Skip to contentSkip to conversation

arm64: Add BRBE support for bpf_get_branch_snapshot()

PATCH Superseded Puranjay Mohan 3 participants 9 messages Apr 13 – Apr 27

Subsystems (5)

v3 of 7 Superseded Latest is v7 →

lore
Share & tools
lore
#0 lore raw

v3 cover arm64: Add BRBE support for bpf_get_branch_snapshot()

v2: https://lore.kernel.org/all/[email protected]/
Changes in v3:
- Move NULL pmu_ctx fix from arm_pmuv3.c to perf core (Leo Yan)
- Use union to clear branch entry bitfields instead of per-field zeroing (Leo Yan)
- Remove per-CPU brbe_active flag; check BRBCR_EL1 == 0 instead (Rob Herring)
- Remove redundant valid_brbidr() check in snapshot path (Rob Herring)
- Introduce for_each_brbe_entry() iterator to deduplicate bank iteration (Rob Herring)
- Include perf core maintainers (Leo Yan, Rob Herring)

v1: https://lore.kernel.org/all/[email protected]/
Changes in v2:
- Rebased on arm64/for-next/core
- Add per-CPU brbe_active flag to guard against UNDEFINED sysreg access on non-BRBE CPUs in heterogeneous big.LITTLE systems.
- Fix pre-existing bug in perf_clear_branch_entry_bitfields() that missed zeroing new_type and priv bitfields, added as a separate patch with Fixes tags (new patch 2).
- Use architecture-specific selftest threshold (#if defined(__aarch64__)) instead of raising the global threshold, to preserve x86 regression detection.

RFC: https://lore.kernel.org/all/[email protected]/
Changes from RFC:
- Fix pre-existing NULL pointer dereference in armv8pmu_sched_task() found by Leo Yan during testing (patch 1)
- Pause BRBE before local_daif_save() to avoid branch pollution from trace_hardirqs_off()
- Use local_daif_save() to prevent pNMI race from counter overflow (Mark Rutland)
- Reuse perf_entry_from_brbe_regset() instead of duplicating register read logic, by making it accept NULL event (Mark Rutland)
- Invalidate BRBE after reading to maintain record contiguity for other consumers (Mark Rutland)
- Adjust selftest wasted_entries threshold for ARM64 (patch 3)
- Tested on ARM FVP with BRBE enabled

This series enables the bpf_get_branch_snapshot() BPF helper on ARM64 by implementing the perf_snapshot_branch_stack static call for ARM's Branch Record Buffer Extension (BRBE).

bpf_get_branch_snapshot() [1] allows BPF programs to capture hardware branch records on-demand from any BPF tracing context. This was previously only available on x86 (Intel LBR) since v5.16. With BRBE available on ARMv9, this series closes the gap for ARM64.

Usage model
-----------

The helper works in conjunction with perf events. The userspace component of the BPF application opens a perf event with PERF_SAMPLE_BRANCH_STACK on each CPU, which configures the hardware to continuously record branches into BRBE (on ARM64) or LBR (on x86). A BPF program attached to a tracepoint, kprobe, or fentry hook can then call bpf_get_branch_snapshot() to snapshot the branch buffer at any point. Without an active perf event, BRBE is not recording and the buffer is empty.

On-demand branch snapshots from BPF are useful for diagnosing which specific code path was taken inside a function. Stack traces only show function boundaries, but branch records reveal the exact sequence of jumps, calls, and returns within a function -- making it possible to identify which specific error check triggered a failure, or which callback implementation was invoked through a function pointer.

For example, retsnoop [2] is a BPF-based tool for non-intrusive mass-tracing of kernel internals. Its LBR mode (--lbr) creates per-CPU perf events with PERF_SAMPLE_BRANCH_STACK and then uses bpf_get_branch_snapshot() in its fentry/fexit BPF programs to capture branch records whenever a traced function returns an error.

Consider debugging a bpf() syscall that returns -EINVAL when creating a BPF map with invalid parameters. Running retsnoop on an ARM64 FVP with BRBE to trace the bpf() syscall and array_map_alloc_check():

  $ retsnoop -e '*sys_bpf' -a 'array_map_alloc_check' --lbr=any \
             -F -k vmlinux --debug full-lbr
  $ simfail bpf-bad-map-max-entries-array  # in another terminal

Output of retsnoop:

--- fentry BPF program (entries #63-#17) ---

[#63-#59] __htab_map_lookup_elem: hash table walk with memcmp (hashtab.c)
[#58] __htab_map_lookup_elem+0x98 -> dump_bpf_prog+0xc850 (hashtab.c:750)
[#57-#55] ... dump_bpf_prog internal branches ...
[#54] dump_bpf_prog+0xcab8 -> bpf_get_current_pid_tgid+0x0 (helpers.c:225)
[#53] bpf_get_current_pid_tgid+0x1c -> dump_bpf_prog+0xcabc (helpers.c:225)
[#52-#51] ... dump_bpf_prog -> __htab_map_lookup_elem ... [#50-#47] __htab_map_lookup_elem: htab_map_hash (jhash2), select_bucket
[#46-#42] lookup_nulls_elem_raw: hash chain walk with memcmp (hashtab.c:717)
[#41] __htab_map_lookup_elem+0x98 -> dump_bpf_prog+0xcaf8 (hashtab.c:750)
[#40-#37] ... dump_bpf_prog -> bpf_ktime_get_ns ...
[#36] bpf_ktime_get_ns+0x10 -> ktime_get_mono_fast_ns+0x0 (helpers.c:178)
[#35-#32] ktime_get_mono_fast_ns: tk_clock_read -> arch_counter_get_cntpct
[#31] ktime_get_mono_fast_ns+0x9c -> bpf_ktime_get_ns+0x14 (timekeeping.c:493)
[#30] bpf_ktime_get_ns+0x18 -> dump_bpf_prog+0xcd50 (helpers.c:178)
[#29-#25] ... dump_bpf_prog internal branches ...
[#24] dump_bpf_prog+0x11b28 -> __bpf_prog_exit_recur+0x0 (trampoline.c:1190)
[#23-#17] __bpf_prog_exit_recur: rcu_read_unlock, migrate_enable (trampoline.c:1195)

--- array_map_alloc_check (entries #16-#12) ---

  [#16] dump_bpf_prog+0x11b38       -> array_map_alloc_check+0x8       (arraymap.c:55)
  [#15] array_map_alloc_check+0x18  -> array_map_alloc_check+0xb8      (arraymap.c:56)
        . bpf_map_attr_numa_node       . bpf_map_attr_numa_node
  [#14] array_map_alloc_check+0xbc  -> array_map_alloc_check+0x20      (arraymap.c:59)
        . bpf_map_attr_numa_node
  [#13] array_map_alloc_check+0x24  -> array_map_alloc_check+0x94      (arraymap.c:64)
  [#12] array_map_alloc_check+0x98  -> dump_bpf_prog+0x11b3c           (arraymap.c:82)

--- fexit trampoline overhead (entries #11-#00) ---

  [#11] dump_bpf_prog+0x11b5c       -> __bpf_prog_enter_recur+0x0      (trampoline.c:1145)
  [#10-#03] __bpf_prog_enter_recur: rcu_read_lock, migrate_disable     (trampoline.c:1146)
  [#02] __bpf_prog_enter_recur+0x114 -> dump_bpf_prog+0x11b60          (trampoline.c:1157)

[#01] dump_bpf_prog+0x11b6c -> dump_bpf_prog+0xd230
[#00] dump_bpf_prog+0xd340 -> arm_brbe_snapshot_branch_stack+0x0 (arm_brbe.c:814)

                   el0t_64_sync+0x168
                   el0t_64_sync_handler+0x98
                   el0_svc+0x28
                   do_el0_svc+0x4c
                   invoke_syscall.constprop.0+0x54
    373us [-EINVAL] __arm64_sys_bpf+0x8
                    __sys_bpf+0x87c
                    map_create+0x120
     95us [-EINVAL] array_map_alloc_check+0x8

The FVP's BRBE buffer has 64 entries (BRBE supports 8, 16, 32, or 64). Of these, entries #63-#17 (47) are consumed by the fentry BPF trampoline that ran before the function, and entries #11-#00 (12) are consumed by the fexit trampoline that runs after. Entry #00 shows the very last branch recorded before BRBE is paused: the call into arm_brbe_snapshot_branch_stack().

The 5 useful entries (#16-#12) show the exact path taken inside array_map_alloc_check(). Record #14 shows a jump from line 56 (bpf_map_attr_numa_node) to line 59 (the if-condition), and #13 shows an immediate jump from line 59 (attr->max_entries == 0) to line 64 (return -EINVAL), skipping lines 60-63. This pinpoints max_entries==0 as the cause -- a diagnosis impossible with stack traces alone.

[1] 856c02dbce4f ("bpf: Introduce helper bpf_get_branch_snapshot")
[2] https://github.com/anakryiko/retsnoop

Puranjay Mohan (4):
perf/core: Fix NULL pmu_ctx passed to PMU sched_task callback
perf: Use a union to clear branch entry bitfields perf/arm64: Add BRBE support for bpf_get_branch_snapshot() selftests/bpf: Adjust wasted entries threshold for ARM64 BRBE

 drivers/perf/arm_brbe.c                       | 107 +++++++++++++++---
 drivers/perf/arm_brbe.h                       |   9 ++
 drivers/perf/arm_pmuv3.c                      |   5 +-
 include/linux/perf_event.h                    |   9 +-
 include/uapi/linux/perf_event.h               |  25 ++--
 kernel/events/core.c                          |   3 +-
 .../bpf/prog_tests/get_branch_snapshot.c      |  13 ++-
 7 files changed, 130 insertions(+), 41 deletions(-)

base-commit: 480a9e57cceaf42db6ff874dbfe91de201935035

Signature · 1 line
2.52.0
#1 lore raw

PATCH v3 1/4 perf/core: Fix NULL pmu_ctx passed to PMU sched_task callback

__perf_pmu_sched_task() passes cpc->task_epc to pmu->sched_task(), which is NULL when no per-task events exist for this PMU. With CPU-wide branch-stack events, PMU callbacks that dereference pmu_ctx crash.

On ARM64 this is easily triggered with:

perf record -b -e cycles -a -- ls

which crashes on the first context switch:

  Unable to handle kernel NULL pointer dereference at virtual address 00[.]
  PC is at armv8pmu_sched_task+0x14/0x50
  Call trace:
    armv8pmu_sched_task+0x14/0x50 (P)
    perf_pmu_sched_task+0xac/0x108
    __perf_event_task_sched_out+0x6c/0xe0

Fall back to &cpc->epc when cpc->task_epc is NULL so the callback always receives a valid pmu_ctx.

Fixes bd2756811766 ("perf: Rewrite core context handling")
---
 kernel/events/core.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)
kernel/events/core.c +2 -1
index 1f5699b339ec..2a8fb78e1347 100644
@@ -3906,7 +3906,8 @@ static void __perf_pmu_sched_task(struct perf_cpu_pmu_context *cpc,
 	perf_ctx_lock(cpuctx, cpuctx->task_ctx);
 	perf_pmu_disable(pmu);
 
-	pmu->sched_task(cpc->task_epc, task, sched_in);
+	pmu->sched_task(cpc->task_epc ? cpc->task_epc : &cpc->epc,
+			task, sched_in);
 
 	perf_pmu_enable(pmu);
 	perf_ctx_unlock(cpuctx, cpuctx->task_ctx);
Signature · 1 line
2.52.0
#2 lore raw

Re: [PATCH v3 1/4] perf/core: Fix NULL pmu_ctx passed to PMU sched_task callback

Sashiko AI review found 1 potential issue(s): - [High] Incomplete Fix / Architectural Regression Masking in __perf_pmu_sched_task() --

Sashiko AI review found 1 potential issue(s):
- [High] Incomplete Fix / Architectural Regression Masking in __perf_pmu_sched_task() --

commit f71d68607ec5b88fb13bb33d01fafd22533f428b
Author: Puranjay Mohan <[email protected]>

perf/core: Fix NULL pmu_ctx passed to PMU sched_task callback

This commit modifies __perf_pmu_sched_task() to avoid a NULL pointer dereference when a task has no perf events for a specific PMU. It falls back to using the CPU context when the task context is NULL, which prevents crashes when using CPU-wide branch-stack events.

kernel/events/core.c static void __perf_pmu_sched_task(struct perf_cpu_pmu_context *cpc, · line 3910

Quoted 11 lines
kernel/events/core.c +2 -1
index 1f5699b339ec8..2a8fb78e13471 100644
@@ -3906,7 +3906,8 @@ static void __perf_pmu_sched_task(struct perf_cpu_pmu_context *cpc,
 	perf_ctx_lock(cpuctx, cpuctx->task_ctx);
 	perf_pmu_disable(pmu);
 
-	pmu->sched_task(cpc->task_epc, task, sched_in);
+	pmu->sched_task(cpc->task_epc ? cpc->task_epc : &cpc->epc,
+			task, sched_in);

While this prevents the NULL pointer dereference when __perf_pmu_sched_task() is called, does this fully resolve the issue if the task has an unrelated perf event?

Looking at the caller perf_pmu_sched_task():

static void perf_pmu_sched_task(struct task_struct *prev,
struct task_struct *next, bool sched_in)

{
	...
	if (prev == next || cpuctx->task_ctx)
		return;
	...
}

If the task has an unrelated event, like a software event, cpuctx->task_ctx is not NULL, and this returns early.

The fallback path perf_event_context_sched_in/out() calls perf_ctx_sched_task_cb(), which iterates over ctx->pmu_ctx_list.

Since a PMU with only CPU-wide events is not in ctx->pmu_ctx_list, will this PMU be silently bypassed?

Could this regression cause branch records to leak across tasks if the scheduled task has an unrelated perf event?

Quoted 3 lines
kernel/events/core.c +0 -0
 	perf_pmu_enable(pmu);
 	perf_ctx_unlock(cpuctx, cpuctx->task_ctx);
Signature · 1 line
Sashiko AI review · https://sashiko.dev/#/patchset/[email protected]?part=1
#3 lore raw

PATCH v3 2/4 perf: Use a union to clear branch entry bitfields

In reply to Puranjay Mohan

perf_clear_branch_entry_bitfields() zeroes individual bitfields of struct perf_branch_entry but has repeatedly fallen out of sync when new fields were added (new_type and priv were missed).

Wrap the bitfields in an anonymous struct inside a union with a u64 bitfields member, and clear them all with a single assignment. This avoids having to update the clearing function every time a new bitfield is added.

Fixes bfe4daf850f4 ("perf/core: Add perf_clear_branch_entry_bitfields() helper")
---
 include/linux/perf_event.h      |  9 +--------
 include/uapi/linux/perf_event.h | 25 +++++++++++++++----------
 2 files changed, 16 insertions(+), 18 deletions(-)
include/linux/perf_event.h +1 -8
index 48d851fbd8ea..f7360c43f902 100644
@@ -1474,14 +1474,7 @@ static inline u32 perf_sample_data_size(struct perf_sample_data *data,
  */
 static inline void perf_clear_branch_entry_bitfields(struct perf_branch_entry *br)
 {
-	br->mispred	= 0;
-	br->predicted	= 0;
-	br->in_tx	= 0;
-	br->abort	= 0;
-	br->cycles	= 0;
-	br->type	= 0;
-	br->spec	= PERF_BR_SPEC_NA;
-	br->reserved	= 0;
+	br->bitfields = 0;
 }
 
 extern void perf_output_sample(struct perf_output_handle *handle,
include/uapi/linux/perf_event.h +15 -10
index fd10aa8d697f..c2e7b1b1c4fa 100644
@@ -1491,16 +1491,21 @@ union perf_mem_data_src {
 struct perf_branch_entry {
 	__u64	from;
 	__u64	to;
-	__u64	mispred   :  1, /* target mispredicted */
-		predicted :  1, /* target predicted */
-		in_tx     :  1, /* in transaction */
-		abort     :  1, /* transaction abort */
-		cycles    : 16, /* cycle count to last branch */
-		type      :  4, /* branch type */
-		spec      :  2, /* branch speculation info */
-		new_type  :  4, /* additional branch type */
-		priv      :  3, /* privilege level */
-		reserved  : 31;
+	union {
+		struct {
+			__u64	mispred   :  1, /* target mispredicted */
+				predicted :  1, /* target predicted */
+				in_tx     :  1, /* in transaction */
+				abort     :  1, /* transaction abort */
+				cycles    : 16, /* cycle count to last branch */
+				type      :  4, /* branch type */
+				spec      :  2, /* branch speculation info */
+				new_type  :  4, /* additional branch type */
+				priv      :  3, /* privilege level */
+				reserved  : 31;
+		};
+		__u64	bitfields;
+	};
 };
 
 /* Size of used info bits in struct perf_branch_entry */
Signature · 1 line
2.52.0
#4 lore raw

Re: [PATCH v3 2/4] perf: Use a union to clear branch entry bitfields

Sashiko AI review found 1 potential issue(s): - [Low] Missing tools/ UAPI header synchronization causing build warnings. --

Sashiko AI review found 1 potential issue(s):
- [Low] Missing tools/ UAPI header synchronization causing build warnings. --

Note: The format of this review is altered and does not contain inline patch quotes due to automated recitation restrictions.

commit 0f3b756dec935106f8ca717cac2777f750f3b8da
Author: Puranjay Mohan <[email protected]>
perf: Use a union to clear branch entry bitfields

This commit wraps the bitfields of struct perf_branch_entry in an anonymous struct inside a union, allowing them to be cleared via a single assignment.

The patch updates include/uapi/linux/perf_event.h to introduce the new union and struct layout for perf_branch_entry, but it does not appear to apply the corresponding change to tools/include/uapi/linux/perf_event.h.

Will this discrepancy trigger a build warning in the perf tools? The kernel's tools/perf/check-headers.sh script explicitly tracks this UAPI header. When these files drift, it usually results in a warning during the tools build stating that the Kernel ABI header differs from the latest version.

Should the tools/include/uapi/linux/perf_event.h header be synchronized in this patch to avoid breaking the header checks?

Signature · 1 line
Sashiko AI review · https://sashiko.dev/#/patchset/[email protected]?part=2
#5 lore raw

PATCH v3 3/4 perf/arm64: Add BRBE support for bpf_get_branch_snapshot()

In reply to Puranjay Mohan

Enable bpf_get_branch_snapshot() on ARM64 by implementing the perf_snapshot_branch_stack static call for BRBE.

BRBE is paused before masking exceptions to avoid branch buffer pollution from trace_hardirqs_off(). Exceptions are then masked with local_daif_save() to prevent PMU overflow pseudo-NMIs from interfering. If an overflow between pause and DAIF save re-enables BRBE, the snapshot detects this via BRBFCR_EL1.PAUSED and bails out.

Branch records are read using perf_entry_from_brbe_regset() with a NULL event pointer to bypass event-specific filtering. The buffer is invalidated after reading.

Introduce a for_each_brbe_entry() iterator to deduplicate bank iteration between brbe_read_filtered_entries() and the snapshot.

---
 drivers/perf/arm_brbe.c  | 107 ++++++++++++++++++++++++++++++++-------
 drivers/perf/arm_brbe.h  |   9 ++++
 drivers/perf/arm_pmuv3.c |   5 +-
 3 files changed, 103 insertions(+), 18 deletions(-)
drivers/perf/arm_brbe.c +90 -17
index ba554e0c846c..fd62019ddc83 100644
@@ -9,6 +9,7 @@
 #include <linux/types.h>
 #include <linux/bitmap.h>
 #include <linux/perf/arm_pmu.h>
+#include <asm/daifflags.h>
 #include "arm_brbe.h"
 
 #define BRBFCR_EL1_BRANCH_FILTERS (BRBFCR_EL1_DIRECT   | \
@@ -271,6 +272,20 @@ static void select_brbe_bank(int bank)
 	isb();
 }
 
+static inline void __brbe_advance(int *bank, int *idx, int nr_hw)
+{
+	if (++(*idx) >= BRBE_BANK_MAX_ENTRIES &&
+	    *bank * BRBE_BANK_MAX_ENTRIES + *idx < nr_hw) {
+		*idx = 0;
+		select_brbe_bank(++(*bank));
+	}
+}
+
+#define for_each_brbe_entry(idx, nr_hw)					\
+	for (int __bank = (select_brbe_bank(0), 0), idx = 0;		\
+	     __bank * BRBE_BANK_MAX_ENTRIES + idx < (nr_hw);		\
+	     __brbe_advance(&__bank, &idx, (nr_hw)))
+
 static bool __read_brbe_regset(struct brbe_regset *entry, int idx)
 {
 	entry->brbinf = get_brbinf_reg(idx);
@@ -618,10 +633,10 @@ static bool perf_entry_from_brbe_regset(int index, struct perf_branch_entry *ent
 
 	brbe_set_perf_entry_type(entry, brbinf);
 
-	if (!branch_sample_no_cycles(event))
+	if (!event || !branch_sample_no_cycles(event))
 		entry->cycles = brbinf_get_cycles(brbinf);
 
-	if (!branch_sample_no_flags(event)) {
+	if (!event || !branch_sample_no_flags(event)) {
 		/* Mispredict info is available for source only and complete branch records. */
 		if (!brbe_record_is_target_only(brbinf)) {
 			entry->mispred = brbinf_get_mispredict(brbinf);
@@ -774,32 +789,90 @@ void brbe_read_filtered_entries(struct perf_branch_stack *branch_stack,
 {
 	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
 	int nr_hw = brbe_num_branch_records(cpu_pmu);
-	int nr_banks = DIV_ROUND_UP(nr_hw, BRBE_BANK_MAX_ENTRIES);
 	int nr_filtered = 0;
 	u64 branch_sample_type = event->attr.branch_sample_type;
 	DECLARE_BITMAP(event_type_mask, PERF_BR_ARM64_MAX);
 
 	prepare_event_branch_type_mask(branch_sample_type, event_type_mask);
 
-	for (int bank = 0; bank < nr_banks; bank++) {
-		int nr_remaining = nr_hw - (bank * BRBE_BANK_MAX_ENTRIES);
-		int nr_this_bank = min(nr_remaining, BRBE_BANK_MAX_ENTRIES);
+	for_each_brbe_entry(i, nr_hw) {
+		struct perf_branch_entry *pbe = &branch_stack->entries[nr_filtered];
 
-		select_brbe_bank(bank);
+		if (!perf_entry_from_brbe_regset(i, pbe, event))
+			break;
 
-		for (int i = 0; i < nr_this_bank; i++) {
-			struct perf_branch_entry *pbe = &branch_stack->entries[nr_filtered];
+		if (!filter_branch_record(pbe, branch_sample_type, event_type_mask))
+			continue;
 
-			if (!perf_entry_from_brbe_regset(i, pbe, event))
-				goto done;
+		nr_filtered++;
+	}
 
-			if (!filter_branch_record(pbe, branch_sample_type, event_type_mask))
-				continue;
+	branch_stack->nr = nr_filtered;
+}
 
-			nr_filtered++;
-		}
+/*
+ * Best-effort BRBE snapshot for BPF tracing. Pause BRBE to avoid
+ * self-recording and return 0 if the snapshot state appears disturbed.
+ */
+int arm_brbe_snapshot_branch_stack(struct perf_branch_entry *entries, unsigned int cnt)
+{
+	unsigned long flags;
+	int nr_hw, nr_copied = 0;
+	u64 brbfcr, brbcr;
+
+	if (!cnt)
+		return 0;
+
+	/*
+	 * Pause BRBE first to avoid recording our own branches. The
+	 * sysreg read/write and ISB are branchless, so pausing before
+	 * checking BRBCR avoids polluting the buffer with our own
+	 * conditional branches.
+	 */
+	brbfcr = read_sysreg_s(SYS_BRBFCR_EL1);
+	brbcr = read_sysreg_s(SYS_BRBCR_EL1);
+	write_sysreg_s(brbfcr | BRBFCR_EL1_PAUSED, SYS_BRBFCR_EL1);
+	isb();
+
+	/* Bail out if BRBE is not enabled (BRBCR_EL1 == 0). */
+	if (!brbcr) {
+		write_sysreg_s(brbfcr, SYS_BRBFCR_EL1);
+		return 0;
 	}
 
-done:
-	branch_stack->nr = nr_filtered;
+	/* Block local exception delivery while reading the buffer. */
+	flags = local_daif_save();
+
+	/*
+	 * A PMU overflow before local_daif_save() could have re-enabled
+	 * BRBE, clearing the PAUSED bit. The overflow handler already
+	 * restored BRBE to its correct state, so just bail out.
+	 */
+	if (!(read_sysreg_s(SYS_BRBFCR_EL1) & BRBFCR_EL1_PAUSED)) {
+		local_daif_restore(flags);
+		return 0;
+	}
+
+	nr_hw = FIELD_GET(BRBIDR0_EL1_NUMREC_MASK,
+			  read_sysreg_s(SYS_BRBIDR0_EL1));
+
+	for_each_brbe_entry(i, nr_hw) {
+		if (nr_copied >= cnt)
+			break;
+
+		if (!perf_entry_from_brbe_regset(i, &entries[nr_copied], NULL))
+			break;
+
+		nr_copied++;
+	}
+
+	brbe_invalidate();
+
+	/* Restore BRBCR before unpausing via BRBFCR, matching brbe_enable(). */
+	write_sysreg_s(brbcr, SYS_BRBCR_EL1);
+	isb();
+	write_sysreg_s(brbfcr, SYS_BRBFCR_EL1);
+	local_daif_restore(flags);
+
+	return nr_copied;
 }
drivers/perf/arm_brbe.h +9 -0
index b7c7d8796c86..c2a1824437fb 100644
@@ -10,6 +10,7 @@
 struct arm_pmu;
 struct perf_branch_stack;
 struct perf_event;
+struct perf_branch_entry;
 
 #ifdef CONFIG_ARM64_BRBE
 void brbe_probe(struct arm_pmu *arm_pmu);
@@ -22,6 +23,8 @@ void brbe_disable(void);
 bool brbe_branch_attr_valid(struct perf_event *event);
 void brbe_read_filtered_entries(struct perf_branch_stack *branch_stack,
 				const struct perf_event *event);
+int arm_brbe_snapshot_branch_stack(struct perf_branch_entry *entries,
+				   unsigned int cnt);
 #else
 static inline void brbe_probe(struct arm_pmu *arm_pmu) { }
 static inline unsigned int brbe_num_branch_records(const struct arm_pmu *armpmu)
@@ -44,4 +47,10 @@ static void brbe_read_filtered_entries(struct perf_branch_stack *branch_stack,
 				       const struct perf_event *event)
 {
 }
+
+static inline int arm_brbe_snapshot_branch_stack(struct perf_branch_entry *entries,
+						 unsigned int cnt)
+{
+	return 0;
+}
 #endif
drivers/perf/arm_pmuv3.c +4 -1
index 8014ff766cff..1a9f129a0f94 100644
@@ -1449,8 +1449,11 @@ static int armv8_pmu_init(struct arm_pmu *cpu_pmu, char *name,
 	cpu_pmu->set_event_filter	= armv8pmu_set_event_filter;
 
 	cpu_pmu->pmu.event_idx		= armv8pmu_user_event_idx;
-	if (brbe_num_branch_records(cpu_pmu))
+	if (brbe_num_branch_records(cpu_pmu)) {
 		cpu_pmu->pmu.sched_task		= armv8pmu_sched_task;
+		static_call_update(perf_snapshot_branch_stack,
+				   arm_brbe_snapshot_branch_stack);
+	}
 
 	cpu_pmu->name			= name;
 	cpu_pmu->map_event		= map_event;
Signature · 1 line
2.52.0
#6 lore raw

Re: [PATCH v3 3/4] perf/arm64: Add BRBE support for bpf_get_branch_snapshot()

Sashiko AI review found 4 potential issue(s): - [High] arm_brbe_snapshot_branch_stack executes BRBE system register reads without validating CPU support, leading to an Undefined Instruction kernel…

Sashiko AI review found 4 potential issue(s):
- [High] arm_brbe_snapshot_branch_stack executes BRBE system register reads without validating CPU support, leading to an Undefined Instruction kernel panic on asymmetric systems.
- [High] arm_brbe_snapshot_branch_stack destructively clears the hardware branch buffer, corrupting data for concurrent perf sessions.
- [High] A TOCTOU race can unintentionally re-enable BRBE after it was explicitly disabled by a PMU interrupt, corrupting hardware state.
- [Medium] Missing isb() context synchronization after unpausing BRBE causes missed branch records.
--

commit ce06705327b522bc73c923ff4219c198fe71f3b4
Author: Puranjay Mohan <[email protected]>
Subject: perf/arm64: Add BRBE support for bpf_get_branch_snapshot()

This commit enables bpf_get_branch_snapshot() on ARM64 by implementing the perf_snapshot_branch_stack static call for BRBE. It pauses BRBE, masks exceptions, reads branch records, and then invalidates the buffer.

Quoted 4 lines
drivers/perf/arm_brbe.c +0 -0
index ba554e0c846c4..fd62019ddc839 100644

[ ... ]

Quoted 10 lines
drivers/perf/arm_brbe.c +10 -0
+/*
+ * Best-effort BRBE snapshot for BPF tracing. Pause BRBE to avoid
+ * self-recording and return 0 if the snapshot state appears disturbed.
+ */
+int arm_brbe_snapshot_branch_stack(struct perf_branch_entry *entries, unsigned int cnt)
+{
+	unsigned long flags;
+	int nr_hw, nr_copied = 0;
+	u64 brbfcr, brbcr;
+

drivers/perf/arm_brbe.c void brbe_read_filtered_entries(struct perf_branch_stack *branch_stack, · line 832

Quoted 10 lines
drivers/perf/arm_brbe.c +10 -0
+	if (!cnt)
+		return 0;
+
+	/*
+	 * Pause BRBE first to avoid recording our own branches. The
+	 * sysreg read/write and ISB are branchless, so pausing before
+	 * checking BRBCR avoids polluting the buffer with our own
+	 * conditional branches.
+	 */
+	brbfcr = read_sysreg_s(SYS_BRBFCR_EL1);

On asymmetric systems (like big.LITTLE) where only a subset of CPU cores implement BRBE, the perf_snapshot_branch_stack static call is enabled globally. If a BPF program invokes this snapshot on a CPU lacking BRBE, will this unconditionally execute read_sysreg_s(SYS_BRBFCR_EL1) and trigger an Undefined Instruction exception kernel panic?

Does this need a local CPU feature check before accessing these registers?

Quoted 9 lines
drivers/perf/arm_brbe.c +9 -0
+	brbcr = read_sysreg_s(SYS_BRBCR_EL1);
+	write_sysreg_s(brbfcr | BRBFCR_EL1_PAUSED, SYS_BRBFCR_EL1);
+	isb();
+
+	/* Bail out if BRBE is not enabled (BRBCR_EL1 == 0). */
+	if (!brbcr) {
+		write_sysreg_s(brbfcr, SYS_BRBFCR_EL1);
+		return 0;
+	}

drivers/perf/arm_brbe.c void brbe_read_filtered_entries(struct perf_branch_stack *branch_stack,

Quoted 10 lines
drivers/perf/arm_brbe.c +10 -0
+
+	/* Block local exception delivery while reading the buffer. */
+	flags = local_daif_save();
+
+	/*
+	 * A PMU overflow before local_daif_save() could have re-enabled
+	 * BRBE, clearing the PAUSED bit. The overflow handler already
+	 * restored BRBE to its correct state, so just bail out.
+	 */
+	if (!(read_sysreg_s(SYS_BRBFCR_EL1) & BRBFCR_EL1_PAUSED)) {

Can a TOCTOU race unintentionally re-enable BRBE if a PMU interrupt fires before exceptions are masked?

If the PMU overflow interrupt decides to stop the event, it calls brbe_disable(), which sets SYS_BRBCR_EL1 to 0 and sets the PAUSED bit in SYS_BRBFCR_EL1.

Upon returning from the interrupt, the PAUSED bit would still be set, so this check evaluates to false and proceeds. At the end of the function, the cached brbcr (which was > 0) and brbfcr are written back, which would unintentionally re-enable BRBE in hardware without an active perf event.

Quoted 8 lines
drivers/perf/arm_brbe.c +8 -0
+		local_daif_restore(flags);
+		return 0;
+	}
+
+	nr_hw = FIELD_GET(BRBIDR0_EL1_NUMREC_MASK,
+			  read_sysreg_s(SYS_BRBIDR0_EL1));
+
+	for_each_brbe_entry(i, nr_hw) {

drivers/perf/arm_brbe.c void brbe_read_filtered_entries(struct perf_branch_stack *branch_stack, · line 869

Quoted 10 lines
drivers/perf/arm_brbe.c +10 -0
+		if (nr_copied >= cnt)
+			break;
+
+		if (!perf_entry_from_brbe_regset(i, &entries[nr_copied], NULL))
+			break;
+
+		nr_copied++;
+	}
+
+	brbe_invalidate();

Does calling brbe_invalidate() here destructively clear the hardware branch buffer?

Since BPF branch snapshots are intended to be non-destructive observations, wiping out the hardware branch buffer could permanently destroy the branch history for a concurrently active perf session.

drivers/perf/arm_brbe.c void brbe_read_filtered_entries(struct perf_branch_stack *branch_stack, · line 874

Quoted 5 lines
drivers/perf/arm_brbe.c +5 -0
+
+	/* Restore BRBCR before unpausing via BRBFCR, matching brbe_enable(). */
+	write_sysreg_s(brbcr, SYS_BRBCR_EL1);
+	isb();
+	write_sysreg_s(brbfcr, SYS_BRBFCR_EL1);

Is an explicit isb() missing after writing to SYS_BRBFCR_EL1?

Since MSR instructions to system registers are not context synchronizing, the processor may delay unpausing BRBE. Could this result in missed branch records until the next context synchronization event naturally occurs?

Quoted 4 lines
drivers/perf/arm_brbe.c +4 -0
+	local_daif_restore(flags);
+
+	return nr_copied;
+}
Signature · 1 line
Sashiko AI review · https://sashiko.dev/#/patchset/[email protected]?part=3
#7 lore raw

Re: [PATCH v3 3/4] perf/arm64: Add BRBE support for bpf_get_branch_snapshot()

Quoted 50 lines · On Mon, Apr 13, 2026 at 9:31 PM <[email protected]> wrote:

Sashiko AI review found 4 potential issue(s):
- [High] arm_brbe_snapshot_branch_stack executes BRBE system register reads without validating CPU support, leading to an Undefined Instruction kernel panic on asymmetric systems.
- [High] arm_brbe_snapshot_branch_stack destructively clears the hardware branch buffer, corrupting data for concurrent perf sessions.
- [High] A TOCTOU race can unintentionally re-enable BRBE after it was explicitly disabled by a PMU interrupt, corrupting hardware state.
- [Medium] Missing isb() context synchronization after unpausing BRBE causes missed branch records.
--

commit ce06705327b522bc73c923ff4219c198fe71f3b4
Author: Puranjay Mohan <[email protected]>
Subject: perf/arm64: Add BRBE support for bpf_get_branch_snapshot()

This commit enables bpf_get_branch_snapshot() on ARM64 by implementing the perf_snapshot_branch_stack static call for BRBE. It pauses BRBE, masks exceptions, reads branch records, and then invalidates the buffer.

Quoted 4 lines
drivers/perf/arm_brbe.c +0 -0
index ba554e0c846c4..fd62019ddc839 100644

[ ... ]

Quoted 10 lines
drivers/perf/arm_brbe.c +10 -0
+/*
+ * Best-effort BRBE snapshot for BPF tracing. Pause BRBE to avoid
+ * self-recording and return 0 if the snapshot state appears disturbed.
+ */
+int arm_brbe_snapshot_branch_stack(struct perf_branch_entry *entries, unsigned int cnt)
+{
+     unsigned long flags;
+     int nr_hw, nr_copied = 0;
+     u64 brbfcr, brbcr;
+

drivers/perf/arm_brbe.c void brbe_read_filtered_entries(struct perf_branch_stack *branch_stack, · line 832

Quoted 10 lines
drivers/perf/arm_brbe.c +10 -0
+     if (!cnt)
+             return 0;
+
+     /*
+      * Pause BRBE first to avoid recording our own branches. The
+      * sysreg read/write and ISB are branchless, so pausing before
+      * checking BRBCR avoids polluting the buffer with our own
+      * conditional branches.
+      */
+     brbfcr = read_sysreg_s(SYS_BRBFCR_EL1);

On asymmetric systems (like big.LITTLE) where only a subset of CPU cores implement BRBE, the perf_snapshot_branch_stack static call is enabled globally. If a BPF program invokes this snapshot on a CPU lacking BRBE, will this unconditionally execute read_sysreg_s(SYS_BRBFCR_EL1) and trigger an Undefined Instruction exception kernel panic?

Quoted 1 line

Does this need a local CPU feature check before accessing these registers?

I had this in the previous version, but Rob explained that this doesn't happen in practice so I removed it.

Quoted 78 lines
Quoted 10 lines
drivers/perf/arm_brbe.c +9 -0
+     brbcr = read_sysreg_s(SYS_BRBCR_EL1);
+     write_sysreg_s(brbfcr | BRBFCR_EL1_PAUSED, SYS_BRBFCR_EL1);
+     isb();
+
+     /* Bail out if BRBE is not enabled (BRBCR_EL1 == 0). */
+     if (!brbcr) {
+             write_sysreg_s(brbfcr, SYS_BRBFCR_EL1);
+             return 0;
+     }

drivers/perf/arm_brbe.c void brbe_read_filtered_entries(struct perf_branch_stack *branch_stack,

Quoted 10 lines
drivers/perf/arm_brbe.c +10 -0
+
+     /* Block local exception delivery while reading the buffer. */
+     flags = local_daif_save();
+
+     /*
+      * A PMU overflow before local_daif_save() could have re-enabled
+      * BRBE, clearing the PAUSED bit. The overflow handler already
+      * restored BRBE to its correct state, so just bail out.
+      */
+     if (!(read_sysreg_s(SYS_BRBFCR_EL1) & BRBFCR_EL1_PAUSED)) {

Can a TOCTOU race unintentionally re-enable BRBE if a PMU interrupt fires before exceptions are masked?

If the PMU overflow interrupt decides to stop the event, it calls brbe_disable(), which sets SYS_BRBCR_EL1 to 0 and sets the PAUSED bit in SYS_BRBFCR_EL1.

Upon returning from the interrupt, the PAUSED bit would still be set, so this check evaluates to false and proceeds. At the end of the function, the cached brbcr (which was > 0) and brbfcr are written back, which would unintentionally re-enable BRBE in hardware without an active perf event.

Quoted 8 lines
drivers/perf/arm_brbe.c +8 -0
+             local_daif_restore(flags);
+             return 0;
+     }
+
+     nr_hw = FIELD_GET(BRBIDR0_EL1_NUMREC_MASK,
+                       read_sysreg_s(SYS_BRBIDR0_EL1));
+
+     for_each_brbe_entry(i, nr_hw) {

drivers/perf/arm_brbe.c void brbe_read_filtered_entries(struct perf_branch_stack *branch_stack, · line 869

Quoted 10 lines
drivers/perf/arm_brbe.c +10 -0
+             if (nr_copied >= cnt)
+                     break;
+
+             if (!perf_entry_from_brbe_regset(i, &entries[nr_copied], NULL))
+                     break;
+
+             nr_copied++;
+     }
+
+     brbe_invalidate();

Does calling brbe_invalidate() here destructively clear the hardware branch buffer?

Since BPF branch snapshots are intended to be non-destructive observations, wiping out the hardware branch buffer could permanently destroy the branch history for a concurrently active perf session.

drivers/perf/arm_brbe.c void brbe_read_filtered_entries(struct perf_branch_stack *branch_stack, · line 874

Quoted 5 lines
drivers/perf/arm_brbe.c +5 -0
+
+     /* Restore BRBCR before unpausing via BRBFCR, matching brbe_enable(). */
+     write_sysreg_s(brbcr, SYS_BRBCR_EL1);
+     isb();
+     write_sysreg_s(brbfcr, SYS_BRBFCR_EL1);

Is an explicit isb() missing after writing to SYS_BRBFCR_EL1?

Since MSR instructions to system registers are not context synchronizing, the processor may delay unpausing BRBE. Could this result in missed branch records until the next context synchronization event naturally occurs?

drivers/perf/arm_brbe.c void brbe_read_filtered_entries(struct perf_branch_stack *branch_stack,

Quoted 4 lines
drivers/perf/arm_brbe.c +4 -0
+     local_daif_restore(flags);
+
+     return nr_copied;
+}

--
Sashiko AI review · https://sashiko.dev/#/patchset/[email protected]?part=3

#8 lore raw

PATCH v3 4/4 selftests/bpf: Adjust wasted entries threshold for ARM64 BRBE

In reply to Puranjay Mohan

The get_branch_snapshot test checks that bpf_get_branch_snapshot() doesn't waste too many branch entries on infrastructure overhead. The threshold of < 10 was calibrated for x86 where about 7 entries are wasted.

On ARM64, the BPF trampoline generates more branches than x86, resulting in about 13 wasted entries. The overhead comes from the BPF trampoline calling __bpf_prog_enter_recur which on ARM64 makes out-of-line calls to __rcu_read_lock and generates more conditional branches than x86:

 [#12] bpf_testmod_loop_test+0x40    -> bpf_trampoline_...+0x48
 [#11] bpf_trampoline_...+0x68       -> __bpf_prog_enter_recur+0x0
 [#10] __bpf_prog_enter_recur+0x20   -> __bpf_prog_enter_recur+0x118
 [#09] __bpf_prog_enter_recur+0x154  -> __bpf_prog_enter_recur+0x160
 [#08] __bpf_prog_enter_recur+0x164  -> __bpf_prog_enter_recur+0x2c
 [#07] __bpf_prog_enter_recur+0x2c   -> __rcu_read_lock+0x0
 [#06] __rcu_read_lock+0x18          -> __bpf_prog_enter_recur+0x30
 [#05] __bpf_prog_enter_recur+0x9c   -> __bpf_prog_enter_recur+0xf0
 [#04] __bpf_prog_enter_recur+0xf4   -> __bpf_prog_enter_recur+0xa8
 [#03] __bpf_prog_enter_recur+0xb8   -> __bpf_prog_enter_recur+0x100
 [#02] __bpf_prog_enter_recur+0x114  -> bpf_trampoline_...+0x6c
 [#01] bpf_trampoline_...+0x78       -> bpf_prog_...test1+0x0
 [#00] bpf_prog_...test1+0x58        -> arm_brbe_snapshot_branch_stack+0x0

Use an architecture-specific threshold of < 14 for ARM64 to accommodate this overhead while still detecting regressions.

---
 .../selftests/bpf/prog_tests/get_branch_snapshot.c  | 13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)
tools/testing/selftests/bpf/prog_tests/get_branch_snapshot.c +9 -4
index 0394a1156d99..8d1a3480767f 100644
@@ -116,13 +116,18 @@ void serial_test_get_branch_snapshot(void)
 
 	ASSERT_GT(skel->bss->test1_hits, 6, "find_looptest_in_lbr");
 
-	/* Given we stop LBR in software, we will waste a few entries.
+	/* Given we stop LBR/BRBE in software, we will waste a few entries.
 	 * But we should try to waste as few as possible entries. We are at
-	 * about 7 on x86_64 systems.
-	 * Add a check for < 10 so that we get heads-up when something
-	 * changes and wastes too many entries.
+	 * about 7 on x86_64 and about 13 on arm64 systems (the arm64 BPF
+	 * trampoline generates more branches than x86_64).
+	 * Add a check so that we get heads-up when something changes and
+	 * wastes too many entries.
 	 */
+#if defined(__aarch64__)
+	ASSERT_LT(skel->bss->wasted_entries, 14, "check_wasted_entries");
+#else
 	ASSERT_LT(skel->bss->wasted_entries, 10, "check_wasted_entries");
+#endif
 
 cleanup:
 	get_branch_snapshot__destroy(skel);
Signature · 1 line
2.52.0