From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1761566AbbA3Kb0 (ORCPT ); Fri, 30 Jan 2015 05:31:26 -0500 Received: from mga03.intel.com ([134.134.136.65]:1218 "EHLO mga03.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1758344AbbA3KbW (ORCPT ); Fri, 30 Jan 2015 05:31:22 -0500 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.09,491,1418112000"; d="scan'208";a="659134178" From: Alexander Shishkin To: Peter Zijlstra Cc: Ingo Molnar , linux-kernel@vger.kernel.org, Robert Richter , Frederic Weisbecker , Mike Galbraith , Paul Mackerras , Stephane Eranian , Andi Kleen , kan.liang@intel.com, adrian.hunter@intel.com, markus.t.metzger@intel.com, mathieu.poirier@linaro.org, Kaixu Xia , acme@infradead.org, Alexander Shishkin Subject: [PATCH] perf: Add a pmu capability for "exclusive" events Date: Fri, 30 Jan 2015 12:31:06 +0200 Message-Id: <1422613866-113186-1-git-send-email-alexander.shishkin@linux.intel.com> X-Mailer: git-send-email 2.1.4 In-Reply-To: <20150129152022.GC26304@twins.programming.kicks-ass.net> References: <20150129152022.GC26304@twins.programming.kicks-ass.net> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Usually, pmus that do, for example, instruction tracing, would only ever be able to have one event per task per cpu (or per perf_event_context). For such pmus it makes sense to disallow creating conflicting events early on, so as to provide consistent behavior for the user. This patch adds a pmu capability that indicates such constraint on event creation. Signed-off-by: Alexander Shishkin --- include/linux/perf_event.h | 2 + kernel/events/core.c | 119 ++++++++++++++++++++++++++++++++++++++++++++- 2 files changed, 119 insertions(+), 2 deletions(-) diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 572e4fb508..60aa395a19 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -168,6 +168,7 @@ struct perf_event; #define PERF_PMU_CAP_NO_INTERRUPT 0x01 #define PERF_PMU_CAP_AUX_NO_SG 0x02 #define PERF_PMU_CAP_AUX_SW_DOUBLEBUF 0x04 +#define PERF_PMU_CAP_EXCLUSIVE 0x08 /** * struct pmu - generic performance monitoring unit @@ -188,6 +189,7 @@ struct pmu { int * __percpu pmu_disable_count; struct perf_cpu_context * __percpu pmu_cpu_context; + atomic_t exclusive_cnt; /* < 0: cpu; > 0: tsk */ int task_ctx_nr; int hrtimer_interval_ms; diff --git a/kernel/events/core.c b/kernel/events/core.c index 67643035de..0f2835f5c6 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -3335,6 +3335,91 @@ static void unaccount_event(struct perf_event *event) unaccount_event_cpu(event, event->cpu); } +/* + * The following implement mutual exclusion of events on "exclusive" pmus + * (PERF_PMU_CAP_EXCLUSIVE). Such pmus can only have one event scheduled + * at a time, so we disallow creating events that might conflict, namely: + * + * 1) cpu-wide events in the presence of per-task events, + * 2) per-task events in the presence of cpu-wide events, + * 3) two matching events on the same context. + * + * The former two cases are handled in the allocation path (perf_event_alloc(), + * __free_event()), the latter -- before the first perf_install_in_context(). + */ +static int exclusive_event_init(struct perf_event *event) +{ + struct pmu *pmu = event->pmu; + + if (!(pmu->capabilities & PERF_PMU_CAP_EXCLUSIVE)) + return 0; + + /* + * Prevent co-existence of per-task and cpu-wide events on the + * same exclusive pmu. + * + * Negative pmu::exclusive_cnt means there are cpu-wide + * events on this "exclusive" pmu, positive means there are + * per-task events. + * + * Since this is called in perf_event_alloc() path, event::ctx + * doesn't exist yet; it is, however, safe to use PERF_ATTACH_TASK + * to mean "per-task event", because unlike other attach states it + * never gets cleared. + */ + if (event->attach_state & PERF_ATTACH_TASK) { + if (!atomic_inc_unless_negative(&pmu->exclusive_cnt)) + return -EBUSY; + } else { + if (!atomic_dec_unless_positive(&pmu->exclusive_cnt)) + return -EBUSY; + } + + return 0; +} + +static void exclusive_event_destroy(struct perf_event *event) +{ + struct pmu *pmu = event->pmu; + + if (!(pmu->capabilities & PERF_PMU_CAP_EXCLUSIVE)) + return; + + /* see comment in exclusive_event_init() */ + if (event->attach_state & PERF_ATTACH_TASK) + atomic_dec(&pmu->exclusive_cnt); + else + atomic_inc(&pmu->exclusive_cnt); +} + +static bool exclusive_event_match(struct perf_event *e1, struct perf_event *e2) +{ + if ((e1->pmu->capabilities & PERF_PMU_CAP_EXCLUSIVE) && + (e1->cpu == e2->cpu || + e1->cpu == -1 || + e2->cpu == -1)) + return true; + return false; +} + +/* Called under the same ctx::mutex as perf_install_in_context() */ +static bool exclusive_event_installable(struct perf_event *event, + struct perf_event_context *ctx) +{ + struct perf_event *iter_event; + struct pmu *pmu = event->pmu; + + if (!(pmu->capabilities & PERF_PMU_CAP_EXCLUSIVE)) + return true; + + list_for_each_entry(iter_event, &ctx->event_list, event_entry) { + if (exclusive_event_match(iter_event, event)) + return false; + } + + return true; +} + static void __free_event(struct perf_event *event) { if (!event->parent) { @@ -3348,8 +3433,10 @@ static void __free_event(struct perf_event *event) if (event->ctx) put_ctx(event->ctx); - if (event->pmu) + if (event->pmu) { + exclusive_event_destroy(event); module_put(event->pmu->module); + } call_rcu(&event->rcu_head, free_event_rcu); } @@ -6907,6 +6994,7 @@ got_cpu_context: pmu->event_idx = perf_event_idx_default; list_add_rcu(&pmu->entry, &pmus); + atomic_set(&pmu->exclusive_cnt, 0); ret = 0; unlock: mutex_unlock(&pmus_lock); @@ -7142,16 +7230,23 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu, goto err_ns; } + err = exclusive_event_init(event); + if (err) + goto err_pmu; + if (!event->parent) { if (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN) { err = get_callchain_buffers(); if (err) - goto err_pmu; + goto err_per_task; } } return event; +err_per_task: + exclusive_event_destroy(event); + err_pmu: if (event->destroy) event->destroy(event); @@ -7500,6 +7595,11 @@ SYSCALL_DEFINE5(perf_event_open, goto err_alloc; } + if ((pmu->capabilities & PERF_PMU_CAP_EXCLUSIVE) && group_leader) { + err = -EBUSY; + goto err_context; + } + if (task) { put_task_struct(task); task = NULL; @@ -7597,6 +7697,13 @@ SYSCALL_DEFINE5(perf_event_open, } } + if (!exclusive_event_installable(event, ctx)) { + err = -EBUSY; + mutex_unlock(&ctx->mutex); + fput(event_file); + goto err_context; + } + perf_install_in_context(ctx, event, event->cpu); perf_unpin_context(ctx); mutex_unlock(&ctx->mutex); @@ -7683,6 +7790,14 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu, WARN_ON_ONCE(ctx->parent_ctx); mutex_lock(&ctx->mutex); + if (!exclusive_event_installable(event, ctx)) { + mutex_unlock(&ctx->mutex); + perf_unpin_context(ctx); + put_ctx(ctx); + err = -EBUSY; + goto err_free; + } + perf_install_in_context(ctx, event, cpu); perf_unpin_context(ctx); mutex_unlock(&ctx->mutex); -- 2.1.4