[tip:perf/core] perf/arm: Special-case hetereogeneous CPUs

[tip-bot for Mark Rutland]

Commit-ID:  5101ef20f0ef1de79091a1fdb6b1a7f07565545a
Gitweb:     http://git.kernel.org/tip/5101ef20f0ef1de79091a1fdb6b1a7f07565545a
Author:     Mark Rutland <mark.rutland@xxxxxxx>
AuthorDate: Tue, 26 Apr 2016 11:33:46 +0100
Committer:  Ingo Molnar <mingo@xxxxxxxxxx>
CommitDate: Thu, 5 May 2016 10:13:59 +0200

perf/arm: Special-case hetereogeneous CPUs

Commit:

  26657848502b7847 ("perf/core: Verify we have a single perf_hw_context PMU")

forcefully prevents multiple PMUs from sharing perf_hw_context, as this
generally doesn't make sense. It is a common bug for uncore PMUs to
use perf_hw_context rather than perf_invalid_context, which this detects.

However, systems exist with heterogeneous CPUs (and hence heterogeneous
HW PMUs), for which sharing perf_hw_context is necessary, and possible
in some limited cases.

To make this work we have to perform some gymnastics, as we did in these
commits:

  66eb579e66ecfea5 ("perf: allow for PMU-specific event filtering")
  c904e32a69b7c779 ("arm: perf: filter unschedulable events")

To allow those systems to work, we must allow PMUs for heterogeneous
CPUs to share perf_hw_context, though we must still disallow sharing
otherwise to detect the common misuse of perf_hw_context.

This patch adds a new PERF_PMU_CAP_HETEROGENEOUS_CPUS for this, updates
the core logic to account for this, and makes use of it in the arm_pmu
code that is used for systems with heterogeneous CPUs. Comments are
added to make the rationale clear and hopefully avoid accidental abuse.

Signed-off-by: Mark Rutland <mark.rutland@xxxxxxx>
Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Cc: Alexander Shishkin <alexander.shishkin@xxxxxxxxxxxxxxx>
Cc: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
Cc: Catalin Marinas <catalin.marinas@xxxxxxx>
Cc: Jiri Olsa <jolsa@xxxxxxxxxx>
Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Stephane Eranian <eranian@xxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Vince Weaver <vincent.weaver@xxxxxxxxx>
Cc: Will Deacon <will.deacon@xxxxxxx>
Cc: linux-arm-kernel@xxxxxxxxxxxxxxxxxxx
Link: http://lkml.kernel.org/r/20160426103346.GA20836@leverpostej
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
---
 drivers/perf/arm_pmu.c     | 8 ++++++++
 include/linux/perf_event.h | 1 +
 kernel/events/core.c       | 8 +++++++-
 3 files changed, 16 insertions(+), 1 deletion(-)

diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c
index f700908..f2d01d4 100644
--- a/drivers/perf/arm_pmu.c
+++ b/drivers/perf/arm_pmu.c
@@ -847,6 +847,14 @@ static int cpu_pmu_init(struct arm_pmu *cpu_pmu)
 	if (!platform_get_irq(cpu_pmu->plat_device, 0))
 		cpu_pmu->pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT;
 
+	/*
+	 * This is a CPU PMU potentially in a heterogeneous configuration (e.g.
+	 * big.LITTLE). This is not an uncore PMU, and we have taken ctx
+	 * sharing into account (e.g. with our pmu::filter_match callback and
+	 * pmu::event_init group validation).
+	 */
+	cpu_pmu->pmu.capabilities |= PERF_PMU_CAP_HETEROGENEOUS_CPUS;
+
 	return 0;
 
 out_unregister:
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index c77e4a1..9e1c3ad 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -225,6 +225,7 @@ struct perf_event;
 #define PERF_PMU_CAP_AUX_SW_DOUBLEBUF		0x08
 #define PERF_PMU_CAP_EXCLUSIVE			0x10
 #define PERF_PMU_CAP_ITRACE			0x20
+#define PERF_PMU_CAP_HETEROGENEOUS_CPUS		0x40
 
 /**
  * struct pmu - generic performance monitoring unit
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 63be654..fc0290f 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -8443,7 +8443,13 @@ skip_type:
 	if (pmu->task_ctx_nr == perf_hw_context) {
 		static int hw_context_taken = 0;
 
-		if (WARN_ON_ONCE(hw_context_taken))
+		/*
+		 * Other than systems with heterogeneous CPUs, it never makes
+		 * sense for two PMUs to share perf_hw_context. PMUs which are
+		 * uncore must use perf_invalid_context.
+		 */
+		if (WARN_ON_ONCE(hw_context_taken &&
+		    !(pmu->capabilities & PERF_PMU_CAP_HETEROGENEOUS_CPUS)))
 			pmu->task_ctx_nr = perf_invalid_context;
 
 		hw_context_taken = 1;