Linux Perf Users
 help / color / mirror / Atom feed
From: Dapeng Mi <dapeng1.mi@linux.intel.com>
To: Peter Zijlstra <peterz@infradead.org>,
	Ingo Molnar <mingo@redhat.com>,
	Arnaldo Carvalho de Melo <acme@kernel.org>,
	Namhyung Kim <namhyung@kernel.org>,
	Ian Rogers <irogers@google.com>,
	Adrian Hunter <adrian.hunter@intel.com>,
	Alexander Shishkin <alexander.shishkin@linux.intel.com>,
	Andi Kleen <ak@linux.intel.com>,
	Eranian Stephane <eranian@google.com>,
	Sandipan Das <sandipan.das@amd.com>,
	Andrii Nakryiko <andrii@kernel.org>, Song Liu <song@kernel.org>,
	Ravi Bangoria <ravi.bangoria@amd.com>,
	Ananth Narayan <ananth.narayan@amd.com>
Cc: linux-kernel@vger.kernel.org, linux-perf-users@vger.kernel.org,
	bpf@vger.kernel.org, Dapeng Mi <dapeng1.mi@intel.com>,
	Zide Chen <zide.chen@intel.com>,
	Falcon Thomas <thomas.falcon@intel.com>,
	Xudong Hao <xudong.hao@intel.com>,
	Dapeng Mi <dapeng1.mi@linux.intel.com>,
	Sashiko <sashiko-bot@kernel.org>, KP Singh <kpsingh@kernel.org>,
	Matt Bobrowski <matt@bobrowski.net>, Jiri Olsa <jolsa@kernel.org>,
	Ihor Solodrai <ihor.solodrai@linux.dev>,
	Daniel Xu <dxu@dxuuu.xyz>
Subject: [Patch v7 23/24] perf/core: Don't mutate shared branch stack depth
Date: Wed, 18 Nov 2026 11:14:52 +0800	[thread overview]
Message-ID: <20261118031453.1353625-24-dapeng1.mi@linux.intel.com> (raw)
In-Reply-To: <20261118031453.1353625-1-dapeng1.mi@linux.intel.com>

perf_sample_save_brstack() clamps the branch stack depth by directly
overwriting brs->nr with min(event->attr.sample_max_stack, brs->nr).
This is unsafe because the branch stack buffer is shared by all branch
events in the same PMI: once one event with a small sample_max_stack
truncates brs->nr, every subsequent event processed in that PMI sees
the shrunken depth and silently loses branch records it asked for.

Add perf_event_brstack_depth(), which computes the per-event depth
without modifying the shared branch stack. Use it in the relevant callers
so each event is limited only by its own sample_max_stack, without
clobbering the shared LBR state.

bpf_read_branch_records() also relied on the clamped brs->nr, so switch
it to perf_event_brstack_depth() to preserve the same per-event limit for
records returned to BPF programs.

Fixes: c53e14f1ea4a ("perf: Extend per event callchain limit to branch stack")
Reported-by: Sashiko <sashiko-bot@kernel.org>
Signed-off-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
Cc: KP Singh <kpsingh@kernel.org>
Cc: Matt Bobrowski <matt@bobrowski.net>
Cc: Song Liu <song@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Ihor Solodrai <ihor.solodrai@linux.dev>
Cc: Daniel Xu <dxu@dxuuu.xyz>
---
 include/linux/perf_event.h | 13 ++++++++++---
 kernel/events/core.c       |  8 ++++----
 kernel/trace/bpf_trace.c   |  6 ++++--
 3 files changed, 18 insertions(+), 9 deletions(-)

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 19de3f1cbd6e..35d3cc4cc07e 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1424,12 +1424,19 @@ static inline bool has_branch_stack(struct perf_event *event)
 	return event->attr.sample_type & PERF_SAMPLE_BRANCH_STACK;
 }
 
+static inline u64 perf_event_brstack_depth(struct perf_event *event,
+					   struct perf_branch_stack *brs)
+{
+	return min_t(u16, event->attr.sample_max_stack, brs->nr);
+}
+
 static inline void perf_sample_save_brstack(struct perf_sample_data *data,
 					    struct perf_event *event,
 					    struct perf_branch_stack *brs,
 					    u64 *brs_cntr)
 {
 	int size = sizeof(u64); /* nr */
+	u64 nr;
 
 	if (!has_branch_stack(event))
 		return;
@@ -1439,9 +1446,9 @@ static inline void perf_sample_save_brstack(struct perf_sample_data *data,
 	if (branch_sample_hw_index(event))
 		size += sizeof(u64);
 
-	brs->nr = min_t(u16, event->attr.sample_max_stack, brs->nr);
+	nr = perf_event_brstack_depth(event, brs);
 
-	size += brs->nr * sizeof(struct perf_branch_entry);
+	size += nr * sizeof(struct perf_branch_entry);
 
 	/*
 	 * The extension space for counters is appended after the
@@ -1449,7 +1456,7 @@ static inline void perf_sample_save_brstack(struct perf_sample_data *data,
 	 * of events of each branch.
 	 */
 	if (brs_cntr)
-		size += brs->nr * sizeof(u64);
+		size += nr * sizeof(u64);
 
 	data->br_stack = brs;
 	data->br_stack_cntr = brs_cntr;
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 457d75ea7142..8b80ca788523 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -8462,12 +8462,12 @@ void perf_output_sample(struct perf_output_handle *handle,
 
 	if (sample_type & PERF_SAMPLE_BRANCH_STACK) {
 		if (data->br_stack) {
+			u64 nr = perf_event_brstack_depth(event, data->br_stack);
 			size_t size;
 
-			size = data->br_stack->nr
-			     * sizeof(struct perf_branch_entry);
+			size = nr * sizeof(struct perf_branch_entry);
 
-			perf_output_put(handle, data->br_stack->nr);
+			perf_output_put(handle, nr);
 			if (branch_sample_hw_index(event))
 				perf_output_put(handle, data->br_stack->hw_idx);
 			perf_output_copy(handle, data->br_stack->entries, size);
@@ -8476,7 +8476,7 @@ void perf_output_sample(struct perf_output_handle *handle,
 			 * right after the struct perf_branch_stack.
 			 */
 			if (data->br_stack_cntr) {
-				size = data->br_stack->nr * sizeof(u64);
+				size = nr * sizeof(u64);
 				perf_output_copy(handle, data->br_stack_cntr, size);
 			}
 		} else {
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 2aec56d7f3d3..7c42bbf05c2f 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -1549,6 +1549,7 @@ BPF_CALL_4(bpf_read_branch_records, struct bpf_perf_event_data_kern *, ctx,
 	static const u32 br_entry_size = sizeof(struct perf_branch_entry);
 	struct perf_branch_stack *br_stack = ctx->data->br_stack;
 	u32 to_copy;
+	u64 nr;
 
 	if (unlikely(flags & ~BPF_F_GET_BRANCH_RECORDS_SIZE))
 		return -EINVAL;
@@ -1559,13 +1560,14 @@ BPF_CALL_4(bpf_read_branch_records, struct bpf_perf_event_data_kern *, ctx,
 	if (unlikely(!br_stack))
 		return -ENOENT;
 
+	nr = perf_event_brstack_depth(ctx->event, br_stack);
 	if (flags & BPF_F_GET_BRANCH_RECORDS_SIZE)
-		return br_stack->nr * br_entry_size;
+		return nr * br_entry_size;
 
 	if (!buf || (size % br_entry_size != 0))
 		return -EINVAL;
 
-	to_copy = min_t(u32, br_stack->nr * br_entry_size, size);
+	to_copy = min_t(u32, nr * br_entry_size, size);
 	memcpy(buf, br_stack->entries, to_copy);
 
 	return to_copy;
-- 
2.34.1


  parent reply	other threads:[~2026-11-18  3:24 UTC|newest]

Thread overview: 49+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-11-18  3:14 [Patch v7 00/24] perf/x86: Fix multiple LBR sampling issues Dapeng Mi
2026-11-18  3:14 ` [Patch v7 01/24] perf/x86: Disable LBR if x86_pmu.lbr_nr exceeds MAX_LBR_ENTRIES Dapeng Mi
2026-11-18  3:50   ` sashiko-bot
2026-11-18  3:14 ` [Patch v7 02/24] perf/x86/intel: Validate LBR XSAVE state before updating LBR stack Dapeng Mi
2026-11-18  3:48   ` sashiko-bot
2026-11-18  3:14 ` [Patch v7 03/24] perf/x86/amd/lbr: Limit branch snapshots to valid entries Dapeng Mi
2026-11-18  3:34   ` sashiko-bot
2026-11-18  3:14 ` [Patch v7 04/24] perf/x86/intel: " Dapeng Mi
2026-11-18  3:37   ` sashiko-bot
2026-11-18  3:14 ` [Patch v7 05/24] perf/x86: Add lbr_enabled to track LBR state Dapeng Mi
2026-11-18  3:58   ` sashiko-bot
2026-11-18  3:14 ` [Patch v7 06/24] perf/x86/amd: Avoid re-enabling PMU and LBR for BPF when disabled Dapeng Mi
2026-11-18  3:43   ` sashiko-bot
2026-11-18  3:14 ` [Patch v7 07/24] perf/x86/intel: Add helper to enable PMU without LBR Dapeng Mi
2026-11-18  3:28   ` sashiko-bot
2026-11-18  3:14 ` [Patch v7 08/24] perf/x86/intel: Avoid re-enabling PMU and LBR for BPF when disabled Dapeng Mi
2026-11-18  3:39   ` sashiko-bot
2026-11-18  3:14 ` [Patch v7 09/24] perf/x86/intel: Keep LBR frozen throughout PMI handling Dapeng Mi
2026-11-18  3:42   ` sashiko-bot
2026-11-18  3:14 ` [Patch v7 10/24] perf: Add counted-bounds tracking for perf_branch_stack Dapeng Mi
2026-11-18  3:35   ` sashiko-bot
2026-11-18  3:14 ` [Patch v7 11/24] perf/x86/intel: Allow LBR read helpers to operate on explicit stacks Dapeng Mi
2026-11-18  3:32   ` sashiko-bot
2026-11-18  3:14 ` [Patch v7 12/24] perf/x86/intel: Use a dedicated LBR stack for BPF snapshotting Dapeng Mi
2026-11-18  3:43   ` sashiko-bot
2026-11-18  3:14 ` [Patch v7 13/24] perf/x86/intel: Always snapshot live hardware LBR state for BPF Dapeng Mi
2026-11-18  3:46   ` sashiko-bot
2026-11-18  3:14 ` [Patch v7 14/24] perf/x86/intel: Account lbr_pebs_users for arch-PEBS events Dapeng Mi
2026-11-18  3:34   ` sashiko-bot
2026-11-18  3:14 ` [Patch v7 15/24] perf/x86/intel: Set PERF_EV_CAP_SIBLING for pure branch counter events Dapeng Mi
2026-11-18  4:05   ` sashiko-bot
2026-11-18  3:14 ` [Patch v7 16/24] perf/x86/intel: Account LBR user counts " Dapeng Mi
2026-11-18  3:49   ` sashiko-bot
2026-11-18  3:14 ` [Patch v7 17/24] perf/x86/intel: Refresh LBR stack for non-PEBS LBR events when needed Dapeng Mi
2026-11-18  3:14 ` [Patch v7 18/24] perf/x86/intel: Fix draining of un-overflowed PEBS buffer in PMI handler Dapeng Mi
2026-11-18  3:46   ` sashiko-bot
2026-11-18  3:14 ` [Patch v7 19/24] perf/x86/intel: Drain PEBS buffer for branch events with PEBS LBR users Dapeng Mi
2026-11-18  3:52   ` sashiko-bot
2026-11-18  3:14 ` [Patch v7 20/24] perf/x86/intel: Clear raw LBR counters in the LBR stack Dapeng Mi
2026-11-18  3:50   ` sashiko-bot
2026-11-18  3:54   ` bot+bpf-ci
2026-11-18  3:14 ` [Patch v7 21/24] perf/x86/intel: Refresh LBR stack for LBR counter events in PMI handler Dapeng Mi
2026-11-18  3:45   ` sashiko-bot
2026-11-18  3:14 ` [Patch v7 22/24] perf/x86/intel: Pass LBR stack size into intel_pmu_store_lbr() Dapeng Mi
2026-11-18  3:46   ` sashiko-bot
2026-11-18  3:14 ` Dapeng Mi [this message]
2026-11-18  3:51   ` [Patch v7 23/24] perf/core: Don't mutate shared branch stack depth sashiko-bot
2026-11-18  3:14 ` [Patch v7 24/24] perf/x86/intel: Fix incorrect PERF_METRICS overflow bit clearing Dapeng Mi
2026-11-18  3:46   ` sashiko-bot

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20261118031453.1353625-24-dapeng1.mi@linux.intel.com \
    --to=dapeng1.mi@linux.intel.com \
    --cc=acme@kernel.org \
    --cc=adrian.hunter@intel.com \
    --cc=ak@linux.intel.com \
    --cc=alexander.shishkin@linux.intel.com \
    --cc=ananth.narayan@amd.com \
    --cc=andrii@kernel.org \
    --cc=bpf@vger.kernel.org \
    --cc=dapeng1.mi@intel.com \
    --cc=dxu@dxuuu.xyz \
    --cc=eranian@google.com \
    --cc=ihor.solodrai@linux.dev \
    --cc=irogers@google.com \
    --cc=jolsa@kernel.org \
    --cc=kpsingh@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-perf-users@vger.kernel.org \
    --cc=matt@bobrowski.net \
    --cc=mingo@redhat.com \
    --cc=namhyung@kernel.org \
    --cc=peterz@infradead.org \
    --cc=ravi.bangoria@amd.com \
    --cc=sandipan.das@amd.com \
    --cc=sashiko-bot@kernel.org \
    --cc=song@kernel.org \
    --cc=thomas.falcon@intel.com \
    --cc=xudong.hao@intel.com \
    --cc=zide.chen@intel.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox