tsc) - improved (cycles:29) 59.2%
128 - 69 cycles(tsc) - 27 cycles(tsc) - improved (cycles:42) 60.9%
158 - 79 cycles(tsc) - 30 cycles(tsc) - improved (cycles:49) 62.0%
250 - 86 cycles(tsc) - 37 cycles(tsc) - improved (cycles:49) 57.0%
Performance with normal SLUB merging is significantly slower for
larger bulking. This is believed to (primarily) be an effect of not
having to share the per-CPU data-structures, as tuning per-CPU size
can achieve similar performance.
bulk - slab_nomerge - normal SLUB merge
1 - 49 cycles(tsc) - 49 cycles(tsc) - merge slower with cycles:0
2 - 30 cycles(tsc) - 30 cycles(tsc) - merge slower with cycles:0
3 - 23 cycles(tsc) - 23 cycles(tsc) - merge slower with cycles:0
4 - 20 cycles(tsc) - 20 cycles(tsc) - merge slower with cycles:0
8 - 18 cycles(tsc) - 18 cycles(tsc) - merge slower with cycles:0
16 - 17 cycles(tsc) - 17 cycles(tsc) - merge slower with cycles:0
30 - 18 cycles(tsc) - 23 cycles(tsc) - merge slower with cycles:5
32 - 18 cycles(tsc) - 22 cycles(tsc) - merge slower with cycles:4
34 - 23 cycles(tsc) - 22 cycles(tsc) - merge slower with cycles:-1
48 - 21 cycles(tsc) - 22 cycles(tsc) - merge slower with cycles:1
64 - 20 cycles(tsc) - 48 cycles(tsc) - merge slower with cycles:28
128 - 27 cycles(tsc) - 57 cycles(tsc) - merge slower with cycles:30
158 - 30 cycles(tsc) - 59 cycles(tsc) - merge slower with cycles:29
250 - 37 cycles(tsc) - 56 cycles(tsc) - merge slower with cycles:19
Joint work with Alexander Duyck.
[1] https://github.com/netoptimizer/prototype-kernel/blob/master/kernel/mm/slab_bulk_test01.c
[akpm@linux-foundation.org: BUG_ON -> WARN_ON;return]
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Acked-by: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-11-20 15:57:49 -08:00
|
|
|
|
2016-03-15 14:53:32 -07:00
|
|
|
|
slub: optimize bulk slowpath free by detached freelist
This change focus on improving the speed of object freeing in the
"slowpath" of kmem_cache_free_bulk.
The calls slab_free (fastpath) and __slab_free (slowpath) have been
extended with support for bulk free, which amortize the overhead of
the (locked) cmpxchg_double.
To use the new bulking feature, we build what I call a detached
freelist. The detached freelist takes advantage of three properties:
1) the free function call owns the object that is about to be freed,
thus writing into this memory is synchronization-free.
2) many freelist's can co-exist side-by-side in the same slab-page
each with a separate head pointer.
3) it is the visibility of the head pointer that needs synchronization.
Given these properties, the brilliant part is that the detached
freelist can be constructed without any need for synchronization. The
freelist is constructed directly in the page objects, without any
synchronization needed. The detached freelist is allocated on the
stack of the function call kmem_cache_free_bulk. Thus, the freelist
head pointer is not visible to other CPUs.
All objects in a SLUB freelist must belong to the same slab-page.
Thus, constructing the detached freelist is about matching objects
that belong to the same slab-page. The bulk free array is scanned is
a progressive manor with a limited look-ahead facility.
Kmem debug support is handled in call of slab_free().
Notice kmem_cache_free_bulk no longer need to disable IRQs. This
only slowed down single free bulk with approx 3 cycles.
Performance data:
Benchmarked[1] obj size 256 bytes on CPU i7-4790K @ 4.00GHz
SLUB fastpath single object quick reuse: 47 cycles(tsc) 11.931 ns
To get stable and comparable numbers, the kernel have been booted with
"slab_merge" (this also improve performance for larger bulk sizes).
Performance data, compared against fallback bulking:
bulk - fallback bulk - improvement with this patch
1 - 62 cycles(tsc) 15.662 ns - 49 cycles(tsc) 12.407 ns- improved 21.0%
2 - 55 cycles(tsc) 13.935 ns - 30 cycles(tsc) 7.506 ns - improved 45.5%
3 - 53 cycles(tsc) 13.341 ns - 23 cycles(tsc) 5.865 ns - improved 56.6%
4 - 52 cycles(tsc) 13.081 ns - 20 cycles(tsc) 5.048 ns - improved 61.5%
8 - 50 cycles(tsc) 12.627 ns - 18 cycles(tsc) 4.659 ns - improved 64.0%
16 - 49 cycles(tsc) 12.412 ns - 17 cycles(tsc) 4.495 ns - improved 65.3%
30 - 49 cycles(tsc) 12.484 ns - 18 cycles(tsc) 4.533 ns - improved 63.3%
32 - 50 cycles(tsc) 12.627 ns - 18 cycles(tsc) 4.707 ns - improved 64.0%
34 - 96 cycles(tsc) 24.243 ns - 23 cycles(tsc) 5.976 ns - improved 76.0%
48 - 83 cycles(tsc) 20.818 ns - 21 cycles(tsc) 5.329 ns - improved 74.7%
64 - 74 cycles(tsc) 18.700 ns - 20 cycles(tsc) 5.127 ns - improved 73.0%
128 - 90 cycles(tsc) 22.734 ns - 27 cycles(tsc) 6.833 ns - improved 70.0%
158 - 99 cycles(tsc) 24.776 ns - 30 cycles(tsc) 7.583 ns - improved 69.7%
250 - 104 cycles(tsc) 26.089 ns - 37 cycles(tsc) 9.280 ns - improved 64.4%
Performance data, compared current in-kernel bulking:
bulk - curr in-kernel - improvement with this patch
1 - 46 cycles(tsc) - 49 cycles(tsc) - improved (cycles:-3) -6.5%
2 - 27 cycles(tsc) - 30 cycles(tsc) - improved (cycles:-3) -11.1%
3 - 21 cycles(tsc) - 23 cycles(tsc) - improved (cycles:-2) -9.5%
4 - 18 cycles(tsc) - 20 cycles(tsc) - improved (cycles:-2) -11.1%
8 - 17 cycles(tsc) - 18 cycles(tsc) - improved (cycles:-1) -5.9%
16 - 18 cycles(tsc) - 17 cycles(tsc) - improved (cycles: 1) 5.6%
30 - 18 cycles(tsc) - 18 cycles(tsc) - improved (cycles: 0) 0.0%
32 - 18 cycles(tsc) - 18 cycles(tsc) - improved (cycles: 0) 0.0%
34 - 78 cycles(tsc) - 23 cycles(tsc) - improved (cycles:55) 70.5%
48 - 60 cycles(tsc) - 21 cycles(tsc) - improved (cycles:39) 65.0%
64 - 49 cycles(tsc) - 20 cycles(tsc) - improved (cycles:29) 59.2%
128 - 69 cycles(tsc) - 27 cycles(tsc) - improved (cycles:42) 60.9%
158 - 79 cycles(tsc) - 30 cycles(tsc) - improved (cycles:49) 62.0%
250 - 86 cycles(tsc) - 37 cycles(tsc) - improved (cycles:49) 57.0%
Performance with normal SLUB merging is significantly slower for
larger bulking. This is believed to (primarily) be an effect of not
having to share the per-CPU data-structures, as tuning per-CPU size
can achieve similar performance.
bulk - slab_nomerge - normal SLUB merge
1 - 49 cycles(tsc) - 49 cycles(tsc) - merge slower with cycles:0
2 - 30 cycles(tsc) - 30 cycles(tsc) - merge slower with cycles:0
3 - 23 cycles(tsc) - 23 cycles(tsc) - merge slower with cycles:0
4 - 20 cycles(tsc) - 20 cycles(tsc) - merge slower with cycles:0
8 - 18 cycles(tsc) - 18 cycles(tsc) - merge slower with cycles:0
16 - 17 cycles(tsc) - 17 cycles(tsc) - merge slower with cycles:0
30 - 18 cycles(tsc) - 23 cycles(tsc) - merge slower with cycles:5
32 - 18 cycles(tsc) - 22 cycles(tsc) - merge slower with cycles:4
34 - 23 cycles(tsc) - 22 cycles(tsc) - merge slower with cycles:-1
48 - 21 cycles(tsc) - 22 cycles(tsc) - merge slower with cycles:1
64 - 20 cycles(tsc) - 48 cycles(tsc) - merge slower with cycles:28
128 - 27 cycles(tsc) - 57 cycles(tsc) - merge slower with cycles:30
158 - 30 cycles(tsc) - 59 cycles(tsc) - merge slower with cycles:29
250 - 37 cycles(tsc) - 56 cycles(tsc) - merge slower with cycles:19
Joint work with Alexander Duyck.
[1] https://github.com/netoptimizer/prototype-kernel/blob/master/kernel/mm/slab_bulk_test01.c
[akpm@linux-foundation.org: BUG_ON -> WARN_ON;return]
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Acked-by: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-11-20 15:57:49 -08:00
|
|
|
|
|
|
|
|
|
2022-04-29 20:30:44 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
slub: optimize bulk slowpath free by detached freelist
This change focus on improving the speed of object freeing in the
"slowpath" of kmem_cache_free_bulk.
The calls slab_free (fastpath) and __slab_free (slowpath) have been
extended with support for bulk free, which amortize the overhead of
the (locked) cmpxchg_double.
To use the new bulking feature, we build what I call a detached
freelist. The detached freelist takes advantage of three properties:
1) the free function call owns the object that is about to be freed,
thus writing into this memory is synchronization-free.
2) many freelist's can co-exist side-by-side in the same slab-page
each with a separate head pointer.
3) it is the visibility of the head pointer that needs synchronization.
Given these properties, the brilliant part is that the detached
freelist can be constructed without any need for synchronization. The
freelist is constructed directly in the page objects, without any
synchronization needed. The detached freelist is allocated on the
stack of the function call kmem_cache_free_bulk. Thus, the freelist
head pointer is not visible to other CPUs.
All objects in a SLUB freelist must belong to the same slab-page.
Thus, constructing the detached freelist is about matching objects
that belong to the same slab-page. The bulk free array is scanned is
a progressive manor with a limited look-ahead facility.
Kmem debug support is handled in call of slab_free().
Notice kmem_cache_free_bulk no longer need to disable IRQs. This
only slowed down single free bulk with approx 3 cycles.
Performance data:
Benchmarked[1] obj size 256 bytes on CPU i7-4790K @ 4.00GHz
SLUB fastpath single object quick reuse: 47 cycles(tsc) 11.931 ns
To get stable and comparable numbers, the kernel have been booted with
"slab_merge" (this also improve performance for larger bulk sizes).
Performance data, compared against fallback bulking:
bulk - fallback bulk - improvement with this patch
1 - 62 cycles(tsc) 15.662 ns - 49 cycles(tsc) 12.407 ns- improved 21.0%
2 - 55 cycles(tsc) 13.935 ns - 30 cycles(tsc) 7.506 ns - improved 45.5%
3 - 53 cycles(tsc) 13.341 ns - 23 cycles(tsc) 5.865 ns - improved 56.6%
4 - 52 cycles(tsc) 13.081 ns - 20 cycles(tsc) 5.048 ns - improved 61.5%
8 - 50 cycles(tsc) 12.627 ns - 18 cycles(tsc) 4.659 ns - improved 64.0%
16 - 49 cycles(tsc) 12.412 ns - 17 cycles(tsc) 4.495 ns - improved 65.3%
30 - 49 cycles(tsc) 12.484 ns - 18 cycles(tsc) 4.533 ns - improved 63.3%
32 - 50 cycles(tsc) 12.627 ns - 18 cycles(tsc) 4.707 ns - improved 64.0%
34 - 96 cycles(tsc) 24.243 ns - 23 cycles(tsc) 5.976 ns - improved 76.0%
48 - 83 cycles(tsc) 20.818 ns - 21 cycles(tsc) 5.329 ns - improved 74.7%
64 - 74 cycles(tsc) 18.700 ns - 20 cycles(tsc) 5.127 ns - improved 73.0%
128 - 90 cycles(tsc) 22.734 ns - 27 cycles(tsc) 6.833 ns - improved 70.0%
158 - 99 cycles(tsc) 24.776 ns - 30 cycles(tsc) 7.583 ns - improved 69.7%
250 - 104 cycles(tsc) 26.089 ns - 37 cycles(tsc) 9.280 ns - improved 64.4%
Performance data, compared current in-kernel bulking:
bulk - curr in-kernel - improvement with this patch
1 - 46 cycles(tsc) - 49 cycles(tsc) - improved (cycles:-3) -6.5%
2 - 27 cycles(tsc) - 30 cycles(tsc) - improved (cycles:-3) -11.1%
3 - 21 cycles(tsc) - 23 cycles(tsc) - improved (cycles:-2) -9.5%
4 - 18 cycles(tsc) - 20 cycles(tsc) - improved (cycles:-2) -11.1%
8 - 17 cycles(tsc) - 18 cycles(tsc) - improved (cycles:-1) -5.9%
16 - 18 cycles(tsc) - 17 cycles(tsc) - improved (cycles: 1) 5.6%
30 - 18 cycles(tsc) - 18 cycles(tsc) - improved (cycles: 0) 0.0%
32 - 18 cycles(tsc) - 18 cycles(tsc) - improved (cycles: 0) 0.0%
34 - 78 cycles(tsc) - 23 cycles(tsc) - improved (cycles:55) 70.5%
48 - 60 cycles(tsc) - 21 cycles(tsc) - improved (cycles:39) 65.0%
64 - 49 cycles(tsc) - 20 cycles(tsc) - improved (cycles:29) 59.2%
128 - 69 cycles(tsc) - 27 cycles(tsc) - improved (cycles:42) 60.9%
158 - 79 cycles(tsc) - 30 cycles(tsc) - improved (cycles:49) 62.0%
250 - 86 cycles(tsc) - 37 cycles(tsc) - improved (cycles:49) 57.0%
Performance with normal SLUB merging is significantly slower for
larger bulking. This is believed to (primarily) be an effect of not
having to share the per-CPU data-structures, as tuning per-CPU size
can achieve similar performance.
bulk - slab_nomerge - normal SLUB merge
1 - 49 cycles(tsc) - 49 cycles(tsc) - merge slower with cycles:0
2 - 30 cycles(tsc) - 30 cycles(tsc) - merge slower with cycles:0
3 - 23 cycles(tsc) - 23 cycles(tsc) - merge slower with cycles:0
4 - 20 cycles(tsc) - 20 cycles(tsc) - merge slower with cycles:0
8 - 18 cycles(tsc) - 18 cycles(tsc) - merge slower with cycles:0
16 - 17 cycles(tsc) - 17 cycles(tsc) - merge slower with cycles:0
30 - 18 cycles(tsc) - 23 cycles(tsc) - merge slower with cycles:5
32 - 18 cycles(tsc) - 22 cycles(tsc) - merge slower with cycles:4
34 - 23 cycles(tsc) - 22 cycles(tsc) - merge slower with cycles:-1
48 - 21 cycles(tsc) - 22 cycles(tsc) - merge slower with cycles:1
64 - 20 cycles(tsc) - 48 cycles(tsc) - merge slower with cycles:28
128 - 27 cycles(tsc) - 57 cycles(tsc) - merge slower with cycles:30
158 - 30 cycles(tsc) - 59 cycles(tsc) - merge slower with cycles:29
250 - 37 cycles(tsc) - 56 cycles(tsc) - merge slower with cycles:19
Joint work with Alexander Duyck.
[1] https://github.com/netoptimizer/prototype-kernel/blob/master/kernel/mm/slab_bulk_test01.c
[akpm@linux-foundation.org: BUG_ON -> WARN_ON;return]
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Acked-by: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-11-20 15:57:49 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-04-29 20:30:44 +08:00
|
|
|
|
slub: optimize bulk slowpath free by detached freelist
This change focus on improving the speed of object freeing in the
"slowpath" of kmem_cache_free_bulk.
The calls slab_free (fastpath) and __slab_free (slowpath) have been
extended with support for bulk free, which amortize the overhead of
the (locked) cmpxchg_double.
To use the new bulking feature, we build what I call a detached
freelist. The detached freelist takes advantage of three properties:
1) the free function call owns the object that is about to be freed,
thus writing into this memory is synchronization-free.
2) many freelist's can co-exist side-by-side in the same slab-page
each with a separate head pointer.
3) it is the visibility of the head pointer that needs synchronization.
Given these properties, the brilliant part is that the detached
freelist can be constructed without any need for synchronization. The
freelist is constructed directly in the page objects, without any
synchronization needed. The detached freelist is allocated on the
stack of the function call kmem_cache_free_bulk. Thus, the freelist
head pointer is not visible to other CPUs.
All objects in a SLUB freelist must belong to the same slab-page.
Thus, constructing the detached freelist is about matching objects
that belong to the same slab-page. The bulk free array is scanned is
a progressive manor with a limited look-ahead facility.
Kmem debug support is handled in call of slab_free().
Notice kmem_cache_free_bulk no longer need to disable IRQs. This
only slowed down single free bulk with approx 3 cycles.
Performance data:
Benchmarked[1] obj size 256 bytes on CPU i7-4790K @ 4.00GHz
SLUB fastpath single object quick reuse: 47 cycles(tsc) 11.931 ns
To get stable and comparable numbers, the kernel have been booted with
"slab_merge" (this also improve performance for larger bulk sizes).
Performance data, compared against fallback bulking:
bulk - fallback bulk - improvement with this patch
1 - 62 cycles(tsc) 15.662 ns - 49 cycles(tsc) 12.407 ns- improved 21.0%
2 - 55 cycles(tsc) 13.935 ns - 30 cycles(tsc) 7.506 ns - improved 45.5%
3 - 53 cycles(tsc) 13.341 ns - 23 cycles(tsc) 5.865 ns - improved 56.6%
4 - 52 cycles(tsc) 13.081 ns - 20 cycles(tsc) 5.048 ns - improved 61.5%
8 - 50 cycles(tsc) 12.627 ns - 18 cycles(tsc) 4.659 ns - improved 64.0%
16 - 49 cycles(tsc) 12.412 ns - 17 cycles(tsc) 4.495 ns - improved 65.3%
30 - 49 cycles(tsc) 12.484 ns - 18 cycles(tsc) 4.533 ns - improved 63.3%
32 - 50 cycles(tsc) 12.627 ns - 18 cycles(tsc) 4.707 ns - improved 64.0%
34 - 96 cycles(tsc) 24.243 ns - 23 cycles(tsc) 5.976 ns - improved 76.0%
48 - 83 cycles(tsc) 20.818 ns - 21 cycles(tsc) 5.329 ns - improved 74.7%
64 - 74 cycles(tsc) 18.700 ns - 20 cycles(tsc) 5.127 ns - improved 73.0%
128 - 90 cycles(tsc) 22.734 ns - 27 cycles(tsc) 6.833 ns - improved 70.0%
158 - 99 cycles(tsc) 24.776 ns - 30 cycles(tsc) 7.583 ns - improved 69.7%
250 - 104 cycles(tsc) 26.089 ns - 37 cycles(tsc) 9.280 ns - improved 64.4%
Performance data, compared current in-kernel bulking:
bulk - curr in-kernel - improvement with this patch
1 - 46 cycles(tsc) - 49 cycles(tsc) - improved (cycles:-3) -6.5%
2 - 27 cycles(tsc) - 30 cycles(tsc) - improved (cycles:-3) -11.1%
3 - 21 cycles(tsc) - 23 cycles(tsc) - improved (cycles:-2) -9.5%
4 - 18 cycles(tsc) - 20 cycles(tsc) - improved (cycles:-2) -11.1%
8 - 17 cycles(tsc) - 18 cycles(tsc) - improved (cycles:-1) -5.9%
16 - 18 cycles(tsc) - 17 cycles(tsc) - improved (cycles: 1) 5.6%
30 - 18 cycles(tsc) - 18 cycles(tsc) - improved (cycles: 0) 0.0%
32 - 18 cycles(tsc) - 18 cycles(tsc) - improved (cycles: 0) 0.0%
34 - 78 cycles(tsc) - 23 cycles(tsc) - improved (cycles:55) 70.5%
48 - 60 cycles(tsc) - 21 cycles(tsc) - improved (cycles:39) 65.0%
64 - 49 cycles(tsc) - 20 cycles(tsc) - improved (cycles:29) 59.2%
128 - 69 cycles(tsc) - 27 cycles(tsc) - improved (cycles:42) 60.9%
158 - 79 cycles(tsc) - 30 cycles(tsc) - improved (cycles:49) 62.0%
250 - 86 cycles(tsc) - 37 cycles(tsc) - improved (cycles:49) 57.0%
Performance with normal SLUB merging is significantly slower for
larger bulking. This is believed to (primarily) be an effect of not
having to share the per-CPU data-structures, as tuning per-CPU size
can achieve similar performance.
bulk - slab_nomerge - normal SLUB merge
1 - 49 cycles(tsc) - 49 cycles(tsc) - merge slower with cycles:0
2 - 30 cycles(tsc) - 30 cycles(tsc) - merge slower with cycles:0
3 - 23 cycles(tsc) - 23 cycles(tsc) - merge slower with cycles:0
4 - 20 cycles(tsc) - 20 cycles(tsc) - merge slower with cycles:0
8 - 18 cycles(tsc) - 18 cycles(tsc) - merge slower with cycles:0
16 - 17 cycles(tsc) - 17 cycles(tsc) - merge slower with cycles:0
30 - 18 cycles(tsc) - 23 cycles(tsc) - merge slower with cycles:5
32 - 18 cycles(tsc) - 22 cycles(tsc) - merge slower with cycles:4
34 - 23 cycles(tsc) - 22 cycles(tsc) - merge slower with cycles:-1
48 - 21 cycles(tsc) - 22 cycles(tsc) - merge slower with cycles:1
64 - 20 cycles(tsc) - 48 cycles(tsc) - merge slower with cycles:28
128 - 27 cycles(tsc) - 57 cycles(tsc) - merge slower with cycles:30
158 - 30 cycles(tsc) - 59 cycles(tsc) - merge slower with cycles:29
250 - 37 cycles(tsc) - 56 cycles(tsc) - merge slower with cycles:19
Joint work with Alexander Duyck.
[1] https://github.com/netoptimizer/prototype-kernel/blob/master/kernel/mm/slab_bulk_test01.c
[akpm@linux-foundation.org: BUG_ON -> WARN_ON;return]
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Acked-by: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-11-20 15:57:49 -08:00
|
|
|
|
|
|
|
|
|
2023-11-02 16:34:39 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-07-29 14:19:28 -04:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-11-02 16:34:39 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-09-04 15:45:37 -07:00
|
|
|
|
2016-03-15 14:53:32 -07:00
|
|
|
|
2015-09-04 15:45:34 -07:00
|
|
|
|
2022-06-15 00:26:34 +09:00
|
|
|
|
slub: optimize bulk slowpath free by detached freelist
This change focus on improving the speed of object freeing in the
"slowpath" of kmem_cache_free_bulk.
The calls slab_free (fastpath) and __slab_free (slowpath) have been
extended with support for bulk free, which amortize the overhead of
the (locked) cmpxchg_double.
To use the new bulking feature, we build what I call a detached
freelist. The detached freelist takes advantage of three properties:
1) the free function call owns the object that is about to be freed,
thus writing into this memory is synchronization-free.
2) many freelist's can co-exist side-by-side in the same slab-page
each with a separate head pointer.
3) it is the visibility of the head pointer that needs synchronization.
Given these properties, the brilliant part is that the detached
freelist can be constructed without any need for synchronization. The
freelist is constructed directly in the page objects, without any
synchronization needed. The detached freelist is allocated on the
stack of the function call kmem_cache_free_bulk. Thus, the freelist
head pointer is not visible to other CPUs.
All objects in a SLUB freelist must belong to the same slab-page.
Thus, constructing the detached freelist is about matching objects
that belong to the same slab-page. The bulk free array is scanned is
a progressive manor with a limited look-ahead facility.
Kmem debug support is handled in call of slab_free().
Notice kmem_cache_free_bulk no longer need to disable IRQs. This
only slowed down single free bulk with approx 3 cycles.
Performance data:
Benchmarked[1] obj size 256 bytes on CPU i7-4790K @ 4.00GHz
SLUB fastpath single object quick reuse: 47 cycles(tsc) 11.931 ns
To get stable and comparable numbers, the kernel have been booted with
"slab_merge" (this also improve performance for larger bulk sizes).
Performance data, compared against fallback bulking:
bulk - fallback bulk - improvement with this patch
1 - 62 cycles(tsc) 15.662 ns - 49 cycles(tsc) 12.407 ns- improved 21.0%
2 - 55 cycles(tsc) 13.935 ns - 30 cycles(tsc) 7.506 ns - improved 45.5%
3 - 53 cycles(tsc) 13.341 ns - 23 cycles(tsc) 5.865 ns - improved 56.6%
4 - 52 cycles(tsc) 13.081 ns - 20 cycles(tsc) 5.048 ns - improved 61.5%
8 - 50 cycles(tsc) 12.627 ns - 18 cycles(tsc) 4.659 ns - improved 64.0%
16 - 49 cycles(tsc) 12.412 ns - 17 cycles(tsc) 4.495 ns - improved 65.3%
30 - 49 cycles(tsc) 12.484 ns - 18 cycles(tsc) 4.533 ns - improved 63.3%
32 - 50 cycles(tsc) 12.627 ns - 18 cycles(tsc) 4.707 ns - improved 64.0%
34 - 96 cycles(tsc) 24.243 ns - 23 cycles(tsc) 5.976 ns - improved 76.0%
48 - 83 cycles(tsc) 20.818 ns - 21 cycles(tsc) 5.329 ns - improved 74.7%
64 - 74 cycles(tsc) 18.700 ns - 20 cycles(tsc) 5.127 ns - improved 73.0%
128 - 90 cycles(tsc) 22.734 ns - 27 cycles(tsc) 6.833 ns - improved 70.0%
158 - 99 cycles(tsc) 24.776 ns - 30 cycles(tsc) 7.583 ns - improved 69.7%
250 - 104 cycles(tsc) 26.089 ns - 37 cycles(tsc) 9.280 ns - improved 64.4%
Performance data, compared current in-kernel bulking:
bulk - curr in-kernel - improvement with this patch
1 - 46 cycles(tsc) - 49 cycles(tsc) - improved (cycles:-3) -6.5%
2 - 27 cycles(tsc) - 30 cycles(tsc) - improved (cycles:-3) -11.1%
3 - 21 cycles(tsc) - 23 cycles(tsc) - improved (cycles:-2) -9.5%
4 - 18 cycles(tsc) - 20 cycles(tsc) - improved (cycles:-2) -11.1%
8 - 17 cycles(tsc) - 18 cycles(tsc) - improved (cycles:-1) -5.9%
16 - 18 cycles(tsc) - 17 cycles(tsc) - improved (cycles: 1) 5.6%
30 - 18 cycles(tsc) - 18 cycles(tsc) - improved (cycles: 0) 0.0%
32 - 18 cycles(tsc) - 18 cycles(tsc) - improved (cycles: 0) 0.0%
34 - 78 cycles(tsc) - 23 cycles(tsc) - improved (cycles:55) 70.5%
48 - 60 cycles(tsc) - 21 cycles(tsc) - improved (cycles:39) 65.0%
64 - 49 cycles(tsc) - 20 cycles(tsc) - improved (cycles:29) 59.2%
128 - 69 cycles(tsc) - 27 cycles(tsc) - improved (cycles:42) 60.9%
158 - 79 cycles(tsc) - 30 cycles(tsc) - improved (cycles:49) 62.0%
250 - 86 cycles(tsc) - 37 cycles(tsc) - improved (cycles:49) 57.0%
Performance with normal SLUB merging is significantly slower for
larger bulking. This is believed to (primarily) be an effect of not
having to share the per-CPU data-structures, as tuning per-CPU size
can achieve similar performance.
bulk - slab_nomerge - normal SLUB merge
1 - 49 cycles(tsc) - 49 cycles(tsc) - merge slower with cycles:0
2 - 30 cycles(tsc) - 30 cycles(tsc) - merge slower with cycles:0
3 - 23 cycles(tsc) - 23 cycles(tsc) - merge slower with cycles:0
4 - 20 cycles(tsc) - 20 cycles(tsc) - merge slower with cycles:0
8 - 18 cycles(tsc) - 18 cycles(tsc) - merge slower with cycles:0
16 - 17 cycles(tsc) - 17 cycles(tsc) - merge slower with cycles:0
30 - 18 cycles(tsc) - 23 cycles(tsc) - merge slower with cycles:5
32 - 18 cycles(tsc) - 22 cycles(tsc) - merge slower with cycles:4
34 - 23 cycles(tsc) - 22 cycles(tsc) - merge slower with cycles:-1
48 - 21 cycles(tsc) - 22 cycles(tsc) - merge slower with cycles:1
64 - 20 cycles(tsc) - 48 cycles(tsc) - merge slower with cycles:28
128 - 27 cycles(tsc) - 57 cycles(tsc) - merge slower with cycles:30
158 - 30 cycles(tsc) - 59 cycles(tsc) - merge slower with cycles:29
250 - 37 cycles(tsc) - 56 cycles(tsc) - merge slower with cycles:19
Joint work with Alexander Duyck.
[1] https://github.com/netoptimizer/prototype-kernel/blob/master/kernel/mm/slab_bulk_test01.c
[akpm@linux-foundation.org: BUG_ON -> WARN_ON;return]
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Acked-by: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-11-20 15:57:49 -08:00
|
|
|
|
2015-09-04 15:45:43 -07:00
|
|
|
|
slub: optimize bulk slowpath free by detached freelist
This change focus on improving the speed of object freeing in the
"slowpath" of kmem_cache_free_bulk.
The calls slab_free (fastpath) and __slab_free (slowpath) have been
extended with support for bulk free, which amortize the overhead of
the (locked) cmpxchg_double.
To use the new bulking feature, we build what I call a detached
freelist. The detached freelist takes advantage of three properties:
1) the free function call owns the object that is about to be freed,
thus writing into this memory is synchronization-free.
2) many freelist's can co-exist side-by-side in the same slab-page
each with a separate head pointer.
3) it is the visibility of the head pointer that needs synchronization.
Given these properties, the brilliant part is that the detached
freelist can be constructed without any need for synchronization. The
freelist is constructed directly in the page objects, without any
synchronization needed. The detached freelist is allocated on the
stack of the function call kmem_cache_free_bulk. Thus, the freelist
head pointer is not visible to other CPUs.
All objects in a SLUB freelist must belong to the same slab-page.
Thus, constructing the detached freelist is about matching objects
that belong to the same slab-page. The bulk free array is scanned is
a progressive manor with a limited look-ahead facility.
Kmem debug support is handled in call of slab_free().
Notice kmem_cache_free_bulk no longer need to disable IRQs. This
only slowed down single free bulk with approx 3 cycles.
Performance data:
Benchmarked[1] obj size 256 bytes on CPU i7-4790K @ 4.00GHz
SLUB fastpath single object quick reuse: 47 cycles(tsc) 11.931 ns
To get stable and comparable numbers, the kernel have been booted with
"slab_merge" (this also improve performance for larger bulk sizes).
Performance data, compared against fallback bulking:
bulk - fallback bulk - improvement with this patch
1 - 62 cycles(tsc) 15.662 ns - 49 cycles(tsc) 12.407 ns- improved 21.0%
2 - 55 cycles(tsc) 13.935 ns - 30 cycles(tsc) 7.506 ns - improved 45.5%
3 - 53 cycles(tsc) 13.341 ns - 23 cycles(tsc) 5.865 ns - improved 56.6%
4 - 52 cycles(tsc) 13.081 ns - 20 cycles(tsc) 5.048 ns - improved 61.5%
8 - 50 cycles(tsc) 12.627 ns - 18 cycles(tsc) 4.659 ns - improved 64.0%
16 - 49 cycles(tsc) 12.412 ns - 17 cycles(tsc) 4.495 ns - improved 65.3%
30 - 49 cycles(tsc) 12.484 ns - 18 cycles(tsc) 4.533 ns - improved 63.3%
32 - 50 cycles(tsc) 12.627 ns - 18 cycles(tsc) 4.707 ns - improved 64.0%
34 - 96 cycles(tsc) 24.243 ns - 23 cycles(tsc) 5.976 ns - improved 76.0%
48 - 83 cycles(tsc) 20.818 ns - 21 cycles(tsc) 5.329 ns - improved 74.7%
64 - 74 cycles(tsc) 18.700 ns - 20 cycles(tsc) 5.127 ns - improved 73.0%
128 - 90 cycles(tsc) 22.734 ns - 27 cycles(tsc) 6.833 ns - improved 70.0%
158 - 99 cycles(tsc) 24.776 ns - 30 cycles(tsc) 7.583 ns - improved 69.7%
250 - 104 cycles(tsc) 26.089 ns - 37 cycles(tsc) 9.280 ns - improved 64.4%
Performance data, compared current in-kernel bulking:
bulk - curr in-kernel - improvement with this patch
1 - 46 cycles(tsc) - 49 cycles(tsc) - improved (cycles:-3) -6.5%
2 - 27 cycles(tsc) - 30 cycles(tsc) - improved (cycles:-3) -11.1%
3 - 21 cycles(tsc) - 23 cycles(tsc) - improved (cycles:-2) -9.5%
4 - 18 cycles(tsc) - 20 cycles(tsc) - improved (cycles:-2) -11.1%
8 - 17 cycles(tsc) - 18 cycles(tsc) - improved (cycles:-1) -5.9%
16 - 18 cycles(tsc) - 17 cycles(tsc) - improved (cycles: 1) 5.6%
30 - 18 cycles(tsc) - 18 cycles(tsc) - improved (cycles: 0) 0.0%
32 - 18 cycles(tsc) - 18 cycles(tsc) - improved (cycles: 0) 0.0%
34 - 78 cycles(tsc) - 23 cycles(tsc) - improved (cycles:55) 70.5%
48 - 60 cycles(tsc) - 21 cycles(tsc) - improved (cycles:39) 65.0%
64 - 49 cycles(tsc) - 20 cycles(tsc) - improved (cycles:29) 59.2%
128 - 69 cycles(tsc) - 27 cycles(tsc) - improved (cycles:42) 60.9%
158 - 79 cycles(tsc) - 30 cycles(tsc) - improved (cycles:49) 62.0%
250 - 86 cycles(tsc) - 37 cycles(tsc) - improved (cycles:49) 57.0%
Performance with normal SLUB merging is significantly slower for
larger bulking. This is believed to (primarily) be an effect of not
having to share the per-CPU data-structures, as tuning per-CPU size
can achieve similar performance.
bulk - slab_nomerge - normal SLUB merge
1 - 49 cycles(tsc) - 49 cycles(tsc) - merge slower with cycles:0
2 - 30 cycles(tsc) - 30 cycles(tsc) - merge slower with cycles:0
3 - 23 cycles(tsc) - 23 cycles(tsc) - merge slower with cycles:0
4 - 20 cycles(tsc) - 20 cycles(tsc) - merge slower with cycles:0
8 - 18 cycles(tsc) - 18 cycles(tsc) - merge slower with cycles:0
16 - 17 cycles(tsc) - 17 cycles(tsc) - merge slower with cycles:0
30 - 18 cycles(tsc) - 23 cycles(tsc) - merge slower with cycles:5
32 - 18 cycles(tsc) - 22 cycles(tsc) - merge slower with cycles:4
34 - 23 cycles(tsc) - 22 cycles(tsc) - merge slower with cycles:-1
48 - 21 cycles(tsc) - 22 cycles(tsc) - merge slower with cycles:1
64 - 20 cycles(tsc) - 48 cycles(tsc) - merge slower with cycles:28
128 - 27 cycles(tsc) - 57 cycles(tsc) - merge slower with cycles:30
158 - 30 cycles(tsc) - 59 cycles(tsc) - merge slower with cycles:29
250 - 37 cycles(tsc) - 56 cycles(tsc) - merge slower with cycles:19
Joint work with Alexander Duyck.
[1] https://github.com/netoptimizer/prototype-kernel/blob/master/kernel/mm/slab_bulk_test01.c
[akpm@linux-foundation.org: BUG_ON -> WARN_ON;return]
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Acked-by: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-11-20 15:57:49 -08:00
|
|
|
|
|
|
|
|
|
2015-09-04 15:45:43 -07:00
|
|
|
|
slub: optimize bulk slowpath free by detached freelist
This change focus on improving the speed of object freeing in the
"slowpath" of kmem_cache_free_bulk.
The calls slab_free (fastpath) and __slab_free (slowpath) have been
extended with support for bulk free, which amortize the overhead of
the (locked) cmpxchg_double.
To use the new bulking feature, we build what I call a detached
freelist. The detached freelist takes advantage of three properties:
1) the free function call owns the object that is about to be freed,
thus writing into this memory is synchronization-free.
2) many freelist's can co-exist side-by-side in the same slab-page
each with a separate head pointer.
3) it is the visibility of the head pointer that needs synchronization.
Given these properties, the brilliant part is that the detached
freelist can be constructed without any need for synchronization. The
freelist is constructed directly in the page objects, without any
synchronization needed. The detached freelist is allocated on the
stack of the function call kmem_cache_free_bulk. Thus, the freelist
head pointer is not visible to other CPUs.
All objects in a SLUB freelist must belong to the same slab-page.
Thus, constructing the detached freelist is about matching objects
that belong to the same slab-page. The bulk free array is scanned is
a progressive manor with a limited look-ahead facility.
Kmem debug support is handled in call of slab_free().
Notice kmem_cache_free_bulk no longer need to disable IRQs. This
only slowed down single free bulk with approx 3 cycles.
Performance data:
Benchmarked[1] obj size 256 bytes on CPU i7-4790K @ 4.00GHz
SLUB fastpath single object quick reuse: 47 cycles(tsc) 11.931 ns
To get stable and comparable numbers, the kernel have been booted with
"slab_merge" (this also improve performance for larger bulk sizes).
Performance data, compared against fallback bulking:
bulk - fallback bulk - improvement with this patch
1 - 62 cycles(tsc) 15.662 ns - 49 cycles(tsc) 12.407 ns- improved 21.0%
2 - 55 cycles(tsc) 13.935 ns - 30 cycles(tsc) 7.506 ns - improved 45.5%
3 - 53 cycles(tsc) 13.341 ns - 23 cycles(tsc) 5.865 ns - improved 56.6%
4 - 52 cycles(tsc) 13.081 ns - 20 cycles(tsc) 5.048 ns - improved 61.5%
8 - 50 cycles(tsc) 12.627 ns - 18 cycles(tsc) 4.659 ns - improved 64.0%
16 - 49 cycles(tsc) 12.412 ns - 17 cycles(tsc) 4.495 ns - improved 65.3%
30 - 49 cycles(tsc) 12.484 ns - 18 cycles(tsc) 4.533 ns - improved 63.3%
32 - 50 cycles(tsc) 12.627 ns - 18 cycles(tsc) 4.707 ns - improved 64.0%
34 - 96 cycles(tsc) 24.243 ns - 23 cycles(tsc) 5.976 ns - improved 76.0%
48 - 83 cycles(tsc) 20.818 ns - 21 cycles(tsc) 5.329 ns - improved 74.7%
64 - 74 cycles(tsc) 18.700 ns - 20 cycles(tsc) 5.127 ns - improved 73.0%
128 - 90 cycles(tsc) 22.734 ns - 27 cycles(tsc) 6.833 ns - improved 70.0%
158 - 99 cycles(tsc) 24.776 ns - 30 cycles(tsc) 7.583 ns - improved 69.7%
250 - 104 cycles(tsc) 26.089 ns - 37 cycles(tsc) 9.280 ns - improved 64.4%
Performance data, compared current in-kernel bulking:
bulk - curr in-kernel - improvement with this patch
1 - 46 cycles(tsc) - 49 cycles(tsc) - improved (cycles:-3) -6.5%
2 - 27 cycles(tsc) - 30 cycles(tsc) - improved (cycles:-3) -11.1%
3 - 21 cycles(tsc) - 23 cycles(tsc) - improved (cycles:-2) -9.5%
4 - 18 cycles(tsc) - 20 cycles(tsc) - improved (cycles:-2) -11.1%
8 - 17 cycles(tsc) - 18 cycles(tsc) - improved (cycles:-1) -5.9%
16 - 18 cycles(tsc) - 17 cycles(tsc) - improved (cycles: 1) 5.6%
30 - 18 cycles(tsc) - 18 cycles(tsc) - improved (cycles: 0) 0.0%
32 - 18 cycles(tsc) - 18 cycles(tsc) - improved (cycles: 0) 0.0%
34 - 78 cycles(tsc) - 23 cycles(tsc) - improved (cycles:55) 70.5%
48 - 60 cycles(tsc) - 21 cycles(tsc) - improved (cycles:39) 65.0%
64 - 49 cycles(tsc) - 20 cycles(tsc) - improved (cycles:29) 59.2%
128 - 69 cycles(tsc) - 27 cycles(tsc) - improved (cycles:42) 60.9%
158 - 79 cycles(tsc) - 30 cycles(tsc) - improved (cycles:49) 62.0%
250 - 86 cycles(tsc) - 37 cycles(tsc) - improved (cycles:49) 57.0%
Performance with normal SLUB merging is significantly slower for
larger bulking. This is believed to (primarily) be an effect of not
having to share the per-CPU data-structures, as tuning per-CPU size
can achieve similar performance.
bulk - slab_nomerge - normal SLUB merge
1 - 49 cycles(tsc) - 49 cycles(tsc) - merge slower with cycles:0
2 - 30 cycles(tsc) - 30 cycles(tsc) - merge slower with cycles:0
3 - 23 cycles(tsc) - 23 cycles(tsc) - merge slower with cycles:0
4 - 20 cycles(tsc) - 20 cycles(tsc) - merge slower with cycles:0
8 - 18 cycles(tsc) - 18 cycles(tsc) - merge slower with cycles:0
16 - 17 cycles(tsc) - 17 cycles(tsc) - merge slower with cycles:0
30 - 18 cycles(tsc) - 23 cycles(tsc) - merge slower with cycles:5
32 - 18 cycles(tsc) - 22 cycles(tsc) - merge slower with cycles:4
34 - 23 cycles(tsc) - 22 cycles(tsc) - merge slower with cycles:-1
48 - 21 cycles(tsc) - 22 cycles(tsc) - merge slower with cycles:1
64 - 20 cycles(tsc) - 48 cycles(tsc) - merge slower with cycles:28
128 - 27 cycles(tsc) - 57 cycles(tsc) - merge slower with cycles:30
158 - 30 cycles(tsc) - 59 cycles(tsc) - merge slower with cycles:29
250 - 37 cycles(tsc) - 56 cycles(tsc) - merge slower with cycles:19
Joint work with Alexander Duyck.
[1] https://github.com/netoptimizer/prototype-kernel/blob/master/kernel/mm/slab_bulk_test01.c
[akpm@linux-foundation.org: BUG_ON -> WARN_ON;return]
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Acked-by: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-11-20 15:57:49 -08:00
|
|
|
|
2021-10-04 14:45:58 +01:00
|
|
|
|
slub: optimize bulk slowpath free by detached freelist
This change focus on improving the speed of object freeing in the
"slowpath" of kmem_cache_free_bulk.
The calls slab_free (fastpath) and __slab_free (slowpath) have been
extended with support for bulk free, which amortize the overhead of
the (locked) cmpxchg_double.
To use the new bulking feature, we build what I call a detached
freelist. The detached freelist takes advantage of three properties:
1) the free function call owns the object that is about to be freed,
thus writing into this memory is synchronization-free.
2) many freelist's can co-exist side-by-side in the same slab-page
each with a separate head pointer.
3) it is the visibility of the head pointer that needs synchronization.
Given these properties, the brilliant part is that the detached
freelist can be constructed without any need for synchronization. The
freelist is constructed directly in the page objects, without any
synchronization needed. The detached freelist is allocated on the
stack of the function call kmem_cache_free_bulk. Thus, the freelist
head pointer is not visible to other CPUs.
All objects in a SLUB freelist must belong to the same slab-page.
Thus, constructing the detached freelist is about matching objects
that belong to the same slab-page. The bulk free array is scanned is
a progressive manor with a limited look-ahead facility.
Kmem debug support is handled in call of slab_free().
Notice kmem_cache_free_bulk no longer need to disable IRQs. This
only slowed down single free bulk with approx 3 cycles.
Performance data:
Benchmarked[1] obj size 256 bytes on CPU i7-4790K @ 4.00GHz
SLUB fastpath single object quick reuse: 47 cycles(tsc) 11.931 ns
To get stable and comparable numbers, the kernel have been booted with
"slab_merge" (this also improve performance for larger bulk sizes).
Performance data, compared against fallback bulking:
bulk - fallback bulk - improvement with this patch
1 - 62 cycles(tsc) 15.662 ns - 49 cycles(tsc) 12.407 ns- improved 21.0%
2 - 55 cycles(tsc) 13.935 ns - 30 cycles(tsc) 7.506 ns - improved 45.5%
3 - 53 cycles(tsc) 13.341 ns - 23 cycles(tsc) 5.865 ns - improved 56.6%
4 - 52 cycles(tsc) 13.081 ns - 20 cycles(tsc) 5.048 ns - improved 61.5%
8 - 50 cycles(tsc) 12.627 ns - 18 cycles(tsc) 4.659 ns - improved 64.0%
16 - 49 cycles(tsc) 12.412 ns - 17 cycles(tsc) 4.495 ns - improved 65.3%
30 - 49 cycles(tsc) 12.484 ns - 18 cycles(tsc) 4.533 ns - improved 63.3%
32 - 50 cycles(tsc) 12.627 ns - 18 cycles(tsc) 4.707 ns - improved 64.0%
34 - 96 cycles(tsc) 24.243 ns - 23 cycles(tsc) 5.976 ns - improved 76.0%
48 - 83 cycles(tsc) 20.818 ns - 21 cycles(tsc) 5.329 ns - improved 74.7%
64 - 74 cycles(tsc) 18.700 ns - 20 cycles(tsc) 5.127 ns - improved 73.0%
128 - 90 cycles(tsc) 22.734 ns - 27 cycles(tsc) 6.833 ns - improved 70.0%
158 - 99 cycles(tsc) 24.776 ns - 30 cycles(tsc) 7.583 ns - improved 69.7%
250 - 104 cycles(tsc) 26.089 ns - 37 cycles(tsc) 9.280 ns - improved 64.4%
Performance data, compared current in-kernel bulking:
bulk - curr in-kernel - improvement with this patch
1 - 46 cycles(tsc) - 49 cycles(tsc) - improved (cycles:-3) -6.5%
2 - 27 cycles(tsc) - 30 cycles(tsc) - improved (cycles:-3) -11.1%
3 - 21 cycles(tsc) - 23 cycles(tsc) - improved (cycles:-2) -9.5%
4 - 18 cycles(tsc) - 20 cycles(tsc) - improved (cycles:-2) -11.1%
8 - 17 cycles(tsc) - 18 cycles(tsc) - improved (cycles:-1) -5.9%
16 - 18 cycles(tsc) - 17 cycles(tsc) - improved (cycles: 1) 5.6%
30 - 18 cycles(tsc) - 18 cycles(tsc) - improved (cycles: 0) 0.0%
32 - 18 cycles(tsc) - 18 cycles(tsc) - improved (cycles: 0) 0.0%
34 - 78 cycles(tsc) - 23 cycles(tsc) - improved (cycles:55) 70.5%
48 - 60 cycles(tsc) - 21 cycles(tsc) - improved (cycles:39) 65.0%
64 - 49 cycles(tsc) - 20 cycles(tsc) - improved (cycles:29) 59.2%
128 - 69 cycles(tsc) - 27 cycles(tsc) - improved (cycles:42) 60.9%
158 - 79 cycles(tsc) - 30 cycles(tsc) - improved (cycles:49) 62.0%
250 - 86 cycles(tsc) - 37 cycles(tsc) - improved (cycles:49) 57.0%
Performance with normal SLUB merging is significantly slower for
larger bulking. This is believed to (primarily) be an effect of not
having to share the per-CPU data-structures, as tuning per-CPU size
can achieve similar performance.
bulk - slab_nomerge - normal SLUB merge
1 - 49 cycles(tsc) - 49 cycles(tsc) - merge slower with cycles:0
2 - 30 cycles(tsc) - 30 cycles(tsc) - merge slower with cycles:0
3 - 23 cycles(tsc) - 23 cycles(tsc) - merge slower with cycles:0
4 - 20 cycles(tsc) - 20 cycles(tsc) - merge slower with cycles:0
8 - 18 cycles(tsc) - 18 cycles(tsc) - merge slower with cycles:0
16 - 17 cycles(tsc) - 17 cycles(tsc) - merge slower with cycles:0
30 - 18 cycles(tsc) - 23 cycles(tsc) - merge slower with cycles:5
32 - 18 cycles(tsc) - 22 cycles(tsc) - merge slower with cycles:4
34 - 23 cycles(tsc) - 22 cycles(tsc) - merge slower with cycles:-1
48 - 21 cycles(tsc) - 22 cycles(tsc) - merge slower with cycles:1
64 - 20 cycles(tsc) - 48 cycles(tsc) - merge slower with cycles:28
128 - 27 cycles(tsc) - 57 cycles(tsc) - merge slower with cycles:30
158 - 30 cycles(tsc) - 59 cycles(tsc) - merge slower with cycles:29
250 - 37 cycles(tsc) - 56 cycles(tsc) - merge slower with cycles:19
Joint work with Alexander Duyck.
[1] https://github.com/netoptimizer/prototype-kernel/blob/master/kernel/mm/slab_bulk_test01.c
[akpm@linux-foundation.org: BUG_ON -> WARN_ON;return]
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Acked-by: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-11-20 15:57:49 -08:00
|
|
|
|
2015-09-04 15:45:43 -07:00
|
|
|
|
2023-11-03 20:24:51 +01:00
|
|
|
|
|
|
|
|
|
slub: optimize bulk slowpath free by detached freelist
This change focus on improving the speed of object freeing in the
"slowpath" of kmem_cache_free_bulk.
The calls slab_free (fastpath) and __slab_free (slowpath) have been
extended with support for bulk free, which amortize the overhead of
the (locked) cmpxchg_double.
To use the new bulking feature, we build what I call a detached
freelist. The detached freelist takes advantage of three properties:
1) the free function call owns the object that is about to be freed,
thus writing into this memory is synchronization-free.
2) many freelist's can co-exist side-by-side in the same slab-page
each with a separate head pointer.
3) it is the visibility of the head pointer that needs synchronization.
Given these properties, the brilliant part is that the detached
freelist can be constructed without any need for synchronization. The
freelist is constructed directly in the page objects, without any
synchronization needed. The detached freelist is allocated on the
stack of the function call kmem_cache_free_bulk. Thus, the freelist
head pointer is not visible to other CPUs.
All objects in a SLUB freelist must belong to the same slab-page.
Thus, constructing the detached freelist is about matching objects
that belong to the same slab-page. The bulk free array is scanned is
a progressive manor with a limited look-ahead facility.
Kmem debug support is handled in call of slab_free().
Notice kmem_cache_free_bulk no longer need to disable IRQs. This
only slowed down single free bulk with approx 3 cycles.
Performance data:
Benchmarked[1] obj size 256 bytes on CPU i7-4790K @ 4.00GHz
SLUB fastpath single object quick reuse: 47 cycles(tsc) 11.931 ns
To get stable and comparable numbers, the kernel have been booted with
"slab_merge" (this also improve performance for larger bulk sizes).
Performance data, compared against fallback bulking:
bulk - fallback bulk - improvement with this patch
1 - 62 cycles(tsc) 15.662 ns - 49 cycles(tsc) 12.407 ns- improved 21.0%
2 - 55 cycles(tsc) 13.935 ns - 30 cycles(tsc) 7.506 ns - improved 45.5%
3 - 53 cycles(tsc) 13.341 ns - 23 cycles(tsc) 5.865 ns - improved 56.6%
4 - 52 cycles(tsc) 13.081 ns - 20 cycles(tsc) 5.048 ns - improved 61.5%
8 - 50 cycles(tsc) 12.627 ns - 18 cycles(tsc) 4.659 ns - improved 64.0%
16 - 49 cycles(tsc) 12.412 ns - 17 cycles(tsc) 4.495 ns - improved 65.3%
30 - 49 cycles(tsc) 12.484 ns - 18 cycles(tsc) 4.533 ns - improved 63.3%
32 - 50 cycles(tsc) 12.627 ns - 18 cycles(tsc) 4.707 ns - improved 64.0%
34 - 96 cycles(tsc) 24.243 ns - 23 cycles(tsc) 5.976 ns - improved 76.0%
48 - 83 cycles(tsc) 20.818 ns - 21 cycles(tsc) 5.329 ns - improved 74.7%
64 - 74 cycles(tsc) 18.700 ns - 20 cycles(tsc) 5.127 ns - improved 73.0%
128 - 90 cycles(tsc) 22.734 ns - 27 cycles(tsc) 6.833 ns - improved 70.0%
158 - 99 cycles(tsc) 24.776 ns - 30 cycles(tsc) 7.583 ns - improved 69.7%
250 - 104 cycles(tsc) 26.089 ns - 37 cycles(tsc) 9.280 ns - improved 64.4%
Performance data, compared current in-kernel bulking:
bulk - curr in-kernel - improvement with this patch
1 - 46 cycles(tsc) - 49 cycles(tsc) - improved (cycles:-3) -6.5%
2 - 27 cycles(tsc) - 30 cycles(tsc) - improved (cycles:-3) -11.1%
3 - 21 cycles(tsc) - 23 cycles(tsc) - improved (cycles:-2) -9.5%
4 - 18 cycles(tsc) - 20 cycles(tsc) - improved (cycles:-2) -11.1%
8 - 17 cycles(tsc) - 18 cycles(tsc) - improved (cycles:-1) -5.9%
16 - 18 cycles(tsc) - 17 cycles(tsc) - improved (cycles: 1) 5.6%
30 - 18 cycles(tsc) - 18 cycles(tsc) - improved (cycles: 0) 0.0%
32 - 18 cycles(tsc) - 18 cycles(tsc) - improved (cycles: 0) 0.0%
34 - 78 cycles(tsc) - 23 cycles(tsc) - improved (cycles:55) 70.5%
48 - 60 cycles(tsc) - 21 cycles(tsc) - improved (cycles:39) 65.0%
64 - 49 cycles(tsc) - 20 cycles(tsc) - improved (cycles:29) 59.2%
128 - 69 cycles(tsc) - 27 cycles(tsc) - improved (cycles:42) 60.9%
158 - 79 cycles(tsc) - 30 cycles(tsc) - improved (cycles:49) 62.0%
250 - 86 cycles(tsc) - 37 cycles(tsc) - improved (cycles:49) 57.0%
Performance with normal SLUB merging is significantly slower for
larger bulking. This is believed to (primarily) be an effect of not
having to share the per-CPU data-structures, as tuning per-CPU size
can achieve similar performance.
bulk - slab_nomerge - normal SLUB merge
1 - 49 cycles(tsc) - 49 cycles(tsc) - merge slower with cycles:0
2 - 30 cycles(tsc) - 30 cycles(tsc) - merge slower with cycles:0
3 - 23 cycles(tsc) - 23 cycles(tsc) - merge slower with cycles:0
4 - 20 cycles(tsc) - 20 cycles(tsc) - merge slower with cycles:0
8 - 18 cycles(tsc) - 18 cycles(tsc) - merge slower with cycles:0
16 - 17 cycles(tsc) - 17 cycles(tsc) - merge slower with cycles:0
30 - 18 cycles(tsc) - 23 cycles(tsc) - merge slower with cycles:5
32 - 18 cycles(tsc) - 22 cycles(tsc) - merge slower with cycles:4
34 - 23 cycles(tsc) - 22 cycles(tsc) - merge slower with cycles:-1
48 - 21 cycles(tsc) - 22 cycles(tsc) - merge slower with cycles:1
64 - 20 cycles(tsc) - 48 cycles(tsc) - merge slower with cycles:28
128 - 27 cycles(tsc) - 57 cycles(tsc) - merge slower with cycles:30
158 - 30 cycles(tsc) - 59 cycles(tsc) - merge slower with cycles:29
250 - 37 cycles(tsc) - 56 cycles(tsc) - merge slower with cycles:19
Joint work with Alexander Duyck.
[1] https://github.com/netoptimizer/prototype-kernel/blob/master/kernel/mm/slab_bulk_test01.c
[akpm@linux-foundation.org: BUG_ON -> WARN_ON;return]
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Acked-by: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-11-20 15:57:49 -08:00
|
|
|
|
2015-09-04 15:45:34 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-11-15 18:14:31 +01:00
|
|
|
|
2023-11-02 16:34:39 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-09-04 15:45:34 -07:00
|
|
|
|
2015-09-04 15:45:37 -07:00
|
|
|
|
2023-02-07 15:16:53 +01:00
|
|
|
|
2015-09-04 15:45:37 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-05-21 14:03:23 +02:00
|
|
|
|
2023-02-07 15:16:53 +01:00
|
|
|
|
2015-09-04 15:45:37 -07:00
|
|
|
|
|
|
|
|
|
2021-02-25 17:19:16 -08:00
|
|
|
|
2015-09-04 15:45:37 -07:00
|
|
|
|
2021-02-25 17:19:16 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-09-04 15:45:40 -07:00
|
|
|
|
2020-03-17 01:28:45 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-02-07 15:16:53 +01:00
|
|
|
|
mm, slub: move disabling/enabling irqs to ___slab_alloc()
Currently __slab_alloc() disables irqs around the whole ___slab_alloc(). This
includes cases where this is not needed, such as when the allocation ends up in
the page allocator and has to awkwardly enable irqs back based on gfp flags.
Also the whole kmem_cache_alloc_bulk() is executed with irqs disabled even when
it hits the __slab_alloc() slow path, and long periods with disabled interrupts
are undesirable.
As a first step towards reducing irq disabled periods, move irq handling into
___slab_alloc(). Callers will instead prevent the s->cpu_slab percpu pointer
from becoming invalid via get_cpu_ptr(), thus preempt_disable(). This does not
protect against modification by an irq handler, which is still done by disabled
irq for most of ___slab_alloc(). As a small immediate benefit,
slab_out_of_memory() from ___slab_alloc() is now called with irqs enabled.
kmem_cache_alloc_bulk() disables irqs for its fastpath and then re-enables them
before calling ___slab_alloc(), which then disables them at its discretion. The
whole kmem_cache_alloc_bulk() operation also disables preemption.
When ___slab_alloc() calls new_slab() to allocate a new page, re-enable
preemption, because new_slab() will re-enable interrupts in contexts that allow
blocking (this will be improved by later patches).
The patch itself will thus increase overhead a bit due to disabled preemption
(on configs where it matters) and increased disabling/enabling irqs in
kmem_cache_alloc_bulk(), but that will be gradually improved in the following
patches.
Note in __slab_alloc() we need to change the #ifdef CONFIG_PREEMPT guard to
CONFIG_PREEMPT_COUNT to make sure preempt disable/enable is properly paired in
all configurations. On configs without involuntary preemption and debugging
the re-read of kmem_cache_cpu pointer is still compiled out as it was before.
[ Mike Galbraith <efault@gmx.de>: Fix kmem_cache_alloc_bulk() error path ]
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2021-05-07 19:32:31 +02:00
|
|
|
|
2015-09-04 15:45:40 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-11-20 15:57:38 -08:00
|
|
|
|
mm/slub: enable debugging memory wasting of kmalloc
kmalloc's API family is critical for mm, with one nature that it will
round up the request size to a fixed one (mostly power of 2). Say
when user requests memory for '2^n + 1' bytes, actually 2^(n+1) bytes
could be allocated, so in worst case, there is around 50% memory
space waste.
The wastage is not a big issue for requests that get allocated/freed
quickly, but may cause problems with objects that have longer life
time.
We've met a kernel boot OOM panic (v5.10), and from the dumped slab
info:
[ 26.062145] kmalloc-2k 814056KB 814056KB
From debug we found there are huge number of 'struct iova_magazine',
whose size is 1032 bytes (1024 + 8), so each allocation will waste
1016 bytes. Though the issue was solved by giving the right (bigger)
size of RAM, it is still nice to optimize the size (either use a
kmalloc friendly size or create a dedicated slab for it).
And from lkml archive, there was another crash kernel OOM case [1]
back in 2019, which seems to be related with the similar slab waste
situation, as the log is similar:
[ 4.332648] iommu: Adding device 0000:20:02.0 to group 16
[ 4.338946] swapper/0 invoked oom-killer: gfp_mask=0x6040c0(GFP_KERNEL|__GFP_COMP), nodemask=(null), order=0, oom_score_adj=0
...
[ 4.857565] kmalloc-2048 59164KB 59164KB
The crash kernel only has 256M memory, and 59M is pretty big here.
(Note: the related code has been changed and optimised in recent
kernel [2], these logs are just picked to demo the problem, also
a patch changing its size to 1024 bytes has been merged)
So add an way to track each kmalloc's memory waste info, and
leverage the existing SLUB debug framework (specifically
SLUB_STORE_USER) to show its call stack of original allocation,
so that user can evaluate the waste situation, identify some hot
spots and optimize accordingly, for a better utilization of memory.
The waste info is integrated into existing interface:
'/sys/kernel/debug/slab/kmalloc-xx/alloc_traces', one example of
'kmalloc-4k' after boot is:
126 ixgbe_alloc_q_vector+0xbe/0x830 [ixgbe] waste=233856/1856 age=280763/281414/282065 pid=1330 cpus=32 nodes=1
__kmem_cache_alloc_node+0x11f/0x4e0
__kmalloc_node+0x4e/0x140
ixgbe_alloc_q_vector+0xbe/0x830 [ixgbe]
ixgbe_init_interrupt_scheme+0x2ae/0xc90 [ixgbe]
ixgbe_probe+0x165f/0x1d20 [ixgbe]
local_pci_probe+0x78/0xc0
work_for_cpu_fn+0x26/0x40
...
which means in 'kmalloc-4k' slab, there are 126 requests of
2240 bytes which got a 4KB space (wasting 1856 bytes each
and 233856 bytes in total), from ixgbe_alloc_q_vector().
And when system starts some real workload like multiple docker
instances, there could are more severe waste.
[1]. https://lkml.org/lkml/2019/8/12/266
[2]. https://lore.kernel.org/lkml/2920df89-9975-5785-f79b-257d3052dfaf@huawei.com/
[Thanks Hyeonggon for pointing out several bugs about sorting/format]
[Thanks Vlastimil for suggesting way to reduce memory usage of
orig_size and keep it only for kmalloc objects]
Signed-off-by: Feng Tang <feng.tang@intel.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Robin Murphy <robin.murphy@arm.com>
Cc: John Garry <john.garry@huawei.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2022-09-13 14:54:20 +08:00
|
|
|
|
2015-11-20 15:57:38 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-09-04 15:45:40 -07:00
|
|
|
|
2019-10-14 14:11:57 -07:00
|
|
|
|
|
|
|
|
|
2023-02-07 15:16:53 +01:00
|
|
|
|
mm, slub: move disabling/enabling irqs to ___slab_alloc()
Currently __slab_alloc() disables irqs around the whole ___slab_alloc(). This
includes cases where this is not needed, such as when the allocation ends up in
the page allocator and has to awkwardly enable irqs back based on gfp flags.
Also the whole kmem_cache_alloc_bulk() is executed with irqs disabled even when
it hits the __slab_alloc() slow path, and long periods with disabled interrupts
are undesirable.
As a first step towards reducing irq disabled periods, move irq handling into
___slab_alloc(). Callers will instead prevent the s->cpu_slab percpu pointer
from becoming invalid via get_cpu_ptr(), thus preempt_disable(). This does not
protect against modification by an irq handler, which is still done by disabled
irq for most of ___slab_alloc(). As a small immediate benefit,
slab_out_of_memory() from ___slab_alloc() is now called with irqs enabled.
kmem_cache_alloc_bulk() disables irqs for its fastpath and then re-enables them
before calling ___slab_alloc(), which then disables them at its discretion. The
whole kmem_cache_alloc_bulk() operation also disables preemption.
When ___slab_alloc() calls new_slab() to allocate a new page, re-enable
preemption, because new_slab() will re-enable interrupts in contexts that allow
blocking (this will be improved by later patches).
The patch itself will thus increase overhead a bit due to disabled preemption
(on configs where it matters) and increased disabling/enabling irqs in
kmem_cache_alloc_bulk(), but that will be gradually improved in the following
patches.
Note in __slab_alloc() we need to change the #ifdef CONFIG_PREEMPT guard to
CONFIG_PREEMPT_COUNT to make sure preempt disable/enable is properly paired in
all configurations. On configs without involuntary preemption and debugging
the re-read of kmem_cache_cpu pointer is still compiled out as it was before.
[ Mike Galbraith <efault@gmx.de>: Fix kmem_cache_alloc_bulk() error path ]
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2021-05-07 19:32:31 +02:00
|
|
|
|
2015-09-04 15:45:40 -07:00
|
|
|
|
|
|
|
|
|
2015-09-04 15:45:37 -07:00
|
|
|
|
|
|
|
|
|
2019-10-14 14:11:57 -07:00
|
|
|
|
2023-08-07 20:50:44 +02:00
|
|
|
|
2015-09-04 15:45:37 -07:00
|
|
|
|
|
|
|
|
|
2023-02-07 15:16:53 +01:00
|
|
|
|
2021-05-21 14:03:23 +02:00
|
|
|
|
2015-09-04 15:45:37 -07:00
|
|
|
|
2015-11-20 15:57:58 -08:00
|
|
|
|
2022-11-21 16:23:50 +01:00
|
|
|
|
2015-11-20 15:57:38 -08:00
|
|
|
|
2021-05-21 14:03:23 +02:00
|
|
|
|
2023-11-02 16:34:39 +01:00
|
|
|
|
2015-11-20 15:57:58 -08:00
|
|
|
|
2022-11-21 16:23:50 +01:00
|
|
|
|
|
|
|
|
|
2022-11-15 18:14:31 +01:00
|
|
|
|
|
|
|
|
|
2023-11-02 16:34:39 +01:00
|
|
|
|
2022-11-15 18:14:31 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-11-02 16:34:39 +01:00
|
|
|
|
2022-11-15 18:14:31 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-11-21 16:23:50 +01:00
|
|
|
|
|
|
|
|
|
2024-03-21 09:36:47 -07:00
|
|
|
|
|
|
|
|
|
2022-11-21 16:23:50 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-03-26 11:37:38 +01:00
|
|
|
|
2022-11-21 16:23:50 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-11-02 16:34:39 +01:00
|
|
|
|
2024-03-26 11:37:38 +01:00
|
|
|
|
|
|
|
|
|
2022-11-21 16:23:50 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-03-26 11:37:38 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-11-02 16:34:39 +01:00
|
|
|
|
2022-11-21 16:23:50 +01:00
|
|
|
|
2015-09-04 15:45:34 -07:00
|
|
|
|
2024-03-21 09:36:47 -07:00
|
|
|
|
2015-09-04 15:45:34 -07:00
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2007-05-09 02:32:39 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-09 02:32:39 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-05-06 18:06:47 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-04-05 16:21:39 -07:00
|
|
|
|
2022-11-21 11:44:54 +01:00
|
|
|
|
|
|
|
|
|
2018-04-05 16:21:39 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-09 02:32:39 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-04-14 19:13:29 +03:00
|
|
|
|
2007-05-09 02:32:39 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2007-05-09 02:32:39 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2023-12-15 11:41:48 +08:00
|
|
|
|
|
|
|
|
|
2007-05-09 02:32:39 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-04-29 22:54:51 -07:00
|
|
|
|
2007-05-09 02:32:39 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2021-10-04 14:45:51 +01:00
|
|
|
|
2023-09-08 12:18:09 +02:00
|
|
|
|
2018-06-07 17:09:10 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2018-04-05 16:21:39 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2023-09-08 12:18:09 +02:00
|
|
|
|
2007-05-09 02:32:46 -07:00
|
|
|
|
2018-04-05 16:21:39 -07:00
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2018-06-07 17:09:10 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2007-05-09 02:32:46 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
2007-05-09 02:32:39 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-06-07 17:09:10 -07:00
|
|
|
|
2007-05-09 02:32:46 -07:00
|
|
|
|
2018-04-05 16:21:39 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-09-08 12:18:09 +02:00
|
|
|
|
2007-05-09 02:32:46 -07:00
|
|
|
|
|
|
|
|
|
mm, slub: better heuristic for number of cpus when calculating slab order
When creating a new kmem cache, SLUB determines how large the slab pages
will based on number of inputs, including the number of CPUs in the
system. Larger slab pages mean that more objects can be allocated/free
from per-cpu slabs before accessing shared structures, but also
potentially more memory can be wasted due to low slab usage and
fragmentation. The rough idea of using number of CPUs is that larger
systems will be more likely to benefit from reduced contention, and also
should have enough memory to spare.
Number of CPUs used to be determined as nr_cpu_ids, which is number of
possible cpus, but on some systems many will never be onlined, thus
commit 045ab8c9487b ("mm/slub: let number of online CPUs determine the
slub page order") changed it to nr_online_cpus(). However, for kmem
caches created early before CPUs are onlined, this may lead to
permamently low slab page sizes.
Vincent reports a regression [1] of hackbench on arm64 systems:
"I'm facing significant performances regression on a large arm64
server system (224 CPUs). Regressions is also present on small arm64
system (8 CPUs) but in a far smaller order of magnitude
On 224 CPUs system : 9 iterations of hackbench -l 16000 -g 16
v5.11-rc4 : 9.135sec (+/- 0.45%)
v5.11-rc4 + revert this patch: 3.173sec (+/- 0.48%)
v5.10: 3.136sec (+/- 0.40%)"
Mel reports a regression [2] of hackbench on x86_64, with lockstat suggesting
page allocator contention:
"i.e. the patch incurs a 7% to 32% performance penalty. This bisected
cleanly yesterday when I was looking for the regression and then
found the thread.
Numerous caches change size. For example, kmalloc-512 goes from
order-0 (vanilla) to order-2 with the revert.
So mostly this is down to the number of times SLUB calls into the
page allocator which only caches order-0 pages on a per-cpu basis"
Clearly num_online_cpus() doesn't work too early in bootup. We could
change the order dynamically in a memory hotplug callback, but runtime
order changing for existing kmem caches has been already shown as
dangerous, and removed in 32a6f409b693 ("mm, slub: remove runtime
allocation order changes").
It could be resurrected in a safe manner with some effort, but to fix
the regression we need something simpler.
We could use num_present_cpus() that should be the number of physically
present CPUs even before they are onlined. That would work for PowerPC
[3], which triggered the original commit, but that still doesn't work on
arm64 [4] as explained in [5].
So this patch tries to determine the best available value without
specific arch knowledge.
- num_present_cpus() if the number is larger than 1, as that means the
arch is likely setting it properly
- nr_cpu_ids otherwise
This should fix the reported regressions while also keeping the effect
of 045ab8c9487b for PowerPC systems. It's possible there are
configurations where num_present_cpus() is 1 during boot while
nr_cpu_ids is at the same time bloated, so these (if they exist) would
keep the large orders based on nr_cpu_ids as was before 045ab8c9487b.
[1] https://lore.kernel.org/linux-mm/CAKfTPtA_JgMf_+zdFbcb_V9rM7JBWNPjAz9irgwFj7Rou=xzZg@mail.gmail.com/
[2] https://lore.kernel.org/linux-mm/20210128134512.GF3592@techsingularity.net/
[3] https://lore.kernel.org/linux-mm/20210123051607.GC2587010@in.ibm.com/
[4] https://lore.kernel.org/linux-mm/CAKfTPtAjyVmS5VYvU6DBxg4-JEo5bdmWbngf-03YsY18cmWv_g@mail.gmail.com/
[5] https://lore.kernel.org/linux-mm/20210126230305.GD30941@willie-the-truck/
Link: https://lkml.kernel.org/r/20210208134108.22286-1-vbabka@suse.cz
Fixes: 045ab8c9487b ("mm/slub: let number of online CPUs determine the slub page order")
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reported-by: Vincent Guittot <vincent.guittot@linaro.org>
Reported-by: Mel Gorman <mgorman@techsingularity.net>
Tested-by: Mel Gorman <mgorman@techsingularity.net>
Tested-by: Vincent Guittot <vincent.guittot@linaro.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Cc: Bharata B Rao <bharata@linux.ibm.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Roman Gushchin <guro@fb.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Jann Horn <jannh@google.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Will Deacon <will@kernel.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-02-09 13:42:32 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-09-08 12:18:09 +02:00
|
|
|
|
mm, slub: better heuristic for number of cpus when calculating slab order
When creating a new kmem cache, SLUB determines how large the slab pages
will based on number of inputs, including the number of CPUs in the
system. Larger slab pages mean that more objects can be allocated/free
from per-cpu slabs before accessing shared structures, but also
potentially more memory can be wasted due to low slab usage and
fragmentation. The rough idea of using number of CPUs is that larger
systems will be more likely to benefit from reduced contention, and also
should have enough memory to spare.
Number of CPUs used to be determined as nr_cpu_ids, which is number of
possible cpus, but on some systems many will never be onlined, thus
commit 045ab8c9487b ("mm/slub: let number of online CPUs determine the
slub page order") changed it to nr_online_cpus(). However, for kmem
caches created early before CPUs are onlined, this may lead to
permamently low slab page sizes.
Vincent reports a regression [1] of hackbench on arm64 systems:
"I'm facing significant performances regression on a large arm64
server system (224 CPUs). Regressions is also present on small arm64
system (8 CPUs) but in a far smaller order of magnitude
On 224 CPUs system : 9 iterations of hackbench -l 16000 -g 16
v5.11-rc4 : 9.135sec (+/- 0.45%)
v5.11-rc4 + revert this patch: 3.173sec (+/- 0.48%)
v5.10: 3.136sec (+/- 0.40%)"
Mel reports a regression [2] of hackbench on x86_64, with lockstat suggesting
page allocator contention:
"i.e. the patch incurs a 7% to 32% performance penalty. This bisected
cleanly yesterday when I was looking for the regression and then
found the thread.
Numerous caches change size. For example, kmalloc-512 goes from
order-0 (vanilla) to order-2 with the revert.
So mostly this is down to the number of times SLUB calls into the
page allocator which only caches order-0 pages on a per-cpu basis"
Clearly num_online_cpus() doesn't work too early in bootup. We could
change the order dynamically in a memory hotplug callback, but runtime
order changing for existing kmem caches has been already shown as
dangerous, and removed in 32a6f409b693 ("mm, slub: remove runtime
allocation order changes").
It could be resurrected in a safe manner with some effort, but to fix
the regression we need something simpler.
We could use num_present_cpus() that should be the number of physically
present CPUs even before they are onlined. That would work for PowerPC
[3], which triggered the original commit, but that still doesn't work on
arm64 [4] as explained in [5].
So this patch tries to determine the best available value without
specific arch knowledge.
- num_present_cpus() if the number is larger than 1, as that means the
arch is likely setting it properly
- nr_cpu_ids otherwise
This should fix the reported regressions while also keeping the effect
of 045ab8c9487b for PowerPC systems. It's possible there are
configurations where num_present_cpus() is 1 during boot while
nr_cpu_ids is at the same time bloated, so these (if they exist) would
keep the large orders based on nr_cpu_ids as was before 045ab8c9487b.
[1] https://lore.kernel.org/linux-mm/CAKfTPtA_JgMf_+zdFbcb_V9rM7JBWNPjAz9irgwFj7Rou=xzZg@mail.gmail.com/
[2] https://lore.kernel.org/linux-mm/20210128134512.GF3592@techsingularity.net/
[3] https://lore.kernel.org/linux-mm/20210123051607.GC2587010@in.ibm.com/
[4] https://lore.kernel.org/linux-mm/CAKfTPtAjyVmS5VYvU6DBxg4-JEo5bdmWbngf-03YsY18cmWv_g@mail.gmail.com/
[5] https://lore.kernel.org/linux-mm/20210126230305.GD30941@willie-the-truck/
Link: https://lkml.kernel.org/r/20210208134108.22286-1-vbabka@suse.cz
Fixes: 045ab8c9487b ("mm/slub: let number of online CPUs determine the slub page order")
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reported-by: Vincent Guittot <vincent.guittot@linaro.org>
Reported-by: Mel Gorman <mgorman@techsingularity.net>
Tested-by: Mel Gorman <mgorman@techsingularity.net>
Tested-by: Vincent Guittot <vincent.guittot@linaro.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Cc: Bharata B Rao <bharata@linux.ibm.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Roman Gushchin <guro@fb.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Jann Horn <jannh@google.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Will Deacon <will@kernel.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-02-09 13:42:32 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-09-08 12:18:09 +02:00
|
|
|
|
|
|
|
|
|
2009-02-12 18:00:17 +02:00
|
|
|
|
|
|
|
|
|
2023-09-08 12:18:09 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
mm/slub: remove min_objects loop from calculate_order()
calculate_order() currently has two nested loops. The inner one that
gradually modifies the acceptable waste from 1/16 up to 1/4, and the
outer one that decreases min_objects down to 2.
Upon closer inspection, the outer loop is unnecessary. Decreasing
min_objects could have in theory two effects to make the inner loop and
its call to calc_slab_order() succeed where a previous iteration with
higher min_objects would not:
- it could cause the min_objects-derived min_order to fit within
slub_max_order. But min_objects is already pre-capped to max_objects
that's derived from slub_max_order above the loops, so every iteration
tries at least slub_max_order in calc_slab_order()
- it could cause calc_slab_order() to be called with lower min_objects
thus potentially lower min_order in its loop. This would make a
difference if the lower order could cause the fractional waste test to
succeed where a higher order has already failed with same fract_leftover
in the previous iteration with a higher min_order. But that's not
possible, because increasing the order can only result in lower (or
same) fractional waste. If we increase the slab size 2 times, we will
fit at least 2 times the number of objects (thus same fraction of
waste), or it will allow us to fit one more object (lower fraction of
waste).
For more confidence I have tried adding a printk to notify when
decreasing min_objects resulted in a success, and simulated calculations
for a range of object sizes, nr_cpus and page_sizes. As expected, the
printk never triggered.
Thus remove the outer loop and adjust comments accordingly.
There's almost no functional change except a weird corner case when
slub_min_objects=1 on boot command line would cause the whole two nested
loops to be skipped before this patch. Now it would try to find the best
layout as usual, resulting in potentially higher orderthat minimizes
waste. This is not wrong and will be further expanded by the next patch.
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Feng Tang <feng.tang@intel.com>
Reviewed-and-tested-by: Jay Patel <jaypatel@linux.ibm.com>
2023-09-08 10:53:26 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-12-15 11:41:48 +08:00
|
|
|
|
|
|
|
|
|
mm/slub: remove min_objects loop from calculate_order()
calculate_order() currently has two nested loops. The inner one that
gradually modifies the acceptable waste from 1/16 up to 1/4, and the
outer one that decreases min_objects down to 2.
Upon closer inspection, the outer loop is unnecessary. Decreasing
min_objects could have in theory two effects to make the inner loop and
its call to calc_slab_order() succeed where a previous iteration with
higher min_objects would not:
- it could cause the min_objects-derived min_order to fit within
slub_max_order. But min_objects is already pre-capped to max_objects
that's derived from slub_max_order above the loops, so every iteration
tries at least slub_max_order in calc_slab_order()
- it could cause calc_slab_order() to be called with lower min_objects
thus potentially lower min_order in its loop. This would make a
difference if the lower order could cause the fractional waste test to
succeed where a higher order has already failed with same fract_leftover
in the previous iteration with a higher min_order. But that's not
possible, because increasing the order can only result in lower (or
same) fractional waste. If we increase the slab size 2 times, we will
fit at least 2 times the number of objects (thus same fraction of
waste), or it will allow us to fit one more object (lower fraction of
waste).
For more confidence I have tried adding a printk to notify when
decreasing min_objects resulted in a success, and simulated calculations
for a range of object sizes, nr_cpus and page_sizes. As expected, the
printk never triggered.
Thus remove the outer loop and adjust comments accordingly.
There's almost no functional change except a weird corner case when
slub_min_objects=1 on boot command line would cause the whole two nested
loops to be skipped before this patch. Now it would try to find the best
layout as usual, resulting in potentially higher orderthat minimizes
waste. This is not wrong and will be further expanded by the next patch.
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Feng Tang <feng.tang@intel.com>
Reviewed-and-tested-by: Jay Patel <jaypatel@linux.ibm.com>
2023-09-08 10:53:26 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
mm/slub: attempt to find layouts up to 1/2 waste in calculate_order()
The main loop in calculate_order() currently tries to find an order with
at most 1/4 waste. If that's impossible (for particular large object
sizes), there's a fallback that will try to place one object within
slab_max_order.
If we expand the loop boundary to also allow up to 1/2 waste as the last
resort, we can remove the fallback and simplify the code, as the loop
will find an order for such sizes as well. Note we don't need to allow
more than 1/2 waste as that will never happen - calc_slab_order() would
calculate more objects to fit, reducing waste below 1/2.
Successfully finding an order in the loop (compared to the fallback)
will also have the benefit in trying to satisfy min_objects, because the
fallback was passing 1. Thus the resulting slab orders might be larger
(not because it would improve waste, but to reduce pressure on shared
locks), which is one of the goals of calculate_order().
For example, with nr_cpus=1 and 4kB PAGE_SIZE, slub_max_order=3, before
the patch we would get the following orders for these object sizes:
2056 to 10920 - order-3 as selected by the loop
10928 to 12280 - order-2 due to fallback, as <1/4 waste is not possible
12288 to 32768 - order-3 as <1/4 waste is again possible
After the patch:
2056 to 32768 - order-3, because even in the range of 10928 to 12280 we
try to satisfy the calculated min_objects.
As a result the code is simpler and gives more consistent results.
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Feng Tang <feng.tang@intel.com>
Reviewed-and-tested-by: Jay Patel <jaypatel@linux.ibm.com>
2023-09-08 11:47:09 +02:00
|
|
|
|
|
|
|
|
|
2023-12-15 11:41:48 +08:00
|
|
|
|
mm/slub: remove min_objects loop from calculate_order()
calculate_order() currently has two nested loops. The inner one that
gradually modifies the acceptable waste from 1/16 up to 1/4, and the
outer one that decreases min_objects down to 2.
Upon closer inspection, the outer loop is unnecessary. Decreasing
min_objects could have in theory two effects to make the inner loop and
its call to calc_slab_order() succeed where a previous iteration with
higher min_objects would not:
- it could cause the min_objects-derived min_order to fit within
slub_max_order. But min_objects is already pre-capped to max_objects
that's derived from slub_max_order above the loops, so every iteration
tries at least slub_max_order in calc_slab_order()
- it could cause calc_slab_order() to be called with lower min_objects
thus potentially lower min_order in its loop. This would make a
difference if the lower order could cause the fractional waste test to
succeed where a higher order has already failed with same fract_leftover
in the previous iteration with a higher min_order. But that's not
possible, because increasing the order can only result in lower (or
same) fractional waste. If we increase the slab size 2 times, we will
fit at least 2 times the number of objects (thus same fraction of
waste), or it will allow us to fit one more object (lower fraction of
waste).
For more confidence I have tried adding a printk to notify when
decreasing min_objects resulted in a success, and simulated calculations
for a range of object sizes, nr_cpus and page_sizes. As expected, the
printk never triggered.
Thus remove the outer loop and adjust comments accordingly.
There's almost no functional change except a weird corner case when
slub_min_objects=1 on boot command line would cause the whole two nested
loops to be skipped before this patch. Now it would try to find the best
layout as usual, resulting in potentially higher orderthat minimizes
waste. This is not wrong and will be further expanded by the next patch.
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Feng Tang <feng.tang@intel.com>
Reviewed-and-tested-by: Jay Patel <jaypatel@linux.ibm.com>
2023-09-08 10:53:26 +02:00
|
|
|
|
mm/slub: attempt to find layouts up to 1/2 waste in calculate_order()
The main loop in calculate_order() currently tries to find an order with
at most 1/4 waste. If that's impossible (for particular large object
sizes), there's a fallback that will try to place one object within
slab_max_order.
If we expand the loop boundary to also allow up to 1/2 waste as the last
resort, we can remove the fallback and simplify the code, as the loop
will find an order for such sizes as well. Note we don't need to allow
more than 1/2 waste as that will never happen - calc_slab_order() would
calculate more objects to fit, reducing waste below 1/2.
Successfully finding an order in the loop (compared to the fallback)
will also have the benefit in trying to satisfy min_objects, because the
fallback was passing 1. Thus the resulting slab orders might be larger
(not because it would improve waste, but to reduce pressure on shared
locks), which is one of the goals of calculate_order().
For example, with nr_cpus=1 and 4kB PAGE_SIZE, slub_max_order=3, before
the patch we would get the following orders for these object sizes:
2056 to 10920 - order-3 as selected by the loop
10928 to 12280 - order-2 due to fallback, as <1/4 waste is not possible
12288 to 32768 - order-3 as <1/4 waste is again possible
After the patch:
2056 to 32768 - order-3, because even in the range of 10928 to 12280 we
try to satisfy the calculated min_objects.
As a result the code is simpler and gives more consistent results.
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Feng Tang <feng.tang@intel.com>
Reviewed-and-tested-by: Jay Patel <jaypatel@linux.ibm.com>
2023-09-08 11:47:09 +02:00
|
|
|
|
2023-09-08 12:18:09 +02:00
|
|
|
|
mm/slub: remove min_objects loop from calculate_order()
calculate_order() currently has two nested loops. The inner one that
gradually modifies the acceptable waste from 1/16 up to 1/4, and the
outer one that decreases min_objects down to 2.
Upon closer inspection, the outer loop is unnecessary. Decreasing
min_objects could have in theory two effects to make the inner loop and
its call to calc_slab_order() succeed where a previous iteration with
higher min_objects would not:
- it could cause the min_objects-derived min_order to fit within
slub_max_order. But min_objects is already pre-capped to max_objects
that's derived from slub_max_order above the loops, so every iteration
tries at least slub_max_order in calc_slab_order()
- it could cause calc_slab_order() to be called with lower min_objects
thus potentially lower min_order in its loop. This would make a
difference if the lower order could cause the fractional waste test to
succeed where a higher order has already failed with same fract_leftover
in the previous iteration with a higher min_order. But that's not
possible, because increasing the order can only result in lower (or
same) fractional waste. If we increase the slab size 2 times, we will
fit at least 2 times the number of objects (thus same fraction of
waste), or it will allow us to fit one more object (lower fraction of
waste).
For more confidence I have tried adding a printk to notify when
decreasing min_objects resulted in a success, and simulated calculations
for a range of object sizes, nr_cpus and page_sizes. As expected, the
printk never triggered.
Thus remove the outer loop and adjust comments accordingly.
There's almost no functional change except a weird corner case when
slub_min_objects=1 on boot command line would cause the whole two nested
loops to be skipped before this patch. Now it would try to find the best
layout as usual, resulting in potentially higher orderthat minimizes
waste. This is not wrong and will be further expanded by the next patch.
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Feng Tang <feng.tang@intel.com>
Reviewed-and-tested-by: Jay Patel <jaypatel@linux.ibm.com>
2023-09-08 10:53:26 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-09 02:32:46 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-12-15 11:41:48 +08:00
|
|
|
|
2007-05-09 02:32:46 -07:00
|
|
|
|
2023-09-08 09:57:13 +02:00
|
|
|
|
2023-12-28 17:47:04 +03:00
|
|
|
|
2007-05-09 02:32:46 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-08-05 09:28:47 +03:00
|
|
|
|
2012-05-11 00:50:47 +09:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-07-17 04:03:32 -07:00
|
|
|
|
2008-04-14 18:53:02 +03:00
|
|
|
|
2008-09-11 12:25:41 -07:00
|
|
|
|
2007-05-06 14:49:42 -07:00
|
|
|
|
2007-07-17 04:03:32 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
2022-11-15 18:14:31 +01:00
|
|
|
|
2010-08-20 12:37:13 -05:00
|
|
|
|
2007-10-16 01:26:08 -07:00
|
|
|
|
2010-08-20 12:37:14 -05:00
|
|
|
|
2022-10-24 16:14:35 +08:00
|
|
|
|
|
|
|
|
|
2009-12-18 16:26:20 -06:00
|
|
|
|
2011-02-25 11:38:54 -06:00
|
|
|
|
2011-06-02 10:19:41 -04:00
|
|
|
|
|
|
|
|
|
2011-02-25 11:38:54 -06:00
|
|
|
|
2011-06-02 10:19:41 -04:00
|
|
|
|
|
|
|
|
|
2009-12-18 16:26:20 -06:00
|
|
|
|
2011-02-25 11:38:54 -06:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-10-16 01:26:08 -07:00
|
|
|
|
2022-11-15 18:14:31 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-10-16 01:26:08 -07:00
|
|
|
|
2010-08-20 12:37:15 -05:00
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-11-08 20:47:37 +08:00
|
|
|
|
|
|
|
|
|
2007-10-16 01:26:08 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2010-08-20 12:37:13 -05:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
2010-08-20 12:37:15 -05:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
|
|
|
|
|
2014-06-04 16:06:34 -07:00
|
|
|
|
|
|
|
|
|
2007-08-22 14:01:57 -07:00
|
|
|
|
|
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2007-07-17 04:03:32 -07:00
|
|
|
|
2010-09-29 07:15:01 -05:00
|
|
|
|
2007-07-17 04:03:32 -07:00
|
|
|
|
2021-04-29 23:00:06 -07:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
|
|
|
|
|
2018-12-28 00:29:41 -08:00
|
|
|
|
2012-05-11 00:50:47 +09:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2008-02-15 23:45:26 -08:00
|
|
|
|
2014-01-24 07:20:23 -08:00
|
|
|
|
2014-02-10 14:25:46 -08:00
|
|
|
|
|
|
|
|
|
2014-01-24 07:20:23 -08:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2014-08-06 16:04:09 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2014-08-06 16:04:09 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2017-09-06 16:19:15 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-02-17 13:11:37 -08:00
|
|
|
|
|
|
|
|
|
2016-07-26 15:21:59 -07:00
|
|
|
|
2022-11-15 18:14:31 +01:00
|
|
|
|
2016-02-17 13:11:37 -08:00
|
|
|
|
2022-11-15 18:14:31 +01:00
|
|
|
|
2016-02-17 13:11:37 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2010-08-20 12:37:13 -05:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
mm, slab, slub: stop taking memory hotplug lock
Since commit 03afc0e25f7f ("slab: get_online_mems for
kmem_cache_{create,destroy,shrink}") we are taking memory hotplug lock for
SLAB and SLUB when creating, destroying or shrinking a cache. It is quite
a heavy lock and it's best to avoid it if possible, as we had several
issues with lockdep complaining about ordering in the past, see e.g.
e4f8e513c3d3 ("mm/slub: fix a deadlock in show_slab_objects()").
The problem scenario in 03afc0e25f7f (solved by the memory hotplug lock)
can be summarized as follows: while there's slab_mutex synchronizing new
kmem cache creation and SLUB's MEM_GOING_ONLINE callback
slab_mem_going_online_callback(), we may miss creation of kmem_cache_node
for the hotplugged node in the new kmem cache, because the hotplug
callback doesn't yet see the new cache, and cache creation in
init_kmem_cache_nodes() only inits kmem_cache_node for nodes in the
N_NORMAL_MEMORY nodemask, which however may not yet include the new node,
as that happens only later after the MEM_GOING_ONLINE callback.
Instead of using get/put_online_mems(), the problem can be solved by SLUB
maintaining its own nodemask of nodes for which it has allocated the
per-node kmem_cache_node structures. This nodemask would generally mirror
the N_NORMAL_MEMORY nodemask, but would be updated only in under SLUB's
control in its memory hotplug callbacks under the slab_mutex. This patch
adds such nodemask and its handling.
Commit 03afc0e25f7f mentiones "issues like [the one above]", but there
don't appear to be further issues. All the paths (shared for SLAB and
SLUB) taking the memory hotplug locks are also taking the slab_mutex,
except kmem_cache_shrink() where 03afc0e25f7f replaced slab_mutex with
get/put_online_mems().
We however cannot simply restore slab_mutex in kmem_cache_shrink(), as
SLUB can enters the function from a write to sysfs 'shrink' file, thus
holding kernfs lock, and in kmem_cache_create() the kernfs lock is nested
within slab_mutex. But on closer inspection we don't actually need to
protect kmem_cache_shrink() from hotplug callbacks: While SLUB's
__kmem_cache_shrink() does for_each_kmem_cache_node(), missing a new node
added in parallel hotplug is not fatal, and parallel hotremove does not
free kmem_cache_node's anymore after the previous patch, so use-after free
cannot happen. The per-node shrinking itself is protected by
n->list_lock. Same is true for SLAB, and SLOB is no-op.
SLAB also doesn't need the memory hotplug locking, which it only gained by
03afc0e25f7f through the shared paths in slab_common.c. Its memory
hotplug callbacks are also protected by slab_mutex against races with
these paths. The problem of SLUB relying on N_NORMAL_MEMORY doesn't apply
to SLAB, as its setup_kmem_cache_nodes relies on N_ONLINE, and the new
node is already set there during the MEM_GOING_ONLINE callback, so no
special care is needed for SLAB.
As such, this patch removes all get/put_online_mems() usage by the slab
subsystem.
Link: https://lkml.kernel.org/r/20210113131634.3671-3-vbabka@suse.cz
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Christoph Lameter <cl@linux.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Qian Cai <cai@redhat.com>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-02-24 12:01:12 -08:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
2010-05-21 14:41:35 -07:00
|
|
|
|
2010-08-20 12:37:13 -05:00
|
|
|
|
2010-05-21 14:41:35 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2010-08-20 12:37:15 -05:00
|
|
|
|
2010-08-20 12:37:13 -05:00
|
|
|
|
2010-05-21 14:41:35 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-05-11 00:50:47 +09:00
|
|
|
|
2017-09-06 16:19:15 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-07-06 15:36:34 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
mm, slub: change percpu partial accounting from objects to pages
With CONFIG_SLUB_CPU_PARTIAL enabled, SLUB keeps a percpu list of
partial slabs that can be promoted to cpu slab when the previous one is
depleted, without accessing the shared partial list. A slab can be
added to this list by 1) refill of an empty list from get_partial_node()
- once we really have to access the shared partial list, we acquire
multiple slabs to amortize the cost of locking, and 2) first free to a
previously full slab - instead of putting the slab on a shared partial
list, we can more cheaply freeze it and put it on the per-cpu list.
To control how large a percpu partial list can grow for a kmem cache,
set_cpu_partial() calculates a target number of free objects on each
cpu's percpu partial list, and this can be also set by the sysfs file
cpu_partial.
However, the tracking of actual number of objects is imprecise, in order
to limit overhead from cpu X freeing an objects to a slab on percpu
partial list of cpu Y. Basically, the percpu partial slabs form a
single linked list, and when we add a new slab to the list with current
head "oldpage", we set in the struct page of the slab we're adding:
page->pages = oldpage->pages + 1; // this is precise
page->pobjects = oldpage->pobjects + (page->objects - page->inuse);
page->next = oldpage;
Thus the real number of free objects in the slab (objects - inuse) is
only determined at the moment of adding the slab to the percpu partial
list, and further freeing doesn't update the pobjects counter nor
propagate it to the current list head. As Jann reports [1], this can
easily lead to large inaccuracies, where the target number of objects
(up to 30 by default) can translate to the same number of (empty) slab
pages on the list. In case 2) above, we put a slab with 1 free object
on the list, thus only increase page->pobjects by 1, even if there are
subsequent frees on the same slab. Jann has noticed this in practice
and so did we [2] when investigating significant increase of kmemcg
usage after switching from SLAB to SLUB.
While this is no longer a problem in kmemcg context thanks to the
accounting rewrite in 5.9, the memory waste is still not ideal and it's
questionable whether it makes sense to perform free object count based
control when object counts can easily become so much inaccurate. So
this patch converts the accounting to be based on number of pages only
(which is precise) and removes the page->pobjects field completely.
This is also ultimately simpler.
To retain the existing set_cpu_partial() heuristic, first calculate the
target number of objects as previously, but then convert it to target
number of pages by assuming the pages will be half-filled on average.
This assumption might obviously also be inaccurate in practice, but
cannot degrade to actual number of pages being equal to the target
number of objects.
We could also skip the intermediate step with target number of objects
and rewrite the heuristic in terms of pages. However we still have the
sysfs file cpu_partial which uses number of objects and could break
existing users if it suddenly becomes number of pages, so this patch
doesn't do that.
In practice, after this patch the heuristics limit the size of percpu
partial list up to 2 pages. In case of a reported regression (which
would mean some workload has benefited from the previous imprecise
object based counting), we can tune the heuristics to get a better
compromise within the new scheme, while still avoid the unexpectedly
long percpu partial lists.
[1] https://lore.kernel.org/linux-mm/CAG48ez2Qx5K1Cab-m8BdSibp6wLTip6ro4=-umR7BLsEgjEYzA@mail.gmail.com/
[2] https://lore.kernel.org/all/2f0f46e8-2535-410a-1859-e9cfa4e57c18@suse.cz/
==========
Evaluation
==========
Mel was kind enough to run v1 through mmtests machinery for netperf
(localhost) and hackbench and, for most significant results see below.
So there are some apparent regressions, especially with hackbench, which
I think ultimately boils down to having shorter percpu partial lists on
average and some benchmarks benefiting from longer ones. Monitoring
slab usage also indicated less memory usage by slab. Based on that, the
following patch will bump the defaults to allow longer percpu partial
lists than after this patch.
However the goal is certainly not such that we would limit the percpu
partial lists to 30 pages just because previously a specific alloc/free
pattern could lead to the limit of 30 objects translate to a limit to 30
pages - that would make little sense. This is a correctness patch, and
if a workload benefits from larger lists, the sysfs tuning knobs are
still there to allow that.
Netperf
2-socket Intel(R) Xeon(R) Gold 5218R CPU @ 2.10GHz (20 cores, 40 threads per socket), 384GB RAM
TCP-RR:
hmean before 127045.79 after 121092.94 (-4.69%, worse)
stddev before 2634.37 after 1254.08
UDP-RR:
hmean before 166985.45 after 160668.94 ( -3.78%, worse)
stddev before 4059.69 after 1943.63
2-socket Intel(R) Xeon(R) CPU E5-2698 v4 @ 2.20GHz (20 cores, 40 threads per socket), 512GB RAM
TCP-RR:
hmean before 84173.25 after 76914.72 ( -8.62%, worse)
UDP-RR:
hmean before 93571.12 after 96428.69 ( 3.05%, better)
stddev before 23118.54 after 16828.14
2-socket Intel(R) Xeon(R) CPU E5-2670 v3 @ 2.30GHz (12 cores, 24 threads per socket), 64GB RAM
TCP-RR:
hmean before 49984.92 after 48922.27 ( -2.13%, worse)
stddev before 6248.15 after 4740.51
UDP-RR:
hmean before 61854.31 after 68761.81 ( 11.17%, better)
stddev before 4093.54 after 5898.91
other machines - within 2%
Hackbench
(results before and after the patch, negative % means worse)
2-socket AMD EPYC 7713 (64 cores, 128 threads per core), 256GB RAM
hackbench-process-sockets
Amean 1 0.5380 0.5583 ( -3.78%)
Amean 4 0.7510 0.8150 ( -8.52%)
Amean 7 0.7930 0.9533 ( -20.22%)
Amean 12 0.7853 1.1313 ( -44.06%)
Amean 21 1.1520 1.4993 ( -30.15%)
Amean 30 1.6223 1.9237 ( -18.57%)
Amean 48 2.6767 2.9903 ( -11.72%)
Amean 79 4.0257 5.1150 ( -27.06%)
Amean 110 5.5193 7.4720 ( -35.38%)
Amean 141 7.2207 9.9840 ( -38.27%)
Amean 172 8.4770 12.1963 ( -43.88%)
Amean 203 9.6473 14.3137 ( -48.37%)
Amean 234 11.3960 18.7917 ( -64.90%)
Amean 265 13.9627 22.4607 ( -60.86%)
Amean 296 14.9163 26.0483 ( -74.63%)
hackbench-thread-sockets
Amean 1 0.5597 0.5877 ( -5.00%)
Amean 4 0.7913 0.8960 ( -13.23%)
Amean 7 0.8190 1.0017 ( -22.30%)
Amean 12 0.9560 1.1727 ( -22.66%)
Amean 21 1.7587 1.5660 ( 10.96%)
Amean 30 2.4477 1.9807 ( 19.08%)
Amean 48 3.4573 3.0630 ( 11.41%)
Amean 79 4.7903 5.1733 ( -8.00%)
Amean 110 6.1370 7.4220 ( -20.94%)
Amean 141 7.5777 9.2617 ( -22.22%)
Amean 172 9.2280 11.0907 ( -20.18%)
Amean 203 10.2793 13.3470 ( -29.84%)
Amean 234 11.2410 17.1070 ( -52.18%)
Amean 265 12.5970 23.3323 ( -85.22%)
Amean 296 17.1540 24.2857 ( -41.57%)
2-socket Intel(R) Xeon(R) Gold 5218R CPU @ 2.10GHz (20 cores, 40 threads
per socket), 384GB RAM
hackbench-process-sockets
Amean 1 0.5760 0.4793 ( 16.78%)
Amean 4 0.9430 0.9707 ( -2.93%)
Amean 7 1.5517 1.8843 ( -21.44%)
Amean 12 2.4903 2.7267 ( -9.49%)
Amean 21 3.9560 4.2877 ( -8.38%)
Amean 30 5.4613 5.8343 ( -6.83%)
Amean 48 8.5337 9.2937 ( -8.91%)
Amean 79 14.0670 15.2630 ( -8.50%)
Amean 110 19.2253 21.2467 ( -10.51%)
Amean 141 23.7557 25.8550 ( -8.84%)
Amean 172 28.4407 29.7603 ( -4.64%)
Amean 203 33.3407 33.9927 ( -1.96%)
Amean 234 38.3633 39.1150 ( -1.96%)
Amean 265 43.4420 43.8470 ( -0.93%)
Amean 296 48.3680 48.9300 ( -1.16%)
hackbench-thread-sockets
Amean 1 0.6080 0.6493 ( -6.80%)
Amean 4 1.0000 1.0513 ( -5.13%)
Amean 7 1.6607 2.0260 ( -22.00%)
Amean 12 2.7637 2.9273 ( -5.92%)
Amean 21 5.0613 4.5153 ( 10.79%)
Amean 30 6.3340 6.1140 ( 3.47%)
Amean 48 9.0567 9.5577 ( -5.53%)
Amean 79 14.5657 15.7983 ( -8.46%)
Amean 110 19.6213 21.6333 ( -10.25%)
Amean 141 24.1563 26.2697 ( -8.75%)
Amean 172 28.9687 30.2187 ( -4.32%)
Amean 203 33.9763 34.6970 ( -2.12%)
Amean 234 38.8647 39.3207 ( -1.17%)
Amean 265 44.0813 44.1507 ( -0.16%)
Amean 296 49.2040 49.4330 ( -0.47%)
2-socket Intel(R) Xeon(R) CPU E5-2698 v4 @ 2.20GHz (20 cores, 40 threads
per socket), 512GB RAM
hackbench-process-sockets
Amean 1 0.5027 0.5017 ( 0.20%)
Amean 4 1.1053 1.2033 ( -8.87%)
Amean 7 1.8760 2.1820 ( -16.31%)
Amean 12 2.9053 3.1810 ( -9.49%)
Amean 21 4.6777 4.9920 ( -6.72%)
Amean 30 6.5180 6.7827 ( -4.06%)
Amean 48 10.0710 10.5227 ( -4.48%)
Amean 79 16.4250 17.5053 ( -6.58%)
Amean 110 22.6203 24.4617 ( -8.14%)
Amean 141 28.0967 31.0363 ( -10.46%)
Amean 172 34.4030 36.9233 ( -7.33%)
Amean 203 40.5933 43.0850 ( -6.14%)
Amean 234 46.6477 48.7220 ( -4.45%)
Amean 265 53.0530 53.9597 ( -1.71%)
Amean 296 59.2760 59.9213 ( -1.09%)
hackbench-thread-sockets
Amean 1 0.5363 0.5330 ( 0.62%)
Amean 4 1.1647 1.2157 ( -4.38%)
Amean 7 1.9237 2.2833 ( -18.70%)
Amean 12 2.9943 3.3110 ( -10.58%)
Amean 21 4.9987 5.1880 ( -3.79%)
Amean 30 6.7583 7.0043 ( -3.64%)
Amean 48 10.4547 10.8353 ( -3.64%)
Amean 79 16.6707 17.6790 ( -6.05%)
Amean 110 22.8207 24.4403 ( -7.10%)
Amean 141 28.7090 31.0533 ( -8.17%)
Amean 172 34.9387 36.8260 ( -5.40%)
Amean 203 41.1567 43.0450 ( -4.59%)
Amean 234 47.3790 48.5307 ( -2.43%)
Amean 265 53.9543 54.6987 ( -1.38%)
Amean 296 60.0820 60.2163 ( -0.22%)
1-socket Intel(R) Xeon(R) CPU E3-1240 v5 @ 3.50GHz (4 cores, 8 threads),
32 GB RAM
hackbench-process-sockets
Amean 1 1.4760 1.5773 ( -6.87%)
Amean 3 3.9370 4.0910 ( -3.91%)
Amean 5 6.6797 6.9357 ( -3.83%)
Amean 7 9.3367 9.7150 ( -4.05%)
Amean 12 15.7627 16.1400 ( -2.39%)
Amean 18 23.5360 23.6890 ( -0.65%)
Amean 24 31.0663 31.3137 ( -0.80%)
Amean 30 38.7283 39.0037 ( -0.71%)
Amean 32 41.3417 41.6097 ( -0.65%)
hackbench-thread-sockets
Amean 1 1.5250 1.6043 ( -5.20%)
Amean 3 4.0897 4.2603 ( -4.17%)
Amean 5 6.7760 7.0933 ( -4.68%)
Amean 7 9.4817 9.9157 ( -4.58%)
Amean 12 15.9610 16.3937 ( -2.71%)
Amean 18 23.9543 24.3417 ( -1.62%)
Amean 24 31.4400 31.7217 ( -0.90%)
Amean 30 39.2457 39.5467 ( -0.77%)
Amean 32 41.8267 42.1230 ( -0.71%)
2-socket Intel(R) Xeon(R) CPU E5-2670 v3 @ 2.30GHz (12 cores, 24 threads
per socket), 64GB RAM
hackbench-process-sockets
Amean 1 1.0347 1.0880 ( -5.15%)
Amean 4 1.7267 1.8527 ( -7.30%)
Amean 7 2.6707 2.8110 ( -5.25%)
Amean 12 4.1617 4.3383 ( -4.25%)
Amean 21 7.0070 7.2600 ( -3.61%)
Amean 30 9.9187 10.2397 ( -3.24%)
Amean 48 15.6710 16.3923 ( -4.60%)
Amean 79 24.7743 26.1247 ( -5.45%)
Amean 110 34.3000 35.9307 ( -4.75%)
Amean 141 44.2043 44.8010 ( -1.35%)
Amean 172 54.2430 54.7260 ( -0.89%)
Amean 192 60.6557 60.9777 ( -0.53%)
hackbench-thread-sockets
Amean 1 1.0610 1.1353 ( -7.01%)
Amean 4 1.7543 1.9140 ( -9.10%)
Amean 7 2.7840 2.9573 ( -6.23%)
Amean 12 4.3813 4.4937 ( -2.56%)
Amean 21 7.3460 7.5350 ( -2.57%)
Amean 30 10.2313 10.5190 ( -2.81%)
Amean 48 15.9700 16.5940 ( -3.91%)
Amean 79 25.3973 26.6637 ( -4.99%)
Amean 110 35.1087 36.4797 ( -3.91%)
Amean 141 45.8220 46.3053 ( -1.05%)
Amean 172 55.4917 55.7320 ( -0.43%)
Amean 192 62.7490 62.5410 ( 0.33%)
Link: https://lkml.kernel.org/r/20211012134651.11258-1-vbabka@suse.cz
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reported-by: Jann Horn <jannh@google.com>
Cc: Roman Gushchin <guro@fb.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-11-05 13:35:17 -07:00
|
|
|
|
|
|
|
|
|
2017-07-06 15:36:34 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
mm, slub: change percpu partial accounting from objects to pages
With CONFIG_SLUB_CPU_PARTIAL enabled, SLUB keeps a percpu list of
partial slabs that can be promoted to cpu slab when the previous one is
depleted, without accessing the shared partial list. A slab can be
added to this list by 1) refill of an empty list from get_partial_node()
- once we really have to access the shared partial list, we acquire
multiple slabs to amortize the cost of locking, and 2) first free to a
previously full slab - instead of putting the slab on a shared partial
list, we can more cheaply freeze it and put it on the per-cpu list.
To control how large a percpu partial list can grow for a kmem cache,
set_cpu_partial() calculates a target number of free objects on each
cpu's percpu partial list, and this can be also set by the sysfs file
cpu_partial.
However, the tracking of actual number of objects is imprecise, in order
to limit overhead from cpu X freeing an objects to a slab on percpu
partial list of cpu Y. Basically, the percpu partial slabs form a
single linked list, and when we add a new slab to the list with current
head "oldpage", we set in the struct page of the slab we're adding:
page->pages = oldpage->pages + 1; // this is precise
page->pobjects = oldpage->pobjects + (page->objects - page->inuse);
page->next = oldpage;
Thus the real number of free objects in the slab (objects - inuse) is
only determined at the moment of adding the slab to the percpu partial
list, and further freeing doesn't update the pobjects counter nor
propagate it to the current list head. As Jann reports [1], this can
easily lead to large inaccuracies, where the target number of objects
(up to 30 by default) can translate to the same number of (empty) slab
pages on the list. In case 2) above, we put a slab with 1 free object
on the list, thus only increase page->pobjects by 1, even if there are
subsequent frees on the same slab. Jann has noticed this in practice
and so did we [2] when investigating significant increase of kmemcg
usage after switching from SLAB to SLUB.
While this is no longer a problem in kmemcg context thanks to the
accounting rewrite in 5.9, the memory waste is still not ideal and it's
questionable whether it makes sense to perform free object count based
control when object counts can easily become so much inaccurate. So
this patch converts the accounting to be based on number of pages only
(which is precise) and removes the page->pobjects field completely.
This is also ultimately simpler.
To retain the existing set_cpu_partial() heuristic, first calculate the
target number of objects as previously, but then convert it to target
number of pages by assuming the pages will be half-filled on average.
This assumption might obviously also be inaccurate in practice, but
cannot degrade to actual number of pages being equal to the target
number of objects.
We could also skip the intermediate step with target number of objects
and rewrite the heuristic in terms of pages. However we still have the
sysfs file cpu_partial which uses number of objects and could break
existing users if it suddenly becomes number of pages, so this patch
doesn't do that.
In practice, after this patch the heuristics limit the size of percpu
partial list up to 2 pages. In case of a reported regression (which
would mean some workload has benefited from the previous imprecise
object based counting), we can tune the heuristics to get a better
compromise within the new scheme, while still avoid the unexpectedly
long percpu partial lists.
[1] https://lore.kernel.org/linux-mm/CAG48ez2Qx5K1Cab-m8BdSibp6wLTip6ro4=-umR7BLsEgjEYzA@mail.gmail.com/
[2] https://lore.kernel.org/all/2f0f46e8-2535-410a-1859-e9cfa4e57c18@suse.cz/
==========
Evaluation
==========
Mel was kind enough to run v1 through mmtests machinery for netperf
(localhost) and hackbench and, for most significant results see below.
So there are some apparent regressions, especially with hackbench, which
I think ultimately boils down to having shorter percpu partial lists on
average and some benchmarks benefiting from longer ones. Monitoring
slab usage also indicated less memory usage by slab. Based on that, the
following patch will bump the defaults to allow longer percpu partial
lists than after this patch.
However the goal is certainly not such that we would limit the percpu
partial lists to 30 pages just because previously a specific alloc/free
pattern could lead to the limit of 30 objects translate to a limit to 30
pages - that would make little sense. This is a correctness patch, and
if a workload benefits from larger lists, the sysfs tuning knobs are
still there to allow that.
Netperf
2-socket Intel(R) Xeon(R) Gold 5218R CPU @ 2.10GHz (20 cores, 40 threads per socket), 384GB RAM
TCP-RR:
hmean before 127045.79 after 121092.94 (-4.69%, worse)
stddev before 2634.37 after 1254.08
UDP-RR:
hmean before 166985.45 after 160668.94 ( -3.78%, worse)
stddev before 4059.69 after 1943.63
2-socket Intel(R) Xeon(R) CPU E5-2698 v4 @ 2.20GHz (20 cores, 40 threads per socket), 512GB RAM
TCP-RR:
hmean before 84173.25 after 76914.72 ( -8.62%, worse)
UDP-RR:
hmean before 93571.12 after 96428.69 ( 3.05%, better)
stddev before 23118.54 after 16828.14
2-socket Intel(R) Xeon(R) CPU E5-2670 v3 @ 2.30GHz (12 cores, 24 threads per socket), 64GB RAM
TCP-RR:
hmean before 49984.92 after 48922.27 ( -2.13%, worse)
stddev before 6248.15 after 4740.51
UDP-RR:
hmean before 61854.31 after 68761.81 ( 11.17%, better)
stddev before 4093.54 after 5898.91
other machines - within 2%
Hackbench
(results before and after the patch, negative % means worse)
2-socket AMD EPYC 7713 (64 cores, 128 threads per core), 256GB RAM
hackbench-process-sockets
Amean 1 0.5380 0.5583 ( -3.78%)
Amean 4 0.7510 0.8150 ( -8.52%)
Amean 7 0.7930 0.9533 ( -20.22%)
Amean 12 0.7853 1.1313 ( -44.06%)
Amean 21 1.1520 1.4993 ( -30.15%)
Amean 30 1.6223 1.9237 ( -18.57%)
Amean 48 2.6767 2.9903 ( -11.72%)
Amean 79 4.0257 5.1150 ( -27.06%)
Amean 110 5.5193 7.4720 ( -35.38%)
Amean 141 7.2207 9.9840 ( -38.27%)
Amean 172 8.4770 12.1963 ( -43.88%)
Amean 203 9.6473 14.3137 ( -48.37%)
Amean 234 11.3960 18.7917 ( -64.90%)
Amean 265 13.9627 22.4607 ( -60.86%)
Amean 296 14.9163 26.0483 ( -74.63%)
hackbench-thread-sockets
Amean 1 0.5597 0.5877 ( -5.00%)
Amean 4 0.7913 0.8960 ( -13.23%)
Amean 7 0.8190 1.0017 ( -22.30%)
Amean 12 0.9560 1.1727 ( -22.66%)
Amean 21 1.7587 1.5660 ( 10.96%)
Amean 30 2.4477 1.9807 ( 19.08%)
Amean 48 3.4573 3.0630 ( 11.41%)
Amean 79 4.7903 5.1733 ( -8.00%)
Amean 110 6.1370 7.4220 ( -20.94%)
Amean 141 7.5777 9.2617 ( -22.22%)
Amean 172 9.2280 11.0907 ( -20.18%)
Amean 203 10.2793 13.3470 ( -29.84%)
Amean 234 11.2410 17.1070 ( -52.18%)
Amean 265 12.5970 23.3323 ( -85.22%)
Amean 296 17.1540 24.2857 ( -41.57%)
2-socket Intel(R) Xeon(R) Gold 5218R CPU @ 2.10GHz (20 cores, 40 threads
per socket), 384GB RAM
hackbench-process-sockets
Amean 1 0.5760 0.4793 ( 16.78%)
Amean 4 0.9430 0.9707 ( -2.93%)
Amean 7 1.5517 1.8843 ( -21.44%)
Amean 12 2.4903 2.7267 ( -9.49%)
Amean 21 3.9560 4.2877 ( -8.38%)
Amean 30 5.4613 5.8343 ( -6.83%)
Amean 48 8.5337 9.2937 ( -8.91%)
Amean 79 14.0670 15.2630 ( -8.50%)
Amean 110 19.2253 21.2467 ( -10.51%)
Amean 141 23.7557 25.8550 ( -8.84%)
Amean 172 28.4407 29.7603 ( -4.64%)
Amean 203 33.3407 33.9927 ( -1.96%)
Amean 234 38.3633 39.1150 ( -1.96%)
Amean 265 43.4420 43.8470 ( -0.93%)
Amean 296 48.3680 48.9300 ( -1.16%)
hackbench-thread-sockets
Amean 1 0.6080 0.6493 ( -6.80%)
Amean 4 1.0000 1.0513 ( -5.13%)
Amean 7 1.6607 2.0260 ( -22.00%)
Amean 12 2.7637 2.9273 ( -5.92%)
Amean 21 5.0613 4.5153 ( 10.79%)
Amean 30 6.3340 6.1140 ( 3.47%)
Amean 48 9.0567 9.5577 ( -5.53%)
Amean 79 14.5657 15.7983 ( -8.46%)
Amean 110 19.6213 21.6333 ( -10.25%)
Amean 141 24.1563 26.2697 ( -8.75%)
Amean 172 28.9687 30.2187 ( -4.32%)
Amean 203 33.9763 34.6970 ( -2.12%)
Amean 234 38.8647 39.3207 ( -1.17%)
Amean 265 44.0813 44.1507 ( -0.16%)
Amean 296 49.2040 49.4330 ( -0.47%)
2-socket Intel(R) Xeon(R) CPU E5-2698 v4 @ 2.20GHz (20 cores, 40 threads
per socket), 512GB RAM
hackbench-process-sockets
Amean 1 0.5027 0.5017 ( 0.20%)
Amean 4 1.1053 1.2033 ( -8.87%)
Amean 7 1.8760 2.1820 ( -16.31%)
Amean 12 2.9053 3.1810 ( -9.49%)
Amean 21 4.6777 4.9920 ( -6.72%)
Amean 30 6.5180 6.7827 ( -4.06%)
Amean 48 10.0710 10.5227 ( -4.48%)
Amean 79 16.4250 17.5053 ( -6.58%)
Amean 110 22.6203 24.4617 ( -8.14%)
Amean 141 28.0967 31.0363 ( -10.46%)
Amean 172 34.4030 36.9233 ( -7.33%)
Amean 203 40.5933 43.0850 ( -6.14%)
Amean 234 46.6477 48.7220 ( -4.45%)
Amean 265 53.0530 53.9597 ( -1.71%)
Amean 296 59.2760 59.9213 ( -1.09%)
hackbench-thread-sockets
Amean 1 0.5363 0.5330 ( 0.62%)
Amean 4 1.1647 1.2157 ( -4.38%)
Amean 7 1.9237 2.2833 ( -18.70%)
Amean 12 2.9943 3.3110 ( -10.58%)
Amean 21 4.9987 5.1880 ( -3.79%)
Amean 30 6.7583 7.0043 ( -3.64%)
Amean 48 10.4547 10.8353 ( -3.64%)
Amean 79 16.6707 17.6790 ( -6.05%)
Amean 110 22.8207 24.4403 ( -7.10%)
Amean 141 28.7090 31.0533 ( -8.17%)
Amean 172 34.9387 36.8260 ( -5.40%)
Amean 203 41.1567 43.0450 ( -4.59%)
Amean 234 47.3790 48.5307 ( -2.43%)
Amean 265 53.9543 54.6987 ( -1.38%)
Amean 296 60.0820 60.2163 ( -0.22%)
1-socket Intel(R) Xeon(R) CPU E3-1240 v5 @ 3.50GHz (4 cores, 8 threads),
32 GB RAM
hackbench-process-sockets
Amean 1 1.4760 1.5773 ( -6.87%)
Amean 3 3.9370 4.0910 ( -3.91%)
Amean 5 6.6797 6.9357 ( -3.83%)
Amean 7 9.3367 9.7150 ( -4.05%)
Amean 12 15.7627 16.1400 ( -2.39%)
Amean 18 23.5360 23.6890 ( -0.65%)
Amean 24 31.0663 31.3137 ( -0.80%)
Amean 30 38.7283 39.0037 ( -0.71%)
Amean 32 41.3417 41.6097 ( -0.65%)
hackbench-thread-sockets
Amean 1 1.5250 1.6043 ( -5.20%)
Amean 3 4.0897 4.2603 ( -4.17%)
Amean 5 6.7760 7.0933 ( -4.68%)
Amean 7 9.4817 9.9157 ( -4.58%)
Amean 12 15.9610 16.3937 ( -2.71%)
Amean 18 23.9543 24.3417 ( -1.62%)
Amean 24 31.4400 31.7217 ( -0.90%)
Amean 30 39.2457 39.5467 ( -0.77%)
Amean 32 41.8267 42.1230 ( -0.71%)
2-socket Intel(R) Xeon(R) CPU E5-2670 v3 @ 2.30GHz (12 cores, 24 threads
per socket), 64GB RAM
hackbench-process-sockets
Amean 1 1.0347 1.0880 ( -5.15%)
Amean 4 1.7267 1.8527 ( -7.30%)
Amean 7 2.6707 2.8110 ( -5.25%)
Amean 12 4.1617 4.3383 ( -4.25%)
Amean 21 7.0070 7.2600 ( -3.61%)
Amean 30 9.9187 10.2397 ( -3.24%)
Amean 48 15.6710 16.3923 ( -4.60%)
Amean 79 24.7743 26.1247 ( -5.45%)
Amean 110 34.3000 35.9307 ( -4.75%)
Amean 141 44.2043 44.8010 ( -1.35%)
Amean 172 54.2430 54.7260 ( -0.89%)
Amean 192 60.6557 60.9777 ( -0.53%)
hackbench-thread-sockets
Amean 1 1.0610 1.1353 ( -7.01%)
Amean 4 1.7543 1.9140 ( -9.10%)
Amean 7 2.7840 2.9573 ( -6.23%)
Amean 12 4.3813 4.4937 ( -2.56%)
Amean 21 7.3460 7.5350 ( -2.57%)
Amean 30 10.2313 10.5190 ( -2.81%)
Amean 48 15.9700 16.5940 ( -3.91%)
Amean 79 25.3973 26.6637 ( -4.99%)
Amean 110 35.1087 36.4797 ( -3.91%)
Amean 141 45.8220 46.3053 ( -1.05%)
Amean 172 55.4917 55.7320 ( -0.43%)
Amean 192 62.7490 62.5410 ( 0.33%)
Link: https://lkml.kernel.org/r/20211012134651.11258-1-vbabka@suse.cz
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reported-by: Jann Horn <jannh@google.com>
Cc: Roman Gushchin <guro@fb.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-11-05 13:35:17 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-07-06 15:36:34 -07:00
|
|
|
|
|
|
|
|
|
mm, slub: change percpu partial accounting from objects to pages
With CONFIG_SLUB_CPU_PARTIAL enabled, SLUB keeps a percpu list of
partial slabs that can be promoted to cpu slab when the previous one is
depleted, without accessing the shared partial list. A slab can be
added to this list by 1) refill of an empty list from get_partial_node()
- once we really have to access the shared partial list, we acquire
multiple slabs to amortize the cost of locking, and 2) first free to a
previously full slab - instead of putting the slab on a shared partial
list, we can more cheaply freeze it and put it on the per-cpu list.
To control how large a percpu partial list can grow for a kmem cache,
set_cpu_partial() calculates a target number of free objects on each
cpu's percpu partial list, and this can be also set by the sysfs file
cpu_partial.
However, the tracking of actual number of objects is imprecise, in order
to limit overhead from cpu X freeing an objects to a slab on percpu
partial list of cpu Y. Basically, the percpu partial slabs form a
single linked list, and when we add a new slab to the list with current
head "oldpage", we set in the struct page of the slab we're adding:
page->pages = oldpage->pages + 1; // this is precise
page->pobjects = oldpage->pobjects + (page->objects - page->inuse);
page->next = oldpage;
Thus the real number of free objects in the slab (objects - inuse) is
only determined at the moment of adding the slab to the percpu partial
list, and further freeing doesn't update the pobjects counter nor
propagate it to the current list head. As Jann reports [1], this can
easily lead to large inaccuracies, where the target number of objects
(up to 30 by default) can translate to the same number of (empty) slab
pages on the list. In case 2) above, we put a slab with 1 free object
on the list, thus only increase page->pobjects by 1, even if there are
subsequent frees on the same slab. Jann has noticed this in practice
and so did we [2] when investigating significant increase of kmemcg
usage after switching from SLAB to SLUB.
While this is no longer a problem in kmemcg context thanks to the
accounting rewrite in 5.9, the memory waste is still not ideal and it's
questionable whether it makes sense to perform free object count based
control when object counts can easily become so much inaccurate. So
this patch converts the accounting to be based on number of pages only
(which is precise) and removes the page->pobjects field completely.
This is also ultimately simpler.
To retain the existing set_cpu_partial() heuristic, first calculate the
target number of objects as previously, but then convert it to target
number of pages by assuming the pages will be half-filled on average.
This assumption might obviously also be inaccurate in practice, but
cannot degrade to actual number of pages being equal to the target
number of objects.
We could also skip the intermediate step with target number of objects
and rewrite the heuristic in terms of pages. However we still have the
sysfs file cpu_partial which uses number of objects and could break
existing users if it suddenly becomes number of pages, so this patch
doesn't do that.
In practice, after this patch the heuristics limit the size of percpu
partial list up to 2 pages. In case of a reported regression (which
would mean some workload has benefited from the previous imprecise
object based counting), we can tune the heuristics to get a better
compromise within the new scheme, while still avoid the unexpectedly
long percpu partial lists.
[1] https://lore.kernel.org/linux-mm/CAG48ez2Qx5K1Cab-m8BdSibp6wLTip6ro4=-umR7BLsEgjEYzA@mail.gmail.com/
[2] https://lore.kernel.org/all/2f0f46e8-2535-410a-1859-e9cfa4e57c18@suse.cz/
==========
Evaluation
==========
Mel was kind enough to run v1 through mmtests machinery for netperf
(localhost) and hackbench and, for most significant results see below.
So there are some apparent regressions, especially with hackbench, which
I think ultimately boils down to having shorter percpu partial lists on
average and some benchmarks benefiting from longer ones. Monitoring
slab usage also indicated less memory usage by slab. Based on that, the
following patch will bump the defaults to allow longer percpu partial
lists than after this patch.
However the goal is certainly not such that we would limit the percpu
partial lists to 30 pages just because previously a specific alloc/free
pattern could lead to the limit of 30 objects translate to a limit to 30
pages - that would make little sense. This is a correctness patch, and
if a workload benefits from larger lists, the sysfs tuning knobs are
still there to allow that.
Netperf
2-socket Intel(R) Xeon(R) Gold 5218R CPU @ 2.10GHz (20 cores, 40 threads per socket), 384GB RAM
TCP-RR:
hmean before 127045.79 after 121092.94 (-4.69%, worse)
stddev before 2634.37 after 1254.08
UDP-RR:
hmean before 166985.45 after 160668.94 ( -3.78%, worse)
stddev before 4059.69 after 1943.63
2-socket Intel(R) Xeon(R) CPU E5-2698 v4 @ 2.20GHz (20 cores, 40 threads per socket), 512GB RAM
TCP-RR:
hmean before 84173.25 after 76914.72 ( -8.62%, worse)
UDP-RR:
hmean before 93571.12 after 96428.69 ( 3.05%, better)
stddev before 23118.54 after 16828.14
2-socket Intel(R) Xeon(R) CPU E5-2670 v3 @ 2.30GHz (12 cores, 24 threads per socket), 64GB RAM
TCP-RR:
hmean before 49984.92 after 48922.27 ( -2.13%, worse)
stddev before 6248.15 after 4740.51
UDP-RR:
hmean before 61854.31 after 68761.81 ( 11.17%, better)
stddev before 4093.54 after 5898.91
other machines - within 2%
Hackbench
(results before and after the patch, negative % means worse)
2-socket AMD EPYC 7713 (64 cores, 128 threads per core), 256GB RAM
hackbench-process-sockets
Amean 1 0.5380 0.5583 ( -3.78%)
Amean 4 0.7510 0.8150 ( -8.52%)
Amean 7 0.7930 0.9533 ( -20.22%)
Amean 12 0.7853 1.1313 ( -44.06%)
Amean 21 1.1520 1.4993 ( -30.15%)
Amean 30 1.6223 1.9237 ( -18.57%)
Amean 48 2.6767 2.9903 ( -11.72%)
Amean 79 4.0257 5.1150 ( -27.06%)
Amean 110 5.5193 7.4720 ( -35.38%)
Amean 141 7.2207 9.9840 ( -38.27%)
Amean 172 8.4770 12.1963 ( -43.88%)
Amean 203 9.6473 14.3137 ( -48.37%)
Amean 234 11.3960 18.7917 ( -64.90%)
Amean 265 13.9627 22.4607 ( -60.86%)
Amean 296 14.9163 26.0483 ( -74.63%)
hackbench-thread-sockets
Amean 1 0.5597 0.5877 ( -5.00%)
Amean 4 0.7913 0.8960 ( -13.23%)
Amean 7 0.8190 1.0017 ( -22.30%)
Amean 12 0.9560 1.1727 ( -22.66%)
Amean 21 1.7587 1.5660 ( 10.96%)
Amean 30 2.4477 1.9807 ( 19.08%)
Amean 48 3.4573 3.0630 ( 11.41%)
Amean 79 4.7903 5.1733 ( -8.00%)
Amean 110 6.1370 7.4220 ( -20.94%)
Amean 141 7.5777 9.2617 ( -22.22%)
Amean 172 9.2280 11.0907 ( -20.18%)
Amean 203 10.2793 13.3470 ( -29.84%)
Amean 234 11.2410 17.1070 ( -52.18%)
Amean 265 12.5970 23.3323 ( -85.22%)
Amean 296 17.1540 24.2857 ( -41.57%)
2-socket Intel(R) Xeon(R) Gold 5218R CPU @ 2.10GHz (20 cores, 40 threads
per socket), 384GB RAM
hackbench-process-sockets
Amean 1 0.5760 0.4793 ( 16.78%)
Amean 4 0.9430 0.9707 ( -2.93%)
Amean 7 1.5517 1.8843 ( -21.44%)
Amean 12 2.4903 2.7267 ( -9.49%)
Amean 21 3.9560 4.2877 ( -8.38%)
Amean 30 5.4613 5.8343 ( -6.83%)
Amean 48 8.5337 9.2937 ( -8.91%)
Amean 79 14.0670 15.2630 ( -8.50%)
Amean 110 19.2253 21.2467 ( -10.51%)
Amean 141 23.7557 25.8550 ( -8.84%)
Amean 172 28.4407 29.7603 ( -4.64%)
Amean 203 33.3407 33.9927 ( -1.96%)
Amean 234 38.3633 39.1150 ( -1.96%)
Amean 265 43.4420 43.8470 ( -0.93%)
Amean 296 48.3680 48.9300 ( -1.16%)
hackbench-thread-sockets
Amean 1 0.6080 0.6493 ( -6.80%)
Amean 4 1.0000 1.0513 ( -5.13%)
Amean 7 1.6607 2.0260 ( -22.00%)
Amean 12 2.7637 2.9273 ( -5.92%)
Amean 21 5.0613 4.5153 ( 10.79%)
Amean 30 6.3340 6.1140 ( 3.47%)
Amean 48 9.0567 9.5577 ( -5.53%)
Amean 79 14.5657 15.7983 ( -8.46%)
Amean 110 19.6213 21.6333 ( -10.25%)
Amean 141 24.1563 26.2697 ( -8.75%)
Amean 172 28.9687 30.2187 ( -4.32%)
Amean 203 33.9763 34.6970 ( -2.12%)
Amean 234 38.8647 39.3207 ( -1.17%)
Amean 265 44.0813 44.1507 ( -0.16%)
Amean 296 49.2040 49.4330 ( -0.47%)
2-socket Intel(R) Xeon(R) CPU E5-2698 v4 @ 2.20GHz (20 cores, 40 threads
per socket), 512GB RAM
hackbench-process-sockets
Amean 1 0.5027 0.5017 ( 0.20%)
Amean 4 1.1053 1.2033 ( -8.87%)
Amean 7 1.8760 2.1820 ( -16.31%)
Amean 12 2.9053 3.1810 ( -9.49%)
Amean 21 4.6777 4.9920 ( -6.72%)
Amean 30 6.5180 6.7827 ( -4.06%)
Amean 48 10.0710 10.5227 ( -4.48%)
Amean 79 16.4250 17.5053 ( -6.58%)
Amean 110 22.6203 24.4617 ( -8.14%)
Amean 141 28.0967 31.0363 ( -10.46%)
Amean 172 34.4030 36.9233 ( -7.33%)
Amean 203 40.5933 43.0850 ( -6.14%)
Amean 234 46.6477 48.7220 ( -4.45%)
Amean 265 53.0530 53.9597 ( -1.71%)
Amean 296 59.2760 59.9213 ( -1.09%)
hackbench-thread-sockets
Amean 1 0.5363 0.5330 ( 0.62%)
Amean 4 1.1647 1.2157 ( -4.38%)
Amean 7 1.9237 2.2833 ( -18.70%)
Amean 12 2.9943 3.3110 ( -10.58%)
Amean 21 4.9987 5.1880 ( -3.79%)
Amean 30 6.7583 7.0043 ( -3.64%)
Amean 48 10.4547 10.8353 ( -3.64%)
Amean 79 16.6707 17.6790 ( -6.05%)
Amean 110 22.8207 24.4403 ( -7.10%)
Amean 141 28.7090 31.0533 ( -8.17%)
Amean 172 34.9387 36.8260 ( -5.40%)
Amean 203 41.1567 43.0450 ( -4.59%)
Amean 234 47.3790 48.5307 ( -2.43%)
Amean 265 53.9543 54.6987 ( -1.38%)
Amean 296 60.0820 60.2163 ( -0.22%)
1-socket Intel(R) Xeon(R) CPU E3-1240 v5 @ 3.50GHz (4 cores, 8 threads),
32 GB RAM
hackbench-process-sockets
Amean 1 1.4760 1.5773 ( -6.87%)
Amean 3 3.9370 4.0910 ( -3.91%)
Amean 5 6.6797 6.9357 ( -3.83%)
Amean 7 9.3367 9.7150 ( -4.05%)
Amean 12 15.7627 16.1400 ( -2.39%)
Amean 18 23.5360 23.6890 ( -0.65%)
Amean 24 31.0663 31.3137 ( -0.80%)
Amean 30 38.7283 39.0037 ( -0.71%)
Amean 32 41.3417 41.6097 ( -0.65%)
hackbench-thread-sockets
Amean 1 1.5250 1.6043 ( -5.20%)
Amean 3 4.0897 4.2603 ( -4.17%)
Amean 5 6.7760 7.0933 ( -4.68%)
Amean 7 9.4817 9.9157 ( -4.58%)
Amean 12 15.9610 16.3937 ( -2.71%)
Amean 18 23.9543 24.3417 ( -1.62%)
Amean 24 31.4400 31.7217 ( -0.90%)
Amean 30 39.2457 39.5467 ( -0.77%)
Amean 32 41.8267 42.1230 ( -0.71%)
2-socket Intel(R) Xeon(R) CPU E5-2670 v3 @ 2.30GHz (12 cores, 24 threads
per socket), 64GB RAM
hackbench-process-sockets
Amean 1 1.0347 1.0880 ( -5.15%)
Amean 4 1.7267 1.8527 ( -7.30%)
Amean 7 2.6707 2.8110 ( -5.25%)
Amean 12 4.1617 4.3383 ( -4.25%)
Amean 21 7.0070 7.2600 ( -3.61%)
Amean 30 9.9187 10.2397 ( -3.24%)
Amean 48 15.6710 16.3923 ( -4.60%)
Amean 79 24.7743 26.1247 ( -5.45%)
Amean 110 34.3000 35.9307 ( -4.75%)
Amean 141 44.2043 44.8010 ( -1.35%)
Amean 172 54.2430 54.7260 ( -0.89%)
Amean 192 60.6557 60.9777 ( -0.53%)
hackbench-thread-sockets
Amean 1 1.0610 1.1353 ( -7.01%)
Amean 4 1.7543 1.9140 ( -9.10%)
Amean 7 2.7840 2.9573 ( -6.23%)
Amean 12 4.3813 4.4937 ( -2.56%)
Amean 21 7.3460 7.5350 ( -2.57%)
Amean 30 10.2313 10.5190 ( -2.81%)
Amean 48 15.9700 16.5940 ( -3.91%)
Amean 79 25.3973 26.6637 ( -4.99%)
Amean 110 35.1087 36.4797 ( -3.91%)
Amean 141 45.8220 46.3053 ( -1.05%)
Amean 172 55.4917 55.7320 ( -0.43%)
Amean 192 62.7490 62.5410 ( 0.33%)
Link: https://lkml.kernel.org/r/20211012134651.11258-1-vbabka@suse.cz
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reported-by: Jann Horn <jannh@google.com>
Cc: Roman Gushchin <guro@fb.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-11-05 13:35:17 -07:00
|
|
|
|
2017-07-06 15:36:34 -07:00
|
|
|
|
mm, slub: change percpu partial accounting from objects to pages
With CONFIG_SLUB_CPU_PARTIAL enabled, SLUB keeps a percpu list of
partial slabs that can be promoted to cpu slab when the previous one is
depleted, without accessing the shared partial list. A slab can be
added to this list by 1) refill of an empty list from get_partial_node()
- once we really have to access the shared partial list, we acquire
multiple slabs to amortize the cost of locking, and 2) first free to a
previously full slab - instead of putting the slab on a shared partial
list, we can more cheaply freeze it and put it on the per-cpu list.
To control how large a percpu partial list can grow for a kmem cache,
set_cpu_partial() calculates a target number of free objects on each
cpu's percpu partial list, and this can be also set by the sysfs file
cpu_partial.
However, the tracking of actual number of objects is imprecise, in order
to limit overhead from cpu X freeing an objects to a slab on percpu
partial list of cpu Y. Basically, the percpu partial slabs form a
single linked list, and when we add a new slab to the list with current
head "oldpage", we set in the struct page of the slab we're adding:
page->pages = oldpage->pages + 1; // this is precise
page->pobjects = oldpage->pobjects + (page->objects - page->inuse);
page->next = oldpage;
Thus the real number of free objects in the slab (objects - inuse) is
only determined at the moment of adding the slab to the percpu partial
list, and further freeing doesn't update the pobjects counter nor
propagate it to the current list head. As Jann reports [1], this can
easily lead to large inaccuracies, where the target number of objects
(up to 30 by default) can translate to the same number of (empty) slab
pages on the list. In case 2) above, we put a slab with 1 free object
on the list, thus only increase page->pobjects by 1, even if there are
subsequent frees on the same slab. Jann has noticed this in practice
and so did we [2] when investigating significant increase of kmemcg
usage after switching from SLAB to SLUB.
While this is no longer a problem in kmemcg context thanks to the
accounting rewrite in 5.9, the memory waste is still not ideal and it's
questionable whether it makes sense to perform free object count based
control when object counts can easily become so much inaccurate. So
this patch converts the accounting to be based on number of pages only
(which is precise) and removes the page->pobjects field completely.
This is also ultimately simpler.
To retain the existing set_cpu_partial() heuristic, first calculate the
target number of objects as previously, but then convert it to target
number of pages by assuming the pages will be half-filled on average.
This assumption might obviously also be inaccurate in practice, but
cannot degrade to actual number of pages being equal to the target
number of objects.
We could also skip the intermediate step with target number of objects
and rewrite the heuristic in terms of pages. However we still have the
sysfs file cpu_partial which uses number of objects and could break
existing users if it suddenly becomes number of pages, so this patch
doesn't do that.
In practice, after this patch the heuristics limit the size of percpu
partial list up to 2 pages. In case of a reported regression (which
would mean some workload has benefited from the previous imprecise
object based counting), we can tune the heuristics to get a better
compromise within the new scheme, while still avoid the unexpectedly
long percpu partial lists.
[1] https://lore.kernel.org/linux-mm/CAG48ez2Qx5K1Cab-m8BdSibp6wLTip6ro4=-umR7BLsEgjEYzA@mail.gmail.com/
[2] https://lore.kernel.org/all/2f0f46e8-2535-410a-1859-e9cfa4e57c18@suse.cz/
==========
Evaluation
==========
Mel was kind enough to run v1 through mmtests machinery for netperf
(localhost) and hackbench and, for most significant results see below.
So there are some apparent regressions, especially with hackbench, which
I think ultimately boils down to having shorter percpu partial lists on
average and some benchmarks benefiting from longer ones. Monitoring
slab usage also indicated less memory usage by slab. Based on that, the
following patch will bump the defaults to allow longer percpu partial
lists than after this patch.
However the goal is certainly not such that we would limit the percpu
partial lists to 30 pages just because previously a specific alloc/free
pattern could lead to the limit of 30 objects translate to a limit to 30
pages - that would make little sense. This is a correctness patch, and
if a workload benefits from larger lists, the sysfs tuning knobs are
still there to allow that.
Netperf
2-socket Intel(R) Xeon(R) Gold 5218R CPU @ 2.10GHz (20 cores, 40 threads per socket), 384GB RAM
TCP-RR:
hmean before 127045.79 after 121092.94 (-4.69%, worse)
stddev before 2634.37 after 1254.08
UDP-RR:
hmean before 166985.45 after 160668.94 ( -3.78%, worse)
stddev before 4059.69 after 1943.63
2-socket Intel(R) Xeon(R) CPU E5-2698 v4 @ 2.20GHz (20 cores, 40 threads per socket), 512GB RAM
TCP-RR:
hmean before 84173.25 after 76914.72 ( -8.62%, worse)
UDP-RR:
hmean before 93571.12 after 96428.69 ( 3.05%, better)
stddev before 23118.54 after 16828.14
2-socket Intel(R) Xeon(R) CPU E5-2670 v3 @ 2.30GHz (12 cores, 24 threads per socket), 64GB RAM
TCP-RR:
hmean before 49984.92 after 48922.27 ( -2.13%, worse)
stddev before 6248.15 after 4740.51
UDP-RR:
hmean before 61854.31 after 68761.81 ( 11.17%, better)
stddev before 4093.54 after 5898.91
other machines - within 2%
Hackbench
(results before and after the patch, negative % means worse)
2-socket AMD EPYC 7713 (64 cores, 128 threads per core), 256GB RAM
hackbench-process-sockets
Amean 1 0.5380 0.5583 ( -3.78%)
Amean 4 0.7510 0.8150 ( -8.52%)
Amean 7 0.7930 0.9533 ( -20.22%)
Amean 12 0.7853 1.1313 ( -44.06%)
Amean 21 1.1520 1.4993 ( -30.15%)
Amean 30 1.6223 1.9237 ( -18.57%)
Amean 48 2.6767 2.9903 ( -11.72%)
Amean 79 4.0257 5.1150 ( -27.06%)
Amean 110 5.5193 7.4720 ( -35.38%)
Amean 141 7.2207 9.9840 ( -38.27%)
Amean 172 8.4770 12.1963 ( -43.88%)
Amean 203 9.6473 14.3137 ( -48.37%)
Amean 234 11.3960 18.7917 ( -64.90%)
Amean 265 13.9627 22.4607 ( -60.86%)
Amean 296 14.9163 26.0483 ( -74.63%)
hackbench-thread-sockets
Amean 1 0.5597 0.5877 ( -5.00%)
Amean 4 0.7913 0.8960 ( -13.23%)
Amean 7 0.8190 1.0017 ( -22.30%)
Amean 12 0.9560 1.1727 ( -22.66%)
Amean 21 1.7587 1.5660 ( 10.96%)
Amean 30 2.4477 1.9807 ( 19.08%)
Amean 48 3.4573 3.0630 ( 11.41%)
Amean 79 4.7903 5.1733 ( -8.00%)
Amean 110 6.1370 7.4220 ( -20.94%)
Amean 141 7.5777 9.2617 ( -22.22%)
Amean 172 9.2280 11.0907 ( -20.18%)
Amean 203 10.2793 13.3470 ( -29.84%)
Amean 234 11.2410 17.1070 ( -52.18%)
Amean 265 12.5970 23.3323 ( -85.22%)
Amean 296 17.1540 24.2857 ( -41.57%)
2-socket Intel(R) Xeon(R) Gold 5218R CPU @ 2.10GHz (20 cores, 40 threads
per socket), 384GB RAM
hackbench-process-sockets
Amean 1 0.5760 0.4793 ( 16.78%)
Amean 4 0.9430 0.9707 ( -2.93%)
Amean 7 1.5517 1.8843 ( -21.44%)
Amean 12 2.4903 2.7267 ( -9.49%)
Amean 21 3.9560 4.2877 ( -8.38%)
Amean 30 5.4613 5.8343 ( -6.83%)
Amean 48 8.5337 9.2937 ( -8.91%)
Amean 79 14.0670 15.2630 ( -8.50%)
Amean 110 19.2253 21.2467 ( -10.51%)
Amean 141 23.7557 25.8550 ( -8.84%)
Amean 172 28.4407 29.7603 ( -4.64%)
Amean 203 33.3407 33.9927 ( -1.96%)
Amean 234 38.3633 39.1150 ( -1.96%)
Amean 265 43.4420 43.8470 ( -0.93%)
Amean 296 48.3680 48.9300 ( -1.16%)
hackbench-thread-sockets
Amean 1 0.6080 0.6493 ( -6.80%)
Amean 4 1.0000 1.0513 ( -5.13%)
Amean 7 1.6607 2.0260 ( -22.00%)
Amean 12 2.7637 2.9273 ( -5.92%)
Amean 21 5.0613 4.5153 ( 10.79%)
Amean 30 6.3340 6.1140 ( 3.47%)
Amean 48 9.0567 9.5577 ( -5.53%)
Amean 79 14.5657 15.7983 ( -8.46%)
Amean 110 19.6213 21.6333 ( -10.25%)
Amean 141 24.1563 26.2697 ( -8.75%)
Amean 172 28.9687 30.2187 ( -4.32%)
Amean 203 33.9763 34.6970 ( -2.12%)
Amean 234 38.8647 39.3207 ( -1.17%)
Amean 265 44.0813 44.1507 ( -0.16%)
Amean 296 49.2040 49.4330 ( -0.47%)
2-socket Intel(R) Xeon(R) CPU E5-2698 v4 @ 2.20GHz (20 cores, 40 threads
per socket), 512GB RAM
hackbench-process-sockets
Amean 1 0.5027 0.5017 ( 0.20%)
Amean 4 1.1053 1.2033 ( -8.87%)
Amean 7 1.8760 2.1820 ( -16.31%)
Amean 12 2.9053 3.1810 ( -9.49%)
Amean 21 4.6777 4.9920 ( -6.72%)
Amean 30 6.5180 6.7827 ( -4.06%)
Amean 48 10.0710 10.5227 ( -4.48%)
Amean 79 16.4250 17.5053 ( -6.58%)
Amean 110 22.6203 24.4617 ( -8.14%)
Amean 141 28.0967 31.0363 ( -10.46%)
Amean 172 34.4030 36.9233 ( -7.33%)
Amean 203 40.5933 43.0850 ( -6.14%)
Amean 234 46.6477 48.7220 ( -4.45%)
Amean 265 53.0530 53.9597 ( -1.71%)
Amean 296 59.2760 59.9213 ( -1.09%)
hackbench-thread-sockets
Amean 1 0.5363 0.5330 ( 0.62%)
Amean 4 1.1647 1.2157 ( -4.38%)
Amean 7 1.9237 2.2833 ( -18.70%)
Amean 12 2.9943 3.3110 ( -10.58%)
Amean 21 4.9987 5.1880 ( -3.79%)
Amean 30 6.7583 7.0043 ( -3.64%)
Amean 48 10.4547 10.8353 ( -3.64%)
Amean 79 16.6707 17.6790 ( -6.05%)
Amean 110 22.8207 24.4403 ( -7.10%)
Amean 141 28.7090 31.0533 ( -8.17%)
Amean 172 34.9387 36.8260 ( -5.40%)
Amean 203 41.1567 43.0450 ( -4.59%)
Amean 234 47.3790 48.5307 ( -2.43%)
Amean 265 53.9543 54.6987 ( -1.38%)
Amean 296 60.0820 60.2163 ( -0.22%)
1-socket Intel(R) Xeon(R) CPU E3-1240 v5 @ 3.50GHz (4 cores, 8 threads),
32 GB RAM
hackbench-process-sockets
Amean 1 1.4760 1.5773 ( -6.87%)
Amean 3 3.9370 4.0910 ( -3.91%)
Amean 5 6.6797 6.9357 ( -3.83%)
Amean 7 9.3367 9.7150 ( -4.05%)
Amean 12 15.7627 16.1400 ( -2.39%)
Amean 18 23.5360 23.6890 ( -0.65%)
Amean 24 31.0663 31.3137 ( -0.80%)
Amean 30 38.7283 39.0037 ( -0.71%)
Amean 32 41.3417 41.6097 ( -0.65%)
hackbench-thread-sockets
Amean 1 1.5250 1.6043 ( -5.20%)
Amean 3 4.0897 4.2603 ( -4.17%)
Amean 5 6.7760 7.0933 ( -4.68%)
Amean 7 9.4817 9.9157 ( -4.58%)
Amean 12 15.9610 16.3937 ( -2.71%)
Amean 18 23.9543 24.3417 ( -1.62%)
Amean 24 31.4400 31.7217 ( -0.90%)
Amean 30 39.2457 39.5467 ( -0.77%)
Amean 32 41.8267 42.1230 ( -0.71%)
2-socket Intel(R) Xeon(R) CPU E5-2670 v3 @ 2.30GHz (12 cores, 24 threads
per socket), 64GB RAM
hackbench-process-sockets
Amean 1 1.0347 1.0880 ( -5.15%)
Amean 4 1.7267 1.8527 ( -7.30%)
Amean 7 2.6707 2.8110 ( -5.25%)
Amean 12 4.1617 4.3383 ( -4.25%)
Amean 21 7.0070 7.2600 ( -3.61%)
Amean 30 9.9187 10.2397 ( -3.24%)
Amean 48 15.6710 16.3923 ( -4.60%)
Amean 79 24.7743 26.1247 ( -5.45%)
Amean 110 34.3000 35.9307 ( -4.75%)
Amean 141 44.2043 44.8010 ( -1.35%)
Amean 172 54.2430 54.7260 ( -0.89%)
Amean 192 60.6557 60.9777 ( -0.53%)
hackbench-thread-sockets
Amean 1 1.0610 1.1353 ( -7.01%)
Amean 4 1.7543 1.9140 ( -9.10%)
Amean 7 2.7840 2.9573 ( -6.23%)
Amean 12 4.3813 4.4937 ( -2.56%)
Amean 21 7.3460 7.5350 ( -2.57%)
Amean 30 10.2313 10.5190 ( -2.81%)
Amean 48 15.9700 16.5940 ( -3.91%)
Amean 79 25.3973 26.6637 ( -4.99%)
Amean 110 35.1087 36.4797 ( -3.91%)
Amean 141 45.8220 46.3053 ( -1.05%)
Amean 172 55.4917 55.7320 ( -0.43%)
Amean 192 62.7490 62.5410 ( 0.33%)
Link: https://lkml.kernel.org/r/20211012134651.11258-1-vbabka@suse.cz
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reported-by: Jann Horn <jannh@google.com>
Cc: Roman Gushchin <guro@fb.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-11-05 13:35:17 -07:00
|
|
|
|
2017-07-06 15:36:34 -07:00
|
|
|
|
mm/slub: increase default cpu partial list sizes
The defaults are determined based on object size and can go up to 30 for
objects smaller than 256 bytes. Before the previous patch changed the
accounting, this could have made cpu partial list contain up to 30
pages. After that patch, only up to 2 pages with default allocation
order.
Very short lists limit the usefulness of the whole concept of cpu
partial lists, so this patch aims at a more reasonable default under the
new accounting. The defaults are quadrupled, except for object size >=
PAGE_SIZE where it's doubled. This makes the lists grow up to 10 pages
in practice.
A quick test of booting a kernel under virtme with 4GB RAM and 8 vcpus
shows the following slab memory usage after boot:
Before previous patch (using page->pobjects):
Slab: 36732 kB
SReclaimable: 14836 kB
SUnreclaim: 21896 kB
After previous patch (using page->pages):
Slab: 34720 kB
SReclaimable: 13716 kB
SUnreclaim: 21004 kB
After this patch (using page->pages, higher defaults):
Slab: 35252 kB
SReclaimable: 13944 kB
SUnreclaim: 21308 kB
In the same setup, I also ran 5 times:
hackbench -l 16000 -g 16
Differences in time were in the noise, we can compare slub stats as
given by slabinfo -r skbuff_head_cache (the other cache heavily used by
hackbench, kmalloc-cg-512 looks similar). Negligible stats left out for
brevity.
Before previous patch (using page->pobjects):
Objects: 1408, Memory Total: 401408 Used : 304128
Slab Perf Counter Alloc Free %Al %Fr
--------------------------------------------------
Fastpath 469952498 5946606 91 1
Slowpath 42053573 506059465 8 98
Page Alloc 41093 41044 0 0
Add partial 18 21229327 0 4
Remove partial 20039522 36051 3 0
Cpu partial list 4686640 24767229 0 4
RemoteObj/SlabFrozen 16 124027841 0 24
Total 512006071 512006071
Flushes 18
Slab Deactivation Occurrences %
-------------------------------------------------
Slab empty 4993 0%
Deactivation bypass 24767229 99%
Refilled from foreign frees 21972674 88%
After previous patch (using page->pages):
Objects: 480, Memory Total: 131072 Used : 103680
Slab Perf Counter Alloc Free %Al %Fr
--------------------------------------------------
Fastpath 473016294 5405653 92 1
Slowpath 38989777 506600418 7 98
Page Alloc 32717 32701 0 0
Add partial 3 22749164 0 4
Remove partial 11371127 32474 2 0
Cpu partial list 11686226 23090059 2 4
RemoteObj/SlabFrozen 2 67541803 0 13
Total 512006071 512006071
Flushes 3
Slab Deactivation Occurrences %
-------------------------------------------------
Slab empty 227 0%
Deactivation bypass 23090059 99%
Refilled from foreign frees 27585695 119%
After this patch (using page->pages, higher defaults):
Objects: 896, Memory Total: 229376 Used : 193536
Slab Perf Counter Alloc Free %Al %Fr
--------------------------------------------------
Fastpath 473799295 4980278 92 0
Slowpath 38206776 507025793 7 99
Page Alloc 32295 32267 0 0
Add partial 11 23291143 0 4
Remove partial 5815764 31278 1 0
Cpu partial list 18119280 23967320 3 4
RemoteObj/SlabFrozen 10 76974794 0 15
Total 512006071 512006071
Flushes 11
Slab Deactivation Occurrences %
-------------------------------------------------
Slab empty 989 0%
Deactivation bypass 23967320 99%
Refilled from foreign frees 32358473 135%
As expected, memory usage dropped significantly with change of
accounting, increasing the defaults increased it, but not as much. The
number of page allocation/frees dropped significantly with the new
accounting, but didn't increase with the higher defaults.
Interestingly, the number of fasthpath allocations increased, as well as
allocations from the cpu partial list, even though it's shorter.
Link: https://lkml.kernel.org/r/20211012134651.11258-2-vbabka@suse.cz
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Christoph Lameter <cl@linux.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Jann Horn <jannh@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Roman Gushchin <guro@fb.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-11-05 13:35:20 -07:00
|
|
|
|
2017-07-06 15:36:34 -07:00
|
|
|
|
mm/slub: increase default cpu partial list sizes
The defaults are determined based on object size and can go up to 30 for
objects smaller than 256 bytes. Before the previous patch changed the
accounting, this could have made cpu partial list contain up to 30
pages. After that patch, only up to 2 pages with default allocation
order.
Very short lists limit the usefulness of the whole concept of cpu
partial lists, so this patch aims at a more reasonable default under the
new accounting. The defaults are quadrupled, except for object size >=
PAGE_SIZE where it's doubled. This makes the lists grow up to 10 pages
in practice.
A quick test of booting a kernel under virtme with 4GB RAM and 8 vcpus
shows the following slab memory usage after boot:
Before previous patch (using page->pobjects):
Slab: 36732 kB
SReclaimable: 14836 kB
SUnreclaim: 21896 kB
After previous patch (using page->pages):
Slab: 34720 kB
SReclaimable: 13716 kB
SUnreclaim: 21004 kB
After this patch (using page->pages, higher defaults):
Slab: 35252 kB
SReclaimable: 13944 kB
SUnreclaim: 21308 kB
In the same setup, I also ran 5 times:
hackbench -l 16000 -g 16
Differences in time were in the noise, we can compare slub stats as
given by slabinfo -r skbuff_head_cache (the other cache heavily used by
hackbench, kmalloc-cg-512 looks similar). Negligible stats left out for
brevity.
Before previous patch (using page->pobjects):
Objects: 1408, Memory Total: 401408 Used : 304128
Slab Perf Counter Alloc Free %Al %Fr
--------------------------------------------------
Fastpath 469952498 5946606 91 1
Slowpath 42053573 506059465 8 98
Page Alloc 41093 41044 0 0
Add partial 18 21229327 0 4
Remove partial 20039522 36051 3 0
Cpu partial list 4686640 24767229 0 4
RemoteObj/SlabFrozen 16 124027841 0 24
Total 512006071 512006071
Flushes 18
Slab Deactivation Occurrences %
-------------------------------------------------
Slab empty 4993 0%
Deactivation bypass 24767229 99%
Refilled from foreign frees 21972674 88%
After previous patch (using page->pages):
Objects: 480, Memory Total: 131072 Used : 103680
Slab Perf Counter Alloc Free %Al %Fr
--------------------------------------------------
Fastpath 473016294 5405653 92 1
Slowpath 38989777 506600418 7 98
Page Alloc 32717 32701 0 0
Add partial 3 22749164 0 4
Remove partial 11371127 32474 2 0
Cpu partial list 11686226 23090059 2 4
RemoteObj/SlabFrozen 2 67541803 0 13
Total 512006071 512006071
Flushes 3
Slab Deactivation Occurrences %
-------------------------------------------------
Slab empty 227 0%
Deactivation bypass 23090059 99%
Refilled from foreign frees 27585695 119%
After this patch (using page->pages, higher defaults):
Objects: 896, Memory Total: 229376 Used : 193536
Slab Perf Counter Alloc Free %Al %Fr
--------------------------------------------------
Fastpath 473799295 4980278 92 0
Slowpath 38206776 507025793 7 99
Page Alloc 32295 32267 0 0
Add partial 11 23291143 0 4
Remove partial 5815764 31278 1 0
Cpu partial list 18119280 23967320 3 4
RemoteObj/SlabFrozen 10 76974794 0 15
Total 512006071 512006071
Flushes 11
Slab Deactivation Occurrences %
-------------------------------------------------
Slab empty 989 0%
Deactivation bypass 23967320 99%
Refilled from foreign frees 32358473 135%
As expected, memory usage dropped significantly with change of
accounting, increasing the defaults increased it, but not as much. The
number of page allocation/frees dropped significantly with the new
accounting, but didn't increase with the higher defaults.
Interestingly, the number of fasthpath allocations increased, as well as
allocations from the cpu partial list, even though it's shorter.
Link: https://lkml.kernel.org/r/20211012134651.11258-2-vbabka@suse.cz
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Christoph Lameter <cl@linux.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Jann Horn <jannh@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Roman Gushchin <guro@fb.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-11-05 13:35:20 -07:00
|
|
|
|
2017-07-06 15:36:34 -07:00
|
|
|
|
mm/slub: increase default cpu partial list sizes
The defaults are determined based on object size and can go up to 30 for
objects smaller than 256 bytes. Before the previous patch changed the
accounting, this could have made cpu partial list contain up to 30
pages. After that patch, only up to 2 pages with default allocation
order.
Very short lists limit the usefulness of the whole concept of cpu
partial lists, so this patch aims at a more reasonable default under the
new accounting. The defaults are quadrupled, except for object size >=
PAGE_SIZE where it's doubled. This makes the lists grow up to 10 pages
in practice.
A quick test of booting a kernel under virtme with 4GB RAM and 8 vcpus
shows the following slab memory usage after boot:
Before previous patch (using page->pobjects):
Slab: 36732 kB
SReclaimable: 14836 kB
SUnreclaim: 21896 kB
After previous patch (using page->pages):
Slab: 34720 kB
SReclaimable: 13716 kB
SUnreclaim: 21004 kB
After this patch (using page->pages, higher defaults):
Slab: 35252 kB
SReclaimable: 13944 kB
SUnreclaim: 21308 kB
In the same setup, I also ran 5 times:
hackbench -l 16000 -g 16
Differences in time were in the noise, we can compare slub stats as
given by slabinfo -r skbuff_head_cache (the other cache heavily used by
hackbench, kmalloc-cg-512 looks similar). Negligible stats left out for
brevity.
Before previous patch (using page->pobjects):
Objects: 1408, Memory Total: 401408 Used : 304128
Slab Perf Counter Alloc Free %Al %Fr
--------------------------------------------------
Fastpath 469952498 5946606 91 1
Slowpath 42053573 506059465 8 98
Page Alloc 41093 41044 0 0
Add partial 18 21229327 0 4
Remove partial 20039522 36051 3 0
Cpu partial list 4686640 24767229 0 4
RemoteObj/SlabFrozen 16 124027841 0 24
Total 512006071 512006071
Flushes 18
Slab Deactivation Occurrences %
-------------------------------------------------
Slab empty 4993 0%
Deactivation bypass 24767229 99%
Refilled from foreign frees 21972674 88%
After previous patch (using page->pages):
Objects: 480, Memory Total: 131072 Used : 103680
Slab Perf Counter Alloc Free %Al %Fr
--------------------------------------------------
Fastpath 473016294 5405653 92 1
Slowpath 38989777 506600418 7 98
Page Alloc 32717 32701 0 0
Add partial 3 22749164 0 4
Remove partial 11371127 32474 2 0
Cpu partial list 11686226 23090059 2 4
RemoteObj/SlabFrozen 2 67541803 0 13
Total 512006071 512006071
Flushes 3
Slab Deactivation Occurrences %
-------------------------------------------------
Slab empty 227 0%
Deactivation bypass 23090059 99%
Refilled from foreign frees 27585695 119%
After this patch (using page->pages, higher defaults):
Objects: 896, Memory Total: 229376 Used : 193536
Slab Perf Counter Alloc Free %Al %Fr
--------------------------------------------------
Fastpath 473799295 4980278 92 0
Slowpath 38206776 507025793 7 99
Page Alloc 32295 32267 0 0
Add partial 11 23291143 0 4
Remove partial 5815764 31278 1 0
Cpu partial list 18119280 23967320 3 4
RemoteObj/SlabFrozen 10 76974794 0 15
Total 512006071 512006071
Flushes 11
Slab Deactivation Occurrences %
-------------------------------------------------
Slab empty 989 0%
Deactivation bypass 23967320 99%
Refilled from foreign frees 32358473 135%
As expected, memory usage dropped significantly with change of
accounting, increasing the defaults increased it, but not as much. The
number of page allocation/frees dropped significantly with the new
accounting, but didn't increase with the higher defaults.
Interestingly, the number of fasthpath allocations increased, as well as
allocations from the cpu partial list, even though it's shorter.
Link: https://lkml.kernel.org/r/20211012134651.11258-2-vbabka@suse.cz
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Christoph Lameter <cl@linux.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Jann Horn <jannh@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Roman Gushchin <guro@fb.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-11-05 13:35:20 -07:00
|
|
|
|
mm, slub: change percpu partial accounting from objects to pages
With CONFIG_SLUB_CPU_PARTIAL enabled, SLUB keeps a percpu list of
partial slabs that can be promoted to cpu slab when the previous one is
depleted, without accessing the shared partial list. A slab can be
added to this list by 1) refill of an empty list from get_partial_node()
- once we really have to access the shared partial list, we acquire
multiple slabs to amortize the cost of locking, and 2) first free to a
previously full slab - instead of putting the slab on a shared partial
list, we can more cheaply freeze it and put it on the per-cpu list.
To control how large a percpu partial list can grow for a kmem cache,
set_cpu_partial() calculates a target number of free objects on each
cpu's percpu partial list, and this can be also set by the sysfs file
cpu_partial.
However, the tracking of actual number of objects is imprecise, in order
to limit overhead from cpu X freeing an objects to a slab on percpu
partial list of cpu Y. Basically, the percpu partial slabs form a
single linked list, and when we add a new slab to the list with current
head "oldpage", we set in the struct page of the slab we're adding:
page->pages = oldpage->pages + 1; // this is precise
page->pobjects = oldpage->pobjects + (page->objects - page->inuse);
page->next = oldpage;
Thus the real number of free objects in the slab (objects - inuse) is
only determined at the moment of adding the slab to the percpu partial
list, and further freeing doesn't update the pobjects counter nor
propagate it to the current list head. As Jann reports [1], this can
easily lead to large inaccuracies, where the target number of objects
(up to 30 by default) can translate to the same number of (empty) slab
pages on the list. In case 2) above, we put a slab with 1 free object
on the list, thus only increase page->pobjects by 1, even if there are
subsequent frees on the same slab. Jann has noticed this in practice
and so did we [2] when investigating significant increase of kmemcg
usage after switching from SLAB to SLUB.
While this is no longer a problem in kmemcg context thanks to the
accounting rewrite in 5.9, the memory waste is still not ideal and it's
questionable whether it makes sense to perform free object count based
control when object counts can easily become so much inaccurate. So
this patch converts the accounting to be based on number of pages only
(which is precise) and removes the page->pobjects field completely.
This is also ultimately simpler.
To retain the existing set_cpu_partial() heuristic, first calculate the
target number of objects as previously, but then convert it to target
number of pages by assuming the pages will be half-filled on average.
This assumption might obviously also be inaccurate in practice, but
cannot degrade to actual number of pages being equal to the target
number of objects.
We could also skip the intermediate step with target number of objects
and rewrite the heuristic in terms of pages. However we still have the
sysfs file cpu_partial which uses number of objects and could break
existing users if it suddenly becomes number of pages, so this patch
doesn't do that.
In practice, after this patch the heuristics limit the size of percpu
partial list up to 2 pages. In case of a reported regression (which
would mean some workload has benefited from the previous imprecise
object based counting), we can tune the heuristics to get a better
compromise within the new scheme, while still avoid the unexpectedly
long percpu partial lists.
[1] https://lore.kernel.org/linux-mm/CAG48ez2Qx5K1Cab-m8BdSibp6wLTip6ro4=-umR7BLsEgjEYzA@mail.gmail.com/
[2] https://lore.kernel.org/all/2f0f46e8-2535-410a-1859-e9cfa4e57c18@suse.cz/
==========
Evaluation
==========
Mel was kind enough to run v1 through mmtests machinery for netperf
(localhost) and hackbench and, for most significant results see below.
So there are some apparent regressions, especially with hackbench, which
I think ultimately boils down to having shorter percpu partial lists on
average and some benchmarks benefiting from longer ones. Monitoring
slab usage also indicated less memory usage by slab. Based on that, the
following patch will bump the defaults to allow longer percpu partial
lists than after this patch.
However the goal is certainly not such that we would limit the percpu
partial lists to 30 pages just because previously a specific alloc/free
pattern could lead to the limit of 30 objects translate to a limit to 30
pages - that would make little sense. This is a correctness patch, and
if a workload benefits from larger lists, the sysfs tuning knobs are
still there to allow that.
Netperf
2-socket Intel(R) Xeon(R) Gold 5218R CPU @ 2.10GHz (20 cores, 40 threads per socket), 384GB RAM
TCP-RR:
hmean before 127045.79 after 121092.94 (-4.69%, worse)
stddev before 2634.37 after 1254.08
UDP-RR:
hmean before 166985.45 after 160668.94 ( -3.78%, worse)
stddev before 4059.69 after 1943.63
2-socket Intel(R) Xeon(R) CPU E5-2698 v4 @ 2.20GHz (20 cores, 40 threads per socket), 512GB RAM
TCP-RR:
hmean before 84173.25 after 76914.72 ( -8.62%, worse)
UDP-RR:
hmean before 93571.12 after 96428.69 ( 3.05%, better)
stddev before 23118.54 after 16828.14
2-socket Intel(R) Xeon(R) CPU E5-2670 v3 @ 2.30GHz (12 cores, 24 threads per socket), 64GB RAM
TCP-RR:
hmean before 49984.92 after 48922.27 ( -2.13%, worse)
stddev before 6248.15 after 4740.51
UDP-RR:
hmean before 61854.31 after 68761.81 ( 11.17%, better)
stddev before 4093.54 after 5898.91
other machines - within 2%
Hackbench
(results before and after the patch, negative % means worse)
2-socket AMD EPYC 7713 (64 cores, 128 threads per core), 256GB RAM
hackbench-process-sockets
Amean 1 0.5380 0.5583 ( -3.78%)
Amean 4 0.7510 0.8150 ( -8.52%)
Amean 7 0.7930 0.9533 ( -20.22%)
Amean 12 0.7853 1.1313 ( -44.06%)
Amean 21 1.1520 1.4993 ( -30.15%)
Amean 30 1.6223 1.9237 ( -18.57%)
Amean 48 2.6767 2.9903 ( -11.72%)
Amean 79 4.0257 5.1150 ( -27.06%)
Amean 110 5.5193 7.4720 ( -35.38%)
Amean 141 7.2207 9.9840 ( -38.27%)
Amean 172 8.4770 12.1963 ( -43.88%)
Amean 203 9.6473 14.3137 ( -48.37%)
Amean 234 11.3960 18.7917 ( -64.90%)
Amean 265 13.9627 22.4607 ( -60.86%)
Amean 296 14.9163 26.0483 ( -74.63%)
hackbench-thread-sockets
Amean 1 0.5597 0.5877 ( -5.00%)
Amean 4 0.7913 0.8960 ( -13.23%)
Amean 7 0.8190 1.0017 ( -22.30%)
Amean 12 0.9560 1.1727 ( -22.66%)
Amean 21 1.7587 1.5660 ( 10.96%)
Amean 30 2.4477 1.9807 ( 19.08%)
Amean 48 3.4573 3.0630 ( 11.41%)
Amean 79 4.7903 5.1733 ( -8.00%)
Amean 110 6.1370 7.4220 ( -20.94%)
Amean 141 7.5777 9.2617 ( -22.22%)
Amean 172 9.2280 11.0907 ( -20.18%)
Amean 203 10.2793 13.3470 ( -29.84%)
Amean 234 11.2410 17.1070 ( -52.18%)
Amean 265 12.5970 23.3323 ( -85.22%)
Amean 296 17.1540 24.2857 ( -41.57%)
2-socket Intel(R) Xeon(R) Gold 5218R CPU @ 2.10GHz (20 cores, 40 threads
per socket), 384GB RAM
hackbench-process-sockets
Amean 1 0.5760 0.4793 ( 16.78%)
Amean 4 0.9430 0.9707 ( -2.93%)
Amean 7 1.5517 1.8843 ( -21.44%)
Amean 12 2.4903 2.7267 ( -9.49%)
Amean 21 3.9560 4.2877 ( -8.38%)
Amean 30 5.4613 5.8343 ( -6.83%)
Amean 48 8.5337 9.2937 ( -8.91%)
Amean 79 14.0670 15.2630 ( -8.50%)
Amean 110 19.2253 21.2467 ( -10.51%)
Amean 141 23.7557 25.8550 ( -8.84%)
Amean 172 28.4407 29.7603 ( -4.64%)
Amean 203 33.3407 33.9927 ( -1.96%)
Amean 234 38.3633 39.1150 ( -1.96%)
Amean 265 43.4420 43.8470 ( -0.93%)
Amean 296 48.3680 48.9300 ( -1.16%)
hackbench-thread-sockets
Amean 1 0.6080 0.6493 ( -6.80%)
Amean 4 1.0000 1.0513 ( -5.13%)
Amean 7 1.6607 2.0260 ( -22.00%)
Amean 12 2.7637 2.9273 ( -5.92%)
Amean 21 5.0613 4.5153 ( 10.79%)
Amean 30 6.3340 6.1140 ( 3.47%)
Amean 48 9.0567 9.5577 ( -5.53%)
Amean 79 14.5657 15.7983 ( -8.46%)
Amean 110 19.6213 21.6333 ( -10.25%)
Amean 141 24.1563 26.2697 ( -8.75%)
Amean 172 28.9687 30.2187 ( -4.32%)
Amean 203 33.9763 34.6970 ( -2.12%)
Amean 234 38.8647 39.3207 ( -1.17%)
Amean 265 44.0813 44.1507 ( -0.16%)
Amean 296 49.2040 49.4330 ( -0.47%)
2-socket Intel(R) Xeon(R) CPU E5-2698 v4 @ 2.20GHz (20 cores, 40 threads
per socket), 512GB RAM
hackbench-process-sockets
Amean 1 0.5027 0.5017 ( 0.20%)
Amean 4 1.1053 1.2033 ( -8.87%)
Amean 7 1.8760 2.1820 ( -16.31%)
Amean 12 2.9053 3.1810 ( -9.49%)
Amean 21 4.6777 4.9920 ( -6.72%)
Amean 30 6.5180 6.7827 ( -4.06%)
Amean 48 10.0710 10.5227 ( -4.48%)
Amean 79 16.4250 17.5053 ( -6.58%)
Amean 110 22.6203 24.4617 ( -8.14%)
Amean 141 28.0967 31.0363 ( -10.46%)
Amean 172 34.4030 36.9233 ( -7.33%)
Amean 203 40.5933 43.0850 ( -6.14%)
Amean 234 46.6477 48.7220 ( -4.45%)
Amean 265 53.0530 53.9597 ( -1.71%)
Amean 296 59.2760 59.9213 ( -1.09%)
hackbench-thread-sockets
Amean 1 0.5363 0.5330 ( 0.62%)
Amean 4 1.1647 1.2157 ( -4.38%)
Amean 7 1.9237 2.2833 ( -18.70%)
Amean 12 2.9943 3.3110 ( -10.58%)
Amean 21 4.9987 5.1880 ( -3.79%)
Amean 30 6.7583 7.0043 ( -3.64%)
Amean 48 10.4547 10.8353 ( -3.64%)
Amean 79 16.6707 17.6790 ( -6.05%)
Amean 110 22.8207 24.4403 ( -7.10%)
Amean 141 28.7090 31.0533 ( -8.17%)
Amean 172 34.9387 36.8260 ( -5.40%)
Amean 203 41.1567 43.0450 ( -4.59%)
Amean 234 47.3790 48.5307 ( -2.43%)
Amean 265 53.9543 54.6987 ( -1.38%)
Amean 296 60.0820 60.2163 ( -0.22%)
1-socket Intel(R) Xeon(R) CPU E3-1240 v5 @ 3.50GHz (4 cores, 8 threads),
32 GB RAM
hackbench-process-sockets
Amean 1 1.4760 1.5773 ( -6.87%)
Amean 3 3.9370 4.0910 ( -3.91%)
Amean 5 6.6797 6.9357 ( -3.83%)
Amean 7 9.3367 9.7150 ( -4.05%)
Amean 12 15.7627 16.1400 ( -2.39%)
Amean 18 23.5360 23.6890 ( -0.65%)
Amean 24 31.0663 31.3137 ( -0.80%)
Amean 30 38.7283 39.0037 ( -0.71%)
Amean 32 41.3417 41.6097 ( -0.65%)
hackbench-thread-sockets
Amean 1 1.5250 1.6043 ( -5.20%)
Amean 3 4.0897 4.2603 ( -4.17%)
Amean 5 6.7760 7.0933 ( -4.68%)
Amean 7 9.4817 9.9157 ( -4.58%)
Amean 12 15.9610 16.3937 ( -2.71%)
Amean 18 23.9543 24.3417 ( -1.62%)
Amean 24 31.4400 31.7217 ( -0.90%)
Amean 30 39.2457 39.5467 ( -0.77%)
Amean 32 41.8267 42.1230 ( -0.71%)
2-socket Intel(R) Xeon(R) CPU E5-2670 v3 @ 2.30GHz (12 cores, 24 threads
per socket), 64GB RAM
hackbench-process-sockets
Amean 1 1.0347 1.0880 ( -5.15%)
Amean 4 1.7267 1.8527 ( -7.30%)
Amean 7 2.6707 2.8110 ( -5.25%)
Amean 12 4.1617 4.3383 ( -4.25%)
Amean 21 7.0070 7.2600 ( -3.61%)
Amean 30 9.9187 10.2397 ( -3.24%)
Amean 48 15.6710 16.3923 ( -4.60%)
Amean 79 24.7743 26.1247 ( -5.45%)
Amean 110 34.3000 35.9307 ( -4.75%)
Amean 141 44.2043 44.8010 ( -1.35%)
Amean 172 54.2430 54.7260 ( -0.89%)
Amean 192 60.6557 60.9777 ( -0.53%)
hackbench-thread-sockets
Amean 1 1.0610 1.1353 ( -7.01%)
Amean 4 1.7543 1.9140 ( -9.10%)
Amean 7 2.7840 2.9573 ( -6.23%)
Amean 12 4.3813 4.4937 ( -2.56%)
Amean 21 7.3460 7.5350 ( -2.57%)
Amean 30 10.2313 10.5190 ( -2.81%)
Amean 48 15.9700 16.5940 ( -3.91%)
Amean 79 25.3973 26.6637 ( -4.99%)
Amean 110 35.1087 36.4797 ( -3.91%)
Amean 141 45.8220 46.3053 ( -1.05%)
Amean 172 55.4917 55.7320 ( -0.43%)
Amean 192 62.7490 62.5410 ( 0.33%)
Link: https://lkml.kernel.org/r/20211012134651.11258-1-vbabka@suse.cz
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reported-by: Jann Horn <jannh@google.com>
Cc: Roman Gushchin <guro@fb.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-11-05 13:35:17 -07:00
|
|
|
|
|
|
|
|
|
2017-07-06 15:36:34 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-09-05 09:56:52 +02:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2017-11-15 17:32:18 -08:00
|
|
|
|
2018-04-05 16:21:28 -07:00
|
|
|
|
2018-04-05 16:21:39 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2008-02-15 23:45:25 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-01-18 02:53:44 -08:00
|
|
|
|
2007-05-16 22:10:50 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-09 02:32:39 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2007-05-09 02:32:39 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2012-06-13 10:24:57 -05:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2007-05-09 02:32:44 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
2007-05-09 02:32:39 -07:00
|
|
|
|
2021-06-15 18:23:26 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-09-05 09:56:52 +02:00
|
|
|
|
2024-08-28 12:56:24 +02:00
|
|
|
|
2024-06-07 16:40:13 +08:00
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-06-15 18:23:22 -07:00
|
|
|
|
2024-06-07 16:40:13 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-05-07 18:36:06 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-09-05 09:56:52 +02:00
|
|
|
|
|
|
|
|
|
2021-06-15 18:23:26 -07:00
|
|
|
|
slub: relocate freelist pointer to middle of object
In a recent discussion[1] with Vitaly Nikolenko and Silvio Cesare, it
became clear that moving the freelist pointer away from the edge of
allocations would likely improve the overall defensive posture of the
inline freelist pointer. My benchmarks show no meaningful change to
performance (they seem to show it being faster), so this looks like a
reasonable change to make.
Instead of having the freelist pointer at the very beginning of an
allocation (offset 0) or at the very end of an allocation (effectively
offset -sizeof(void *) from the next allocation), move it away from the
edges of the allocation and into the middle. This provides some
protection against small-sized neighboring overflows (or underflows), for
which the freelist pointer is commonly the target. (Large or well
controlled overwrites are much more likely to attack live object contents,
instead of attempting freelist corruption.)
The vaunted kernel build benchmark, across 5 runs. Before:
Mean: 250.05
Std Dev: 1.85
and after, which appears mysteriously faster:
Mean: 247.13
Std Dev: 0.76
Attempts at running "sysbench --test=memory" show the change to be well in
the noise (sysbench seems to be pretty unstable here -- it's not really
measuring allocation).
Hackbench is more allocation-heavy, and while the std dev is above the
difference, it looks like may manifest as an improvement as well:
20 runs of "hackbench -g 20 -l 1000", before:
Mean: 36.322
Std Dev: 0.577
and after:
Mean: 36.056
Std Dev: 0.598
[1] https://twitter.com/vnik5287/status/1235113523098685440
Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Christoph Lameter <cl@linux.com>
Cc: Vitaly Nikolenko <vnik@duasynt.com>
Cc: Silvio Cesare <silvio.cesare@gmail.com>
Cc: Christoph Lameter <cl@linux.com>Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Link: http://lkml.kernel.org/r/202003051624.AAAC9AECC@keescook
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-04-01 21:04:27 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-06-15 18:23:26 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
2007-05-23 13:57:31 -07:00
|
|
|
|
mm/slub: enable debugging memory wasting of kmalloc
kmalloc's API family is critical for mm, with one nature that it will
round up the request size to a fixed one (mostly power of 2). Say
when user requests memory for '2^n + 1' bytes, actually 2^(n+1) bytes
could be allocated, so in worst case, there is around 50% memory
space waste.
The wastage is not a big issue for requests that get allocated/freed
quickly, but may cause problems with objects that have longer life
time.
We've met a kernel boot OOM panic (v5.10), and from the dumped slab
info:
[ 26.062145] kmalloc-2k 814056KB 814056KB
From debug we found there are huge number of 'struct iova_magazine',
whose size is 1032 bytes (1024 + 8), so each allocation will waste
1016 bytes. Though the issue was solved by giving the right (bigger)
size of RAM, it is still nice to optimize the size (either use a
kmalloc friendly size or create a dedicated slab for it).
And from lkml archive, there was another crash kernel OOM case [1]
back in 2019, which seems to be related with the similar slab waste
situation, as the log is similar:
[ 4.332648] iommu: Adding device 0000:20:02.0 to group 16
[ 4.338946] swapper/0 invoked oom-killer: gfp_mask=0x6040c0(GFP_KERNEL|__GFP_COMP), nodemask=(null), order=0, oom_score_adj=0
...
[ 4.857565] kmalloc-2048 59164KB 59164KB
The crash kernel only has 256M memory, and 59M is pretty big here.
(Note: the related code has been changed and optimised in recent
kernel [2], these logs are just picked to demo the problem, also
a patch changing its size to 1024 bytes has been merged)
So add an way to track each kmalloc's memory waste info, and
leverage the existing SLUB debug framework (specifically
SLUB_STORE_USER) to show its call stack of original allocation,
so that user can evaluate the waste situation, identify some hot
spots and optimize accordingly, for a better utilization of memory.
The waste info is integrated into existing interface:
'/sys/kernel/debug/slab/kmalloc-xx/alloc_traces', one example of
'kmalloc-4k' after boot is:
126 ixgbe_alloc_q_vector+0xbe/0x830 [ixgbe] waste=233856/1856 age=280763/281414/282065 pid=1330 cpus=32 nodes=1
__kmem_cache_alloc_node+0x11f/0x4e0
__kmalloc_node+0x4e/0x140
ixgbe_alloc_q_vector+0xbe/0x830 [ixgbe]
ixgbe_init_interrupt_scheme+0x2ae/0xc90 [ixgbe]
ixgbe_probe+0x165f/0x1d20 [ixgbe]
local_pci_probe+0x78/0xc0
work_for_cpu_fn+0x26/0x40
...
which means in 'kmalloc-4k' slab, there are 126 requests of
2240 bytes which got a 4KB space (wasting 1856 bytes each
and 233856 bytes in total), from ixgbe_alloc_q_vector().
And when system starts some real workload like multiple docker
instances, there could are more severe waste.
[1]. https://lkml.org/lkml/2019/8/12/266
[2]. https://lore.kernel.org/lkml/2920df89-9975-5785-f79b-257d3052dfaf@huawei.com/
[Thanks Hyeonggon for pointing out several bugs about sorting/format]
[Thanks Vlastimil for suggesting way to reduce memory usage of
orig_size and keep it only for kmalloc objects]
Signed-off-by: Feng Tang <feng.tang@intel.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Robin Murphy <robin.murphy@arm.com>
Cc: John Garry <john.garry@huawei.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2022-09-13 14:54:20 +08:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
mm/slub: enable debugging memory wasting of kmalloc
kmalloc's API family is critical for mm, with one nature that it will
round up the request size to a fixed one (mostly power of 2). Say
when user requests memory for '2^n + 1' bytes, actually 2^(n+1) bytes
could be allocated, so in worst case, there is around 50% memory
space waste.
The wastage is not a big issue for requests that get allocated/freed
quickly, but may cause problems with objects that have longer life
time.
We've met a kernel boot OOM panic (v5.10), and from the dumped slab
info:
[ 26.062145] kmalloc-2k 814056KB 814056KB
From debug we found there are huge number of 'struct iova_magazine',
whose size is 1032 bytes (1024 + 8), so each allocation will waste
1016 bytes. Though the issue was solved by giving the right (bigger)
size of RAM, it is still nice to optimize the size (either use a
kmalloc friendly size or create a dedicated slab for it).
And from lkml archive, there was another crash kernel OOM case [1]
back in 2019, which seems to be related with the similar slab waste
situation, as the log is similar:
[ 4.332648] iommu: Adding device 0000:20:02.0 to group 16
[ 4.338946] swapper/0 invoked oom-killer: gfp_mask=0x6040c0(GFP_KERNEL|__GFP_COMP), nodemask=(null), order=0, oom_score_adj=0
...
[ 4.857565] kmalloc-2048 59164KB 59164KB
The crash kernel only has 256M memory, and 59M is pretty big here.
(Note: the related code has been changed and optimised in recent
kernel [2], these logs are just picked to demo the problem, also
a patch changing its size to 1024 bytes has been merged)
So add an way to track each kmalloc's memory waste info, and
leverage the existing SLUB debug framework (specifically
SLUB_STORE_USER) to show its call stack of original allocation,
so that user can evaluate the waste situation, identify some hot
spots and optimize accordingly, for a better utilization of memory.
The waste info is integrated into existing interface:
'/sys/kernel/debug/slab/kmalloc-xx/alloc_traces', one example of
'kmalloc-4k' after boot is:
126 ixgbe_alloc_q_vector+0xbe/0x830 [ixgbe] waste=233856/1856 age=280763/281414/282065 pid=1330 cpus=32 nodes=1
__kmem_cache_alloc_node+0x11f/0x4e0
__kmalloc_node+0x4e/0x140
ixgbe_alloc_q_vector+0xbe/0x830 [ixgbe]
ixgbe_init_interrupt_scheme+0x2ae/0xc90 [ixgbe]
ixgbe_probe+0x165f/0x1d20 [ixgbe]
local_pci_probe+0x78/0xc0
work_for_cpu_fn+0x26/0x40
...
which means in 'kmalloc-4k' slab, there are 126 requests of
2240 bytes which got a 4KB space (wasting 1856 bytes each
and 233856 bytes in total), from ixgbe_alloc_q_vector().
And when system starts some real workload like multiple docker
instances, there could are more severe waste.
[1]. https://lkml.org/lkml/2019/8/12/266
[2]. https://lore.kernel.org/lkml/2920df89-9975-5785-f79b-257d3052dfaf@huawei.com/
[Thanks Hyeonggon for pointing out several bugs about sorting/format]
[Thanks Vlastimil for suggesting way to reduce memory usage of
orig_size and keep it only for kmalloc objects]
Signed-off-by: Feng Tang <feng.tang@intel.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Robin Murphy <robin.murphy@arm.com>
Cc: John Garry <john.garry@huawei.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2022-09-13 14:54:20 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-07-28 15:49:07 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2016-07-28 15:49:07 -07:00
|
|
|
|
|
|
|
|
|
2016-03-15 14:55:12 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-12-29 22:14:56 +01:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-03-15 14:55:12 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-09 02:32:44 -07:00
|
|
|
|
2007-05-09 02:32:39 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-11-28 16:23:16 +00:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2020-08-06 23:20:42 -07:00
|
|
|
|
2022-03-09 17:20:36 +08:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2018-04-05 16:21:39 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
2024-04-13 15:56:03 +00:00
|
|
|
|
2008-02-14 14:21:32 -08:00
|
|
|
|
|
|
|
|
|
2013-01-10 19:14:19 +00:00
|
|
|
|
2008-02-14 14:21:32 -08:00
|
|
|
|
mm: add support for kmem caches in DMA32 zone
Patch series "iommu/io-pgtable-arm-v7s: Use DMA32 zone for page tables",
v6.
This is a followup to the discussion in [1], [2].
IOMMUs using ARMv7 short-descriptor format require page tables (level 1
and 2) to be allocated within the first 4GB of RAM, even on 64-bit
systems.
For L1 tables that are bigger than a page, we can just use
__get_free_pages with GFP_DMA32 (on arm64 systems only, arm would still
use GFP_DMA).
For L2 tables that only take 1KB, it would be a waste to allocate a full
page, so we considered 3 approaches:
1. This series, adding support for GFP_DMA32 slab caches.
2. genalloc, which requires pre-allocating the maximum number of L2 page
tables (4096, so 4MB of memory).
3. page_frag, which is not very memory-efficient as it is unable to reuse
freed fragments until the whole page is freed. [3]
This series is the most memory-efficient approach.
stable@ note:
We confirmed that this is a regression, and IOMMU errors happen on 4.19
and linux-next/master on MT8173 (elm, Acer Chromebook R13). The issue
most likely starts from commit ad67f5a6545f ("arm64: replace ZONE_DMA
with ZONE_DMA32"), i.e. 4.15, and presumably breaks a number of Mediatek
platforms (and maybe others?).
[1] https://lists.linuxfoundation.org/pipermail/iommu/2018-November/030876.html
[2] https://lists.linuxfoundation.org/pipermail/iommu/2018-December/031696.html
[3] https://patchwork.codeaurora.org/patch/671639/
This patch (of 3):
IOMMUs using ARMv7 short-descriptor format require page tables to be
allocated within the first 4GB of RAM, even on 64-bit systems. On arm64,
this is done by passing GFP_DMA32 flag to memory allocation functions.
For IOMMU L2 tables that only take 1KB, it would be a waste to allocate
a full page using get_free_pages, so we considered 3 approaches:
1. This patch, adding support for GFP_DMA32 slab caches.
2. genalloc, which requires pre-allocating the maximum number of L2
page tables (4096, so 4MB of memory).
3. page_frag, which is not very memory-efficient as it is unable
to reuse freed fragments until the whole page is freed.
This change makes it possible to create a custom cache in DMA32 zone using
kmem_cache_create, then allocate memory using kmem_cache_alloc.
We do not create a DMA32 kmalloc cache array, as there are currently no
users of kmalloc(..., GFP_DMA32). These calls will continue to trigger a
warning, as we keep GFP_DMA32 in GFP_SLAB_BUG_MASK.
This implies that calls to kmem_cache_*alloc on a SLAB_CACHE_DMA32
kmem_cache must _not_ use GFP_DMA32 (it is anyway redundant and
unnecessary).
Link: http://lkml.kernel.org/r/20181210011504.122604-2-drinkcat@chromium.org
Signed-off-by: Nicolas Boichat <drinkcat@chromium.org>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Will Deacon <will.deacon@arm.com>
Cc: Robin Murphy <robin.murphy@arm.com>
Cc: Joerg Roedel <joro@8bytes.org>
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Sasha Levin <Alexander.Levin@microsoft.com>
Cc: Huaisheng Ye <yehs1@lenovo.com>
Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Yong Wu <yong.wu@mediatek.com>
Cc: Matthias Brugger <matthias.bgg@gmail.com>
Cc: Tomasz Figa <tfiga@google.com>
Cc: Yingjoe Chen <yingjoe.chen@mediatek.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Hsin-Yi Wang <hsinyi@chromium.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-28 20:43:42 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-02-14 14:21:32 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-06-07 17:09:10 -07:00
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2008-04-14 19:11:31 +03:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2020-06-25 20:29:55 -07:00
|
|
|
|
2008-04-25 12:22:43 -07:00
|
|
|
|
|
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2008-04-25 12:22:43 -07:00
|
|
|
|
2020-06-01 21:45:53 -07:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2008-04-25 12:22:43 -07:00
|
|
|
|
2022-08-23 19:03:59 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2008-04-25 12:22:43 -07:00
|
|
|
|
2022-08-23 19:03:59 +02:00
|
|
|
|
2024-10-01 18:20:48 +02:00
|
|
|
|
|
|
|
|
|
2021-03-19 18:12:45 +08:00
|
|
|
|
2008-04-25 12:22:43 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-08-23 19:03:59 +02:00
|
|
|
|
2008-04-25 12:22:43 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2008-04-23 12:36:52 -07:00
|
|
|
|
2016-02-17 13:11:37 -08:00
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2008-04-23 12:36:52 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
mm/slub.c: run free_partial() outside of the kmem_cache_node->list_lock
With debugobjects enabled and using SLAB_DESTROY_BY_RCU, when a
kmem_cache_node is destroyed the call_rcu() may trigger a slab
allocation to fill the debug object pool (__debug_object_init:fill_pool).
Everywhere but during kmem_cache_destroy(), discard_slab() is performed
outside of the kmem_cache_node->list_lock and avoids a lockdep warning
about potential recursion:
=============================================
[ INFO: possible recursive locking detected ]
4.8.0-rc1-gfxbench+ #1 Tainted: G U
---------------------------------------------
rmmod/8895 is trying to acquire lock:
(&(&n->list_lock)->rlock){-.-...}, at: [<ffffffff811c80d7>] get_partial_node.isra.63+0x47/0x430
but task is already holding lock:
(&(&n->list_lock)->rlock){-.-...}, at: [<ffffffff811cbda4>] __kmem_cache_shutdown+0x54/0x320
other info that might help us debug this:
Possible unsafe locking scenario:
CPU0
----
lock(&(&n->list_lock)->rlock);
lock(&(&n->list_lock)->rlock);
*** DEADLOCK ***
May be due to missing lock nesting notation
5 locks held by rmmod/8895:
#0: (&dev->mutex){......}, at: driver_detach+0x42/0xc0
#1: (&dev->mutex){......}, at: driver_detach+0x50/0xc0
#2: (cpu_hotplug.dep_map){++++++}, at: get_online_cpus+0x2d/0x80
#3: (slab_mutex){+.+.+.}, at: kmem_cache_destroy+0x3c/0x220
#4: (&(&n->list_lock)->rlock){-.-...}, at: __kmem_cache_shutdown+0x54/0x320
stack backtrace:
CPU: 6 PID: 8895 Comm: rmmod Tainted: G U 4.8.0-rc1-gfxbench+ #1
Hardware name: Gigabyte Technology Co., Ltd. H87M-D3H/H87M-D3H, BIOS F11 08/18/2015
Call Trace:
__lock_acquire+0x1646/0x1ad0
lock_acquire+0xb2/0x200
_raw_spin_lock+0x36/0x50
get_partial_node.isra.63+0x47/0x430
___slab_alloc.constprop.67+0x1a7/0x3b0
__slab_alloc.isra.64.constprop.66+0x43/0x80
kmem_cache_alloc+0x236/0x2d0
__debug_object_init+0x2de/0x400
debug_object_activate+0x109/0x1e0
__call_rcu.constprop.63+0x32/0x2f0
call_rcu+0x12/0x20
discard_slab+0x3d/0x40
__kmem_cache_shutdown+0xdb/0x320
shutdown_cache+0x19/0x60
kmem_cache_destroy+0x1ae/0x220
i915_gem_load_cleanup+0x14/0x40 [i915]
i915_driver_unload+0x151/0x180 [i915]
i915_pci_remove+0x14/0x20 [i915]
pci_device_remove+0x34/0xb0
__device_release_driver+0x95/0x140
driver_detach+0xb6/0xc0
bus_remove_driver+0x53/0xd0
driver_unregister+0x27/0x50
pci_unregister_driver+0x25/0x70
i915_exit+0x1a/0x1e2 [i915]
SyS_delete_module+0x193/0x1f0
entry_SYSCALL_64_fastpath+0x1c/0xac
Fixes: 52b4b950b507 ("mm: slab: free kmem_cache_node after destroy sysfs file")
Link: http://lkml.kernel.org/r/1470759070-18743-1-git-send-email-chris@chris-wilson.co.uk
Reported-by: Dave Gordon <david.s.gordon@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Vladimir Davydov <vdavydov@virtuozzo.com>
Acked-by: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Dmitry Safonov <dsafonov@virtuozzo.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Dave Gordon <david.s.gordon@intel.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-08-10 16:27:58 -07:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2016-02-17 13:11:37 -08:00
|
|
|
|
|
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-04-25 12:22:43 -07:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2020-06-25 20:29:55 -07:00
|
|
|
|
2008-04-23 12:36:52 -07:00
|
|
|
|
2008-04-25 12:22:43 -07:00
|
|
|
|
2016-02-17 13:11:37 -08:00
|
|
|
|
mm/slub.c: run free_partial() outside of the kmem_cache_node->list_lock
With debugobjects enabled and using SLAB_DESTROY_BY_RCU, when a
kmem_cache_node is destroyed the call_rcu() may trigger a slab
allocation to fill the debug object pool (__debug_object_init:fill_pool).
Everywhere but during kmem_cache_destroy(), discard_slab() is performed
outside of the kmem_cache_node->list_lock and avoids a lockdep warning
about potential recursion:
=============================================
[ INFO: possible recursive locking detected ]
4.8.0-rc1-gfxbench+ #1 Tainted: G U
---------------------------------------------
rmmod/8895 is trying to acquire lock:
(&(&n->list_lock)->rlock){-.-...}, at: [<ffffffff811c80d7>] get_partial_node.isra.63+0x47/0x430
but task is already holding lock:
(&(&n->list_lock)->rlock){-.-...}, at: [<ffffffff811cbda4>] __kmem_cache_shutdown+0x54/0x320
other info that might help us debug this:
Possible unsafe locking scenario:
CPU0
----
lock(&(&n->list_lock)->rlock);
lock(&(&n->list_lock)->rlock);
*** DEADLOCK ***
May be due to missing lock nesting notation
5 locks held by rmmod/8895:
#0: (&dev->mutex){......}, at: driver_detach+0x42/0xc0
#1: (&dev->mutex){......}, at: driver_detach+0x50/0xc0
#2: (cpu_hotplug.dep_map){++++++}, at: get_online_cpus+0x2d/0x80
#3: (slab_mutex){+.+.+.}, at: kmem_cache_destroy+0x3c/0x220
#4: (&(&n->list_lock)->rlock){-.-...}, at: __kmem_cache_shutdown+0x54/0x320
stack backtrace:
CPU: 6 PID: 8895 Comm: rmmod Tainted: G U 4.8.0-rc1-gfxbench+ #1
Hardware name: Gigabyte Technology Co., Ltd. H87M-D3H/H87M-D3H, BIOS F11 08/18/2015
Call Trace:
__lock_acquire+0x1646/0x1ad0
lock_acquire+0xb2/0x200
_raw_spin_lock+0x36/0x50
get_partial_node.isra.63+0x47/0x430
___slab_alloc.constprop.67+0x1a7/0x3b0
__slab_alloc.isra.64.constprop.66+0x43/0x80
kmem_cache_alloc+0x236/0x2d0
__debug_object_init+0x2de/0x400
debug_object_activate+0x109/0x1e0
__call_rcu.constprop.63+0x32/0x2f0
call_rcu+0x12/0x20
discard_slab+0x3d/0x40
__kmem_cache_shutdown+0xdb/0x320
shutdown_cache+0x19/0x60
kmem_cache_destroy+0x1ae/0x220
i915_gem_load_cleanup+0x14/0x40 [i915]
i915_driver_unload+0x151/0x180 [i915]
i915_pci_remove+0x14/0x20 [i915]
pci_device_remove+0x34/0xb0
__device_release_driver+0x95/0x140
driver_detach+0xb6/0xc0
bus_remove_driver+0x53/0xd0
driver_unregister+0x27/0x50
pci_unregister_driver+0x25/0x70
i915_exit+0x1a/0x1e2 [i915]
SyS_delete_module+0x193/0x1f0
entry_SYSCALL_64_fastpath+0x1c/0xac
Fixes: 52b4b950b507 ("mm: slab: free kmem_cache_node after destroy sysfs file")
Link: http://lkml.kernel.org/r/1470759070-18743-1-git-send-email-chris@chris-wilson.co.uk
Reported-by: Dave Gordon <david.s.gordon@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Vladimir Davydov <vdavydov@virtuozzo.com>
Acked-by: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Dmitry Safonov <dsafonov@virtuozzo.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Dave Gordon <david.s.gordon@intel.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-08-10 16:27:58 -07:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
2018-04-05 16:21:57 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-04-13 22:34:51 +08:00
|
|
|
|
2018-04-05 16:21:57 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2007-05-09 02:32:39 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2016-02-17 13:11:37 -08:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
2014-08-06 16:04:09 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2021-02-26 17:11:55 +01:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2014-08-06 16:04:09 -07:00
|
|
|
|
2008-04-23 12:36:52 -07:00
|
|
|
|
2023-04-13 22:34:51 +08:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-01-07 13:46:11 -08:00
|
|
|
|
2022-04-14 19:13:40 -07:00
|
|
|
|
mm: Add mem_dump_obj() to print source of memory block
There are kernel facilities such as per-CPU reference counts that give
error messages in generic handlers or callbacks, whose messages are
unenlightening. In the case of per-CPU reference-count underflow, this
is not a problem when creating a new use of this facility because in that
case the bug is almost certainly in the code implementing that new use.
However, trouble arises when deploying across many systems, which might
exercise corner cases that were not seen during development and testing.
Here, it would be really nice to get some kind of hint as to which of
several uses the underflow was caused by.
This commit therefore exposes a mem_dump_obj() function that takes
a pointer to memory (which must still be allocated if it has been
dynamically allocated) and prints available information on where that
memory came from. This pointer can reference the middle of the block as
well as the beginning of the block, as needed by things like RCU callback
functions and timer handlers that might not know where the beginning of
the memory block is. These functions and handlers can use mem_dump_obj()
to print out better hints as to where the problem might lie.
The information printed can depend on kernel configuration. For example,
the allocation return address can be printed only for slab and slub,
and even then only when the necessary debug has been enabled. For slab,
build with CONFIG_DEBUG_SLAB=y, and either use sizes with ample space
to the next power of two or use the SLAB_STORE_USER when creating the
kmem_cache structure. For slub, build with CONFIG_SLUB_DEBUG=y and
boot with slub_debug=U, or pass SLAB_STORE_USER to kmem_cache_create()
if more focused use is desired. Also for slub, use CONFIG_STACKTRACE
to enable printing of the allocation-time stack trace.
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: <linux-mm@kvack.org>
Reported-by: Andrii Nakryiko <andrii@kernel.org>
[ paulmck: Convert to printing and change names per Joonsoo Kim. ]
[ paulmck: Move slab definition per Stephen Rothwell and kbuild test robot. ]
[ paulmck: Handle CONFIG_MMU=n case where vmalloc() is kmalloc(). ]
[ paulmck: Apply Vlastimil Babka feedback on slab.c kmem_provenance(). ]
[ paulmck: Extract more info from !SLUB_DEBUG per Joonsoo Kim. ]
[ paulmck: Explicitly check for small pointers per Naresh Kamboju. ]
Acked-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Tested-by: Naresh Kamboju <naresh.kamboju@linaro.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
2020-12-07 17:41:02 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-10-04 14:45:55 +01:00
|
|
|
|
mm: Add mem_dump_obj() to print source of memory block
There are kernel facilities such as per-CPU reference counts that give
error messages in generic handlers or callbacks, whose messages are
unenlightening. In the case of per-CPU reference-count underflow, this
is not a problem when creating a new use of this facility because in that
case the bug is almost certainly in the code implementing that new use.
However, trouble arises when deploying across many systems, which might
exercise corner cases that were not seen during development and testing.
Here, it would be really nice to get some kind of hint as to which of
several uses the underflow was caused by.
This commit therefore exposes a mem_dump_obj() function that takes
a pointer to memory (which must still be allocated if it has been
dynamically allocated) and prints available information on where that
memory came from. This pointer can reference the middle of the block as
well as the beginning of the block, as needed by things like RCU callback
functions and timer handlers that might not know where the beginning of
the memory block is. These functions and handlers can use mem_dump_obj()
to print out better hints as to where the problem might lie.
The information printed can depend on kernel configuration. For example,
the allocation return address can be printed only for slab and slub,
and even then only when the necessary debug has been enabled. For slab,
build with CONFIG_DEBUG_SLAB=y, and either use sizes with ample space
to the next power of two or use the SLAB_STORE_USER when creating the
kmem_cache structure. For slub, build with CONFIG_SLUB_DEBUG=y and
boot with slub_debug=U, or pass SLAB_STORE_USER to kmem_cache_create()
if more focused use is desired. Also for slub, use CONFIG_STACKTRACE
to enable printing of the allocation-time stack trace.
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: <linux-mm@kvack.org>
Reported-by: Andrii Nakryiko <andrii@kernel.org>
[ paulmck: Convert to printing and change names per Joonsoo Kim. ]
[ paulmck: Move slab definition per Stephen Rothwell and kbuild test robot. ]
[ paulmck: Handle CONFIG_MMU=n case where vmalloc() is kmalloc(). ]
[ paulmck: Apply Vlastimil Babka feedback on slab.c kmem_provenance(). ]
[ paulmck: Extract more info from !SLUB_DEBUG per Joonsoo Kim. ]
[ paulmck: Explicitly check for small pointers per Naresh Kamboju. ]
Acked-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Tested-by: Naresh Kamboju <naresh.kamboju@linaro.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
2020-12-07 17:41:02 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-10-04 14:45:55 +01:00
|
|
|
|
mm: Add mem_dump_obj() to print source of memory block
There are kernel facilities such as per-CPU reference counts that give
error messages in generic handlers or callbacks, whose messages are
unenlightening. In the case of per-CPU reference-count underflow, this
is not a problem when creating a new use of this facility because in that
case the bug is almost certainly in the code implementing that new use.
However, trouble arises when deploying across many systems, which might
exercise corner cases that were not seen during development and testing.
Here, it would be really nice to get some kind of hint as to which of
several uses the underflow was caused by.
This commit therefore exposes a mem_dump_obj() function that takes
a pointer to memory (which must still be allocated if it has been
dynamically allocated) and prints available information on where that
memory came from. This pointer can reference the middle of the block as
well as the beginning of the block, as needed by things like RCU callback
functions and timer handlers that might not know where the beginning of
the memory block is. These functions and handlers can use mem_dump_obj()
to print out better hints as to where the problem might lie.
The information printed can depend on kernel configuration. For example,
the allocation return address can be printed only for slab and slub,
and even then only when the necessary debug has been enabled. For slab,
build with CONFIG_DEBUG_SLAB=y, and either use sizes with ample space
to the next power of two or use the SLAB_STORE_USER when creating the
kmem_cache structure. For slub, build with CONFIG_SLUB_DEBUG=y and
boot with slub_debug=U, or pass SLAB_STORE_USER to kmem_cache_create()
if more focused use is desired. Also for slub, use CONFIG_STACKTRACE
to enable printing of the allocation-time stack trace.
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: <linux-mm@kvack.org>
Reported-by: Andrii Nakryiko <andrii@kernel.org>
[ paulmck: Convert to printing and change names per Joonsoo Kim. ]
[ paulmck: Move slab definition per Stephen Rothwell and kbuild test robot. ]
[ paulmck: Handle CONFIG_MMU=n case where vmalloc() is kmalloc(). ]
[ paulmck: Apply Vlastimil Babka feedback on slab.c kmem_provenance(). ]
[ paulmck: Extract more info from !SLUB_DEBUG per Joonsoo Kim. ]
[ paulmck: Explicitly check for small pointers per Naresh Kamboju. ]
Acked-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Tested-by: Naresh Kamboju <naresh.kamboju@linaro.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
2020-12-07 17:41:02 -08:00
|
|
|
|
2021-10-04 14:45:55 +01:00
|
|
|
|
mm: Add mem_dump_obj() to print source of memory block
There are kernel facilities such as per-CPU reference counts that give
error messages in generic handlers or callbacks, whose messages are
unenlightening. In the case of per-CPU reference-count underflow, this
is not a problem when creating a new use of this facility because in that
case the bug is almost certainly in the code implementing that new use.
However, trouble arises when deploying across many systems, which might
exercise corner cases that were not seen during development and testing.
Here, it would be really nice to get some kind of hint as to which of
several uses the underflow was caused by.
This commit therefore exposes a mem_dump_obj() function that takes
a pointer to memory (which must still be allocated if it has been
dynamically allocated) and prints available information on where that
memory came from. This pointer can reference the middle of the block as
well as the beginning of the block, as needed by things like RCU callback
functions and timer handlers that might not know where the beginning of
the memory block is. These functions and handlers can use mem_dump_obj()
to print out better hints as to where the problem might lie.
The information printed can depend on kernel configuration. For example,
the allocation return address can be printed only for slab and slub,
and even then only when the necessary debug has been enabled. For slab,
build with CONFIG_DEBUG_SLAB=y, and either use sizes with ample space
to the next power of two or use the SLAB_STORE_USER when creating the
kmem_cache structure. For slub, build with CONFIG_SLUB_DEBUG=y and
boot with slub_debug=U, or pass SLAB_STORE_USER to kmem_cache_create()
if more focused use is desired. Also for slub, use CONFIG_STACKTRACE
to enable printing of the allocation-time stack trace.
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: <linux-mm@kvack.org>
Reported-by: Andrii Nakryiko <andrii@kernel.org>
[ paulmck: Convert to printing and change names per Joonsoo Kim. ]
[ paulmck: Move slab definition per Stephen Rothwell and kbuild test robot. ]
[ paulmck: Handle CONFIG_MMU=n case where vmalloc() is kmalloc(). ]
[ paulmck: Apply Vlastimil Babka feedback on slab.c kmem_provenance(). ]
[ paulmck: Extract more info from !SLUB_DEBUG per Joonsoo Kim. ]
[ paulmck: Explicitly check for small pointers per Naresh Kamboju. ]
Acked-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Tested-by: Naresh Kamboju <naresh.kamboju@linaro.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
2020-12-07 17:41:02 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-11-02 15:42:04 +01:00
|
|
|
|
mm: Add mem_dump_obj() to print source of memory block
There are kernel facilities such as per-CPU reference counts that give
error messages in generic handlers or callbacks, whose messages are
unenlightening. In the case of per-CPU reference-count underflow, this
is not a problem when creating a new use of this facility because in that
case the bug is almost certainly in the code implementing that new use.
However, trouble arises when deploying across many systems, which might
exercise corner cases that were not seen during development and testing.
Here, it would be really nice to get some kind of hint as to which of
several uses the underflow was caused by.
This commit therefore exposes a mem_dump_obj() function that takes
a pointer to memory (which must still be allocated if it has been
dynamically allocated) and prints available information on where that
memory came from. This pointer can reference the middle of the block as
well as the beginning of the block, as needed by things like RCU callback
functions and timer handlers that might not know where the beginning of
the memory block is. These functions and handlers can use mem_dump_obj()
to print out better hints as to where the problem might lie.
The information printed can depend on kernel configuration. For example,
the allocation return address can be printed only for slab and slub,
and even then only when the necessary debug has been enabled. For slab,
build with CONFIG_DEBUG_SLAB=y, and either use sizes with ample space
to the next power of two or use the SLAB_STORE_USER when creating the
kmem_cache structure. For slub, build with CONFIG_SLUB_DEBUG=y and
boot with slub_debug=U, or pass SLAB_STORE_USER to kmem_cache_create()
if more focused use is desired. Also for slub, use CONFIG_STACKTRACE
to enable printing of the allocation-time stack trace.
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: <linux-mm@kvack.org>
Reported-by: Andrii Nakryiko <andrii@kernel.org>
[ paulmck: Convert to printing and change names per Joonsoo Kim. ]
[ paulmck: Move slab definition per Stephen Rothwell and kbuild test robot. ]
[ paulmck: Handle CONFIG_MMU=n case where vmalloc() is kmalloc(). ]
[ paulmck: Apply Vlastimil Babka feedback on slab.c kmem_provenance(). ]
[ paulmck: Extract more info from !SLUB_DEBUG per Joonsoo Kim. ]
[ paulmck: Explicitly check for small pointers per Naresh Kamboju. ]
Acked-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Tested-by: Naresh Kamboju <naresh.kamboju@linaro.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
2020-12-07 17:41:02 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-10-04 14:45:55 +01:00
|
|
|
|
|
|
|
|
|
mm: Add mem_dump_obj() to print source of memory block
There are kernel facilities such as per-CPU reference counts that give
error messages in generic handlers or callbacks, whose messages are
unenlightening. In the case of per-CPU reference-count underflow, this
is not a problem when creating a new use of this facility because in that
case the bug is almost certainly in the code implementing that new use.
However, trouble arises when deploying across many systems, which might
exercise corner cases that were not seen during development and testing.
Here, it would be really nice to get some kind of hint as to which of
several uses the underflow was caused by.
This commit therefore exposes a mem_dump_obj() function that takes
a pointer to memory (which must still be allocated if it has been
dynamically allocated) and prints available information on where that
memory came from. This pointer can reference the middle of the block as
well as the beginning of the block, as needed by things like RCU callback
functions and timer handlers that might not know where the beginning of
the memory block is. These functions and handlers can use mem_dump_obj()
to print out better hints as to where the problem might lie.
The information printed can depend on kernel configuration. For example,
the allocation return address can be printed only for slab and slub,
and even then only when the necessary debug has been enabled. For slab,
build with CONFIG_DEBUG_SLAB=y, and either use sizes with ample space
to the next power of two or use the SLAB_STORE_USER when creating the
kmem_cache structure. For slub, build with CONFIG_SLUB_DEBUG=y and
boot with slub_debug=U, or pass SLAB_STORE_USER to kmem_cache_create()
if more focused use is desired. Also for slub, use CONFIG_STACKTRACE
to enable printing of the allocation-time stack trace.
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: <linux-mm@kvack.org>
Reported-by: Andrii Nakryiko <andrii@kernel.org>
[ paulmck: Convert to printing and change names per Joonsoo Kim. ]
[ paulmck: Move slab definition per Stephen Rothwell and kbuild test robot. ]
[ paulmck: Handle CONFIG_MMU=n case where vmalloc() is kmalloc(). ]
[ paulmck: Apply Vlastimil Babka feedback on slab.c kmem_provenance(). ]
[ paulmck: Extract more info from !SLUB_DEBUG per Joonsoo Kim. ]
[ paulmck: Explicitly check for small pointers per Naresh Kamboju. ]
Acked-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Tested-by: Naresh Kamboju <naresh.kamboju@linaro.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
2020-12-07 17:41:02 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-03-16 16:07:10 +05:30
|
|
|
|
mm: Add mem_dump_obj() to print source of memory block
There are kernel facilities such as per-CPU reference counts that give
error messages in generic handlers or callbacks, whose messages are
unenlightening. In the case of per-CPU reference-count underflow, this
is not a problem when creating a new use of this facility because in that
case the bug is almost certainly in the code implementing that new use.
However, trouble arises when deploying across many systems, which might
exercise corner cases that were not seen during development and testing.
Here, it would be really nice to get some kind of hint as to which of
several uses the underflow was caused by.
This commit therefore exposes a mem_dump_obj() function that takes
a pointer to memory (which must still be allocated if it has been
dynamically allocated) and prints available information on where that
memory came from. This pointer can reference the middle of the block as
well as the beginning of the block, as needed by things like RCU callback
functions and timer handlers that might not know where the beginning of
the memory block is. These functions and handlers can use mem_dump_obj()
to print out better hints as to where the problem might lie.
The information printed can depend on kernel configuration. For example,
the allocation return address can be printed only for slab and slub,
and even then only when the necessary debug has been enabled. For slab,
build with CONFIG_DEBUG_SLAB=y, and either use sizes with ample space
to the next power of two or use the SLAB_STORE_USER when creating the
kmem_cache structure. For slub, build with CONFIG_SLUB_DEBUG=y and
boot with slub_debug=U, or pass SLAB_STORE_USER to kmem_cache_create()
if more focused use is desired. Also for slub, use CONFIG_STACKTRACE
to enable printing of the allocation-time stack trace.
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: <linux-mm@kvack.org>
Reported-by: Andrii Nakryiko <andrii@kernel.org>
[ paulmck: Convert to printing and change names per Joonsoo Kim. ]
[ paulmck: Move slab definition per Stephen Rothwell and kbuild test robot. ]
[ paulmck: Handle CONFIG_MMU=n case where vmalloc() is kmalloc(). ]
[ paulmck: Apply Vlastimil Babka feedback on slab.c kmem_provenance(). ]
[ paulmck: Extract more info from !SLUB_DEBUG per Joonsoo Kim. ]
[ paulmck: Explicitly check for small pointers per Naresh Kamboju. ]
Acked-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Tested-by: Naresh Kamboju <naresh.kamboju@linaro.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
2020-12-07 17:41:02 -08:00
|
|
|
|
|
|
|
|
|
2021-07-07 18:07:47 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-03-16 16:07:11 +05:30
|
|
|
|
2021-07-07 18:07:47 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-03-16 16:07:11 +05:30
|
|
|
|
mm: Add mem_dump_obj() to print source of memory block
There are kernel facilities such as per-CPU reference counts that give
error messages in generic handlers or callbacks, whose messages are
unenlightening. In the case of per-CPU reference-count underflow, this
is not a problem when creating a new use of this facility because in that
case the bug is almost certainly in the code implementing that new use.
However, trouble arises when deploying across many systems, which might
exercise corner cases that were not seen during development and testing.
Here, it would be really nice to get some kind of hint as to which of
several uses the underflow was caused by.
This commit therefore exposes a mem_dump_obj() function that takes
a pointer to memory (which must still be allocated if it has been
dynamically allocated) and prints available information on where that
memory came from. This pointer can reference the middle of the block as
well as the beginning of the block, as needed by things like RCU callback
functions and timer handlers that might not know where the beginning of
the memory block is. These functions and handlers can use mem_dump_obj()
to print out better hints as to where the problem might lie.
The information printed can depend on kernel configuration. For example,
the allocation return address can be printed only for slab and slub,
and even then only when the necessary debug has been enabled. For slab,
build with CONFIG_DEBUG_SLAB=y, and either use sizes with ample space
to the next power of two or use the SLAB_STORE_USER when creating the
kmem_cache structure. For slub, build with CONFIG_SLUB_DEBUG=y and
boot with slub_debug=U, or pass SLAB_STORE_USER to kmem_cache_create()
if more focused use is desired. Also for slub, use CONFIG_STACKTRACE
to enable printing of the allocation-time stack trace.
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: <linux-mm@kvack.org>
Reported-by: Andrii Nakryiko <andrii@kernel.org>
[ paulmck: Convert to printing and change names per Joonsoo Kim. ]
[ paulmck: Move slab definition per Stephen Rothwell and kbuild test robot. ]
[ paulmck: Handle CONFIG_MMU=n case where vmalloc() is kmalloc(). ]
[ paulmck: Apply Vlastimil Babka feedback on slab.c kmem_provenance(). ]
[ paulmck: Extract more info from !SLUB_DEBUG per Joonsoo Kim. ]
[ paulmck: Explicitly check for small pointers per Naresh Kamboju. ]
Acked-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Tested-by: Naresh Kamboju <naresh.kamboju@linaro.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
2020-12-07 17:41:02 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-01-07 13:46:11 -08:00
|
|
|
|
mm: Add mem_dump_obj() to print source of memory block
There are kernel facilities such as per-CPU reference counts that give
error messages in generic handlers or callbacks, whose messages are
unenlightening. In the case of per-CPU reference-count underflow, this
is not a problem when creating a new use of this facility because in that
case the bug is almost certainly in the code implementing that new use.
However, trouble arises when deploying across many systems, which might
exercise corner cases that were not seen during development and testing.
Here, it would be really nice to get some kind of hint as to which of
several uses the underflow was caused by.
This commit therefore exposes a mem_dump_obj() function that takes
a pointer to memory (which must still be allocated if it has been
dynamically allocated) and prints available information on where that
memory came from. This pointer can reference the middle of the block as
well as the beginning of the block, as needed by things like RCU callback
functions and timer handlers that might not know where the beginning of
the memory block is. These functions and handlers can use mem_dump_obj()
to print out better hints as to where the problem might lie.
The information printed can depend on kernel configuration. For example,
the allocation return address can be printed only for slab and slub,
and even then only when the necessary debug has been enabled. For slab,
build with CONFIG_DEBUG_SLAB=y, and either use sizes with ample space
to the next power of two or use the SLAB_STORE_USER when creating the
kmem_cache structure. For slub, build with CONFIG_SLUB_DEBUG=y and
boot with slub_debug=U, or pass SLAB_STORE_USER to kmem_cache_create()
if more focused use is desired. Also for slub, use CONFIG_STACKTRACE
to enable printing of the allocation-time stack trace.
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: <linux-mm@kvack.org>
Reported-by: Andrii Nakryiko <andrii@kernel.org>
[ paulmck: Convert to printing and change names per Joonsoo Kim. ]
[ paulmck: Move slab definition per Stephen Rothwell and kbuild test robot. ]
[ paulmck: Handle CONFIG_MMU=n case where vmalloc() is kmalloc(). ]
[ paulmck: Apply Vlastimil Babka feedback on slab.c kmem_provenance(). ]
[ paulmck: Extract more info from !SLUB_DEBUG per Joonsoo Kim. ]
[ paulmck: Explicitly check for small pointers per Naresh Kamboju. ]
Acked-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Tested-by: Naresh Kamboju <naresh.kamboju@linaro.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
2020-12-07 17:41:02 -08:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-04-05 16:21:39 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2023-09-20 15:44:13 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-12-15 11:41:48 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-04-05 16:21:39 -07:00
|
|
|
|
2023-12-28 17:47:04 +03:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2023-09-20 15:44:13 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-12-15 11:41:48 +08:00
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-04-05 16:21:39 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-12-15 11:41:48 +08:00
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2024-10-01 12:08:06 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-06-23 15:24:05 -07:00
|
|
|
|
|
|
|
|
|
2018-01-10 15:17:01 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-06-23 15:24:05 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-10-04 14:45:56 +01:00
|
|
|
|
|
|
|
|
|
2016-06-23 15:24:05 -07:00
|
|
|
|
|
|
|
|
|
2018-04-05 16:21:20 -07:00
|
|
|
|
2021-02-25 17:19:16 -08:00
|
|
|
|
2016-06-23 15:24:05 -07:00
|
|
|
|
2019-01-08 15:23:15 -08:00
|
|
|
|
|
|
|
|
|
2016-06-23 15:24:05 -07:00
|
|
|
|
2021-10-04 14:45:56 +01:00
|
|
|
|
2016-06-23 15:24:05 -07:00
|
|
|
|
|
|
|
|
|
2021-10-04 14:45:56 +01:00
|
|
|
|
2018-01-10 14:48:22 -08:00
|
|
|
|
|
|
|
|
|
2016-06-23 15:24:05 -07:00
|
|
|
|
|
|
|
|
|
2021-02-25 17:19:16 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-10-04 14:45:56 +01:00
|
|
|
|
2016-06-23 15:24:05 -07:00
|
|
|
|
|
|
|
|
|
2021-02-25 17:19:16 -08:00
|
|
|
|
2016-06-23 15:24:05 -07:00
|
|
|
|
2018-01-10 14:48:22 -08:00
|
|
|
|
|
|
|
|
|
2016-06-23 15:24:05 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-01-10 15:17:01 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-01-10 14:48:22 -08:00
|
|
|
|
2016-06-23 15:24:05 -07:00
|
|
|
|
2018-01-10 14:48:22 -08:00
|
|
|
|
2016-06-23 15:24:05 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-02-12 14:59:41 -08:00
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:46 -07:00
|
|
|
|
2015-02-12 14:59:41 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-09 02:32:39 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:46 -07:00
|
|
|
|
2021-02-26 17:11:55 +01:00
|
|
|
|
2007-05-06 14:49:46 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
|
|
|
|
|
2015-02-12 14:59:41 -08:00
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:46 -07:00
|
|
|
|
2015-02-12 14:59:44 -08:00
|
|
|
|
2007-05-06 14:49:46 -07:00
|
|
|
|
2014-08-06 16:04:09 -07:00
|
|
|
|
2015-02-12 14:59:41 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:46 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-02-12 14:59:41 -08:00
|
|
|
|
2007-05-06 14:49:46 -07:00
|
|
|
|
2007-05-09 02:32:39 -07:00
|
|
|
|
2021-11-15 16:55:15 +01:00
|
|
|
|
2007-05-06 14:49:46 -07:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
|
|
|
|
|
2015-02-12 14:59:41 -08:00
|
|
|
|
2021-11-15 16:55:15 +01:00
|
|
|
|
2015-02-12 14:59:41 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
|
|
|
|
|
2023-11-02 03:23:24 +00:00
|
|
|
|
2011-08-09 16:12:22 -05:00
|
|
|
|
mm/slub: restrict sysfs validation to debug caches and make it safe
Rongwei Wang reports [1] that cache validation triggered by writing to
/sys/kernel/slab/<cache>/validate is racy against normal cache
operations (e.g. freeing) in a way that can cause false positive
inconsistency reports for caches with debugging enabled. The problem is
that debugging actions that mark object free or active and actual
freelist operations are not atomic, and the validation can see an
inconsistent state.
For caches that do or don't have debugging enabled, additional races
involving n->nr_slabs are possible that result in false reports of wrong
slab counts.
This patch attempts to solve these issues while not adding overhead to
normal (especially fastpath) operations for caches that do not have
debugging enabled. Such overhead would not be justified to make possible
userspace-triggered validation safe. Instead, disable the validation for
caches that don't have debugging enabled and make their sysfs validate
handler return -EINVAL.
For caches that do have debugging enabled, we can instead extend the
existing approach of not using percpu freelists to force all alloc/free
operations to the slow paths where debugging flags is checked and acted
upon. There can adjust the debug-specific paths to increase n->list_lock
coverage against concurrent validation as necessary.
The processing on free in free_debug_processing() already happens under
n->list_lock so we can extend it to actually do the freeing as well and
thus make it atomic against concurrent validation. As observed by
Hyeonggon Yoo, we do not really need to take slab_lock() anymore here
because all paths we could race with are protected by n->list_lock under
the new scheme, so drop its usage here.
The processing on alloc in alloc_debug_processing() currently doesn't
take any locks, but we have to first allocate the object from a slab on
the partial list (as debugging caches have no percpu slabs) and thus
take the n->list_lock anyway. Add a function alloc_single_from_partial()
that grabs just the allocated object instead of the whole freelist, and
does the debug processing. The n->list_lock coverage again makes it
atomic against validation and it is also ultimately more efficient than
the current grabbing of freelist immediately followed by slab
deactivation.
To prevent races on n->nr_slabs updates, make sure that for caches with
debugging enabled, inc_slabs_node() or dec_slabs_node() is called under
n->list_lock. When allocating a new slab for a debug cache, handle the
allocation by a new function alloc_single_from_new_slab() instead of the
current forced deactivation path.
Neither of these changes affect the fast paths at all. The changes in
slow paths are negligible for non-debug caches.
[1] https://lore.kernel.org/all/20220529081535.69275-1-rongwei.wang@linux.alibaba.com/
Reported-by: Rongwei Wang <rongwei.wang@linux.alibaba.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
2022-08-23 19:03:57 +02:00
|
|
|
|
2015-02-12 14:59:41 -08:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2007-05-06 14:49:46 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-02-12 14:59:41 -08:00
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:46 -07:00
|
|
|
|
2015-02-12 14:59:41 -08:00
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:46 -07:00
|
|
|
|
|
|
|
|
|
2011-08-09 16:12:22 -05:00
|
|
|
|
|
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
mm/slub: restrict sysfs validation to debug caches and make it safe
Rongwei Wang reports [1] that cache validation triggered by writing to
/sys/kernel/slab/<cache>/validate is racy against normal cache
operations (e.g. freeing) in a way that can cause false positive
inconsistency reports for caches with debugging enabled. The problem is
that debugging actions that mark object free or active and actual
freelist operations are not atomic, and the validation can see an
inconsistent state.
For caches that do or don't have debugging enabled, additional races
involving n->nr_slabs are possible that result in false reports of wrong
slab counts.
This patch attempts to solve these issues while not adding overhead to
normal (especially fastpath) operations for caches that do not have
debugging enabled. Such overhead would not be justified to make possible
userspace-triggered validation safe. Instead, disable the validation for
caches that don't have debugging enabled and make their sysfs validate
handler return -EINVAL.
For caches that do have debugging enabled, we can instead extend the
existing approach of not using percpu freelists to force all alloc/free
operations to the slow paths where debugging flags is checked and acted
upon. There can adjust the debug-specific paths to increase n->list_lock
coverage against concurrent validation as necessary.
The processing on free in free_debug_processing() already happens under
n->list_lock so we can extend it to actually do the freeing as well and
thus make it atomic against concurrent validation. As observed by
Hyeonggon Yoo, we do not really need to take slab_lock() anymore here
because all paths we could race with are protected by n->list_lock under
the new scheme, so drop its usage here.
The processing on alloc in alloc_debug_processing() currently doesn't
take any locks, but we have to first allocate the object from a slab on
the partial list (as debugging caches have no percpu slabs) and thus
take the n->list_lock anyway. Add a function alloc_single_from_partial()
that grabs just the allocated object instead of the whole freelist, and
does the debug processing. The n->list_lock coverage again makes it
atomic against validation and it is also ultimately more efficient than
the current grabbing of freelist immediately followed by slab
deactivation.
To prevent races on n->nr_slabs updates, make sure that for caches with
debugging enabled, inc_slabs_node() or dec_slabs_node() is called under
n->list_lock. When allocating a new slab for a debug cache, handle the
allocation by a new function alloc_single_from_new_slab() instead of the
current forced deactivation path.
Neither of these changes affect the fast paths at all. The changes in
slow paths are negligible for non-debug caches.
[1] https://lore.kernel.org/all/20220529081535.69275-1-rongwei.wang@linux.alibaba.com/
Reported-by: Rongwei Wang <rongwei.wang@linux.alibaba.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
2022-08-23 19:03:57 +02:00
|
|
|
|
2015-02-12 14:59:44 -08:00
|
|
|
|
2023-04-13 22:34:51 +08:00
|
|
|
|
2015-02-12 14:59:44 -08:00
|
|
|
|
2007-05-06 14:49:46 -07:00
|
|
|
|
|
|
|
|
|
2015-02-12 14:59:44 -08:00
|
|
|
|
2007-05-06 14:49:46 -07:00
|
|
|
|
|
|
|
|
|
2021-02-26 17:11:55 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-10-21 16:41:37 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-07-06 15:25:12 -05:00
|
|
|
|
2021-02-26 17:11:55 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-07-06 15:25:12 -05:00
|
|
|
|
2007-10-21 16:41:37 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-12-11 16:01:05 -08:00
|
|
|
|
2007-10-21 16:41:37 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-07-06 15:25:12 -05:00
|
|
|
|
mm, slab, slub: stop taking memory hotplug lock
Since commit 03afc0e25f7f ("slab: get_online_mems for
kmem_cache_{create,destroy,shrink}") we are taking memory hotplug lock for
SLAB and SLUB when creating, destroying or shrinking a cache. It is quite
a heavy lock and it's best to avoid it if possible, as we had several
issues with lockdep complaining about ordering in the past, see e.g.
e4f8e513c3d3 ("mm/slub: fix a deadlock in show_slab_objects()").
The problem scenario in 03afc0e25f7f (solved by the memory hotplug lock)
can be summarized as follows: while there's slab_mutex synchronizing new
kmem cache creation and SLUB's MEM_GOING_ONLINE callback
slab_mem_going_online_callback(), we may miss creation of kmem_cache_node
for the hotplugged node in the new kmem cache, because the hotplug
callback doesn't yet see the new cache, and cache creation in
init_kmem_cache_nodes() only inits kmem_cache_node for nodes in the
N_NORMAL_MEMORY nodemask, which however may not yet include the new node,
as that happens only later after the MEM_GOING_ONLINE callback.
Instead of using get/put_online_mems(), the problem can be solved by SLUB
maintaining its own nodemask of nodes for which it has allocated the
per-node kmem_cache_node structures. This nodemask would generally mirror
the N_NORMAL_MEMORY nodemask, but would be updated only in under SLUB's
control in its memory hotplug callbacks under the slab_mutex. This patch
adds such nodemask and its handling.
Commit 03afc0e25f7f mentiones "issues like [the one above]", but there
don't appear to be further issues. All the paths (shared for SLAB and
SLUB) taking the memory hotplug locks are also taking the slab_mutex,
except kmem_cache_shrink() where 03afc0e25f7f replaced slab_mutex with
get/put_online_mems().
We however cannot simply restore slab_mutex in kmem_cache_shrink(), as
SLUB can enters the function from a write to sysfs 'shrink' file, thus
holding kernfs lock, and in kmem_cache_create() the kernfs lock is nested
within slab_mutex. But on closer inspection we don't actually need to
protect kmem_cache_shrink() from hotplug callbacks: While SLUB's
__kmem_cache_shrink() does for_each_kmem_cache_node(), missing a new node
added in parallel hotplug is not fatal, and parallel hotremove does not
free kmem_cache_node's anymore after the previous patch, so use-after free
cannot happen. The per-node shrinking itself is protected by
n->list_lock. Same is true for SLAB, and SLOB is no-op.
SLAB also doesn't need the memory hotplug locking, which it only gained by
03afc0e25f7f through the shared paths in slab_common.c. Its memory
hotplug callbacks are also protected by slab_mutex against races with
these paths. The problem of SLUB relying on N_NORMAL_MEMORY doesn't apply
to SLAB, as its setup_kmem_cache_nodes relies on N_ONLINE, and the new
node is already set there during the MEM_GOING_ONLINE callback, so no
special care is needed for SLAB.
As such, this patch removes all get/put_online_mems() usage by the slab
subsystem.
Link: https://lkml.kernel.org/r/20210113131634.3671-3-vbabka@suse.cz
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Christoph Lameter <cl@linux.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Qian Cai <cai@redhat.com>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-02-24 12:01:12 -08:00
|
|
|
|
mm, slub: stop freeing kmem_cache_node structures on node offline
Patch series "mm, slab, slub: remove cpu and memory hotplug locks".
Some related work caused me to look at how we use get/put_mems_online()
and get/put_online_cpus() during kmem cache
creation/descruction/shrinking, and realize that it should be actually
safe to remove all of that with rather small effort (as e.g. Michal Hocko
suspected in some of the past discussions already). This has the benefit
to avoid rather heavy locks that have caused locking order issues already
in the past. So this is the result, Patches 2 and 3 remove memory hotplug
and cpu hotplug locking, respectively. Patch 1 is due to realization that
in fact some races exist despite the locks (even if not removed), but the
most sane solution is not to introduce more of them, but rather accept
some wasted memory in scenarios that should be rare anyway (full memory
hot remove), as we do the same in other contexts already.
This patch (of 3):
Commit e4f8e513c3d3 ("mm/slub: fix a deadlock in show_slab_objects()") has
fixed a problematic locking order by removing the memory hotplug lock
get/put_online_mems() from show_slab_objects(). During the discussion, it
was argued [1] that this is OK, because existing slabs on the node would
prevent a hotremove to proceed.
That's true, but per-node kmem_cache_node structures are not necessarily
allocated on the same node and may exist even without actual slab pages on
the same node. Any path that uses get_node() directly or via
for_each_kmem_cache_node() (such as show_slab_objects()) can race with
freeing of kmem_cache_node even with the !NULL check, resulting in
use-after-free.
To that end, commit e4f8e513c3d3 argues in a comment that:
* We don't really need mem_hotplug_lock (to hold off
* slab_mem_going_offline_callback) here because slab's memory hot
* unplug code doesn't destroy the kmem_cache->node[] data.
While it's true that slab_mem_going_offline_callback() doesn't free the
kmem_cache_node, the later callback slab_mem_offline_callback() actually
does, so the race and use-after-free exists. Not just for
show_slab_objects() after commit e4f8e513c3d3, but also many other places
that are not under slab_mutex. And adding slab_mutex locking or other
synchronization to SLUB paths such as get_any_partial() would be bad for
performance and error-prone.
The easiest solution is therefore to make the abovementioned comment true
and stop freeing the kmem_cache_node structures, accepting some wasted
memory in the full memory node removal scenario. Analogically we also
don't free hotremoved pgdat as mentioned in [1], nor the similar per-node
structures in SLAB. Importantly this approach will not block the
hotremove, as generally such nodes should be movable in order to succeed
hotremove in the first place, and thus the GFP_KERNEL allocated
kmem_cache_node will come from elsewhere.
[1] https://lore.kernel.org/linux-mm/20190924151147.GB23050@dhcp22.suse.cz/
Link: https://lkml.kernel.org/r/20210113131634.3671-1-vbabka@suse.cz
Link: https://lkml.kernel.org/r/20210113131634.3671-2-vbabka@suse.cz
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Cc: Qian Cai <cai@redhat.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-02-24 12:01:08 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-07-06 15:25:12 -05:00
|
|
|
|
2007-10-21 16:41:37 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-12-11 16:01:05 -08:00
|
|
|
|
2007-10-21 16:41:37 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-04-29 16:11:12 -07:00
|
|
|
|
2007-10-21 16:41:37 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-07-06 15:25:12 -05:00
|
|
|
|
2007-10-21 16:41:37 -07:00
|
|
|
|
mm, slub: stop freeing kmem_cache_node structures on node offline
Patch series "mm, slab, slub: remove cpu and memory hotplug locks".
Some related work caused me to look at how we use get/put_mems_online()
and get/put_online_cpus() during kmem cache
creation/descruction/shrinking, and realize that it should be actually
safe to remove all of that with rather small effort (as e.g. Michal Hocko
suspected in some of the past discussions already). This has the benefit
to avoid rather heavy locks that have caused locking order issues already
in the past. So this is the result, Patches 2 and 3 remove memory hotplug
and cpu hotplug locking, respectively. Patch 1 is due to realization that
in fact some races exist despite the locks (even if not removed), but the
most sane solution is not to introduce more of them, but rather accept
some wasted memory in scenarios that should be rare anyway (full memory
hot remove), as we do the same in other contexts already.
This patch (of 3):
Commit e4f8e513c3d3 ("mm/slub: fix a deadlock in show_slab_objects()") has
fixed a problematic locking order by removing the memory hotplug lock
get/put_online_mems() from show_slab_objects(). During the discussion, it
was argued [1] that this is OK, because existing slabs on the node would
prevent a hotremove to proceed.
That's true, but per-node kmem_cache_node structures are not necessarily
allocated on the same node and may exist even without actual slab pages on
the same node. Any path that uses get_node() directly or via
for_each_kmem_cache_node() (such as show_slab_objects()) can race with
freeing of kmem_cache_node even with the !NULL check, resulting in
use-after-free.
To that end, commit e4f8e513c3d3 argues in a comment that:
* We don't really need mem_hotplug_lock (to hold off
* slab_mem_going_offline_callback) here because slab's memory hot
* unplug code doesn't destroy the kmem_cache->node[] data.
While it's true that slab_mem_going_offline_callback() doesn't free the
kmem_cache_node, the later callback slab_mem_offline_callback() actually
does, so the race and use-after-free exists. Not just for
show_slab_objects() after commit e4f8e513c3d3, but also many other places
that are not under slab_mutex. And adding slab_mutex locking or other
synchronization to SLUB paths such as get_any_partial() would be bad for
performance and error-prone.
The easiest solution is therefore to make the abovementioned comment true
and stop freeing the kmem_cache_node structures, accepting some wasted
memory in the full memory node removal scenario. Analogically we also
don't free hotremoved pgdat as mentioned in [1], nor the similar per-node
structures in SLAB. Importantly this approach will not block the
hotremove, as generally such nodes should be movable in order to succeed
hotremove in the first place, and thus the GFP_KERNEL allocated
kmem_cache_node will come from elsewhere.
[1] https://lore.kernel.org/linux-mm/20190924151147.GB23050@dhcp22.suse.cz/
Link: https://lkml.kernel.org/r/20210113131634.3671-1-vbabka@suse.cz
Link: https://lkml.kernel.org/r/20210113131634.3671-2-vbabka@suse.cz
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Cc: Qian Cai <cai@redhat.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-02-24 12:01:08 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-10-21 16:41:37 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2010-08-25 14:51:14 -05:00
|
|
|
|
2007-10-21 16:41:37 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-05-11 00:50:47 +09:00
|
|
|
|
2007-10-21 16:41:37 -07:00
|
|
|
|
|
|
|
|
|
mm, slab, slub: stop taking memory hotplug lock
Since commit 03afc0e25f7f ("slab: get_online_mems for
kmem_cache_{create,destroy,shrink}") we are taking memory hotplug lock for
SLAB and SLUB when creating, destroying or shrinking a cache. It is quite
a heavy lock and it's best to avoid it if possible, as we had several
issues with lockdep complaining about ordering in the past, see e.g.
e4f8e513c3d3 ("mm/slub: fix a deadlock in show_slab_objects()").
The problem scenario in 03afc0e25f7f (solved by the memory hotplug lock)
can be summarized as follows: while there's slab_mutex synchronizing new
kmem cache creation and SLUB's MEM_GOING_ONLINE callback
slab_mem_going_online_callback(), we may miss creation of kmem_cache_node
for the hotplugged node in the new kmem cache, because the hotplug
callback doesn't yet see the new cache, and cache creation in
init_kmem_cache_nodes() only inits kmem_cache_node for nodes in the
N_NORMAL_MEMORY nodemask, which however may not yet include the new node,
as that happens only later after the MEM_GOING_ONLINE callback.
Instead of using get/put_online_mems(), the problem can be solved by SLUB
maintaining its own nodemask of nodes for which it has allocated the
per-node kmem_cache_node structures. This nodemask would generally mirror
the N_NORMAL_MEMORY nodemask, but would be updated only in under SLUB's
control in its memory hotplug callbacks under the slab_mutex. This patch
adds such nodemask and its handling.
Commit 03afc0e25f7f mentiones "issues like [the one above]", but there
don't appear to be further issues. All the paths (shared for SLAB and
SLUB) taking the memory hotplug locks are also taking the slab_mutex,
except kmem_cache_shrink() where 03afc0e25f7f replaced slab_mutex with
get/put_online_mems().
We however cannot simply restore slab_mutex in kmem_cache_shrink(), as
SLUB can enters the function from a write to sysfs 'shrink' file, thus
holding kernfs lock, and in kmem_cache_create() the kernfs lock is nested
within slab_mutex. But on closer inspection we don't actually need to
protect kmem_cache_shrink() from hotplug callbacks: While SLUB's
__kmem_cache_shrink() does for_each_kmem_cache_node(), missing a new node
added in parallel hotplug is not fatal, and parallel hotremove does not
free kmem_cache_node's anymore after the previous patch, so use-after free
cannot happen. The per-node shrinking itself is protected by
n->list_lock. Same is true for SLAB, and SLOB is no-op.
SLAB also doesn't need the memory hotplug locking, which it only gained by
03afc0e25f7f through the shared paths in slab_common.c. Its memory
hotplug callbacks are also protected by slab_mutex against races with
these paths. The problem of SLUB relying on N_NORMAL_MEMORY doesn't apply
to SLAB, as its setup_kmem_cache_nodes relies on N_ONLINE, and the new
node is already set there during the MEM_GOING_ONLINE callback, so no
special care is needed for SLAB.
As such, this patch removes all get/put_online_mems() usage by the slab
subsystem.
Link: https://lkml.kernel.org/r/20210113131634.3671-3-vbabka@suse.cz
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Christoph Lameter <cl@linux.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Qian Cai <cai@redhat.com>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-02-24 12:01:12 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-10-21 16:41:37 -07:00
|
|
|
|
2012-07-06 15:25:12 -05:00
|
|
|
|
2007-10-21 16:41:37 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-12-01 13:13:48 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-10-21 16:41:37 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2010-08-20 12:37:15 -05:00
|
|
|
|
|
|
|
|
|
2012-11-28 16:23:07 +00:00
|
|
|
|
|
|
|
|
|
2010-08-20 12:37:15 -05:00
|
|
|
|
|
|
|
|
|
2012-11-28 16:23:07 +00:00
|
|
|
|
2010-08-20 12:37:15 -05:00
|
|
|
|
|
|
|
|
|
2012-11-28 16:23:07 +00:00
|
|
|
|
2014-08-06 16:04:09 -07:00
|
|
|
|
2010-08-20 12:37:15 -05:00
|
|
|
|
2012-11-28 16:23:07 +00:00
|
|
|
|
2010-08-20 12:37:15 -05:00
|
|
|
|
2013-02-22 20:20:00 +04:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2014-08-06 16:04:09 -07:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2010-08-20 12:37:15 -05:00
|
|
|
|
2019-05-13 17:16:12 -07:00
|
|
|
|
2014-08-06 16:04:09 -07:00
|
|
|
|
2010-08-20 12:37:15 -05:00
|
|
|
|
2011-04-12 15:22:26 +08:00
|
|
|
|
2019-05-13 17:16:12 -07:00
|
|
|
|
2014-08-06 16:04:09 -07:00
|
|
|
|
2010-08-20 12:37:15 -05:00
|
|
|
|
|
|
|
|
|
2012-11-28 16:23:07 +00:00
|
|
|
|
|
|
|
|
|
2010-08-20 12:37:15 -05:00
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
2012-11-28 16:23:07 +00:00
|
|
|
|
|
|
|
|
|
mm, slab, slub: stop taking memory hotplug lock
Since commit 03afc0e25f7f ("slab: get_online_mems for
kmem_cache_{create,destroy,shrink}") we are taking memory hotplug lock for
SLAB and SLUB when creating, destroying or shrinking a cache. It is quite
a heavy lock and it's best to avoid it if possible, as we had several
issues with lockdep complaining about ordering in the past, see e.g.
e4f8e513c3d3 ("mm/slub: fix a deadlock in show_slab_objects()").
The problem scenario in 03afc0e25f7f (solved by the memory hotplug lock)
can be summarized as follows: while there's slab_mutex synchronizing new
kmem cache creation and SLUB's MEM_GOING_ONLINE callback
slab_mem_going_online_callback(), we may miss creation of kmem_cache_node
for the hotplugged node in the new kmem cache, because the hotplug
callback doesn't yet see the new cache, and cache creation in
init_kmem_cache_nodes() only inits kmem_cache_node for nodes in the
N_NORMAL_MEMORY nodemask, which however may not yet include the new node,
as that happens only later after the MEM_GOING_ONLINE callback.
Instead of using get/put_online_mems(), the problem can be solved by SLUB
maintaining its own nodemask of nodes for which it has allocated the
per-node kmem_cache_node structures. This nodemask would generally mirror
the N_NORMAL_MEMORY nodemask, but would be updated only in under SLUB's
control in its memory hotplug callbacks under the slab_mutex. This patch
adds such nodemask and its handling.
Commit 03afc0e25f7f mentiones "issues like [the one above]", but there
don't appear to be further issues. All the paths (shared for SLAB and
SLUB) taking the memory hotplug locks are also taking the slab_mutex,
except kmem_cache_shrink() where 03afc0e25f7f replaced slab_mutex with
get/put_online_mems().
We however cannot simply restore slab_mutex in kmem_cache_shrink(), as
SLUB can enters the function from a write to sysfs 'shrink' file, thus
holding kernfs lock, and in kmem_cache_create() the kernfs lock is nested
within slab_mutex. But on closer inspection we don't actually need to
protect kmem_cache_shrink() from hotplug callbacks: While SLUB's
__kmem_cache_shrink() does for_each_kmem_cache_node(), missing a new node
added in parallel hotplug is not fatal, and parallel hotremove does not
free kmem_cache_node's anymore after the previous patch, so use-after free
cannot happen. The per-node shrinking itself is protected by
n->list_lock. Same is true for SLAB, and SLOB is no-op.
SLAB also doesn't need the memory hotplug locking, which it only gained by
03afc0e25f7f through the shared paths in slab_common.c. Its memory
hotplug callbacks are also protected by slab_mutex against races with
these paths. The problem of SLUB relying on N_NORMAL_MEMORY doesn't apply
to SLAB, as its setup_kmem_cache_nodes relies on N_ONLINE, and the new
node is already set there during the MEM_GOING_ONLINE callback, so no
special care is needed for SLAB.
As such, this patch removes all get/put_online_mems() usage by the slab
subsystem.
Link: https://lkml.kernel.org/r/20210113131634.3671-3-vbabka@suse.cz
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Christoph Lameter <cl@linux.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Qian Cai <cai@redhat.com>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-02-24 12:01:12 -08:00
|
|
|
|
2010-08-20 12:37:15 -05:00
|
|
|
|
2012-01-10 15:07:32 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-06-28 19:34:52 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-11-28 16:23:07 +00:00
|
|
|
|
|
|
|
|
|
2010-08-20 12:37:15 -05:00
|
|
|
|
mm, slab, slub: stop taking memory hotplug lock
Since commit 03afc0e25f7f ("slab: get_online_mems for
kmem_cache_{create,destroy,shrink}") we are taking memory hotplug lock for
SLAB and SLUB when creating, destroying or shrinking a cache. It is quite
a heavy lock and it's best to avoid it if possible, as we had several
issues with lockdep complaining about ordering in the past, see e.g.
e4f8e513c3d3 ("mm/slub: fix a deadlock in show_slab_objects()").
The problem scenario in 03afc0e25f7f (solved by the memory hotplug lock)
can be summarized as follows: while there's slab_mutex synchronizing new
kmem cache creation and SLUB's MEM_GOING_ONLINE callback
slab_mem_going_online_callback(), we may miss creation of kmem_cache_node
for the hotplugged node in the new kmem cache, because the hotplug
callback doesn't yet see the new cache, and cache creation in
init_kmem_cache_nodes() only inits kmem_cache_node for nodes in the
N_NORMAL_MEMORY nodemask, which however may not yet include the new node,
as that happens only later after the MEM_GOING_ONLINE callback.
Instead of using get/put_online_mems(), the problem can be solved by SLUB
maintaining its own nodemask of nodes for which it has allocated the
per-node kmem_cache_node structures. This nodemask would generally mirror
the N_NORMAL_MEMORY nodemask, but would be updated only in under SLUB's
control in its memory hotplug callbacks under the slab_mutex. This patch
adds such nodemask and its handling.
Commit 03afc0e25f7f mentiones "issues like [the one above]", but there
don't appear to be further issues. All the paths (shared for SLAB and
SLUB) taking the memory hotplug locks are also taking the slab_mutex,
except kmem_cache_shrink() where 03afc0e25f7f replaced slab_mutex with
get/put_online_mems().
We however cannot simply restore slab_mutex in kmem_cache_shrink(), as
SLUB can enters the function from a write to sysfs 'shrink' file, thus
holding kernfs lock, and in kmem_cache_create() the kernfs lock is nested
within slab_mutex. But on closer inspection we don't actually need to
protect kmem_cache_shrink() from hotplug callbacks: While SLUB's
__kmem_cache_shrink() does for_each_kmem_cache_node(), missing a new node
added in parallel hotplug is not fatal, and parallel hotremove does not
free kmem_cache_node's anymore after the previous patch, so use-after free
cannot happen. The per-node shrinking itself is protected by
n->list_lock. Same is true for SLAB, and SLOB is no-op.
SLAB also doesn't need the memory hotplug locking, which it only gained by
03afc0e25f7f through the shared paths in slab_common.c. Its memory
hotplug callbacks are also protected by slab_mutex against races with
these paths. The problem of SLUB relying on N_NORMAL_MEMORY doesn't apply
to SLAB, as its setup_kmem_cache_nodes relies on N_ONLINE, and the new
node is already set there during the MEM_GOING_ONLINE callback, so no
special care is needed for SLAB.
As such, this patch removes all get/put_online_mems() usage by the slab
subsystem.
Link: https://lkml.kernel.org/r/20210113131634.3671-3-vbabka@suse.cz
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Christoph Lameter <cl@linux.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Qian Cai <cai@redhat.com>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-02-24 12:01:12 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-11-28 16:23:07 +00:00
|
|
|
|
2024-03-21 09:36:30 -07:00
|
|
|
|
|
|
|
|
|
2007-10-21 16:41:37 -07:00
|
|
|
|
2022-09-23 11:33:42 +08:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-11-28 16:23:07 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-03-21 09:36:30 -07:00
|
|
|
|
2012-09-04 23:18:33 +00:00
|
|
|
|
2012-11-28 16:23:07 +00:00
|
|
|
|
|
|
|
|
|
2010-08-20 12:37:15 -05:00
|
|
|
|
|
|
|
|
|
2015-06-24 16:55:57 -07:00
|
|
|
|
2024-01-30 09:41:07 +08:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2016-07-26 15:21:59 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-08-18 14:57:19 +02:00
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2019-03-05 15:48:26 -08:00
|
|
|
|
2013-01-10 19:12:17 +00:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2009-06-12 14:03:06 +03:00
|
|
|
|
|
|
|
|
|
2022-11-15 18:14:31 +01:00
|
|
|
|
2022-09-19 18:39:29 +02:00
|
|
|
|
|
|
|
|
|
2022-11-15 18:14:31 +01:00
|
|
|
|
2009-06-12 14:03:06 +03:00
|
|
|
|
|
|
|
|
|
2012-12-18 14:22:34 -08:00
|
|
|
|
2018-04-05 16:20:37 -07:00
|
|
|
|
2017-11-15 17:32:18 -08:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2020-08-06 23:21:27 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
memcg, slab: never try to merge memcg caches
When a kmem cache is created (kmem_cache_create_memcg()), we first try to
find a compatible cache that already exists and can handle requests from
the new cache, i.e. has the same object size, alignment, ctor, etc. If
there is such a cache, we do not create any new caches, instead we simply
increment the refcount of the cache found and return it.
Currently we do this procedure not only when creating root caches, but
also for memcg caches. However, there is no point in that, because, as
every memcg cache has exactly the same parameters as its parent and cache
merging cannot be turned off in runtime (only on boot by passing
"slub_nomerge"), the root caches of any two potentially mergeable memcg
caches should be merged already, i.e. it must be the same root cache, and
therefore we couldn't even get to the memcg cache creation, because it
already exists.
The only exception is boot caches - they are explicitly forbidden to be
merged by setting their refcount to -1. There are currently only two of
them - kmem_cache and kmem_cache_node, which are used in slab internals (I
do not count kmalloc caches as their refcount is set to 1 immediately
after creation). Since they are prevented from merging preliminary I
guess we should avoid to merge their children too.
So let's remove the useless code responsible for merging memcg caches.
Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Glauber Costa <glommer@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-04-07 15:39:23 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2022-05-31 08:55:50 +08:00
|
|
|
|
mm/slab: Allow cache creation to proceed even if sysfs registration fails
When kobject_init_and_add() fails during cache creation,
kobj->name can be leaked because SLUB does not call kobject_put(),
which should be invoked per the kobject API documentation.
This has a bit of historical context, though; SLUB does not call
kobject_put() to avoid double-free for struct kmem_cache because
1) simply calling it would free all resources related to the cache, and
2) struct kmem_cache descriptor is always freed by cache_cache()'s
error handling path, causing struct kmem_cache to be freed twice.
This issue can be reproduced by creating new slab caches while applying
failslab for kernfs_node_cache. This makes kobject_add_varg() succeed,
but causes kobject_add_internal() to fail in kobject_init_and_add()
during cache creation.
Historically, this issue has attracted developers' attention several times.
Each time a fix addressed either the leak or the double-free,
it caused the other issue. Let's summarize a bit of history here:
The leak has existed since the early days of SLUB.
Commit 54b6a731025f ("slub: fix leak of 'name' in sysfs_slab_add")
introduced a double-free bug while fixing the leak.
Commit 80da026a8e5d ("mm/slub: fix slab double-free in case of duplicate
sysfs filename") re-introduced the leak while fixing the double-free
error.
Commit dde3c6b72a16 ("mm/slub: fix a memory leak in sysfs_slab_add()")
fixed the memory leak, but it was later reverted by commit 757fed1d0898
("Revert "mm/slub: fix a memory leak in sysfs_slab_add()"") to avoid
the double-free error.
This is where we are now: we've chosen a memory leak over a double-free.
To resolve this memory leak, skip creating sysfs files if it fails
and continue with cache creation regardless (as suggested by Christoph).
This resolves the memory leak because both the cache and the kobject
remain alive on kobject_init_and_add() failure.
If SLUB tries to create an alias for a cache without sysfs files,
its symbolic link will not be generated.
Since a slab cache might not have associated sysfs files, call kobject_del()
only if such files exist.
Signed-off-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2024-11-01 22:08:44 +09:00
|
|
|
|
|
|
|
|
|
2022-05-31 08:55:50 +08:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2014-04-07 15:39:29 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-04-05 16:21:17 -07:00
|
|
|
|
2018-04-05 16:21:06 -07:00
|
|
|
|
2007-07-17 04:03:31 -07:00
|
|
|
|
2008-02-15 23:45:26 -08:00
|
|
|
|
2012-09-05 00:18:32 +00:00
|
|
|
|
|
|
|
|
|
2010-09-14 23:21:12 +03:00
|
|
|
|
2024-09-05 09:56:51 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-09-05 00:18:32 +00:00
|
|
|
|
2024-09-05 09:56:50 +02:00
|
|
|
|
2012-07-06 15:25:13 -05:00
|
|
|
|
2024-09-05 09:56:51 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-09-05 09:56:50 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-09-05 09:56:51 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-09-05 09:56:50 +02:00
|
|
|
|
2024-09-05 09:56:52 +02:00
|
|
|
|
2024-09-05 09:56:50 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-09-05 09:56:52 +02:00
|
|
|
|
2024-09-05 09:56:50 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-07-06 15:25:13 -05:00
|
|
|
|
mm/slab: Allow cache creation to proceed even if sysfs registration fails
When kobject_init_and_add() fails during cache creation,
kobj->name can be leaked because SLUB does not call kobject_put(),
which should be invoked per the kobject API documentation.
This has a bit of historical context, though; SLUB does not call
kobject_put() to avoid double-free for struct kmem_cache because
1) simply calling it would free all resources related to the cache, and
2) struct kmem_cache descriptor is always freed by cache_cache()'s
error handling path, causing struct kmem_cache to be freed twice.
This issue can be reproduced by creating new slab caches while applying
failslab for kernfs_node_cache. This makes kobject_add_varg() succeed,
but causes kobject_add_internal() to fail in kobject_init_and_add()
during cache creation.
Historically, this issue has attracted developers' attention several times.
Each time a fix addressed either the leak or the double-free,
it caused the other issue. Let's summarize a bit of history here:
The leak has existed since the early days of SLUB.
Commit 54b6a731025f ("slub: fix leak of 'name' in sysfs_slab_add")
introduced a double-free bug while fixing the leak.
Commit 80da026a8e5d ("mm/slub: fix slab double-free in case of duplicate
sysfs filename") re-introduced the leak while fixing the double-free
error.
Commit dde3c6b72a16 ("mm/slub: fix a memory leak in sysfs_slab_add()")
fixed the memory leak, but it was later reverted by commit 757fed1d0898
("Revert "mm/slub: fix a memory leak in sysfs_slab_add()"") to avoid
the double-free error.
This is where we are now: we've chosen a memory leak over a double-free.
To resolve this memory leak, skip creating sysfs files if it fails
and continue with cache creation regardless (as suggested by Christoph).
This resolves the memory leak because both the cache and the kobject
remain alive on kobject_init_and_add() failure.
If SLUB tries to create an alias for a cache without sysfs files,
its symbolic link will not be generated.
Since a slab cache might not have associated sysfs files, call kobject_del()
only if such files exist.
Signed-off-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2024-11-01 22:08:44 +09:00
|
|
|
|
2012-11-28 16:23:07 +00:00
|
|
|
|
mm/slab: Allow cache creation to proceed even if sysfs registration fails
When kobject_init_and_add() fails during cache creation,
kobj->name can be leaked because SLUB does not call kobject_put(),
which should be invoked per the kobject API documentation.
This has a bit of historical context, though; SLUB does not call
kobject_put() to avoid double-free for struct kmem_cache because
1) simply calling it would free all resources related to the cache, and
2) struct kmem_cache descriptor is always freed by cache_cache()'s
error handling path, causing struct kmem_cache to be freed twice.
This issue can be reproduced by creating new slab caches while applying
failslab for kernfs_node_cache. This makes kobject_add_varg() succeed,
but causes kobject_add_internal() to fail in kobject_init_and_add()
during cache creation.
Historically, this issue has attracted developers' attention several times.
Each time a fix addressed either the leak or the double-free,
it caused the other issue. Let's summarize a bit of history here:
The leak has existed since the early days of SLUB.
Commit 54b6a731025f ("slub: fix leak of 'name' in sysfs_slab_add")
introduced a double-free bug while fixing the leak.
Commit 80da026a8e5d ("mm/slub: fix slab double-free in case of duplicate
sysfs filename") re-introduced the leak while fixing the double-free
error.
Commit dde3c6b72a16 ("mm/slub: fix a memory leak in sysfs_slab_add()")
fixed the memory leak, but it was later reverted by commit 757fed1d0898
("Revert "mm/slub: fix a memory leak in sysfs_slab_add()"") to avoid
the double-free error.
This is where we are now: we've chosen a memory leak over a double-free.
To resolve this memory leak, skip creating sysfs files if it fails
and continue with cache creation regardless (as suggested by Christoph).
This resolves the memory leak because both the cache and the kobject
remain alive on kobject_init_and_add() failure.
If SLUB tries to create an alias for a cache without sysfs files,
its symbolic link will not be generated.
Since a slab cache might not have associated sysfs files, call kobject_del()
only if such files exist.
Signed-off-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2024-11-01 22:08:44 +09:00
|
|
|
|
|
|
|
|
|
2024-09-05 09:56:50 +02:00
|
|
|
|
2012-09-05 12:07:44 +03:00
|
|
|
|
mm/slab: Allow cache creation to proceed even if sysfs registration fails
When kobject_init_and_add() fails during cache creation,
kobj->name can be leaked because SLUB does not call kobject_put(),
which should be invoked per the kobject API documentation.
This has a bit of historical context, though; SLUB does not call
kobject_put() to avoid double-free for struct kmem_cache because
1) simply calling it would free all resources related to the cache, and
2) struct kmem_cache descriptor is always freed by cache_cache()'s
error handling path, causing struct kmem_cache to be freed twice.
This issue can be reproduced by creating new slab caches while applying
failslab for kernfs_node_cache. This makes kobject_add_varg() succeed,
but causes kobject_add_internal() to fail in kobject_init_and_add()
during cache creation.
Historically, this issue has attracted developers' attention several times.
Each time a fix addressed either the leak or the double-free,
it caused the other issue. Let's summarize a bit of history here:
The leak has existed since the early days of SLUB.
Commit 54b6a731025f ("slub: fix leak of 'name' in sysfs_slab_add")
introduced a double-free bug while fixing the leak.
Commit 80da026a8e5d ("mm/slub: fix slab double-free in case of duplicate
sysfs filename") re-introduced the leak while fixing the double-free
error.
Commit dde3c6b72a16 ("mm/slub: fix a memory leak in sysfs_slab_add()")
fixed the memory leak, but it was later reverted by commit 757fed1d0898
("Revert "mm/slub: fix a memory leak in sysfs_slab_add()"") to avoid
the double-free error.
This is where we are now: we've chosen a memory leak over a double-free.
To resolve this memory leak, skip creating sysfs files if it fails
and continue with cache creation regardless (as suggested by Christoph).
This resolves the memory leak because both the cache and the kobject
remain alive on kobject_init_and_add() failure.
If SLUB tries to create an alias for a cache without sysfs files,
its symbolic link will not be generated.
Since a slab cache might not have associated sysfs files, call kobject_del()
only if such files exist.
Signed-off-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2024-11-01 22:08:44 +09:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-06-28 19:34:55 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-09-05 09:56:50 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
2022-11-14 18:18:39 +01:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2008-04-14 19:11:40 +03:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2008-04-14 19:11:40 +03:00
|
|
|
|
|
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2008-04-14 19:11:40 +03:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2008-04-14 19:11:40 +03:00
|
|
|
|
2010-10-05 13:57:26 -05:00
|
|
|
|
2008-04-14 19:11:40 +03:00
|
|
|
|
2010-10-05 13:57:26 -05:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2021-05-23 01:37:07 +02:00
|
|
|
|
2007-05-06 14:49:43 -07:00
|
|
|
|
|
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2007-05-06 14:49:43 -07:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2022-08-23 19:03:58 +02:00
|
|
|
|
2007-05-06 14:49:43 -07:00
|
|
|
|
|
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
|
|
|
|
|
2021-05-23 01:37:07 +02:00
|
|
|
|
2019-11-30 17:49:37 -08:00
|
|
|
|
2007-05-06 14:49:43 -07:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2019-11-30 17:49:37 -08:00
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:43 -07:00
|
|
|
|
|
|
|
|
|
2007-07-17 04:03:30 -07:00
|
|
|
|
2021-05-23 01:37:07 +02:00
|
|
|
|
2007-05-06 14:49:43 -07:00
|
|
|
|
|
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2007-05-06 14:49:43 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:43 -07:00
|
|
|
|
|
|
|
|
|
2021-06-28 19:34:33 -07:00
|
|
|
|
2014-06-04 16:06:34 -07:00
|
|
|
|
|
|
|
|
|
2021-06-28 19:34:33 -07:00
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:43 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:43 -07:00
|
|
|
|
|
|
|
|
|
2023-04-13 22:34:52 +08:00
|
|
|
|
2014-06-04 16:06:34 -07:00
|
|
|
|
2023-04-13 22:34:52 +08:00
|
|
|
|
2021-06-28 19:34:33 -07:00
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:43 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-06-28 19:34:33 -07:00
|
|
|
|
2007-05-06 14:49:43 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2014-08-06 16:04:09 -07:00
|
|
|
|
2021-05-23 01:37:07 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:43 -07:00
|
|
|
|
|
|
|
|
|
2014-08-06 16:04:09 -07:00
|
|
|
|
2021-05-23 01:37:07 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-01-30 22:11:57 -08:00
|
|
|
|
2007-05-06 14:49:43 -07:00
|
|
|
|
|
|
|
|
|
2021-06-28 19:34:33 -07:00
|
|
|
|
|
|
|
|
|
2021-06-28 19:34:55 -07:00
|
|
|
|
2007-05-06 14:49:45 -07:00
|
|
|
|
2007-05-09 02:32:39 -07:00
|
|
|
|
2007-05-06 14:49:45 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-05-21 14:11:25 +02:00
|
|
|
|
2007-05-06 14:49:45 -07:00
|
|
|
|
2008-08-19 20:43:25 +03:00
|
|
|
|
mm/slub: enable debugging memory wasting of kmalloc
kmalloc's API family is critical for mm, with one nature that it will
round up the request size to a fixed one (mostly power of 2). Say
when user requests memory for '2^n + 1' bytes, actually 2^(n+1) bytes
could be allocated, so in worst case, there is around 50% memory
space waste.
The wastage is not a big issue for requests that get allocated/freed
quickly, but may cause problems with objects that have longer life
time.
We've met a kernel boot OOM panic (v5.10), and from the dumped slab
info:
[ 26.062145] kmalloc-2k 814056KB 814056KB
From debug we found there are huge number of 'struct iova_magazine',
whose size is 1032 bytes (1024 + 8), so each allocation will waste
1016 bytes. Though the issue was solved by giving the right (bigger)
size of RAM, it is still nice to optimize the size (either use a
kmalloc friendly size or create a dedicated slab for it).
And from lkml archive, there was another crash kernel OOM case [1]
back in 2019, which seems to be related with the similar slab waste
situation, as the log is similar:
[ 4.332648] iommu: Adding device 0000:20:02.0 to group 16
[ 4.338946] swapper/0 invoked oom-killer: gfp_mask=0x6040c0(GFP_KERNEL|__GFP_COMP), nodemask=(null), order=0, oom_score_adj=0
...
[ 4.857565] kmalloc-2048 59164KB 59164KB
The crash kernel only has 256M memory, and 59M is pretty big here.
(Note: the related code has been changed and optimised in recent
kernel [2], these logs are just picked to demo the problem, also
a patch changing its size to 1024 bytes has been merged)
So add an way to track each kmalloc's memory waste info, and
leverage the existing SLUB debug framework (specifically
SLUB_STORE_USER) to show its call stack of original allocation,
so that user can evaluate the waste situation, identify some hot
spots and optimize accordingly, for a better utilization of memory.
The waste info is integrated into existing interface:
'/sys/kernel/debug/slab/kmalloc-xx/alloc_traces', one example of
'kmalloc-4k' after boot is:
126 ixgbe_alloc_q_vector+0xbe/0x830 [ixgbe] waste=233856/1856 age=280763/281414/282065 pid=1330 cpus=32 nodes=1
__kmem_cache_alloc_node+0x11f/0x4e0
__kmalloc_node+0x4e/0x140
ixgbe_alloc_q_vector+0xbe/0x830 [ixgbe]
ixgbe_init_interrupt_scheme+0x2ae/0xc90 [ixgbe]
ixgbe_probe+0x165f/0x1d20 [ixgbe]
local_pci_probe+0x78/0xc0
work_for_cpu_fn+0x26/0x40
...
which means in 'kmalloc-4k' slab, there are 126 requests of
2240 bytes which got a 4KB space (wasting 1856 bytes each
and 233856 bytes in total), from ixgbe_alloc_q_vector().
And when system starts some real workload like multiple docker
instances, there could are more severe waste.
[1]. https://lkml.org/lkml/2019/8/12/266
[2]. https://lore.kernel.org/lkml/2920df89-9975-5785-f79b-257d3052dfaf@huawei.com/
[Thanks Hyeonggon for pointing out several bugs about sorting/format]
[Thanks Vlastimil for suggesting way to reduce memory usage of
orig_size and keep it only for kmalloc objects]
Signed-off-by: Feng Tang <feng.tang@intel.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Robin Murphy <robin.murphy@arm.com>
Cc: John Garry <john.garry@huawei.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2022-09-13 14:54:20 +08:00
|
|
|
|
2007-05-09 02:32:45 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2009-01-01 10:12:29 +10:30
|
|
|
|
2007-05-09 02:32:45 -07:00
|
|
|
|
2007-05-06 14:49:45 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-12-10 14:47:02 -08:00
|
|
|
|
2007-05-06 14:49:45 -07:00
|
|
|
|
|
|
|
|
|
2021-06-28 19:34:55 -07:00
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:45 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-07-17 04:03:20 -07:00
|
|
|
|
2007-05-06 14:49:45 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-07-17 04:03:20 -07:00
|
|
|
|
2007-05-06 14:49:45 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
mm/slub: enable debugging memory wasting of kmalloc
kmalloc's API family is critical for mm, with one nature that it will
round up the request size to a fixed one (mostly power of 2). Say
when user requests memory for '2^n + 1' bytes, actually 2^(n+1) bytes
could be allocated, so in worst case, there is around 50% memory
space waste.
The wastage is not a big issue for requests that get allocated/freed
quickly, but may cause problems with objects that have longer life
time.
We've met a kernel boot OOM panic (v5.10), and from the dumped slab
info:
[ 26.062145] kmalloc-2k 814056KB 814056KB
From debug we found there are huge number of 'struct iova_magazine',
whose size is 1032 bytes (1024 + 8), so each allocation will waste
1016 bytes. Though the issue was solved by giving the right (bigger)
size of RAM, it is still nice to optimize the size (either use a
kmalloc friendly size or create a dedicated slab for it).
And from lkml archive, there was another crash kernel OOM case [1]
back in 2019, which seems to be related with the similar slab waste
situation, as the log is similar:
[ 4.332648] iommu: Adding device 0000:20:02.0 to group 16
[ 4.338946] swapper/0 invoked oom-killer: gfp_mask=0x6040c0(GFP_KERNEL|__GFP_COMP), nodemask=(null), order=0, oom_score_adj=0
...
[ 4.857565] kmalloc-2048 59164KB 59164KB
The crash kernel only has 256M memory, and 59M is pretty big here.
(Note: the related code has been changed and optimised in recent
kernel [2], these logs are just picked to demo the problem, also
a patch changing its size to 1024 bytes has been merged)
So add an way to track each kmalloc's memory waste info, and
leverage the existing SLUB debug framework (specifically
SLUB_STORE_USER) to show its call stack of original allocation,
so that user can evaluate the waste situation, identify some hot
spots and optimize accordingly, for a better utilization of memory.
The waste info is integrated into existing interface:
'/sys/kernel/debug/slab/kmalloc-xx/alloc_traces', one example of
'kmalloc-4k' after boot is:
126 ixgbe_alloc_q_vector+0xbe/0x830 [ixgbe] waste=233856/1856 age=280763/281414/282065 pid=1330 cpus=32 nodes=1
__kmem_cache_alloc_node+0x11f/0x4e0
__kmalloc_node+0x4e/0x140
ixgbe_alloc_q_vector+0xbe/0x830 [ixgbe]
ixgbe_init_interrupt_scheme+0x2ae/0xc90 [ixgbe]
ixgbe_probe+0x165f/0x1d20 [ixgbe]
local_pci_probe+0x78/0xc0
work_for_cpu_fn+0x26/0x40
...
which means in 'kmalloc-4k' slab, there are 126 requests of
2240 bytes which got a 4KB space (wasting 1856 bytes each
and 233856 bytes in total), from ixgbe_alloc_q_vector().
And when system starts some real workload like multiple docker
instances, there could are more severe waste.
[1]. https://lkml.org/lkml/2019/8/12/266
[2]. https://lore.kernel.org/lkml/2920df89-9975-5785-f79b-257d3052dfaf@huawei.com/
[Thanks Hyeonggon for pointing out several bugs about sorting/format]
[Thanks Vlastimil for suggesting way to reduce memory usage of
orig_size and keep it only for kmalloc objects]
Signed-off-by: Feng Tang <feng.tang@intel.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Robin Murphy <robin.murphy@arm.com>
Cc: John Garry <john.garry@huawei.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2022-09-13 14:54:20 +08:00
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:45 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
mm/slub: enable debugging memory wasting of kmalloc
kmalloc's API family is critical for mm, with one nature that it will
round up the request size to a fixed one (mostly power of 2). Say
when user requests memory for '2^n + 1' bytes, actually 2^(n+1) bytes
could be allocated, so in worst case, there is around 50% memory
space waste.
The wastage is not a big issue for requests that get allocated/freed
quickly, but may cause problems with objects that have longer life
time.
We've met a kernel boot OOM panic (v5.10), and from the dumped slab
info:
[ 26.062145] kmalloc-2k 814056KB 814056KB
From debug we found there are huge number of 'struct iova_magazine',
whose size is 1032 bytes (1024 + 8), so each allocation will waste
1016 bytes. Though the issue was solved by giving the right (bigger)
size of RAM, it is still nice to optimize the size (either use a
kmalloc friendly size or create a dedicated slab for it).
And from lkml archive, there was another crash kernel OOM case [1]
back in 2019, which seems to be related with the similar slab waste
situation, as the log is similar:
[ 4.332648] iommu: Adding device 0000:20:02.0 to group 16
[ 4.338946] swapper/0 invoked oom-killer: gfp_mask=0x6040c0(GFP_KERNEL|__GFP_COMP), nodemask=(null), order=0, oom_score_adj=0
...
[ 4.857565] kmalloc-2048 59164KB 59164KB
The crash kernel only has 256M memory, and 59M is pretty big here.
(Note: the related code has been changed and optimised in recent
kernel [2], these logs are just picked to demo the problem, also
a patch changing its size to 1024 bytes has been merged)
So add an way to track each kmalloc's memory waste info, and
leverage the existing SLUB debug framework (specifically
SLUB_STORE_USER) to show its call stack of original allocation,
so that user can evaluate the waste situation, identify some hot
spots and optimize accordingly, for a better utilization of memory.
The waste info is integrated into existing interface:
'/sys/kernel/debug/slab/kmalloc-xx/alloc_traces', one example of
'kmalloc-4k' after boot is:
126 ixgbe_alloc_q_vector+0xbe/0x830 [ixgbe] waste=233856/1856 age=280763/281414/282065 pid=1330 cpus=32 nodes=1
__kmem_cache_alloc_node+0x11f/0x4e0
__kmalloc_node+0x4e/0x140
ixgbe_alloc_q_vector+0xbe/0x830 [ixgbe]
ixgbe_init_interrupt_scheme+0x2ae/0xc90 [ixgbe]
ixgbe_probe+0x165f/0x1d20 [ixgbe]
local_pci_probe+0x78/0xc0
work_for_cpu_fn+0x26/0x40
...
which means in 'kmalloc-4k' slab, there are 126 requests of
2240 bytes which got a 4KB space (wasting 1856 bytes each
and 233856 bytes in total), from ixgbe_alloc_q_vector().
And when system starts some real workload like multiple docker
instances, there could are more severe waste.
[1]. https://lkml.org/lkml/2019/8/12/266
[2]. https://lore.kernel.org/lkml/2920df89-9975-5785-f79b-257d3052dfaf@huawei.com/
[Thanks Hyeonggon for pointing out several bugs about sorting/format]
[Thanks Vlastimil for suggesting way to reduce memory usage of
orig_size and keep it only for kmalloc objects]
Signed-off-by: Feng Tang <feng.tang@intel.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Robin Murphy <robin.murphy@arm.com>
Cc: John Garry <john.garry@huawei.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2022-09-13 14:54:20 +08:00
|
|
|
|
2007-05-09 02:32:45 -07:00
|
|
|
|
2021-05-21 14:11:25 +02:00
|
|
|
|
mm/slub: enable debugging memory wasting of kmalloc
kmalloc's API family is critical for mm, with one nature that it will
round up the request size to a fixed one (mostly power of 2). Say
when user requests memory for '2^n + 1' bytes, actually 2^(n+1) bytes
could be allocated, so in worst case, there is around 50% memory
space waste.
The wastage is not a big issue for requests that get allocated/freed
quickly, but may cause problems with objects that have longer life
time.
We've met a kernel boot OOM panic (v5.10), and from the dumped slab
info:
[ 26.062145] kmalloc-2k 814056KB 814056KB
From debug we found there are huge number of 'struct iova_magazine',
whose size is 1032 bytes (1024 + 8), so each allocation will waste
1016 bytes. Though the issue was solved by giving the right (bigger)
size of RAM, it is still nice to optimize the size (either use a
kmalloc friendly size or create a dedicated slab for it).
And from lkml archive, there was another crash kernel OOM case [1]
back in 2019, which seems to be related with the similar slab waste
situation, as the log is similar:
[ 4.332648] iommu: Adding device 0000:20:02.0 to group 16
[ 4.338946] swapper/0 invoked oom-killer: gfp_mask=0x6040c0(GFP_KERNEL|__GFP_COMP), nodemask=(null), order=0, oom_score_adj=0
...
[ 4.857565] kmalloc-2048 59164KB 59164KB
The crash kernel only has 256M memory, and 59M is pretty big here.
(Note: the related code has been changed and optimised in recent
kernel [2], these logs are just picked to demo the problem, also
a patch changing its size to 1024 bytes has been merged)
So add an way to track each kmalloc's memory waste info, and
leverage the existing SLUB debug framework (specifically
SLUB_STORE_USER) to show its call stack of original allocation,
so that user can evaluate the waste situation, identify some hot
spots and optimize accordingly, for a better utilization of memory.
The waste info is integrated into existing interface:
'/sys/kernel/debug/slab/kmalloc-xx/alloc_traces', one example of
'kmalloc-4k' after boot is:
126 ixgbe_alloc_q_vector+0xbe/0x830 [ixgbe] waste=233856/1856 age=280763/281414/282065 pid=1330 cpus=32 nodes=1
__kmem_cache_alloc_node+0x11f/0x4e0
__kmalloc_node+0x4e/0x140
ixgbe_alloc_q_vector+0xbe/0x830 [ixgbe]
ixgbe_init_interrupt_scheme+0x2ae/0xc90 [ixgbe]
ixgbe_probe+0x165f/0x1d20 [ixgbe]
local_pci_probe+0x78/0xc0
work_for_cpu_fn+0x26/0x40
...
which means in 'kmalloc-4k' slab, there are 126 requests of
2240 bytes which got a 4KB space (wasting 1856 bytes each
and 233856 bytes in total), from ixgbe_alloc_q_vector().
And when system starts some real workload like multiple docker
instances, there could are more severe waste.
[1]. https://lkml.org/lkml/2019/8/12/266
[2]. https://lore.kernel.org/lkml/2920df89-9975-5785-f79b-257d3052dfaf@huawei.com/
[Thanks Hyeonggon for pointing out several bugs about sorting/format]
[Thanks Vlastimil for suggesting way to reduce memory usage of
orig_size and keep it only for kmalloc objects]
Signed-off-by: Feng Tang <feng.tang@intel.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Robin Murphy <robin.murphy@arm.com>
Cc: John Garry <john.garry@huawei.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2022-09-13 14:54:20 +08:00
|
|
|
|
2007-05-06 14:49:45 -07:00
|
|
|
|
2021-05-21 14:11:25 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:45 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
mm/slub: enable debugging memory wasting of kmalloc
kmalloc's API family is critical for mm, with one nature that it will
round up the request size to a fixed one (mostly power of 2). Say
when user requests memory for '2^n + 1' bytes, actually 2^(n+1) bytes
could be allocated, so in worst case, there is around 50% memory
space waste.
The wastage is not a big issue for requests that get allocated/freed
quickly, but may cause problems with objects that have longer life
time.
We've met a kernel boot OOM panic (v5.10), and from the dumped slab
info:
[ 26.062145] kmalloc-2k 814056KB 814056KB
From debug we found there are huge number of 'struct iova_magazine',
whose size is 1032 bytes (1024 + 8), so each allocation will waste
1016 bytes. Though the issue was solved by giving the right (bigger)
size of RAM, it is still nice to optimize the size (either use a
kmalloc friendly size or create a dedicated slab for it).
And from lkml archive, there was another crash kernel OOM case [1]
back in 2019, which seems to be related with the similar slab waste
situation, as the log is similar:
[ 4.332648] iommu: Adding device 0000:20:02.0 to group 16
[ 4.338946] swapper/0 invoked oom-killer: gfp_mask=0x6040c0(GFP_KERNEL|__GFP_COMP), nodemask=(null), order=0, oom_score_adj=0
...
[ 4.857565] kmalloc-2048 59164KB 59164KB
The crash kernel only has 256M memory, and 59M is pretty big here.
(Note: the related code has been changed and optimised in recent
kernel [2], these logs are just picked to demo the problem, also
a patch changing its size to 1024 bytes has been merged)
So add an way to track each kmalloc's memory waste info, and
leverage the existing SLUB debug framework (specifically
SLUB_STORE_USER) to show its call stack of original allocation,
so that user can evaluate the waste situation, identify some hot
spots and optimize accordingly, for a better utilization of memory.
The waste info is integrated into existing interface:
'/sys/kernel/debug/slab/kmalloc-xx/alloc_traces', one example of
'kmalloc-4k' after boot is:
126 ixgbe_alloc_q_vector+0xbe/0x830 [ixgbe] waste=233856/1856 age=280763/281414/282065 pid=1330 cpus=32 nodes=1
__kmem_cache_alloc_node+0x11f/0x4e0
__kmalloc_node+0x4e/0x140
ixgbe_alloc_q_vector+0xbe/0x830 [ixgbe]
ixgbe_init_interrupt_scheme+0x2ae/0xc90 [ixgbe]
ixgbe_probe+0x165f/0x1d20 [ixgbe]
local_pci_probe+0x78/0xc0
work_for_cpu_fn+0x26/0x40
...
which means in 'kmalloc-4k' slab, there are 126 requests of
2240 bytes which got a 4KB space (wasting 1856 bytes each
and 233856 bytes in total), from ixgbe_alloc_q_vector().
And when system starts some real workload like multiple docker
instances, there could are more severe waste.
[1]. https://lkml.org/lkml/2019/8/12/266
[2]. https://lore.kernel.org/lkml/2920df89-9975-5785-f79b-257d3052dfaf@huawei.com/
[Thanks Hyeonggon for pointing out several bugs about sorting/format]
[Thanks Vlastimil for suggesting way to reduce memory usage of
orig_size and keep it only for kmalloc objects]
Signed-off-by: Feng Tang <feng.tang@intel.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Robin Murphy <robin.murphy@arm.com>
Cc: John Garry <john.garry@huawei.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2022-09-13 14:54:20 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-09 02:32:45 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2009-01-01 10:12:29 +10:30
|
|
|
|
|
|
|
|
|
2007-05-09 02:32:45 -07:00
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:45 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-09 02:32:45 -07:00
|
|
|
|
2007-05-06 14:49:45 -07:00
|
|
|
|
2021-05-21 14:11:25 +02:00
|
|
|
|
|
|
|
|
|
mm/slub: enable debugging memory wasting of kmalloc
kmalloc's API family is critical for mm, with one nature that it will
round up the request size to a fixed one (mostly power of 2). Say
when user requests memory for '2^n + 1' bytes, actually 2^(n+1) bytes
could be allocated, so in worst case, there is around 50% memory
space waste.
The wastage is not a big issue for requests that get allocated/freed
quickly, but may cause problems with objects that have longer life
time.
We've met a kernel boot OOM panic (v5.10), and from the dumped slab
info:
[ 26.062145] kmalloc-2k 814056KB 814056KB
From debug we found there are huge number of 'struct iova_magazine',
whose size is 1032 bytes (1024 + 8), so each allocation will waste
1016 bytes. Though the issue was solved by giving the right (bigger)
size of RAM, it is still nice to optimize the size (either use a
kmalloc friendly size or create a dedicated slab for it).
And from lkml archive, there was another crash kernel OOM case [1]
back in 2019, which seems to be related with the similar slab waste
situation, as the log is similar:
[ 4.332648] iommu: Adding device 0000:20:02.0 to group 16
[ 4.338946] swapper/0 invoked oom-killer: gfp_mask=0x6040c0(GFP_KERNEL|__GFP_COMP), nodemask=(null), order=0, oom_score_adj=0
...
[ 4.857565] kmalloc-2048 59164KB 59164KB
The crash kernel only has 256M memory, and 59M is pretty big here.
(Note: the related code has been changed and optimised in recent
kernel [2], these logs are just picked to demo the problem, also
a patch changing its size to 1024 bytes has been merged)
So add an way to track each kmalloc's memory waste info, and
leverage the existing SLUB debug framework (specifically
SLUB_STORE_USER) to show its call stack of original allocation,
so that user can evaluate the waste situation, identify some hot
spots and optimize accordingly, for a better utilization of memory.
The waste info is integrated into existing interface:
'/sys/kernel/debug/slab/kmalloc-xx/alloc_traces', one example of
'kmalloc-4k' after boot is:
126 ixgbe_alloc_q_vector+0xbe/0x830 [ixgbe] waste=233856/1856 age=280763/281414/282065 pid=1330 cpus=32 nodes=1
__kmem_cache_alloc_node+0x11f/0x4e0
__kmalloc_node+0x4e/0x140
ixgbe_alloc_q_vector+0xbe/0x830 [ixgbe]
ixgbe_init_interrupt_scheme+0x2ae/0xc90 [ixgbe]
ixgbe_probe+0x165f/0x1d20 [ixgbe]
local_pci_probe+0x78/0xc0
work_for_cpu_fn+0x26/0x40
...
which means in 'kmalloc-4k' slab, there are 126 requests of
2240 bytes which got a 4KB space (wasting 1856 bytes each
and 233856 bytes in total), from ixgbe_alloc_q_vector().
And when system starts some real workload like multiple docker
instances, there could are more severe waste.
[1]. https://lkml.org/lkml/2019/8/12/266
[2]. https://lore.kernel.org/lkml/2920df89-9975-5785-f79b-257d3052dfaf@huawei.com/
[Thanks Hyeonggon for pointing out several bugs about sorting/format]
[Thanks Vlastimil for suggesting way to reduce memory usage of
orig_size and keep it only for kmalloc objects]
Signed-off-by: Feng Tang <feng.tang@intel.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Robin Murphy <robin.murphy@arm.com>
Cc: John Garry <john.garry@huawei.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2022-09-13 14:54:20 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:45 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-09 02:32:39 -07:00
|
|
|
|
2007-05-06 14:49:45 -07:00
|
|
|
|
2007-07-17 04:03:20 -07:00
|
|
|
|
2007-05-06 14:49:45 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-09 02:32:45 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-05-21 14:11:25 +02:00
|
|
|
|
mm/slub: enable debugging memory wasting of kmalloc
kmalloc's API family is critical for mm, with one nature that it will
round up the request size to a fixed one (mostly power of 2). Say
when user requests memory for '2^n + 1' bytes, actually 2^(n+1) bytes
could be allocated, so in worst case, there is around 50% memory
space waste.
The wastage is not a big issue for requests that get allocated/freed
quickly, but may cause problems with objects that have longer life
time.
We've met a kernel boot OOM panic (v5.10), and from the dumped slab
info:
[ 26.062145] kmalloc-2k 814056KB 814056KB
From debug we found there are huge number of 'struct iova_magazine',
whose size is 1032 bytes (1024 + 8), so each allocation will waste
1016 bytes. Though the issue was solved by giving the right (bigger)
size of RAM, it is still nice to optimize the size (either use a
kmalloc friendly size or create a dedicated slab for it).
And from lkml archive, there was another crash kernel OOM case [1]
back in 2019, which seems to be related with the similar slab waste
situation, as the log is similar:
[ 4.332648] iommu: Adding device 0000:20:02.0 to group 16
[ 4.338946] swapper/0 invoked oom-killer: gfp_mask=0x6040c0(GFP_KERNEL|__GFP_COMP), nodemask=(null), order=0, oom_score_adj=0
...
[ 4.857565] kmalloc-2048 59164KB 59164KB
The crash kernel only has 256M memory, and 59M is pretty big here.
(Note: the related code has been changed and optimised in recent
kernel [2], these logs are just picked to demo the problem, also
a patch changing its size to 1024 bytes has been merged)
So add an way to track each kmalloc's memory waste info, and
leverage the existing SLUB debug framework (specifically
SLUB_STORE_USER) to show its call stack of original allocation,
so that user can evaluate the waste situation, identify some hot
spots and optimize accordingly, for a better utilization of memory.
The waste info is integrated into existing interface:
'/sys/kernel/debug/slab/kmalloc-xx/alloc_traces', one example of
'kmalloc-4k' after boot is:
126 ixgbe_alloc_q_vector+0xbe/0x830 [ixgbe] waste=233856/1856 age=280763/281414/282065 pid=1330 cpus=32 nodes=1
__kmem_cache_alloc_node+0x11f/0x4e0
__kmalloc_node+0x4e/0x140
ixgbe_alloc_q_vector+0xbe/0x830 [ixgbe]
ixgbe_init_interrupt_scheme+0x2ae/0xc90 [ixgbe]
ixgbe_probe+0x165f/0x1d20 [ixgbe]
local_pci_probe+0x78/0xc0
work_for_cpu_fn+0x26/0x40
...
which means in 'kmalloc-4k' slab, there are 126 requests of
2240 bytes which got a 4KB space (wasting 1856 bytes each
and 233856 bytes in total), from ixgbe_alloc_q_vector().
And when system starts some real workload like multiple docker
instances, there could are more severe waste.
[1]. https://lkml.org/lkml/2019/8/12/266
[2]. https://lore.kernel.org/lkml/2920df89-9975-5785-f79b-257d3052dfaf@huawei.com/
[Thanks Hyeonggon for pointing out several bugs about sorting/format]
[Thanks Vlastimil for suggesting way to reduce memory usage of
orig_size and keep it only for kmalloc objects]
Signed-off-by: Feng Tang <feng.tang@intel.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Robin Murphy <robin.murphy@arm.com>
Cc: John Garry <john.garry@huawei.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2022-09-13 14:54:20 +08:00
|
|
|
|
2009-01-01 10:12:29 +10:30
|
|
|
|
|
|
|
|
|
2007-05-09 02:32:45 -07:00
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:45 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2021-05-23 01:28:37 +02:00
|
|
|
|
2007-05-06 14:49:45 -07:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
mm/slub: enable debugging memory wasting of kmalloc
kmalloc's API family is critical for mm, with one nature that it will
round up the request size to a fixed one (mostly power of 2). Say
when user requests memory for '2^n + 1' bytes, actually 2^(n+1) bytes
could be allocated, so in worst case, there is around 50% memory
space waste.
The wastage is not a big issue for requests that get allocated/freed
quickly, but may cause problems with objects that have longer life
time.
We've met a kernel boot OOM panic (v5.10), and from the dumped slab
info:
[ 26.062145] kmalloc-2k 814056KB 814056KB
From debug we found there are huge number of 'struct iova_magazine',
whose size is 1032 bytes (1024 + 8), so each allocation will waste
1016 bytes. Though the issue was solved by giving the right (bigger)
size of RAM, it is still nice to optimize the size (either use a
kmalloc friendly size or create a dedicated slab for it).
And from lkml archive, there was another crash kernel OOM case [1]
back in 2019, which seems to be related with the similar slab waste
situation, as the log is similar:
[ 4.332648] iommu: Adding device 0000:20:02.0 to group 16
[ 4.338946] swapper/0 invoked oom-killer: gfp_mask=0x6040c0(GFP_KERNEL|__GFP_COMP), nodemask=(null), order=0, oom_score_adj=0
...
[ 4.857565] kmalloc-2048 59164KB 59164KB
The crash kernel only has 256M memory, and 59M is pretty big here.
(Note: the related code has been changed and optimised in recent
kernel [2], these logs are just picked to demo the problem, also
a patch changing its size to 1024 bytes has been merged)
So add an way to track each kmalloc's memory waste info, and
leverage the existing SLUB debug framework (specifically
SLUB_STORE_USER) to show its call stack of original allocation,
so that user can evaluate the waste situation, identify some hot
spots and optimize accordingly, for a better utilization of memory.
The waste info is integrated into existing interface:
'/sys/kernel/debug/slab/kmalloc-xx/alloc_traces', one example of
'kmalloc-4k' after boot is:
126 ixgbe_alloc_q_vector+0xbe/0x830 [ixgbe] waste=233856/1856 age=280763/281414/282065 pid=1330 cpus=32 nodes=1
__kmem_cache_alloc_node+0x11f/0x4e0
__kmalloc_node+0x4e/0x140
ixgbe_alloc_q_vector+0xbe/0x830 [ixgbe]
ixgbe_init_interrupt_scheme+0x2ae/0xc90 [ixgbe]
ixgbe_probe+0x165f/0x1d20 [ixgbe]
local_pci_probe+0x78/0xc0
work_for_cpu_fn+0x26/0x40
...
which means in 'kmalloc-4k' slab, there are 126 requests of
2240 bytes which got a 4KB space (wasting 1856 bytes each
and 233856 bytes in total), from ixgbe_alloc_q_vector().
And when system starts some real workload like multiple docker
instances, there could are more severe waste.
[1]. https://lkml.org/lkml/2019/8/12/266
[2]. https://lore.kernel.org/lkml/2920df89-9975-5785-f79b-257d3052dfaf@huawei.com/
[Thanks Hyeonggon for pointing out several bugs about sorting/format]
[Thanks Vlastimil for suggesting way to reduce memory usage of
orig_size and keep it only for kmalloc objects]
Signed-off-by: Feng Tang <feng.tang@intel.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Robin Murphy <robin.murphy@arm.com>
Cc: John Garry <john.garry@huawei.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2022-09-13 14:54:20 +08:00
|
|
|
|
2007-05-06 14:49:45 -07:00
|
|
|
|
|
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2021-05-23 01:28:37 +02:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2021-05-23 01:28:37 +02:00
|
|
|
|
mm/slub: enable debugging memory wasting of kmalloc
kmalloc's API family is critical for mm, with one nature that it will
round up the request size to a fixed one (mostly power of 2). Say
when user requests memory for '2^n + 1' bytes, actually 2^(n+1) bytes
could be allocated, so in worst case, there is around 50% memory
space waste.
The wastage is not a big issue for requests that get allocated/freed
quickly, but may cause problems with objects that have longer life
time.
We've met a kernel boot OOM panic (v5.10), and from the dumped slab
info:
[ 26.062145] kmalloc-2k 814056KB 814056KB
From debug we found there are huge number of 'struct iova_magazine',
whose size is 1032 bytes (1024 + 8), so each allocation will waste
1016 bytes. Though the issue was solved by giving the right (bigger)
size of RAM, it is still nice to optimize the size (either use a
kmalloc friendly size or create a dedicated slab for it).
And from lkml archive, there was another crash kernel OOM case [1]
back in 2019, which seems to be related with the similar slab waste
situation, as the log is similar:
[ 4.332648] iommu: Adding device 0000:20:02.0 to group 16
[ 4.338946] swapper/0 invoked oom-killer: gfp_mask=0x6040c0(GFP_KERNEL|__GFP_COMP), nodemask=(null), order=0, oom_score_adj=0
...
[ 4.857565] kmalloc-2048 59164KB 59164KB
The crash kernel only has 256M memory, and 59M is pretty big here.
(Note: the related code has been changed and optimised in recent
kernel [2], these logs are just picked to demo the problem, also
a patch changing its size to 1024 bytes has been merged)
So add an way to track each kmalloc's memory waste info, and
leverage the existing SLUB debug framework (specifically
SLUB_STORE_USER) to show its call stack of original allocation,
so that user can evaluate the waste situation, identify some hot
spots and optimize accordingly, for a better utilization of memory.
The waste info is integrated into existing interface:
'/sys/kernel/debug/slab/kmalloc-xx/alloc_traces', one example of
'kmalloc-4k' after boot is:
126 ixgbe_alloc_q_vector+0xbe/0x830 [ixgbe] waste=233856/1856 age=280763/281414/282065 pid=1330 cpus=32 nodes=1
__kmem_cache_alloc_node+0x11f/0x4e0
__kmalloc_node+0x4e/0x140
ixgbe_alloc_q_vector+0xbe/0x830 [ixgbe]
ixgbe_init_interrupt_scheme+0x2ae/0xc90 [ixgbe]
ixgbe_probe+0x165f/0x1d20 [ixgbe]
local_pci_probe+0x78/0xc0
work_for_cpu_fn+0x26/0x40
...
which means in 'kmalloc-4k' slab, there are 126 requests of
2240 bytes which got a 4KB space (wasting 1856 bytes each
and 233856 bytes in total), from ixgbe_alloc_q_vector().
And when system starts some real workload like multiple docker
instances, there could are more severe waste.
[1]. https://lkml.org/lkml/2019/8/12/266
[2]. https://lore.kernel.org/lkml/2920df89-9975-5785-f79b-257d3052dfaf@huawei.com/
[Thanks Hyeonggon for pointing out several bugs about sorting/format]
[Thanks Vlastimil for suggesting way to reduce memory usage of
orig_size and keep it only for kmalloc objects]
Signed-off-by: Feng Tang <feng.tang@intel.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Robin Murphy <robin.murphy@arm.com>
Cc: John Garry <john.garry@huawei.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2022-09-13 14:54:20 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:45 -07:00
|
|
|
|
2021-06-28 19:34:55 -07:00
|
|
|
|
2019-05-13 17:16:09 -07:00
|
|
|
|
2007-05-06 14:49:45 -07:00
|
|
|
|
2022-11-14 18:18:39 +01:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2008-04-14 19:11:40 +03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
2008-04-14 19:11:40 +03:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-04-14 19:11:40 +03:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2008-03-02 23:28:24 +03:00
|
|
|
|
2020-12-14 19:14:57 -08:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-12-14 19:14:57 -08:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
treewide: kzalloc() -> kcalloc()
The kzalloc() function has a 2-factor argument form, kcalloc(). This
patch replaces cases of:
kzalloc(a * b, gfp)
with:
kcalloc(a * b, gfp)
as well as handling cases of:
kzalloc(a * b * c, gfp)
with:
kzalloc(array3_size(a, b, c), gfp)
as it's slightly less ugly than:
kzalloc_array(array_size(a, b), c, gfp)
This does, however, attempt to ignore constant size factors like:
kzalloc(4 * 1024, gfp)
though any constants defined via macros get caught up in the conversion.
Any factors with a sizeof() of "unsigned char", "char", and "u8" were
dropped, since they're redundant.
The Coccinelle script used for this was:
// Fix redundant parens around sizeof().
@@
type TYPE;
expression THING, E;
@@
(
kzalloc(
- (sizeof(TYPE)) * E
+ sizeof(TYPE) * E
, ...)
|
kzalloc(
- (sizeof(THING)) * E
+ sizeof(THING) * E
, ...)
)
// Drop single-byte sizes and redundant parens.
@@
expression COUNT;
typedef u8;
typedef __u8;
@@
(
kzalloc(
- sizeof(u8) * (COUNT)
+ COUNT
, ...)
|
kzalloc(
- sizeof(__u8) * (COUNT)
+ COUNT
, ...)
|
kzalloc(
- sizeof(char) * (COUNT)
+ COUNT
, ...)
|
kzalloc(
- sizeof(unsigned char) * (COUNT)
+ COUNT
, ...)
|
kzalloc(
- sizeof(u8) * COUNT
+ COUNT
, ...)
|
kzalloc(
- sizeof(__u8) * COUNT
+ COUNT
, ...)
|
kzalloc(
- sizeof(char) * COUNT
+ COUNT
, ...)
|
kzalloc(
- sizeof(unsigned char) * COUNT
+ COUNT
, ...)
)
// 2-factor product with sizeof(type/expression) and identifier or constant.
@@
type TYPE;
expression THING;
identifier COUNT_ID;
constant COUNT_CONST;
@@
(
- kzalloc
+ kcalloc
(
- sizeof(TYPE) * (COUNT_ID)
+ COUNT_ID, sizeof(TYPE)
, ...)
|
- kzalloc
+ kcalloc
(
- sizeof(TYPE) * COUNT_ID
+ COUNT_ID, sizeof(TYPE)
, ...)
|
- kzalloc
+ kcalloc
(
- sizeof(TYPE) * (COUNT_CONST)
+ COUNT_CONST, sizeof(TYPE)
, ...)
|
- kzalloc
+ kcalloc
(
- sizeof(TYPE) * COUNT_CONST
+ COUNT_CONST, sizeof(TYPE)
, ...)
|
- kzalloc
+ kcalloc
(
- sizeof(THING) * (COUNT_ID)
+ COUNT_ID, sizeof(THING)
, ...)
|
- kzalloc
+ kcalloc
(
- sizeof(THING) * COUNT_ID
+ COUNT_ID, sizeof(THING)
, ...)
|
- kzalloc
+ kcalloc
(
- sizeof(THING) * (COUNT_CONST)
+ COUNT_CONST, sizeof(THING)
, ...)
|
- kzalloc
+ kcalloc
(
- sizeof(THING) * COUNT_CONST
+ COUNT_CONST, sizeof(THING)
, ...)
)
// 2-factor product, only identifiers.
@@
identifier SIZE, COUNT;
@@
- kzalloc
+ kcalloc
(
- SIZE * COUNT
+ COUNT, SIZE
, ...)
// 3-factor product with 1 sizeof(type) or sizeof(expression), with
// redundant parens removed.
@@
expression THING;
identifier STRIDE, COUNT;
type TYPE;
@@
(
kzalloc(
- sizeof(TYPE) * (COUNT) * (STRIDE)
+ array3_size(COUNT, STRIDE, sizeof(TYPE))
, ...)
|
kzalloc(
- sizeof(TYPE) * (COUNT) * STRIDE
+ array3_size(COUNT, STRIDE, sizeof(TYPE))
, ...)
|
kzalloc(
- sizeof(TYPE) * COUNT * (STRIDE)
+ array3_size(COUNT, STRIDE, sizeof(TYPE))
, ...)
|
kzalloc(
- sizeof(TYPE) * COUNT * STRIDE
+ array3_size(COUNT, STRIDE, sizeof(TYPE))
, ...)
|
kzalloc(
- sizeof(THING) * (COUNT) * (STRIDE)
+ array3_size(COUNT, STRIDE, sizeof(THING))
, ...)
|
kzalloc(
- sizeof(THING) * (COUNT) * STRIDE
+ array3_size(COUNT, STRIDE, sizeof(THING))
, ...)
|
kzalloc(
- sizeof(THING) * COUNT * (STRIDE)
+ array3_size(COUNT, STRIDE, sizeof(THING))
, ...)
|
kzalloc(
- sizeof(THING) * COUNT * STRIDE
+ array3_size(COUNT, STRIDE, sizeof(THING))
, ...)
)
// 3-factor product with 2 sizeof(variable), with redundant parens removed.
@@
expression THING1, THING2;
identifier COUNT;
type TYPE1, TYPE2;
@@
(
kzalloc(
- sizeof(TYPE1) * sizeof(TYPE2) * COUNT
+ array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2))
, ...)
|
kzalloc(
- sizeof(TYPE1) * sizeof(THING2) * (COUNT)
+ array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2))
, ...)
|
kzalloc(
- sizeof(THING1) * sizeof(THING2) * COUNT
+ array3_size(COUNT, sizeof(THING1), sizeof(THING2))
, ...)
|
kzalloc(
- sizeof(THING1) * sizeof(THING2) * (COUNT)
+ array3_size(COUNT, sizeof(THING1), sizeof(THING2))
, ...)
|
kzalloc(
- sizeof(TYPE1) * sizeof(THING2) * COUNT
+ array3_size(COUNT, sizeof(TYPE1), sizeof(THING2))
, ...)
|
kzalloc(
- sizeof(TYPE1) * sizeof(THING2) * (COUNT)
+ array3_size(COUNT, sizeof(TYPE1), sizeof(THING2))
, ...)
)
// 3-factor product, only identifiers, with redundant parens removed.
@@
identifier STRIDE, SIZE, COUNT;
@@
(
kzalloc(
- (COUNT) * STRIDE * SIZE
+ array3_size(COUNT, STRIDE, SIZE)
, ...)
|
kzalloc(
- COUNT * (STRIDE) * SIZE
+ array3_size(COUNT, STRIDE, SIZE)
, ...)
|
kzalloc(
- COUNT * STRIDE * (SIZE)
+ array3_size(COUNT, STRIDE, SIZE)
, ...)
|
kzalloc(
- (COUNT) * (STRIDE) * SIZE
+ array3_size(COUNT, STRIDE, SIZE)
, ...)
|
kzalloc(
- COUNT * (STRIDE) * (SIZE)
+ array3_size(COUNT, STRIDE, SIZE)
, ...)
|
kzalloc(
- (COUNT) * STRIDE * (SIZE)
+ array3_size(COUNT, STRIDE, SIZE)
, ...)
|
kzalloc(
- (COUNT) * (STRIDE) * (SIZE)
+ array3_size(COUNT, STRIDE, SIZE)
, ...)
|
kzalloc(
- COUNT * STRIDE * SIZE
+ array3_size(COUNT, STRIDE, SIZE)
, ...)
)
// Any remaining multi-factor products, first at least 3-factor products,
// when they're not all constants...
@@
expression E1, E2, E3;
constant C1, C2, C3;
@@
(
kzalloc(C1 * C2 * C3, ...)
|
kzalloc(
- (E1) * E2 * E3
+ array3_size(E1, E2, E3)
, ...)
|
kzalloc(
- (E1) * (E2) * E3
+ array3_size(E1, E2, E3)
, ...)
|
kzalloc(
- (E1) * (E2) * (E3)
+ array3_size(E1, E2, E3)
, ...)
|
kzalloc(
- E1 * E2 * E3
+ array3_size(E1, E2, E3)
, ...)
)
// And then all remaining 2 factors products when they're not all constants,
// keeping sizeof() as the second factor argument.
@@
expression THING, E1, E2;
type TYPE;
constant C1, C2, C3;
@@
(
kzalloc(sizeof(THING) * C2, ...)
|
kzalloc(sizeof(TYPE) * C2, ...)
|
kzalloc(C1 * C2 * C3, ...)
|
kzalloc(C1 * C2, ...)
|
- kzalloc
+ kcalloc
(
- sizeof(TYPE) * (E2)
+ E2, sizeof(TYPE)
, ...)
|
- kzalloc
+ kcalloc
(
- sizeof(TYPE) * E2
+ E2, sizeof(TYPE)
, ...)
|
- kzalloc
+ kcalloc
(
- sizeof(THING) * (E2)
+ E2, sizeof(THING)
, ...)
|
- kzalloc
+ kcalloc
(
- sizeof(THING) * E2
+ E2, sizeof(THING)
, ...)
|
- kzalloc
+ kcalloc
(
- (E1) * E2
+ E1, E2
, ...)
|
- kzalloc
+ kcalloc
(
- (E1) * (E2)
+ E1, E2
, ...)
|
- kzalloc
+ kcalloc
(
- E1 * E2
+ E1, E2
, ...)
)
Signed-off-by: Kees Cook <keescook@chromium.org>
2018-06-12 14:03:40 -07:00
|
|
|
|
2008-03-02 23:28:24 +03:00
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2008-04-14 19:11:40 +03:00
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2008-04-14 19:11:40 +03:00
|
|
|
|
2013-07-15 09:05:29 +08:00
|
|
|
|
|
|
|
|
|
2012-05-09 10:09:56 -05:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2007-10-16 01:26:05 -07:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
|
|
|
|
|
2012-05-09 10:09:56 -05:00
|
|
|
|
2008-04-14 19:11:40 +03:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2012-05-09 10:09:56 -05:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2012-05-09 10:09:56 -05:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2012-05-09 10:09:56 -05:00
|
|
|
|
|
|
|
|
|
2011-08-09 16:12:27 -05:00
|
|
|
|
2012-05-09 10:09:56 -05:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-11-10 14:12:45 +01:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-09-10 11:43:37 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-03-21 11:48:15 +08:00
|
|
|
|
2011-11-22 16:02:02 +01:00
|
|
|
|
|
|
|
|
|
2011-08-09 16:12:27 -05:00
|
|
|
|
2021-11-10 14:12:45 +01:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
mm/slub: fix a deadlock in show_slab_objects()
A long time ago we fixed a similar deadlock in show_slab_objects() [1].
However, it is apparently due to the commits like 01fb58bcba63 ("slab:
remove synchronous synchronize_sched() from memcg cache deactivation
path") and 03afc0e25f7f ("slab: get_online_mems for
kmem_cache_{create,destroy,shrink}"), this kind of deadlock is back by
just reading files in /sys/kernel/slab which will generate a lockdep
splat below.
Since the "mem_hotplug_lock" here is only to obtain a stable online node
mask while racing with NUMA node hotplug, in the worst case, the results
may me miscalculated while doing NUMA node hotplug, but they shall be
corrected by later reads of the same files.
WARNING: possible circular locking dependency detected
------------------------------------------------------
cat/5224 is trying to acquire lock:
ffff900012ac3120 (mem_hotplug_lock.rw_sem){++++}, at:
show_slab_objects+0x94/0x3a8
but task is already holding lock:
b8ff009693eee398 (kn->count#45){++++}, at: kernfs_seq_start+0x44/0xf0
which lock already depends on the new lock.
the existing dependency chain (in reverse order) is:
-> #2 (kn->count#45){++++}:
lock_acquire+0x31c/0x360
__kernfs_remove+0x290/0x490
kernfs_remove+0x30/0x44
sysfs_remove_dir+0x70/0x88
kobject_del+0x50/0xb0
sysfs_slab_unlink+0x2c/0x38
shutdown_cache+0xa0/0xf0
kmemcg_cache_shutdown_fn+0x1c/0x34
kmemcg_workfn+0x44/0x64
process_one_work+0x4f4/0x950
worker_thread+0x390/0x4bc
kthread+0x1cc/0x1e8
ret_from_fork+0x10/0x18
-> #1 (slab_mutex){+.+.}:
lock_acquire+0x31c/0x360
__mutex_lock_common+0x16c/0xf78
mutex_lock_nested+0x40/0x50
memcg_create_kmem_cache+0x38/0x16c
memcg_kmem_cache_create_func+0x3c/0x70
process_one_work+0x4f4/0x950
worker_thread+0x390/0x4bc
kthread+0x1cc/0x1e8
ret_from_fork+0x10/0x18
-> #0 (mem_hotplug_lock.rw_sem){++++}:
validate_chain+0xd10/0x2bcc
__lock_acquire+0x7f4/0xb8c
lock_acquire+0x31c/0x360
get_online_mems+0x54/0x150
show_slab_objects+0x94/0x3a8
total_objects_show+0x28/0x34
slab_attr_show+0x38/0x54
sysfs_kf_seq_show+0x198/0x2d4
kernfs_seq_show+0xa4/0xcc
seq_read+0x30c/0x8a8
kernfs_fop_read+0xa8/0x314
__vfs_read+0x88/0x20c
vfs_read+0xd8/0x10c
ksys_read+0xb0/0x120
__arm64_sys_read+0x54/0x88
el0_svc_handler+0x170/0x240
el0_svc+0x8/0xc
other info that might help us debug this:
Chain exists of:
mem_hotplug_lock.rw_sem --> slab_mutex --> kn->count#45
Possible unsafe locking scenario:
CPU0 CPU1
---- ----
lock(kn->count#45);
lock(slab_mutex);
lock(kn->count#45);
lock(mem_hotplug_lock.rw_sem);
*** DEADLOCK ***
3 locks held by cat/5224:
#0: 9eff00095b14b2a0 (&p->lock){+.+.}, at: seq_read+0x4c/0x8a8
#1: 0eff008997041480 (&of->mutex){+.+.}, at: kernfs_seq_start+0x34/0xf0
#2: b8ff009693eee398 (kn->count#45){++++}, at:
kernfs_seq_start+0x44/0xf0
stack backtrace:
Call trace:
dump_backtrace+0x0/0x248
show_stack+0x20/0x2c
dump_stack+0xd0/0x140
print_circular_bug+0x368/0x380
check_noncircular+0x248/0x250
validate_chain+0xd10/0x2bcc
__lock_acquire+0x7f4/0xb8c
lock_acquire+0x31c/0x360
get_online_mems+0x54/0x150
show_slab_objects+0x94/0x3a8
total_objects_show+0x28/0x34
slab_attr_show+0x38/0x54
sysfs_kf_seq_show+0x198/0x2d4
kernfs_seq_show+0xa4/0xcc
seq_read+0x30c/0x8a8
kernfs_fop_read+0xa8/0x314
__vfs_read+0x88/0x20c
vfs_read+0xd8/0x10c
ksys_read+0xb0/0x120
__arm64_sys_read+0x54/0x88
el0_svc_handler+0x170/0x240
el0_svc+0x8/0xc
I think it is important to mention that this doesn't expose the
show_slab_objects to use-after-free. There is only a single path that
might really race here and that is the slab hotplug notifier callback
__kmem_cache_shrink (via slab_mem_going_offline_callback) but that path
doesn't really destroy kmem_cache_node data structures.
[1] http://lkml.iu.edu/hypermail/linux/kernel/1101.0/02850.html
[akpm@linux-foundation.org: add comment explaining why we don't need mem_hotplug_lock]
Link: http://lkml.kernel.org/r/1570192309-10132-1-git-send-email-cai@lca.pw
Fixes: 01fb58bcba63 ("slab: remove synchronous synchronize_sched() from memcg cache deactivation path")
Fixes: 03afc0e25f7f ("slab: get_online_mems for kmem_cache_{create,destroy,shrink}")
Signed-off-by: Qian Cai <cai@lca.pw>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Cc: Roman Gushchin <guro@fb.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-10-14 14:11:51 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2010-10-05 13:57:26 -05:00
|
|
|
|
2008-04-14 19:11:40 +03:00
|
|
|
|
2014-08-06 16:04:09 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2013-07-15 09:05:29 +08:00
|
|
|
|
2023-04-13 22:34:52 +08:00
|
|
|
|
2013-07-15 09:05:29 +08:00
|
|
|
|
2023-04-13 22:34:52 +08:00
|
|
|
|
2008-04-14 19:11:40 +03:00
|
|
|
|
2023-04-13 22:34:52 +08:00
|
|
|
|
2008-04-14 19:11:40 +03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2010-10-05 13:57:26 -05:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2014-08-06 16:04:09 -07:00
|
|
|
|
2008-04-14 19:11:40 +03:00
|
|
|
|
2014-08-06 16:04:09 -07:00
|
|
|
|
2008-04-14 19:11:40 +03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-12-14 19:14:57 -08:00
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2020-12-14 19:14:57 -08:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2020-12-14 19:14:57 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2020-12-14 19:14:57 -08:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2020-12-14 19:14:57 -08:00
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-07-14 15:07:13 +03:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-03-06 15:38:18 +08:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
2022-03-06 15:38:18 +08:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-12-14 19:14:57 -08:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-12-14 19:14:57 -08:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-12-14 19:14:57 -08:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-12-14 19:14:57 -08:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-12-14 19:14:57 -08:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2020-08-06 23:18:41 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
slub: add min_partial sysfs tunable
Now that a cache's min_partial has been moved to struct kmem_cache, it's
possible to easily tune it from userspace by adding a sysfs attribute.
It may not be desirable to keep a large number of partial slabs around
if a cache is used infrequently and memory, especially when constrained
by a cgroup, is scarce. It's better to allow userspace to set the
minimum policy per cache instead of relying explicitly on
kmem_cache_shrink().
The memory savings from simply moving min_partial from struct
kmem_cache_node to struct kmem_cache is obviously not significant
(unless maybe you're from SGI or something), at the largest it's
# allocated caches * (MAX_NUMNODES - 1) * sizeof(unsigned long)
The true savings occurs when userspace reduces the number of partial
slabs that would otherwise be wasted, especially on machines with a
large number of nodes (ia64 with CONFIG_NODES_SHIFT at 10 for default?).
As well as the kernel estimates ideal values for n->min_partial and
ensures it's within a sane range, userspace has no other input other
than writing to /sys/kernel/slab/cache/shrink.
There simply isn't any better heuristic to add when calculating the
partial values for a better estimate that works for all possible caches.
And since it's currently a static value, the user really has no way of
reclaiming that wasted space, which can be significant when constrained
by a cgroup (either cpusets or, later, memory controller slab limits)
without shrinking it entirely.
This also allows the user to specify that increased fragmentation and
more partial slabs are actually desired to avoid the cost of allocating
new slabs at runtime for specific caches.
There's also no reason why this should be a per-struct kmem_cache_node
value in the first place. You could argue that a machine would have
such node size asymmetries that it should be specified on a per-node
basis, but we know nobody is doing that right now since it's a purely
static value at the moment and there's no convenient way to tune that
via slub's sysfs interface.
Cc: Christoph Lameter <cl@linux-foundation.org>
Signed-off-by: David Rientjes <rientjes@google.com>
Signed-off-by: Pekka Enberg <penberg@cs.helsinki.fi>
2009-02-22 17:40:09 -08:00
|
|
|
|
|
|
|
|
|
2020-12-14 19:14:57 -08:00
|
|
|
|
slub: add min_partial sysfs tunable
Now that a cache's min_partial has been moved to struct kmem_cache, it's
possible to easily tune it from userspace by adding a sysfs attribute.
It may not be desirable to keep a large number of partial slabs around
if a cache is used infrequently and memory, especially when constrained
by a cgroup, is scarce. It's better to allow userspace to set the
minimum policy per cache instead of relying explicitly on
kmem_cache_shrink().
The memory savings from simply moving min_partial from struct
kmem_cache_node to struct kmem_cache is obviously not significant
(unless maybe you're from SGI or something), at the largest it's
# allocated caches * (MAX_NUMNODES - 1) * sizeof(unsigned long)
The true savings occurs when userspace reduces the number of partial
slabs that would otherwise be wasted, especially on machines with a
large number of nodes (ia64 with CONFIG_NODES_SHIFT at 10 for default?).
As well as the kernel estimates ideal values for n->min_partial and
ensures it's within a sane range, userspace has no other input other
than writing to /sys/kernel/slab/cache/shrink.
There simply isn't any better heuristic to add when calculating the
partial values for a better estimate that works for all possible caches.
And since it's currently a static value, the user really has no way of
reclaiming that wasted space, which can be significant when constrained
by a cgroup (either cpusets or, later, memory controller slab limits)
without shrinking it entirely.
This also allows the user to specify that increased fragmentation and
more partial slabs are actually desired to avoid the cost of allocating
new slabs at runtime for specific caches.
There's also no reason why this should be a per-struct kmem_cache_node
value in the first place. You could argue that a machine would have
such node size asymmetries that it should be specified on a per-node
basis, but we know nobody is doing that right now since it's a purely
static value at the moment and there's no convenient way to tune that
via slub's sysfs interface.
Cc: Christoph Lameter <cl@linux-foundation.org>
Signed-off-by: David Rientjes <rientjes@google.com>
Signed-off-by: Pekka Enberg <penberg@cs.helsinki.fi>
2009-02-22 17:40:09 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-09-11 14:20:25 -07:00
|
|
|
|
slub: add min_partial sysfs tunable
Now that a cache's min_partial has been moved to struct kmem_cache, it's
possible to easily tune it from userspace by adding a sysfs attribute.
It may not be desirable to keep a large number of partial slabs around
if a cache is used infrequently and memory, especially when constrained
by a cgroup, is scarce. It's better to allow userspace to set the
minimum policy per cache instead of relying explicitly on
kmem_cache_shrink().
The memory savings from simply moving min_partial from struct
kmem_cache_node to struct kmem_cache is obviously not significant
(unless maybe you're from SGI or something), at the largest it's
# allocated caches * (MAX_NUMNODES - 1) * sizeof(unsigned long)
The true savings occurs when userspace reduces the number of partial
slabs that would otherwise be wasted, especially on machines with a
large number of nodes (ia64 with CONFIG_NODES_SHIFT at 10 for default?).
As well as the kernel estimates ideal values for n->min_partial and
ensures it's within a sane range, userspace has no other input other
than writing to /sys/kernel/slab/cache/shrink.
There simply isn't any better heuristic to add when calculating the
partial values for a better estimate that works for all possible caches.
And since it's currently a static value, the user really has no way of
reclaiming that wasted space, which can be significant when constrained
by a cgroup (either cpusets or, later, memory controller slab limits)
without shrinking it entirely.
This also allows the user to specify that increased fragmentation and
more partial slabs are actually desired to avoid the cost of allocating
new slabs at runtime for specific caches.
There's also no reason why this should be a per-struct kmem_cache_node
value in the first place. You could argue that a machine would have
such node size asymmetries that it should be specified on a per-node
basis, but we know nobody is doing that right now since it's a purely
static value at the moment and there's no convenient way to tune that
via slub's sysfs interface.
Cc: Christoph Lameter <cl@linux-foundation.org>
Signed-off-by: David Rientjes <rientjes@google.com>
Signed-off-by: Pekka Enberg <penberg@cs.helsinki.fi>
2009-02-22 17:40:09 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-03-07 07:40:55 +00:00
|
|
|
|
slub: add min_partial sysfs tunable
Now that a cache's min_partial has been moved to struct kmem_cache, it's
possible to easily tune it from userspace by adding a sysfs attribute.
It may not be desirable to keep a large number of partial slabs around
if a cache is used infrequently and memory, especially when constrained
by a cgroup, is scarce. It's better to allow userspace to set the
minimum policy per cache instead of relying explicitly on
kmem_cache_shrink().
The memory savings from simply moving min_partial from struct
kmem_cache_node to struct kmem_cache is obviously not significant
(unless maybe you're from SGI or something), at the largest it's
# allocated caches * (MAX_NUMNODES - 1) * sizeof(unsigned long)
The true savings occurs when userspace reduces the number of partial
slabs that would otherwise be wasted, especially on machines with a
large number of nodes (ia64 with CONFIG_NODES_SHIFT at 10 for default?).
As well as the kernel estimates ideal values for n->min_partial and
ensures it's within a sane range, userspace has no other input other
than writing to /sys/kernel/slab/cache/shrink.
There simply isn't any better heuristic to add when calculating the
partial values for a better estimate that works for all possible caches.
And since it's currently a static value, the user really has no way of
reclaiming that wasted space, which can be significant when constrained
by a cgroup (either cpusets or, later, memory controller slab limits)
without shrinking it entirely.
This also allows the user to specify that increased fragmentation and
more partial slabs are actually desired to avoid the cost of allocating
new slabs at runtime for specific caches.
There's also no reason why this should be a per-struct kmem_cache_node
value in the first place. You could argue that a machine would have
such node size asymmetries that it should be specified on a per-node
basis, but we know nobody is doing that right now since it's a purely
static value at the moment and there's no convenient way to tune that
via slub's sysfs interface.
Cc: Christoph Lameter <cl@linux-foundation.org>
Signed-off-by: David Rientjes <rientjes@google.com>
Signed-off-by: Pekka Enberg <penberg@cs.helsinki.fi>
2009-02-22 17:40:09 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-08-09 16:12:27 -05:00
|
|
|
|
|
|
|
|
|
mm, slub: change percpu partial accounting from objects to pages
With CONFIG_SLUB_CPU_PARTIAL enabled, SLUB keeps a percpu list of
partial slabs that can be promoted to cpu slab when the previous one is
depleted, without accessing the shared partial list. A slab can be
added to this list by 1) refill of an empty list from get_partial_node()
- once we really have to access the shared partial list, we acquire
multiple slabs to amortize the cost of locking, and 2) first free to a
previously full slab - instead of putting the slab on a shared partial
list, we can more cheaply freeze it and put it on the per-cpu list.
To control how large a percpu partial list can grow for a kmem cache,
set_cpu_partial() calculates a target number of free objects on each
cpu's percpu partial list, and this can be also set by the sysfs file
cpu_partial.
However, the tracking of actual number of objects is imprecise, in order
to limit overhead from cpu X freeing an objects to a slab on percpu
partial list of cpu Y. Basically, the percpu partial slabs form a
single linked list, and when we add a new slab to the list with current
head "oldpage", we set in the struct page of the slab we're adding:
page->pages = oldpage->pages + 1; // this is precise
page->pobjects = oldpage->pobjects + (page->objects - page->inuse);
page->next = oldpage;
Thus the real number of free objects in the slab (objects - inuse) is
only determined at the moment of adding the slab to the percpu partial
list, and further freeing doesn't update the pobjects counter nor
propagate it to the current list head. As Jann reports [1], this can
easily lead to large inaccuracies, where the target number of objects
(up to 30 by default) can translate to the same number of (empty) slab
pages on the list. In case 2) above, we put a slab with 1 free object
on the list, thus only increase page->pobjects by 1, even if there are
subsequent frees on the same slab. Jann has noticed this in practice
and so did we [2] when investigating significant increase of kmemcg
usage after switching from SLAB to SLUB.
While this is no longer a problem in kmemcg context thanks to the
accounting rewrite in 5.9, the memory waste is still not ideal and it's
questionable whether it makes sense to perform free object count based
control when object counts can easily become so much inaccurate. So
this patch converts the accounting to be based on number of pages only
(which is precise) and removes the page->pobjects field completely.
This is also ultimately simpler.
To retain the existing set_cpu_partial() heuristic, first calculate the
target number of objects as previously, but then convert it to target
number of pages by assuming the pages will be half-filled on average.
This assumption might obviously also be inaccurate in practice, but
cannot degrade to actual number of pages being equal to the target
number of objects.
We could also skip the intermediate step with target number of objects
and rewrite the heuristic in terms of pages. However we still have the
sysfs file cpu_partial which uses number of objects and could break
existing users if it suddenly becomes number of pages, so this patch
doesn't do that.
In practice, after this patch the heuristics limit the size of percpu
partial list up to 2 pages. In case of a reported regression (which
would mean some workload has benefited from the previous imprecise
object based counting), we can tune the heuristics to get a better
compromise within the new scheme, while still avoid the unexpectedly
long percpu partial lists.
[1] https://lore.kernel.org/linux-mm/CAG48ez2Qx5K1Cab-m8BdSibp6wLTip6ro4=-umR7BLsEgjEYzA@mail.gmail.com/
[2] https://lore.kernel.org/all/2f0f46e8-2535-410a-1859-e9cfa4e57c18@suse.cz/
==========
Evaluation
==========
Mel was kind enough to run v1 through mmtests machinery for netperf
(localhost) and hackbench and, for most significant results see below.
So there are some apparent regressions, especially with hackbench, which
I think ultimately boils down to having shorter percpu partial lists on
average and some benchmarks benefiting from longer ones. Monitoring
slab usage also indicated less memory usage by slab. Based on that, the
following patch will bump the defaults to allow longer percpu partial
lists than after this patch.
However the goal is certainly not such that we would limit the percpu
partial lists to 30 pages just because previously a specific alloc/free
pattern could lead to the limit of 30 objects translate to a limit to 30
pages - that would make little sense. This is a correctness patch, and
if a workload benefits from larger lists, the sysfs tuning knobs are
still there to allow that.
Netperf
2-socket Intel(R) Xeon(R) Gold 5218R CPU @ 2.10GHz (20 cores, 40 threads per socket), 384GB RAM
TCP-RR:
hmean before 127045.79 after 121092.94 (-4.69%, worse)
stddev before 2634.37 after 1254.08
UDP-RR:
hmean before 166985.45 after 160668.94 ( -3.78%, worse)
stddev before 4059.69 after 1943.63
2-socket Intel(R) Xeon(R) CPU E5-2698 v4 @ 2.20GHz (20 cores, 40 threads per socket), 512GB RAM
TCP-RR:
hmean before 84173.25 after 76914.72 ( -8.62%, worse)
UDP-RR:
hmean before 93571.12 after 96428.69 ( 3.05%, better)
stddev before 23118.54 after 16828.14
2-socket Intel(R) Xeon(R) CPU E5-2670 v3 @ 2.30GHz (12 cores, 24 threads per socket), 64GB RAM
TCP-RR:
hmean before 49984.92 after 48922.27 ( -2.13%, worse)
stddev before 6248.15 after 4740.51
UDP-RR:
hmean before 61854.31 after 68761.81 ( 11.17%, better)
stddev before 4093.54 after 5898.91
other machines - within 2%
Hackbench
(results before and after the patch, negative % means worse)
2-socket AMD EPYC 7713 (64 cores, 128 threads per core), 256GB RAM
hackbench-process-sockets
Amean 1 0.5380 0.5583 ( -3.78%)
Amean 4 0.7510 0.8150 ( -8.52%)
Amean 7 0.7930 0.9533 ( -20.22%)
Amean 12 0.7853 1.1313 ( -44.06%)
Amean 21 1.1520 1.4993 ( -30.15%)
Amean 30 1.6223 1.9237 ( -18.57%)
Amean 48 2.6767 2.9903 ( -11.72%)
Amean 79 4.0257 5.1150 ( -27.06%)
Amean 110 5.5193 7.4720 ( -35.38%)
Amean 141 7.2207 9.9840 ( -38.27%)
Amean 172 8.4770 12.1963 ( -43.88%)
Amean 203 9.6473 14.3137 ( -48.37%)
Amean 234 11.3960 18.7917 ( -64.90%)
Amean 265 13.9627 22.4607 ( -60.86%)
Amean 296 14.9163 26.0483 ( -74.63%)
hackbench-thread-sockets
Amean 1 0.5597 0.5877 ( -5.00%)
Amean 4 0.7913 0.8960 ( -13.23%)
Amean 7 0.8190 1.0017 ( -22.30%)
Amean 12 0.9560 1.1727 ( -22.66%)
Amean 21 1.7587 1.5660 ( 10.96%)
Amean 30 2.4477 1.9807 ( 19.08%)
Amean 48 3.4573 3.0630 ( 11.41%)
Amean 79 4.7903 5.1733 ( -8.00%)
Amean 110 6.1370 7.4220 ( -20.94%)
Amean 141 7.5777 9.2617 ( -22.22%)
Amean 172 9.2280 11.0907 ( -20.18%)
Amean 203 10.2793 13.3470 ( -29.84%)
Amean 234 11.2410 17.1070 ( -52.18%)
Amean 265 12.5970 23.3323 ( -85.22%)
Amean 296 17.1540 24.2857 ( -41.57%)
2-socket Intel(R) Xeon(R) Gold 5218R CPU @ 2.10GHz (20 cores, 40 threads
per socket), 384GB RAM
hackbench-process-sockets
Amean 1 0.5760 0.4793 ( 16.78%)
Amean 4 0.9430 0.9707 ( -2.93%)
Amean 7 1.5517 1.8843 ( -21.44%)
Amean 12 2.4903 2.7267 ( -9.49%)
Amean 21 3.9560 4.2877 ( -8.38%)
Amean 30 5.4613 5.8343 ( -6.83%)
Amean 48 8.5337 9.2937 ( -8.91%)
Amean 79 14.0670 15.2630 ( -8.50%)
Amean 110 19.2253 21.2467 ( -10.51%)
Amean 141 23.7557 25.8550 ( -8.84%)
Amean 172 28.4407 29.7603 ( -4.64%)
Amean 203 33.3407 33.9927 ( -1.96%)
Amean 234 38.3633 39.1150 ( -1.96%)
Amean 265 43.4420 43.8470 ( -0.93%)
Amean 296 48.3680 48.9300 ( -1.16%)
hackbench-thread-sockets
Amean 1 0.6080 0.6493 ( -6.80%)
Amean 4 1.0000 1.0513 ( -5.13%)
Amean 7 1.6607 2.0260 ( -22.00%)
Amean 12 2.7637 2.9273 ( -5.92%)
Amean 21 5.0613 4.5153 ( 10.79%)
Amean 30 6.3340 6.1140 ( 3.47%)
Amean 48 9.0567 9.5577 ( -5.53%)
Amean 79 14.5657 15.7983 ( -8.46%)
Amean 110 19.6213 21.6333 ( -10.25%)
Amean 141 24.1563 26.2697 ( -8.75%)
Amean 172 28.9687 30.2187 ( -4.32%)
Amean 203 33.9763 34.6970 ( -2.12%)
Amean 234 38.8647 39.3207 ( -1.17%)
Amean 265 44.0813 44.1507 ( -0.16%)
Amean 296 49.2040 49.4330 ( -0.47%)
2-socket Intel(R) Xeon(R) CPU E5-2698 v4 @ 2.20GHz (20 cores, 40 threads
per socket), 512GB RAM
hackbench-process-sockets
Amean 1 0.5027 0.5017 ( 0.20%)
Amean 4 1.1053 1.2033 ( -8.87%)
Amean 7 1.8760 2.1820 ( -16.31%)
Amean 12 2.9053 3.1810 ( -9.49%)
Amean 21 4.6777 4.9920 ( -6.72%)
Amean 30 6.5180 6.7827 ( -4.06%)
Amean 48 10.0710 10.5227 ( -4.48%)
Amean 79 16.4250 17.5053 ( -6.58%)
Amean 110 22.6203 24.4617 ( -8.14%)
Amean 141 28.0967 31.0363 ( -10.46%)
Amean 172 34.4030 36.9233 ( -7.33%)
Amean 203 40.5933 43.0850 ( -6.14%)
Amean 234 46.6477 48.7220 ( -4.45%)
Amean 265 53.0530 53.9597 ( -1.71%)
Amean 296 59.2760 59.9213 ( -1.09%)
hackbench-thread-sockets
Amean 1 0.5363 0.5330 ( 0.62%)
Amean 4 1.1647 1.2157 ( -4.38%)
Amean 7 1.9237 2.2833 ( -18.70%)
Amean 12 2.9943 3.3110 ( -10.58%)
Amean 21 4.9987 5.1880 ( -3.79%)
Amean 30 6.7583 7.0043 ( -3.64%)
Amean 48 10.4547 10.8353 ( -3.64%)
Amean 79 16.6707 17.6790 ( -6.05%)
Amean 110 22.8207 24.4403 ( -7.10%)
Amean 141 28.7090 31.0533 ( -8.17%)
Amean 172 34.9387 36.8260 ( -5.40%)
Amean 203 41.1567 43.0450 ( -4.59%)
Amean 234 47.3790 48.5307 ( -2.43%)
Amean 265 53.9543 54.6987 ( -1.38%)
Amean 296 60.0820 60.2163 ( -0.22%)
1-socket Intel(R) Xeon(R) CPU E3-1240 v5 @ 3.50GHz (4 cores, 8 threads),
32 GB RAM
hackbench-process-sockets
Amean 1 1.4760 1.5773 ( -6.87%)
Amean 3 3.9370 4.0910 ( -3.91%)
Amean 5 6.6797 6.9357 ( -3.83%)
Amean 7 9.3367 9.7150 ( -4.05%)
Amean 12 15.7627 16.1400 ( -2.39%)
Amean 18 23.5360 23.6890 ( -0.65%)
Amean 24 31.0663 31.3137 ( -0.80%)
Amean 30 38.7283 39.0037 ( -0.71%)
Amean 32 41.3417 41.6097 ( -0.65%)
hackbench-thread-sockets
Amean 1 1.5250 1.6043 ( -5.20%)
Amean 3 4.0897 4.2603 ( -4.17%)
Amean 5 6.7760 7.0933 ( -4.68%)
Amean 7 9.4817 9.9157 ( -4.58%)
Amean 12 15.9610 16.3937 ( -2.71%)
Amean 18 23.9543 24.3417 ( -1.62%)
Amean 24 31.4400 31.7217 ( -0.90%)
Amean 30 39.2457 39.5467 ( -0.77%)
Amean 32 41.8267 42.1230 ( -0.71%)
2-socket Intel(R) Xeon(R) CPU E5-2670 v3 @ 2.30GHz (12 cores, 24 threads
per socket), 64GB RAM
hackbench-process-sockets
Amean 1 1.0347 1.0880 ( -5.15%)
Amean 4 1.7267 1.8527 ( -7.30%)
Amean 7 2.6707 2.8110 ( -5.25%)
Amean 12 4.1617 4.3383 ( -4.25%)
Amean 21 7.0070 7.2600 ( -3.61%)
Amean 30 9.9187 10.2397 ( -3.24%)
Amean 48 15.6710 16.3923 ( -4.60%)
Amean 79 24.7743 26.1247 ( -5.45%)
Amean 110 34.3000 35.9307 ( -4.75%)
Amean 141 44.2043 44.8010 ( -1.35%)
Amean 172 54.2430 54.7260 ( -0.89%)
Amean 192 60.6557 60.9777 ( -0.53%)
hackbench-thread-sockets
Amean 1 1.0610 1.1353 ( -7.01%)
Amean 4 1.7543 1.9140 ( -9.10%)
Amean 7 2.7840 2.9573 ( -6.23%)
Amean 12 4.3813 4.4937 ( -2.56%)
Amean 21 7.3460 7.5350 ( -2.57%)
Amean 30 10.2313 10.5190 ( -2.81%)
Amean 48 15.9700 16.5940 ( -3.91%)
Amean 79 25.3973 26.6637 ( -4.99%)
Amean 110 35.1087 36.4797 ( -3.91%)
Amean 141 45.8220 46.3053 ( -1.05%)
Amean 172 55.4917 55.7320 ( -0.43%)
Amean 192 62.7490 62.5410 ( 0.33%)
Link: https://lkml.kernel.org/r/20211012134651.11258-1-vbabka@suse.cz
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reported-by: Jann Horn <jannh@google.com>
Cc: Roman Gushchin <guro@fb.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-11-05 13:35:17 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-08-09 16:12:27 -05:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-04-05 16:21:10 -07:00
|
|
|
|
2011-08-09 16:12:27 -05:00
|
|
|
|
|
|
|
|
|
2018-04-05 16:21:10 -07:00
|
|
|
|
2011-08-09 16:12:27 -05:00
|
|
|
|
|
|
|
|
|
2013-06-19 14:05:52 +09:00
|
|
|
|
2012-01-09 13:19:45 -08:00
|
|
|
|
2011-08-09 16:12:27 -05:00
|
|
|
|
2017-07-06 15:36:34 -07:00
|
|
|
|
2011-08-09 16:12:27 -05:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
2011-01-13 15:45:52 -08:00
|
|
|
|
|
|
|
|
|
2020-12-14 19:14:57 -08:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-12-14 19:14:57 -08:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-02-15 15:22:21 -08:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-02-15 15:22:21 -08:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-04-14 19:11:40 +03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-08-09 16:12:27 -05:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2021-11-10 14:12:45 +01:00
|
|
|
|
2020-12-14 19:14:57 -08:00
|
|
|
|
2011-08-09 16:12:27 -05:00
|
|
|
|
2021-11-10 14:12:45 +01:00
|
|
|
|
2011-08-09 16:12:27 -05:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2017-07-06 15:36:31 -07:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2011-08-09 16:12:27 -05:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2024-03-21 11:48:15 +08:00
|
|
|
|
2011-08-09 16:12:27 -05:00
|
|
|
|
2021-11-10 14:12:45 +01:00
|
|
|
|
2011-08-09 16:12:27 -05:00
|
|
|
|
2021-11-15 16:55:15 +01:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
|
|
|
|
|
2011-08-09 16:12:27 -05:00
|
|
|
|
2023-04-13 22:34:50 +08:00
|
|
|
|
2011-08-09 16:12:27 -05:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2017-07-06 15:36:31 -07:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
|
|
|
|
|
2024-03-21 11:48:15 +08:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2020-12-14 19:14:57 -08:00
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
mm, slub: change percpu partial accounting from objects to pages
With CONFIG_SLUB_CPU_PARTIAL enabled, SLUB keeps a percpu list of
partial slabs that can be promoted to cpu slab when the previous one is
depleted, without accessing the shared partial list. A slab can be
added to this list by 1) refill of an empty list from get_partial_node()
- once we really have to access the shared partial list, we acquire
multiple slabs to amortize the cost of locking, and 2) first free to a
previously full slab - instead of putting the slab on a shared partial
list, we can more cheaply freeze it and put it on the per-cpu list.
To control how large a percpu partial list can grow for a kmem cache,
set_cpu_partial() calculates a target number of free objects on each
cpu's percpu partial list, and this can be also set by the sysfs file
cpu_partial.
However, the tracking of actual number of objects is imprecise, in order
to limit overhead from cpu X freeing an objects to a slab on percpu
partial list of cpu Y. Basically, the percpu partial slabs form a
single linked list, and when we add a new slab to the list with current
head "oldpage", we set in the struct page of the slab we're adding:
page->pages = oldpage->pages + 1; // this is precise
page->pobjects = oldpage->pobjects + (page->objects - page->inuse);
page->next = oldpage;
Thus the real number of free objects in the slab (objects - inuse) is
only determined at the moment of adding the slab to the percpu partial
list, and further freeing doesn't update the pobjects counter nor
propagate it to the current list head. As Jann reports [1], this can
easily lead to large inaccuracies, where the target number of objects
(up to 30 by default) can translate to the same number of (empty) slab
pages on the list. In case 2) above, we put a slab with 1 free object
on the list, thus only increase page->pobjects by 1, even if there are
subsequent frees on the same slab. Jann has noticed this in practice
and so did we [2] when investigating significant increase of kmemcg
usage after switching from SLAB to SLUB.
While this is no longer a problem in kmemcg context thanks to the
accounting rewrite in 5.9, the memory waste is still not ideal and it's
questionable whether it makes sense to perform free object count based
control when object counts can easily become so much inaccurate. So
this patch converts the accounting to be based on number of pages only
(which is precise) and removes the page->pobjects field completely.
This is also ultimately simpler.
To retain the existing set_cpu_partial() heuristic, first calculate the
target number of objects as previously, but then convert it to target
number of pages by assuming the pages will be half-filled on average.
This assumption might obviously also be inaccurate in practice, but
cannot degrade to actual number of pages being equal to the target
number of objects.
We could also skip the intermediate step with target number of objects
and rewrite the heuristic in terms of pages. However we still have the
sysfs file cpu_partial which uses number of objects and could break
existing users if it suddenly becomes number of pages, so this patch
doesn't do that.
In practice, after this patch the heuristics limit the size of percpu
partial list up to 2 pages. In case of a reported regression (which
would mean some workload has benefited from the previous imprecise
object based counting), we can tune the heuristics to get a better
compromise within the new scheme, while still avoid the unexpectedly
long percpu partial lists.
[1] https://lore.kernel.org/linux-mm/CAG48ez2Qx5K1Cab-m8BdSibp6wLTip6ro4=-umR7BLsEgjEYzA@mail.gmail.com/
[2] https://lore.kernel.org/all/2f0f46e8-2535-410a-1859-e9cfa4e57c18@suse.cz/
==========
Evaluation
==========
Mel was kind enough to run v1 through mmtests machinery for netperf
(localhost) and hackbench and, for most significant results see below.
So there are some apparent regressions, especially with hackbench, which
I think ultimately boils down to having shorter percpu partial lists on
average and some benchmarks benefiting from longer ones. Monitoring
slab usage also indicated less memory usage by slab. Based on that, the
following patch will bump the defaults to allow longer percpu partial
lists than after this patch.
However the goal is certainly not such that we would limit the percpu
partial lists to 30 pages just because previously a specific alloc/free
pattern could lead to the limit of 30 objects translate to a limit to 30
pages - that would make little sense. This is a correctness patch, and
if a workload benefits from larger lists, the sysfs tuning knobs are
still there to allow that.
Netperf
2-socket Intel(R) Xeon(R) Gold 5218R CPU @ 2.10GHz (20 cores, 40 threads per socket), 384GB RAM
TCP-RR:
hmean before 127045.79 after 121092.94 (-4.69%, worse)
stddev before 2634.37 after 1254.08
UDP-RR:
hmean before 166985.45 after 160668.94 ( -3.78%, worse)
stddev before 4059.69 after 1943.63
2-socket Intel(R) Xeon(R) CPU E5-2698 v4 @ 2.20GHz (20 cores, 40 threads per socket), 512GB RAM
TCP-RR:
hmean before 84173.25 after 76914.72 ( -8.62%, worse)
UDP-RR:
hmean before 93571.12 after 96428.69 ( 3.05%, better)
stddev before 23118.54 after 16828.14
2-socket Intel(R) Xeon(R) CPU E5-2670 v3 @ 2.30GHz (12 cores, 24 threads per socket), 64GB RAM
TCP-RR:
hmean before 49984.92 after 48922.27 ( -2.13%, worse)
stddev before 6248.15 after 4740.51
UDP-RR:
hmean before 61854.31 after 68761.81 ( 11.17%, better)
stddev before 4093.54 after 5898.91
other machines - within 2%
Hackbench
(results before and after the patch, negative % means worse)
2-socket AMD EPYC 7713 (64 cores, 128 threads per core), 256GB RAM
hackbench-process-sockets
Amean 1 0.5380 0.5583 ( -3.78%)
Amean 4 0.7510 0.8150 ( -8.52%)
Amean 7 0.7930 0.9533 ( -20.22%)
Amean 12 0.7853 1.1313 ( -44.06%)
Amean 21 1.1520 1.4993 ( -30.15%)
Amean 30 1.6223 1.9237 ( -18.57%)
Amean 48 2.6767 2.9903 ( -11.72%)
Amean 79 4.0257 5.1150 ( -27.06%)
Amean 110 5.5193 7.4720 ( -35.38%)
Amean 141 7.2207 9.9840 ( -38.27%)
Amean 172 8.4770 12.1963 ( -43.88%)
Amean 203 9.6473 14.3137 ( -48.37%)
Amean 234 11.3960 18.7917 ( -64.90%)
Amean 265 13.9627 22.4607 ( -60.86%)
Amean 296 14.9163 26.0483 ( -74.63%)
hackbench-thread-sockets
Amean 1 0.5597 0.5877 ( -5.00%)
Amean 4 0.7913 0.8960 ( -13.23%)
Amean 7 0.8190 1.0017 ( -22.30%)
Amean 12 0.9560 1.1727 ( -22.66%)
Amean 21 1.7587 1.5660 ( 10.96%)
Amean 30 2.4477 1.9807 ( 19.08%)
Amean 48 3.4573 3.0630 ( 11.41%)
Amean 79 4.7903 5.1733 ( -8.00%)
Amean 110 6.1370 7.4220 ( -20.94%)
Amean 141 7.5777 9.2617 ( -22.22%)
Amean 172 9.2280 11.0907 ( -20.18%)
Amean 203 10.2793 13.3470 ( -29.84%)
Amean 234 11.2410 17.1070 ( -52.18%)
Amean 265 12.5970 23.3323 ( -85.22%)
Amean 296 17.1540 24.2857 ( -41.57%)
2-socket Intel(R) Xeon(R) Gold 5218R CPU @ 2.10GHz (20 cores, 40 threads
per socket), 384GB RAM
hackbench-process-sockets
Amean 1 0.5760 0.4793 ( 16.78%)
Amean 4 0.9430 0.9707 ( -2.93%)
Amean 7 1.5517 1.8843 ( -21.44%)
Amean 12 2.4903 2.7267 ( -9.49%)
Amean 21 3.9560 4.2877 ( -8.38%)
Amean 30 5.4613 5.8343 ( -6.83%)
Amean 48 8.5337 9.2937 ( -8.91%)
Amean 79 14.0670 15.2630 ( -8.50%)
Amean 110 19.2253 21.2467 ( -10.51%)
Amean 141 23.7557 25.8550 ( -8.84%)
Amean 172 28.4407 29.7603 ( -4.64%)
Amean 203 33.3407 33.9927 ( -1.96%)
Amean 234 38.3633 39.1150 ( -1.96%)
Amean 265 43.4420 43.8470 ( -0.93%)
Amean 296 48.3680 48.9300 ( -1.16%)
hackbench-thread-sockets
Amean 1 0.6080 0.6493 ( -6.80%)
Amean 4 1.0000 1.0513 ( -5.13%)
Amean 7 1.6607 2.0260 ( -22.00%)
Amean 12 2.7637 2.9273 ( -5.92%)
Amean 21 5.0613 4.5153 ( 10.79%)
Amean 30 6.3340 6.1140 ( 3.47%)
Amean 48 9.0567 9.5577 ( -5.53%)
Amean 79 14.5657 15.7983 ( -8.46%)
Amean 110 19.6213 21.6333 ( -10.25%)
Amean 141 24.1563 26.2697 ( -8.75%)
Amean 172 28.9687 30.2187 ( -4.32%)
Amean 203 33.9763 34.6970 ( -2.12%)
Amean 234 38.8647 39.3207 ( -1.17%)
Amean 265 44.0813 44.1507 ( -0.16%)
Amean 296 49.2040 49.4330 ( -0.47%)
2-socket Intel(R) Xeon(R) CPU E5-2698 v4 @ 2.20GHz (20 cores, 40 threads
per socket), 512GB RAM
hackbench-process-sockets
Amean 1 0.5027 0.5017 ( 0.20%)
Amean 4 1.1053 1.2033 ( -8.87%)
Amean 7 1.8760 2.1820 ( -16.31%)
Amean 12 2.9053 3.1810 ( -9.49%)
Amean 21 4.6777 4.9920 ( -6.72%)
Amean 30 6.5180 6.7827 ( -4.06%)
Amean 48 10.0710 10.5227 ( -4.48%)
Amean 79 16.4250 17.5053 ( -6.58%)
Amean 110 22.6203 24.4617 ( -8.14%)
Amean 141 28.0967 31.0363 ( -10.46%)
Amean 172 34.4030 36.9233 ( -7.33%)
Amean 203 40.5933 43.0850 ( -6.14%)
Amean 234 46.6477 48.7220 ( -4.45%)
Amean 265 53.0530 53.9597 ( -1.71%)
Amean 296 59.2760 59.9213 ( -1.09%)
hackbench-thread-sockets
Amean 1 0.5363 0.5330 ( 0.62%)
Amean 4 1.1647 1.2157 ( -4.38%)
Amean 7 1.9237 2.2833 ( -18.70%)
Amean 12 2.9943 3.3110 ( -10.58%)
Amean 21 4.9987 5.1880 ( -3.79%)
Amean 30 6.7583 7.0043 ( -3.64%)
Amean 48 10.4547 10.8353 ( -3.64%)
Amean 79 16.6707 17.6790 ( -6.05%)
Amean 110 22.8207 24.4403 ( -7.10%)
Amean 141 28.7090 31.0533 ( -8.17%)
Amean 172 34.9387 36.8260 ( -5.40%)
Amean 203 41.1567 43.0450 ( -4.59%)
Amean 234 47.3790 48.5307 ( -2.43%)
Amean 265 53.9543 54.6987 ( -1.38%)
Amean 296 60.0820 60.2163 ( -0.22%)
1-socket Intel(R) Xeon(R) CPU E3-1240 v5 @ 3.50GHz (4 cores, 8 threads),
32 GB RAM
hackbench-process-sockets
Amean 1 1.4760 1.5773 ( -6.87%)
Amean 3 3.9370 4.0910 ( -3.91%)
Amean 5 6.6797 6.9357 ( -3.83%)
Amean 7 9.3367 9.7150 ( -4.05%)
Amean 12 15.7627 16.1400 ( -2.39%)
Amean 18 23.5360 23.6890 ( -0.65%)
Amean 24 31.0663 31.3137 ( -0.80%)
Amean 30 38.7283 39.0037 ( -0.71%)
Amean 32 41.3417 41.6097 ( -0.65%)
hackbench-thread-sockets
Amean 1 1.5250 1.6043 ( -5.20%)
Amean 3 4.0897 4.2603 ( -4.17%)
Amean 5 6.7760 7.0933 ( -4.68%)
Amean 7 9.4817 9.9157 ( -4.58%)
Amean 12 15.9610 16.3937 ( -2.71%)
Amean 18 23.9543 24.3417 ( -1.62%)
Amean 24 31.4400 31.7217 ( -0.90%)
Amean 30 39.2457 39.5467 ( -0.77%)
Amean 32 41.8267 42.1230 ( -0.71%)
2-socket Intel(R) Xeon(R) CPU E5-2670 v3 @ 2.30GHz (12 cores, 24 threads
per socket), 64GB RAM
hackbench-process-sockets
Amean 1 1.0347 1.0880 ( -5.15%)
Amean 4 1.7267 1.8527 ( -7.30%)
Amean 7 2.6707 2.8110 ( -5.25%)
Amean 12 4.1617 4.3383 ( -4.25%)
Amean 21 7.0070 7.2600 ( -3.61%)
Amean 30 9.9187 10.2397 ( -3.24%)
Amean 48 15.6710 16.3923 ( -4.60%)
Amean 79 24.7743 26.1247 ( -5.45%)
Amean 110 34.3000 35.9307 ( -4.75%)
Amean 141 44.2043 44.8010 ( -1.35%)
Amean 172 54.2430 54.7260 ( -0.89%)
Amean 192 60.6557 60.9777 ( -0.53%)
hackbench-thread-sockets
Amean 1 1.0610 1.1353 ( -7.01%)
Amean 4 1.7543 1.9140 ( -9.10%)
Amean 7 2.7840 2.9573 ( -6.23%)
Amean 12 4.3813 4.4937 ( -2.56%)
Amean 21 7.3460 7.5350 ( -2.57%)
Amean 30 10.2313 10.5190 ( -2.81%)
Amean 48 15.9700 16.5940 ( -3.91%)
Amean 79 25.3973 26.6637 ( -4.99%)
Amean 110 35.1087 36.4797 ( -3.91%)
Amean 141 45.8220 46.3053 ( -1.05%)
Amean 172 55.4917 55.7320 ( -0.43%)
Amean 192 62.7490 62.5410 ( 0.33%)
Link: https://lkml.kernel.org/r/20211012134651.11258-1-vbabka@suse.cz
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reported-by: Jann Horn <jannh@google.com>
Cc: Roman Gushchin <guro@fb.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-11-05 13:35:17 -07:00
|
|
|
|
2011-08-09 16:12:27 -05:00
|
|
|
|
|
|
|
|
|
2020-12-14 19:14:57 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-08-09 16:12:27 -05:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
2020-12-14 19:14:57 -08:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2020-08-06 23:18:48 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-12-14 19:14:57 -08:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-12-14 19:14:57 -08:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-11-16 15:56:32 +01:00
|
|
|
|
usercopy: Prepare for usercopy whitelisting
This patch prepares the slab allocator to handle caches having annotations
(useroffset and usersize) defining usercopy regions.
This patch is modified from Brad Spengler/PaX Team's PAX_USERCOPY
whitelisting code in the last public patch of grsecurity/PaX based on
my understanding of the code. Changes or omissions from the original
code are mine and don't reflect the original grsecurity/PaX code.
Currently, hardened usercopy performs dynamic bounds checking on slab
cache objects. This is good, but still leaves a lot of kernel memory
available to be copied to/from userspace in the face of bugs. To further
restrict what memory is available for copying, this creates a way to
whitelist specific areas of a given slab cache object for copying to/from
userspace, allowing much finer granularity of access control. Slab caches
that are never exposed to userspace can declare no whitelist for their
objects, thereby keeping them unavailable to userspace via dynamic copy
operations. (Note, an implicit form of whitelisting is the use of constant
sizes in usercopy operations and get_user()/put_user(); these bypass
hardened usercopy checks since these sizes cannot change at runtime.)
To support this whitelist annotation, usercopy region offset and size
members are added to struct kmem_cache. The slab allocator receives a
new function, kmem_cache_create_usercopy(), that creates a new cache
with a usercopy region defined, suitable for declaring spans of fields
within the objects that get copied to/from userspace.
In this patch, the default kmem_cache_create() marks the entire allocation
as whitelisted, leaving it semantically unchanged. Once all fine-grained
whitelists have been added (in subsequent patches), this will be changed
to a usersize of 0, making caches created with kmem_cache_create() not
copyable to/from userspace.
After the entire usercopy whitelist series is applied, less than 15%
of the slab cache memory remains exposed to potential usercopy bugs
after a fresh boot:
Total Slab Memory: 48074720
Usercopyable Memory: 6367532 13.2%
task_struct 0.2% 4480/1630720
RAW 0.3% 300/96000
RAWv6 2.1% 1408/64768
ext4_inode_cache 3.0% 269760/8740224
dentry 11.1% 585984/5273856
mm_struct 29.1% 54912/188448
kmalloc-8 100.0% 24576/24576
kmalloc-16 100.0% 28672/28672
kmalloc-32 100.0% 81920/81920
kmalloc-192 100.0% 96768/96768
kmalloc-128 100.0% 143360/143360
names_cache 100.0% 163840/163840
kmalloc-64 100.0% 167936/167936
kmalloc-256 100.0% 339968/339968
kmalloc-512 100.0% 350720/350720
kmalloc-96 100.0% 455616/455616
kmalloc-8192 100.0% 655360/655360
kmalloc-1024 100.0% 812032/812032
kmalloc-4096 100.0% 819200/819200
kmalloc-2048 100.0% 1310720/1310720
After some kernel build workloads, the percentage (mainly driven by
dentry and inode caches expanding) drops under 10%:
Total Slab Memory: 95516184
Usercopyable Memory: 8497452 8.8%
task_struct 0.2% 4000/1456000
RAW 0.3% 300/96000
RAWv6 2.1% 1408/64768
ext4_inode_cache 3.0% 1217280/39439872
dentry 11.1% 1623200/14608800
mm_struct 29.1% 73216/251264
kmalloc-8 100.0% 24576/24576
kmalloc-16 100.0% 28672/28672
kmalloc-32 100.0% 94208/94208
kmalloc-192 100.0% 96768/96768
kmalloc-128 100.0% 143360/143360
names_cache 100.0% 163840/163840
kmalloc-64 100.0% 245760/245760
kmalloc-256 100.0% 339968/339968
kmalloc-512 100.0% 350720/350720
kmalloc-96 100.0% 563520/563520
kmalloc-8192 100.0% 655360/655360
kmalloc-1024 100.0% 794624/794624
kmalloc-4096 100.0% 819200/819200
kmalloc-2048 100.0% 1257472/1257472
Signed-off-by: David Windsor <dave@nullcore.net>
[kees: adjust commit log, split out a few extra kmalloc hunks]
[kees: add field names to function declarations]
[kees: convert BUGs to WARNs and fail closed]
[kees: add attack surface reduction analysis to commit log]
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: linux-mm@kvack.org
Cc: linux-xfs@vger.kernel.org
Signed-off-by: Kees Cook <keescook@chromium.org>
Acked-by: Christoph Lameter <cl@linux.com>
2017-06-10 22:50:28 -04:00
|
|
|
|
|
|
|
|
|
2020-12-14 19:14:57 -08:00
|
|
|
|
usercopy: Prepare for usercopy whitelisting
This patch prepares the slab allocator to handle caches having annotations
(useroffset and usersize) defining usercopy regions.
This patch is modified from Brad Spengler/PaX Team's PAX_USERCOPY
whitelisting code in the last public patch of grsecurity/PaX based on
my understanding of the code. Changes or omissions from the original
code are mine and don't reflect the original grsecurity/PaX code.
Currently, hardened usercopy performs dynamic bounds checking on slab
cache objects. This is good, but still leaves a lot of kernel memory
available to be copied to/from userspace in the face of bugs. To further
restrict what memory is available for copying, this creates a way to
whitelist specific areas of a given slab cache object for copying to/from
userspace, allowing much finer granularity of access control. Slab caches
that are never exposed to userspace can declare no whitelist for their
objects, thereby keeping them unavailable to userspace via dynamic copy
operations. (Note, an implicit form of whitelisting is the use of constant
sizes in usercopy operations and get_user()/put_user(); these bypass
hardened usercopy checks since these sizes cannot change at runtime.)
To support this whitelist annotation, usercopy region offset and size
members are added to struct kmem_cache. The slab allocator receives a
new function, kmem_cache_create_usercopy(), that creates a new cache
with a usercopy region defined, suitable for declaring spans of fields
within the objects that get copied to/from userspace.
In this patch, the default kmem_cache_create() marks the entire allocation
as whitelisted, leaving it semantically unchanged. Once all fine-grained
whitelists have been added (in subsequent patches), this will be changed
to a usersize of 0, making caches created with kmem_cache_create() not
copyable to/from userspace.
After the entire usercopy whitelist series is applied, less than 15%
of the slab cache memory remains exposed to potential usercopy bugs
after a fresh boot:
Total Slab Memory: 48074720
Usercopyable Memory: 6367532 13.2%
task_struct 0.2% 4480/1630720
RAW 0.3% 300/96000
RAWv6 2.1% 1408/64768
ext4_inode_cache 3.0% 269760/8740224
dentry 11.1% 585984/5273856
mm_struct 29.1% 54912/188448
kmalloc-8 100.0% 24576/24576
kmalloc-16 100.0% 28672/28672
kmalloc-32 100.0% 81920/81920
kmalloc-192 100.0% 96768/96768
kmalloc-128 100.0% 143360/143360
names_cache 100.0% 163840/163840
kmalloc-64 100.0% 167936/167936
kmalloc-256 100.0% 339968/339968
kmalloc-512 100.0% 350720/350720
kmalloc-96 100.0% 455616/455616
kmalloc-8192 100.0% 655360/655360
kmalloc-1024 100.0% 812032/812032
kmalloc-4096 100.0% 819200/819200
kmalloc-2048 100.0% 1310720/1310720
After some kernel build workloads, the percentage (mainly driven by
dentry and inode caches expanding) drops under 10%:
Total Slab Memory: 95516184
Usercopyable Memory: 8497452 8.8%
task_struct 0.2% 4000/1456000
RAW 0.3% 300/96000
RAWv6 2.1% 1408/64768
ext4_inode_cache 3.0% 1217280/39439872
dentry 11.1% 1623200/14608800
mm_struct 29.1% 73216/251264
kmalloc-8 100.0% 24576/24576
kmalloc-16 100.0% 28672/28672
kmalloc-32 100.0% 94208/94208
kmalloc-192 100.0% 96768/96768
kmalloc-128 100.0% 143360/143360
names_cache 100.0% 163840/163840
kmalloc-64 100.0% 245760/245760
kmalloc-256 100.0% 339968/339968
kmalloc-512 100.0% 350720/350720
kmalloc-96 100.0% 563520/563520
kmalloc-8192 100.0% 655360/655360
kmalloc-1024 100.0% 794624/794624
kmalloc-4096 100.0% 819200/819200
kmalloc-2048 100.0% 1257472/1257472
Signed-off-by: David Windsor <dave@nullcore.net>
[kees: adjust commit log, split out a few extra kmalloc hunks]
[kees: add field names to function declarations]
[kees: convert BUGs to WARNs and fail closed]
[kees: add attack surface reduction analysis to commit log]
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: linux-mm@kvack.org
Cc: linux-xfs@vger.kernel.org
Signed-off-by: Kees Cook <keescook@chromium.org>
Acked-by: Christoph Lameter <cl@linux.com>
2017-06-10 22:50:28 -04:00
|
|
|
|
|
|
|
|
|
2022-11-16 15:56:32 +01:00
|
|
|
|
usercopy: Prepare for usercopy whitelisting
This patch prepares the slab allocator to handle caches having annotations
(useroffset and usersize) defining usercopy regions.
This patch is modified from Brad Spengler/PaX Team's PAX_USERCOPY
whitelisting code in the last public patch of grsecurity/PaX based on
my understanding of the code. Changes or omissions from the original
code are mine and don't reflect the original grsecurity/PaX code.
Currently, hardened usercopy performs dynamic bounds checking on slab
cache objects. This is good, but still leaves a lot of kernel memory
available to be copied to/from userspace in the face of bugs. To further
restrict what memory is available for copying, this creates a way to
whitelist specific areas of a given slab cache object for copying to/from
userspace, allowing much finer granularity of access control. Slab caches
that are never exposed to userspace can declare no whitelist for their
objects, thereby keeping them unavailable to userspace via dynamic copy
operations. (Note, an implicit form of whitelisting is the use of constant
sizes in usercopy operations and get_user()/put_user(); these bypass
hardened usercopy checks since these sizes cannot change at runtime.)
To support this whitelist annotation, usercopy region offset and size
members are added to struct kmem_cache. The slab allocator receives a
new function, kmem_cache_create_usercopy(), that creates a new cache
with a usercopy region defined, suitable for declaring spans of fields
within the objects that get copied to/from userspace.
In this patch, the default kmem_cache_create() marks the entire allocation
as whitelisted, leaving it semantically unchanged. Once all fine-grained
whitelists have been added (in subsequent patches), this will be changed
to a usersize of 0, making caches created with kmem_cache_create() not
copyable to/from userspace.
After the entire usercopy whitelist series is applied, less than 15%
of the slab cache memory remains exposed to potential usercopy bugs
after a fresh boot:
Total Slab Memory: 48074720
Usercopyable Memory: 6367532 13.2%
task_struct 0.2% 4480/1630720
RAW 0.3% 300/96000
RAWv6 2.1% 1408/64768
ext4_inode_cache 3.0% 269760/8740224
dentry 11.1% 585984/5273856
mm_struct 29.1% 54912/188448
kmalloc-8 100.0% 24576/24576
kmalloc-16 100.0% 28672/28672
kmalloc-32 100.0% 81920/81920
kmalloc-192 100.0% 96768/96768
kmalloc-128 100.0% 143360/143360
names_cache 100.0% 163840/163840
kmalloc-64 100.0% 167936/167936
kmalloc-256 100.0% 339968/339968
kmalloc-512 100.0% 350720/350720
kmalloc-96 100.0% 455616/455616
kmalloc-8192 100.0% 655360/655360
kmalloc-1024 100.0% 812032/812032
kmalloc-4096 100.0% 819200/819200
kmalloc-2048 100.0% 1310720/1310720
After some kernel build workloads, the percentage (mainly driven by
dentry and inode caches expanding) drops under 10%:
Total Slab Memory: 95516184
Usercopyable Memory: 8497452 8.8%
task_struct 0.2% 4000/1456000
RAW 0.3% 300/96000
RAWv6 2.1% 1408/64768
ext4_inode_cache 3.0% 1217280/39439872
dentry 11.1% 1623200/14608800
mm_struct 29.1% 73216/251264
kmalloc-8 100.0% 24576/24576
kmalloc-16 100.0% 28672/28672
kmalloc-32 100.0% 94208/94208
kmalloc-192 100.0% 96768/96768
kmalloc-128 100.0% 143360/143360
names_cache 100.0% 163840/163840
kmalloc-64 100.0% 245760/245760
kmalloc-256 100.0% 339968/339968
kmalloc-512 100.0% 350720/350720
kmalloc-96 100.0% 563520/563520
kmalloc-8192 100.0% 655360/655360
kmalloc-1024 100.0% 794624/794624
kmalloc-4096 100.0% 819200/819200
kmalloc-2048 100.0% 1257472/1257472
Signed-off-by: David Windsor <dave@nullcore.net>
[kees: adjust commit log, split out a few extra kmalloc hunks]
[kees: add field names to function declarations]
[kees: convert BUGs to WARNs and fail closed]
[kees: add attack surface reduction analysis to commit log]
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: linux-mm@kvack.org
Cc: linux-xfs@vger.kernel.org
Signed-off-by: Kees Cook <keescook@chromium.org>
Acked-by: Christoph Lameter <cl@linux.com>
2017-06-10 22:50:28 -04:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
2020-12-14 19:14:57 -08:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2010-10-05 13:57:26 -05:00
|
|
|
|
2010-10-05 13:57:27 -05:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-04-13 22:34:49 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2010-10-05 13:57:27 -05:00
|
|
|
|
|
|
|
|
|
2020-12-14 19:14:57 -08:00
|
|
|
|
2010-10-05 13:57:27 -05:00
|
|
|
|
2020-08-06 23:18:45 -07:00
|
|
|
|
2010-10-05 13:57:27 -05:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-12-14 19:14:57 -08:00
|
|
|
|
2010-10-05 13:57:27 -05:00
|
|
|
|
2020-08-06 23:18:45 -07:00
|
|
|
|
2010-10-05 13:57:27 -05:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
2020-12-14 19:14:57 -08:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
mm, slub: make some slub_debug related attributes read-only
SLUB_DEBUG creates several files under /sys/kernel/slab/<cache>/ that can
be read to check if the respective debugging options are enabled for given
cache. The options can be also toggled at runtime by writing into the
files. Some of those, namely red_zone, poison, and store_user can be
toggled only when no objects yet exist in the cache.
Vijayanand reports [1] that there is a problem with freelist randomization
if changing the debugging option's state results in different number of
objects per page, and the random sequence cache needs thus needs to be
recomputed.
However, another problem is that the check for "no objects yet exist in
the cache" is racy, as noted by Jann [2] and fixing that would add
overhead or otherwise complicate the allocation/freeing paths. Thus it
would be much simpler just to remove the runtime toggling support. The
documentation describes it's "In case you forgot to enable debugging on
the kernel command line", but the neccessity of having no objects limits
its usefulness anyway for many caches.
Vijayanand describes an use case [3] where debugging is enabled for all
but zram caches for memory overhead reasons, and using the runtime toggles
was the only way to achieve such configuration. After the previous patch
it's now possible to do that directly from the kernel boot option, so we
can remove the dangerous runtime toggles by making the /sys attribute
files read-only.
While updating it, also improve the documentation of the debugging /sys files.
[1] https://lkml.kernel.org/r/1580379523-32272-1-git-send-email-vjitta@codeaurora.org
[2] https://lore.kernel.org/r/CAG48ez31PP--h6_FzVyfJ4H86QYczAFPdxtJHUEEan+7VJETAQ@mail.gmail.com
[3] https://lore.kernel.org/r/1383cd32-1ddc-4dac-b5f8-9c42282fa81c@codeaurora.org
Reported-by: Vijayanand Jitta <vjitta@codeaurora.org>
Reported-by: Jann Horn <jannh@google.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Kees Cook <keescook@chromium.org>
Acked-by: Roman Gushchin <guro@fb.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Pekka Enberg <penberg@kernel.org>
Link: http://lkml.kernel.org/r/20200610163135.17364-3-vbabka@suse.cz
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-08-06 23:18:38 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-12-14 19:14:57 -08:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
mm, slub: make some slub_debug related attributes read-only
SLUB_DEBUG creates several files under /sys/kernel/slab/<cache>/ that can
be read to check if the respective debugging options are enabled for given
cache. The options can be also toggled at runtime by writing into the
files. Some of those, namely red_zone, poison, and store_user can be
toggled only when no objects yet exist in the cache.
Vijayanand reports [1] that there is a problem with freelist randomization
if changing the debugging option's state results in different number of
objects per page, and the random sequence cache needs thus needs to be
recomputed.
However, another problem is that the check for "no objects yet exist in
the cache" is racy, as noted by Jann [2] and fixing that would add
overhead or otherwise complicate the allocation/freeing paths. Thus it
would be much simpler just to remove the runtime toggling support. The
documentation describes it's "In case you forgot to enable debugging on
the kernel command line", but the neccessity of having no objects limits
its usefulness anyway for many caches.
Vijayanand describes an use case [3] where debugging is enabled for all
but zram caches for memory overhead reasons, and using the runtime toggles
was the only way to achieve such configuration. After the previous patch
it's now possible to do that directly from the kernel boot option, so we
can remove the dangerous runtime toggles by making the /sys attribute
files read-only.
While updating it, also improve the documentation of the debugging /sys files.
[1] https://lkml.kernel.org/r/1580379523-32272-1-git-send-email-vjitta@codeaurora.org
[2] https://lore.kernel.org/r/CAG48ez31PP--h6_FzVyfJ4H86QYczAFPdxtJHUEEan+7VJETAQ@mail.gmail.com
[3] https://lore.kernel.org/r/1383cd32-1ddc-4dac-b5f8-9c42282fa81c@codeaurora.org
Reported-by: Vijayanand Jitta <vjitta@codeaurora.org>
Reported-by: Jann Horn <jannh@google.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Kees Cook <keescook@chromium.org>
Acked-by: Roman Gushchin <guro@fb.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Pekka Enberg <penberg@kernel.org>
Link: http://lkml.kernel.org/r/20200610163135.17364-3-vbabka@suse.cz
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-08-06 23:18:38 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-12-14 19:14:57 -08:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
mm, slub: make some slub_debug related attributes read-only
SLUB_DEBUG creates several files under /sys/kernel/slab/<cache>/ that can
be read to check if the respective debugging options are enabled for given
cache. The options can be also toggled at runtime by writing into the
files. Some of those, namely red_zone, poison, and store_user can be
toggled only when no objects yet exist in the cache.
Vijayanand reports [1] that there is a problem with freelist randomization
if changing the debugging option's state results in different number of
objects per page, and the random sequence cache needs thus needs to be
recomputed.
However, another problem is that the check for "no objects yet exist in
the cache" is racy, as noted by Jann [2] and fixing that would add
overhead or otherwise complicate the allocation/freeing paths. Thus it
would be much simpler just to remove the runtime toggling support. The
documentation describes it's "In case you forgot to enable debugging on
the kernel command line", but the neccessity of having no objects limits
its usefulness anyway for many caches.
Vijayanand describes an use case [3] where debugging is enabled for all
but zram caches for memory overhead reasons, and using the runtime toggles
was the only way to achieve such configuration. After the previous patch
it's now possible to do that directly from the kernel boot option, so we
can remove the dangerous runtime toggles by making the /sys attribute
files read-only.
While updating it, also improve the documentation of the debugging /sys files.
[1] https://lkml.kernel.org/r/1580379523-32272-1-git-send-email-vjitta@codeaurora.org
[2] https://lore.kernel.org/r/CAG48ez31PP--h6_FzVyfJ4H86QYczAFPdxtJHUEEan+7VJETAQ@mail.gmail.com
[3] https://lore.kernel.org/r/1383cd32-1ddc-4dac-b5f8-9c42282fa81c@codeaurora.org
Reported-by: Vijayanand Jitta <vjitta@codeaurora.org>
Reported-by: Jann Horn <jannh@google.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Kees Cook <keescook@chromium.org>
Acked-by: Roman Gushchin <guro@fb.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Pekka Enberg <penberg@kernel.org>
Link: http://lkml.kernel.org/r/20200610163135.17364-3-vbabka@suse.cz
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-08-06 23:18:38 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2007-05-06 14:49:43 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-07-17 04:03:30 -07:00
|
|
|
|
|
|
|
|
|
mm/slub: restrict sysfs validation to debug caches and make it safe
Rongwei Wang reports [1] that cache validation triggered by writing to
/sys/kernel/slab/<cache>/validate is racy against normal cache
operations (e.g. freeing) in a way that can cause false positive
inconsistency reports for caches with debugging enabled. The problem is
that debugging actions that mark object free or active and actual
freelist operations are not atomic, and the validation can see an
inconsistent state.
For caches that do or don't have debugging enabled, additional races
involving n->nr_slabs are possible that result in false reports of wrong
slab counts.
This patch attempts to solve these issues while not adding overhead to
normal (especially fastpath) operations for caches that do not have
debugging enabled. Such overhead would not be justified to make possible
userspace-triggered validation safe. Instead, disable the validation for
caches that don't have debugging enabled and make their sysfs validate
handler return -EINVAL.
For caches that do have debugging enabled, we can instead extend the
existing approach of not using percpu freelists to force all alloc/free
operations to the slow paths where debugging flags is checked and acted
upon. There can adjust the debug-specific paths to increase n->list_lock
coverage against concurrent validation as necessary.
The processing on free in free_debug_processing() already happens under
n->list_lock so we can extend it to actually do the freeing as well and
thus make it atomic against concurrent validation. As observed by
Hyeonggon Yoo, we do not really need to take slab_lock() anymore here
because all paths we could race with are protected by n->list_lock under
the new scheme, so drop its usage here.
The processing on alloc in alloc_debug_processing() currently doesn't
take any locks, but we have to first allocate the object from a slab on
the partial list (as debugging caches have no percpu slabs) and thus
take the n->list_lock anyway. Add a function alloc_single_from_partial()
that grabs just the allocated object instead of the whole freelist, and
does the debug processing. The n->list_lock coverage again makes it
atomic against validation and it is also ultimately more efficient than
the current grabbing of freelist immediately followed by slab
deactivation.
To prevent races on n->nr_slabs updates, make sure that for caches with
debugging enabled, inc_slabs_node() or dec_slabs_node() is called under
n->list_lock. When allocating a new slab for a debug cache, handle the
allocation by a new function alloc_single_from_new_slab() instead of the
current forced deactivation path.
Neither of these changes affect the fast paths at all. The changes in
slow paths are negligible for non-debug caches.
[1] https://lore.kernel.org/all/20220529081535.69275-1-rongwei.wang@linux.alibaba.com/
Reported-by: Rongwei Wang <rongwei.wang@linux.alibaba.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
2022-08-23 19:03:57 +02:00
|
|
|
|
2007-07-17 04:03:30 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:43 -07:00
|
|
|
|
|
|
|
|
|
2010-10-05 13:57:27 -05:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-12-14 19:14:57 -08:00
|
|
|
|
2010-10-05 13:57:27 -05:00
|
|
|
|
2022-09-20 15:11:11 +03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2010-10-05 13:57:26 -05:00
|
|
|
|
2007-05-06 14:49:43 -07:00
|
|
|
|
2007-05-06 14:49:46 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-02-12 14:59:41 -08:00
|
|
|
|
2020-08-06 23:21:27 -07:00
|
|
|
|
2015-02-12 14:59:41 -08:00
|
|
|
|
2007-05-06 14:49:46 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2008-01-07 23:20:26 -08:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2020-12-14 19:14:57 -08:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
2008-01-07 23:20:26 -08:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
2018-04-05 16:20:48 -07:00
|
|
|
|
2008-04-29 16:11:12 -07:00
|
|
|
|
|
|
|
|
|
2018-04-05 16:20:48 -07:00
|
|
|
|
2008-04-29 16:11:12 -07:00
|
|
|
|
|
|
|
|
|
2018-04-05 16:20:48 -07:00
|
|
|
|
|
|
|
|
|
2008-04-29 16:11:12 -07:00
|
|
|
|
2018-04-05 16:20:48 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-01-07 23:20:26 -08:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
2008-02-07 17:47:41 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-12-14 19:14:57 -08:00
|
|
|
|
treewide: kmalloc() -> kmalloc_array()
The kmalloc() function has a 2-factor argument form, kmalloc_array(). This
patch replaces cases of:
kmalloc(a * b, gfp)
with:
kmalloc_array(a * b, gfp)
as well as handling cases of:
kmalloc(a * b * c, gfp)
with:
kmalloc(array3_size(a, b, c), gfp)
as it's slightly less ugly than:
kmalloc_array(array_size(a, b), c, gfp)
This does, however, attempt to ignore constant size factors like:
kmalloc(4 * 1024, gfp)
though any constants defined via macros get caught up in the conversion.
Any factors with a sizeof() of "unsigned char", "char", and "u8" were
dropped, since they're redundant.
The tools/ directory was manually excluded, since it has its own
implementation of kmalloc().
The Coccinelle script used for this was:
// Fix redundant parens around sizeof().
@@
type TYPE;
expression THING, E;
@@
(
kmalloc(
- (sizeof(TYPE)) * E
+ sizeof(TYPE) * E
, ...)
|
kmalloc(
- (sizeof(THING)) * E
+ sizeof(THING) * E
, ...)
)
// Drop single-byte sizes and redundant parens.
@@
expression COUNT;
typedef u8;
typedef __u8;
@@
(
kmalloc(
- sizeof(u8) * (COUNT)
+ COUNT
, ...)
|
kmalloc(
- sizeof(__u8) * (COUNT)
+ COUNT
, ...)
|
kmalloc(
- sizeof(char) * (COUNT)
+ COUNT
, ...)
|
kmalloc(
- sizeof(unsigned char) * (COUNT)
+ COUNT
, ...)
|
kmalloc(
- sizeof(u8) * COUNT
+ COUNT
, ...)
|
kmalloc(
- sizeof(__u8) * COUNT
+ COUNT
, ...)
|
kmalloc(
- sizeof(char) * COUNT
+ COUNT
, ...)
|
kmalloc(
- sizeof(unsigned char) * COUNT
+ COUNT
, ...)
)
// 2-factor product with sizeof(type/expression) and identifier or constant.
@@
type TYPE;
expression THING;
identifier COUNT_ID;
constant COUNT_CONST;
@@
(
- kmalloc
+ kmalloc_array
(
- sizeof(TYPE) * (COUNT_ID)
+ COUNT_ID, sizeof(TYPE)
, ...)
|
- kmalloc
+ kmalloc_array
(
- sizeof(TYPE) * COUNT_ID
+ COUNT_ID, sizeof(TYPE)
, ...)
|
- kmalloc
+ kmalloc_array
(
- sizeof(TYPE) * (COUNT_CONST)
+ COUNT_CONST, sizeof(TYPE)
, ...)
|
- kmalloc
+ kmalloc_array
(
- sizeof(TYPE) * COUNT_CONST
+ COUNT_CONST, sizeof(TYPE)
, ...)
|
- kmalloc
+ kmalloc_array
(
- sizeof(THING) * (COUNT_ID)
+ COUNT_ID, sizeof(THING)
, ...)
|
- kmalloc
+ kmalloc_array
(
- sizeof(THING) * COUNT_ID
+ COUNT_ID, sizeof(THING)
, ...)
|
- kmalloc
+ kmalloc_array
(
- sizeof(THING) * (COUNT_CONST)
+ COUNT_CONST, sizeof(THING)
, ...)
|
- kmalloc
+ kmalloc_array
(
- sizeof(THING) * COUNT_CONST
+ COUNT_CONST, sizeof(THING)
, ...)
)
// 2-factor product, only identifiers.
@@
identifier SIZE, COUNT;
@@
- kmalloc
+ kmalloc_array
(
- SIZE * COUNT
+ COUNT, SIZE
, ...)
// 3-factor product with 1 sizeof(type) or sizeof(expression), with
// redundant parens removed.
@@
expression THING;
identifier STRIDE, COUNT;
type TYPE;
@@
(
kmalloc(
- sizeof(TYPE) * (COUNT) * (STRIDE)
+ array3_size(COUNT, STRIDE, sizeof(TYPE))
, ...)
|
kmalloc(
- sizeof(TYPE) * (COUNT) * STRIDE
+ array3_size(COUNT, STRIDE, sizeof(TYPE))
, ...)
|
kmalloc(
- sizeof(TYPE) * COUNT * (STRIDE)
+ array3_size(COUNT, STRIDE, sizeof(TYPE))
, ...)
|
kmalloc(
- sizeof(TYPE) * COUNT * STRIDE
+ array3_size(COUNT, STRIDE, sizeof(TYPE))
, ...)
|
kmalloc(
- sizeof(THING) * (COUNT) * (STRIDE)
+ array3_size(COUNT, STRIDE, sizeof(THING))
, ...)
|
kmalloc(
- sizeof(THING) * (COUNT) * STRIDE
+ array3_size(COUNT, STRIDE, sizeof(THING))
, ...)
|
kmalloc(
- sizeof(THING) * COUNT * (STRIDE)
+ array3_size(COUNT, STRIDE, sizeof(THING))
, ...)
|
kmalloc(
- sizeof(THING) * COUNT * STRIDE
+ array3_size(COUNT, STRIDE, sizeof(THING))
, ...)
)
// 3-factor product with 2 sizeof(variable), with redundant parens removed.
@@
expression THING1, THING2;
identifier COUNT;
type TYPE1, TYPE2;
@@
(
kmalloc(
- sizeof(TYPE1) * sizeof(TYPE2) * COUNT
+ array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2))
, ...)
|
kmalloc(
- sizeof(TYPE1) * sizeof(THING2) * (COUNT)
+ array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2))
, ...)
|
kmalloc(
- sizeof(THING1) * sizeof(THING2) * COUNT
+ array3_size(COUNT, sizeof(THING1), sizeof(THING2))
, ...)
|
kmalloc(
- sizeof(THING1) * sizeof(THING2) * (COUNT)
+ array3_size(COUNT, sizeof(THING1), sizeof(THING2))
, ...)
|
kmalloc(
- sizeof(TYPE1) * sizeof(THING2) * COUNT
+ array3_size(COUNT, sizeof(TYPE1), sizeof(THING2))
, ...)
|
kmalloc(
- sizeof(TYPE1) * sizeof(THING2) * (COUNT)
+ array3_size(COUNT, sizeof(TYPE1), sizeof(THING2))
, ...)
)
// 3-factor product, only identifiers, with redundant parens removed.
@@
identifier STRIDE, SIZE, COUNT;
@@
(
kmalloc(
- (COUNT) * STRIDE * SIZE
+ array3_size(COUNT, STRIDE, SIZE)
, ...)
|
kmalloc(
- COUNT * (STRIDE) * SIZE
+ array3_size(COUNT, STRIDE, SIZE)
, ...)
|
kmalloc(
- COUNT * STRIDE * (SIZE)
+ array3_size(COUNT, STRIDE, SIZE)
, ...)
|
kmalloc(
- (COUNT) * (STRIDE) * SIZE
+ array3_size(COUNT, STRIDE, SIZE)
, ...)
|
kmalloc(
- COUNT * (STRIDE) * (SIZE)
+ array3_size(COUNT, STRIDE, SIZE)
, ...)
|
kmalloc(
- (COUNT) * STRIDE * (SIZE)
+ array3_size(COUNT, STRIDE, SIZE)
, ...)
|
kmalloc(
- (COUNT) * (STRIDE) * (SIZE)
+ array3_size(COUNT, STRIDE, SIZE)
, ...)
|
kmalloc(
- COUNT * STRIDE * SIZE
+ array3_size(COUNT, STRIDE, SIZE)
, ...)
)
// Any remaining multi-factor products, first at least 3-factor products,
// when they're not all constants...
@@
expression E1, E2, E3;
constant C1, C2, C3;
@@
(
kmalloc(C1 * C2 * C3, ...)
|
kmalloc(
- (E1) * E2 * E3
+ array3_size(E1, E2, E3)
, ...)
|
kmalloc(
- (E1) * (E2) * E3
+ array3_size(E1, E2, E3)
, ...)
|
kmalloc(
- (E1) * (E2) * (E3)
+ array3_size(E1, E2, E3)
, ...)
|
kmalloc(
- E1 * E2 * E3
+ array3_size(E1, E2, E3)
, ...)
)
// And then all remaining 2 factors products when they're not all constants,
// keeping sizeof() as the second factor argument.
@@
expression THING, E1, E2;
type TYPE;
constant C1, C2, C3;
@@
(
kmalloc(sizeof(THING) * C2, ...)
|
kmalloc(sizeof(TYPE) * C2, ...)
|
kmalloc(C1 * C2 * C3, ...)
|
kmalloc(C1 * C2, ...)
|
- kmalloc
+ kmalloc_array
(
- sizeof(TYPE) * (E2)
+ E2, sizeof(TYPE)
, ...)
|
- kmalloc
+ kmalloc_array
(
- sizeof(TYPE) * E2
+ E2, sizeof(TYPE)
, ...)
|
- kmalloc
+ kmalloc_array
(
- sizeof(THING) * (E2)
+ E2, sizeof(THING)
, ...)
|
- kmalloc
+ kmalloc_array
(
- sizeof(THING) * E2
+ E2, sizeof(THING)
, ...)
|
- kmalloc
+ kmalloc_array
(
- (E1) * E2
+ E1, E2
, ...)
|
- kmalloc
+ kmalloc_array
(
- (E1) * (E2)
+ E1, E2
, ...)
|
- kmalloc
+ kmalloc_array
(
- E1 * E2
+ E1, E2
, ...)
)
Signed-off-by: Kees Cook <keescook@chromium.org>
2018-06-12 13:55:00 -07:00
|
|
|
|
2008-02-07 17:47:41 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2009-12-18 16:26:20 -06:00
|
|
|
|
2008-02-07 17:47:41 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2020-12-14 19:14:57 -08:00
|
|
|
|
2008-02-07 17:47:41 -08:00
|
|
|
|
2008-04-14 18:52:05 +03:00
|
|
|
|
2008-02-07 17:47:41 -08:00
|
|
|
|
2020-12-14 19:14:57 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-02-07 17:47:41 -08:00
|
|
|
|
2008-04-14 18:52:05 +03:00
|
|
|
|
2008-02-07 17:47:41 -08:00
|
|
|
|
2020-12-14 19:14:57 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-02-07 17:47:41 -08:00
|
|
|
|
|
|
|
|
|
2009-10-15 02:20:22 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2009-12-18 16:26:20 -06:00
|
|
|
|
2009-10-15 02:20:22 -07:00
|
|
|
|
|
|
|
|
|
2008-02-07 17:47:41 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2009-10-15 02:20:22 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-02-07 17:47:41 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-06-01 12:25:57 -05:00
|
|
|
|
2008-02-07 17:47:41 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-06-01 12:25:58 -05:00
|
|
|
|
2008-04-14 19:11:40 +03:00
|
|
|
|
2011-06-01 12:25:49 -05:00
|
|
|
|
|
|
|
|
|
2011-08-09 16:12:27 -05:00
|
|
|
|
|
|
|
|
|
2012-02-03 23:34:56 +08:00
|
|
|
|
|
|
|
|
|
2019-05-13 17:16:09 -07:00
|
|
|
|
2008-02-07 17:47:41 -08:00
|
|
|
|
2022-08-15 05:53:53 +10:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-01-07 23:20:27 -08:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
slub: add min_partial sysfs tunable
Now that a cache's min_partial has been moved to struct kmem_cache, it's
possible to easily tune it from userspace by adding a sysfs attribute.
It may not be desirable to keep a large number of partial slabs around
if a cache is used infrequently and memory, especially when constrained
by a cgroup, is scarce. It's better to allow userspace to set the
minimum policy per cache instead of relying explicitly on
kmem_cache_shrink().
The memory savings from simply moving min_partial from struct
kmem_cache_node to struct kmem_cache is obviously not significant
(unless maybe you're from SGI or something), at the largest it's
# allocated caches * (MAX_NUMNODES - 1) * sizeof(unsigned long)
The true savings occurs when userspace reduces the number of partial
slabs that would otherwise be wasted, especially on machines with a
large number of nodes (ia64 with CONFIG_NODES_SHIFT at 10 for default?).
As well as the kernel estimates ideal values for n->min_partial and
ensures it's within a sane range, userspace has no other input other
than writing to /sys/kernel/slab/cache/shrink.
There simply isn't any better heuristic to add when calculating the
partial values for a better estimate that works for all possible caches.
And since it's currently a static value, the user really has no way of
reclaiming that wasted space, which can be significant when constrained
by a cgroup (either cpusets or, later, memory controller slab limits)
without shrinking it entirely.
This also allows the user to specify that increased fragmentation and
more partial slabs are actually desired to avoid the cost of allocating
new slabs at runtime for specific caches.
There's also no reason why this should be a per-struct kmem_cache_node
value in the first place. You could argue that a machine would have
such node size asymmetries that it should be specified on a per-node
basis, but we know nobody is doing that right now since it's a purely
static value at the moment and there's no convenient way to tune that
via slub's sysfs interface.
Cc: Christoph Lameter <cl@linux-foundation.org>
Signed-off-by: David Rientjes <rientjes@google.com>
Signed-off-by: Pekka Enberg <penberg@cs.helsinki.fi>
2009-02-22 17:40:09 -08:00
|
|
|
|
2011-08-09 16:12:27 -05:00
|
|
|
|
2008-04-14 19:11:40 +03:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2010-10-05 13:57:27 -05:00
|
|
|
|
2011-08-09 16:12:27 -05:00
|
|
|
|
2010-10-05 13:57:26 -05:00
|
|
|
|
2010-10-05 13:57:27 -05:00
|
|
|
|
2023-04-13 22:34:49 +08:00
|
|
|
|
2010-10-05 13:57:27 -05:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:43 -07:00
|
|
|
|
2010-10-05 13:57:26 -05:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-01-07 23:20:26 -08:00
|
|
|
|
2008-02-07 17:47:41 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-06-01 12:25:57 -05:00
|
|
|
|
2008-02-07 17:47:41 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-06-01 12:25:58 -05:00
|
|
|
|
2008-04-14 19:11:40 +03:00
|
|
|
|
2011-06-01 12:25:49 -05:00
|
|
|
|
|
|
|
|
|
2011-08-09 16:12:27 -05:00
|
|
|
|
|
|
|
|
|
2012-02-03 23:34:56 +08:00
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2010-02-26 09:36:12 +03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-11-16 15:56:32 +01:00
|
|
|
|
usercopy: Prepare for usercopy whitelisting
This patch prepares the slab allocator to handle caches having annotations
(useroffset and usersize) defining usercopy regions.
This patch is modified from Brad Spengler/PaX Team's PAX_USERCOPY
whitelisting code in the last public patch of grsecurity/PaX based on
my understanding of the code. Changes or omissions from the original
code are mine and don't reflect the original grsecurity/PaX code.
Currently, hardened usercopy performs dynamic bounds checking on slab
cache objects. This is good, but still leaves a lot of kernel memory
available to be copied to/from userspace in the face of bugs. To further
restrict what memory is available for copying, this creates a way to
whitelist specific areas of a given slab cache object for copying to/from
userspace, allowing much finer granularity of access control. Slab caches
that are never exposed to userspace can declare no whitelist for their
objects, thereby keeping them unavailable to userspace via dynamic copy
operations. (Note, an implicit form of whitelisting is the use of constant
sizes in usercopy operations and get_user()/put_user(); these bypass
hardened usercopy checks since these sizes cannot change at runtime.)
To support this whitelist annotation, usercopy region offset and size
members are added to struct kmem_cache. The slab allocator receives a
new function, kmem_cache_create_usercopy(), that creates a new cache
with a usercopy region defined, suitable for declaring spans of fields
within the objects that get copied to/from userspace.
In this patch, the default kmem_cache_create() marks the entire allocation
as whitelisted, leaving it semantically unchanged. Once all fine-grained
whitelists have been added (in subsequent patches), this will be changed
to a usersize of 0, making caches created with kmem_cache_create() not
copyable to/from userspace.
After the entire usercopy whitelist series is applied, less than 15%
of the slab cache memory remains exposed to potential usercopy bugs
after a fresh boot:
Total Slab Memory: 48074720
Usercopyable Memory: 6367532 13.2%
task_struct 0.2% 4480/1630720
RAW 0.3% 300/96000
RAWv6 2.1% 1408/64768
ext4_inode_cache 3.0% 269760/8740224
dentry 11.1% 585984/5273856
mm_struct 29.1% 54912/188448
kmalloc-8 100.0% 24576/24576
kmalloc-16 100.0% 28672/28672
kmalloc-32 100.0% 81920/81920
kmalloc-192 100.0% 96768/96768
kmalloc-128 100.0% 143360/143360
names_cache 100.0% 163840/163840
kmalloc-64 100.0% 167936/167936
kmalloc-256 100.0% 339968/339968
kmalloc-512 100.0% 350720/350720
kmalloc-96 100.0% 455616/455616
kmalloc-8192 100.0% 655360/655360
kmalloc-1024 100.0% 812032/812032
kmalloc-4096 100.0% 819200/819200
kmalloc-2048 100.0% 1310720/1310720
After some kernel build workloads, the percentage (mainly driven by
dentry and inode caches expanding) drops under 10%:
Total Slab Memory: 95516184
Usercopyable Memory: 8497452 8.8%
task_struct 0.2% 4000/1456000
RAW 0.3% 300/96000
RAWv6 2.1% 1408/64768
ext4_inode_cache 3.0% 1217280/39439872
dentry 11.1% 1623200/14608800
mm_struct 29.1% 73216/251264
kmalloc-8 100.0% 24576/24576
kmalloc-16 100.0% 28672/28672
kmalloc-32 100.0% 94208/94208
kmalloc-192 100.0% 96768/96768
kmalloc-128 100.0% 143360/143360
names_cache 100.0% 163840/163840
kmalloc-64 100.0% 245760/245760
kmalloc-256 100.0% 339968/339968
kmalloc-512 100.0% 350720/350720
kmalloc-96 100.0% 563520/563520
kmalloc-8192 100.0% 655360/655360
kmalloc-1024 100.0% 794624/794624
kmalloc-4096 100.0% 819200/819200
kmalloc-2048 100.0% 1257472/1257472
Signed-off-by: David Windsor <dave@nullcore.net>
[kees: adjust commit log, split out a few extra kmalloc hunks]
[kees: add field names to function declarations]
[kees: convert BUGs to WARNs and fail closed]
[kees: add attack surface reduction analysis to commit log]
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: linux-mm@kvack.org
Cc: linux-xfs@vger.kernel.org
Signed-off-by: Kees Cook <keescook@chromium.org>
Acked-by: Christoph Lameter <cl@linux.com>
2017-06-10 22:50:28 -04:00
|
|
|
|
2022-11-16 15:56:32 +01:00
|
|
|
|
2022-08-15 05:53:53 +10:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2010-02-26 09:36:12 +03:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-09-06 16:21:56 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-08-22 01:38:30 +00:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-08-22 01:38:30 +00:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
2014-05-06 12:50:08 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2010-01-19 02:58:23 +01:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-02-20 23:25:28 +00:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2014-05-06 12:50:08 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
2007-11-01 09:29:06 -06:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2014-04-07 15:39:31 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-09-26 22:20:41 +08:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
2008-02-15 23:45:26 -08:00
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-08-31 22:54:54 +08:00
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
mm: add support for kmem caches in DMA32 zone
Patch series "iommu/io-pgtable-arm-v7s: Use DMA32 zone for page tables",
v6.
This is a followup to the discussion in [1], [2].
IOMMUs using ARMv7 short-descriptor format require page tables (level 1
and 2) to be allocated within the first 4GB of RAM, even on 64-bit
systems.
For L1 tables that are bigger than a page, we can just use
__get_free_pages with GFP_DMA32 (on arm64 systems only, arm would still
use GFP_DMA).
For L2 tables that only take 1KB, it would be a waste to allocate a full
page, so we considered 3 approaches:
1. This series, adding support for GFP_DMA32 slab caches.
2. genalloc, which requires pre-allocating the maximum number of L2 page
tables (4096, so 4MB of memory).
3. page_frag, which is not very memory-efficient as it is unable to reuse
freed fragments until the whole page is freed. [3]
This series is the most memory-efficient approach.
stable@ note:
We confirmed that this is a regression, and IOMMU errors happen on 4.19
and linux-next/master on MT8173 (elm, Acer Chromebook R13). The issue
most likely starts from commit ad67f5a6545f ("arm64: replace ZONE_DMA
with ZONE_DMA32"), i.e. 4.15, and presumably breaks a number of Mediatek
platforms (and maybe others?).
[1] https://lists.linuxfoundation.org/pipermail/iommu/2018-November/030876.html
[2] https://lists.linuxfoundation.org/pipermail/iommu/2018-December/031696.html
[3] https://patchwork.codeaurora.org/patch/671639/
This patch (of 3):
IOMMUs using ARMv7 short-descriptor format require page tables to be
allocated within the first 4GB of RAM, even on 64-bit systems. On arm64,
this is done by passing GFP_DMA32 flag to memory allocation functions.
For IOMMU L2 tables that only take 1KB, it would be a waste to allocate
a full page using get_free_pages, so we considered 3 approaches:
1. This patch, adding support for GFP_DMA32 slab caches.
2. genalloc, which requires pre-allocating the maximum number of L2
page tables (4096, so 4MB of memory).
3. page_frag, which is not very memory-efficient as it is unable
to reuse freed fragments until the whole page is freed.
This change makes it possible to create a custom cache in DMA32 zone using
kmem_cache_create, then allocate memory using kmem_cache_alloc.
We do not create a DMA32 kmalloc cache array, as there are currently no
users of kmalloc(..., GFP_DMA32). These calls will continue to trigger a
warning, as we keep GFP_DMA32 in GFP_SLAB_BUG_MASK.
This implies that calls to kmem_cache_*alloc on a SLAB_CACHE_DMA32
kmem_cache must _not_ use GFP_DMA32 (it is anyway redundant and
unnecessary).
Link: http://lkml.kernel.org/r/20181210011504.122604-2-drinkcat@chromium.org
Signed-off-by: Nicolas Boichat <drinkcat@chromium.org>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Will Deacon <will.deacon@arm.com>
Cc: Robin Murphy <robin.murphy@arm.com>
Cc: Joerg Roedel <joro@8bytes.org>
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Sasha Levin <Alexander.Levin@microsoft.com>
Cc: Huaisheng Ye <yehs1@lenovo.com>
Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Yong Wu <yong.wu@mediatek.com>
Cc: Matthias Brugger <matthias.bgg@gmail.com>
Cc: Tomasz Figa <tfiga@google.com>
Cc: Yingjoe Chen <yingjoe.chen@mediatek.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Hsin-Yi Wang <hsinyi@chromium.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-28 20:43:42 -07:00
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
2016-03-15 14:55:06 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2016-01-14 15:18:15 -08:00
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
2022-09-26 22:20:41 +08:00
|
|
|
|
2012-12-18 14:22:34 -08:00
|
|
|
|
2022-09-26 22:20:41 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-09-15 17:03:49 +02:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-02-22 15:41:39 -08:00
|
|
|
|
2012-11-28 16:23:07 +00:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
2017-11-15 17:32:25 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-11-01 09:29:06 -06:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-08-31 22:54:54 +08:00
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
2017-02-22 15:41:39 -08:00
|
|
|
|
2014-01-04 16:32:31 +09:00
|
|
|
|
2021-01-28 19:32:50 +08:00
|
|
|
|
2015-09-04 15:45:51 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
2014-04-07 15:39:32 -07:00
|
|
|
|
|
|
|
|
|
2014-04-07 15:39:31 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2014-04-07 15:39:32 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
2018-06-27 23:26:09 -07:00
|
|
|
|
|
|
|
|
|
mm/slab: Allow cache creation to proceed even if sysfs registration fails
When kobject_init_and_add() fails during cache creation,
kobj->name can be leaked because SLUB does not call kobject_put(),
which should be invoked per the kobject API documentation.
This has a bit of historical context, though; SLUB does not call
kobject_put() to avoid double-free for struct kmem_cache because
1) simply calling it would free all resources related to the cache, and
2) struct kmem_cache descriptor is always freed by cache_cache()'s
error handling path, causing struct kmem_cache to be freed twice.
This issue can be reproduced by creating new slab caches while applying
failslab for kernfs_node_cache. This makes kobject_add_varg() succeed,
but causes kobject_add_internal() to fail in kobject_init_and_add()
during cache creation.
Historically, this issue has attracted developers' attention several times.
Each time a fix addressed either the leak or the double-free,
it caused the other issue. Let's summarize a bit of history here:
The leak has existed since the early days of SLUB.
Commit 54b6a731025f ("slub: fix leak of 'name' in sysfs_slab_add")
introduced a double-free bug while fixing the leak.
Commit 80da026a8e5d ("mm/slub: fix slab double-free in case of duplicate
sysfs filename") re-introduced the leak while fixing the double-free
error.
Commit dde3c6b72a16 ("mm/slub: fix a memory leak in sysfs_slab_add()")
fixed the memory leak, but it was later reverted by commit 757fed1d0898
("Revert "mm/slub: fix a memory leak in sysfs_slab_add()"") to avoid
the double-free error.
This is where we are now: we've chosen a memory leak over a double-free.
To resolve this memory leak, skip creating sysfs files if it fails
and continue with cache creation regardless (as suggested by Christoph).
This resolves the memory leak because both the cache and the kobject
remain alive on kobject_init_and_add() failure.
If SLUB tries to create an alias for a cache without sysfs files,
its symbolic link will not be generated.
Since a slab cache might not have associated sysfs files, call kobject_del()
only if such files exist.
Signed-off-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2024-11-01 22:08:44 +09:00
|
|
|
|
|
|
|
|
|
2018-06-27 23:26:09 -07:00
|
|
|
|
|
|
|
|
|
2017-02-22 15:41:11 -08:00
|
|
|
|
|
|
|
|
|
2024-02-28 11:04:08 +08:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-12-05 14:08:08 +11:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-07-17 04:03:27 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-07-06 15:25:11 -05:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-11-01 09:29:06 -06:00
|
|
|
|
mm/slab: Allow cache creation to proceed even if sysfs registration fails
When kobject_init_and_add() fails during cache creation,
kobj->name can be leaked because SLUB does not call kobject_put(),
which should be invoked per the kobject API documentation.
This has a bit of historical context, though; SLUB does not call
kobject_put() to avoid double-free for struct kmem_cache because
1) simply calling it would free all resources related to the cache, and
2) struct kmem_cache descriptor is always freed by cache_cache()'s
error handling path, causing struct kmem_cache to be freed twice.
This issue can be reproduced by creating new slab caches while applying
failslab for kernfs_node_cache. This makes kobject_add_varg() succeed,
but causes kobject_add_internal() to fail in kobject_init_and_add()
during cache creation.
Historically, this issue has attracted developers' attention several times.
Each time a fix addressed either the leak or the double-free,
it caused the other issue. Let's summarize a bit of history here:
The leak has existed since the early days of SLUB.
Commit 54b6a731025f ("slub: fix leak of 'name' in sysfs_slab_add")
introduced a double-free bug while fixing the leak.
Commit 80da026a8e5d ("mm/slub: fix slab double-free in case of duplicate
sysfs filename") re-introduced the leak while fixing the double-free
error.
Commit dde3c6b72a16 ("mm/slub: fix a memory leak in sysfs_slab_add()")
fixed the memory leak, but it was later reverted by commit 757fed1d0898
("Revert "mm/slub: fix a memory leak in sysfs_slab_add()"") to avoid
the double-free error.
This is where we are now: we've chosen a memory leak over a double-free.
To resolve this memory leak, skip creating sysfs files if it fails
and continue with cache creation regardless (as suggested by Christoph).
This resolves the memory leak because both the cache and the kobject
remain alive on kobject_init_and_add() failure.
If SLUB tries to create an alias for a cache without sysfs files,
its symbolic link will not be generated.
Since a slab cache might not have associated sysfs files, call kobject_del()
only if such files exist.
Signed-off-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2024-11-01 22:08:44 +09:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-11-01 09:29:06 -06:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2022-09-15 17:03:49 +02:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-07-17 04:03:19 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
2012-07-06 15:25:12 -05:00
|
|
|
|
2010-07-19 11:39:11 -05:00
|
|
|
|
2020-06-01 21:45:50 -07:00
|
|
|
|
2007-11-01 09:29:06 -06:00
|
|
|
|
2012-07-06 15:25:12 -05:00
|
|
|
|
2014-06-04 16:06:34 -07:00
|
|
|
|
2023-04-13 22:34:48 +08:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
2012-07-06 15:25:11 -05:00
|
|
|
|
2007-05-09 02:32:39 -07:00
|
|
|
|
2007-07-17 04:03:19 -07:00
|
|
|
|
2007-05-09 02:32:39 -07:00
|
|
|
|
2007-08-30 23:56:26 -07:00
|
|
|
|
2014-06-04 16:06:34 -07:00
|
|
|
|
|
|
|
|
|
2007-05-09 02:32:39 -07:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-08-30 23:56:26 -07:00
|
|
|
|
2014-06-04 16:06:34 -07:00
|
|
|
|
|
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-07-06 15:25:12 -05:00
|
|
|
|
2007-05-06 14:49:36 -07:00
|
|
|
|
|
|
|
|
|
2022-09-30 12:27:12 +02:00
|
|
|
|
2022-11-14 18:18:39 +01:00
|
|
|
|
2008-01-01 17:23:28 +01:00
|
|
|
|
2021-06-28 19:34:55 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-12-10 14:47:02 -08:00
|
|
|
|
|
|
|
|
|
2021-06-28 19:34:55 -07:00
|
|
|
|
2021-12-10 14:47:02 -08:00
|
|
|
|
2021-06-28 19:34:55 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
mm/slub: enable debugging memory wasting of kmalloc
kmalloc's API family is critical for mm, with one nature that it will
round up the request size to a fixed one (mostly power of 2). Say
when user requests memory for '2^n + 1' bytes, actually 2^(n+1) bytes
could be allocated, so in worst case, there is around 50% memory
space waste.
The wastage is not a big issue for requests that get allocated/freed
quickly, but may cause problems with objects that have longer life
time.
We've met a kernel boot OOM panic (v5.10), and from the dumped slab
info:
[ 26.062145] kmalloc-2k 814056KB 814056KB
From debug we found there are huge number of 'struct iova_magazine',
whose size is 1032 bytes (1024 + 8), so each allocation will waste
1016 bytes. Though the issue was solved by giving the right (bigger)
size of RAM, it is still nice to optimize the size (either use a
kmalloc friendly size or create a dedicated slab for it).
And from lkml archive, there was another crash kernel OOM case [1]
back in 2019, which seems to be related with the similar slab waste
situation, as the log is similar:
[ 4.332648] iommu: Adding device 0000:20:02.0 to group 16
[ 4.338946] swapper/0 invoked oom-killer: gfp_mask=0x6040c0(GFP_KERNEL|__GFP_COMP), nodemask=(null), order=0, oom_score_adj=0
...
[ 4.857565] kmalloc-2048 59164KB 59164KB
The crash kernel only has 256M memory, and 59M is pretty big here.
(Note: the related code has been changed and optimised in recent
kernel [2], these logs are just picked to demo the problem, also
a patch changing its size to 1024 bytes has been merged)
So add an way to track each kmalloc's memory waste info, and
leverage the existing SLUB debug framework (specifically
SLUB_STORE_USER) to show its call stack of original allocation,
so that user can evaluate the waste situation, identify some hot
spots and optimize accordingly, for a better utilization of memory.
The waste info is integrated into existing interface:
'/sys/kernel/debug/slab/kmalloc-xx/alloc_traces', one example of
'kmalloc-4k' after boot is:
126 ixgbe_alloc_q_vector+0xbe/0x830 [ixgbe] waste=233856/1856 age=280763/281414/282065 pid=1330 cpus=32 nodes=1
__kmem_cache_alloc_node+0x11f/0x4e0
__kmalloc_node+0x4e/0x140
ixgbe_alloc_q_vector+0xbe/0x830 [ixgbe]
ixgbe_init_interrupt_scheme+0x2ae/0xc90 [ixgbe]
ixgbe_probe+0x165f/0x1d20 [ixgbe]
local_pci_probe+0x78/0xc0
work_for_cpu_fn+0x26/0x40
...
which means in 'kmalloc-4k' slab, there are 126 requests of
2240 bytes which got a 4KB space (wasting 1856 bytes each
and 233856 bytes in total), from ixgbe_alloc_q_vector().
And when system starts some real workload like multiple docker
instances, there could are more severe waste.
[1]. https://lkml.org/lkml/2019/8/12/266
[2]. https://lore.kernel.org/lkml/2920df89-9975-5785-f79b-257d3052dfaf@huawei.com/
[Thanks Hyeonggon for pointing out several bugs about sorting/format]
[Thanks Vlastimil for suggesting way to reduce memory usage of
orig_size and keep it only for kmalloc objects]
Signed-off-by: Feng Tang <feng.tang@intel.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Robin Murphy <robin.murphy@arm.com>
Cc: John Garry <john.garry@huawei.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2022-09-13 14:54:20 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-06-28 19:34:55 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-05-21 14:11:25 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-06-28 19:34:55 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-12-10 14:47:02 -08:00
|
|
|
|
2021-06-28 19:34:55 -07:00
|
|
|
|
2021-12-10 14:47:02 -08:00
|
|
|
|
2021-06-28 19:34:55 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-05-21 14:11:26 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-06-28 19:34:55 -07:00
|
|
|
|
|
|
|
|
|
2021-12-10 14:47:02 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-06-28 19:34:55 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-05-23 01:28:37 +02:00
|
|
|
|
|
|
|
|
|
2021-10-18 15:15:52 -07:00
|
|
|
|
2021-05-23 01:28:37 +02:00
|
|
|
|
2021-06-28 19:34:55 -07:00
|
|
|
|
2021-10-18 15:15:52 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-01-12 08:07:01 +00:00
|
|
|
|
2021-06-28 19:34:55 -07:00
|
|
|
|
2021-05-23 01:28:37 +02:00
|
|
|
|
|
|
|
|
|
2021-10-18 15:15:52 -07:00
|
|
|
|
2021-06-28 19:34:55 -07:00
|
|
|
|
2021-05-23 01:28:37 +02:00
|
|
|
|
2021-06-28 19:34:55 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
2021-06-28 19:34:55 -07:00
|
|
|
|
2023-04-13 22:34:52 +08:00
|
|
|
|
2021-06-28 19:34:55 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
mm/slub: Convert most struct page to struct slab by spatch
The majority of conversion from struct page to struct slab in SLUB
internals can be delegated to a coccinelle semantic patch. This includes
renaming of variables with 'page' in name to 'slab', and similar.
Big thanks to Julia Lawall and Luis Chamberlain for help with
coccinelle.
// Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c
// Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the
// embedded script
// build list of functions to exclude from applying the next rule
@initialize:ocaml@
@@
let ok_function p =
not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"])
// convert the type from struct page to struct page in all functions except the
// list from previous rule
// this also affects struct kmem_cache_cpu, but that's ok
@@
position p : script:ocaml() { ok_function p };
@@
- struct page@p
+ struct slab
// in struct kmem_cache_cpu, change the name from page to slab
// the type was already converted by the previous rule
@@
@@
struct kmem_cache_cpu {
...
-struct slab *page;
+struct slab *slab;
...
}
// there are many places that use c->page which is now c->slab after the
// previous rule
@@
struct kmem_cache_cpu *c;
@@
-c->page
+c->slab
@@
@@
struct kmem_cache {
...
- unsigned int cpu_partial_pages;
+ unsigned int cpu_partial_slabs;
...
}
@@
struct kmem_cache *s;
@@
- s->cpu_partial_pages
+ s->cpu_partial_slabs
@@
@@
static void
- setup_page_debug(
+ setup_slab_debug(
...)
{...}
@@
@@
- setup_page_debug(
+ setup_slab_debug(
...);
// for all functions (with exceptions), change any "struct slab *page"
// parameter to "struct slab *slab" in the signature, and generally all
// occurences of "page" to "slab" in the body - with some special cases.
@@
identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj";
@@
fn(...,
- struct slab *page
+ struct slab *slab
,...)
{
<...
- page
+ slab
...>
}
// similar to previous but the param is called partial_page
@@
identifier fn;
@@
fn(...,
- struct slab *partial_page
+ struct slab *partial_slab
,...)
{
<...
- partial_page
+ partial_slab
...>
}
// similar to previous but for functions that take pointer to struct page ptr
@@
identifier fn;
@@
fn(...,
- struct slab **ret_page
+ struct slab **ret_slab
,...)
{
<...
- ret_page
+ ret_slab
...>
}
// functions converted by previous rules that were temporarily called using
// slab_page(E) so we want to remove the wrapper now that they accept struct
// slab ptr directly
@@
identifier fn =~ "slab_free|do_slab_free";
expression E;
@@
fn(...,
- slab_page(E)
+ E
,...)
// similar to previous but for another pattern
@@
identifier fn =~ "slab_pad_check|check_object";
@@
fn(...,
- folio_page(folio, 0)
+ slab
,...)
// functions that were returning struct page ptr and now will return struct
// slab ptr, including slab_page() wrapper removal
@@
identifier fn =~ "allocate_slab|new_slab";
expression E;
@@
static
-struct slab *
+struct slab *
fn(...)
{
<...
- slab_page(E)
+ E
...>
}
// rename any former struct page * declarations
@@
@@
struct slab *
(
- page
+ slab
|
- partial_page
+ partial_slab
|
- oldpage
+ oldslab
)
;
// this has to be separate from previous rule as page and page2 appear at the
// same line
@@
@@
struct slab *
-page2
+slab2
;
// similar but with initial assignment
@@
expression E;
@@
struct slab *
(
- page
+ slab
|
- flush_page
+ flush_slab
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
= E;
// convert most of struct page to struct slab usage inside functions (with
// exceptions), including specific variable renames
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
expression E;
@@
fn(...)
{
<...
(
- int pages;
+ int slabs;
|
- int pages = E;
+ int slabs = E;
|
- page
+ slab
|
- flush_page
+ flush_slab
|
- partial_page
+ partial_slab
|
- oldpage->pages
+ oldslab->slabs
|
- oldpage
+ oldslab
|
- unsigned int nr_pages;
+ unsigned int nr_slabs;
|
- nr_pages
+ nr_slabs
|
- unsigned int partial_pages = E;
+ unsigned int partial_slabs = E;
|
- partial_pages
+ partial_slabs
)
...>
}
// this has to be split out from the previous rule so that lines containing
// multiple matching changes will be fully converted
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- slab->pages
+ slab->slabs
|
- pages
+ slabs
|
- page2
+ slab2
|
- discard_page
+ slab_to_discard
|
- page_to_unfreeze
+ slab_to_unfreeze
)
...>
}
// after we simply changed all occurences of page to slab, some usages need
// adjustment for slab-specific functions, or use slab_page() wrapper
@@
identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node";
@@
fn(...)
{
<...
(
- page_slab(slab)
+ slab
|
- kasan_poison_slab(slab)
+ kasan_poison_slab(slab_page(slab))
|
- page_address(slab)
+ slab_address(slab)
|
- page_size(slab)
+ slab_size(slab)
|
- PageSlab(slab)
+ folio_test_slab(slab_folio(slab))
|
- page_to_nid(slab)
+ slab_nid(slab)
|
- compound_order(slab)
+ slab_order(slab)
)
...>
}
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Julia Lawall <julia.lawall@inria.fr>
Cc: Luis Chamberlain <mcgrof@kernel.org>
2021-11-03 15:39:59 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-06-28 19:34:55 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-05-21 14:11:26 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2021-05-23 01:28:37 +02:00
|
|
|
|
2021-06-28 19:34:55 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2025-01-12 08:07:01 +00:00
|
|
|
|
|
|
|
|
|
2021-06-28 19:34:55 -07:00
|
|
|
|
2025-01-12 08:07:01 +00:00
|
|
|
|
|
|
|
|
|
2021-06-28 19:34:55 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2023-02-02 15:20:22 +01:00
|
|
|
|
2021-06-28 19:34:55 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-01-01 17:23:28 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-11-15 17:32:03 -08:00
|
|
|
|
2012-10-19 18:20:27 +04:00
|
|
|
|
2008-01-01 17:23:28 +01:00
|
|
|
|
|
|
|
|
|
2008-04-14 19:11:40 +03:00
|
|
|
|
|
|
|
|
|
2008-01-01 17:23:28 +01:00
|
|
|
|
2014-08-06 16:04:09 -07:00
|
|
|
|
2008-01-01 17:23:28 +01:00
|
|
|
|
2014-08-06 16:04:09 -07:00
|
|
|
|
2013-07-04 08:33:26 +08:00
|
|
|
|
|
|
|
|
|
slub: introduce count_partial_free_approx()
When reading "/proc/slabinfo", the kernel needs to report the number
of free objects for each kmem_cache. The current implementation uses
count_partial() to get it by scanning each kmem_cache_node's partial
slab list and summing free objects from every partial slab. This
process must hold per-kmem_cache_node spinlock and disable IRQ, and
may take a long time. Consequently, it can block slab allocations on
other CPUs and cause timeouts for network devices, when the partial
list is long. In production, even NMI watchdog can be triggered due
to this matter: e.g., for "buffer_head", the number of partial slabs
was observed to be ~1M in one kmem_cache_node. This problem was also
confirmed by others [1-3].
Iterating a partial list to get the exact count of objects can cause
soft lockups for a long list with or without the lock (e.g., if
preemption is disabled), and may not be very useful: the object count
can change after the lock is released. The approach of maintaining
free-object counters requires atomic operations on the fast path [3].
So, the fix is to introduce count_partial_free_approx(). This function
can be used for getting the free object count in a kmem_cache_node's
partial list. It limits the number of slabs to scan and avoids scanning
the whole list by giving an approximation for a long list. Suppose the
limit is N. If the list's length is not greater than N, output the exact
count by traversing the list; if its length is greater than N, output an
approximated count by traversing a subset of the list. The proposed
method is to scan N/2 slabs from the list's head and N/2 slabs from
the tail. For a partial list with ~280K slabs, benchmarks show that
it performs better than just counting from the list's head, after slabs
get sorted by kmem_cache_shrink(). Default the limit to 10000, as it
produces an approximation within 1% of the exact count for both
scenarios. Then, use count_partial_free_approx() in get_slabinfo().
Benchmarks: Diff = (exact - approximated) / exact
* Normal case (w/o kmem_cache_shrink()):
| MAX_TO_SCAN | Diff (count from head)| Diff (count head+tail)|
| 1000 | 0.43 % | 1.09 % |
| 5000 | 0.06 % | 0.37 % |
| 10000 | 0.02 % | 0.16 % |
| 20000 | 0.009 % | -0.003 % |
* Skewed case (w/ kmem_cache_shrink()):
| MAX_TO_SCAN | Diff (count from head)| Diff (count head+tail)|
| 1000 | 12.46 % | 6.75 % |
| 5000 | 5.38 % | 1.27 % |
| 10000 | 4.99 % | 0.22 % |
| 20000 | 4.86 % | -0.06 % |
[1] https://lore.kernel.org/linux-mm/alpine.DEB.2.21.2003031602460.1537@www.lameter.com/T/
[2] https://lore.kernel.org/lkml/alpine.DEB.2.22.394.2008071258020.55871@www.lameter.com/T/
[3] https://lore.kernel.org/lkml/1e01092b-140d-2bab-aeba-321a74a194ee@linux.com/T/
Signed-off-by: Jianfeng Wang <jianfeng.w.wang@oracle.com>
Acked-by: David Rientjes <rientjes@google.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2024-04-22 21:55:53 -07:00
|
|
|
|
2008-01-01 17:23:28 +01:00
|
|
|
|
|
|
|
|
|
2012-10-19 18:20:27 +04:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-01-01 17:23:28 +01:00
|
|
|
|
2017-11-15 17:32:03 -08:00
|
|
|
|