From ddaaf4e291dd63db0667991e4a335fcf3a7df13e Mon Sep 17 00:00:00 2001 From: Stephane Eranian Date: Thu, 12 Nov 2015 11:00:03 +0100 Subject: perf/core: Fix RCU problem with cgroup context switching code The RCU checker detected RCU violation in the cgroup switching routines perf_cgroup_sched_in() and perf_cgroup_sched_out(). We were dereferencing cgroup from task without holding the RCU lock. Fix this by holding the RCU read lock. We move the locking from perf_cgroup_switch() to avoid double locking. Signed-off-by: Stephane Eranian Signed-off-by: Peter Zijlstra (Intel) Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Vince Weaver Cc: edumazet@google.com Link: http://lkml.kernel.org/r/1447322404-10920-2-git-send-email-eranian@google.com Signed-off-by: Ingo Molnar --- kernel/events/core.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) (limited to 'kernel/events') diff --git a/kernel/events/core.c b/kernel/events/core.c index 36babfd20648..60e71ca42c22 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -489,7 +489,6 @@ static void perf_cgroup_switch(struct task_struct *task, int mode) * we reschedule only in the presence of cgroup * constrained events. */ - rcu_read_lock(); list_for_each_entry_rcu(pmu, &pmus, entry) { cpuctx = this_cpu_ptr(pmu->pmu_cpu_context); @@ -531,8 +530,6 @@ static void perf_cgroup_switch(struct task_struct *task, int mode) } } - rcu_read_unlock(); - local_irq_restore(flags); } @@ -542,6 +539,7 @@ static inline void perf_cgroup_sched_out(struct task_struct *task, struct perf_cgroup *cgrp1; struct perf_cgroup *cgrp2 = NULL; + rcu_read_lock(); /* * we come here when we know perf_cgroup_events > 0 */ @@ -561,6 +559,8 @@ static inline void perf_cgroup_sched_out(struct task_struct *task, */ if (cgrp1 != cgrp2) perf_cgroup_switch(task, PERF_CGROUP_SWOUT); + + rcu_read_unlock(); } static inline void perf_cgroup_sched_in(struct task_struct *prev, @@ -569,6 +569,7 @@ static inline void perf_cgroup_sched_in(struct task_struct *prev, struct perf_cgroup *cgrp1; struct perf_cgroup *cgrp2 = NULL; + rcu_read_lock(); /* * we come here when we know perf_cgroup_events > 0 */ @@ -584,6 +585,8 @@ static inline void perf_cgroup_sched_in(struct task_struct *prev, */ if (cgrp1 != cgrp2) perf_cgroup_switch(task, PERF_CGROUP_SWIN); + + rcu_read_unlock(); } static inline int perf_cgroup_connect(int fd, struct perf_event *event, @@ -9452,7 +9455,9 @@ static void perf_cgroup_css_free(struct cgroup_subsys_state *css) static int __perf_cgroup_move(void *info) { struct task_struct *task = info; + rcu_read_lock(); perf_cgroup_switch(task, PERF_CGROUP_SWOUT | PERF_CGROUP_SWIN); + rcu_read_unlock(); return 0; } -- cgit v1.2.3 From 614e4c4ebc75517295bccd29b20ddbc5b52af6fc Mon Sep 17 00:00:00 2001 From: Stephane Eranian Date: Thu, 12 Nov 2015 11:00:04 +0100 Subject: perf/core: Robustify the perf_cgroup_from_task() RCU checks This patch reinforces the lockdep checks performed by perf_cgroup_from_tsk() by passing the perf_event_context whenever possible. It is okay to not hold the RCU read lock when we know we hold the ctx->lock. This patch makes sure this property holds. In some functions, such as perf_cgroup_sched_in(), we do not pass the context because we are sure we are holding the RCU read lock. Signed-off-by: Stephane Eranian Signed-off-by: Peter Zijlstra (Intel) Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Vince Weaver Cc: edumazet@google.com Link: http://lkml.kernel.org/r/1447322404-10920-3-git-send-email-eranian@google.com Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/perf_event_intel_cqm.c | 2 +- include/linux/perf_event.h | 6 ++++-- kernel/events/core.c | 20 +++++++++++++------- 3 files changed, 18 insertions(+), 10 deletions(-) (limited to 'kernel/events') diff --git a/arch/x86/kernel/cpu/perf_event_intel_cqm.c b/arch/x86/kernel/cpu/perf_event_intel_cqm.c index 377e8f8ed391..a316ca96f1b6 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_cqm.c +++ b/arch/x86/kernel/cpu/perf_event_intel_cqm.c @@ -298,7 +298,7 @@ static bool __match_event(struct perf_event *a, struct perf_event *b) static inline struct perf_cgroup *event_to_cgroup(struct perf_event *event) { if (event->attach_state & PERF_ATTACH_TASK) - return perf_cgroup_from_task(event->hw.target); + return perf_cgroup_from_task(event->hw.target, event->ctx); return event->cgrp; } diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index d841d33bcdc9..f9828a48f16a 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -697,9 +697,11 @@ struct perf_cgroup { * if there is no cgroup event for the current CPU context. */ static inline struct perf_cgroup * -perf_cgroup_from_task(struct task_struct *task) +perf_cgroup_from_task(struct task_struct *task, struct perf_event_context *ctx) { - return container_of(task_css(task, perf_event_cgrp_id), + return container_of(task_css_check(task, perf_event_cgrp_id, + ctx ? lockdep_is_held(&ctx->lock) + : true), struct perf_cgroup, css); } #endif /* CONFIG_CGROUP_PERF */ diff --git a/kernel/events/core.c b/kernel/events/core.c index 60e71ca42c22..1ac857aff7b0 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -435,7 +435,7 @@ static inline void update_cgrp_time_from_event(struct perf_event *event) if (!is_cgroup_event(event)) return; - cgrp = perf_cgroup_from_task(current); + cgrp = perf_cgroup_from_task(current, event->ctx); /* * Do not update time when cgroup is not active */ @@ -458,7 +458,7 @@ perf_cgroup_set_timestamp(struct task_struct *task, if (!task || !ctx->nr_cgroups) return; - cgrp = perf_cgroup_from_task(task); + cgrp = perf_cgroup_from_task(task, ctx); info = this_cpu_ptr(cgrp->info); info->timestamp = ctx->timestamp; } @@ -521,8 +521,10 @@ static void perf_cgroup_switch(struct task_struct *task, int mode) * set cgrp before ctxsw in to allow * event_filter_match() to not have to pass * task around + * we pass the cpuctx->ctx to perf_cgroup_from_task() + * because cgorup events are only per-cpu */ - cpuctx->cgrp = perf_cgroup_from_task(task); + cpuctx->cgrp = perf_cgroup_from_task(task, &cpuctx->ctx); cpu_ctx_sched_in(cpuctx, EVENT_ALL, task); } perf_pmu_enable(cpuctx->ctx.pmu); @@ -542,15 +544,17 @@ static inline void perf_cgroup_sched_out(struct task_struct *task, rcu_read_lock(); /* * we come here when we know perf_cgroup_events > 0 + * we do not need to pass the ctx here because we know + * we are holding the rcu lock */ - cgrp1 = perf_cgroup_from_task(task); + cgrp1 = perf_cgroup_from_task(task, NULL); /* * next is NULL when called from perf_event_enable_on_exec() * that will systematically cause a cgroup_switch() */ if (next) - cgrp2 = perf_cgroup_from_task(next); + cgrp2 = perf_cgroup_from_task(next, NULL); /* * only schedule out current cgroup events if we know @@ -572,11 +576,13 @@ static inline void perf_cgroup_sched_in(struct task_struct *prev, rcu_read_lock(); /* * we come here when we know perf_cgroup_events > 0 + * we do not need to pass the ctx here because we know + * we are holding the rcu lock */ - cgrp1 = perf_cgroup_from_task(task); + cgrp1 = perf_cgroup_from_task(task, NULL); /* prev can never be NULL */ - cgrp2 = perf_cgroup_from_task(prev); + cgrp2 = perf_cgroup_from_task(prev, NULL); /* * only need to schedule in cgroup events if we are changing -- cgit v1.2.3 From 90eec103b96e30401c0b846045bf8a1c7159b6da Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 16 Nov 2015 11:08:45 +0100 Subject: treewide: Remove old email address There were still a number of references to my old Red Hat email address in the kernel source. Remove these while keeping the Red Hat copyright notices intact. Signed-off-by: Peter Zijlstra (Intel) Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Thomas Gleixner Cc: Vince Weaver Signed-off-by: Ingo Molnar --- arch/blackfin/kernel/perf_event.c | 2 +- arch/sh/kernel/perf_event.c | 2 +- arch/sparc/kernel/perf_event.c | 2 +- arch/tile/kernel/perf_event.c | 2 +- arch/x86/kernel/cpu/perf_event.c | 2 +- arch/x86/kernel/cpu/perf_event.h | 2 +- arch/x86/kernel/irq_work.c | 2 +- include/asm-generic/tlb.h | 2 +- include/linux/jump_label.h | 2 +- include/linux/lockdep.h | 2 +- include/linux/proportions.h | 2 +- include/linux/uprobes.h | 2 +- kernel/events/callchain.c | 2 +- kernel/events/core.c | 2 +- kernel/events/ring_buffer.c | 2 +- kernel/events/uprobes.c | 2 +- kernel/irq_work.c | 2 +- kernel/jump_label.c | 2 +- kernel/locking/lockdep.c | 2 +- kernel/locking/lockdep_proc.c | 2 +- kernel/sched/clock.c | 2 +- kernel/sched/fair.c | 2 +- kernel/trace/trace_event_perf.c | 2 +- lib/btree.c | 2 +- lib/proportions.c | 2 +- mm/page-writeback.c | 2 +- 26 files changed, 26 insertions(+), 26 deletions(-) (limited to 'kernel/events') diff --git a/arch/blackfin/kernel/perf_event.c b/arch/blackfin/kernel/perf_event.c index 1e9c8b0bf486..170d786807c4 100644 --- a/arch/blackfin/kernel/perf_event.c +++ b/arch/blackfin/kernel/perf_event.c @@ -14,7 +14,7 @@ * Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar * Copyright (C) 2009 Jaswinder Singh Rajput * Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter - * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra + * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra * Copyright (C) 2009 Intel Corporation, * * ppc: diff --git a/arch/sh/kernel/perf_event.c b/arch/sh/kernel/perf_event.c index 7cfd7f153966..4dca18347ee9 100644 --- a/arch/sh/kernel/perf_event.c +++ b/arch/sh/kernel/perf_event.c @@ -10,7 +10,7 @@ * Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar * Copyright (C) 2009 Jaswinder Singh Rajput * Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter - * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra + * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra * Copyright (C) 2009 Intel Corporation, * * ppc: diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c index b0da5aedb336..3091267c5cc3 100644 --- a/arch/sparc/kernel/perf_event.c +++ b/arch/sparc/kernel/perf_event.c @@ -9,7 +9,7 @@ * Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar * Copyright (C) 2009 Jaswinder Singh Rajput * Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter - * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra + * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra */ #include diff --git a/arch/tile/kernel/perf_event.c b/arch/tile/kernel/perf_event.c index bb509cee3b59..8767060d70fb 100644 --- a/arch/tile/kernel/perf_event.c +++ b/arch/tile/kernel/perf_event.c @@ -21,7 +21,7 @@ * Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar * Copyright (C) 2009 Jaswinder Singh Rajput * Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter - * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra + * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra * Copyright (C) 2009 Intel Corporation, * Copyright (C) 2009 Google, Inc., Stephane Eranian */ diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 4562cf070c27..2bf79d7c97df 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -5,7 +5,7 @@ * Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar * Copyright (C) 2009 Jaswinder Singh Rajput * Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter - * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra + * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra * Copyright (C) 2009 Intel Corporation, * Copyright (C) 2009 Google, Inc., Stephane Eranian * diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h index ffa7a92025e1..ab18b8a91583 100644 --- a/arch/x86/kernel/cpu/perf_event.h +++ b/arch/x86/kernel/cpu/perf_event.h @@ -5,7 +5,7 @@ * Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar * Copyright (C) 2009 Jaswinder Singh Rajput * Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter - * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra + * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra * Copyright (C) 2009 Intel Corporation, * Copyright (C) 2009 Google, Inc., Stephane Eranian * diff --git a/arch/x86/kernel/irq_work.c b/arch/x86/kernel/irq_work.c index dc5fa6a1e8d6..3512ba607361 100644 --- a/arch/x86/kernel/irq_work.c +++ b/arch/x86/kernel/irq_work.c @@ -1,7 +1,7 @@ /* * x86 specific code for irq_work * - * Copyright (C) 2010 Red Hat, Inc., Peter Zijlstra + * Copyright (C) 2010 Red Hat, Inc., Peter Zijlstra */ #include diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h index db284bff29dc..9dbb739cafa0 100644 --- a/include/asm-generic/tlb.h +++ b/include/asm-generic/tlb.h @@ -5,7 +5,7 @@ * Copyright 2001 Red Hat, Inc. * Based on code from mm/memory.c Copyright Linus Torvalds and others. * - * Copyright 2011 Red Hat, Inc., Peter Zijlstra + * Copyright 2011 Red Hat, Inc., Peter Zijlstra * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h index 8dde55974f18..0536524bb9eb 100644 --- a/include/linux/jump_label.h +++ b/include/linux/jump_label.h @@ -5,7 +5,7 @@ * Jump label support * * Copyright (C) 2009-2012 Jason Baron - * Copyright (C) 2011-2012 Peter Zijlstra + * Copyright (C) 2011-2012 Red Hat, Inc., Peter Zijlstra * * DEPRECATED API: * diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 70400dc7660f..c57e424d914b 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -2,7 +2,7 @@ * Runtime locking correctness validator * * Copyright (C) 2006,2007 Red Hat, Inc., Ingo Molnar - * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra + * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra * * see Documentation/locking/lockdep-design.txt for more details. */ diff --git a/include/linux/proportions.h b/include/linux/proportions.h index 5440f64d2942..21221338ad18 100644 --- a/include/linux/proportions.h +++ b/include/linux/proportions.h @@ -1,7 +1,7 @@ /* * FLoating proportions * - * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra + * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra * * This file contains the public data structure and API definitions. */ diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h index 0bdc72f36905..4a29c75b146e 100644 --- a/include/linux/uprobes.h +++ b/include/linux/uprobes.h @@ -21,7 +21,7 @@ * Authors: * Srikar Dronamraju * Jim Keniston - * Copyright (C) 2011-2012 Red Hat, Inc., Peter Zijlstra + * Copyright (C) 2011-2012 Red Hat, Inc., Peter Zijlstra */ #include diff --git a/kernel/events/callchain.c b/kernel/events/callchain.c index d659487254d5..9c418002b8c1 100644 --- a/kernel/events/callchain.c +++ b/kernel/events/callchain.c @@ -3,7 +3,7 @@ * * Copyright (C) 2008 Thomas Gleixner * Copyright (C) 2008-2011 Red Hat, Inc., Ingo Molnar - * Copyright (C) 2008-2011 Red Hat, Inc., Peter Zijlstra + * Copyright (C) 2008-2011 Red Hat, Inc., Peter Zijlstra * Copyright © 2009 Paul Mackerras, IBM Corp. * * For licensing details see kernel-base/COPYING diff --git a/kernel/events/core.c b/kernel/events/core.c index 1ac857aff7b0..5854fcf7f05a 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -3,7 +3,7 @@ * * Copyright (C) 2008 Thomas Gleixner * Copyright (C) 2008-2011 Red Hat, Inc., Ingo Molnar - * Copyright (C) 2008-2011 Red Hat, Inc., Peter Zijlstra + * Copyright (C) 2008-2011 Red Hat, Inc., Peter Zijlstra * Copyright © 2009 Paul Mackerras, IBM Corp. * * For licensing details see kernel-base/COPYING diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index b5d1ea79c595..adfdc0536117 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -3,7 +3,7 @@ * * Copyright (C) 2008 Thomas Gleixner * Copyright (C) 2008-2011 Red Hat, Inc., Ingo Molnar - * Copyright (C) 2008-2011 Red Hat, Inc., Peter Zijlstra + * Copyright (C) 2008-2011 Red Hat, Inc., Peter Zijlstra * Copyright © 2009 Paul Mackerras, IBM Corp. * * For licensing details see kernel-base/COPYING diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 4e5e9798aa0c..7dad84913abf 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -19,7 +19,7 @@ * Authors: * Srikar Dronamraju * Jim Keniston - * Copyright (C) 2011-2012 Red Hat, Inc., Peter Zijlstra + * Copyright (C) 2011-2012 Red Hat, Inc., Peter Zijlstra */ #include diff --git a/kernel/irq_work.c b/kernel/irq_work.c index cbf9fb899d92..bcf107ce0854 100644 --- a/kernel/irq_work.c +++ b/kernel/irq_work.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2010 Red Hat, Inc., Peter Zijlstra + * Copyright (C) 2010 Red Hat, Inc., Peter Zijlstra * * Provides a framework for enqueueing and running callbacks from hardirq * context. The enqueueing is NMI-safe. diff --git a/kernel/jump_label.c b/kernel/jump_label.c index f7dd15d537f9..05254eeb4b4e 100644 --- a/kernel/jump_label.c +++ b/kernel/jump_label.c @@ -2,7 +2,7 @@ * jump label support * * Copyright (C) 2009 Jason Baron - * Copyright (C) 2011 Peter Zijlstra + * Copyright (C) 2011 Peter Zijlstra * */ #include diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index deae3907ac1e..60ace56618f6 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -6,7 +6,7 @@ * Started by Ingo Molnar: * * Copyright (C) 2006,2007 Red Hat, Inc., Ingo Molnar - * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra + * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra * * this code maps all the lock dependencies as they occur in a live kernel * and will warn about the following classes of locking bugs: diff --git a/kernel/locking/lockdep_proc.c b/kernel/locking/lockdep_proc.c index d83d798bef95..dbb61a302548 100644 --- a/kernel/locking/lockdep_proc.c +++ b/kernel/locking/lockdep_proc.c @@ -6,7 +6,7 @@ * Started by Ingo Molnar: * * Copyright (C) 2006,2007 Red Hat, Inc., Ingo Molnar - * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra + * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra * * Code for /proc/lockdep and /proc/lockdep_stats: * diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c index c0a205101c23..caf4041f5b0a 100644 --- a/kernel/sched/clock.c +++ b/kernel/sched/clock.c @@ -1,7 +1,7 @@ /* * sched_clock for unstable cpu clocks * - * Copyright (C) 2008 Red Hat, Inc., Peter Zijlstra + * Copyright (C) 2008 Red Hat, Inc., Peter Zijlstra * * Updates and enhancements: * Copyright (C) 2008 Red Hat, Inc. Steven Rostedt diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index f04fda8f669c..90e26b11deaa 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -17,7 +17,7 @@ * Copyright (C) 2007, Thomas Gleixner * * Adaptive scheduling granularity, math enhancements by Peter Zijlstra - * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra + * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra */ #include diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c index abfc903e741e..cc9f7a9319be 100644 --- a/kernel/trace/trace_event_perf.c +++ b/kernel/trace/trace_event_perf.c @@ -1,7 +1,7 @@ /* * trace event based perf event profiling/tracing * - * Copyright (C) 2009 Red Hat Inc, Peter Zijlstra + * Copyright (C) 2009 Red Hat Inc, Peter Zijlstra * Copyright (C) 2009-2010 Frederic Weisbecker */ diff --git a/lib/btree.c b/lib/btree.c index 4264871ea1a0..f93a945274af 100644 --- a/lib/btree.c +++ b/lib/btree.c @@ -5,7 +5,7 @@ * * Copyright (c) 2007-2008 Joern Engel * Bits and pieces stolen from Peter Zijlstra's code, which is - * Copyright 2007, Red Hat Inc. Peter Zijlstra + * Copyright 2007, Red Hat Inc. Peter Zijlstra * GPLv2 * * see http://programming.kicks-ass.net/kernel-patches/vma_lookup/btree.patch diff --git a/lib/proportions.c b/lib/proportions.c index 6f724298f67a..efa54f259ea9 100644 --- a/lib/proportions.c +++ b/lib/proportions.c @@ -1,7 +1,7 @@ /* * Floating proportions * - * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra + * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra * * Description: * diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 3e4d65445fa7..d15d88c8efa1 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -2,7 +2,7 @@ * mm/page-writeback.c * * Copyright (C) 2002, Linus Torvalds. - * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra + * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra * * Contains functions related to writing back dirty pages at the * address_space level. -- cgit v1.2.3 From 1f7dd3e5a6e4f093017fff12232572ee1aa4639b Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 3 Dec 2015 10:18:21 -0500 Subject: cgroup: fix handling of multi-destination migration from subtree_control enabling Consider the following v2 hierarchy. P0 (+memory) --- P1 (-memory) --- A \- B P0 has memory enabled in its subtree_control while P1 doesn't. If both A and B contain processes, they would belong to the memory css of P1. Now if memory is enabled on P1's subtree_control, memory csses should be created on both A and B and A's processes should be moved to the former and B's processes the latter. IOW, enabling controllers can cause atomic migrations into different csses. The core cgroup migration logic has been updated accordingly but the controller migration methods haven't and still assume that all tasks migrate to a single target css; furthermore, the methods were fed the css in which subtree_control was updated which is the parent of the target csses. pids controller depends on the migration methods to move charges and this made the controller attribute charges to the wrong csses often triggering the following warning by driving a counter negative. WARNING: CPU: 1 PID: 1 at kernel/cgroup_pids.c:97 pids_cancel.constprop.6+0x31/0x40() Modules linked in: CPU: 1 PID: 1 Comm: systemd Not tainted 4.4.0-rc1+ #29 ... ffffffff81f65382 ffff88007c043b90 ffffffff81551ffc 0000000000000000 ffff88007c043bc8 ffffffff810de202 ffff88007a752000 ffff88007a29ab00 ffff88007c043c80 ffff88007a1d8400 0000000000000001 ffff88007c043bd8 Call Trace: [] dump_stack+0x4e/0x82 [] warn_slowpath_common+0x82/0xc0 [] warn_slowpath_null+0x1a/0x20 [] pids_cancel.constprop.6+0x31/0x40 [] pids_can_attach+0x6d/0xf0 [] cgroup_taskset_migrate+0x6c/0x330 [] cgroup_migrate+0xf5/0x190 [] cgroup_attach_task+0x176/0x200 [] __cgroup_procs_write+0x2ad/0x460 [] cgroup_procs_write+0x14/0x20 [] cgroup_file_write+0x35/0x1c0 [] kernfs_fop_write+0x141/0x190 [] __vfs_write+0x28/0xe0 [] vfs_write+0xac/0x1a0 [] SyS_write+0x49/0xb0 [] entry_SYSCALL_64_fastpath+0x12/0x76 This patch fixes the bug by removing @css parameter from the three migration methods, ->can_attach, ->cancel_attach() and ->attach() and updating cgroup_taskset iteration helpers also return the destination css in addition to the task being migrated. All controllers are updated accordingly. * Controllers which don't care whether there are one or multiple target csses can be converted trivially. cpu, io, freezer, perf, netclassid and netprio fall in this category. * cpuset's current implementation assumes that there's single source and destination and thus doesn't support v2 hierarchy already. The only change made by this patchset is how that single destination css is obtained. * memory migration path already doesn't do anything on v2. How the single destination css is obtained is updated and the prep stage of mem_cgroup_can_attach() is reordered to accomodate the change. * pids is the only controller which was affected by this bug. It now correctly handles multi-destination migrations and no longer causes counter underflow from incorrect accounting. Signed-off-by: Tejun Heo Reported-and-tested-by: Daniel Wagner Cc: Aleksa Sarai --- block/blk-cgroup.c | 6 +++--- include/linux/cgroup-defs.h | 9 +++------ include/linux/cgroup.h | 33 +++++++++++++++++++++----------- kernel/cgroup.c | 43 +++++++++++++++++++++++++++++++++--------- kernel/cgroup_freezer.c | 6 +++--- kernel/cgroup_pids.c | 16 ++++++++-------- kernel/cpuset.c | 33 ++++++++++++++++++++------------ kernel/events/core.c | 6 +++--- kernel/sched/core.c | 12 ++++++------ mm/memcontrol.c | 45 ++++++++++++++++++++++---------------------- net/core/netclassid_cgroup.c | 11 ++++++----- net/core/netprio_cgroup.c | 9 +++++---- 12 files changed, 137 insertions(+), 92 deletions(-) (limited to 'kernel/events') diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 5bcdfc10c23a..5a37188b559f 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -1127,15 +1127,15 @@ void blkcg_exit_queue(struct request_queue *q) * of the main cic data structures. For now we allow a task to change * its cgroup only if it's the only owner of its ioc. */ -static int blkcg_can_attach(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset) +static int blkcg_can_attach(struct cgroup_taskset *tset) { struct task_struct *task; + struct cgroup_subsys_state *dst_css; struct io_context *ioc; int ret = 0; /* task_lock() is needed to avoid races with exit_io_context() */ - cgroup_taskset_for_each(task, tset) { + cgroup_taskset_for_each(task, dst_css, tset) { task_lock(task); ioc = task->io_context; if (ioc && atomic_read(&ioc->nr_tasks) > 1) diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 869fd4a3d28e..06b77f9dd3f2 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -422,12 +422,9 @@ struct cgroup_subsys { void (*css_reset)(struct cgroup_subsys_state *css); void (*css_e_css_changed)(struct cgroup_subsys_state *css); - int (*can_attach)(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset); - void (*cancel_attach)(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset); - void (*attach)(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset); + int (*can_attach)(struct cgroup_taskset *tset); + void (*cancel_attach)(struct cgroup_taskset *tset); + void (*attach)(struct cgroup_taskset *tset); int (*can_fork)(struct task_struct *task, void **priv_p); void (*cancel_fork)(struct task_struct *task, void *priv); void (*fork)(struct task_struct *task, void *priv); diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index f64083030ad5..cb91b44f5f78 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -120,8 +120,10 @@ struct cgroup_subsys_state *css_rightmost_descendant(struct cgroup_subsys_state struct cgroup_subsys_state *css_next_descendant_post(struct cgroup_subsys_state *pos, struct cgroup_subsys_state *css); -struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset); -struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset); +struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset, + struct cgroup_subsys_state **dst_cssp); +struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset, + struct cgroup_subsys_state **dst_cssp); void css_task_iter_start(struct cgroup_subsys_state *css, struct css_task_iter *it); @@ -236,30 +238,39 @@ void css_task_iter_end(struct css_task_iter *it); /** * cgroup_taskset_for_each - iterate cgroup_taskset * @task: the loop cursor + * @dst_css: the destination css * @tset: taskset to iterate * * @tset may contain multiple tasks and they may belong to multiple - * processes. When there are multiple tasks in @tset, if a task of a - * process is in @tset, all tasks of the process are in @tset. Also, all - * are guaranteed to share the same source and destination csses. + * processes. + * + * On the v2 hierarchy, there may be tasks from multiple processes and they + * may not share the source or destination csses. + * + * On traditional hierarchies, when there are multiple tasks in @tset, if a + * task of a process is in @tset, all tasks of the process are in @tset. + * Also, all are guaranteed to share the same source and destination csses. * * Iteration is not in any specific order. */ -#define cgroup_taskset_for_each(task, tset) \ - for ((task) = cgroup_taskset_first((tset)); (task); \ - (task) = cgroup_taskset_next((tset))) +#define cgroup_taskset_for_each(task, dst_css, tset) \ + for ((task) = cgroup_taskset_first((tset), &(dst_css)); \ + (task); \ + (task) = cgroup_taskset_next((tset), &(dst_css))) /** * cgroup_taskset_for_each_leader - iterate group leaders in a cgroup_taskset * @leader: the loop cursor + * @dst_css: the destination css * @tset: takset to iterate * * Iterate threadgroup leaders of @tset. For single-task migrations, @tset * may not contain any. */ -#define cgroup_taskset_for_each_leader(leader, tset) \ - for ((leader) = cgroup_taskset_first((tset)); (leader); \ - (leader) = cgroup_taskset_next((tset))) \ +#define cgroup_taskset_for_each_leader(leader, dst_css, tset) \ + for ((leader) = cgroup_taskset_first((tset), &(dst_css)); \ + (leader); \ + (leader) = cgroup_taskset_next((tset), &(dst_css))) \ if ((leader) != (leader)->group_leader) \ ; \ else diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 5cea63fe4095..470f6536b9e8 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -2237,6 +2237,9 @@ struct cgroup_taskset { struct list_head src_csets; struct list_head dst_csets; + /* the subsys currently being processed */ + int ssid; + /* * Fields for cgroup_taskset_*() iteration. * @@ -2299,25 +2302,29 @@ static void cgroup_taskset_add(struct task_struct *task, /** * cgroup_taskset_first - reset taskset and return the first task * @tset: taskset of interest + * @dst_cssp: output variable for the destination css * * @tset iteration is initialized and the first task is returned. */ -struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset) +struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset, + struct cgroup_subsys_state **dst_cssp) { tset->cur_cset = list_first_entry(tset->csets, struct css_set, mg_node); tset->cur_task = NULL; - return cgroup_taskset_next(tset); + return cgroup_taskset_next(tset, dst_cssp); } /** * cgroup_taskset_next - iterate to the next task in taskset * @tset: taskset of interest + * @dst_cssp: output variable for the destination css * * Return the next task in @tset. Iteration must have been initialized * with cgroup_taskset_first(). */ -struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset) +struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset, + struct cgroup_subsys_state **dst_cssp) { struct css_set *cset = tset->cur_cset; struct task_struct *task = tset->cur_task; @@ -2332,6 +2339,18 @@ struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset) if (&task->cg_list != &cset->mg_tasks) { tset->cur_cset = cset; tset->cur_task = task; + + /* + * This function may be called both before and + * after cgroup_taskset_migrate(). The two cases + * can be distinguished by looking at whether @cset + * has its ->mg_dst_cset set. + */ + if (cset->mg_dst_cset) + *dst_cssp = cset->mg_dst_cset->subsys[tset->ssid]; + else + *dst_cssp = cset->subsys[tset->ssid]; + return task; } @@ -2367,7 +2386,8 @@ static int cgroup_taskset_migrate(struct cgroup_taskset *tset, /* check that we can legitimately attach to the cgroup */ for_each_e_css(css, i, dst_cgrp) { if (css->ss->can_attach) { - ret = css->ss->can_attach(css, tset); + tset->ssid = i; + ret = css->ss->can_attach(tset); if (ret) { failed_css = css; goto out_cancel_attach; @@ -2400,9 +2420,12 @@ static int cgroup_taskset_migrate(struct cgroup_taskset *tset, */ tset->csets = &tset->dst_csets; - for_each_e_css(css, i, dst_cgrp) - if (css->ss->attach) - css->ss->attach(css, tset); + for_each_e_css(css, i, dst_cgrp) { + if (css->ss->attach) { + tset->ssid = i; + css->ss->attach(tset); + } + } ret = 0; goto out_release_tset; @@ -2411,8 +2434,10 @@ out_cancel_attach: for_each_e_css(css, i, dst_cgrp) { if (css == failed_css) break; - if (css->ss->cancel_attach) - css->ss->cancel_attach(css, tset); + if (css->ss->cancel_attach) { + tset->ssid = i; + css->ss->cancel_attach(tset); + } } out_release_tset: spin_lock_bh(&css_set_lock); diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c index ff02a8e51bb3..2d3df82c54f2 100644 --- a/kernel/cgroup_freezer.c +++ b/kernel/cgroup_freezer.c @@ -155,10 +155,10 @@ static void freezer_css_free(struct cgroup_subsys_state *css) * @freezer->lock. freezer_attach() makes the new tasks conform to the * current state and all following state changes can see the new tasks. */ -static void freezer_attach(struct cgroup_subsys_state *new_css, - struct cgroup_taskset *tset) +static void freezer_attach(struct cgroup_taskset *tset) { struct task_struct *task; + struct cgroup_subsys_state *new_css; mutex_lock(&freezer_mutex); @@ -172,7 +172,7 @@ static void freezer_attach(struct cgroup_subsys_state *new_css, * current state before executing the following - !frozen tasks may * be visible in a FROZEN cgroup and frozen tasks in a THAWED one. */ - cgroup_taskset_for_each(task, tset) { + cgroup_taskset_for_each(task, new_css, tset) { struct freezer *freezer = css_freezer(new_css); if (!(freezer->state & CGROUP_FREEZING)) { diff --git a/kernel/cgroup_pids.c b/kernel/cgroup_pids.c index de3359a48dbb..8e27fc5dbb20 100644 --- a/kernel/cgroup_pids.c +++ b/kernel/cgroup_pids.c @@ -162,13 +162,13 @@ revert: return -EAGAIN; } -static int pids_can_attach(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset) +static int pids_can_attach(struct cgroup_taskset *tset) { - struct pids_cgroup *pids = css_pids(css); struct task_struct *task; + struct cgroup_subsys_state *dst_css; - cgroup_taskset_for_each(task, tset) { + cgroup_taskset_for_each(task, dst_css, tset) { + struct pids_cgroup *pids = css_pids(dst_css); struct cgroup_subsys_state *old_css; struct pids_cgroup *old_pids; @@ -187,13 +187,13 @@ static int pids_can_attach(struct cgroup_subsys_state *css, return 0; } -static void pids_cancel_attach(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset) +static void pids_cancel_attach(struct cgroup_taskset *tset) { - struct pids_cgroup *pids = css_pids(css); struct task_struct *task; + struct cgroup_subsys_state *dst_css; - cgroup_taskset_for_each(task, tset) { + cgroup_taskset_for_each(task, dst_css, tset) { + struct pids_cgroup *pids = css_pids(dst_css); struct cgroup_subsys_state *old_css; struct pids_cgroup *old_pids; diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 10ae73611d80..02a8ea5c9963 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -1429,15 +1429,16 @@ static int fmeter_getrate(struct fmeter *fmp) static struct cpuset *cpuset_attach_old_cs; /* Called by cgroups to determine if a cpuset is usable; cpuset_mutex held */ -static int cpuset_can_attach(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset) +static int cpuset_can_attach(struct cgroup_taskset *tset) { - struct cpuset *cs = css_cs(css); + struct cgroup_subsys_state *css; + struct cpuset *cs; struct task_struct *task; int ret; /* used later by cpuset_attach() */ - cpuset_attach_old_cs = task_cs(cgroup_taskset_first(tset)); + cpuset_attach_old_cs = task_cs(cgroup_taskset_first(tset, &css)); + cs = css_cs(css); mutex_lock(&cpuset_mutex); @@ -1447,7 +1448,7 @@ static int cpuset_can_attach(struct cgroup_subsys_state *css, (cpumask_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed))) goto out_unlock; - cgroup_taskset_for_each(task, tset) { + cgroup_taskset_for_each(task, css, tset) { ret = task_can_attach(task, cs->cpus_allowed); if (ret) goto out_unlock; @@ -1467,9 +1468,14 @@ out_unlock: return ret; } -static void cpuset_cancel_attach(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset) +static void cpuset_cancel_attach(struct cgroup_taskset *tset) { + struct cgroup_subsys_state *css; + struct cpuset *cs; + + cgroup_taskset_first(tset, &css); + cs = css_cs(css); + mutex_lock(&cpuset_mutex); css_cs(css)->attach_in_progress--; mutex_unlock(&cpuset_mutex); @@ -1482,16 +1488,19 @@ static void cpuset_cancel_attach(struct cgroup_subsys_state *css, */ static cpumask_var_t cpus_attach; -static void cpuset_attach(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset) +static void cpuset_attach(struct cgroup_taskset *tset) { /* static buf protected by cpuset_mutex */ static nodemask_t cpuset_attach_nodemask_to; struct task_struct *task; struct task_struct *leader; - struct cpuset *cs = css_cs(css); + struct cgroup_subsys_state *css; + struct cpuset *cs; struct cpuset *oldcs = cpuset_attach_old_cs; + cgroup_taskset_first(tset, &css); + cs = css_cs(css); + mutex_lock(&cpuset_mutex); /* prepare for attach */ @@ -1502,7 +1511,7 @@ static void cpuset_attach(struct cgroup_subsys_state *css, guarantee_online_mems(cs, &cpuset_attach_nodemask_to); - cgroup_taskset_for_each(task, tset) { + cgroup_taskset_for_each(task, css, tset) { /* * can_attach beforehand should guarantee that this doesn't * fail. TODO: have a better way to handle failure here @@ -1518,7 +1527,7 @@ static void cpuset_attach(struct cgroup_subsys_state *css, * sleep and should be moved outside migration path proper. */ cpuset_attach_nodemask_to = cs->effective_mems; - cgroup_taskset_for_each_leader(leader, tset) { + cgroup_taskset_for_each_leader(leader, css, tset) { struct mm_struct *mm = get_task_mm(leader); if (mm) { diff --git a/kernel/events/core.c b/kernel/events/core.c index 36babfd20648..026305dfe523 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -9456,12 +9456,12 @@ static int __perf_cgroup_move(void *info) return 0; } -static void perf_cgroup_attach(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset) +static void perf_cgroup_attach(struct cgroup_taskset *tset) { struct task_struct *task; + struct cgroup_subsys_state *css; - cgroup_taskset_for_each(task, tset) + cgroup_taskset_for_each(task, css, tset) task_function_call(task, __perf_cgroup_move, task); } diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 4d568ac9319e..a9db4819e586 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -8217,12 +8217,12 @@ static void cpu_cgroup_fork(struct task_struct *task, void *private) sched_move_task(task); } -static int cpu_cgroup_can_attach(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset) +static int cpu_cgroup_can_attach(struct cgroup_taskset *tset) { struct task_struct *task; + struct cgroup_subsys_state *css; - cgroup_taskset_for_each(task, tset) { + cgroup_taskset_for_each(task, css, tset) { #ifdef CONFIG_RT_GROUP_SCHED if (!sched_rt_can_attach(css_tg(css), task)) return -EINVAL; @@ -8235,12 +8235,12 @@ static int cpu_cgroup_can_attach(struct cgroup_subsys_state *css, return 0; } -static void cpu_cgroup_attach(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset) +static void cpu_cgroup_attach(struct cgroup_taskset *tset) { struct task_struct *task; + struct cgroup_subsys_state *css; - cgroup_taskset_for_each(task, tset) + cgroup_taskset_for_each(task, css, tset) sched_move_task(task); } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 9acfb165eb52..c92a65b2b4ab 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -4779,23 +4779,18 @@ static void mem_cgroup_clear_mc(void) spin_unlock(&mc.lock); } -static int mem_cgroup_can_attach(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset) +static int mem_cgroup_can_attach(struct cgroup_taskset *tset) { - struct mem_cgroup *memcg = mem_cgroup_from_css(css); + struct cgroup_subsys_state *css; + struct mem_cgroup *memcg; struct mem_cgroup *from; struct task_struct *leader, *p; struct mm_struct *mm; unsigned long move_flags; int ret = 0; - /* - * We are now commited to this value whatever it is. Changes in this - * tunable will only affect upcoming migrations, not the current one. - * So we need to save it, and keep it going. - */ - move_flags = READ_ONCE(memcg->move_charge_at_immigrate); - if (!move_flags) + /* charge immigration isn't supported on the default hierarchy */ + if (cgroup_subsys_on_dfl(memory_cgrp_subsys)) return 0; /* @@ -4805,13 +4800,23 @@ static int mem_cgroup_can_attach(struct cgroup_subsys_state *css, * multiple. */ p = NULL; - cgroup_taskset_for_each_leader(leader, tset) { + cgroup_taskset_for_each_leader(leader, css, tset) { WARN_ON_ONCE(p); p = leader; + memcg = mem_cgroup_from_css(css); } if (!p) return 0; + /* + * We are now commited to this value whatever it is. Changes in this + * tunable will only affect upcoming migrations, not the current one. + * So we need to save it, and keep it going. + */ + move_flags = READ_ONCE(memcg->move_charge_at_immigrate); + if (!move_flags) + return 0; + from = mem_cgroup_from_task(p); VM_BUG_ON(from == memcg); @@ -4842,8 +4847,7 @@ static int mem_cgroup_can_attach(struct cgroup_subsys_state *css, return ret; } -static void mem_cgroup_cancel_attach(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset) +static void mem_cgroup_cancel_attach(struct cgroup_taskset *tset) { if (mc.to) mem_cgroup_clear_mc(); @@ -4985,10 +4989,10 @@ retry: atomic_dec(&mc.from->moving_account); } -static void mem_cgroup_move_task(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset) +static void mem_cgroup_move_task(struct cgroup_taskset *tset) { - struct task_struct *p = cgroup_taskset_first(tset); + struct cgroup_subsys_state *css; + struct task_struct *p = cgroup_taskset_first(tset, &css); struct mm_struct *mm = get_task_mm(p); if (mm) { @@ -5000,17 +5004,14 @@ static void mem_cgroup_move_task(struct cgroup_subsys_state *css, mem_cgroup_clear_mc(); } #else /* !CONFIG_MMU */ -static int mem_cgroup_can_attach(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset) +static int mem_cgroup_can_attach(struct cgroup_taskset *tset) { return 0; } -static void mem_cgroup_cancel_attach(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset) +static void mem_cgroup_cancel_attach(struct cgroup_taskset *tset) { } -static void mem_cgroup_move_task(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset) +static void mem_cgroup_move_task(struct cgroup_taskset *tset) { } #endif diff --git a/net/core/netclassid_cgroup.c b/net/core/netclassid_cgroup.c index 6441f47b1a8f..81cb3c72efe8 100644 --- a/net/core/netclassid_cgroup.c +++ b/net/core/netclassid_cgroup.c @@ -67,14 +67,15 @@ static int update_classid(const void *v, struct file *file, unsigned n) return 0; } -static void cgrp_attach(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset) +static void cgrp_attach(struct cgroup_taskset *tset) { - struct cgroup_cls_state *cs = css_cls_state(css); - void *v = (void *)(unsigned long)cs->classid; struct task_struct *p; + struct cgroup_subsys_state *css; + + cgroup_taskset_for_each(p, css, tset) { + struct cgroup_cls_state *cs = css_cls_state(css); + void *v = (void *)(unsigned long)cs->classid; - cgroup_taskset_for_each(p, tset) { task_lock(p); iterate_fd(p->files, 0, update_classid, v); task_unlock(p); diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c index cbd0a199bf52..40fd09fe06ae 100644 --- a/net/core/netprio_cgroup.c +++ b/net/core/netprio_cgroup.c @@ -218,13 +218,14 @@ static int update_netprio(const void *v, struct file *file, unsigned n) return 0; } -static void net_prio_attach(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset) +static void net_prio_attach(struct cgroup_taskset *tset) { struct task_struct *p; - void *v = (void *)(unsigned long)css->cgroup->id; + struct cgroup_subsys_state *css; + + cgroup_taskset_for_each(p, css, tset) { + void *v = (void *)(unsigned long)css->cgroup->id; - cgroup_taskset_for_each(p, tset) { task_lock(p); iterate_fd(p->files, 0, update_netprio, v); task_unlock(p); -- cgit v1.2.3 From 642c2d671ceff40e9453203ea0c66e991e11e249 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 30 Nov 2015 12:56:15 +0100 Subject: perf: Fix PERF_EVENT_IOC_PERIOD deadlock Dmitry reported a fairly silly recursive lock deadlock for PERF_EVENT_IOC_PERIOD, fix this by explicitly doing the inactive part of __perf_event_period() instead of calling that function. Reported-by: Dmitry Vyukov Signed-off-by: Peter Zijlstra (Intel) Cc: Cc: Alexander Potapenko Cc: Arnaldo Carvalho de Melo Cc: Arnaldo Carvalho de Melo Cc: Eric Dumazet Cc: Jiri Olsa Cc: Kostya Serebryany Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Sasha Levin Cc: Stephane Eranian Cc: Thomas Gleixner Cc: Vince Weaver Fixes: c7999c6f3fed ("perf: Fix PERF_EVENT_IOC_PERIOD migration race") Link: http://lkml.kernel.org/r/20151130115615.GJ17308@twins.programming.kicks-ass.net Signed-off-by: Ingo Molnar --- kernel/events/core.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'kernel/events') diff --git a/kernel/events/core.c b/kernel/events/core.c index 5854fcf7f05a..49a5118f3564 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -4225,7 +4225,14 @@ retry: goto retry; } - __perf_event_period(&pe); + if (event->attr.freq) { + event->attr.sample_freq = value; + } else { + event->attr.sample_period = value; + event->hw.sample_period = value; + } + + local64_set(&event->hw.period_left, 0); raw_spin_unlock_irq(&ctx->lock); return 0; -- cgit v1.2.3 From 4e93ad601a4308d4a67673c81556580817d56940 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 4 Nov 2015 16:00:05 +0100 Subject: perf: Do not send exit event twice In case we monitor events system wide, we get EXIT event (when configured) twice for each task that exited. Note doubled lines with same pid/tid in following example: $ sudo ./perf record -a ^C[ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.480 MB perf.data (2518 samples) ] $ sudo ./perf report -D | grep EXIT 0 60290687567581 0x59910 [0x38]: PERF_RECORD_EXIT(1250:1250):(1250:1250) 0 60290687568354 0x59948 [0x38]: PERF_RECORD_EXIT(1250:1250):(1250:1250) 0 60290687988744 0x59ad8 [0x38]: PERF_RECORD_EXIT(1250:1250):(1250:1250) 0 60290687989198 0x59b10 [0x38]: PERF_RECORD_EXIT(1250:1250):(1250:1250) 1 60290692567895 0x62af0 [0x38]: PERF_RECORD_EXIT(1253:1253):(1253:1253) 1 60290692568322 0x62b28 [0x38]: PERF_RECORD_EXIT(1253:1253):(1253:1253) 2 60290692739276 0x69a18 [0x38]: PERF_RECORD_EXIT(1252:1252):(1252:1252) 2 60290692739910 0x69a50 [0x38]: PERF_RECORD_EXIT(1252:1252):(1252:1252) The reason is that the cpu contexts are processes each time we call perf_event_task. I'm changing the perf_event_aux logic to serve task_ctx and cpu contexts separately, which ensure we don't get EXIT event generated twice on same cpu context. This does not affect other auxiliary events, as they don't use task_ctx at all. Signed-off-by: Jiri Olsa Signed-off-by: Peter Zijlstra (Intel) Cc: Arnaldo Carvalho de Melo Cc: Arnaldo Carvalho de Melo Cc: David Ahern Cc: Jiri Olsa Cc: Linus Torvalds Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Thomas Gleixner Cc: Vince Weaver Link: http://lkml.kernel.org/r/1446649205-5822-1-git-send-email-jolsa@kernel.org Signed-off-by: Ingo Molnar --- kernel/events/core.c | 42 +++++++++++++++++++++++++++++++----------- 1 file changed, 31 insertions(+), 11 deletions(-) (limited to 'kernel/events') diff --git a/kernel/events/core.c b/kernel/events/core.c index 49a5118f3564..39cf4a40aa4c 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -5682,6 +5682,17 @@ perf_event_aux_ctx(struct perf_event_context *ctx, } } +static void +perf_event_aux_task_ctx(perf_event_aux_output_cb output, void *data, + struct perf_event_context *task_ctx) +{ + rcu_read_lock(); + preempt_disable(); + perf_event_aux_ctx(task_ctx, output, data); + preempt_enable(); + rcu_read_unlock(); +} + static void perf_event_aux(perf_event_aux_output_cb output, void *data, struct perf_event_context *task_ctx) @@ -5691,14 +5702,23 @@ perf_event_aux(perf_event_aux_output_cb output, void *data, struct pmu *pmu; int ctxn; + /* + * If we have task_ctx != NULL we only notify + * the task context itself. The task_ctx is set + * only for EXIT events before releasing task + * context. + */ + if (task_ctx) { + perf_event_aux_task_ctx(output, data, task_ctx); + return; + } + rcu_read_lock(); list_for_each_entry_rcu(pmu, &pmus, entry) { cpuctx = get_cpu_ptr(pmu->pmu_cpu_context); if (cpuctx->unique_pmu != pmu) goto next; perf_event_aux_ctx(&cpuctx->ctx, output, data); - if (task_ctx) - goto next; ctxn = pmu->task_ctx_nr; if (ctxn < 0) goto next; @@ -5708,12 +5728,6 @@ perf_event_aux(perf_event_aux_output_cb output, void *data, next: put_cpu_ptr(pmu->pmu_cpu_context); } - - if (task_ctx) { - preempt_disable(); - perf_event_aux_ctx(task_ctx, output, data); - preempt_enable(); - } rcu_read_unlock(); } @@ -8803,10 +8817,8 @@ static void perf_event_exit_task_context(struct task_struct *child, int ctxn) struct perf_event_context *child_ctx, *clone_ctx = NULL; unsigned long flags; - if (likely(!child->perf_event_ctxp[ctxn])) { - perf_event_task(child, NULL, 0); + if (likely(!child->perf_event_ctxp[ctxn])) return; - } local_irq_save(flags); /* @@ -8890,6 +8902,14 @@ void perf_event_exit_task(struct task_struct *child) for_each_task_context_nr(ctxn) perf_event_exit_task_context(child, ctxn); + + /* + * The perf_event_exit_task_context calls perf_event_task + * with child's task_ctx, which generates EXIT events for + * child contexts and sets child->perf_event_ctxp[] to NULL. + * At this point we need to send EXIT events to cpu contexts. + */ + perf_event_task(child, NULL, 0); } static void perf_free_event(struct perf_event *event, -- cgit v1.2.3