Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   Anshuman Khandual <anshuman.khandual@arm.com>
To:     linux-arm-kernel@lists.infradead.org, linux-kernel@vger.kernel.org,
        will@kernel.org, catalin.marinas@arm.com, mark.rutland@arm.com
Cc:     Anshuman Khandual <anshuman.khandual@arm.com>,
        Mark Brown <broonie@kernel.org>,
        James Clark <james.clark@arm.com>,
        Rob Herring <robh@kernel.org>, Marc Zyngier <maz@kernel.org>,
        Suzuki Poulose <suzuki.poulose@arm.com>,
        Peter Zijlstra <peterz@infradead.org>,
        Ingo Molnar <mingo@redhat.com>,
        Arnaldo Carvalho de Melo <acme@kernel.org>,
        linux-perf-users@vger.kernel.org
Subject: [PATCH V13 - RESEND 09/10] arm64/perf: Implement branch records save on task sched out
Date:   Tue, 11 Jul 2023 13:54:54 +0530
Message-Id: <20230711082455.215983-10-anshuman.khandual@arm.com>
In-Reply-To: <20230711082455.215983-1-anshuman.khandual@arm.com>
References: <20230711082455.215983-1-anshuman.khandual@arm.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

This modifies current armv8pmu_sched_task(), to implement a branch records
save mechanism via armv8pmu_branch_save() when a task scheds out of a cpu.
BRBE is paused and disabled for all exception levels before branch records
get captured, which then get concatenated with all existing stored records
present in the task context maintaining the contiguity. Although the final
length of the concatenated buffer does not exceed implemented BRBE length.

Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
Tested-by: James Clark <james.clark@arm.com>
Acked-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Anshuman Khandual <anshuman.khandual@arm.com>
---
 arch/arm/include/asm/arm_pmuv3.h    |  1 +
 arch/arm64/include/asm/perf_event.h |  2 ++
 drivers/perf/arm_brbe.c             | 30 +++++++++++++++++++++++++++++
 drivers/perf/arm_pmuv3.c            | 14 ++++++++++++--
 4 files changed, 45 insertions(+), 2 deletions(-)

diff --git a/arch/arm/include/asm/arm_pmuv3.h b/arch/arm/include/asm/arm_pmuv3.h
index 3d8faf4200dc..3d047d2c9430 100644
--- a/arch/arm/include/asm/arm_pmuv3.h
+++ b/arch/arm/include/asm/arm_pmuv3.h
@@ -259,5 +259,6 @@ static inline void armv8pmu_branch_probe(struct arm_pmu *arm_pmu) { }
 static inline void armv8pmu_branch_reset(void) { }
 static inline int armv8pmu_task_ctx_cache_alloc(struct arm_pmu *arm_pmu) { return 0; }
 static inline void armv8pmu_task_ctx_cache_free(struct arm_pmu *arm_pmu) { }
+static inline void armv8pmu_branch_save(struct arm_pmu *arm_pmu, void *ctx) { }
 #endif
 #endif
diff --git a/arch/arm64/include/asm/perf_event.h b/arch/arm64/include/asm/perf_event.h
index b0c12a5882df..36e7dfb466a6 100644
--- a/arch/arm64/include/asm/perf_event.h
+++ b/arch/arm64/include/asm/perf_event.h
@@ -40,6 +40,7 @@ void armv8pmu_branch_probe(struct arm_pmu *arm_pmu);
 void armv8pmu_branch_reset(void);
 int armv8pmu_task_ctx_cache_alloc(struct arm_pmu *arm_pmu);
 void armv8pmu_task_ctx_cache_free(struct arm_pmu *arm_pmu);
+void armv8pmu_branch_save(struct arm_pmu *arm_pmu, void *ctx);
 #else
 static inline void armv8pmu_branch_read(struct pmu_hw_events *cpuc, struct perf_event *event)
 {
@@ -66,6 +67,7 @@ static inline void armv8pmu_branch_probe(struct arm_pmu *arm_pmu) { }
 static inline void armv8pmu_branch_reset(void) { }
 static inline int armv8pmu_task_ctx_cache_alloc(struct arm_pmu *arm_pmu) { return 0; }
 static inline void armv8pmu_task_ctx_cache_free(struct arm_pmu *arm_pmu) { }
+static inline void armv8pmu_branch_save(struct arm_pmu *arm_pmu, void *ctx) { }
 #endif
 #endif
 #endif
diff --git a/drivers/perf/arm_brbe.c b/drivers/perf/arm_brbe.c
index 203cd4f350d5..2177632befa6 100644
--- a/drivers/perf/arm_brbe.c
+++ b/drivers/perf/arm_brbe.c
@@ -165,6 +165,36 @@ static int stitch_stored_live_entries(struct brbe_regset *stored,
 	return min(nr_live + nr_stored, nr_max);
 }
 
+static int brbe_branch_save(struct brbe_regset *live, int nr_hw_entries)
+{
+	u64 brbfcr = read_sysreg_s(SYS_BRBFCR_EL1);
+	int nr_live;
+
+	write_sysreg_s(brbfcr | BRBFCR_EL1_PAUSED, SYS_BRBFCR_EL1);
+	isb();
+
+	nr_live = capture_brbe_regset(live, nr_hw_entries);
+
+	write_sysreg_s(brbfcr & ~BRBFCR_EL1_PAUSED, SYS_BRBFCR_EL1);
+	isb();
+
+	return nr_live;
+}
+
+void armv8pmu_branch_save(struct arm_pmu *arm_pmu, void *ctx)
+{
+	struct arm64_perf_task_context *task_ctx = ctx;
+	struct brbe_regset live[BRBE_MAX_ENTRIES];
+	int nr_live, nr_store, nr_hw_entries;
+
+	nr_hw_entries = brbe_get_numrec(arm_pmu->reg_brbidr);
+	nr_live = brbe_branch_save(live, nr_hw_entries);
+	nr_store = task_ctx->nr_brbe_records;
+	nr_store = stitch_stored_live_entries(task_ctx->store, live, nr_store,
+					      nr_live, nr_hw_entries);
+	task_ctx->nr_brbe_records = nr_store;
+}
+
 /*
  * Generic perf branch filters supported on BRBE
  *
diff --git a/drivers/perf/arm_pmuv3.c b/drivers/perf/arm_pmuv3.c
index 408974d5c57b..aa3c7b3dcdd6 100644
--- a/drivers/perf/arm_pmuv3.c
+++ b/drivers/perf/arm_pmuv3.c
@@ -923,9 +923,19 @@ static int armv8pmu_user_event_idx(struct perf_event *event)
 static void armv8pmu_sched_task(struct perf_event_pmu_context *pmu_ctx, bool sched_in)
 {
 	struct arm_pmu *armpmu = to_arm_pmu(pmu_ctx->pmu);
+	void *task_ctx = pmu_ctx ? pmu_ctx->task_ctx_data : NULL;
 
-	if (sched_in && armpmu->has_branch_stack)
-		armv8pmu_branch_reset();
+	if (armpmu->has_branch_stack) {
+		/* Save branch records in task_ctx on sched out */
+		if (task_ctx && !sched_in) {
+			armv8pmu_branch_save(armpmu, task_ctx);
+			return;
+		}
+
+		/* Reset branch records on sched in */
+		if (sched_in)
+			armv8pmu_branch_reset();
+	}
 }
 
 /*
-- 
2.25.1