Skip to content

R
raspberrypi-kernel

openeuler / raspberrypi-kernel

通知 13
Star 1
Fork 0
R
raspberrypi-kernel
切换分支/标签
  1. 02 3月, 2017 6 次提交
  3. 28 2月, 2017 1 次提交
  5. 23 2月, 2017 1 次提交
  7. 20 2月, 2017 1 次提交
  9. 03 2月, 2017 2 次提交
    • P
      prctl: propagate has_child_subreaper flag to every descendant · 749860ce
      由 Pavel Tikhomirov 提交于 
      If process forks some children when it has is_child_subreaper
flag enabled they will inherit has_child_subreaper flag - first
group, when is_child_subreaper is disabled forked children will
not inherit it - second group. So child-subreaper does not reparent
all his descendants when their parents die. Having these two
differently behaving groups can lead to confusion. Also it is
a problem for CRIU, as when we restore process tree we need to
somehow determine which descendants belong to which group and
much harder - to put them exactly to these group.

To simplify these we can add a propagation of has_child_subreaper
flag on PR_SET_CHILD_SUBREAPER, walking all descendants of child-
subreaper to setup has_child_subreaper flag.

In common cases when process like systemd first sets itself to
be a child-subreaper and only after that forks its services, we will
have zero-length list of descendants to walk. Testing with binary
subtree of 2^15 processes prctl took < 0.007 sec and has shown close
to linear dependency(~0.2 * n * usec) on lower numbers of processes.

Moreover, I doubt someone intentionaly pre-forks the children whitch
should reparent to init before becoming subreaper, because some our
ancestor migh have had is_child_subreaper flag while forking our
sub-tree and our childs will all inherit has_child_subreaper flag,
and we have no way to influence it. And only way to check if we have
no has_child_subreaper flag is to create some childs, kill them and
see where they will reparent to.

Using walk_process_tree helper to walk subtree, thanks to Oleg! Timing
seems to be the same.

Optimize:

a) When descendant already has has_child_subreaper flag all his subtree
has it too already.

* for a) to be true need to move has_child_subreaper inheritance under
the same tasklist_lock with adding task to its ->real_parent->children
as without it process can inherit zero has_child_subreaper, then we
set 1 to it's parent flag, check that parent has no more children, and
only after child with wrong flag is added to the tree.

* Also make these inheritance more clear by using real_parent instead of
current, as on clone(CLONE_PARENT) if current has is_child_subreaper
and real_parent has no is_child_subreaper or has_child_subreaper, child
will have has_child_subreaper flag set without actually having a
subreaper in it's ancestors.

b) When some descendant is child_reaper, it's subtree is in different
pidns from us(original child-subreaper) and processes from other pidns
will never reparent to us.

So we can skip their(a,b) subtree from walk.

v2: switch to walk_process_tree() general helper, move
has_child_subreaper inheritance
v3: remove csr_descendant leftover, change current to real_parent
in has_child_subreaper inheritance
v4: small commit message fix

Fixes: ebec18a6 ("prctl: add PR_{SET,GET}_CHILD_SUBREAPER to allow simple process supervision")
Signed-off-by: NPavel Tikhomirov <ptikhomirov@virtuozzo.com>
Reviewed-by: NOleg Nesterov <oleg@redhat.com>
Signed-off-by: NEric W. Biederman <ebiederm@xmission.com>
      749860ce
    • O
      introduce the walk_process_tree() helper · 0f1b92cb
      由 Oleg Nesterov 提交于 
      Add the new helper to walk the process tree, the next patch adds a user.
Note that it visits the group leaders only, proc_visitor can do
for_each_thread itself or we can trivially extend walk_process_tree() to
do this.
Signed-off-by: NOleg Nesterov <oleg@redhat.com>
Signed-off-by: NPavel Tikhomirov <ptikhomirov@virtuozzo.com>
Signed-off-by: NEric W. Biederman <ebiederm@xmission.com>
      0f1b92cb
  11. 01 2月, 2017 1 次提交
  13. 28 1月, 2017 1 次提交
  15. 14 1月, 2017 1 次提交
    • P
      locking/mutex: Fix mutex handoff · e274795e
      由 Peter Zijlstra 提交于 
      While reviewing the ww_mutex patches, I noticed that it was still
possible to (incorrectly) succeed for (incorrect) code like:

	mutex_lock(&a);
	mutex_lock(&a);

This was possible if the second mutex_lock() would block (as expected)
but then receive a spurious wakeup. At that point it would find itself
at the front of the queue, request a handoff and instantly claim
ownership and continue, since owner would point to itself.

Avoid this scenario and simplify the code by introducing a third low
bit to signal handoff pickup. So once we request handoff, unlock
clears the handoff bit and sets the pickup bit along with the new
owner.

This also removes the need for the .handoff argument to
__mutex_trylock(), since that becomes superfluous with PICKUP.

In order to guarantee enough low bits, ensure task_struct alignment is
at least L1_CACHE_BYTES (which seems a good ideal regardless).
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Fixes: 9d659ae1 ("locking/mutex: Add lock handoff to avoid starvation")
Signed-off-by: NIngo Molnar <mingo@kernel.org>
      e274795e
  17. 25 12月, 2016 1 次提交
  19. 13 12月, 2016 1 次提交
  21. 08 12月, 2016 1 次提交
  23. 29 11月, 2016 1 次提交
    • P
      sched/idle: Add support for tasks that inject idle · c1de45ca
      由 Peter Zijlstra 提交于 
      Idle injection drivers such as Intel powerclamp and ACPI PAD drivers use
realtime tasks to take control of CPU then inject idle. There are two
issues with this approach:

 1. Low efficiency: injected idle task is treated as busy so sched ticks
    do not stop during injected idle period, the result of these
    unwanted wakeups can be ~20% loss in power savings.

 2. Idle accounting: injected idle time is presented to user as busy.

This patch addresses the issues by introducing a new PF_IDLE flag which
allows any given task to be treated as idle task while the flag is set.
Therefore, idle injection tasks can run through the normal flow of NOHZ
idle enter/exit to get the correct accounting as well as tick stop when
possible.

The implication is that idle task is then no longer limited to PID == 0.
Acked-by: NIngo Molnar <mingo@kernel.org>
Signed-off-by: NPeter Zijlstra <peterz@infradead.org>
Signed-off-by: NJacob Pan <jacob.jun.pan@linux.intel.com>
Signed-off-by: NRafael J. Wysocki <rafael.j.wysocki@intel.com>
      c1de45ca
  25. 23 11月, 2016 1 次提交
    • E
      mm: Add a user_ns owner to mm_struct and fix ptrace permission checks · bfedb589
      由 Eric W. Biederman 提交于 
      During exec dumpable is cleared if the file that is being executed is
not readable by the user executing the file.  A bug in
ptrace_may_access allows reading the file if the executable happens to
enter into a subordinate user namespace (aka clone(CLONE_NEWUSER),
unshare(CLONE_NEWUSER), or setns(fd, CLONE_NEWUSER).

This problem is fixed with only necessary userspace breakage by adding
a user namespace owner to mm_struct, captured at the time of exec, so
it is clear in which user namespace CAP_SYS_PTRACE must be present in
to be able to safely give read permission to the executable.

The function ptrace_may_access is modified to verify that the ptracer
has CAP_SYS_ADMIN in task->mm->user_ns instead of task->cred->user_ns.
This ensures that if the task changes it's cred into a subordinate
user namespace it does not become ptraceable.

The function ptrace_attach is modified to only set PT_PTRACE_CAP when
CAP_SYS_PTRACE is held over task->mm->user_ns.  The intent of
PT_PTRACE_CAP is to be a flag to note that whatever permission changes
the task might go through the tracer has sufficient permissions for
it not to be an issue.  task->cred->user_ns is always the same
as or descendent of mm->user_ns.  Which guarantees that having
CAP_SYS_PTRACE over mm->user_ns is the worst case for the tasks
credentials.

To prevent regressions mm->dumpable and mm->user_ns are not considered
when a task has no mm.  As simply failing ptrace_may_attach causes
regressions in privileged applications attempting to read things
such as /proc/<pid>/stat

Cc: stable@vger.kernel.org
Acked-by: NKees Cook <keescook@chromium.org>
Tested-by: NCyrill Gorcunov <gorcunov@openvz.org>
Fixes: 8409cca7 ("userns: allow ptrace from non-init user namespaces")
Signed-off-by: N"Eric W. Biederman" <ebiederm@xmission.com>
      bfedb589
  27. 16 11月, 2016 1 次提交
  29. 15 11月, 2016 1 次提交
  31. 01 11月, 2016 1 次提交
  33. 11 10月, 2016 2 次提交
    • E
      latent_entropy: Mark functions with __latent_entropy · 0766f788
      由 Emese Revfy 提交于 
      The __latent_entropy gcc attribute can be used only on functions and
variables.  If it is on a function then the plugin will instrument it for
gathering control-flow entropy. If the attribute is on a variable then
the plugin will initialize it with random contents.  The variable must
be an integer, an integer array type or a structure with integer fields.

These specific functions have been selected because they are init
functions (to help gather boot-time entropy), are called at unpredictable
times, or they have variable loops, each of which provide some level of
latent entropy.
Signed-off-by: NEmese Revfy <re.emese@gmail.com>
[kees: expanded commit message]
Signed-off-by: NKees Cook <keescook@chromium.org>
      0766f788
    • E
      gcc-plugins: Add latent_entropy plugin · 38addce8
      由 Emese Revfy 提交于 
      This adds a new gcc plugin named "latent_entropy". It is designed to
extract as much possible uncertainty from a running system at boot time as
possible, hoping to capitalize on any possible variation in CPU operation
(due to runtime data differences, hardware differences, SMP ordering,
thermal timing variation, cache behavior, etc).

At the very least, this plugin is a much more comprehensive example for
how to manipulate kernel code using the gcc plugin internals.

The need for very-early boot entropy tends to be very architecture or
system design specific, so this plugin is more suited for those sorts
of special cases. The existing kernel RNG already attempts to extract
entropy from reliable runtime variation, but this plugin takes the idea to
a logical extreme by permuting a global variable based on any variation
in code execution (e.g. a different value (and permutation function)
is used to permute the global based on loop count, case statement,
if/then/else branching, etc).

To do this, the plugin starts by inserting a local variable in every
marked function. The plugin then adds logic so that the value of this
variable is modified by randomly chosen operations (add, xor and rol) and
random values (gcc generates separate static values for each location at
compile time and also injects the stack pointer at runtime). The resulting
value depends on the control flow path (e.g., loops and branches taken).

Before the function returns, the plugin mixes this local variable into
the latent_entropy global variable. The value of this global variable
is added to the kernel entropy pool in do_one_initcall() and _do_fork(),
though it does not credit any bytes of entropy to the pool; the contents
of the global are just used to mix the pool.

Additionally, the plugin can pre-initialize arrays with build-time
random contents, so that two different kernel builds running on identical
hardware will not have the same starting values.
Signed-off-by: NEmese Revfy <re.emese@gmail.com>
[kees: expanded commit message and code comments]
Signed-off-by: NKees Cook <keescook@chromium.org>
      38addce8
  35. 08 10月, 2016 4 次提交
    • A
      thp: reduce usage of huge zero page's atomic counter · 6fcb52a5
      由 Aaron Lu 提交于 
      The global zero page is used to satisfy an anonymous read fault.  If
THP(Transparent HugePage) is enabled then the global huge zero page is
used.  The global huge zero page uses an atomic counter for reference
counting and is allocated/freed dynamically according to its counter
value.

CPU time spent on that counter will greatly increase if there are a lot
of processes doing anonymous read faults.  This patch proposes a way to
reduce the access to the global counter so that the CPU load can be
reduced accordingly.

To do this, a new flag of the mm_struct is introduced:
MMF_USED_HUGE_ZERO_PAGE.  With this flag, the process only need to touch
the global counter in two cases:

 1 The first time it uses the global huge zero page;
 2 The time when mm_user of its mm_struct reaches zero.

Note that right now, the huge zero page is eligible to be freed as soon
as its last use goes away.  With this patch, the page will not be
eligible to be freed until the exit of the last process from which it
was ever used.

And with the use of mm_user, the kthread is not eligible to use huge
zero page either.  Since no kthread is using huge zero page today, there
is no difference after applying this patch.  But if that is not desired,
I can change it to when mm_count reaches zero.

Case used for test on Haswell EP:

  usemem -n 72 --readonly -j 0x200000 100G

Which spawns 72 processes and each will mmap 100G anonymous space and
then do read only access to that space sequentially with a step of 2MB.

  CPU cycles from perf report for base commit:
      54.03%  usemem   [kernel.kallsyms]   [k] get_huge_zero_page
  CPU cycles from perf report for this commit:
       0.11%  usemem   [kernel.kallsyms]   [k] mm_get_huge_zero_page

Performance(throughput) of the workload for base commit: 1784430792
Performance(throughput) of the workload for this commit: 4726928591
164% increase.

Runtime of the workload for base commit: 707592 us
Runtime of the workload for this commit: 303970 us
50% drop.

Link: http://lkml.kernel.org/r/fe51a88f-446a-4622-1363-ad1282d71385@intel.comSigned-off-by: NAaron Lu <aaron.lu@intel.com>
Cc: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Tim Chen <tim.c.chen@linux.intel.com>
Cc: Huang Ying <ying.huang@intel.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Jerome Marchand <jmarchan@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Ebru Akagunduz <ebru.akagunduz@gmail.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>
      6fcb52a5
    • M
      mm, oom: get rid of signal_struct::oom_victims · 862e3073
      由 Michal Hocko 提交于 
      After "oom: keep mm of the killed task available" we can safely detect
an oom victim by checking task->signal->oom_mm so we do not need the
signal_struct counter anymore so let's get rid of it.

This alone wouldn't be sufficient for nommu archs because
exit_oom_victim doesn't hide the process from the oom killer anymore.
We can, however, mark the mm with a MMF flag in __mmput.  We can reuse
MMF_OOM_REAPED and rename it to a more generic MMF_OOM_SKIP.

Link: http://lkml.kernel.org/r/1472119394-11342-6-git-send-email-mhocko@kernel.orgSigned-off-by: NMichal Hocko <mhocko@suse.com>
Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Vladimir Davydov <vdavydov@parallels.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>
      862e3073
    • M
      kernel, oom: fix potential pgd_lock deadlock from __mmdrop · 7283094e
      由 Michal Hocko 提交于 
      Lockdep complains that __mmdrop is not safe from the softirq context:

  =================================
  [ INFO: inconsistent lock state ]
  4.6.0-oomfortification2-00011-geeb3eadeab96-dirty #949 Tainted: G        W
  ---------------------------------
  inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W} usage.
  swapper/1/0 [HC0[0]:SC1[1]:HE1:SE0] takes:
   (pgd_lock){+.?...}, at: pgd_free+0x19/0x6b
  {SOFTIRQ-ON-W} state was registered at:
     __lock_acquire+0xa06/0x196e
     lock_acquire+0x139/0x1e1
     _raw_spin_lock+0x32/0x41
     __change_page_attr_set_clr+0x2a5/0xacd
     change_page_attr_set_clr+0x16f/0x32c
     set_memory_nx+0x37/0x3a
     free_init_pages+0x9e/0xc7
     alternative_instructions+0xa2/0xb3
     check_bugs+0xe/0x2d
     start_kernel+0x3ce/0x3ea
     x86_64_start_reservations+0x2a/0x2c
     x86_64_start_kernel+0x17a/0x18d
  irq event stamp: 105916
  hardirqs last  enabled at (105916): free_hot_cold_page+0x37e/0x390
  hardirqs last disabled at (105915): free_hot_cold_page+0x2c1/0x390
  softirqs last  enabled at (105878): _local_bh_enable+0x42/0x44
  softirqs last disabled at (105879): irq_exit+0x6f/0xd1

  other info that might help us debug this:
   Possible unsafe locking scenario:

         CPU0
         ----
    lock(pgd_lock);
    <Interrupt>
      lock(pgd_lock);

   *** DEADLOCK ***

  1 lock held by swapper/1/0:
   #0:  (rcu_callback){......}, at: rcu_process_callbacks+0x390/0x800

  stack backtrace:
  CPU: 1 PID: 0 Comm: swapper/1 Tainted: G        W       4.6.0-oomfortification2-00011-geeb3eadeab96-dirty #949
  Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Debian-1.8.2-1 04/01/2014
  Call Trace:
   <IRQ>
    print_usage_bug.part.25+0x259/0x268
    mark_lock+0x381/0x567
    __lock_acquire+0x993/0x196e
    lock_acquire+0x139/0x1e1
    _raw_spin_lock+0x32/0x41
    pgd_free+0x19/0x6b
    __mmdrop+0x25/0xb9
    __put_task_struct+0x103/0x11e
    delayed_put_task_struct+0x157/0x15e
    rcu_process_callbacks+0x660/0x800
    __do_softirq+0x1ec/0x4d5
    irq_exit+0x6f/0xd1
    smp_apic_timer_interrupt+0x42/0x4d
    apic_timer_interrupt+0x8e/0xa0
   <EOI>
    arch_cpu_idle+0xf/0x11
    default_idle_call+0x32/0x34
    cpu_startup_entry+0x20c/0x399
    start_secondary+0xfe/0x101

More over commit a79e53d8 ("x86/mm: Fix pgd_lock deadlock") was
explicit about pgd_lock not to be called from the irq context.  This
means that __mmdrop called from free_signal_struct has to be postponed
to a user context.  We already have a similar mechanism for mmput_async
so we can use it here as well.  This is safe because mm_count is pinned
by mm_users.

This fixes bug introduced by "oom: keep mm of the killed task available"

Link: http://lkml.kernel.org/r/1472119394-11342-5-git-send-email-mhocko@kernel.orgSigned-off-by: NMichal Hocko <mhocko@suse.com>
Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Vladimir Davydov <vdavydov@parallels.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>
      7283094e
    • M
      oom: keep mm of the killed task available · 26db62f1
      由 Michal Hocko 提交于 
      oom_reap_task has to call exit_oom_victim in order to make sure that the
oom vicim will not block the oom killer for ever.  This is, however,
opening new problems (e.g oom_killer_disable exclusion - see commit
74070542 ("oom, suspend: fix oom_reaper vs.  oom_killer_disable
race")).  exit_oom_victim should be only called from the victim's
context ideally.

One way to achieve this would be to rely on per mm_struct flags.  We
already have MMF_OOM_REAPED to hide a task from the oom killer since
"mm, oom: hide mm which is shared with kthread or global init". The
problem is that the exit path:

  do_exit
    exit_mm
      tsk->mm = NULL;
      mmput
        __mmput
      exit_oom_victim

doesn't guarantee that exit_oom_victim will get called in a bounded
amount of time.  At least exit_aio depends on IO which might get blocked
due to lack of memory and who knows what else is lurking there.

This patch takes a different approach.  We remember tsk->mm into the
signal_struct and bind it to the signal struct life time for all oom
victims.  __oom_reap_task_mm as well as oom_scan_process_thread do not
have to rely on find_lock_task_mm anymore and they will have a reliable
reference to the mm struct.  As a result all the oom specific
communication inside the OOM killer can be done via tsk->signal->oom_mm.

Increasing the signal_struct for something as unlikely as the oom killer
is far from ideal but this approach will make the code much more
reasonable and long term we even might want to move task->mm into the
signal_struct anyway.  In the next step we might want to make the oom
killer exclusion and access to memory reserves completely independent
which would be also nice.

Link: http://lkml.kernel.org/r/1472119394-11342-4-git-send-email-mhocko@kernel.orgSigned-off-by: NMichal Hocko <mhocko@suse.com>
Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Vladimir Davydov <vdavydov@parallels.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>
      26db62f1
  37. 16 9月, 2016 2 次提交
  39. 02 9月, 2016 1 次提交
    • M
      kernel/fork: fix CLONE_CHILD_CLEARTID regression in nscd · 735f2770
      由 Michal Hocko 提交于 
      Commit fec1d011 ("[PATCH] Disable CLONE_CHILD_CLEARTID for abnormal
exit") has caused a subtle regression in nscd which uses
CLONE_CHILD_CLEARTID to clear the nscd_certainly_running flag in the
shared databases, so that the clients are notified when nscd is
restarted.  Now, when nscd uses a non-persistent database, clients that
have it mapped keep thinking the database is being updated by nscd, when
in fact nscd has created a new (anonymous) one (for non-persistent
databases it uses an unlinked file as backend).

The original proposal for the CLONE_CHILD_CLEARTID change claimed
(https://lkml.org/lkml/2006/10/25/233):

: The NPTL library uses the CLONE_CHILD_CLEARTID flag on clone() syscalls
: on behalf of pthread_create() library calls.  This feature is used to
: request that the kernel clear the thread-id in user space (at an address
: provided in the syscall) when the thread disassociates itself from the
: address space, which is done in mm_release().
:
: Unfortunately, when a multi-threaded process incurs a core dump (such as
: from a SIGSEGV), the core-dumping thread sends SIGKILL signals to all of
: the other threads, which then proceed to clear their user-space tids
: before synchronizing in exit_mm() with the start of core dumping.  This
: misrepresents the state of process's address space at the time of the
: SIGSEGV and makes it more difficult for someone to debug NPTL and glibc
: problems (misleading him/her to conclude that the threads had gone away
: before the fault).
:
: The fix below is to simply avoid the CLONE_CHILD_CLEARTID action if a
: core dump has been initiated.

The resulting patch from Roland (https://lkml.org/lkml/2006/10/26/269)
seems to have a larger scope than the original patch asked for.  It
seems that limitting the scope of the check to core dumping should work
for SIGSEGV issue describe above.

[Changelog partly based on Andreas' description]
Fixes: fec1d011 ("[PATCH] Disable CLONE_CHILD_CLEARTID for abnormal exit")
Link: http://lkml.kernel.org/r/1471968749-26173-1-git-send-email-mhocko@kernel.orgSigned-off-by: NMichal Hocko <mhocko@suse.com>
Tested-by: NWilliam Preston <wpreston@suse.com>
Acked-by: NOleg Nesterov <oleg@redhat.com>
Cc: Roland McGrath <roland@hack.frob.com>
Cc: Andreas Schwab <schwab@suse.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>
      735f2770
  41. 01 9月, 2016 1 次提交
  43. 24 8月, 2016 1 次提交
  45. 17 8月, 2016 1 次提交
    • B
      cgroup: reduce read locked section of cgroup_threadgroup_rwsem during fork · 568ac888
      由 Balbir Singh 提交于 
      cgroup_threadgroup_rwsem is acquired in read mode during process exit
and fork.  It is also grabbed in write mode during
__cgroups_proc_write().  I've recently run into a scenario with lots
of memory pressure and OOM and I am beginning to see

systemd

 __switch_to+0x1f8/0x350
 __schedule+0x30c/0x990
 schedule+0x48/0xc0
 percpu_down_write+0x114/0x170
 __cgroup_procs_write.isra.12+0xb8/0x3c0
 cgroup_file_write+0x74/0x1a0
 kernfs_fop_write+0x188/0x200
 __vfs_write+0x6c/0xe0
 vfs_write+0xc0/0x230
 SyS_write+0x6c/0x110
 system_call+0x38/0xb4

This thread is waiting on the reader of cgroup_threadgroup_rwsem to
exit.  The reader itself is under memory pressure and has gone into
reclaim after fork. There are times the reader also ends up waiting on
oom_lock as well.

 __switch_to+0x1f8/0x350
 __schedule+0x30c/0x990
 schedule+0x48/0xc0
 jbd2_log_wait_commit+0xd4/0x180
 ext4_evict_inode+0x88/0x5c0
 evict+0xf8/0x2a0
 dispose_list+0x50/0x80
 prune_icache_sb+0x6c/0x90
 super_cache_scan+0x190/0x210
 shrink_slab.part.15+0x22c/0x4c0
 shrink_zone+0x288/0x3c0
 do_try_to_free_pages+0x1dc/0x590
 try_to_free_pages+0xdc/0x260
 __alloc_pages_nodemask+0x72c/0xc90
 alloc_pages_current+0xb4/0x1a0
 page_table_alloc+0xc0/0x170
 __pte_alloc+0x58/0x1f0
 copy_page_range+0x4ec/0x950
 copy_process.isra.5+0x15a0/0x1870
 _do_fork+0xa8/0x4b0
 ppc_clone+0x8/0xc

In the meanwhile, all processes exiting/forking are blocked almost
stalling the system.

This patch moves the threadgroup_change_begin from before
cgroup_fork() to just before cgroup_canfork().  There is no nee to
worry about threadgroup changes till the task is actually added to the
threadgroup.  This avoids having to call reclaim with
cgroup_threadgroup_rwsem held.

tj: Subject and description edits.
Signed-off-by: NBalbir Singh <bsingharora@gmail.com>
Acked-by: NZefan Li <lizefan@huawei.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: stable@vger.kernel.org # v4.2+
Signed-off-by: NTejun Heo <tj@kernel.org>
      568ac888
  47. 09 8月, 2016 3 次提交
  49. 29 7月, 2016 2 次提交
  51. 27 7月, 2016 1 次提交
    • V
      mm: charge/uncharge kmemcg from generic page allocator paths · 4949148a
      由 Vladimir Davydov 提交于 
      Currently, to charge a non-slab allocation to kmemcg one has to use
alloc_kmem_pages helper with __GFP_ACCOUNT flag.  A page allocated with
this helper should finally be freed using free_kmem_pages, otherwise it
won't be uncharged.

This API suits its current users fine, but it turns out to be impossible
to use along with page reference counting, i.e.  when an allocation is
supposed to be freed with put_page, as it is the case with pipe or unix
socket buffers.

To overcome this limitation, this patch moves charging/uncharging to
generic page allocator paths, i.e.  to __alloc_pages_nodemask and
free_pages_prepare, and zaps alloc/free_kmem_pages helpers.  This way,
one can use any of the available page allocation functions to get the
allocated page charged to kmemcg - it's enough to pass __GFP_ACCOUNT,
just like in case of kmalloc and friends.  A charged page will be
automatically uncharged on free.

To make it possible, we need to mark pages charged to kmemcg somehow.
To avoid introducing a new page flag, we make use of page->_mapcount for
marking such pages.  Since pages charged to kmemcg are not supposed to
be mapped to userspace, it should work just fine.  There are other
(ab)users of page->_mapcount - buddy and balloon pages - but we don't
conflict with them.

In case kmemcg is compiled out or not used at runtime, this patch
introduces no overhead to generic page allocator paths.  If kmemcg is
used, it will be plus one gfp flags check on alloc and plus one
page->_mapcount check on free, which shouldn't hurt performance, because
the data accessed are hot.

Link: http://lkml.kernel.org/r/a9736d856f895bcb465d9f257b54efe32eda6f99.1464079538.git.vdavydov@virtuozzo.comSigned-off-by: NVladimir Davydov <vdavydov@virtuozzo.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Minchan Kim <minchan@kernel.org>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>
      4949148a