commit 62c0b10615 upstream.
In perf_adjust_period, we will first calculate period, and then use
this period to calculate delta. However, when delta is less than 0,
there will be a deviation compared to when delta is greater than or
equal to 0. For example, when delta is in the range of [-14,-1], the
range of delta = delta + 7 is between [-7,6], so the final value of
delta/8 is 0. Therefore, the impact of -1 and -2 will be ignored.
This is unacceptable when the target period is very short, because
we will lose a lot of samples.
Here are some tests and analyzes:
before:
# perf record -e cs -F 1000 ./a.out
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.022 MB perf.data (518 samples) ]
# perf script
...
a.out 396 257.956048: 23 cs: ffffffff81f4eeec schedul>
a.out 396 257.957891: 23 cs: ffffffff81f4eeec schedul>
a.out 396 257.959730: 23 cs: ffffffff81f4eeec schedul>
a.out 396 257.961545: 23 cs: ffffffff81f4eeec schedul>
a.out 396 257.963355: 23 cs: ffffffff81f4eeec schedul>
a.out 396 257.965163: 23 cs: ffffffff81f4eeec schedul>
a.out 396 257.966973: 23 cs: ffffffff81f4eeec schedul>
a.out 396 257.968785: 23 cs: ffffffff81f4eeec schedul>
a.out 396 257.970593: 23 cs: ffffffff81f4eeec schedul>
...
after:
# perf record -e cs -F 1000 ./a.out
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.058 MB perf.data (1466 samples) ]
# perf script
...
a.out 395 59.338813: 11 cs: ffffffff81f4eeec schedul>
a.out 395 59.339707: 12 cs: ffffffff81f4eeec schedul>
a.out 395 59.340682: 13 cs: ffffffff81f4eeec schedul>
a.out 395 59.341751: 13 cs: ffffffff81f4eeec schedul>
a.out 395 59.342799: 12 cs: ffffffff81f4eeec schedul>
a.out 395 59.343765: 11 cs: ffffffff81f4eeec schedul>
a.out 395 59.344651: 11 cs: ffffffff81f4eeec schedul>
a.out 395 59.345539: 12 cs: ffffffff81f4eeec schedul>
a.out 395 59.346502: 13 cs: ffffffff81f4eeec schedul>
...
test.c
int main() {
for (int i = 0; i < 20000; i++)
usleep(10);
return 0;
}
# time ./a.out
real 0m1.583s
user 0m0.040s
sys 0m0.298s
The above results were tested on x86-64 qemu with KVM enabled using
test.c as test program. Ideally, we should have around 1500 samples,
but the previous algorithm had only about 500, whereas the modified
algorithm now has about 1400. Further more, the new version shows 1
sample per 0.001s, while the previous one is 1 sample per 0.002s.This
indicates that the new algorithm is more sensitive to small negative
values compared to old algorithm.
Fixes: bd2b5b1284 ("perf_counter: More aggressive frequency adjustment")
Signed-off-by: Luo Gengkun <luogengkun@huaweicloud.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Adrian Hunter <adrian.hunter@intel.com>
Reviewed-by: Kan Liang <kan.liang@linux.intel.com>
Cc: stable@vger.kernel.org
Link: https://lkml.kernel.org/r/20240831074316.2106159-2-luogengkun@huaweicloud.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit dbc48c8f41 ]
nr_pages is unsigned long but gets passed to rb_alloc_aux() as an int,
and is stored as an int.
Only power-of-2 values are accepted, so if nr_pages is a 64_bit value, it
will be passed to rb_alloc_aux() as zero.
That is not ideal because:
1. the value is incorrect
2. rb_alloc_aux() is at risk of misbehaving, although it manages to
return -ENOMEM in that case, it is a result of passing zero to get_order()
even though the get_order() result is documented to be undefined in that
case.
Fix by simply validating the maximum supported value in the first place.
Use -ENOMEM error code for consistency with the current error code that
is returned in that case.
Fixes: 45bfb2e504 ("perf: Add AUX area to ring buffer for raw data streams")
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20240624201101.60186-6-adrian.hunter@intel.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 74751ef5c1 ]
In our production environment, we found many hung tasks which are
blocked for more than 18 hours. Their call traces are like this:
[346278.191038] __schedule+0x2d8/0x890
[346278.191046] schedule+0x4e/0xb0
[346278.191049] perf_event_free_task+0x220/0x270
[346278.191056] ? init_wait_var_entry+0x50/0x50
[346278.191060] copy_process+0x663/0x18d0
[346278.191068] kernel_clone+0x9d/0x3d0
[346278.191072] __do_sys_clone+0x5d/0x80
[346278.191076] __x64_sys_clone+0x25/0x30
[346278.191079] do_syscall_64+0x5c/0xc0
[346278.191083] ? syscall_exit_to_user_mode+0x27/0x50
[346278.191086] ? do_syscall_64+0x69/0xc0
[346278.191088] ? irqentry_exit_to_user_mode+0x9/0x20
[346278.191092] ? irqentry_exit+0x19/0x30
[346278.191095] ? exc_page_fault+0x89/0x160
[346278.191097] ? asm_exc_page_fault+0x8/0x30
[346278.191102] entry_SYSCALL_64_after_hwframe+0x44/0xae
The task was waiting for the refcount become to 1, but from the vmcore,
we found the refcount has already been 1. It seems that the task didn't
get woken up by perf_event_release_kernel() and got stuck forever. The
below scenario may cause the problem.
Thread A Thread B
... ...
perf_event_free_task perf_event_release_kernel
...
acquire event->child_mutex
...
get_ctx
... release event->child_mutex
acquire ctx->mutex
...
perf_free_event (acquire/release event->child_mutex)
...
release ctx->mutex
wait_var_event
acquire ctx->mutex
acquire event->child_mutex
# move existing events to free_list
release event->child_mutex
release ctx->mutex
put_ctx
... ...
In this case, all events of the ctx have been freed, so we couldn't
find the ctx in free_list and Thread A will miss the wakeup. It's thus
necessary to add a wakeup after dropping the reference.
Fixes: 1cf8dfe8a6 ("perf/core: Fix race between close() and fork()")
Signed-off-by: Haifeng Xu <haifeng.xu@shopee.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Frederic Weisbecker <frederic@kernel.org>
Acked-by: Mark Rutland <mark.rutland@arm.com>
Cc: stable@vger.kernel.org
Link: https://lkml.kernel.org/r/20240513103948.33570-1-haifeng.xu@shopee.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
commit 6b959ba22d upstream.
perf_output_read_group may respond to IPI request of other cores and invoke
__perf_install_in_context function. As a result, hwc configuration is modified.
causing inconsistency and unexpected consequences.
Interrupts are not disabled when perf_output_read_group reads PMU counter.
In this case, IPI request may be received from other cores.
As a result, PMU configuration is modified and an error occurs when
reading PMU counter:
CPU0 CPU1
__se_sys_perf_event_open
perf_install_in_context
perf_output_read_group smp_call_function_single
for_each_sibling_event(sub, leader) { generic_exec_single
if ((sub != event) && remote_function
(sub->state == PERF_EVENT_STATE_ACTIVE)) |
<enter IPI handler: __perf_install_in_context> <----RAISE IPI-----+
__perf_install_in_context
ctx_resched
event_sched_out
armpmu_del
...
hwc->idx = -1; // event->hwc.idx is set to -1
...
<exit IPI>
sub->pmu->read(sub);
armpmu_read
armv8pmu_read_counter
armv8pmu_read_hw_counter
int idx = event->hw.idx; // idx = -1
u64 val = armv8pmu_read_evcntr(idx);
u32 counter = ARMV8_IDX_TO_COUNTER(idx); // invalid counter = 30
read_pmevcntrn(counter) // undefined instruction
Signed-off-by: Yang Jihong <yangjihong1@huawei.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20220902082918.179248-1-yangjihong1@huawei.com
Signed-off-by: Thadeu Lima de Souza Cascardo <cascardo@igalia.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit 7e2c1e4b34 upstream.
When lockdep is enabled, the for_each_sibling_event(sibling, event)
macro checks that event->ctx->mutex is held. When creating a new group
leader event, we call perf_event_validate_size() on a partially
initialized event where event->ctx is NULL, and so when
for_each_sibling_event() attempts to check event->ctx->mutex, we get a
splat, as reported by Lucas De Marchi:
WARNING: CPU: 8 PID: 1471 at kernel/events/core.c:1950 __do_sys_perf_event_open+0xf37/0x1080
This only happens for a new event which is its own group_leader, and in
this case there cannot be any sibling events. Thus it's safe to skip the
check for siblings, which avoids having to make invasive and ugly
changes to for_each_sibling_event().
Avoid the splat by bailing out early when the new event is its own
group_leader.
Fixes: 382c27f4ed ("perf: Fix perf_event_validate_size()")
Closes: https://lore.kernel.org/lkml/20231214000620.3081018-1-lucas.demarchi@intel.com/
Closes: https://lore.kernel.org/lkml/ZXpm6gQ%2Fd59jGsuW@xpf.sh.intel.com/
Reported-by: Lucas De Marchi <lucas.demarchi@intel.com>
Reported-by: Pengfei Xu <pengfei.xu@intel.com>
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20231215112450.3972309-1-mark.rutland@arm.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit 382c27f4ed ]
Budimir noted that perf_event_validate_size() only checks the size of
the newly added event, even though the sizes of all existing events
can also change due to not all events having the same read_format.
When we attach the new event, perf_group_attach(), we do re-compute
the size for all events.
Fixes: a723968c0e ("perf: Fix u16 overflows")
Reported-by: Budimir Markovic <markovicbudimir@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 119a784c81 ]
Sometimes we want to know an accurate number of samples even if it's
lost. Currenlty PERF_RECORD_LOST is generated for a ring-buffer which
might be shared with other events. So it's hard to know per-event
lost count.
Add event->lost_samples field and PERF_FORMAT_LOST to retrieve it from
userspace.
Original-patch-by: Jiri Olsa <jolsa@redhat.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20220616180623.1358843-1-namhyung@kernel.org
Stable-dep-of: 382c27f4ed ("perf: Fix perf_event_validate_size()")
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 54aee5f15b ]
When perf-record with a large AUX area, e.g 4GB, it fails with:
#perf record -C 0 -m ,4G -e arm_spe_0// -- sleep 1
failed to mmap with 12 (Cannot allocate memory)
and it reveals a WARNING with __alloc_pages():
------------[ cut here ]------------
WARNING: CPU: 44 PID: 17573 at mm/page_alloc.c:5568 __alloc_pages+0x1ec/0x248
Call trace:
__alloc_pages+0x1ec/0x248
__kmalloc_large_node+0xc0/0x1f8
__kmalloc_node+0x134/0x1e8
rb_alloc_aux+0xe0/0x298
perf_mmap+0x440/0x660
mmap_region+0x308/0x8a8
do_mmap+0x3c0/0x528
vm_mmap_pgoff+0xf4/0x1b8
ksys_mmap_pgoff+0x18c/0x218
__arm64_sys_mmap+0x38/0x58
invoke_syscall+0x50/0x128
el0_svc_common.constprop.0+0x58/0x188
do_el0_svc+0x34/0x50
el0_svc+0x34/0x108
el0t_64_sync_handler+0xb8/0xc0
el0t_64_sync+0x1a4/0x1a8
'rb->aux_pages' allocated by kcalloc() is a pointer array which is used to
maintains AUX trace pages. The allocated page for this array is physically
contiguous (and virtually contiguous) with an order of 0..MAX_ORDER. If the
size of pointer array crosses the limitation set by MAX_ORDER, it reveals a
WARNING.
So bail out early with -ENOMEM if the request AUX area is out of bound,
e.g.:
#perf record -C 0 -m ,4G -e arm_spe_0// -- sleep 1
failed to mmap with 12 (Cannot allocate memory)
Signed-off-by: Shuai Xue <xueshuai@linux.alibaba.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
commit 32671e3799 upstream.
Because group consistency is non-atomic between parent (filedesc) and children
(inherited) events, it is possible for PERF_FORMAT_GROUP read() to try and sum
non-matching counter groups -- with non-sensical results.
Add group_generation to distinguish the case where a parent group removes and
adds an event and thus has the same number, but a different configuration of
events as inherited groups.
This became a problem when commit fa8c269353 ("perf/core: Invert
perf_read_group() loops") flipped the order of child_list and sibling_list.
Previously it would iterate the group (sibling_list) first, and for each
sibling traverse the child_list. In this order, only the group composition of
the parent is relevant. By flipping the order the group composition of the
child (inherited) events becomes an issue and the mis-match in group
composition becomes evident.
That said; even prior to this commit, while reading of a group that is not
equally inherited was not broken, it still made no sense.
(Ab)use ECHILD as error return to indicate issues with child process group
composition.
Fixes: fa8c269353 ("perf/core: Invert perf_read_group() loops")
Reported-by: Budimir Markovic <markovicbudimir@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20231018115654.GK33217@noisy.programming.kicks-ass.net
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit 1af6239d1d upstream.
With the advent of CFI it is no longer acceptible to cast function
pointers.
The robot complains thusly:
kernel-events-core.c:warning:cast-from-int-(-)(struct-perf_cpu_pmu_context-)-to-remote_function_f-(aka-int-(-)(void-)-)-converts-to-incompatible-function-type
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Cixi Geng <cixi.geng1@unisoc.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit 15def34e26 ]
commit e050e3f0a7 ("perf: Fix broken interrupt rate throttling")
introduces a change in throttling threshold judgment. Before this,
compare hwc->interrupts and max_samples_per_tick, then increase
hwc->interrupts by 1, but this commit reverses order of these two
behaviors, causing the semantics of max_samples_per_tick to change.
In literal sense of "max_samples_per_tick", if hwc->interrupts ==
max_samples_per_tick, it should not be throttled, therefore, the judgment
condition should be changed to "hwc->interrupts > max_samples_per_tick".
In fact, this may cause the hardlockup to fail, The minimum value of
max_samples_per_tick may be 1, in this case, the return value of
__perf_event_account_interrupt function is 1.
As a result, nmi_watchdog gets throttled, which would stop PMU (Use x86
architecture as an example, see x86_pmu_handle_irq).
Fixes: e050e3f0a7 ("perf: Fix broken interrupt rate throttling")
Signed-off-by: Yang Jihong <yangjihong1@huawei.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20230227023508.102230-1-yangjihong1@huawei.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 24d3ae2f37 ]
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 bd27568117 ("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 c3f00c7027
("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 50f16a8bf9 ("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
c3f00c7027. The patch may cannot be applied between the commit
c3f00c7027 and commit 50f16a8bf9. Anybody that wants to back-port
this at that period may have to find other solutions.
Fixes: c3f00c7027 ("perf: Separate find_get_context() from event initialization")
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Zhengjun Xing <zhengjun.xing@linux.intel.com>
Link: https://lkml.kernel.org/r/20230322202449.512091-1-kan.liang@linux.intel.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit e8d7a90c08 ]
In pmu_dev_alloc(), when dev_set_name() failed, it will goto free_dev
and call put_device(pmu->dev) to release it.
However pmu->dev->release is assigned after this, which makes warning
and memleak.
Call dev_set_name() after pmu->dev->release = pmu_dev_release to fix it.
Device '(null)' does not have a release() function...
WARNING: CPU: 2 PID: 441 at drivers/base/core.c:2332 device_release+0x1b9/0x240
...
Call Trace:
<TASK>
kobject_put+0x17f/0x460
put_device+0x20/0x30
pmu_dev_alloc+0x152/0x400
perf_pmu_register+0x96b/0xee0
...
kmemleak: 1 new suspected memory leaks (see /sys/kernel/debug/kmemleak)
unreferenced object 0xffff888014759000 (size 2048):
comm "modprobe", pid 441, jiffies 4294931444 (age 38.332s)
backtrace:
[<0000000005aed3b4>] kmalloc_trace+0x27/0x110
[<000000006b38f9b8>] pmu_dev_alloc+0x50/0x400
[<00000000735f17be>] perf_pmu_register+0x96b/0xee0
[<00000000e38477f1>] 0xffffffffc0ad8603
[<000000004e162216>] do_one_initcall+0xd0/0x4e0
...
Fixes: abe4340057 ("perf: Sysfs enumeration")
Signed-off-by: Chen Zhongjin <chenzhongjin@huawei.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20221111103653.91058-1-chenzhongjin@huawei.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 68e3c69803 ]
Yang Jihing reported a race between perf_event_set_output() and
perf_mmap_close():
CPU1 CPU2
perf_mmap_close(e2)
if (atomic_dec_and_test(&e2->rb->mmap_count)) // 1 - > 0
detach_rest = true
ioctl(e1, IOC_SET_OUTPUT, e2)
perf_event_set_output(e1, e2)
...
list_for_each_entry_rcu(e, &e2->rb->event_list, rb_entry)
ring_buffer_attach(e, NULL);
// e1 isn't yet added and
// therefore not detached
ring_buffer_attach(e1, e2->rb)
list_add_rcu(&e1->rb_entry,
&e2->rb->event_list)
After this; e1 is attached to an unmapped rb and a subsequent
perf_mmap() will loop forever more:
again:
mutex_lock(&e->mmap_mutex);
if (event->rb) {
...
if (!atomic_inc_not_zero(&e->rb->mmap_count)) {
...
mutex_unlock(&e->mmap_mutex);
goto again;
}
}
The loop in perf_mmap_close() holds e2->mmap_mutex, while the attach
in perf_event_set_output() holds e1->mmap_mutex. As such there is no
serialization to avoid this race.
Change perf_event_set_output() to take both e1->mmap_mutex and
e2->mmap_mutex to alleviate that problem. Additionally, have the loop
in perf_mmap() detach the rb directly, this avoids having to wait for
the concurrent perf_mmap_close() to get around to doing it to make
progress.
Fixes: 9bb5d40cd9 ("perf: Fix mmap() accounting hole")
Reported-by: Yang Jihong <yangjihong1@huawei.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Yang Jihong <yangjihong1@huawei.com>
Link: https://lkml.kernel.org/r/YsQ3jm2GR38SW7uD@worktop.programming.kicks-ass.net
Signed-off-by: Sasha Levin <sashal@kernel.org>
commit 3ac6487e58 upstream.
Norbert reported that it's possible to race sys_perf_event_open() such
that the looser ends up in another context from the group leader,
triggering many WARNs.
The move_group case checks for races against itself, but the
!move_group case doesn't, seemingly relying on the previous
group_leader->ctx == ctx check. However, that check is racy due to not
holding any locks at that time.
Therefore, re-check the result after acquiring locks and bailing
if they no longer match.
Additionally, clarify the not_move_group case from the
move_group-vs-move_group race.
Fixes: f63a8daa58 ("perf: Fix event->ctx locking")
Reported-by: Norbert Slusarek <nslusarek@gmx.net>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit 5f4e5ce638 upstream.
There's list corruption on cgrp_cpuctx_list. This happens on the
following path:
perf_cgroup_switch: list_for_each_entry(cgrp_cpuctx_list)
cpu_ctx_sched_in
ctx_sched_in
ctx_pinned_sched_in
merge_sched_in
perf_cgroup_event_disable: remove the event from the list
Use list_for_each_entry_safe() to allow removing an entry during
iteration.
Fixes: 058fe1c044 ("perf/core: Make cgroup switch visit only cpuctxs with cgroup events")
Signed-off-by: Song Liu <song@kernel.org>
Reviewed-by: Rik van Riel <riel@surriel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20220204004057.2961252-1-song@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit ff083a2d97 upstream.
Protect perf_guest_cbs with RCU to fix multiple possible errors. Luckily,
all paths that read perf_guest_cbs already require RCU protection, e.g. to
protect the callback chains, so only the direct perf_guest_cbs touchpoints
need to be modified.
Bug #1 is a simple lack of WRITE_ONCE/READ_ONCE behavior to ensure
perf_guest_cbs isn't reloaded between a !NULL check and a dereference.
Fixed via the READ_ONCE() in rcu_dereference().
Bug #2 is that on weakly-ordered architectures, updates to the callbacks
themselves are not guaranteed to be visible before the pointer is made
visible to readers. Fixed by the smp_store_release() in
rcu_assign_pointer() when the new pointer is non-NULL.
Bug #3 is that, because the callbacks are global, it's possible for
readers to run in parallel with an unregisters, and thus a module
implementing the callbacks can be unloaded while readers are in flight,
resulting in a use-after-free. Fixed by a synchronize_rcu() call when
unregistering callbacks.
Bug #1 escaped notice because it's extremely unlikely a compiler will
reload perf_guest_cbs in this sequence. perf_guest_cbs does get reloaded
for future derefs, e.g. for ->is_user_mode(), but the ->is_in_guest()
guard all but guarantees the consumer will win the race, e.g. to nullify
perf_guest_cbs, KVM has to completely exit the guest and teardown down
all VMs before KVM start its module unload / unregister sequence. This
also makes it all but impossible to encounter bug #3.
Bug #2 has not been a problem because all architectures that register
callbacks are strongly ordered and/or have a static set of callbacks.
But with help, unloading kvm_intel can trigger bug #1 e.g. wrapping
perf_guest_cbs with READ_ONCE in perf_misc_flags() while spamming
kvm_intel module load/unload leads to:
BUG: kernel NULL pointer dereference, address: 0000000000000000
#PF: supervisor read access in kernel mode
#PF: error_code(0x0000) - not-present page
PGD 0 P4D 0
Oops: 0000 [#1] PREEMPT SMP
CPU: 6 PID: 1825 Comm: stress Not tainted 5.14.0-rc2+ #459
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 0.0.0 02/06/2015
RIP: 0010:perf_misc_flags+0x1c/0x70
Call Trace:
perf_prepare_sample+0x53/0x6b0
perf_event_output_forward+0x67/0x160
__perf_event_overflow+0x52/0xf0
handle_pmi_common+0x207/0x300
intel_pmu_handle_irq+0xcf/0x410
perf_event_nmi_handler+0x28/0x50
nmi_handle+0xc7/0x260
default_do_nmi+0x6b/0x170
exc_nmi+0x103/0x130
asm_exc_nmi+0x76/0xbf
Fixes: 39447b386c ("perf: Enhance perf to allow for guest statistic collection from host")
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20211111020738.2512932-2-seanjc@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit 4716023a8f upstream.
PEBS PERF_SAMPLE_PHYS_ADDR events use perf_virt_to_phys() to convert PMU
sampled virtual addresses to physical using get_user_page_fast_only()
and page_to_phys().
Some get_user_page_fast_only() error cases return false, indicating no
page reference, but still initialize the output page pointer with an
unreferenced page. In these error cases perf_virt_to_phys() calls
put_page(). This causes page reference count underflow, which can lead
to unintentional page sharing.
Fix perf_virt_to_phys() to only put_page() if get_user_page_fast_only()
returns a referenced page.
Fixes: fc7ce9c74c ("perf/core, x86: Add PERF_SAMPLE_PHYS_ADDR")
Signed-off-by: Greg Thelen <gthelen@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20211111021814.757086-1-gthelen@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit b89a05b21f upstream.
In perf_event_addr_filters_apply, the task associated with
the event (event->ctx->task) is read using READ_ONCE at the beginning
of the function, checked, and then re-read from event->ctx->task,
voiding all guarantees of the checks. Reuse the value that was read by
READ_ONCE to ensure the consistency of the task struct throughout the
function.
Fixes: 375637bc52 ("perf/core: Introduce address range filtering")
Signed-off-by: Baptiste Lepers <baptiste.lepers@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20210906015310.12802-1-baptiste.lepers@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit 6c605f8371 upstream.
KCSAN reports a data race between increment and decrement of pin_count:
write to 0xffff888237c2d4e0 of 4 bytes by task 15740 on cpu 1:
find_get_context kernel/events/core.c:4617
__do_sys_perf_event_open kernel/events/core.c:12097 [inline]
__se_sys_perf_event_open kernel/events/core.c:11933
...
read to 0xffff888237c2d4e0 of 4 bytes by task 15743 on cpu 0:
perf_unpin_context kernel/events/core.c:1525 [inline]
__do_sys_perf_event_open kernel/events/core.c:12328 [inline]
__se_sys_perf_event_open kernel/events/core.c:11933
...
Because neither read-modify-write here is atomic, this can lead to one
of the operations being lost, resulting in an inconsistent pin_count.
Fix it by adding the missing locking in the CPU-event case.
Fixes: fe4b04fa31 ("perf: Cure task_oncpu_function_call() races")
Reported-by: syzbot+142c9018f5962db69c7e@syzkaller.appspotmail.com
Signed-off-by: Marco Elver <elver@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20210527104711.2671610-1-elver@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit 08ef1af4de upstream.
Currently, the lockdown state is queried unconditionally, even though
its result is used only if the PERF_SAMPLE_REGS_INTR bit is set in
attr.sample_type. While that doesn't matter in case of the Lockdown LSM,
it causes trouble with the SELinux's lockdown hook implementation.
SELinux implements the locked_down hook with a check whether the current
task's type has the corresponding "lockdown" class permission
("integrity" or "confidentiality") allowed in the policy. This means
that calling the hook when the access control decision would be ignored
generates a bogus permission check and audit record.
Fix this by checking sample_type first and only calling the hook when
its result would be honored.
Fixes: b0c8fdc7fd ("lockdown: Lock down perf when in confidentiality mode")
Signed-off-by: Ondrej Mosnacek <omosnace@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Paul Moore <paul@paul-moore.com>
Link: https://lkml.kernel.org/r/20210224215628.192519-1-omosnace@redhat.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit 78af4dc949 ]
Syzbot reported a lock inversion involving perf. The sore point being
perf holding exec_update_mutex() for a very long time, specifically
across a whole bunch of filesystem ops in pmu::event_init() (uprobes)
and anon_inode_getfile().
This then inverts against procfs code trying to take
exec_update_mutex.
Move the permission checks later, such that we need to hold the mutex
over less code.
Reported-by: syzbot+db9cdf3dd1f64252c6ef@syzkaller.appspotmail.com
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
commit f91072ed1b upstream.
There's a possible race in perf_mmap_close() when checking ring buffer's
mmap_count refcount value. The problem is that the mmap_count check is
not atomic because we call atomic_dec() and atomic_read() separately.
perf_mmap_close:
...
atomic_dec(&rb->mmap_count);
...
if (atomic_read(&rb->mmap_count))
goto out_put;
<ring buffer detach>
free_uid
out_put:
ring_buffer_put(rb); /* could be last */
The race can happen when we have two (or more) events sharing same ring
buffer and they go through atomic_dec() and then they both see 0 as refcount
value later in atomic_read(). Then both will go on and execute code which
is meant to be run just once.
The code that detaches ring buffer is probably fine to be executed more
than once, but the problem is in calling free_uid(), which will later on
demonstrate in related crashes and refcount warnings, like:
refcount_t: addition on 0; use-after-free.
...
RIP: 0010:refcount_warn_saturate+0x6d/0xf
...
Call Trace:
prepare_creds+0x190/0x1e0
copy_creds+0x35/0x172
copy_process+0x471/0x1a80
_do_fork+0x83/0x3a0
__do_sys_wait4+0x83/0x90
__do_sys_clone+0x85/0xa0
do_syscall_64+0x5b/0x1e0
entry_SYSCALL_64_after_hwframe+0x44/0xa9
Using atomic decrease and check instead of separated calls.
Tested-by: Michael Petlan <mpetlan@redhat.com>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Wade Mealing <wmealing@redhat.com>
Fixes: 9bb5d40cd9 ("perf: Fix mmap() accounting hole");
Link: https://lore.kernel.org/r/20200916115311.GE2301783@krava
[sudip: used ring_buffer]
Signed-off-by: Sudip Mukherjee <sudipm.mukherjee@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit 7bdb157cde upstream.
As shown through runtime testing, the "filename" allocation is not
always freed in perf_event_parse_addr_filter().
There are three possible ways that this could happen:
- It could be allocated twice on subsequent iterations through the loop,
- or leaked on the success path,
- or on the failure path.
Clean up the code flow to make it obvious that 'filename' is always
freed in the reallocation path and in the two return paths as well.
We rely on the fact that kfree(NULL) is NOP and filename is initialized
with NULL.
This fixes the leak. No other side effects expected.
[ Dan Carpenter: cleaned up the code flow & added a changelog. ]
[ Ingo Molnar: updated the changelog some more. ]
Fixes: 375637bc52 ("perf/core: Introduce address range filtering")
Signed-off-by: "kiyin(尹亮)" <kiyin@tencent.com>
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: "Srivatsa S. Bhat" <srivatsa@csail.mit.edu>
Cc: Anthony Liguori <aliguori@amazon.com>
--
kernel/events/core.c | 12 +++++-------
1 file changed, 5 insertions(+), 7 deletions(-)
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit 6914303824 ]
This changes perf_event_set_clock to use the new exec_update_mutex
instead of cred_guard_mutex.
This should be safe, as the credentials are only used for reading.
Signed-off-by: Bernd Edlinger <bernd.edlinger@hotmail.de>
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
commit fe5ed7ab99 upstream.
If a tracee is uprobed and it hits int3 inserted by debugger, handle_swbp()
does send_sig(SIGTRAP, current, 0) which means si_code == SI_USER. This used
to work when this code was written, but then GDB started to validate si_code
and now it simply can't use breakpoints if the tracee has an active uprobe:
# cat test.c
void unused_func(void)
{
}
int main(void)
{
return 0;
}
# gcc -g test.c -o test
# perf probe -x ./test -a unused_func
# perf record -e probe_test:unused_func gdb ./test -ex run
GNU gdb (GDB) 10.0.50.20200714-git
...
Program received signal SIGTRAP, Trace/breakpoint trap.
0x00007ffff7ddf909 in dl_main () from /lib64/ld-linux-x86-64.so.2
(gdb)
The tracee hits the internal breakpoint inserted by GDB to monitor shared
library events but GDB misinterprets this SIGTRAP and reports a signal.
Change handle_swbp() to use force_sig(SIGTRAP), this matches do_int3_user()
and fixes the problem.
This is the minimal fix for -stable, arch/x86/kernel/uprobes.c is equally
wrong; it should use send_sigtrap(TRAP_TRACE) instead of send_sig(SIGTRAP),
but this doesn't confuse GDB and needs another x86-specific patch.
Reported-by: Aaron Merey <amerey@redhat.com>
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20200723154420.GA32043@redhat.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit 013b2deba9 upstream.
uprobe_write_opcode() must not cross page boundary; prepare_uprobe()
relies on arch_uprobe_analyze_insn() which should validate "vaddr" but
some architectures (csky, s390, and sparc) don't do this.
We can remove the BUG_ON() check in prepare_uprobe() and validate the
offset early in __uprobe_register(). The new IS_ALIGNED() check matches
the alignment check in arch_prepare_kprobe() on supported architectures,
so I think that all insns must be aligned to UPROBE_SWBP_INSN_SIZE.
Another problem is __update_ref_ctr() which was wrong from the very
beginning, it can read/write outside of kmap'ed page unless "vaddr" is
aligned to sizeof(short), __uprobe_register() should check this too.
Reported-by: Linus Torvalds <torvalds@linux-foundation.org>
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Reviewed-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Acked-by: Christian Borntraeger <borntraeger@de.ibm.com>
Tested-by: Sven Schnelle <svens@linux.ibm.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: stable@vger.kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit d3296fb372 ]
We hit following warning when running tests on kernel
compiled with CONFIG_DEBUG_ATOMIC_SLEEP=y:
WARNING: CPU: 19 PID: 4472 at mm/gup.c:2381 __get_user_pages_fast+0x1a4/0x200
CPU: 19 PID: 4472 Comm: dummy Not tainted 5.6.0-rc6+ #3
RIP: 0010:__get_user_pages_fast+0x1a4/0x200
...
Call Trace:
perf_prepare_sample+0xff1/0x1d90
perf_event_output_forward+0xe8/0x210
__perf_event_overflow+0x11a/0x310
__intel_pmu_pebs_event+0x657/0x850
intel_pmu_drain_pebs_nhm+0x7de/0x11d0
handle_pmi_common+0x1b2/0x650
intel_pmu_handle_irq+0x17b/0x370
perf_event_nmi_handler+0x40/0x60
nmi_handle+0x192/0x590
default_do_nmi+0x6d/0x150
do_nmi+0x2f9/0x3c0
nmi+0x8e/0xd7
While __get_user_pages_fast() is IRQ-safe, it calls access_ok(),
which warns on:
WARN_ON_ONCE(!in_task() && !pagefault_disabled())
Peter suggested disabling page faults around __get_user_pages_fast(),
which gets rid of the warning in access_ok() call.
Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lkml.kernel.org/r/20200407141427.3184722-1-jolsa@kernel.org
Signed-off-by: Sasha Levin <sashal@kernel.org>
commit da9ec3d3dd upstream.
Vince reports a worrying issue:
| so I was tracking down some odd behavior in the perf_fuzzer which turns
| out to be because perf_even_open() sometimes returns 0 (indicating a file
| descriptor of 0) even though as far as I can tell stdin is still open.
... and further the cause:
| error is triggered if aux_sample_size has non-zero value.
|
| seems to be this line in kernel/events/core.c:
|
| if (perf_need_aux_event(event) && !perf_get_aux_event(event, group_leader))
| goto err_locked;
|
| (note, err is never set)
This seems to be a thinko in commit:
ab43762ef0 ("perf: Allow normal events to output AUX data")
... and we should probably return -EINVAL here, as this should only
happen when the new event is mis-configured or does not have a
compatible aux_event group leader.
Fixes: ab43762ef0 ("perf: Allow normal events to output AUX data")
Reported-by: Vince Weaver <vincent.weaver@maine.edu>
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Tested-by: Vince Weaver <vincent.weaver@maine.edu>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit 36b3db03b4 ]
Commit:
5e6c3c7b1e ("perf/aux: Fix tracking of auxiliary trace buffer allocation")
tried to guess the correct combination of arithmetic operations that would
undo the AUX buffer's mlock accounting, and failed, leaking the bottom part
when an allocation needs to be charged partially to both user->locked_vm
and mm->pinned_vm, eventually leaving the user with no locked bonus:
$ perf record -e intel_pt//u -m1,128 uname
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.061 MB perf.data ]
$ perf record -e intel_pt//u -m1,128 uname
Permission error mapping pages.
Consider increasing /proc/sys/kernel/perf_event_mlock_kb,
or try again with a smaller value of -m/--mmap_pages.
(current value: 1,128)
Fix this by subtracting both locked and pinned counts when AUX buffer is
unmapped.
Reported-by: Thomas Richter <tmricht@linux.ibm.com>
Tested-by: Thomas Richter <tmricht@linux.ibm.com>
Signed-off-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
Oleg Nesterov