From 5e6c3c7b1ec217c1c4c95d9148182302b9969b97 Mon Sep 17 00:00:00 2001 From: Thomas Richter Date: Mon, 21 Oct 2019 10:33:54 +0200 Subject: perf/aux: Fix tracking of auxiliary trace buffer allocation The following commit from the v5.4 merge window: d44248a41337 ("perf/core: Rework memory accounting in perf_mmap()") ... breaks auxiliary trace buffer tracking. If I run command 'perf record -e rbd000' to record samples and saving them in the **auxiliary** trace buffer then the value of 'locked_vm' becomes negative after all trace buffers have been allocated and released: During allocation the values increase: [52.250027] perf_mmap user->locked_vm:0x87 pinned_vm:0x0 ret:0 [52.250115] perf_mmap user->locked_vm:0x107 pinned_vm:0x0 ret:0 [52.250251] perf_mmap user->locked_vm:0x188 pinned_vm:0x0 ret:0 [52.250326] perf_mmap user->locked_vm:0x208 pinned_vm:0x0 ret:0 [52.250441] perf_mmap user->locked_vm:0x289 pinned_vm:0x0 ret:0 [52.250498] perf_mmap user->locked_vm:0x309 pinned_vm:0x0 ret:0 [52.250613] perf_mmap user->locked_vm:0x38a pinned_vm:0x0 ret:0 [52.250715] perf_mmap user->locked_vm:0x408 pinned_vm:0x2 ret:0 [52.250834] perf_mmap user->locked_vm:0x408 pinned_vm:0x83 ret:0 [52.250915] perf_mmap user->locked_vm:0x408 pinned_vm:0x103 ret:0 [52.251061] perf_mmap user->locked_vm:0x408 pinned_vm:0x184 ret:0 [52.251146] perf_mmap user->locked_vm:0x408 pinned_vm:0x204 ret:0 [52.251299] perf_mmap user->locked_vm:0x408 pinned_vm:0x285 ret:0 [52.251383] perf_mmap user->locked_vm:0x408 pinned_vm:0x305 ret:0 [52.251544] perf_mmap user->locked_vm:0x408 pinned_vm:0x386 ret:0 [52.251634] perf_mmap user->locked_vm:0x408 pinned_vm:0x406 ret:0 [52.253018] perf_mmap user->locked_vm:0x408 pinned_vm:0x487 ret:0 [52.253197] perf_mmap user->locked_vm:0x408 pinned_vm:0x508 ret:0 [52.253374] perf_mmap user->locked_vm:0x408 pinned_vm:0x589 ret:0 [52.253550] perf_mmap user->locked_vm:0x408 pinned_vm:0x60a ret:0 [52.253726] perf_mmap user->locked_vm:0x408 pinned_vm:0x68b ret:0 [52.253903] perf_mmap user->locked_vm:0x408 pinned_vm:0x70c ret:0 [52.254084] perf_mmap user->locked_vm:0x408 pinned_vm:0x78d ret:0 [52.254263] perf_mmap user->locked_vm:0x408 pinned_vm:0x80e ret:0 The value of user->locked_vm increases to a limit then the memory is tracked by pinned_vm. During deallocation the size is subtracted from pinned_vm until it hits a limit. Then a larger value is subtracted from locked_vm leading to a large number (because of type unsigned): [64.267797] perf_mmap_close mmap_user->locked_vm:0x408 pinned_vm:0x78d [64.267826] perf_mmap_close mmap_user->locked_vm:0x408 pinned_vm:0x70c [64.267848] perf_mmap_close mmap_user->locked_vm:0x408 pinned_vm:0x68b [64.267869] perf_mmap_close mmap_user->locked_vm:0x408 pinned_vm:0x60a [64.267891] perf_mmap_close mmap_user->locked_vm:0x408 pinned_vm:0x589 [64.267911] perf_mmap_close mmap_user->locked_vm:0x408 pinned_vm:0x508 [64.267933] perf_mmap_close mmap_user->locked_vm:0x408 pinned_vm:0x487 [64.267952] perf_mmap_close mmap_user->locked_vm:0x408 pinned_vm:0x406 [64.268883] perf_mmap_close mmap_user->locked_vm:0x307 pinned_vm:0x406 [64.269117] perf_mmap_close mmap_user->locked_vm:0x206 pinned_vm:0x406 [64.269433] perf_mmap_close mmap_user->locked_vm:0x105 pinned_vm:0x406 [64.269536] perf_mmap_close mmap_user->locked_vm:0x4 pinned_vm:0x404 [64.269797] perf_mmap_close mmap_user->locked_vm:0xffffffffffffff84 pinned_vm:0x303 [64.270105] perf_mmap_close mmap_user->locked_vm:0xffffffffffffff04 pinned_vm:0x202 [64.270374] perf_mmap_close mmap_user->locked_vm:0xfffffffffffffe84 pinned_vm:0x101 [64.270628] perf_mmap_close mmap_user->locked_vm:0xfffffffffffffe04 pinned_vm:0x0 This value sticks for the user until system is rebooted, causing follow-on system calls using locked_vm resource limit to fail. Note: There is no issue using the normal trace buffer. In fact the issue is in perf_mmap_close(). During allocation auxiliary trace buffer memory is either traced as 'extra' and added to 'pinned_vm' or trace as 'user_extra' and added to 'locked_vm'. This applies for normal trace buffers and auxiliary trace buffer. However in function perf_mmap_close() all auxiliary trace buffer is subtraced from 'locked_vm' and never from 'pinned_vm'. This breaks the ballance. Signed-off-by: Thomas Richter Acked-by: Peter Zijlstra Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: acme@kernel.org Cc: gor@linux.ibm.com Cc: hechaol@fb.com Cc: heiko.carstens@de.ibm.com Cc: linux-perf-users@vger.kernel.org Cc: songliubraving@fb.com Fixes: d44248a41337 ("perf/core: Rework memory accounting in perf_mmap()") Link: https://lkml.kernel.org/r/20191021083354.67868-1-tmricht@linux.ibm.com [ Minor readability edits. ] Signed-off-by: Ingo Molnar --- kernel/events/core.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'kernel/events') diff --git a/kernel/events/core.c b/kernel/events/core.c index 9ec0b0bfddbd..f5d7950d1931 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -5607,8 +5607,10 @@ static void perf_mmap_close(struct vm_area_struct *vma) perf_pmu_output_stop(event); /* now it's safe to free the pages */ - atomic_long_sub(rb->aux_nr_pages, &mmap_user->locked_vm); - atomic64_sub(rb->aux_mmap_locked, &vma->vm_mm->pinned_vm); + if (!rb->aux_mmap_locked) + atomic_long_sub(rb->aux_nr_pages, &mmap_user->locked_vm); + else + atomic64_sub(rb->aux_mmap_locked, &vma->vm_mm->pinned_vm); /* this has to be the last one */ rb_free_aux(rb); -- cgit v1.2.3 From f3a519e4add93b7b31a6616f0b09635ff2e6a159 Mon Sep 17 00:00:00 2001 From: Alexander Shishkin Date: Tue, 22 Oct 2019 10:39:40 +0300 Subject: perf/aux: Fix AUX output stopping Commit: 8a58ddae2379 ("perf/core: Fix exclusive events' grouping") allows CAP_EXCLUSIVE events to be grouped with other events. Since all of those also happen to be AUX events (which is not the case the other way around, because arch/s390), this changes the rules for stopping the output: the AUX event may not be on its PMU's context any more, if it's grouped with a HW event, in which case it will be on that HW event's context instead. If that's the case, munmap() of the AUX buffer can't find and stop the AUX event, potentially leaving the last reference with the atomic context, which will then end up freeing the AUX buffer. This will then trip warnings: Fix this by using the context's PMU context when looking for events to stop, instead of the event's PMU context. Signed-off-by: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Thomas Gleixner Cc: Vince Weaver Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20191022073940.61814-1-alexander.shishkin@linux.intel.com Signed-off-by: Ingo Molnar --- kernel/events/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/events') diff --git a/kernel/events/core.c b/kernel/events/core.c index f5d7950d1931..bb3748d29b04 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -6949,7 +6949,7 @@ static void __perf_event_output_stop(struct perf_event *event, void *data) static int __perf_pmu_output_stop(void *info) { struct perf_event *event = info; - struct pmu *pmu = event->pmu; + struct pmu *pmu = event->ctx->pmu; struct perf_cpu_context *cpuctx = this_cpu_ptr(pmu->pmu_cpu_context); struct remote_output ro = { .rb = event->rb, -- cgit v1.2.3 From 8c7e975667fbc3b7c816119dd56104739899f125 Mon Sep 17 00:00:00 2001 From: Alexander Shishkin Date: Fri, 25 Oct 2019 15:16:36 +0300 Subject: perf/core: Start rejecting the syscall with attr.__reserved_2 set Commit: 1a5941312414c ("perf: Add wakeup watermark control to the AUX area") added attr.__reserved_2 padding, but forgot to add an ABI check to reject attributes with this field set. Fix that. Signed-off-by: Alexander Shishkin Signed-off-by: Peter Zijlstra (Intel) Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Mark Rutland Cc: Namhyung Kim Cc: Stephane Eranian Cc: Thomas Gleixner Cc: Vince Weaver Cc: adrian.hunter@intel.com Cc: mathieu.poirier@linaro.org Link: https://lkml.kernel.org/r/20191025121636.75182-1-alexander.shishkin@linux.intel.com Signed-off-by: Ingo Molnar --- kernel/events/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/events') diff --git a/kernel/events/core.c b/kernel/events/core.c index bb3748d29b04..aec8dba2bea4 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -10635,7 +10635,7 @@ static int perf_copy_attr(struct perf_event_attr __user *uattr, attr->size = size; - if (attr->__reserved_1) + if (attr->__reserved_1 || attr->__reserved_2) return -EINVAL; if (attr->sample_type & ~(PERF_SAMPLE_MAX-1)) -- cgit v1.2.3