We pass around a variable called "error_code" all around the page
fault code. Sounds simple enough, especially since "error_code" looks
like it exactly matches the values that the hardware gives us on the
stack to report the page fault error code (PFEC in SDM parlance).
But, that's not how it works.
For part of the page fault handler, "error_code" does exactly match
PFEC. But, during later parts, it diverges and starts to mean
something a bit different.
Give it two names for its two jobs.
The place it diverges is also really screwy. It's only in a spot
where the hardware tells us we have kernel-mode access that occurred
while we were in usermode accessing user-controlled address space.
Add a warning in there.
Cc: x86@kernel.org
Cc: Jann Horn <jannh@google.com>
Cc: Sean Christopherson <sean.j.christopherson@intel.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Andy Lutomirski <luto@kernel.org>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20180928160220.4A2272C9@viggo.jf.intel.com
Lazy TLB mode can result in an idle CPU being woken up by a TLB flush,
when all it really needs to do is reload %CR3 at the next context switch,
assuming no page table pages got freed.
Memory ordering is used to prevent race conditions between switch_mm_irqs_off,
which checks whether .tlb_gen changed, and the TLB invalidation code, which
increments .tlb_gen whenever page table entries get invalidated.
The atomic increment in inc_mm_tlb_gen is its own barrier; the context
switch code adds an explicit barrier between reading tlbstate.is_lazy and
next->context.tlb_gen.
CPUs in lazy TLB mode remain part of the mm_cpumask(mm), both because
that allows TLB flush IPIs to be sent at page table freeing time, and
because the cache line bouncing on the mm_cpumask(mm) was responsible
for about half the CPU use in switch_mm_irqs_off().
We can change native_flush_tlb_others() without touching other
(paravirt) implementations of flush_tlb_others() because we'll be
flushing less. The existing implementations flush more and are
therefore still correct.
Cc: npiggin@gmail.com
Cc: mingo@kernel.org
Cc: will.deacon@arm.com
Cc: kernel-team@fb.com
Cc: luto@kernel.org
Cc: hpa@zytor.com
Tested-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Rik van Riel <riel@surriel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20180926035844.1420-8-riel@surriel.com
Move some code that will be needed for the lazy -> !lazy state
transition when a lazy TLB CPU has gotten out of date.
No functional changes, since the if (real_prev == next) branch
always returns.
(cherry picked from commit 61d0beb579)
Cc: npiggin@gmail.com
Cc: efault@gmx.de
Cc: will.deacon@arm.com
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: songliubraving@fb.com
Cc: kernel-team@fb.com
Cc: hpa@zytor.com
Suggested-by: Andy Lutomirski <luto@kernel.org>
Signed-off-by: Rik van Riel <riel@surriel.com>
Acked-by: Dave Hansen <dave.hansen@intel.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20180716190337.26133-4-riel@surriel.com
On most workloads, the number of context switches far exceeds the
number of TLB flushes sent. Optimizing the context switches, by always
using lazy TLB mode, speeds up those workloads.
This patch results in about a 1% reduction in CPU use on a two socket
Broadwell system running a memcache like workload.
Cc: npiggin@gmail.com
Cc: efault@gmx.de
Cc: will.deacon@arm.com
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: kernel-team@fb.com
Cc: hpa@zytor.com
Cc: luto@kernel.org
Tested-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Rik van Riel <riel@surriel.com>
(cherry picked from commit 95b0e6357d)
Acked-by: Dave Hansen <dave.hansen@intel.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20180716190337.26133-7-riel@surriel.com
Use the new tlb_get_unmap_shift() to determine the stride of the
INVLPG loop.
Cc: Nick Piggin <npiggin@gmail.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Support 640x480 as a frame size for video input devices of vivid.
Signed-off-by: Keiichi Watanabe <keiichiw@chromium.org>
Acked-by: Hans Verkuil <hans.verkuil@cisco.com>
Reviewed-by: Kieran Bingham <kieran.bingham+renesas@ideasonboard.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
pblk's write buffer must guarantee that it respects the device's
constrains for reads (i.e., mw_cunits). This is done by maintaining a
backpointer that updates the L2P table as entries wrap up, making them
point to the media instead of pointing to the write buffer.
This mechanism can race in case that the write thread stalls, as the
write pointer will protect the last written entry, thus disregarding the
read constrains.
This patch adds an extra check on wrap up, making sure that the
threshold is respected at all times, preventing new entries to overwrite
committed data, also in case of write thread stall.
Reported-by: Heiner Litz <hlitz@ucsc.edu>
Signed-off-by: Javier González <javier@cnexlabs.com>
Reviewed-by: Heiner Litz <hlitz@ucsc.edu>
Signed-off-by: Matias Bjørling <mb@lightnvm.io>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
When do GC, the number of read/write sectors are determined
by max_write_pgs(see gc_rq preparation in pblk_gc_line_prepare_ws).
Due to max_write_pgs doesn't consider max hw sectors
supported by nvme controller(128K), which leads to GC
tries to read 64 * 4K in one command, and see below error
caused by pblk_bio_map_addr in function pblk_submit_read_gc.
[ 2923.005376] pblk: could not add page to bio
[ 2923.005377] pblk: could not allocate GC bio (18446744073709551604)
Signed-off-by: Zhoujie Wu <zjwu@marvell.com>
Reviewed-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Matias Bjørling <mb@lightnvm.io>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
In the too many bad blocks error handling case, we should release all
the allocated resources, otherwise it will cause memory leak.
Fixes: 2deeefc02d ("lightnvm: pblk: fail gracefully on line alloc. failure")
Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com>
Reviewed-by: Hans Holmberg <hans.holmberg@cnexlabs.com>
Signed-off-by: Matias Bjørling <mb@lightnvm.io>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
1.2 devices exposes their data and metadata size through the separate
identify command. Make sure that the NVMe LBA format does not override
these values.
Signed-off-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Matias Bjørling <mb@lightnvm.io>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
OCSSD 2.0 defines the amount of data that the host must buffer per chunk
to guarantee reads through the geometry field mw_cunits. This value is
the base that pblk uses to determine the size of its read buffer.
Currently, this size is set to be the closes power-of-2 to mw_cunits
times the number of parallel units available to the pblk instance for
each open line (currently one). When an entry (4KB) is put in the
buffer, the L2P table points to it. As the buffer wraps up, the L2P is
updated to point to addresses on the device, thus guaranteeing mw_cunits
at a chunk level.
However, given that pblk cannot write to the device under ws_min
(normally ws_opt), there might be a window in which the buffer starts
wrapping up and updating L2P entries before the mw_cunits value in a
chunk has been surpassed.
In order not to violate the mw_cunits constrain in this case, account
for ws_opt on the read buffer creation.
Signed-off-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Matias Bjørling <mb@lightnvm.io>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
pblk's read/write buffer currently takes a buffer and its size and uses
it to create the metadata around it to use it as a ring buffer. This
puts the responsibility of allocating/freeing ring buffer memory on the
ring buffer user. Instead, move it inside of the ring buffer helpers
(pblk-rb.c). This simplifies creation/destruction routines.
Signed-off-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Matias Bjørling <mb@lightnvm.io>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
pblk's read/write buffer is always a power-of-2, thus wrapping up the
buffer can be done with a bit mask. Since this is an implementation
detail internal to the write buffer, make a helper that hides pointer
increment + wrap, and allows to transparently relax this assumption in
the future.
Signed-off-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Matias Bjørling <mb@lightnvm.io>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
pblk exposes a sysfs interface that represents its internal state. Part
of this state is the map bitmap for the current open line, which should
be protected by the line lock to avoid a race when freeing the line
metadata. Currently, it is not.
This patch makes sure that the line state is consistent and NULL
bitmap pointers are not dereferenced.
Signed-off-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Matias Bjørling <mb@lightnvm.io>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
In the OCSSD 2.0 spec, each chunk reports its write pointer. This means
that pblk does not need to scan open lines to find the write pointer,
but instead, it can retrieve it directly (and verify it).
This patch uses the write pointer on open lines to (i) recover the line
up until the last written lba and (ii) reconstruct the map bitmap and
rest of line metadata so that the line can be used for new data.
Since the 1.2 path in lightnvm core has been re-implemented to populate
the chunk structure and thus recover the write pointer on
initialization, this patch removes 1.2 specific recovery, as the 2.0
path can be reused.
Signed-off-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Matias Bjørling <mb@lightnvm.io>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
pblk guarantees write ordering at a chunk level through a per open chunk
semaphore. At this point, since we only have an open I/O stream for both
user and GC data, the semaphore is per parallel unit.
For the metadata I/O that is synchronous, the semaphore is not needed as
ordering is guaranteed. However, if the metadata scheme changes or
multiple streams are open, this guarantee might not be preserved.
This patch makes sure that all writes go through the semaphore, even for
synchronous I/O. This is consistent with pblk's write I/O model. It also
simplifies maintenance since changes in the metadata scheme could cause
ordering issues.
Signed-off-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Matias Bjørling <mb@lightnvm.io>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
pblk maintains two different metadata paths for smeta and emeta, which
store metadata at the start of the line and at the end of the line,
respectively. Until now, these path has been common for writing and
retrieving metadata, however, as these paths diverge, the common code
becomes less clear and unnecessary complicated.
In preparation for further changes to the metadata write path, this
patch separates the write and read paths for smeta and emeta and
removes the synchronous emeta path as it not used anymore (emeta is
scheduled asynchronously to prevent jittering due to internal I/Os).
Signed-off-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Matias Bjørling <mb@lightnvm.io>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
dma allocations for ppa_list and meta_list in rqd are replicated in
several places across the pblk codebase. Make helpers to encapsulate
creation and deletion to simplify the code.
Signed-off-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Matias Bjørling <mb@lightnvm.io>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The lightnvm subsystem provides helpers to retrieve chunk metadata,
where the target needs to provide a buffer to store the metadata. An
implicit assumption is that this buffer is contiguous and can be used to
retrieve the data from the device. If the device exposes too many
chunks, then kmalloc might fail, thus failing instance creation.
This patch removes this assumption by implementing an internal buffer in
the lightnvm subsystem to retrieve chunk metadata. Targets can then
use virtual memory allocations. Since this is a target API change, adapt
pblk accordingly.
Signed-off-by: Javier González <javier@cnexlabs.com>
Reviewed-by: Hans Holmberg <hans.holmberg@cnexlabs.com>
Signed-off-by: Matias Bjørling <mb@lightnvm.io>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The driver may sleep with holding a spinlock.
The function call paths (from bottom to top) in Linux-4.16 are:
[FUNC] nvm_dev_dma_alloc(GFP_KERNEL)
drivers/lightnvm/pblk-core.c, 754:
nvm_dev_dma_alloc in pblk_line_submit_smeta_io
drivers/lightnvm/pblk-core.c, 1048:
pblk_line_submit_smeta_io in pblk_line_init_bb
drivers/lightnvm/pblk-core.c, 1434:
pblk_line_init_bb in pblk_line_replace_data
drivers/lightnvm/pblk-recovery.c, 980:
pblk_line_replace_data in pblk_recov_l2p
drivers/lightnvm/pblk-recovery.c, 976:
spin_lock in pblk_recov_l2p
[FUNC] bio_map_kern(GFP_KERNEL)
drivers/lightnvm/pblk-core.c, 762:
bio_map_kern in pblk_line_submit_smeta_io
drivers/lightnvm/pblk-core.c, 1048:
pblk_line_submit_smeta_io in pblk_line_init_bb
drivers/lightnvm/pblk-core.c, 1434:
pblk_line_init_bb in pblk_line_replace_data
drivers/lightnvm/pblk-recovery.c, 980:
pblk_line_replace_data in pblk_recov_l2p
drivers/lightnvm/pblk-recovery.c, 976:
spin_lock in pblk_recov_l2p
To fix these bugs, the call to pblk_line_replace_data()
is moved out of the spinlock protection.
These bugs are found by my static analysis tool DSAC.
Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Reviewed-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Matias Bjørling <mb@lightnvm.io>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
On 1.2-devices, the mapping-out of remaning sectors in the
failed-write's block can result in an infinite loop,
stalling the write pipeline, fix this.
Fixes: 6a3abf5bee ("lightnvm: pblk: rework write error recovery path")
Signed-off-by: Hans Holmberg <hans.holmberg@cnexlabs.com>
Signed-off-by: Matias Bjørling <mb@lightnvm.io>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Pblk should not create a set of global caches every time
a pblk instance is created. The global caches should be
made available only when there is one or more pblk instances.
This patch bundles the global caches together with a kref
keeping track of whether the caches should be available or not.
Also, turn the global pblk lock into a mutex that explicitly
protects the caches (as this was the only purpose of the lock).
Signed-off-by: Hans Holmberg <hans.holmberg@cnexlabs.com>
Signed-off-by: Matias Bjørling <mb@lightnvm.io>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
If a line is padded, calculate the pad distance directly on the helper
being used for this purpose.
Signed-off-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Matias Bjørling <mb@lightnvm.io>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Continuing the effort of moving 1.2 and 2.0 specific code to core, move
64_to_32 and 32_to_64 ppa helpers from pblk to core.
Signed-off-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Matias Bjørling <mb@lightnvm.io>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Add trace events for logging for line state changes.
Signed-off-by: Hans Holmberg <hans.holmberg@cnexlabs.com>
Signed-off-by: Matias Bjørling <mb@lightnvm.io>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Introduce trace points for tracking chunk states in pblk - this is
useful for inspection of the entire state of the drive, and real handy
for both fw and pblk debugging.
Signed-off-by: Hans Holmberg <hans.holmberg@cnexlabs.com>
Signed-off-by: Matias Bjørling <mb@lightnvm.io>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Remove the debug only iteration within __pblk_down_page, which
then allows us to reduce the number of arguments down to pblk and
the parallel unit from the functions that calls it. Simplifying the
callers logic considerably.
Also, rename the functions pblk_[down/up]_page to
pblk_[down/up]_chunk, to communicate that it manages the write
pointer of the chunk. Note that it also protects the parallel unit
such that at most one chunk is active per parallel unit.
Signed-off-by: Matias Bjørling <mb@lightnvm.io>
Reviewed-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
When the user data counter exceeds 32 bits, the write amplification
calculation does not provide the right value. Fix this by using
div64_u64 in stead of div64.
Fixes: 76758390f8 ("lightnvm: pblk: export write amplification counters to sysfs")
Signed-off-by: Hans Holmberg <hans.holmberg@cnexlabs.com>
Signed-off-by: Matias Bjørling <mb@lightnvm.io>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The prefix when printing ppas in pblk_read_check_rand should be "rnd"
not "seq", so fix this so we can differentiate between lba missmatches
in random and sequential reads. Also change the print order so
we align with pblk_read_check_seq, printing read lba first.
Signed-off-by: Hans Holmberg <hans.holmberg@cnexlabs.com>
Signed-off-by: Matias Bjørling <mb@lightnvm.io>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The parameters nr_ppas and ppa_list are not used, so remove them.
Signed-off-by: Hans Holmberg <hans.holmberg@cnexlabs.com>
Signed-off-by: Matias Bjørling <mb@lightnvm.io>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Line map bitmap allocations are fairly large and can fail. Allocation
failures are fatal to pblk, stopping the write pipeline. To avoid this,
allocate the bitmaps using a mempool instead.
Mempool allocations never fail if called from a process context,
and pblk *should* only allocate map bitmaps in process context,
but keep the failure handling for robustness sake.
Signed-off-by: Hans Holmberg <hans.holmberg@cnexlabs.com>
Signed-off-by: Matias Bjørling <mb@lightnvm.io>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
There is a number of places in the lightnvm subsystem where the user
iterates over the ppa list. Before iterating, the user must know if it
is a single or multiple LBAs due to vector commands using either the
nvm_rq ->ppa_addr or ->ppa_list fields on command submission, which
leads to open-coding the if/else statement.
Instead of having multiple if/else's, move it into a function that can
be called by its users.
A nice side effect of this cleanup is that this patch fixes up a
bunch of cases where we don't consider the single-ppa case in pblk.
Signed-off-by: Hans Holmberg <hans.holmberg@cnexlabs.com>
Signed-off-by: Matias Bjørling <mb@lightnvm.io>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
If a line is recovered from open chunks, the memory structures for
emeta have not necessarily been properly set on line initialization.
When closing a line, make sure that emeta is consistent so that the line
can be recovered on the fast path on next reboot.
Also, remove a couple of empty lines at the end of the function.
Signed-off-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Matias Bjørling <mb@lightnvm.io>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The current helper to obtain a line from a ppa returns the line id,
which requires its users to explicitly retrieve the pointer to the line
with the id.
Make 2 different helpers: one returning the line id and one returning
the line directly.
Signed-off-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Matias Bjørling <mb@lightnvm.io>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Implement helpers to go from ppas to a chunk within a line and an
address within a chunk.
These helpers will be used on the patches adding trace support in pblk,
which will be sent in this window.
Signed-off-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Matias Bjørling <mb@lightnvm.io>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The read completion path uses the put_line variable to decide whether
the reference on a line should be released. The function name used for
that is pblk_read_put_rqd_kref, which could lead one to believe that it
is the rqd that is releasing the reference, while it is the line
reference that is put.
Rename and also split the function in two to account for either rqd or
single ppa callers and move it to core, such that it later can be used
in the write path as well.
Signed-off-by: Matias Bjørling <mb@lightnvm.io>
Reviewed-by: Javier González <javier@cnexlabs.com>
Reviewed-by: Heiner Litz <hlitz@ucsc.edu>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The I/O size and capacity checks are already done by the block layer.
Signed-off-by: Matias Bjørling <mb@lightnvm.io>
Reviewed-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The calculation of pblk->min_write_pgs should only use the optimal
write size attribute provided by the drive, it does not correlate to
the memory page size of the system, which can be smaller or larger
than the LBA size reported.
Signed-off-by: Matias Bjørling <mb@lightnvm.io>
Reviewed-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Both NVM_MAX_VLBA and PBLK_MAX_REQ_ADDRS define how many LBAs that
are available in a vector command. pblk uses them interchangeably
in its implementation. Use NVM_MAX_VLBA as the main one and remove
usages of PBLK_MAX_REQ_ADDRS.
Also remove the power representation that only has one user, and
instead calculate it at runtime.
Signed-off-by: Matias Bjørling <mb@lightnvm.io>
Reviewed-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
