From af169b7759a9b9369b5106cd07a25c57ce60119e Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 21 Nov 2022 15:57:44 +0100 Subject: [PATCH 1/2] perf: Fixup SIGTRAP and sample_flags interaction The perf_event_attr::sigtrap functionality relies on data->addr being set. However commit 7b0846301531 ("perf: Use sample_flags for addr") changed this to only initialize data->addr when not 0. Fixes: 7b0846301531 ("perf: Use sample_flags for addr") Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/Y3426b4OimE%2FI5po%40hirez.programming.kicks-ass.net --- kernel/events/core.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/kernel/events/core.c b/kernel/events/core.c index 884871427a94..f2bb27e5c316 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -9328,7 +9328,10 @@ static int __perf_event_overflow(struct perf_event *event, */ WARN_ON_ONCE(event->pending_sigtrap != pending_id); } - event->pending_addr = data->addr; + + event->pending_addr = 0; + if (data->sample_flags & PERF_SAMPLE_ADDR) + event->pending_addr = data->addr; irq_work_queue(&event->pending_irq); } From 030a976efae83f7b6593afb11a8254d42f9290fe Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Sat, 19 Nov 2022 10:45:54 +0800 Subject: [PATCH 2/2] perf: Consider OS filter fail Some PMUs (notably the traditional hardware kind) have boundary issues with the OS filter. Specifically, it is possible for perf_event_attr::exclude_kernel=1 events to trigger in-kernel due to SKID or errata. This can upset the sigtrap logic some and trigger the WARN. However, if this invalid sample is the first we must not loose the SIGTRAP, OTOH if it is the second, it must not override the pending_addr with a (possibly) invalid one. Fixes: ca6c21327c6a ("perf: Fix missing SIGTRAPs") Reported-by: Pengfei Xu Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Marco Elver Tested-by: Pengfei Xu Link: https://lkml.kernel.org/r/Y3hDYiXwRnJr8RYG@xpf.sh.intel.com --- kernel/events/core.c | 24 ++++++++++++++++++++++-- 1 file changed, 22 insertions(+), 2 deletions(-) diff --git a/kernel/events/core.c b/kernel/events/core.c index f2bb27e5c316..9d15d2d96119 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -9273,6 +9273,19 @@ int perf_event_account_interrupt(struct perf_event *event) return __perf_event_account_interrupt(event, 1); } +static inline bool sample_is_allowed(struct perf_event *event, struct pt_regs *regs) +{ + /* + * Due to interrupt latency (AKA "skid"), we may enter the + * kernel before taking an overflow, even if the PMU is only + * counting user events. + */ + if (event->attr.exclude_kernel && !user_mode(regs)) + return false; + + return true; +} + /* * Generic event overflow handling, sampling. */ @@ -9306,6 +9319,13 @@ static int __perf_event_overflow(struct perf_event *event, } if (event->attr.sigtrap) { + /* + * The desired behaviour of sigtrap vs invalid samples is a bit + * tricky; on the one hand, one should not loose the SIGTRAP if + * it is the first event, on the other hand, we should also not + * trigger the WARN or override the data address. + */ + bool valid_sample = sample_is_allowed(event, regs); unsigned int pending_id = 1; if (regs) @@ -9313,7 +9333,7 @@ static int __perf_event_overflow(struct perf_event *event, if (!event->pending_sigtrap) { event->pending_sigtrap = pending_id; local_inc(&event->ctx->nr_pending); - } else if (event->attr.exclude_kernel) { + } else if (event->attr.exclude_kernel && valid_sample) { /* * Should not be able to return to user space without * consuming pending_sigtrap; with exceptions: @@ -9330,7 +9350,7 @@ static int __perf_event_overflow(struct perf_event *event, } event->pending_addr = 0; - if (data->sample_flags & PERF_SAMPLE_ADDR) + if (valid_sample && (data->sample_flags & PERF_SAMPLE_ADDR)) event->pending_addr = data->addr; irq_work_queue(&event->pending_irq); }