[PATCH bpf 2/3] perf/arm64: Add BRBE support for bpf_get_branch_snapshot()

[Puranjay Mohan <puranjay@kernel.org>]

Implement the perf_snapshot_branch_stack static call for ARM's Branch
Record Buffer Extension (BRBE), enabling the bpf_get_branch_snapshot()
BPF helper on ARM64.

This is a best-effort snapshot helper intended for tracing and debugging
use. It favors non-invasive snapshotting over strong serialization, and
returns 0 whenever a clean snapshot cannot be obtained. Nested
invocations are not serialized; callers may observe a 0-length result
when a clean snapshot cannot be preserved.

BRBE is paused before the helper does any other work to avoid recording
its own branches. The sysreg writes used to pause are branchless.
local_daif_save() blocks local exception delivery while reading the
buffer. If a PMU overflow raced before that point and re-enabled BRBE,
the helper detects the cleared PAUSED state and returns 0.

Branch records are read using perf_entry_from_brbe_regset() without
event-specific filtering. The BPF program is responsible for applying
its own filter criteria. The BRBE buffer is invalidated after reading
to maintain contiguity for other consumers.

Signed-off-by: Puranjay Mohan <puranjay@kernel.org>
---
 drivers/perf/arm_brbe.c  | 70 ++++++++++++++++++++++++++++++++++++++--
 drivers/perf/arm_brbe.h  |  9 ++++++
 drivers/perf/arm_pmuv3.c |  5 ++-
 3 files changed, 81 insertions(+), 3 deletions(-)

diff --git a/drivers/perf/arm_brbe.c b/drivers/perf/arm_brbe.c
index ba554e0c846c..db5e000b2575 100644
--- a/drivers/perf/arm_brbe.c
+++ b/drivers/perf/arm_brbe.c
@@ -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   | \
@@ -618,10 +619,10 @@ 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);
@@ -803,3 +804,68 @@ void brbe_read_filtered_entries(struct perf_branch_stack *branch_stack,
 done:
 	branch_stack->nr = 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_banks, nr_copied = 0;
+	u64 brbidr, brbfcr, brbcr;
+
+	if (!cnt)
+		return 0;
+
+	/* Pause BRBE first to avoid recording our own 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();
+
+	/* 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. Bail out.
+	 */
+	if (!(read_sysreg_s(SYS_BRBFCR_EL1) & BRBFCR_EL1_PAUSED))
+		goto out;
+
+	brbidr = read_sysreg_s(SYS_BRBIDR0_EL1);
+	if (!valid_brbidr(brbidr))
+		goto out;
+
+	nr_hw = FIELD_GET(BRBIDR0_EL1_NUMREC_MASK, brbidr);
+	nr_banks = DIV_ROUND_UP(nr_hw, BRBE_BANK_MAX_ENTRIES);
+
+	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);
+
+		select_brbe_bank(bank);
+
+		for (int i = 0; i < nr_this_bank; i++) {
+			if (nr_copied >= cnt)
+				goto done;
+
+			if (!perf_entry_from_brbe_regset(i, &entries[nr_copied], NULL))
+				goto done;
+
+			nr_copied++;
+		}
+	}
+
+done:
+	brbe_invalidate();
+out:
+	/* 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;
+}
diff --git a/drivers/perf/arm_brbe.h b/drivers/perf/arm_brbe.h
index b7c7d8796c86..c2a1824437fb 100644
--- a/drivers/perf/arm_brbe.h
+++ b/drivers/perf/arm_brbe.h
@@ -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
diff --git a/drivers/perf/arm_pmuv3.c b/drivers/perf/arm_pmuv3.c
index 2d097fad9c10..e00c7c47a98d 100644
--- a/drivers/perf/arm_pmuv3.c
+++ b/drivers/perf/arm_pmuv3.c
@@ -1456,8 +1456,11 @@ 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;
-- 
2.52.0