summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorMark Rutland <mark.rutland@arm.com>2016-04-26 11:33:46 +0100
committerIngo Molnar <mingo@kernel.org>2016-05-05 10:13:59 +0200
commit5101ef20f0ef1de79091a1fdb6b1a7f07565545a (patch)
treee258e92de18196699b547763bed143d74e812387
parent6e855cd4f4b5258016cf707f94f96bfa51c32f32 (diff)
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@arm.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vince Weaver <vincent.weaver@maine.edu> Cc: Will Deacon <will.deacon@arm.com> Cc: linux-arm-kernel@lists.infradead.org Link: http://lkml.kernel.org/r/20160426103346.GA20836@leverpostej Signed-off-by: Ingo Molnar <mingo@kernel.org>
-rw-r--r--drivers/perf/arm_pmu.c8
-rw-r--r--include/linux/perf_event.h1
-rw-r--r--kernel/events/core.c8
3 files changed, 16 insertions, 1 deletions
diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c
index f70090897fdf..f2d01d4d9364 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 c77e4a159fa2..9e1c3ada91c4 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 63be65437e9e..fc0290f25482 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;