JITed BPF programs are indistinguishable from kernel functions, but unlike
kernel code BPF code can be changed often.
Typical approach of "perf record" + "perf report" profiling and tuning of
kernel code works just as well for BPF programs, but kernel code doesn't
need to be monitored whereas BPF programs do.
Users load and run large amount of BPF programs.
These BPF stats allow tools monitor the usage of BPF on the server.
The monitoring tools will turn sysctl kernel.bpf_stats_enabled
on and off for few seconds to sample average cost of the programs.
Aggregated data over hours and days will provide an insight into cost of BPF
and alarms can trigger in case given program suddenly gets more expensive.
The cost of two sched_clock() per program invocation adds ~20 nsec.
Fast BPF progs (like selftests/bpf/progs/test_pkt_access.c) will slow down
from ~10 nsec to ~30 nsec.
static_key minimizes the cost of the stats collection.
There is no measurable difference before/after this patch
with kernel.bpf_stats_enabled=0
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
If the number of input parameters is less than the total parameters, an
EINVAL error will be returned.
For example, we use proc_doulongvec_minmax to pass up to two parameters
with kern_table:
{
.procname = "monitor_signals",
.data = &monitor_sigs,
.maxlen = 2*sizeof(unsigned long),
.mode = 0644,
.proc_handler = proc_doulongvec_minmax,
},
Reproduce:
When passing two parameters, it's work normal. But passing only one
parameter, an error "Invalid argument"(EINVAL) is returned.
[root@cl150 ~]# echo 1 2 > /proc/sys/kernel/monitor_signals
[root@cl150 ~]# cat /proc/sys/kernel/monitor_signals
1 2
[root@cl150 ~]# echo 3 > /proc/sys/kernel/monitor_signals
-bash: echo: write error: Invalid argument
[root@cl150 ~]# echo $?
1
[root@cl150 ~]# cat /proc/sys/kernel/monitor_signals
3 2
[root@cl150 ~]#
The following is the result after apply this patch. No error is
returned when the number of input parameters is less than the total
parameters.
[root@cl150 ~]# echo 1 2 > /proc/sys/kernel/monitor_signals
[root@cl150 ~]# cat /proc/sys/kernel/monitor_signals
1 2
[root@cl150 ~]# echo 3 > /proc/sys/kernel/monitor_signals
[root@cl150 ~]# echo $?
0
[root@cl150 ~]# cat /proc/sys/kernel/monitor_signals
3 2
[root@cl150 ~]#
There are three processing functions dealing with digital parameters,
__do_proc_dointvec/__do_proc_douintvec/__do_proc_doulongvec_minmax.
This patch deals with __do_proc_doulongvec_minmax, just as
__do_proc_dointvec does, adding a check for parameters 'left'. In
__do_proc_douintvec, its code implementation explicitly does not support
multiple inputs.
static int __do_proc_douintvec(...){
...
/*
* Arrays are not supported, keep this simple. *Do not* add
* support for them.
*/
if (vleft != 1) {
*lenp = 0;
return -EINVAL;
}
...
}
So, just __do_proc_doulongvec_minmax has the problem. And most use of
proc_doulongvec_minmax/proc_doulongvec_ms_jiffies_minmax just have one
parameter.
Link: http://lkml.kernel.org/r/1544081775-15720-1-git-send-email-cheng.lin130@zte.com.cn
Signed-off-by: Cheng Lin <cheng.lin130@zte.com.cn>
Acked-by: Luis Chamberlain <mcgrof@kernel.org>
Reviewed-by: Kees Cook <keescook@chromium.org>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
An external fragmentation event was previously described as
When the page allocator fragments memory, it records the event using
the mm_page_alloc_extfrag event. If the fallback_order is smaller
than a pageblock order (order-9 on 64-bit x86) then it's considered
an event that will cause external fragmentation issues in the future.
The kernel reduces the probability of such events by increasing the
watermark sizes by calling set_recommended_min_free_kbytes early in the
lifetime of the system. This works reasonably well in general but if
there are enough sparsely populated pageblocks then the problem can still
occur as enough memory is free overall and kswapd stays asleep.
This patch introduces a watermark_boost_factor sysctl that allows a zone
watermark to be temporarily boosted when an external fragmentation causing
events occurs. The boosting will stall allocations that would decrease
free memory below the boosted low watermark and kswapd is woken if the
calling context allows to reclaim an amount of memory relative to the size
of the high watermark and the watermark_boost_factor until the boost is
cleared. When kswapd finishes, it wakes kcompactd at the pageblock order
to clean some of the pageblocks that may have been affected by the
fragmentation event. kswapd avoids any writeback, slab shrinkage and swap
from reclaim context during this operation to avoid excessive system
disruption in the name of fragmentation avoidance. Care is taken so that
kswapd will do normal reclaim work if the system is really low on memory.
This was evaluated using the same workloads as "mm, page_alloc: Spread
allocations across zones before introducing fragmentation".
1-socket Skylake machine
config-global-dhp__workload_thpfioscale XFS (no special madvise)
4 fio threads, 1 THP allocating thread
--------------------------------------
4.20-rc3 extfrag events < order 9: 804694
4.20-rc3+patch: 408912 (49% reduction)
4.20-rc3+patch1-4: 18421 (98% reduction)
4.20.0-rc3 4.20.0-rc3
lowzone-v5r8 boost-v5r8
Amean fault-base-1 653.58 ( 0.00%) 652.71 ( 0.13%)
Amean fault-huge-1 0.00 ( 0.00%) 178.93 * -99.00%*
4.20.0-rc3 4.20.0-rc3
lowzone-v5r8 boost-v5r8
Percentage huge-1 0.00 ( 0.00%) 5.12 ( 100.00%)
Note that external fragmentation causing events are massively reduced by
this path whether in comparison to the previous kernel or the vanilla
kernel. The fault latency for huge pages appears to be increased but that
is only because THP allocations were successful with the patch applied.
1-socket Skylake machine
global-dhp__workload_thpfioscale-madvhugepage-xfs (MADV_HUGEPAGE)
-----------------------------------------------------------------
4.20-rc3 extfrag events < order 9: 291392
4.20-rc3+patch: 191187 (34% reduction)
4.20-rc3+patch1-4: 13464 (95% reduction)
thpfioscale Fault Latencies
4.20.0-rc3 4.20.0-rc3
lowzone-v5r8 boost-v5r8
Min fault-base-1 912.00 ( 0.00%) 905.00 ( 0.77%)
Min fault-huge-1 127.00 ( 0.00%) 135.00 ( -6.30%)
Amean fault-base-1 1467.55 ( 0.00%) 1481.67 ( -0.96%)
Amean fault-huge-1 1127.11 ( 0.00%) 1063.88 * 5.61%*
4.20.0-rc3 4.20.0-rc3
lowzone-v5r8 boost-v5r8
Percentage huge-1 77.64 ( 0.00%) 83.46 ( 7.49%)
As before, massive reduction in external fragmentation events, some jitter
on latencies and an increase in THP allocation success rates.
2-socket Haswell machine
config-global-dhp__workload_thpfioscale XFS (no special madvise)
4 fio threads, 5 THP allocating threads
----------------------------------------------------------------
4.20-rc3 extfrag events < order 9: 215698
4.20-rc3+patch: 200210 (7% reduction)
4.20-rc3+patch1-4: 14263 (93% reduction)
4.20.0-rc3 4.20.0-rc3
lowzone-v5r8 boost-v5r8
Amean fault-base-5 1346.45 ( 0.00%) 1306.87 ( 2.94%)
Amean fault-huge-5 3418.60 ( 0.00%) 1348.94 ( 60.54%)
4.20.0-rc3 4.20.0-rc3
lowzone-v5r8 boost-v5r8
Percentage huge-5 0.78 ( 0.00%) 7.91 ( 910.64%)
There is a 93% reduction in fragmentation causing events, there is a big
reduction in the huge page fault latency and allocation success rate is
higher.
2-socket Haswell machine
global-dhp__workload_thpfioscale-madvhugepage-xfs (MADV_HUGEPAGE)
-----------------------------------------------------------------
4.20-rc3 extfrag events < order 9: 166352
4.20-rc3+patch: 147463 (11% reduction)
4.20-rc3+patch1-4: 11095 (93% reduction)
thpfioscale Fault Latencies
4.20.0-rc3 4.20.0-rc3
lowzone-v5r8 boost-v5r8
Amean fault-base-5 6217.43 ( 0.00%) 7419.67 * -19.34%*
Amean fault-huge-5 3163.33 ( 0.00%) 3263.80 ( -3.18%)
4.20.0-rc3 4.20.0-rc3
lowzone-v5r8 boost-v5r8
Percentage huge-5 95.14 ( 0.00%) 87.98 ( -7.53%)
There is a large reduction in fragmentation events with some jitter around
the latencies and success rates. As before, the high THP allocation
success rate does mean the system is under a lot of pressure. However, as
the fragmentation events are reduced, it would be expected that the
long-term allocation success rate would be higher.
Link: http://lkml.kernel.org/r/20181123114528.28802-5-mgorman@techsingularity.net
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Zi Yan <zi.yan@cs.rutgers.edu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Introduce CONFIG_STACKLEAK_RUNTIME_DISABLE option, which provides
'stack_erasing' sysctl. It can be used in runtime to control kernel
stack erasing for kernels built with CONFIG_GCC_PLUGIN_STACKLEAK.
Suggested-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Alexander Popov <alex.popov@linux.com>
Tested-by: Laura Abbott <labbott@redhat.com>
Signed-off-by: Kees Cook <keescook@chromium.org>
Disallows open of FIFOs or regular files not owned by the user in world
writable sticky directories, unless the owner is the same as that of the
directory or the file is opened without the O_CREAT flag. The purpose
is to make data spoofing attacks harder. This protection can be turned
on and off separately for FIFOs and regular files via sysctl, just like
the symlinks/hardlinks protection. This patch is based on Openwall's
"HARDEN_FIFO" feature by Solar Designer.
This is a brief list of old vulnerabilities that could have been prevented
by this feature, some of them even allow for privilege escalation:
CVE-2000-1134
CVE-2007-3852
CVE-2008-0525
CVE-2009-0416
CVE-2011-4834
CVE-2015-1838
CVE-2015-7442
CVE-2016-7489
This list is not meant to be complete. It's difficult to track down all
vulnerabilities of this kind because they were often reported without any
mention of this particular attack vector. In fact, before
hardlinks/symlinks restrictions, fifos/regular files weren't the favorite
vehicle to exploit them.
[s.mesoraca16@gmail.com: fix bug reported by Dan Carpenter]
Link: https://lkml.kernel.org/r/20180426081456.GA7060@mwanda
Link: http://lkml.kernel.org/r/1524829819-11275-1-git-send-email-s.mesoraca16@gmail.com
[keescook@chromium.org: drop pr_warn_ratelimited() in favor of audit changes in the future]
[keescook@chromium.org: adjust commit subjet]
Link: http://lkml.kernel.org/r/20180416175918.GA13494@beast
Signed-off-by: Salvatore Mesoraca <s.mesoraca16@gmail.com>
Signed-off-by: Kees Cook <keescook@chromium.org>
Suggested-by: Solar Designer <solar@openwall.com>
Suggested-by: Kees Cook <keescook@chromium.org>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Currently task hung checking interval is equal to timeout, as the result
hung is detected anywhere between timeout and 2*timeout. This is fine for
most interactive environments, but this hurts automated testing setups
(syzbot). In an automated setup we need to strictly order CPU lockup <
RCU stall < workqueue lockup < task hung < silent loss, so that RCU stall
is not detected as task hung and task hung is not detected as silent
machine loss. The large variance in task hung detection timeout requires
setting silent machine loss timeout to a very large value (e.g. if task
hung is 3 mins, then silent loss need to be set to ~7 mins). The
additional 3 minutes significantly reduce testing efficiency because
usually we crash kernel within a minute, and this can add hours to bug
localization process as it needs to do dozens of tests.
Allow setting checking interval separately from timeout. This allows to
set timeout to, say, 3 minutes, but checking interval to 10 secs.
The interval is controlled via a new hung_task_check_interval_secs sysctl,
similar to the existing hung_task_timeout_secs sysctl. The default value
of 0 results in the current behavior: checking interval is equal to
timeout.
[akpm@linux-foundation.org: update hung_task_timeout_max's comment]
Link: http://lkml.kernel.org/r/20180611111004.203513-1-dvyukov@google.com
Signed-off-by: Dmitry Vyukov <dvyukov@google.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Currently one requires to test four kernel configurations to test the
firmware API completely:
0)
CONFIG_FW_LOADER=y
1)
o CONFIG_FW_LOADER=y
o CONFIG_FW_LOADER_USER_HELPER=y
2)
o CONFIG_FW_LOADER=y
o CONFIG_FW_LOADER_USER_HELPER=y
o CONFIG_FW_LOADER_USER_HELPER_FALLBACK=y
3) When CONFIG_FW_LOADER=m the built-in stuff is disabled, we have
no current tests for this.
We can reduce the requirements to three kernel configurations by making
fw_config.force_sysfs_fallback a proc knob we flip on off. For kernels that
disable CONFIG_IKCONFIG_PROC this can also enable one to inspect if
CONFIG_FW_LOADER_USER_HELPER_FALLBACK was enabled at build time by checking
the proc value at boot time.
Acked-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Luis R. Rodriguez <mcgrof@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Patch series "pipe: buffer limits fixes and cleanups", v2.
This series simplifies the sysctl handler for pipe-max-size and fixes
another set of bugs related to the pipe buffer limits:
- The root user wasn't allowed to exceed the limits when creating new
pipes.
- There was an off-by-one error when checking the limits, so a limit of
N was actually treated as N - 1.
- F_SETPIPE_SZ accepted values over UINT_MAX.
- Reading the pipe buffer limits could be racy.
This patch (of 7):
Before validating the given value against pipe_min_size,
do_proc_dopipe_max_size_conv() calls round_pipe_size(), which rounds the
value up to pipe_min_size. Therefore, the second check against
pipe_min_size is redundant. Remove it.
Link: http://lkml.kernel.org/r/20180111052902.14409-2-ebiggers3@gmail.com
Signed-off-by: Eric Biggers <ebiggers@google.com>
Acked-by: Kees Cook <keescook@chromium.org>
Acked-by: Joe Lawrence <joe.lawrence@redhat.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: "Luis R . Rodriguez" <mcgrof@kernel.org>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: Mikulas Patocka <mpatocka@redhat.com>
Cc: Willy Tarreau <w@1wt.eu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
hugepages_treat_as_movable has been introduced by 396faf0303 ("Allow
huge page allocations to use GFP_HIGH_MOVABLE") to allow hugetlb
allocations from ZONE_MOVABLE even when hugetlb pages were not
migrateable. The purpose of the movable zone was different at the time.
It aimed at reducing memory fragmentation and hugetlb pages being long
lived and large werre not contributing to the fragmentation so it was
acceptable to use the zone back then.
Things have changed though and the primary purpose of the zone became
migratability guarantee. If we allow non migrateable hugetlb pages to
be in ZONE_MOVABLE memory hotplug might fail to offline the memory.
Remove the knob and only rely on hugepage_migration_supported to allow
movable zones.
Mel said:
: Primarily it was aimed at allowing the hugetlb pool to safely shrink with
: the ability to grow it again. The use case was for batched jobs, some of
: which needed huge pages and others that did not but didn't want the memory
: useless pinned in the huge pages pool.
:
: I suspect that more users rely on THP than hugetlbfs for flexible use of
: huge pages with fallback options so I think that removing the option
: should be ok.
Link: http://lkml.kernel.org/r/20171003072619.8654-1-mhocko@kernel.org
Signed-off-by: Michal Hocko <mhocko@suse.com>
Reported-by: Alexandru Moise <00moses.alexander00@gmail.com>
Acked-by: Mel Gorman <mgorman@suse.de>
Cc: Alexandru Moise <00moses.alexander00@gmail.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Mikulas noticed in the existing do_proc_douintvec_minmax_conv() and
do_proc_dopipe_max_size_conv() introduced in this patchset, that they
inconsistently handle overflow and min/max range inputs:
For example:
0 ... param->min - 1 ---> ERANGE
param->min ... param->max ---> the value is accepted
param->max + 1 ... 0x100000000L + param->min - 1 ---> ERANGE
0x100000000L + param->min ... 0x100000000L + param->max ---> EINVAL
0x100000000L + param->max + 1, 0x200000000L + param->min - 1 ---> ERANGE
0x200000000L + param->min ... 0x200000000L + param->max ---> EINVAL
0x200000000L + param->max + 1, 0x300000000L + param->min - 1 ---> ERANGE
In do_proc_do*() routines which store values into unsigned int variables
(4 bytes wide for 64-bit builds), first validate that the input unsigned
long value (8 bytes wide for 64-bit builds) will fit inside the smaller
unsigned int variable. Then check that the unsigned int value falls
inside the specified parameter min, max range. Otherwise the unsigned
long -> unsigned int conversion drops leading bits from the input value,
leading to the inconsistent pattern Mikulas documented above.
Link: http://lkml.kernel.org/r/1507658689-11669-5-git-send-email-joe.lawrence@redhat.com
Signed-off-by: Joe Lawrence <joe.lawrence@redhat.com>
Reported-by: Mikulas Patocka <mpatocka@redhat.com>
Reviewed-by: Mikulas Patocka <mpatocka@redhat.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
pipe_max_size is assigned directly via procfs sysctl:
static struct ctl_table fs_table[] = {
...
{
.procname = "pipe-max-size",
.data = &pipe_max_size,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = &pipe_proc_fn,
.extra1 = &pipe_min_size,
},
...
int pipe_proc_fn(struct ctl_table *table, int write, void __user *buf,
size_t *lenp, loff_t *ppos)
{
...
ret = proc_dointvec_minmax(table, write, buf, lenp, ppos)
...
and then later rounded in-place a few statements later:
...
pipe_max_size = round_pipe_size(pipe_max_size);
...
This leaves a window of time between initial assignment and rounding
that may be visible to other threads. (For example, one thread sets a
non-rounded value to pipe_max_size while another reads its value.)
Similar reads of pipe_max_size are potentially racy:
pipe.c :: alloc_pipe_info()
pipe.c :: pipe_set_size()
Add a new proc_dopipe_max_size() that consolidates reading the new value
from the user buffer, verifying bounds, and calling round_pipe_size()
with a single assignment to pipe_max_size.
Link: http://lkml.kernel.org/r/1507658689-11669-4-git-send-email-joe.lawrence@redhat.com
Signed-off-by: Joe Lawrence <joe.lawrence@redhat.com>
Reported-by: Mikulas Patocka <mpatocka@redhat.com>
Reviewed-by: Mikulas Patocka <mpatocka@redhat.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Patch series "A few round_pipe_size() and pipe-max-size fixups", v3.
While backporting Michael's "pipe: fix limit handling" patchset to a
distro-kernel, Mikulas noticed that current upstream pipe limit handling
contains a few problems:
1 - procfs signed wrap: echo'ing a large number into
/proc/sys/fs/pipe-max-size and then cat'ing it back out shows a
negative value.
2 - round_pipe_size() nr_pages overflow on 32bit: this would
subsequently try roundup_pow_of_two(0), which is undefined.
3 - visible non-rounded pipe-max-size value: there is no mutual
exclusion or protection between the time pipe_max_size is assigned
a raw value from proc_dointvec_minmax() and when it is rounded.
4 - unsigned long -> unsigned int conversion makes for potential odd
return errors from do_proc_douintvec_minmax_conv() and
do_proc_dopipe_max_size_conv().
This version underwent the same testing as v1:
https://marc.info/?l=linux-kernel&m=150643571406022&w=2
This patch (of 4):
pipe_max_size is defined as an unsigned int:
unsigned int pipe_max_size = 1048576;
but its procfs/sysctl representation is an integer:
static struct ctl_table fs_table[] = {
...
{
.procname = "pipe-max-size",
.data = &pipe_max_size,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = &pipe_proc_fn,
.extra1 = &pipe_min_size,
},
...
that is signed:
int pipe_proc_fn(struct ctl_table *table, int write, void __user *buf,
size_t *lenp, loff_t *ppos)
{
...
ret = proc_dointvec_minmax(table, write, buf, lenp, ppos)
This leads to signed results via procfs for large values of pipe_max_size:
% echo 2147483647 >/proc/sys/fs/pipe-max-size
% cat /proc/sys/fs/pipe-max-size
-2147483648
Use unsigned operations on this variable to avoid such negative values.
Link: http://lkml.kernel.org/r/1507658689-11669-2-git-send-email-joe.lawrence@redhat.com
Signed-off-by: Joe Lawrence <joe.lawrence@redhat.com>
Reported-by: Mikulas Patocka <mpatocka@redhat.com>
Reviewed-by: Mikulas Patocka <mpatocka@redhat.com>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This is the second step which introduces a tunable interface that allow
numa stats configurable for optimizing zone_statistics(), as suggested
by Dave Hansen and Ying Huang.
=========================================================================
When page allocation performance becomes a bottleneck and you can
tolerate some possible tool breakage and decreased numa counter
precision, you can do:
echo 0 > /proc/sys/vm/numa_stat
In this case, numa counter update is ignored. We can see about
*4.8%*(185->176) drop of cpu cycles per single page allocation and
reclaim on Jesper's page_bench01 (single thread) and *8.1%*(343->315)
drop of cpu cycles per single page allocation and reclaim on Jesper's
page_bench03 (88 threads) running on a 2-Socket Broadwell-based server
(88 threads, 126G memory).
Benchmark link provided by Jesper D Brouer (increase loop times to
10000000):
https://github.com/netoptimizer/prototype-kernel/tree/master/kernel/mm/bench
=========================================================================
When page allocation performance is not a bottleneck and you want all
tooling to work, you can do:
echo 1 > /proc/sys/vm/numa_stat
This is system default setting.
Many thanks to Michal Hocko, Dave Hansen, Ying Huang and Vlastimil Babka
for comments to help improve the original patch.
[keescook@chromium.org: make sure mutex is a global static]
Link: http://lkml.kernel.org/r/20171107213809.GA4314@beast
Link: http://lkml.kernel.org/r/1508290927-8518-1-git-send-email-kemi.wang@intel.com
Signed-off-by: Kemi Wang <kemi.wang@intel.com>
Signed-off-by: Kees Cook <keescook@chromium.org>
Reported-by: Jesper Dangaard Brouer <brouer@redhat.com>
Suggested-by: Dave Hansen <dave.hansen@intel.com>
Suggested-by: Ying Huang <ying.huang@intel.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: "Luis R . Rodriguez" <mcgrof@kernel.org>
Cc: Kees Cook <keescook@chromium.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Christopher Lameter <cl@linux.com>
Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: Andrey Ryabinin <aryabinin@virtuozzo.com>
Cc: Tim Chen <tim.c.chen@intel.com>
Cc: Andi Kleen <andi.kleen@intel.com>
Cc: Aaron Lu <aaron.lu@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
