Across suspend, we may see a very large drift in timestamps if the sched
clock is unstable, prompting the global trace's ringbuffer code to warn
and suggest switching to the global clock. Preempt this request by
detecting when the sched clock is unstable (determined during
late_initcall) and automatically switching the default clock over to
trace_global_clock.
This should prevent requiring user interaction to resolve warnings such
as:
Delta way too big! 18446743856563626466 ts=18446744054496180323 write stamp = 197932553857
If you just came from a suspend/resume,
please switch to the trace global clock:
echo global > /sys/kernel/debug/tracing/trace_clock
Link: http://lkml.kernel.org/r/20180330150132.16903-1-chris@chris-wilson.co.uk
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Pull perf/urgent fixes from Arnaldo Carvalho de Melo:
- Show group details on the title line in the annotate browser
and 'perf annotate --stdio2' output, so that the per-event
columns can have headers (Arnaldo Carvalho de Melo)
- Fixup vertical line separating metrics from instructions and
cleaning unused lines at the bottom, both in the annotate TUI
browser (Arnaldo Carvalho de Melo)
- Remove duplicated 'samples' in lost samples warning in
'perf report' (Arnaldo Carvalho de Melo)
- Synchronize i915_drm.h, silencing the perf build process,
automagically adding support for the new DRM_I915_QUERY
ioctl (Arnaldo Carvalho de Melo)
- Make auxtrace_queues__add_buffer() allocate struct buffer,
from a patchkit already applied (Adrian Hunter)
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Commit 84676c1f21 ("genirq/affinity: assign vectors to all possible CPUs")
tried to spread the interrupts accross all possible CPUs to make sure that
in case of phsyical hotplug (e.g. virtualization) the CPUs which get
plugged in after the device was initialized are targeted by a hardware
queue and the corresponding interrupt.
This has a downside in cases where the ACPI tables claim that there are
more possible CPUs than present CPUs and the number of interrupts to spread
out is smaller than the number of possible CPUs. These bogus ACPI tables
are unfortunately not uncommon.
In such a case the vector spreading algorithm assigns interrupts to CPUs
which can never be utilized and as a consequence these interrupts are
unused instead of being mapped to present CPUs. As a result the performance
of the device is suboptimal.
To fix this spread the interrupt vectors in two stages:
1) Spread as many interrupts as possible among the present CPUs
2) Spread the remaining vectors among non present CPUs
On a 8 core system, where CPU 0-3 are present and CPU 4-7 are not present,
for a device with 4 queues the resulting interrupt affinity is:
1) Before 84676c1f21 ("genirq/affinity: assign vectors to all possible CPUs")
irq 39, cpu list 0
irq 40, cpu list 1
irq 41, cpu list 2
irq 42, cpu list 3
2) With 84676c1f21 ("genirq/affinity: assign vectors to all possible CPUs")
irq 39, cpu list 0-2
irq 40, cpu list 3-4,6
irq 41, cpu list 5
irq 42, cpu list 7
3) With the refined vector spread applied:
irq 39, cpu list 0,4
irq 40, cpu list 1,6
irq 41, cpu list 2,5
irq 42, cpu list 3,7
On a 8 core system, where all CPUs are present the resulting interrupt
affinity for the 4 queues is:
irq 39, cpu list 0,1
irq 40, cpu list 2,3
irq 41, cpu list 4,5
irq 42, cpu list 6,7
This is independent of the number of CPUs which are online at the point of
initialization because in such a system the offline CPUs can be easily
onlined afterwards, while in non-present CPUs need to be plugged physically
or virtually which requires external interaction.
The downside of this approach is that in case of physical hotplug the
interrupt vector spreading might be suboptimal when CPUs 4-7 are physically
plugged. Suboptimal from a NUMA point of view and due to the single target
nature of interrupt affinities the later plugged CPUs might not be targeted
by interrupts at all.
Though, physical hotplug systems are not the common case while the broken
ACPI table disease is wide spread. So it's preferred to have as many
interrupts as possible utilized at the point where the device is
initialized.
Block multi-queue devices like NVME create a hardware queue per possible
CPU, so the goal of commit 84676c1f21 to assign one interrupt vector per
possible CPU is still achieved even with physical/virtual hotplug.
[ tglx: Changed from online to present CPUs for the first spreading stage,
renamed variables for readability sake, added comments and massaged
changelog ]
Reported-by: Laurence Oberman <loberman@redhat.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: linux-block@vger.kernel.org
Cc: Christoph Hellwig <hch@infradead.org>
Link: https://lkml.kernel.org/r/20180308105358.1506-5-ming.lei@redhat.com
When the allocation of node_to_possible_cpumask fails, then
irq_create_affinity_masks() returns with a pointer to the empty affinity
masks array, which will cause malfunction.
Reorder the allocations so the masks array allocation comes last and every
failure path returns NULL.
Fixes: 9a0ef98e18 ("genirq/affinity: Assign vectors to all present CPUs")
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Ming Lei <ming.lei@redhat.com>
Open code readX() inside inX() so that inX() variants have their own
overrideable Port IO barrier combinations as __io_pbr() and __io_par() for
actions to be taken before port IO and after port IO read.
Signed-off-by: Sinan Kaya <okaya@codeaurora.org>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Open code writeX() inside outX() so that outX() variants have their own
overrideable Port IO barrier combinations as __io_pbw() and __io_paw() for
actions to be taken before port IO and after port IO write.
Signed-off-by: Sinan Kaya <okaya@codeaurora.org>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
The default implementation of mapping writeX() to __raw_writeX() is wrong.
writeX() has stronger ordering semantics. Compiler is allowed to reorder
memory writes against __raw_writeX().
Use the previously defined __io_aw() and __io_bw() macros to harden
code generation according to architecture support.
Signed-off-by: Sinan Kaya <okaya@codeaurora.org>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
The default implementation of mapping readX() to __raw_readX() is wrong.
readX() has stronger ordering semantics. Compiler is allowed to reorder
__raw_readX() against the memory accesses following register read.
Use the previously defined __io_ar() and __io_br() macros to harden
code generation according to architecture support.
Signed-off-by: Sinan Kaya <okaya@codeaurora.org>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Getting ready to harden readX()/writeX() and inX()/outX() semantics for the
generic implementation.
Defining two set of macros as __io_br() and __io_ar() to indicate actions
to be taken before and after MMIO read.
Defining two set of macros as __io_bw() and __io_aw() to indicate actions
to be taken before and after MMIO write.
Defining two set of macros as __io_pbw() and __io_paw() to indicate actions
to be taken before and after Port IO write.
Defining two set of macros as __io_pbr() and __io_par() to indicate actions
to be taken before and after Port IO read.
If rmb() is available for the architecture, prefer rmb() as the default
implementation of __io_ar()/__io_par().
If wmb() is available for the architecture, prefer wmb() as the default
implementation of __io_bw()/__io_pbw().
Signed-off-by: Sinan Kaya <okaya@codeaurora.org>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Add a new pointer argument to cpuidle_select() and to the ->select
cpuidle governor callback to allow a boolean value indicating
whether or not the tick should be stopped before entering the
selected state to be returned from there.
Make the ladder governor ignore that pointer (to preserve its
current behavior) and make the menu governor return 'false" through
it if:
(1) the idle exit latency is constrained at 0, or
(2) the selected state is a polling one, or
(3) the expected idle period duration is within the tick period
range.
In addition to that, the correction factor computations in the menu
governor need to take the possibility that the tick may not be
stopped into account to avoid artificially small correction factor
values. To that end, add a mechanism to record tick wakeups, as
suggested by Peter Zijlstra, and use it to modify the menu_update()
behavior when tick wakeup occurs. Namely, if the CPU is woken up by
the tick and the return value of tick_nohz_get_sleep_length() is not
within the tick boundary, the predicted idle duration is likely too
short, so make menu_update() try to compensate for that by updating
the governor statistics as though the CPU was idle for a long time.
Since the value returned through the new argument pointer of
cpuidle_select() is not used by its caller yet, this change by
itself is not expected to alter the functionality of the code.
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Since the subsequent changes will need a TICK_USEC definition
analogous to TICK_NSEC, rename the existing TICK_USEC as
USER_TICK_USEC, update its users and redefine TICK_USEC
accordingly.
Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Frederic Weisbecker <frederic@kernel.org>
Currently calling list_del on smd subdev remove path results in
null pointer dereference on glink only platforms. Fix this by
adding safety checks in glink/smd subdev remove paths.
Signed-off-by: Sibi Sankar <sibis@codeaurora.org>
Signed-off-by: Bjorn Andersson <bjorn.andersson@linaro.org>
I got "oom_reaper: unable to reap pid:" messages when the victim thread
was blocked inside free_pgtables() (which occurred after returning from
unmap_vmas() and setting MMF_OOM_SKIP). We don't need to complain when
exit_mmap() already set MMF_OOM_SKIP.
Killed process 7558 (a.out) total-vm:4176kB, anon-rss:84kB, file-rss:0kB, shmem-rss:0kB
oom_reaper: unable to reap pid:7558 (a.out)
a.out D13272 7558 6931 0x00100084
Call Trace:
schedule+0x2d/0x80
rwsem_down_write_failed+0x2bb/0x440
call_rwsem_down_write_failed+0x13/0x20
down_write+0x49/0x60
unlink_file_vma+0x28/0x50
free_pgtables+0x36/0x100
exit_mmap+0xbb/0x180
mmput+0x50/0x110
copy_process.part.41+0xb61/0x1fe0
_do_fork+0xe6/0x560
do_syscall_64+0x74/0x230
entry_SYSCALL_64_after_hwframe+0x42/0xb7
Link: http://lkml.kernel.org/r/201803221946.DHG65638.VFJHFtOSQLOMOF@I-love.SAKURA.ne.jp
Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Acked-by: David Rientjes <rientjes@google.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This patch fixes a corner case for KSM. When two pages belong or
belonged to the same transparent hugepage, and they should be merged,
KSM fails to split the page, and therefore no merging happens.
This bug can be reproduced by:
* making sure ksm is running (in case disabling ksmtuned)
* enabling transparent hugepages
* allocating a THP-aligned 1-THP-sized buffer
e.g. on amd64: posix_memalign(&p, 1<<21, 1<<21)
* filling it with the same values
e.g. memset(p, 42, 1<<21)
* performing madvise to make it mergeable
e.g. madvise(p, 1<<21, MADV_MERGEABLE)
* waiting for KSM to perform a few scans
The expected outcome is that the all the pages get merged (1 shared and
the rest sharing); the actual outcome is that no pages get merged (1
unshared and the rest volatile)
The reason of this behaviour is that we increase the reference count
once for both pages we want to merge, but if they belong to the same
hugepage (or compound page), the reference counter used in both cases is
the one of the head of the compound page. This means that
split_huge_page will find a value of the reference counter too high and
will fail.
This patch solves this problem by testing if the two pages to merge
belong to the same hugepage when attempting to merge them. If so, the
hugepage is split safely. This means that the hugepage is not split if
not necessary.
Link: http://lkml.kernel.org/r/1521548069-24758-1-git-send-email-imbrenda@linux.vnet.ibm.com
Signed-off-by: Claudio Imbrenda <imbrenda@linux.vnet.ibm.com>
Co-authored-by: Gerald Schaefer <gerald.schaefer@de.ibm.com>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Currently <linux/slab.h> #includes <linux/kmemleak.h> for no obvious
reason. It looks like it's only a convenience, so remove kmemleak.h
from slab.h and add <linux/kmemleak.h> to any users of kmemleak_* that
don't already #include it. Also remove <linux/kmemleak.h> from source
files that do not use it.
This is tested on i386 allmodconfig and x86_64 allmodconfig. It would
be good to run it through the 0day bot for other $ARCHes. I have
neither the horsepower nor the storage space for the other $ARCHes.
Update: This patch has been extensively build-tested by both the 0day
bot & kisskb/ozlabs build farms. Both of them reported 2 build failures
for which patches are included here (in v2).
[ slab.h is the second most used header file after module.h; kernel.h is
right there with slab.h. There could be some minor error in the
counting due to some #includes having comments after them and I didn't
combine all of those. ]
[akpm@linux-foundation.org: security/keys/big_key.c needs vmalloc.h, per sfr]
Link: http://lkml.kernel.org/r/e4309f98-3749-93e1-4bb7-d9501a39d015@infradead.org
Link: http://kisskb.ellerman.id.au/kisskb/head/13396/
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Reviewed-by: Ingo Molnar <mingo@kernel.org>
Reported-by: Michael Ellerman <mpe@ellerman.id.au> [2 build failures]
Reported-by: Fengguang Wu <fengguang.wu@intel.com> [2 build failures]
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Wei Yongjun <weiyongjun1@huawei.com>
Cc: Luis R. Rodriguez <mcgrof@kernel.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Mimi Zohar <zohar@linux.vnet.ibm.com>
Cc: John Johansen <john.johansen@canonical.com>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
At present the construct
if (VM_WARN(...))
will compile OK with CONFIG_DEBUG_VM=y and will fail with
CONFIG_DEBUG_VM=n. The reason is that VM_{WARN,BUG}* have always been
special wrt. {WARN/BUG}* and never generate any code when DEBUG_VM is
disabled. So we cannot really use it in conditionals.
We considered changing things so that this construct works in both cases
but that might cause unwanted code generation with CONFIG_DEBUG_VM=n.
It is safer and simpler to make the build fail in both cases.
[akpm@linux-foundation.org: changelog]
Signed-off-by: Michal Hocko <mhocko@suse.com>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
start_isolate_page_range() is used to set the migrate type of a set of
pageblocks to MIGRATE_ISOLATE while attempting to start a migration
operation. It assumes that only one thread is calling it for the
specified range. This routine is used by CMA, memory hotplug and
gigantic huge pages. Each of these users synchronize access to the
range within their subsystem. However, two subsystems (CMA and gigantic
huge pages for example) could attempt operations on the same range. If
this happens, one thread may 'undo' the work another thread is doing.
This can result in pageblocks being incorrectly left marked as
MIGRATE_ISOLATE and therefore not available for page allocation.
What is ideally needed is a way to synchronize access to a set of
pageblocks that are undergoing isolation and migration. The only thing
we know about these pageblocks is that they are all in the same zone. A
per-node mutex is too coarse as we want to allow multiple operations on
different ranges within the same zone concurrently. Instead, we will
use the migration type of the pageblocks themselves as a form of
synchronization.
start_isolate_page_range sets the migration type on a set of page-
blocks going in order from the one associated with the smallest pfn to
the largest pfn. The zone lock is acquired to check and set the
migration type. When going through the list of pageblocks check if
MIGRATE_ISOLATE is already set. If so, this indicates another thread is
working on this pageblock. We know exactly which pageblocks we set, so
clean up by undo those and return -EBUSY.
This allows start_isolate_page_range to serve as a synchronization
mechanism and will allow for more general use of callers making use of
these interfaces. Update comments in alloc_contig_range to reflect this
new functionality.
Each CPU holds the associated zone lock to modify or examine the
migration type of a pageblock. And, it will only examine/update a
single pageblock per lock acquire/release cycle.
Link: http://lkml.kernel.org/r/20180309224731.16978-1-mike.kravetz@oracle.com
Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Luiz Capitulino <lcapitulino@redhat.com>
Cc: Michal Nazarewicz <mina86@mina86.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The plan for these patches is to introduce the typedef, initially just
as documentation ("These functions should return a VM_FAULT_ status").
We'll trickle the patches to individual drivers/filesystems in through
the maintainers, as far as possible. Then we'll change the typedef to
an unsigned int and break the compilation of any unconverted
drivers/filesystems.
vmf_insert_page(), vmf_insert_mixed() and vmf_insert_pfn() are three
newly added functions. The various drivers/filesystems where return
value of fault(), huge_fault(), page_mkwrite() and pfn_mkwrite() get
converted, will need them. These functions will return correct
VM_FAULT_ code based on err value.
We've had bugs before where drivers returned -EFOO. And we have this
silly inefficiency where vm_insert_xxx() return an errno which (afaict)
every driver then converts into a VM_FAULT code. In many cases drivers
failed to return correct VM_FAULT code value despite of vm_insert_xxx()
fails. We have indentified and clean up all those existing bugs and
silly inefficiencies in driver/filesystems by adding these three new
inline wrappers. As mentioned above, we will trickle those patches to
individual drivers/filesystems in through maintainers after these three
wrapper functions are merged.
Eventually we can convert vm_insert_xxx() into vmf_insert_xxx() and
remove these inline wrappers, but these are a good intermediate step.
Link: http://lkml.kernel.org/r/20180310162351.GA7422@jordon-HP-15-Notebook-PC
Signed-off-by: Souptick Joarder <jrdr.linux@gmail.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Matthew Wilcox <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Kswapd will not wakeup if per-zone watermarks are not failing or if too
many previous attempts at background reclaim have failed.
This can be true if there is a lot of free memory available. For high-
order allocations, kswapd is responsible for waking up kcompactd for
background compaction. If the zone is not below its watermarks or
reclaim has recently failed (lots of free memory, nothing left to
reclaim), kcompactd does not get woken up.
When __GFP_DIRECT_RECLAIM is not allowed, allow kcompactd to still be
woken up even if kswapd will not reclaim. This allows high-order
allocations, such as thp, to still trigger background compaction even
when the zone has an abundance of free memory.
Link: http://lkml.kernel.org/r/alpine.DEB.2.20.1803111659420.209721@chino.kir.corp.google.com
Signed-off-by: David Rientjes <rientjes@google.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Mel Gorman <mgorman@techsingularity.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
KASAN splats indicate that in some cases we free a live mm, then
continue to access it, with potentially disastrous results. This is
likely due to a mismatched mmdrop() somewhere in the kernel, but so far
the culprit remains elusive.
Let's have __mmdrop() verify that the mm isn't live for the current
task, similar to the existing check for init_mm. This way, we can catch
this class of issue earlier, and without requiring KASAN.
Currently, idle_task_exit() leaves active_mm stale after it switches to
init_mm. This isn't harmful, but will trigger the new assertions, so we
must adjust idle_task_exit() to update active_mm.
Link: http://lkml.kernel.org/r/20180312140103.19235-1-mark.rutland@arm.com
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Will Deacon <will.deacon@arm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
During the reclaiming slab of a memcg, shrink_slab iterates over all
registered shrinkers in the system, and tries to count and consume
objects related to the cgroup. In case of memory pressure, this behaves
bad: I observe high system time and time spent in list_lru_count_one()
for many processes on RHEL7 kernel.
This patch makes list_lru_node::memcg_lrus rcu protected, that allows to
skip taking spinlock in list_lru_count_one().
Shakeel Butt with the patch observes significant perf graph change. He
says:
========================================================================
Setup: running a fork-bomb in a memcg of 200MiB on a 8GiB and 4 vcpu
VM and recording the trace with 'perf record -g -a'.
The trace without the patch:
+ 34.19% fb.sh [kernel.kallsyms] [k] queued_spin_lock_slowpath
+ 30.77% fb.sh [kernel.kallsyms] [k] _raw_spin_lock
+ 3.53% fb.sh [kernel.kallsyms] [k] list_lru_count_one
+ 2.26% fb.sh [kernel.kallsyms] [k] super_cache_count
+ 1.68% fb.sh [kernel.kallsyms] [k] shrink_slab
+ 0.59% fb.sh [kernel.kallsyms] [k] down_read_trylock
+ 0.48% fb.sh [kernel.kallsyms] [k] _raw_spin_unlock_irqrestore
+ 0.38% fb.sh [kernel.kallsyms] [k] shrink_node_memcg
+ 0.32% fb.sh [kernel.kallsyms] [k] queue_work_on
+ 0.26% fb.sh [kernel.kallsyms] [k] count_shadow_nodes
With the patch:
+ 0.16% swapper [kernel.kallsyms] [k] default_idle
+ 0.13% oom_reaper [kernel.kallsyms] [k] mutex_spin_on_owner
+ 0.05% perf [kernel.kallsyms] [k] copy_user_generic_string
+ 0.05% init.real [kernel.kallsyms] [k] wait_consider_task
+ 0.05% kworker/0:0 [kernel.kallsyms] [k] finish_task_switch
+ 0.04% kworker/2:1 [kernel.kallsyms] [k] finish_task_switch
+ 0.04% kworker/3:1 [kernel.kallsyms] [k] finish_task_switch
+ 0.04% kworker/1:0 [kernel.kallsyms] [k] finish_task_switch
+ 0.03% binary [kernel.kallsyms] [k] copy_page
========================================================================
Thanks Shakeel for the testing.
[ktkhai@virtuozzo.com: v2]
Link: http://lkml.kernel.org/r/151203869520.3915.2587549826865799173.stgit@localhost.localdomain
Link: http://lkml.kernel.org/r/150583358557.26700.8490036563698102569.stgit@localhost.localdomain
Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Tested-by: Shakeel Butt <shakeelb@google.com>
Acked-by: Vladimir Davydov <vdavydov.dev@gmail.com>
Cc: Andrey Ryabinin <aryabinin@virtuozzo.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Remove ZRAM's enforced "huge object" value and use zsmalloc huge-class
watermark instead, which makes more sense.
TEST
- I used a 1G zram device, LZO compression back-end, original
data set size was 444MB. Looking at zsmalloc classes stats the
test ended up to be pretty fair.
BASE ZRAM/ZSMALLOC
=====================
zram mm_stat
498978816 191482495 199831552 0 199831552 15634 0
zsmalloc classes
class size almost_full almost_empty obj_allocated obj_used pages_used pages_per_zspage freeable
...
151 2448 0 0 1240 1240 744 3 0
168 2720 0 0 4200 4200 2800 2 0
190 3072 0 0 10100 10100 7575 3 0
202 3264 0 0 380 380 304 4 0
254 4096 0 0 10620 10620 10620 1 0
Total 7 46 106982 106187 48787 0
PATCHED ZRAM/ZSMALLOC
=====================
zram mm_stat
498978816 182579184 194248704 0 194248704 15628 0
zsmalloc classes
class size almost_full almost_empty obj_allocated obj_used pages_used pages_per_zspage freeable
...
151 2448 0 0 1240 1240 744 3 0
168 2720 0 0 4200 4200 2800 2 0
190 3072 0 0 10100 10100 7575 3 0
202 3264 0 0 7180 7180 5744 4 0
254 4096 0 0 3820 3820 3820 1 0
Total 8 45 106959 106193 47424 0
As we can see, we reduced the number of objects stored in class-4096,
because a huge number of objects which we previously forcibly stored in
class-4096 now stored in non-huge class-3264. This results in lower
memory consumption:
- zsmalloc now uses 47424 physical pages, which is less than 48787 pages
zsmalloc used before.
- objects that we store in class-3264 share zspages. That's why overall
the number of pages that both class-4096 and class-3264 consumed went
down from 10924 to 9564.
[sergey.senozhatsky.work@gmail.com: add pool param to zs_huge_class_size()]
Link: http://lkml.kernel.org/r/20180314081833.1096-3-sergey.senozhatsky@gmail.com
Link: http://lkml.kernel.org/r/20180306070639.7389-3-sergey.senozhatsky@gmail.com
Signed-off-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Acked-by: Minchan Kim <minchan@kernel.org>
Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Patch series "zsmalloc/zram: drop zram's max_zpage_size", v3.
ZRAM's max_zpage_size is a bad thing. It forces zsmalloc to store
normal objects as huge ones, which results in bigger zsmalloc memory
usage. Drop it and use actual zsmalloc huge-class value when decide if
the object is huge or not.
This patch (of 2):
Not every object can be share its zspage with other objects, e.g. when
the object is as big as zspage or nearly as big a zspage. For such
objects zsmalloc has a so called huge class - every object which belongs
to huge class consumes the entire zspage (which consists of a physical
page). On x86_64, PAGE_SHIFT 12 box, the first non-huge class size is
3264, so starting down from size 3264, objects can share page(-s) and
thus minimize memory wastage.
ZRAM, however, has its own statically defined watermark for huge
objects, namely "3 * PAGE_SIZE / 4 = 3072", and forcibly stores every
object larger than this watermark (3072) as a PAGE_SIZE object, in other
words, to a huge class, while zsmalloc can keep some of those objects in
non-huge classes. This results in increased memory consumption.
zsmalloc knows better if the object is huge or not. Introduce
zs_huge_class_size() function which tells if the given object can be
stored in one of non-huge classes or not. This will let us to drop
ZRAM's huge object watermark and fully rely on zsmalloc when we decide
if the object is huge.
[sergey.senozhatsky.work@gmail.com: add pool param to zs_huge_class_size()]
Link: http://lkml.kernel.org/r/20180314081833.1096-2-sergey.senozhatsky@gmail.com
Link: http://lkml.kernel.org/r/20180306070639.7389-2-sergey.senozhatsky@gmail.com
Signed-off-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Acked-by: Minchan Kim <minchan@kernel.org>
Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Thanks to commit 4b3ef9daa4 ("mm/swap: split swap cache into 64MB
trunks"), after swapoff the address_space associated with the swap
device will be freed. So page_mapping() users which may touch the
address_space need some kind of mechanism to prevent the address_space
from being freed during accessing.
The dcache flushing functions (flush_dcache_page(), etc) in architecture
specific code may access the address_space of swap device for anonymous
pages in swap cache via page_mapping() function. But in some cases
there are no mechanisms to prevent the swap device from being swapoff,
for example,
CPU1 CPU2
__get_user_pages() swapoff()
flush_dcache_page()
mapping = page_mapping()
... exit_swap_address_space()
... kvfree(spaces)
mapping_mapped(mapping)
The address space may be accessed after being freed.
But from cachetlb.txt and Russell King, flush_dcache_page() only care
about file cache pages, for anonymous pages, flush_anon_page() should be
used. The implementation of flush_dcache_page() in all architectures
follows this too. They will check whether page_mapping() is NULL and
whether mapping_mapped() is true to determine whether to flush the
dcache immediately. And they will use interval tree (mapping->i_mmap)
to find all user space mappings. While mapping_mapped() and
mapping->i_mmap isn't used by anonymous pages in swap cache at all.
So, to fix the race between swapoff and flush dcache, __page_mapping()
is add to return the address_space for file cache pages and NULL
otherwise. All page_mapping() invoking in flush dcache functions are
replaced with page_mapping_file().
[akpm@linux-foundation.org: simplify page_mapping_file(), per Mike]
Link: http://lkml.kernel.org/r/20180305083634.15174-1-ying.huang@intel.com
Signed-off-by: "Huang, Ying" <ying.huang@intel.com>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Chen Liqin <liqin.linux@gmail.com>
Cc: Russell King <linux@armlinux.org.uk>
Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
Cc: "James E.J. Bottomley" <jejb@parisc-linux.org>
Cc: Guan Xuetao <gxt@mprc.pku.edu.cn>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Chris Zankel <chris@zankel.net>
Cc: Vineet Gupta <vgupta@synopsys.com>
Cc: Ley Foon Tan <lftan@altera.com>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Patch series "mm, smaps: MMUPageSize for device-dax", v3.
Similar to commit 31383c6865 ("mm, hugetlbfs: introduce ->split() to
vm_operations_struct") here is another occasion where we want
special-case hugetlbfs/hstate enabling to also apply to device-dax.
This prompts the question what other hstate conversions we might do
beyond ->split() and ->pagesize(), but this appears to be the last of
the usages of hstate_vma() in generic/non-hugetlbfs specific code paths.
This patch (of 3):
The current powerpc definition of vma_mmu_pagesize() open codes looking
up the page size via hstate. It is identical to the generic
vma_kernel_pagesize() implementation.
Now, vma_kernel_pagesize() is growing support for determining the page
size of Device-DAX vmas in addition to the existing Hugetlbfs page size
determination.
Ideally, if the powerpc vma_mmu_pagesize() used vma_kernel_pagesize() it
would automatically benefit from any new vma-type support that is added
to vma_kernel_pagesize(). However, the powerpc vma_mmu_pagesize() is
prevented from calling vma_kernel_pagesize() due to a circular header
dependency that requires vma_mmu_pagesize() to be defined before
including <linux/hugetlb.h>.
Break this circular dependency by defining the default vma_mmu_pagesize()
as a __weak symbol to be overridden by the powerpc version.
Link: http://lkml.kernel.org/r/151996254179.27922.2213728278535578744.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Jane Chu <jane.chu@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
When a page is freed back to the global pool, its buddy will be checked
to see if it's possible to do a merge. This requires accessing buddy's
page structure and that access could take a long time if it's cache
cold.
This patch adds a prefetch to the to-be-freed page's buddy outside of
zone->lock in hope of accessing buddy's page structure later under
zone->lock will be faster. Since we *always* do buddy merging and check
an order-0 page's buddy to try to merge it when it goes into the main
allocator, the cacheline will always come in, i.e. the prefetched data
will never be unused.
Normally, the number of prefetch will be pcp->batch(default=31 and has
an upper limit of (PAGE_SHIFT * 8)=96 on x86_64) but in the case of
pcp's pages get all drained, it will be pcp->count which has an upper
limit of pcp->high. pcp->high, although has a default value of 186
(pcp->batch=31 * 6), can be changed by user through
/proc/sys/vm/percpu_pagelist_fraction and there is no software upper
limit so could be large, like several thousand. For this reason, only
the first pcp->batch number of page's buddy structure is prefetched to
avoid excessive prefetching.
In the meantime, there are two concerns:
1. the prefetch could potentially evict existing cachelines, especially
for L1D cache since it is not huge
2. there is some additional instruction overhead, namely calculating
buddy pfn twice
For 1, it's hard to say, this microbenchmark though shows good result
but the actual benefit of this patch will be workload/CPU dependant;
For 2, since the calculation is a XOR on two local variables, it's
expected in many cases that cycles spent will be offset by reduced
memory latency later. This is especially true for NUMA machines where
multiple CPUs are contending on zone->lock and the most time consuming
part under zone->lock is the wait of 'struct page' cacheline of the
to-be-freed pages and their buddies.
Test with will-it-scale/page_fault1 full load:
kernel Broadwell(2S) Skylake(2S) Broadwell(4S) Skylake(4S)
v4.16-rc2+ 9034215 7971818 13667135 15677465
patch2/3 9536374 +5.6% 8314710 +4.3% 14070408 +3.0% 16675866 +6.4%
this patch 10180856 +6.8% 8506369 +2.3% 14756865 +4.9% 17325324 +3.9%
Note: this patch's performance improvement percent is against patch2/3.
(Changelog stolen from Dave Hansen and Mel Gorman's comments at
http://lkml.kernel.org/r/148a42d8-8306-2f2f-7f7c-86bc118f8ccd@intel.com)
[aaron.lu@intel.com: use helper function, avoid disordering pages]
Link: http://lkml.kernel.org/r/20180301062845.26038-4-aaron.lu@intel.com
Link: http://lkml.kernel.org/r/20180320113146.GB24737@intel.com
[aaron.lu@intel.com: v4]
Link: http://lkml.kernel.org/r/20180301062845.26038-4-aaron.lu@intel.com
Link: http://lkml.kernel.org/r/20180309082431.GB30868@intel.com
Link: http://lkml.kernel.org/r/20180301062845.26038-4-aaron.lu@intel.com
Signed-off-by: Aaron Lu <aaron.lu@intel.com>
Suggested-by: Ying Huang <ying.huang@intel.com>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Kemi Wang <kemi.wang@intel.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Tim Chen <tim.c.chen@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
It's possible for free pages to become stranded on per-cpu pagesets
(pcps) that, if drained, could be merged with buddy pages on the zone's
free area to form large order pages, including up to MAX_ORDER.
Consider a verbose example using the tools/vm/page-types tool at the
beginning of a ZONE_NORMAL ('B' indicates a buddy page and 'S' indicates
a slab page). Pages on pcps do not have any page flags set.
109954 1 _______S________________________________________________________
109955 2 __________B_____________________________________________________
109957 1 ________________________________________________________________
109958 1 __________B_____________________________________________________
109959 7 ________________________________________________________________
109960 1 __________B_____________________________________________________
109961 9 ________________________________________________________________
10996a 1 __________B_____________________________________________________
10996b 3 ________________________________________________________________
10996e 1 __________B_____________________________________________________
10996f 1 ________________________________________________________________
...
109f8c 1 __________B_____________________________________________________
109f8d 2 ________________________________________________________________
109f8f 2 __________B_____________________________________________________
109f91 f ________________________________________________________________
109fa0 1 __________B_____________________________________________________
109fa1 7 ________________________________________________________________
109fa8 1 __________B_____________________________________________________
109fa9 1 ________________________________________________________________
109faa 1 __________B_____________________________________________________
109fab 1 _______S________________________________________________________
The compaction migration scanner is attempting to defragment this memory
since it is at the beginning of the zone. It has done so quite well,
all movable pages have been migrated. From pfn [0x109955, 0x109fab),
there are only buddy pages and pages without flags set.
These pages may be stranded on pcps that could otherwise allow this
memory to be coalesced if freed back to the zone free area. It is
possible that some of these pages may not be on pcps and that something
has called alloc_pages() and used the memory directly, but we rely on
the absence of __GFP_MOVABLE in these cases to allocate from
MIGATE_UNMOVABLE pageblocks to try to keep these MIGRATE_MOVABLE
pageblocks as free as possible.
These buddy and pcp pages, spanning 1,621 pages, could be coalesced and
allow for three transparent hugepages to be dynamically allocated.
Running the numbers for all such spans on the system, it was found that
there were over 400 such spans of only buddy pages and pages without
flags set at the time this /proc/kpageflags sample was collected.
Without this support, there were _no_ order-9 or order-10 pages free.
When kcompactd fails to defragment memory such that a cc.order page can
be allocated, drain all pcps for the zone back to the buddy allocator so
this stranding cannot occur. Compaction for that order will
subsequently be deferred, which acts as a ratelimit on this drain.
Link: http://lkml.kernel.org/r/alpine.DEB.2.20.1803010340100.88270@chino.kir.corp.google.com
Signed-off-by: David Rientjes <rientjes@google.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Mel Gorman <mgorman@techsingularity.net>
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>
should_failslab() is a convenient function to hook into for directed
error injection into kmalloc(). However, it is only available if a
config flag is set.
The following BCC script, for example, fails kmalloc() calls after a
btrfs umount:
from bcc import BPF
prog = r"""
BPF_HASH(flag);
#include <linux/mm.h>
int kprobe__btrfs_close_devices(void *ctx) {
u64 key = 1;
flag.update(&key, &key);
return 0;
}
int kprobe__should_failslab(struct pt_regs *ctx) {
u64 key = 1;
u64 *res;
res = flag.lookup(&key);
if (res != 0) {
bpf_override_return(ctx, -ENOMEM);
}
return 0;
}
"""
b = BPF(text=prog)
while 1:
b.kprobe_poll()
This patch refactors the should_failslab implementation so that the
function is always available for error injection, independent of flags.
This change would be similar in nature to commit f5490d3ec921 ("block:
Add should_fail_bio() for bpf error injection").
Link: http://lkml.kernel.org/r/20180222020320.6944-1-hmclauchlan@fb.com
Signed-off-by: Howard McLauchlan <hmclauchlan@fb.com>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Akinobu Mita <akinobu.mita@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>
Cc: Josef Bacik <jbacik@fb.com>
Cc: Johannes Weiner <jweiner@fb.com>
Cc: Alexei Starovoitov <ast@fb.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
