Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752399AbaGGGcR (ORCPT ); Mon, 7 Jul 2014 02:32:17 -0400 Received: from mga09.intel.com ([134.134.136.24]:36667 "EHLO mga09.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751816AbaGGG3A (ORCPT ); Mon, 7 Jul 2014 02:29:00 -0400 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.01,616,1400050800"; d="scan'208";a="539565488" From: "Yan, Zheng" To: linux-kernel@vger.kernel.org Cc: a.p.zijlstra@chello.nl, mingo@kernel.org, acme@infradead.org, eranian@google.com, andi@firstfloor.org, "Yan, Zheng" Subject: [PATCH v5 05/16] perf, core: pmu specific data for perf task context Date: Mon, 7 Jul 2014 14:28:34 +0800 Message-Id: <1404714527-18603-6-git-send-email-zheng.z.yan@intel.com> X-Mailer: git-send-email 1.9.3 In-Reply-To: <1404714527-18603-1-git-send-email-zheng.z.yan@intel.com> References: <1404714527-18603-1-git-send-email-zheng.z.yan@intel.com> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Introduce a new flag PERF_ATTACH_TASK_DATA for perf event's attach stata. The flag is set by PMU's event_init() callback, it indicates that perf event needs PMU specific data. The PMU specific data are initialized to zeros. Later patches will use PMU specific data to save LBR stack. Signed-off-by: Yan, Zheng --- include/linux/perf_event.h | 6 ++++++ kernel/events/core.c | 40 ++++++++++++++++++++++++++++++++++++---- 2 files changed, 42 insertions(+), 4 deletions(-) diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 5d665e8..123f8d0 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -264,6 +264,10 @@ struct pmu { */ void (*sched_task) (struct perf_event_context *ctx, bool sched_in); + /* + * PMU specific data size + */ + size_t task_ctx_size; }; /** @@ -298,6 +302,7 @@ struct swevent_hlist { #define PERF_ATTACH_CONTEXT 0x01 #define PERF_ATTACH_GROUP 0x02 #define PERF_ATTACH_TASK 0x04 +#define PERF_ATTACH_TASK_DATA 0x08 struct perf_cgroup; struct ring_buffer; @@ -507,6 +512,7 @@ struct perf_event_context { u64 generation; int pin_count; int nr_cgroups; /* cgroup evts */ + void *task_ctx_data; /* pmu specific data */ struct rcu_head rcu_head; }; diff --git a/kernel/events/core.c b/kernel/events/core.c index 1ba83e2..51e221e 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -890,6 +890,15 @@ static void get_ctx(struct perf_event_context *ctx) WARN_ON(!atomic_inc_not_zero(&ctx->refcount)); } +static void free_ctx(struct rcu_head *head) +{ + struct perf_event_context *ctx; + + ctx = container_of(head, struct perf_event_context, rcu_head); + kfree(ctx->task_ctx_data); + kfree(ctx); +} + static void put_ctx(struct perf_event_context *ctx) { if (atomic_dec_and_test(&ctx->refcount)) { @@ -897,7 +906,7 @@ static void put_ctx(struct perf_event_context *ctx) put_ctx(ctx->parent_ctx); if (ctx->task) put_task_struct(ctx->task); - kfree_rcu(ctx, rcu_head); + call_rcu(&ctx->rcu_head, free_ctx); } } @@ -3112,12 +3121,15 @@ errout: * Returns a matching context with refcount and pincount. */ static struct perf_event_context * -find_get_context(struct pmu *pmu, struct task_struct *task, int cpu) +find_get_context(struct pmu *pmu, struct task_struct *task, + struct perf_event *event) { struct perf_event_context *ctx; struct perf_cpu_context *cpuctx; + void *task_ctx_data = NULL; unsigned long flags; int ctxn, err; + int cpu = event->cpu; if (!task) { /* Must be root to operate on a CPU event: */ @@ -3145,11 +3157,24 @@ find_get_context(struct pmu *pmu, struct task_struct *task, int cpu) if (ctxn < 0) goto errout; + if (event->attach_state & PERF_ATTACH_TASK_DATA) { + task_ctx_data = kzalloc(pmu->task_ctx_size, GFP_KERNEL); + if (!task_ctx_data) { + err = -ENOMEM; + goto errout; + } + } + retry: ctx = perf_lock_task_context(task, ctxn, &flags); if (ctx) { unclone_ctx(ctx); ++ctx->pin_count; + + if (task_ctx_data && !ctx->task_ctx_data) { + ctx->task_ctx_data = task_ctx_data; + task_ctx_data = NULL; + } raw_spin_unlock_irqrestore(&ctx->lock, flags); } else { ctx = alloc_perf_context(pmu, task); @@ -3157,6 +3182,11 @@ retry: if (!ctx) goto errout; + if (task_ctx_data) { + ctx->task_ctx_data = task_ctx_data; + task_ctx_data = NULL; + } + err = 0; mutex_lock(&task->perf_event_mutex); /* @@ -3183,9 +3213,11 @@ retry: } } + kfree(task_ctx_data); return ctx; errout: + kfree(task_ctx_data); return ERR_PTR(err); } @@ -7178,7 +7210,7 @@ SYSCALL_DEFINE5(perf_event_open, /* * Get the target context (task or percpu): */ - ctx = find_get_context(pmu, task, event->cpu); + ctx = find_get_context(pmu, task, event); if (IS_ERR(ctx)) { err = PTR_ERR(ctx); goto err_alloc; @@ -7344,7 +7376,7 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu, account_event(event); - ctx = find_get_context(event->pmu, task, cpu); + ctx = find_get_context(event->pmu, task, event); if (IS_ERR(ctx)) { err = PTR_ERR(ctx); goto err_free; -- 1.9.3 -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/