From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753879Ab0K1Rgk (ORCPT ); Sun, 28 Nov 2010 12:36:40 -0500 Received: from mx2.mail.elte.hu ([157.181.151.9]:37981 "EHLO mx2.mail.elte.hu" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753608Ab0K1Rgj (ORCPT ); Sun, 28 Nov 2010 12:36:39 -0500 Date: Sun, 28 Nov 2010 18:36:19 +0100 From: Ingo Molnar To: Linus Torvalds Cc: linux-kernel@vger.kernel.org, Peter Zijlstra , Arnaldo Carvalho de Melo , Thomas Gleixner , =?iso-8859-1?Q?Fr=E9d=E9ric?= Weisbecker , Andrew Morton Subject: [GIT PULL] perf fixes Message-ID: <20101128173619.GA11930@elte.hu> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline User-Agent: Mutt/1.5.20 (2009-08-17) X-ELTE-SpamScore: -2.0 X-ELTE-SpamLevel: X-ELTE-SpamCheck: no X-ELTE-SpamVersion: ELTE 2.0 X-ELTE-SpamCheck-Details: score=-2.0 required=5.9 tests=BAYES_00 autolearn=no SpamAssassin version=3.2.5 -2.0 BAYES_00 BODY: Bayesian spam probability is 0 to 1% [score: 0.0000] Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Linus, Please pull the latest perf-fixes-for-linus git tree from: git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git perf-fixes-for-linus Thanks, Ingo ------------------> Don Zickus (1): x86, perf, nmi: Disable perf if counters are not accessible Peter Zijlstra (2): perf, x86: Fixup Kconfig deps perf: Fix the software context switch counter Thomas Gleixner (1): perf: Fix inherit vs. context rotation bug arch/x86/Kconfig | 2 +- arch/x86/kernel/cpu/perf_event.c | 20 ++++++++++++++++++++ include/linux/perf_event.h | 30 ++++++++++++++++-------------- kernel/perf_event.c | 24 ++++++++++++++++++++---- 4 files changed, 57 insertions(+), 19 deletions(-) diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index e832768..e330da2 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -21,7 +21,7 @@ config X86 select HAVE_UNSTABLE_SCHED_CLOCK select HAVE_IDE select HAVE_OPROFILE - select HAVE_PERF_EVENTS if (!M386 && !M486) + select HAVE_PERF_EVENTS select HAVE_IRQ_WORK select HAVE_IOREMAP_PROT select HAVE_KPROBES diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index ed63101..6d75b91 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -381,6 +381,20 @@ static void release_pmc_hardware(void) {} #endif +static bool check_hw_exists(void) +{ + u64 val, val_new = 0; + int ret = 0; + + val = 0xabcdUL; + ret |= checking_wrmsrl(x86_pmu.perfctr, val); + ret |= rdmsrl_safe(x86_pmu.perfctr, &val_new); + if (ret || val != val_new) + return false; + + return true; +} + static void reserve_ds_buffers(void); static void release_ds_buffers(void); @@ -1372,6 +1386,12 @@ void __init init_hw_perf_events(void) pmu_check_apic(); + /* sanity check that the hardware exists or is emulated */ + if (!check_hw_exists()) { + pr_cont("Broken PMU hardware detected, software events only.\n"); + return; + } + pr_cont("%s PMU driver.\n", x86_pmu.name); if (x86_pmu.quirks) diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 40150f3..de2c417 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -850,6 +850,7 @@ struct perf_event_context { int nr_active; int is_active; int nr_stat; + int rotate_disable; atomic_t refcount; struct task_struct *task; @@ -908,20 +909,6 @@ extern int perf_num_counters(void); extern const char *perf_pmu_name(void); extern void __perf_event_task_sched_in(struct task_struct *task); extern void __perf_event_task_sched_out(struct task_struct *task, struct task_struct *next); - -extern atomic_t perf_task_events; - -static inline void perf_event_task_sched_in(struct task_struct *task) -{ - COND_STMT(&perf_task_events, __perf_event_task_sched_in(task)); -} - -static inline -void perf_event_task_sched_out(struct task_struct *task, struct task_struct *next) -{ - COND_STMT(&perf_task_events, __perf_event_task_sched_out(task, next)); -} - extern int perf_event_init_task(struct task_struct *child); extern void perf_event_exit_task(struct task_struct *child); extern void perf_event_free_task(struct task_struct *task); @@ -1030,6 +1017,21 @@ have_event: __perf_sw_event(event_id, nr, nmi, regs, addr); } +extern atomic_t perf_task_events; + +static inline void perf_event_task_sched_in(struct task_struct *task) +{ + COND_STMT(&perf_task_events, __perf_event_task_sched_in(task)); +} + +static inline +void perf_event_task_sched_out(struct task_struct *task, struct task_struct *next) +{ + perf_sw_event(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, 1, NULL, 0); + + COND_STMT(&perf_task_events, __perf_event_task_sched_out(task, next)); +} + extern void perf_event_mmap(struct vm_area_struct *vma); extern struct perf_guest_info_callbacks *perf_guest_cbs; extern int perf_register_guest_info_callbacks(struct perf_guest_info_callbacks *callbacks); diff --git a/kernel/perf_event.c b/kernel/perf_event.c index 671f6c8..eac7e33 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -1287,8 +1287,6 @@ void __perf_event_task_sched_out(struct task_struct *task, { int ctxn; - perf_sw_event(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, 1, NULL, 0); - for_each_task_context_nr(ctxn) perf_event_context_sched_out(task, ctxn, next); } @@ -1622,8 +1620,12 @@ static void rotate_ctx(struct perf_event_context *ctx) { raw_spin_lock(&ctx->lock); - /* Rotate the first entry last of non-pinned groups */ - list_rotate_left(&ctx->flexible_groups); + /* + * Rotate the first entry last of non-pinned groups. Rotation might be + * disabled by the inheritance code. + */ + if (!ctx->rotate_disable) + list_rotate_left(&ctx->flexible_groups); raw_spin_unlock(&ctx->lock); } @@ -6162,6 +6164,7 @@ int perf_event_init_context(struct task_struct *child, int ctxn) struct perf_event *event; struct task_struct *parent = current; int inherited_all = 1; + unsigned long flags; int ret = 0; child->perf_event_ctxp[ctxn] = NULL; @@ -6202,6 +6205,15 @@ int perf_event_init_context(struct task_struct *child, int ctxn) break; } + /* + * We can't hold ctx->lock when iterating the ->flexible_group list due + * to allocations, but we need to prevent rotation because + * rotate_ctx() will change the list from interrupt context. + */ + raw_spin_lock_irqsave(&parent_ctx->lock, flags); + parent_ctx->rotate_disable = 1; + raw_spin_unlock_irqrestore(&parent_ctx->lock, flags); + list_for_each_entry(event, &parent_ctx->flexible_groups, group_entry) { ret = inherit_task_group(event, parent, parent_ctx, child, ctxn, &inherited_all); @@ -6209,6 +6221,10 @@ int perf_event_init_context(struct task_struct *child, int ctxn) break; } + raw_spin_lock_irqsave(&parent_ctx->lock, flags); + parent_ctx->rotate_disable = 0; + raw_spin_unlock_irqrestore(&parent_ctx->lock, flags); + child_ctx = child->perf_event_ctxp[ctxn]; if (child_ctx && inherited_all) {