From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756590AbaCQGDa (ORCPT ); Mon, 17 Mar 2014 02:03:30 -0400 Received: from mga02.intel.com ([134.134.136.20]:65260 "EHLO mga02.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932354AbaCQF6h (ORCPT ); Mon, 17 Mar 2014 01:58:37 -0400 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="4.97,667,1389772800"; d="scan'208";a="473898332" 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 v4 06/16] perf, core: always switch pmu specific data during context switch Date: Mon, 17 Mar 2014 13:57:26 +0800 Message-Id: <1395035856-15411-7-git-send-email-zheng.z.yan@intel.com> X-Mailer: git-send-email 1.8.5.3 In-Reply-To: <1395035856-15411-1-git-send-email-zheng.z.yan@intel.com> References: <1395035856-15411-1-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 If two tasks were both forked from the same parent task, Events in their perf task contexts can be the same. Perf core may leave out switching the perf event contexts. Previous patch inroduces pmu specific data. The data is for saving the LBR stack, it is task specific. So we need to switch the data even when context switch is optimized out. Signed-off-by: Yan, Zheng --- kernel/events/core.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/kernel/events/core.c b/kernel/events/core.c index f262c57..20da73c 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -2336,6 +2336,7 @@ static void perf_event_context_sched_out(struct task_struct *task, int ctxn, raw_spin_lock(&ctx->lock); raw_spin_lock_nested(&next_ctx->lock, SINGLE_DEPTH_NESTING); if (context_equiv(ctx, next_ctx)) { + void *ctx_data; /* * XXX do we need a memory barrier of sorts * wrt to rcu_dereference() of perf_event_ctxp @@ -2344,6 +2345,11 @@ static void perf_event_context_sched_out(struct task_struct *task, int ctxn, next->perf_event_ctxp[ctxn] = ctx; ctx->task = next; next_ctx->task = task; + + ctx_data = next_ctx->task_ctx_data; + next_ctx->task_ctx_data = ctx->task_ctx_data; + ctx->task_ctx_data = ctx_data; + do_switch = 0; perf_event_sync_stat(ctx, next_ctx); -- 1.8.5.3