Andreas Schwab noticed that the 1 << tk->shift could overflow if the
shift value was greater than 30, since 1 would be a 32bit long on
32bit architectures. This issue was introduced by 1e75fa8be (time:
Condense timekeeper.xtime into xtime_sec)
Use 1ULL instead to ensure we don't overflow on the shift.
Reported-by: Andreas Schwab <schwab@linux-m68k.org>
Signed-off-by: John Stultz <john.stultz@linaro.org>
Cc: Prarit Bhargava <prarit@redhat.com>
Cc: Ingo Molnar <mingo@kernel.org>
Link: http://lkml.kernel.org/r/1345595449-34965-4-git-send-email-john.stultz@linaro.org
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
arch_gettimeoffset returns a u32 value which when shifted by tk->shift
can overflow. This issue was introduced with 1e75fa8be (time: Condense
timekeeper.xtime into xtime_sec)
Cast it to u64 first.
Signed-off-by: Andreas Schwab <schwab@linux-m68k.org>
Signed-off-by: John Stultz <john.stultz@linaro.org>
Cc: Prarit Bhargava <prarit@redhat.com>
Cc: Ingo Molnar <mingo@kernel.org>
Link: http://lkml.kernel.org/r/1345595449-34965-3-git-send-email-john.stultz@linaro.org
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Andreas noticed problems with resume on specific hardware after commit
1e75fa8b (time: Condense timekeeper.xtime into xtime_sec) combined
with commit b44d50dca (time: Fix casting issue in tk_set_xtime and
tk_xtime_add)
After some digging I realized we aren't normalizing the timekeeper
after the add. Add the missing normalize call.
Reported-by: Andreas Schwab <schwab@linux-m68k.org>
Tested-by: Andreas Schwab <schwab@linux-m68k.org>
Signed-off-by: John Stultz <john.stultz@linaro.org>
Cc: Prarit Bhargava <prarit@redhat.com>
Cc: Ingo Molnar <mingo@kernel.org>
Link: http://lkml.kernel.org/r/1345595449-34965-2-git-send-email-john.stultz@linaro.org
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
When one CPU is going down and this CPU is the last one in irq
affinity, current code is setting cpu_all_mask as the new
affinity for that irq.
But for some systems (such as in Medfield Android mobile) the
firmware sends the interrupt to each CPU in the irq affinity
mask, averaged, and cpu_all_mask includes all potential CPUs,
i.e. offline ones as well.
So replace cpu_all_mask with cpu_online_mask.
Signed-off-by: liu chuansheng <chuansheng.liu@intel.com>
Acked-by: Yanmin Zhang <yanmin_zhang@linux.intel.com>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/27240C0AC20F114CBF8149A2696CBE4A137286@SHSMSX101.ccr.corp.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Commit 7849398fa2 introduced a bug,
causing the following error to be reported:
[ 370.827819] cannot lock PLL
[ 370.830749] CFG1 0x1e
[ 370.833160] CFG2 0x602004
[ 370.835876] CFG4 0x40000
[ 370.838562] omapdss HDMI: Failed to lock PLL
However, HDMI output is still enabled.
The problem is that we enable the HDMI video output temporarily when
reading EDID or detecting if a HDMI cable is connected (ugh), and the
commit above changes the behavior of the driver so that the video
timings are not yet configured at the point when EDID is read.
This patch fixes the problem by configuring the initial VGA timings at
HDMI probe.
Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
This comment is no longer true. We support up to 2^16 CPUs
because __ticket_t is an u16 if NR_CPUS is larger than 256.
Signed-off-by: Richard Weinberger <richard@nod.at>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
The destination address of unicast frames forwarded through a mesh gate
was being replaced with the broadcast address. Instead leave the
original destination address as the mesh DA. If the nexthop address is
not in the mpath table it will be resolved. If that fails, the frame
will be forwarded to known mesh gates.
Reported-by: Cedric Voncken <cedric.voncken@acksys.fr>
Signed-off-by: Thomas Pedersen <thomas@cozybit.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
This is a particularly nasty SCSI ATA Translation Layer (SATL) problem.
SAT-2 says (section 8.12.2)
if the device is in the stopped state as the result of
processing a START STOP UNIT command (see 9.11), then the SATL
shall terminate the TEST UNIT READY command with CHECK CONDITION
status with the sense key set to NOT READY and the additional
sense code of LOGICAL UNIT NOT READY, INITIALIZING COMMAND
REQUIRED;
mpt2sas internal SATL seems to implement this. The result is very confusing
standby behaviour (using hdparm -y). If you suspend a drive and then send
another command, usually it wakes up. However, if the next command is a TEST
UNIT READY, the SATL sees that the drive is suspended and proceeds to follow
the SATL rules for this, returning NOT READY to all subsequent commands. This
means that the ordering of TEST UNIT READY is crucial: if you send TUR and
then a command, you get a NOT READY to both back. If you send a command and
then a TUR, you get GOOD status because the preceeding command woke the drive.
This bit us badly because
commit 85ef06d1d2
Author: Tejun Heo <tj@kernel.org>
Date: Fri Jul 1 16:17:47 2011 +0200
block: flush MEDIA_CHANGE from drivers on close(2)
Changed our ordering on TEST UNIT READY commands meaning that SATA drives
connected to an mpt2sas now suspend and refuse to wake (because the mpt2sas
SATL sees the suspend *before* the drives get awoken by the next ATA command)
resulting in lots of failed commands.
The standard is completely nuts forcing this inconsistent behaviour, but we
have to work around it.
The fix for this is twofold:
1. Set the allow_restart flag so we wake the drive when we see it has been
suspended
2. Return all TEST UNIT READY status directly to the mid layer without any
further error handling which prevents us causing error handling which
may offline the device just because of a media check TUR.
Reported-by: Matthias Prager <linux@matthiasprager.de>
Cc: stable@vger.kernel.org
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
Instead of having to define the match table to NULL if CONFIG_OF isn't
set, use the of_match_ptr() macro which will do this for us.
Signed-off-by: Tobias Klauser <tklauser@distanz.ch>
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
The following patch moves the poll_aen_lock initializer from
megasas_probe_one() to megasas_init(). This prevents a crash when a user
loads the driver and tries to issue a poll() system call on the ioctl
interface with no adapters present.
Signed-off-by: Kashyap Desai <Kashyap.Desai@lsi.com>
Signed-off-by: Adam Radford <aradford@gmail.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
If the specified max_queue_depth setting is less than the
expected number of internal commands, then driver will calculate
the queue depth size to a negitive number. This negitive number
is actually a very large number because variable is unsigned
16bit integer. So, the driver will ask for a very large amount of
memory for message frames and resulting into oops as memory
allocation routines will not able to handle such a large request.
So, in order to limit this kind of oops, The driver need to set
the max_queue_depth to a scsi mid layer's can_queue value. Then
the overall message frames required for IO is minimum of either
(max_queue_depth plus internal commands) or the IOC global
credits.
Signed-off-by: Sreekanth Reddy <sreekanth.reddy@lsi.com>
Cc: <stable@kernel.org>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
Switch to using __u32/__s32 instead of ordinary 'int' in structures
forming userspace API.
Also internally make request_id unsigned int.
Signed-off-by: Dmitry Torokhov <dtor@mail.ru>
If uinput_request_submit() fails after new request ID was allocated
we need to mark that request ID as free, otherwise it will always
stay occupied and we may run out of available IDs.
Signed-off-by: Dmitry Torokhov <dtor@mail.ru>
Consider two threads calling read() on the same uinput-fd, both
non-blocking. Assume there is data-available so both will simultaneously
pass:
udev->head == udev->tail
Then the first thread goes to sleep and the second one pops the message
from the queue. Now assume udev->head == udev->tail. If the first thread
wakes up it will call wait_event_*() and sleep in the waitq. This
effectively turns the non-blocking FD into a blocking one.
We fix this by attempting to fetch events from the queue first and only
if we fail to retrieve any events we either return -EAGAIN (in case of
non-blocing read) or wait until there are more events.
This also fixes incorrect return code (we were returning 0 instead of
-EAGAIN for non-blocking reads) when an event is "stolen" by another
thread. Blocking reads will now continue to wait instead of returning 0
in this scenario.
Count of 0 continues to be a special case, as per spec: we will check for
device existence and whether there are events in the queue, but no events
will be actually retrieved.
Reported-by: David Herrmann <dh.herrmann@googlemail.com>
Signed-off-by: Dmitry Torokhov <dtor@mail.ru>
Let's check whether the user-supplied buffer is actually big enough and
return -EINVAL if it is not. This differs from current behavior, which
caused 0 to be returned and actually does not make any sense, as
broken application will simply repeat the read getting into endless
loop.
Note that we treat 0 as a special case, according to the standard:
"Before any action described below is taken, and if nbyte is zero,
the read() function may detect and return errors as described below.
In the absence of errors, or if error detection is not performed,
the read() function shall return zero and have no other results."
Signed-off-by: David Herrmann <dh.herrmann@googlemail.com>
Signed-off-by: Dmitry Torokhov <dtor@mail.ru>
When fetching events form device's buffer in uinput_read() we need to
take input device's event_lock to avoid racing with new event delivery.
Signed-off-by: Dmitry Torokhov <dtor@mail.ru>
MATCH_BIT() is ugly and stupid, we have much nicer bitmap_subset() which
does the same and does not hide control flow.
Reported-by: Baodong Chen <chenbdchenbd@gmail.com>
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
This adds devicetree bindings to the rotary encoder driver and some
documentation about how to use them. Tested on a PXA3xx platform.
Signed-off-by: Daniel Mack <zonque@gmail.com>
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Drivers should not be changing platform data attached to the device
because they do not own it.
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Use gpio_request_one() instead of separate calls to gpio_request() and
gpio_direction_input() to simplify the code.
Signed-off-by: Daniel Mack <zonque@gmail.com>
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Don't call gpio_to_irq() on GPIOs before gpio_request() succeeded on
them. This avoids Ooopses with incorrect DT bindings.
Signed-off-by: Daniel Mack <zonque@gmail.com>
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
As the power button causes a wake from suspend, we need to register
the event with the pm sustem to avoid racing with suspend.
As the input event is reported in the interrupt handler, as simple
pm_wakeup_event() is sufficient.
Signed-off-by: NeilBrown <neilb@suse.de>
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
In order to avoid races with suspend, a wakeup event must register as
such by calling pm_wakeup_event() or pm_stay_awake(). This will ensure
that the current suspend cycle aborts.
When the user-space visible event is created in the interrupt handler
(gpio_keys_irq_isr), a simple pm_wakeup_event() with no delay is
sufficient as suspend will synchronise with all interrupt delivery.
When the user-space visible event is created later
(gpio_keys_gpio_isr), we need to bracket the event with
pm_stay_awake() and pm_relax().
Signed-off-by: NeilBrown <neilb@suse.de>
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Adds support for the EMR digitizer on the Cintiq 24HD touch. The
EMR digitizer should work identically to that found on the Cintiq
24HD. The touch digitizer is a separate USB device similar to how
we split apart some other devices.
Signed-off-by: Jason Gerecke <killertofu@gmail.com>
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
They all define their chassis type as "Other" and therefore are not
categorized as "laptops" by the driver, which tries to perform AUX IRQ
delivery test which fails and causes touchpad not working.
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=42620
Cc: stable@kernel.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Ensure the hardware is correctly initialized before requesting the
interrupt, otherwise if a key was already touched since power-on the
kernel enters an interrupt loop. To fix this issue we clear pending
interrupt sources. We also have to make sure clk is enabled while
changing the keypad registers.
Signed-off-by: Michael Grzeschik <m.grzeschik@pengutronix.de>
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
This fixes the following breakage:
edt-ft5x06.c: In function edt_ft5x06_ts_remove:
edt-ft5x06.c:846:14: error: struct edt_ft5x06_ts_data has no member named
raw_buffer
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Acked-by: Simon Budig <simon.budig@kernelconcepts.de>
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Convert a 0 error return code to a negative one, as returned elsewhere in the
function.
A simplified version of the semantic match that finds this problem is as
follows: (http://coccinelle.lip6.fr/)
// <smpl>
@@
identifier ret;
expression e,e1,e2,e3,e4,x;
@@
(
if (\(ret != 0\|ret < 0\) || ...) { ... return ...; }
|
ret = 0
)
... when != ret = e1
*x = \(kmalloc\|kzalloc\|kcalloc\|devm_kzalloc\|ioremap\|ioremap_nocache\|devm_ioremap\|devm_ioremap_nocache\)(...);
... when != x = e2
when != ret = e3
*if (x == NULL || ...)
{
... when != ret = e4
* return ret;
}
// </smpl>
Signed-off-by: Julia Lawall <Julia.Lawall@lip6.fr>
Signed-off-by: Vinod Koul <vinod.koul@linux.intel.com>
So we've had a fair few reports of fbcon handover breakage between
efi/vesafb and i915 surface recently, so I dedicated a couple of
days to finding the problem.
Essentially the last thing we saw was the conflicting framebuffer
message and that was all.
So after much tracing with direct netconsole writes (printks
under console_lock not so useful), I think I found the race.
Thread A (driver load) Thread B (timer thread)
unbind_con_driver -> |
bind_con_driver -> |
vc->vc_sw->con_deinit -> |
fbcon_deinit -> |
console_lock() |
| |
| fbcon_flashcursor timer fires
| console_lock() <- blocked for A
|
|
fbcon_del_cursor_timer ->
del_timer_sync
(BOOM)
Of course because all of this is under the console lock,
we never see anything, also since we also just unbound the active
console guess what we never see anything.
Hopefully this fixes the problem for anyone seeing vesafb->kms
driver handoff.
v1.1: add comment suggestion from Alan.
Cc: stable@vger.kernel.org
Signed-off-by: Dave Airlie <airlied@redhat.com>
Fix some problems with the use of devm_ functions.
devm_kzalloc: devm_kfree is not needed
devm_ioremap: iounmap should not be used, no free is needed
devm_request_irq: the devm_free_irq is followed by irq_dispose_mapping. I
don't know if it is safe to move the freeing of the irq in this case, so I
have just un-devm'd this function, since the implicit freeing is never
taken advantage of.
In the original code failure of of_address_to_resource jumped to free_mem,
but should have jumped to irq_dispose, since irq_of_parse_and_map has
completed at this point.
In the original code unmap_mem was after irq_dispose, but it should have
been before, again since irq_of_parse_and_map has completed at this point.
One of these problems was found using the following semantic match:
(http://coccinelle.lip6.fr/)
// <smpl>
@@
expression x;
@@
*x = devm_ioremap(...)
...
iounmap(x);
// </smpl>
Signed-off-by: Julia Lawall <Julia.Lawall@lip6.fr>
Acked-by: Barry Song <Baohua.Song@csr.com>
Signed-off-by: Vinod Koul <vinod.koul@linux.intel.com>
Merge fixes from Andrew Morton.
Random drivers and some VM fixes.
* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (17 commits)
mm: compaction: Abort async compaction if locks are contended or taking too long
mm: have order > 0 compaction start near a pageblock with free pages
rapidio/tsi721: fix unused variable compiler warning
rapidio/tsi721: fix inbound doorbell interrupt handling
drivers/rtc/rtc-rs5c348.c: fix hour decoding in 12-hour mode
mm: correct page->pfmemalloc to fix deactivate_slab regression
drivers/rtc/rtc-pcf2123.c: initialize dynamic sysfs attributes
mm/compaction.c: fix deferring compaction mistake
drivers/misc/sgi-xp/xpc_uv.c: SGI XPC fails to load when cpu 0 is out of IRQ resources
string: do not export memweight() to userspace
hugetlb: update hugetlbpage.txt
checkpatch: add control statement test to SINGLE_STATEMENT_DO_WHILE_MACRO
mm: hugetlbfs: correctly populate shared pmd
cciss: fix incorrect scsi status reporting
Documentation: update mount option in filesystem/vfat.txt
mm: change nr_ptes BUG_ON to WARN_ON
cs5535-clockevt: typo, it's MFGPT, not MFPGT
Pull media fixes from Mauro Carvalho Chehab:
"For bug fixes, at soc_camera, si470x, uvcvideo, iguanaworks IR driver,
radio_shark Kbuild fixes, and at the V4L2 core (radio fixes)."
* 'v4l_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mchehab/linux-media:
[media] media: soc_camera: don't clear pix->sizeimage in JPEG mode
[media] media: mx2_camera: Fix clock handling for i.MX27
[media] video: mx2_camera: Use clk_prepare_enable/clk_disable_unprepare
[media] video: mx1_camera: Use clk_prepare_enable/clk_disable_unprepare
[media] media: mx3_camera: buf_init() add buffer state check
[media] radio-shark2: Only compile led support when CONFIG_LED_CLASS is set
[media] radio-shark: Only compile led support when CONFIG_LED_CLASS is set
[media] radio-shark*: Call cancel_work_sync from disconnect rather then release
[media] radio-shark*: Remove work-around for dangling pointer in usb intfdata
[media] Add USB dependency for IguanaWorks USB IR Transceiver
[media] Add missing logging for rangelow/high of hwseek
[media] VIDIOC_ENUM_FREQ_BANDS fix
[media] mem2mem_testdev: fix querycap regression
[media] si470x: v4l2-compliance fixes
[media] DocBook: Remove a spurious character
[media] uvcvideo: Reset the bytesused field when recycling an erroneous buffer
Pull networking update from David Miller:
"A couple weeks of bug fixing in there. The largest chunk is all the
broken crap Amerigo Wang found in the netpoll layer."
1) netpoll and it's users has several serious bugs:
a) uses GFP_KERNEL with locks held
b) interfaces requiring interrupts disabled are called with them
enabled
c) and vice versa
d) VLAN tag demuxing, as per all other RX packet input paths, is not
applied
All from Amerigo Wang.
2) Hopefully cure the ipv4 mapped ipv6 address TCP early demux bugs for
good, from Neal Cardwell.
3) Unlike AF_UNIX, AF_PACKET sockets don't set a default credentials
when the user doesn't specify one explicitly during sendmsg().
Instead we attach an empty (zero) SCM credential block which is
definitely not what we want. Fix from Eric Dumazet.
4) IPv6 illegally invokes netdevice notifiers with RCU lock held, fix
from Ben Hutchings.
5) inet_csk_route_child_sock() checks wrong inet options pointer, fix
from Christoph Paasch.
6) When AF_PACKET is used for transmit, packet loopback doesn't behave
properly when a socket fanout is enabled, from Eric Leblond.
7) On bluetooth l2cap channel create failure, we leak the socket, from
Jaganath Kanakkassery.
8) Fix all the netprio file handling bugs found by Al Viro, from John
Fastabend.
9) Several error return and NULL deref bug fixes in networking drivers
from Julia Lawall.
10) A large smattering of struct padding et al. kernel memory leaks to
userspace found of Mathias Krause.
11) Conntrack expections in netfilter can access an uninitialized timer,
fix from Pablo Neira Ayuso.
12) Several netfilter SIP tracker bug fixes from Patrick McHardy.
13) IPSEC ipv6 routes are not initialized correctly all the time,
resulting in an OOPS in inet_putpeer(). Also from Patrick McHardy.
14) Bridging does rcu_dereference() outside of RCU protected area, from
Stephen Hemminger.
15) Fix routing cache removal performance regression when looking up
output routes that have a local destination. From Zheng Yan.
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (87 commits)
af_netlink: force credentials passing [CVE-2012-3520]
ipv4: fix ip header ident selection in __ip_make_skb()
ipv4: Use newinet->inet_opt in inet_csk_route_child_sock()
tcp: fix possible socket refcount problem
net: tcp: move sk_rx_dst_set call after tcp_create_openreq_child()
net/core/dev.c: fix kernel-doc warning
netconsole: remove a redundant netconsole_target_put()
net: ipv6: fix oops in inet_putpeer()
net/stmmac: fix issue of clk_get for Loongson1B.
caif: Do not dereference NULL in chnl_recv_cb()
af_packet: don't emit packet on orig fanout group
drivers/net/irda: fix error return code
drivers/net/wan/dscc4.c: fix error return code
drivers/net/wimax/i2400m/fw.c: fix error return code
smsc75xx: add missing entry to MAINTAINERS
net: qmi_wwan: new devices: UML290 and K5006-Z
net: sh_eth: Add eth support for R8A7779 device
netdev/phy: skip disabled mdio-mux nodes
dt: introduce for_each_available_child_of_node, of_get_next_available_child
net: netprio: fix cgrp create and write priomap race
...
Jim Schutt reported a problem that pointed at compaction contending
heavily on locks. The workload is straight-forward and in his own words;
The systems in question have 24 SAS drives spread across 3 HBAs,
running 24 Ceph OSD instances, one per drive. FWIW these servers
are dual-socket Intel 5675 Xeons w/48 GB memory. I've got ~160
Ceph Linux clients doing dd simultaneously to a Ceph file system
backed by 12 of these servers.
Early in the test everything looks fine
procs -------------------memory------------------ ---swap-- -----io---- --system-- -----cpu-------
r b swpd free buff cache si so bi bo in cs us sy id wa st
31 15 0 287216 576 38606628 0 0 2 1158 2 14 1 3 95 0 0
27 15 0 225288 576 38583384 0 0 18 2222016 203357 134876 11 56 17 15 0
28 17 0 219256 576 38544736 0 0 11 2305932 203141 146296 11 49 23 17 0
6 18 0 215596 576 38552872 0 0 7 2363207 215264 166502 12 45 22 20 0
22 18 0 226984 576 38596404 0 0 3 2445741 223114 179527 12 43 23 22 0
and then it goes to pot
procs -------------------memory------------------ ---swap-- -----io---- --system-- -----cpu-------
r b swpd free buff cache si so bi bo in cs us sy id wa st
163 8 0 464308 576 36791368 0 0 11 22210 866 536 3 13 79 4 0
207 14 0 917752 576 36181928 0 0 712 1345376 134598 47367 7 90 1 2 0
123 12 0 685516 576 36296148 0 0 429 1386615 158494 60077 8 84 5 3 0
123 12 0 598572 576 36333728 0 0 1107 1233281 147542 62351 7 84 5 4 0
622 7 0 660768 576 36118264 0 0 557 1345548 151394 59353 7 85 4 3 0
223 11 0 283960 576 36463868 0 0 46 1107160 121846 33006 6 93 1 1 0
Note that system CPU usage is very high blocks being written out has
dropped by 42%. He analysed this with perf and found
perf record -g -a sleep 10
perf report --sort symbol --call-graph fractal,5
34.63% [k] _raw_spin_lock_irqsave
|
|--97.30%-- isolate_freepages
| compaction_alloc
| unmap_and_move
| migrate_pages
| compact_zone
| compact_zone_order
| try_to_compact_pages
| __alloc_pages_direct_compact
| __alloc_pages_slowpath
| __alloc_pages_nodemask
| alloc_pages_vma
| do_huge_pmd_anonymous_page
| handle_mm_fault
| do_page_fault
| page_fault
| |
| |--87.39%-- skb_copy_datagram_iovec
| | tcp_recvmsg
| | inet_recvmsg
| | sock_recvmsg
| | sys_recvfrom
| | system_call
| | __recv
| | |
| | --100.00%-- (nil)
| |
| --12.61%-- memcpy
--2.70%-- [...]
There was other data but primarily it is all showing that compaction is
contended heavily on the zone->lock and zone->lru_lock.
commit [b2eef8c0: mm: compaction: minimise the time IRQs are disabled
while isolating pages for migration] noted that it was possible for
migration to hold the lru_lock for an excessive amount of time. Very
broadly speaking this patch expands the concept.
This patch introduces compact_checklock_irqsave() to check if a lock
is contended or the process needs to be scheduled. If either condition
is true then async compaction is aborted and the caller is informed.
The page allocator will fail a THP allocation if compaction failed due
to contention. This patch also introduces compact_trylock_irqsave()
which will acquire the lock only if it is not contended and the process
does not need to schedule.
Reported-by: Jim Schutt <jaschut@sandia.gov>
Tested-by: Jim Schutt <jaschut@sandia.gov>
Signed-off-by: Mel Gorman <mgorman@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Commit 7db8889ab0 ("mm: have order > 0 compaction start off where it
left") introduced a caching mechanism to reduce the amount work the free
page scanner does in compaction. However, it has a problem. Consider
two process simultaneously scanning free pages
C
Process A M S F
|---------------------------------------|
Process B M FS
C is zone->compact_cached_free_pfn
S is cc->start_pfree_pfn
M is cc->migrate_pfn
F is cc->free_pfn
In this diagram, Process A has just reached its migrate scanner, wrapped
around and updated compact_cached_free_pfn accordingly.
Simultaneously, Process B finishes isolating in a block and updates
compact_cached_free_pfn again to the location of its free scanner.
Process A moves to "end_of_zone - one_pageblock" and runs this check
if (cc->order > 0 && (!cc->wrapped ||
zone->compact_cached_free_pfn >
cc->start_free_pfn))
pfn = min(pfn, zone->compact_cached_free_pfn);
compact_cached_free_pfn is above where it started so the free scanner
skips almost the entire space it should have scanned. When there are
multiple processes compacting it can end in a situation where the entire
zone is not being scanned at all. Further, it is possible for two
processes to ping-pong update to compact_cached_free_pfn which is just
random.
Overall, the end result wrecks allocation success rates.
There is not an obvious way around this problem without introducing new
locking and state so this patch takes a different approach.
First, it gets rid of the skip logic because it's not clear that it
matters if two free scanners happen to be in the same block but with
racing updates it's too easy for it to skip over blocks it should not.
Second, it updates compact_cached_free_pfn in a more limited set of
circumstances.
If a scanner has wrapped, it updates compact_cached_free_pfn to the end
of the zone. When a wrapped scanner isolates a page, it updates
compact_cached_free_pfn to point to the highest pageblock it
can isolate pages from.
If a scanner has not wrapped when it has finished isolated pages it
checks if compact_cached_free_pfn is pointing to the end of the
zone. If so, the value is updated to point to the highest
pageblock that pages were isolated from. This value will not
be updated again until a free page scanner wraps and resets
compact_cached_free_pfn.
This is not optimal and it can still race but the compact_cached_free_pfn
will be pointing to or very near a pageblock with free pages.
Signed-off-by: Mel Gorman <mgorman@suse.de>
Reviewed-by: Rik van Riel <riel@redhat.com>
Reviewed-by: Minchan Kim <minchan@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Fix unused variable compiler warning when built with CONFIG_RAPIDIO_DEBUG
option off.
This patch is applicable to kernel versions starting from v3.2
Signed-off-by: Alexandre Bounine <alexandre.bounine@idt.com>
Cc: Matt Porter <mporter@kernel.crashing.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Make sure that there is no doorbell messages left behind due to disabled
interrupts during inbound doorbell processing.
The most common case for this bug is loss of rionet JOIN messages in
systems with three or more rionet participants and MSI or MSI-X enabled.
As result, requests for packet transfers may finish with "destination
unreachable" error message.
This patch is applicable to kernel versions starting from v3.2.
Signed-off-by: Alexandre Bounine <alexandre.bounine@idt.com>
Cc: Matt Porter <mporter@kernel.crashing.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Correct the offset by subtracting 20 from tm_hour before taking the
modulo 12.
[ "Why 20?" I hear you ask. Or at least I did.
Here's the reason why: RS5C348_BIT_PM is 32, and is - stupidly -
included in the RS5C348_HOURS_MASK define. So it's really subtracting
out that bit to get "hour+12". But then because it does things modulo
12, it needs to add the 12 in again afterwards anyway.
This code is confused. It would be much clearer if RS5C348_HOURS_MASK
just didn't include the RS5C348_BIT_PM bit at all, then it wouldn't
need to do the silly subtract either.
Whatever. It's all just math, the end result is the same. - Linus ]
Reported-by: James Nute <newten82@gmail.com>
Tested-by: James Nute <newten82@gmail.com>
Signed-off-by: Atsushi Nemoto <anemo@mba.ocn.ne.jp>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Commit cfd19c5a9e ("mm: only set page->pfmemalloc when
ALLOC_NO_WATERMARKS was used") tried to narrow down page->pfmemalloc
setting, but it missed some places the pfmemalloc should be set.
So, in __slab_alloc, the unalignment pfmemalloc and ALLOC_NO_WATERMARKS
cause incorrect deactivate_slab() on our core2 server:
64.73% fio [kernel.kallsyms] [k] _raw_spin_lock
|
--- _raw_spin_lock
|
|---0.34%-- deactivate_slab
| __slab_alloc
| kmem_cache_alloc
| |
That causes our fio sync write performance to have a 40% regression.
Move the checking in get_page_from_freelist() which resolves this issue.
Signed-off-by: Alex Shi <alex.shi@intel.com>
Acked-by: Mel Gorman <mgorman@suse.de>
Cc: David Miller <davem@davemloft.net
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Tested-by: Eric Dumazet <eric.dumazet@gmail.com>
Tested-by: Sage Weil <sage@inktank.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Dynamically allocated sysfs attributes must be initialized using
sysfs_attr_init(), otherwise lockdep complains: BUG: key <address> not in
.data!
Found by Linux Driver Verification project (linuxtesting.org).
Signed-off-by: Ilya Shchepetkov <shchepetkov@ispras.ru>
Cc: Chris Verges <chrisv@cyberswitching.com>
Cc: Christian Pellegrin <chripell@fsfe.org>
Cc: Alessandro Zummo <a.zummo@towertech.it>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Commit aff622495c ("vmscan: only defer compaction for failed order and
higher") fixed bad deferring policy but made mistake about checking
compact_order_failed in __compact_pgdat(). So it can't update
compact_order_failed with the new order. This ends up preventing
correct operation of policy deferral. This patch fixes it.
Signed-off-by: Minchan Kim <minchan@kernel.org>
Reviewed-by: Rik van Riel <riel@redhat.com>
Acked-by: Mel Gorman <mel@csn.ul.ie>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
On many of our larger systems, CPU 0 has had all of its IRQ resources
consumed before XPC loads. Worst cases on machines with multiple 10
GigE cards and multiple IB cards have depleted the entire first socket
of IRQs.
This patch makes selecting the node upon which IRQs are allocated (as
well as all the other GRU Message Queue structures) specifiable as a
module load param and has a default behavior of searching all nodes/cpus
for an available resources.
[akpm@linux-foundation.org: fix build: include cpu.h and module.h]
Signed-off-by: Robin Holt <holt@sgi.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
