Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752666AbZJNF6y (ORCPT ); Wed, 14 Oct 2009 01:58:54 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1751193AbZJNF6y (ORCPT ); Wed, 14 Oct 2009 01:58:54 -0400 Received: from ozlabs.org ([203.10.76.45]:48684 "EHLO ozlabs.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750925AbZJNF6x (ORCPT ); Wed, 14 Oct 2009 01:58:53 -0400 MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Message-ID: <19157.26731.855609.165622@cargo.ozlabs.ibm.com> Date: Wed, 14 Oct 2009 16:58:03 +1100 From: Paul Mackerras To: Peter Zijlstra , Ingo Molnar , "Mark W. Krentel" CC: linux-kernel@vger.kernel.org, Corey Ashford Subject: [PATCH] perf_event: Adjust frequency and unthrottle for non-group-leader events X-Mailer: VM 8.0.12 under 22.2.1 (i486-pc-linux-gnu) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 2028 Lines: 51 The loop in perf_ctx_adjust_freq checks the frequency of sampling event counters, and adjusts the event interval and unthrottles the event if required, and resets the interrupt count for the event. However, at present it only looks at group leaders. This means that a sampling event that is not a group leader will eventually get throttled, once its interrupt count reaches sysctl_perf_event_sample_rate/HZ --- and that is guaranteed to happen, if the event is active for long enough, since the interrupt count never gets reset. Once it is throttled it never gets unthrottled, so it basically just stops working at that point. This fixes it by making perf_ctx_adjust_freq use ctx->event_list rather than ctx->group_list. The existing spin_lock/spin_unlock around the loop makes it unnecessary to put rcu_read_lock/ rcu_read_unlock around the list_for_each_entry_rcu(). Reported-by: Mark W. Krentel Signed-off-by: Paul Mackerras --- Apparently this bug was only seen on powerpc, and not on x86. I have no idea why. Looks to me like we want a similar patch for 2.6.31 with some names changed (event -> counter etc.). If people agree with this patch I'll do one for stable. kernel/perf_event.c | 2 +- 1 files changed, 1 insertions(+), 1 deletions(-) diff --git a/kernel/perf_event.c b/kernel/perf_event.c index 76ac4db..1d6b938 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -1368,7 +1368,7 @@ static void perf_ctx_adjust_freq(struct perf_event_context *ctx) u64 interrupts, freq; spin_lock(&ctx->lock); - list_for_each_entry(event, &ctx->group_list, group_entry) { + list_for_each_entry_rcu(event, &ctx->event_list, event_entry) { if (event->state != PERF_EVENT_STATE_ACTIVE) continue; -- 1.6.0.4 -- 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/