linux-stable.git/kernel, branch v4.19.282

cgroup/cpuset: Wake up cpuset_attach_wq tasks in cpuset_cancel_attach()

2023-04-20T10:04:40+00:00

commit ba9182a89626d5f83c2ee4594f55cb9c1e60f0e2 upstream.

After a successful cpuset_can_attach() call which increments the
attach_in_progress flag, either cpuset_cancel_attach() or cpuset_attach()
will be called later. In cpuset_attach(), tasks in cpuset_attach_wq,
if present, will be woken up at the end. That is not the case in
cpuset_cancel_attach(). So missed wakeup is possible if the attach
operation is somehow cancelled. Fix that by doing the wakeup in
cpuset_cancel_attach() as well.

Fixes: e44193d39e8d ("cpuset: let hotplug propagation work wait for task attaching")
Signed-off-by: Waiman Long 
Reviewed-by: Michal Koutný 
Cc: stable@vger.kernel.org # v3.11+
Signed-off-by: Tejun Heo 
Signed-off-by: Greg Kroah-Hartman

ring-buffer: Fix race while reader and writer are on the same page

2023-04-20T10:04:39+00:00

commit 6455b6163d8c680366663cdb8c679514d55fc30c upstream.

When user reads file 'trace_pipe', kernel keeps printing following logs
that warn at "cpu_buffer->reader_page->read > rb_page_size(reader)" in
rb_get_reader_page(). It just looks like there's an infinite loop in
tracing_read_pipe(). This problem occurs several times on arm64 platform
when testing v5.10 and below.

  Call trace:
   rb_get_reader_page+0x248/0x1300
   rb_buffer_peek+0x34/0x160
   ring_buffer_peek+0xbc/0x224
   peek_next_entry+0x98/0xbc
   __find_next_entry+0xc4/0x1c0
   trace_find_next_entry_inc+0x30/0x94
   tracing_read_pipe+0x198/0x304
   vfs_read+0xb4/0x1e0
   ksys_read+0x74/0x100
   __arm64_sys_read+0x24/0x30
   el0_svc_common.constprop.0+0x7c/0x1bc
   do_el0_svc+0x2c/0x94
   el0_svc+0x20/0x30
   el0_sync_handler+0xb0/0xb4
   el0_sync+0x160/0x180

Then I dump the vmcore and look into the problematic per_cpu ring_buffer,
I found that tail_page/commit_page/reader_page are on the same page while
reader_page->read is obviously abnormal:
  tail_page == commit_page == reader_page == {
    .write = 0x100d20,
    .read = 0x8f9f4805,  // Far greater than 0xd20, obviously abnormal!!!
    .entries = 0x10004c,
    .real_end = 0x0,
    .page = {
      .time_stamp = 0x857257416af0,
      .commit = 0xd20,  // This page hasn't been full filled.
      // .data[0...0xd20] seems normal.
    }
 }

The root cause is most likely the race that reader and writer are on the
same page while reader saw an event that not fully committed by writer.

To fix this, add memory barriers to make sure the reader can see the
content of what is committed. Since commit a0fcaaed0c46 ("ring-buffer: Fix
race between reset page and reading page") has added the read barrier in
rb_get_reader_page(), here we just need to add the write barrier.

Link: https://lore.kernel.org/linux-trace-kernel/20230325021247.2923907-1-zhengyejian1@huawei.com

Cc: stable@vger.kernel.org
Fixes: 77ae365eca89 ("ring-buffer: make lockless")
Suggested-by: Steven Rostedt (Google) 
Signed-off-by: Zheng Yejian 
Signed-off-by: Steven Rostedt (Google) 
Signed-off-by: Greg Kroah-Hartman

perf/core: Fix the same task check in perf_event_set_output

2023-04-20T10:04:39+00:00

[ Upstream commit 24d3ae2f37d8bc3c14b31d353c5d27baf582b6a6 ]

The same task check in perf_event_set_output has some potential issues
for some usages.

For the current perf code, there is a problem if using of
perf_event_open() to have multiple samples getting into the same mmap’d
memory when they are both attached to the same process.
https://lore.kernel.org/all/92645262-D319-4068-9C44-2409EF44888E@gmail.com/
Because the event->ctx is not ready when the perf_event_set_output() is
invoked in the perf_event_open().

Besides the above issue, before the commit bd2756811766 ("perf: Rewrite
core context handling"), perf record can errors out when sampling with
a hardware event and a software event as below.
 $ perf record -e cycles,dummy --per-thread ls
 failed to mmap with 22 (Invalid argument)
That's because that prior to the commit a hardware event and a software
event are from different task context.

The problem should be a long time issue since commit c3f00c70276d
("perk: Separate find_get_context() from event initialization").

The task struct is stored in the event->hw.target for each per-thread
event. It is a more reliable way to determine whether two events are
attached to the same task.

The event->hw.target was also introduced several years ago by the
commit 50f16a8bf9d7 ("perf: Remove type specific target pointers"). It
can not only be used to fix the issue with the current code, but also
back port to fix the issues with an older kernel.

Note: The event->hw.target was introduced later than commit
c3f00c70276d. The patch may cannot be applied between the commit
c3f00c70276d and commit 50f16a8bf9d7. Anybody that wants to back-port
this at that period may have to find other solutions.

Fixes: c3f00c70276d ("perf: Separate find_get_context() from event initialization")
Signed-off-by: Kan Liang 
Signed-off-by: Peter Zijlstra (Intel) 
Reviewed-by: Zhengjun Xing 
Link: https://lkml.kernel.org/r/20230322202449.512091-1-kan.liang@linux.intel.com
Signed-off-by: Sasha Levin

cgroup: Add missing cpus_read_lock() to cgroup_attach_task_all()

2023-04-05T09:15:43+00:00

commit 43626dade36fa74d3329046f4ae2d7fdefe401c6 upstream.

syzbot is hitting percpu_rwsem_assert_held(&cpu_hotplug_lock) warning at
cpuset_attach() [1], for commit 4f7e7236435ca0ab ("cgroup: Fix
threadgroup_rwsem <-> cpus_read_lock() deadlock") missed that
cpuset_attach() is also called from cgroup_attach_task_all().
Add cpus_read_lock() like what cgroup_procs_write_start() does.

Link: https://syzkaller.appspot.com/bug?extid=29d3a3b4d86c8136ad9e [1]
Reported-by: syzbot 
Signed-off-by: Tetsuo Handa 
Fixes: 4f7e7236435ca0ab ("cgroup: Fix threadgroup_rwsem <-> cpus_read_lock() deadlock")
Signed-off-by: Tejun Heo 
Signed-off-by: Cai Xinchen 
Signed-off-by: Greg Kroah-Hartman

cgroup: Fix threadgroup_rwsem <-> cpus_read_lock() deadlock

2023-04-05T09:15:43+00:00

commit 4f7e7236435ca0abe005c674ebd6892c6e83aeb3 upstream.

Add #include  to avoid compile error on some architectures.

commit 9a3284fad42f6 ("cgroup: Optimize single thread migration") and
commit 671c11f0619e5 ("cgroup: Elide write-locking threadgroup_rwsem
when updating csses on an empty subtree") are not backport. So ignore the
input parameter of cgroup_attach_lock/cgroup_attach_unlock.

original commit message:

Bringing up a CPU may involve creating and destroying tasks which requires
read-locking threadgroup_rwsem, so threadgroup_rwsem nests inside
cpus_read_lock(). However, cpuset's ->attach(), which may be called with
thredagroup_rwsem write-locked, also wants to disable CPU hotplug and
acquires cpus_read_lock(), leading to a deadlock.

Fix it by guaranteeing that ->attach() is always called with CPU hotplug
disabled and removing cpus_read_lock() call from cpuset_attach().

Signed-off-by: Tejun Heo 
Reviewed-and-tested-by: Imran Khan 
Reported-and-tested-by: Xuewen Yan 
Fixes: 05c7b7a92cc8 ("cgroup/cpuset: Fix a race between cpuset_attach() and cpu hotplug")
Cc: stable@vger.kernel.org # v5.17+
Signed-off-by: Cai Xinchen 
Signed-off-by: Greg Kroah-Hartman

cgroup/cpuset: Change cpuset_rwsem and hotplug lock order

2023-04-05T09:15:42+00:00

commit d74b27d63a8bebe2fe634944e4ebdc7b10db7a39 upstream.

commit 1243dc518c9da ("cgroup/cpuset: Convert cpuset_mutex to
percpu_rwsem") is performance patch which is not backport. So
convert percpu_rwsem to cpuset_mutex.

commit aa44002e7db25 ("cpuset: Fix unsafe lock order between
cpuset lock and cpuslock") makes lock order keep cpuset_mutex
->cpu_hotplug_lock. We should change lock order in cpuset_attach.

original commit message:

cpuset_rwsem is going to be acquired from sched_setscheduler() with a
following patch. There are however paths (e.g., spawn_ksoftirqd) in
which sched_scheduler() is eventually called while holding hotplug lock;
this creates a dependecy between hotplug lock (to be always acquired
first) and cpuset_rwsem (to be always acquired after hotplug lock).

Fix paths which currently take the two locks in the wrong order (after
a following patch is applied).

Tested-by: Dietmar Eggemann 
Signed-off-by: Juri Lelli 
Signed-off-by: Peter Zijlstra (Intel) 
Cc: Linus Torvalds 
Cc: Peter Zijlstra 
Cc: Thomas Gleixner 
Cc: bristot@redhat.com
Cc: claudio@evidence.eu.com
Cc: lizefan@huawei.com
Cc: longman@redhat.com
Cc: luca.abeni@santannapisa.it
Cc: mathieu.poirier@linaro.org
Cc: rostedt@goodmis.org
Cc: tj@kernel.org
Cc: tommaso.cucinotta@santannapisa.it
Link: https://lkml.kernel.org/r/20190719140000.31694-7-juri.lelli@redhat.com
Signed-off-by: Ingo Molnar 
Signed-off-by: Cai Xinchen 
Signed-off-by: Greg Kroah-Hartman

sched_getaffinity: don't assume 'cpumask_size()' is fully initialized

2023-04-05T09:15:39+00:00

[ Upstream commit 6015b1aca1a233379625385feb01dd014aca60b5 ]

The getaffinity() system call uses 'cpumask_size()' to decide how big
the CPU mask is - so far so good.  It is indeed the allocation size of a
cpumask.

But the code also assumes that the whole allocation is initialized
without actually doing so itself.  That's wrong, because we might have
fixed-size allocations (making copying and clearing more efficient), but
not all of it is then necessarily used if 'nr_cpu_ids' is smaller.

Having checked other users of 'cpumask_size()', they all seem to be ok,
either using it purely for the allocation size, or explicitly zeroing
the cpumask before using the size in bytes to copy it.

See for example the ublk_ctrl_get_queue_affinity() function that uses
the proper 'zalloc_cpumask_var()' to make sure that the whole mask is
cleared, whether the storage is on the stack or if it was an external
allocation.

Fix this by just zeroing the allocation before using it.  Do the same
for the compat version of sched_getaffinity(), which had the same logic.

Also, for consistency, make sched_getaffinity() use 'cpumask_bits()' to
access the bits.  For a cpumask_var_t, it ends up being a pointer to the
same data either way, but it's just a good idea to treat it like you
would a 'cpumask_t'.  The compat case already did that.

Reported-by: Ryan Roberts 
Link: https://lore.kernel.org/lkml/7d026744-6bd6-6827-0471-b5e8eae0be3f@arm.com/
Cc: Yury Norov 
Signed-off-by: Linus Torvalds 
Signed-off-by: Sasha Levin

sched/fair: Sanitize vruntime of entity being migrated

2023-04-05T09:15:38+00:00

commit a53ce18cacb477dd0513c607f187d16f0fa96f71 upstream.

Commit 829c1651e9c4 ("sched/fair: sanitize vruntime of entity being placed")
fixes an overflowing bug, but ignore a case that se->exec_start is reset
after a migration.

For fixing this case, we delay the reset of se->exec_start after
placing the entity which se->exec_start to detect long sleeping task.

In order to take into account a possible divergence between the clock_task
of 2 rqs, we increase the threshold to around 104 days.

Fixes: 829c1651e9c4 ("sched/fair: sanitize vruntime of entity being placed")
Originally-by: Zhang Qiao 
Signed-off-by: Vincent Guittot 
Signed-off-by: Peter Zijlstra (Intel) 
Tested-by: Zhang Qiao 
Link: https://lore.kernel.org/r/20230317160810.107988-1-vincent.guittot@linaro.org
Signed-off-by: Greg Kroah-Hartman

sched/fair: sanitize vruntime of entity being placed

2023-04-05T09:15:38+00:00

commit 829c1651e9c4a6f78398d3e67651cef9bb6b42cc upstream.

When a scheduling entity is placed onto cfs_rq, its vruntime is pulled
to the base level (around cfs_rq->min_vruntime), so that the entity
doesn't gain extra boost when placed backwards.

However, if the entity being placed wasn't executed for a long time, its
vruntime may get too far behind (e.g. while cfs_rq was executing a
low-weight hog), which can inverse the vruntime comparison due to s64
overflow.  This results in the entity being placed with its original
vruntime way forwards, so that it will effectively never get to the cpu.

To prevent that, ignore the vruntime of the entity being placed if it
didn't execute for much longer than the characteristic sheduler time
scale.

[rkagan: formatted, adjusted commit log, comments, cutoff value]
Signed-off-by: Zhang Qiao 
Co-developed-by: Roman Kagan 
Signed-off-by: Roman Kagan 
Signed-off-by: Peter Zijlstra (Intel) 
Link: https://lkml.kernel.org/r/20230130122216.3555094-1-rkagan@amazon.de
Signed-off-by: Greg Kroah-Hartman

bpf: Adjust insufficient default bpf_jit_limit

2023-04-05T09:15:34+00:00

[ Upstream commit 10ec8ca8ec1a2f04c4ed90897225231c58c124a7 ]

We've seen recent AWS EKS (Kubernetes) user reports like the following:

  After upgrading EKS nodes from v20230203 to v20230217 on our 1.24 EKS
  clusters after a few days a number of the nodes have containers stuck
  in ContainerCreating state or liveness/readiness probes reporting the
  following error:

    Readiness probe errored: rpc error: code = Unknown desc = failed to
    exec in container: failed to start exec "4a11039f730203ffc003b7[...]":
    OCI runtime exec failed: exec failed: unable to start container process:
    unable to init seccomp: error loading seccomp filter into kernel:
    error loading seccomp filter: errno 524: unknown

  However, we had not been seeing this issue on previous AMIs and it only
  started to occur on v20230217 (following the upgrade from kernel 5.4 to
  5.10) with no other changes to the underlying cluster or workloads.

  We tried the suggestions from that issue (sysctl net.core.bpf_jit_limit=452534528)
  which helped to immediately allow containers to be created and probes to
  execute but after approximately a day the issue returned and the value
  returned by cat /proc/vmallocinfo | grep bpf_jit | awk '{s+=$2} END {print s}'
  was steadily increasing.

I tested bpf tree to observe bpf_jit_charge_modmem, bpf_jit_uncharge_modmem
their sizes passed in as well as bpf_jit_current under tcpdump BPF filter,
seccomp BPF and native (e)BPF programs, and the behavior all looks sane
and expected, that is nothing "leaking" from an upstream perspective.

The bpf_jit_limit knob was originally added in order to avoid a situation
where unprivileged applications loading BPF programs (e.g. seccomp BPF
policies) consuming all the module memory space via BPF JIT such that loading
of kernel modules would be prevented. The default limit was defined back in
2018 and while good enough back then, we are generally seeing far more BPF
consumers today.

Adjust the limit for the BPF JIT pool from originally 1/4 to now 1/2 of the
module memory space to better reflect today's needs and avoid more users
running into potentially hard to debug issues.

Fixes: fdadd04931c2 ("bpf: fix bpf_jit_limit knob for PAGE_SIZE >= 64K")
Reported-by: Stephen Haynes 
Reported-by: Lefteris Alexakis 
Signed-off-by: Daniel Borkmann 
Link: https://github.com/awslabs/amazon-eks-ami/issues/1179
Link: https://github.com/awslabs/amazon-eks-ami/issues/1219
Reviewed-by: Kuniyuki Iwashima 
Link: https://lore.kernel.org/r/20230320143725.8394-1-daniel@iogearbox.net
Signed-off-by: Alexei Starovoitov 
Signed-off-by: Sasha Levin