[PATCH v3] perf/core: fix mlock accounting in perf_mmap()

[PATCH v3] perf/core: fix mlock accounting in perf_mmap()

[Song Liu]

Eecreasing sysctl_perf_event_mlock between two consecutive perf_mmap()s of
a perf ring buffer may lead to an integer underflow in locked memory
accounting. This may lead to the undesired behaviors, such as failures in
BPF map creation.

Address this by adjusting the accounting logic to take into account the
possibility that the amount of already locked memory may exceed the
current limit.

Fixes: c4b75479741c ("perf/core: Make the mlock accounting simple again")
Signed-off-by: Song Liu <songliubraving@fb.com>
Suggested-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
---
 kernel/events/core.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index e543bab787e5..fdb7f7ef380c 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -5917,7 +5917,15 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma)
 	 */
 	user_lock_limit *= num_online_cpus();
 
-	user_locked = atomic_long_read(&user->locked_vm) + user_extra;
+	user_locked = atomic_long_read(&user->locked_vm);
+
+	/*
+	 * sysctl_perf_event_mlock may have changed, so that
+	 *     user->locked_vm > user_lock_limit
+	 */
+	if (user_locked > user_lock_limit)
+		user_locked = user_lock_limit;
+	user_locked += user_extra;
 
 	if (user_locked > user_lock_limit) {
 		/*
-- 
2.17.1

Re: [PATCH v3] perf/core: fix mlock accounting in perf_mmap()

[Alexander Shishkin]

Song Liu <songliubraving@fb.com> writes:

> Eecreasing sysctl_perf_event_mlock between two consecutive perf_mmap()s of

Typo: "Decreasing".

> a perf ring buffer may lead to an integer underflow in locked memory
> accounting. This may lead to the undesired behaviors, such as failures in
> BPF map creation.
>
> Address this by adjusting the accounting logic to take into account the
> possibility that the amount of already locked memory may exceed the
> current limit.
>
> Fixes: c4b75479741c ("perf/core: Make the mlock accounting simple again")
> Signed-off-by: Song Liu <songliubraving@fb.com>
> Suggested-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
> Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
> Cc: Jiri Olsa <jolsa@kernel.org>
> Cc: Peter Zijlstra <peterz@infradead.org>

Other than that,

Acked-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>

Thanks,
--
Alex

Re: [PATCH v3] perf/core: fix mlock accounting in perf_mmap()

[Song Liu]

Thanks Alex!

> On Jan 24, 2020, at 1:25 AM, Alexander Shishkin <alexander.shishkin@linux.intel.com> wrote:
> 
> Song Liu <songliubraving@fb.com> writes:
> 
>> Eecreasing sysctl_perf_event_mlock between two consecutive perf_mmap()s of
> 
> Typo: "Decreasing".

Peter, could you please fix this typo when you apply the patch? I guess
it is not necessary to spam the list with a v4 just for this typo. 

Thanks,
Song

> 
>> a perf ring buffer may lead to an integer underflow in locked memory
>> accounting. This may lead to the undesired behaviors, such as failures in
>> BPF map creation.
>> 
>> Address this by adjusting the accounting logic to take into account the
>> possibility that the amount of already locked memory may exceed the
>> current limit.
>> 
>> Fixes: c4b75479741c ("perf/core: Make the mlock accounting simple again")
>> Signed-off-by: Song Liu <songliubraving@fb.com>
>> Suggested-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
>> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
>> Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
>> Cc: Jiri Olsa <jolsa@kernel.org>
>> Cc: Peter Zijlstra <peterz@infradead.org>
> 
> Other than that,
> 
> Acked-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
> 
> Thanks,
> --
> Alex

Re: [PATCH v3] perf/core: fix mlock accounting in perf_mmap()

[Peter Zijlstra]

On Fri, Jan 24, 2020 at 09:28:26PM +0000, Song Liu wrote:
> Thanks Alex!
> 
> > On Jan 24, 2020, at 1:25 AM, Alexander Shishkin <alexander.shishkin@linux.intel.com> wrote:
> > 
> > Song Liu <songliubraving@fb.com> writes:
> > 
> >> Eecreasing sysctl_perf_event_mlock between two consecutive perf_mmap()s of
> > 
> > Typo: "Decreasing".
> 
> Peter, could you please fix this typo when you apply the patch? I guess
> it is not necessary to spam the list with a v4 just for this typo. 

Done!

[tip: perf/urgent] perf/core: Fix mlock accounting in perf_mmap()

[tip-bot2 for Song Liu]

The following commit has been merged into the perf/urgent branch of tip:

Commit-ID:     003461559ef7a9bd0239bae35a22ad8924d6e9ad
Gitweb:        https://git.kernel.org/tip/003461559ef7a9bd0239bae35a22ad8924d6e9ad
Author:        Song Liu <songliubraving@fb.com>
AuthorDate:    Thu, 23 Jan 2020 10:11:46 -08:00
Committer:     Ingo Molnar <mingo@kernel.org>
CommitterDate: Tue, 28 Jan 2020 21:20:18 +01:00

perf/core: Fix mlock accounting in perf_mmap()

Decreasing sysctl_perf_event_mlock between two consecutive perf_mmap()s of
a perf ring buffer may lead to an integer underflow in locked memory
accounting. This may lead to the undesired behaviors, such as failures in
BPF map creation.

Address this by adjusting the accounting logic to take into account the
possibility that the amount of already locked memory may exceed the
current limit.

Fixes: c4b75479741c ("perf/core: Make the mlock accounting simple again")
Suggested-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Signed-off-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: <stable@vger.kernel.org>
Acked-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Link: https://lkml.kernel.org/r/20200123181146.2238074-1-songliubraving@fb.com
---
 kernel/events/core.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 2173c23..2d9aeba 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -5916,7 +5916,15 @@ accounting:
 	 */
 	user_lock_limit *= num_online_cpus();
 
-	user_locked = atomic_long_read(&user->locked_vm) + user_extra;
+	user_locked = atomic_long_read(&user->locked_vm);
+
+	/*
+	 * sysctl_perf_event_mlock may have changed, so that
+	 *     user->locked_vm > user_lock_limit
+	 */
+	if (user_locked > user_lock_limit)
+		user_locked = user_lock_limit;
+	user_locked += user_extra;
 
 	if (user_locked > user_lock_limit) {
 		/*