From 34c06254ff82a815fdccdfae7517a06c9b768cee Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 5 Nov 2015 00:12:24 -0500 Subject: cgroup: fix cftype->file_offset handling 6f60eade2433 ("cgroup: generalize obtaining the handles of and notifying cgroup files") introduced cftype->file_offset so that the handles for per-css file instances can be recorded. These handles then can be used, for example, to generate file modified notifications. Unfortunately, it made the wrong assumption that files are created once for a given css and removed on its destruction. Due to the dependencies among subsystems, a css may be hidden from userland and then later shown again. This is implemented by removing and re-creating the affected files, so the associated kernfs_node for a given cgroup file may change over time. This incorrect assumption led to the corruption of css->files lists. Reimplement cftype->file_offset handling so that cgroup_file->kn is protected by a lock and updated as files are created and destroyed. This also makes keeping them on per-cgroup list unnecessary. Signed-off-by: Tejun Heo Reported-by: James Sedgwick Fixes: 6f60eade2433 ("cgroup: generalize obtaining the handles of and notifying cgroup files") Acked-by: Johannes Weiner Acked-by: Zefan Li --- kernel/cgroup.c | 42 ++++++++++++++++++++++++++++++++++-------- 1 file changed, 34 insertions(+), 8 deletions(-) (limited to 'kernel') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index f1603c153890..b316debadeb3 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -97,6 +97,12 @@ static DEFINE_SPINLOCK(css_set_lock); */ static DEFINE_SPINLOCK(cgroup_idr_lock); +/* + * Protects cgroup_file->kn for !self csses. It synchronizes notifications + * against file removal/re-creation across css hiding. + */ +static DEFINE_SPINLOCK(cgroup_file_kn_lock); + /* * Protects cgroup_subsys->release_agent_path. Modifying it also requires * cgroup_mutex. Reading requires either cgroup_mutex or this spinlock. @@ -1393,6 +1399,16 @@ static void cgroup_rm_file(struct cgroup *cgrp, const struct cftype *cft) char name[CGROUP_FILE_NAME_MAX]; lockdep_assert_held(&cgroup_mutex); + + if (cft->file_offset) { + struct cgroup_subsys_state *css = cgroup_css(cgrp, cft->ss); + struct cgroup_file *cfile = (void *)css + cft->file_offset; + + spin_lock_irq(&cgroup_file_kn_lock); + cfile->kn = NULL; + spin_unlock_irq(&cgroup_file_kn_lock); + } + kernfs_remove_by_name(cgrp->kn, cgroup_file_name(cgrp, cft, name)); } @@ -1856,7 +1872,6 @@ static void init_cgroup_housekeeping(struct cgroup *cgrp) INIT_LIST_HEAD(&cgrp->self.sibling); INIT_LIST_HEAD(&cgrp->self.children); - INIT_LIST_HEAD(&cgrp->self.files); INIT_LIST_HEAD(&cgrp->cset_links); INIT_LIST_HEAD(&cgrp->pidlists); mutex_init(&cgrp->pidlist_mutex); @@ -3313,9 +3328,9 @@ static int cgroup_add_file(struct cgroup_subsys_state *css, struct cgroup *cgrp, if (cft->file_offset) { struct cgroup_file *cfile = (void *)css + cft->file_offset; - kernfs_get(kn); + spin_lock_irq(&cgroup_file_kn_lock); cfile->kn = kn; - list_add(&cfile->node, &css->files); + spin_unlock_irq(&cgroup_file_kn_lock); } return 0; @@ -3552,6 +3567,22 @@ int cgroup_add_legacy_cftypes(struct cgroup_subsys *ss, struct cftype *cfts) return cgroup_add_cftypes(ss, cfts); } +/** + * cgroup_file_notify - generate a file modified event for a cgroup_file + * @cfile: target cgroup_file + * + * @cfile must have been obtained by setting cftype->file_offset. + */ +void cgroup_file_notify(struct cgroup_file *cfile) +{ + unsigned long flags; + + spin_lock_irqsave(&cgroup_file_kn_lock, flags); + if (cfile->kn) + kernfs_notify(cfile->kn); + spin_unlock_irqrestore(&cgroup_file_kn_lock, flags); +} + /** * cgroup_task_count - count the number of tasks in a cgroup. * @cgrp: the cgroup in question @@ -4613,13 +4644,9 @@ static void css_free_work_fn(struct work_struct *work) container_of(work, struct cgroup_subsys_state, destroy_work); struct cgroup_subsys *ss = css->ss; struct cgroup *cgrp = css->cgroup; - struct cgroup_file *cfile; percpu_ref_exit(&css->refcnt); - list_for_each_entry(cfile, &css->files, node) - kernfs_put(cfile->kn); - if (ss) { /* css free path */ int id = css->id; @@ -4724,7 +4751,6 @@ static void init_and_link_css(struct cgroup_subsys_state *css, css->ss = ss; INIT_LIST_HEAD(&css->sibling); INIT_LIST_HEAD(&css->children); - INIT_LIST_HEAD(&css->files); css->serial_nr = css_serial_nr_next++; if (cgroup_parent(cgrp)) { -- cgit v1.2.2 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') 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 v1.2.2 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 --- kernel/events/core.c | 20 +++++++++++++------- 1 file changed, 13 insertions(+), 7 deletions(-) (limited to 'kernel') 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 v1.2.2 From 89b411081d70fe3772efa4665279293269c1150d Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 12 Nov 2015 17:19:58 +0100 Subject: sched/rt: Hide the push_irq_work_func() declaration The push_irq_work_func() function is conditionally defined only when both CONFIG_SMP and HAVE_RT_PUSH_IPI are defined, but the forward declaration remains visibile without HAVE_RT_PUSH_IPI, causing a gcc warning in ARM64 allnoconfig: kernel/sched/rt.c:68:13: warning: 'push_irq_work_func' declared 'static' but never defined [-Wunused-function] This changes the code to use the same condition for both the declaration and the function definition, which gets rid of the warning. As Peter Zijlstra, we can possibly get rid of the whole HAVE_RT_PUSH_IPI thing after: 8053871d0f7f ("smp: Fix smp_call_function_single_async() locking") Until that is done, this patch can be used to avoid the warning. Signed-off-by: Arnd Bergmann Signed-off-by: Peter Zijlstra (Intel) Acked-by: Steven Rostedt Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Fixes: b6366f048e0c ("sched/rt: Use IPI to trigger RT task push migration instead of pulling") Link: http://lkml.kernel.org/r/3828565.oKfGk7yNIT@wuerfel Signed-off-by: Ingo Molnar --- kernel/sched/rt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index e3cc16312046..8ec86abe0ea1 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -64,7 +64,7 @@ static void start_rt_bandwidth(struct rt_bandwidth *rt_b) raw_spin_unlock(&rt_b->rt_runtime_lock); } -#ifdef CONFIG_SMP +#if defined(CONFIG_SMP) && defined(HAVE_RT_PUSH_IPI) static void push_irq_work_func(struct irq_work *work); #endif -- cgit v1.2.2 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 --- 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 +- 11 files changed, 11 insertions(+), 11 deletions(-) (limited to 'kernel') 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 */ -- cgit v1.2.2 From b81f472a208d3e2b4392faa6d17037a89442f4ce Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Mon, 23 Nov 2015 10:35:36 -0500 Subject: ring-buffer: Update read stamp with first real commit on page Do not update the read stamp after swapping out the reader page from the write buffer. If the reader page is swapped out of the buffer before an event is written to it, then the read_stamp may get an out of date timestamp, as the page timestamp is updated on the first commit to that page. rb_get_reader_page() only returns a page if it has an event on it, otherwise it will return NULL. At that point, check if the page being returned has events and has not been read yet. Then at that point update the read_stamp to match the time stamp of the reader page. Cc: stable@vger.kernel.org # 2.6.30+ Signed-off-by: Steven Rostedt --- kernel/trace/ring_buffer.c | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 75f1d05ea82d..4dd6d5bc4e11 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -1887,12 +1887,6 @@ rb_event_index(struct ring_buffer_event *event) return (addr & ~PAGE_MASK) - BUF_PAGE_HDR_SIZE; } -static void rb_reset_reader_page(struct ring_buffer_per_cpu *cpu_buffer) -{ - cpu_buffer->read_stamp = cpu_buffer->reader_page->page->time_stamp; - cpu_buffer->reader_page->read = 0; -} - static void rb_inc_iter(struct ring_buffer_iter *iter) { struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer; @@ -3626,7 +3620,7 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer) /* Finally update the reader page to the new head */ cpu_buffer->reader_page = reader; - rb_reset_reader_page(cpu_buffer); + cpu_buffer->reader_page->read = 0; if (overwrite != cpu_buffer->last_overrun) { cpu_buffer->lost_events = overwrite - cpu_buffer->last_overrun; @@ -3636,6 +3630,10 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer) goto again; out: + /* Update the read_stamp on the first event */ + if (reader && reader->read == 0) + cpu_buffer->read_stamp = reader->page->time_stamp; + arch_spin_unlock(&cpu_buffer->lock); local_irq_restore(flags); -- cgit v1.2.2 From bd1b7cd360f529394936f28746eb4aaa12d6770a Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Mon, 23 Nov 2015 17:35:24 -0500 Subject: ring-buffer: Put back the length if crossed page with add_timestamp Commit fcc742eaad7c "ring-buffer: Add event descriptor to simplify passing data" added a descriptor that holds various data instead of passing around several variables through parameters. The problem was that one of the parameters was modified in a function and the code was designed not to have an effect on that modified parameter. Now that the parameter is a descriptor and any modifications to it are non-volatile, the size of the data could be unnecessarily expanded. Remove the extra space added if a timestamp was added and the event went across the page. Cc: stable@vger.kernel.org # 4.3+ Fixes: fcc742eaad7c "ring-buffer: Add event descriptor to simplify passing data" Signed-off-by: Steven Rostedt --- kernel/trace/ring_buffer.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 4dd6d5bc4e11..9c6045a27ba3 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -2797,8 +2797,11 @@ rb_reserve_next_event(struct ring_buffer *buffer, event = __rb_reserve_next(cpu_buffer, &info); - if (unlikely(PTR_ERR(event) == -EAGAIN)) + if (unlikely(PTR_ERR(event) == -EAGAIN)) { + if (info.add_timestamp) + info.length -= RB_LEN_TIME_EXTEND; goto again; + } if (!event) goto out_fail; -- cgit v1.2.2 From 81b1a832d79749058863cffe2c0ed4ef40f6e6ec Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 24 Nov 2015 11:39:54 -0800 Subject: pidns: fix NULL dereference in __task_pid_nr_ns() I got a crash during a "perf top" session that was caused by a race in __task_pid_nr_ns() : pid_nr_ns() was inlined, but apparently compiler chose to read task->pids[type].pid twice, and the pid->level dereference crashed because we got a NULL pointer at the second read : if (pid && ns->level <= pid->level) { // CRASH Just use RCU API properly to solve this race, and not worry about "perf top" crashing hosts :( get_task_pid() can benefit from same fix. Signed-off-by: Eric Dumazet Signed-off-by: Linus Torvalds --- kernel/pid.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/pid.c b/kernel/pid.c index ca368793808e..78b3d9f80d44 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -467,7 +467,7 @@ struct pid *get_task_pid(struct task_struct *task, enum pid_type type) rcu_read_lock(); if (type != PIDTYPE_PID) task = task->group_leader; - pid = get_pid(task->pids[type].pid); + pid = get_pid(rcu_dereference(task->pids[type].pid)); rcu_read_unlock(); return pid; } @@ -528,7 +528,7 @@ pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type, if (likely(pid_alive(task))) { if (type != PIDTYPE_PID) task = task->group_leader; - nr = pid_nr_ns(task->pids[type].pid, ns); + nr = pid_nr_ns(rcu_dereference(task->pids[type].pid), ns); } rcu_read_unlock(); -- cgit v1.2.2 From c9da161c6517ba12154059d3b965c2cbaf16f90f Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 24 Nov 2015 21:28:15 +0100 Subject: bpf: fix clearing on persistent program array maps Currently, when having map file descriptors pointing to program arrays, there's still the issue that we unconditionally flush program array contents via bpf_fd_array_map_clear() in bpf_map_release(). This happens when such a file descriptor is released and is independent of the map's refcount. Having this flush independent of the refcount is for a reason: there can be arbitrary complex dependency chains among tail calls, also circular ones (direct or indirect, nesting limit determined during runtime), and we need to make sure that the map drops all references to eBPF programs it holds, so that the map's refcount can eventually drop to zero and initiate its freeing. Btw, a walk of the whole dependency graph would not be possible for various reasons, one being complexity and another one inconsistency, i.e. new programs can be added to parts of the graph at any time, so there's no guaranteed consistent state for the time of such a walk. Now, the program array pinning itself works, but the issue is that each derived file descriptor on close would nevertheless call unconditionally into bpf_fd_array_map_clear(). Instead, keep track of users and postpone this flush until the last reference to a user is dropped. As this only concerns a subset of references (f.e. a prog array could hold a program that itself has reference on the prog array holding it, etc), we need to track them separately. Short analysis on the refcounting: on map creation time usercnt will be one, so there's no change in behaviour for bpf_map_release(), if unpinned. If we already fail in map_create(), we are immediately freed, and no file descriptor has been made public yet. In bpf_obj_pin_user(), we need to probe for a possible map in bpf_fd_probe_obj() already with a usercnt reference, so before we drop the reference on the fd with fdput(). Therefore, if actual pinning fails, we need to drop that reference again in bpf_any_put(), otherwise we keep holding it. When last reference drops on the inode, the bpf_any_put() in bpf_evict_inode() will take care of dropping the usercnt again. In the bpf_obj_get_user() case, the bpf_any_get() will grab a reference on the usercnt, still at a time when we have the reference on the path. Should we later on fail to grab a new file descriptor, bpf_any_put() will drop it, otherwise we hold it until bpf_map_release() time. Joint work with Alexei. Fixes: b2197755b263 ("bpf: add support for persistent maps/progs") Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov Signed-off-by: David S. Miller --- kernel/bpf/inode.c | 6 +++--- kernel/bpf/syscall.c | 36 +++++++++++++++++++++++++----------- kernel/bpf/verifier.c | 3 +-- 3 files changed, 29 insertions(+), 16 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index be6d726e31c9..5a8a797d50b7 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -34,7 +34,7 @@ static void *bpf_any_get(void *raw, enum bpf_type type) atomic_inc(&((struct bpf_prog *)raw)->aux->refcnt); break; case BPF_TYPE_MAP: - atomic_inc(&((struct bpf_map *)raw)->refcnt); + bpf_map_inc(raw, true); break; default: WARN_ON_ONCE(1); @@ -51,7 +51,7 @@ static void bpf_any_put(void *raw, enum bpf_type type) bpf_prog_put(raw); break; case BPF_TYPE_MAP: - bpf_map_put(raw); + bpf_map_put_with_uref(raw); break; default: WARN_ON_ONCE(1); @@ -64,7 +64,7 @@ static void *bpf_fd_probe_obj(u32 ufd, enum bpf_type *type) void *raw; *type = BPF_TYPE_MAP; - raw = bpf_map_get(ufd); + raw = bpf_map_get_with_uref(ufd); if (IS_ERR(raw)) { *type = BPF_TYPE_PROG; raw = bpf_prog_get(ufd); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 0d3313d02a7e..4a8f3c1d7da6 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -82,6 +82,14 @@ static void bpf_map_free_deferred(struct work_struct *work) map->ops->map_free(map); } +static void bpf_map_put_uref(struct bpf_map *map) +{ + if (atomic_dec_and_test(&map->usercnt)) { + if (map->map_type == BPF_MAP_TYPE_PROG_ARRAY) + bpf_fd_array_map_clear(map); + } +} + /* decrement map refcnt and schedule it for freeing via workqueue * (unrelying map implementation ops->map_free() might sleep) */ @@ -93,17 +101,15 @@ void bpf_map_put(struct bpf_map *map) } } -static int bpf_map_release(struct inode *inode, struct file *filp) +void bpf_map_put_with_uref(struct bpf_map *map) { - struct bpf_map *map = filp->private_data; - - if (map->map_type == BPF_MAP_TYPE_PROG_ARRAY) - /* prog_array stores refcnt-ed bpf_prog pointers - * release them all when user space closes prog_array_fd - */ - bpf_fd_array_map_clear(map); - + bpf_map_put_uref(map); bpf_map_put(map); +} + +static int bpf_map_release(struct inode *inode, struct file *filp) +{ + bpf_map_put_with_uref(filp->private_data); return 0; } @@ -142,6 +148,7 @@ static int map_create(union bpf_attr *attr) return PTR_ERR(map); atomic_set(&map->refcnt, 1); + atomic_set(&map->usercnt, 1); err = bpf_map_charge_memlock(map); if (err) @@ -174,7 +181,14 @@ struct bpf_map *__bpf_map_get(struct fd f) return f.file->private_data; } -struct bpf_map *bpf_map_get(u32 ufd) +void bpf_map_inc(struct bpf_map *map, bool uref) +{ + atomic_inc(&map->refcnt); + if (uref) + atomic_inc(&map->usercnt); +} + +struct bpf_map *bpf_map_get_with_uref(u32 ufd) { struct fd f = fdget(ufd); struct bpf_map *map; @@ -183,7 +197,7 @@ struct bpf_map *bpf_map_get(u32 ufd) if (IS_ERR(map)) return map; - atomic_inc(&map->refcnt); + bpf_map_inc(map, true); fdput(f); return map; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index c6073056badf..a7945d10b378 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -2021,8 +2021,7 @@ static int replace_map_fd_with_map_ptr(struct verifier_env *env) * will be used by the valid program until it's unloaded * and all maps are released in free_bpf_prog_info() */ - atomic_inc(&map->refcnt); - + bpf_map_inc(map, false); fdput(f); next_insn: insn++; -- cgit v1.2.2 From 53254f900bd9ff1e3cc5628e76126bb403d9d160 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 23 Nov 2015 14:55:41 -0500 Subject: cgroup: make css_set pin its css's to avoid use-afer-free A css_set represents the relationship between a set of tasks and css's. css_set never pinned the associated css's. This was okay because tasks used to always disassociate immediately (in RCU sense) - either a task is moved to a different css_set or exits and never accesses css_set again. Unfortunately, afcf6c8b7544 ("cgroup: add cgroup_subsys->free() method and use it to fix pids controller") and patches leading up to it made a zombie hold onto its css_set and deref the associated css's on its release. Nothing pins the css's after exit and it might have already been freed leading to use-after-free. general protection fault: 0000 [#1] PREEMPT SMP task: ffffffff81bf2500 ti: ffffffff81be4000 task.ti: ffffffff81be4000 RIP: 0010:[] [] pids_cancel.constprop.4+0x5/0x40 ... Call Trace: [] ? pids_free+0x3d/0xa0 [] cgroup_free+0x53/0xe0 [] __put_task_struct+0x42/0x130 [] delayed_put_task_struct+0x77/0x130 [] rcu_process_callbacks+0x2f4/0x820 [] ? rcu_process_callbacks+0x2b3/0x820 [] __do_softirq+0xd4/0x460 [] irq_exit+0x89/0xa0 [] smp_apic_timer_interrupt+0x42/0x50 [] apic_timer_interrupt+0x84/0x90 ... Code: 5b 5d c3 48 89 df 48 c7 c2 c9 f9 ae 81 48 c7 c6 91 2c ae 81 e8 1d 94 0e 00 31 c0 5b 5d c3 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 48 83 87 e0 00 00 00 ff 78 01 c3 80 3d 08 7a c1 00 00 74 02 RIP [] pids_cancel.constprop.4+0x5/0x40 RSP ---[ end trace 89a4a4b916b90c49 ]--- Kernel panic - not syncing: Fatal exception in interrupt Kernel Offset: disabled ---[ end Kernel panic - not syncing: Fatal exception in interrupt Fix it by making css_set pin the associate css's until its release. Signed-off-by: Tejun Heo Reported-by: Dave Jones Reported-by: Daniel Wagner Link: http://lkml.kernel.org/g/20151120041836.GA18390@codemonkey.org.uk Link: http://lkml.kernel.org/g/5652D448.3080002@bmw-carit.de Fixes: afcf6c8b7544 ("cgroup: add cgroup_subsys->free() method and use it to fix pids controller") --- kernel/cgroup.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index b316debadeb3..5cea63fe4095 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -760,9 +760,11 @@ static void put_css_set_locked(struct css_set *cset) if (!atomic_dec_and_test(&cset->refcount)) return; - /* This css_set is dead. unlink it and release cgroup refcounts */ - for_each_subsys(ss, ssid) + /* This css_set is dead. unlink it and release cgroup and css refs */ + for_each_subsys(ss, ssid) { list_del(&cset->e_cset_node[ssid]); + css_put(cset->subsys[ssid]); + } hash_del(&cset->hlist); css_set_count--; @@ -1062,9 +1064,13 @@ static struct css_set *find_css_set(struct css_set *old_cset, key = css_set_hash(cset->subsys); hash_add(css_set_table, &cset->hlist, key); - for_each_subsys(ss, ssid) + for_each_subsys(ss, ssid) { + struct cgroup_subsys_state *css = cset->subsys[ssid]; + list_add_tail(&cset->e_cset_node[ssid], - &cset->subsys[ssid]->cgroup->e_csets[ssid]); + &css->cgroup->e_csets[ssid]); + css_get(css); + } spin_unlock_bh(&css_set_lock); -- cgit v1.2.2 From c9e75f0492b248aeaa7af8991a6fc9a21506bc96 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Fri, 27 Nov 2015 19:57:19 +0100 Subject: cgroup: pids: fix race between cgroup_post_fork() and cgroup_migrate() If the new child migrates to another cgroup before cgroup_post_fork() calls subsys->fork(), then both pids_can_attach() and pids_fork() will do the same pids_uncharge(old_pids) + pids_charge(pids) sequence twice. Change copy_process() to call threadgroup_change_begin/threadgroup_change_end unconditionally. percpu_down_read() is cheap and this allows other cleanups, see the next changes. Also, this way we can unify cgroup_threadgroup_rwsem and dup_mmap_sem. Signed-off-by: Oleg Nesterov Acked-by: Zefan Li Signed-off-by: Tejun Heo --- kernel/cgroup_pids.c | 21 ++------------------- kernel/fork.c | 9 +++------ 2 files changed, 5 insertions(+), 25 deletions(-) (limited to 'kernel') diff --git a/kernel/cgroup_pids.c b/kernel/cgroup_pids.c index cdd8df4e991c..15ef2e46c396 100644 --- a/kernel/cgroup_pids.c +++ b/kernel/cgroup_pids.c @@ -243,27 +243,10 @@ static void pids_cancel_fork(struct task_struct *task, void *priv) static void pids_fork(struct task_struct *task, void *priv) { - struct cgroup_subsys_state *css; - struct cgroup_subsys_state *old_css = priv; - struct pids_cgroup *pids; - struct pids_cgroup *old_pids = css_pids(old_css); - - css = task_get_css(task, pids_cgrp_id); - pids = css_pids(css); - - /* - * If the association has changed, we have to revert and reapply the - * charge/uncharge on the wrong hierarchy to the current one. Since - * the association can only change due to an organisation event, its - * okay for us to ignore the limit in this case. - */ - if (pids != old_pids) { - pids_uncharge(old_pids, 1); - pids_charge(pids, 1); - } + struct cgroup_subsys_state *css = priv; + WARN_ON(task_css_check(task, pids_cgrp_id, true) != css); css_put(css); - css_put(old_css); } static void pids_free(struct task_struct *task) diff --git a/kernel/fork.c b/kernel/fork.c index f97f2c449f5c..fce002ee3ddf 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1368,8 +1368,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, p->real_start_time = ktime_get_boot_ns(); p->io_context = NULL; p->audit_context = NULL; - if (clone_flags & CLONE_THREAD) - threadgroup_change_begin(current); + threadgroup_change_begin(current); cgroup_fork(p); #ifdef CONFIG_NUMA p->mempolicy = mpol_dup(p->mempolicy); @@ -1610,8 +1609,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, proc_fork_connector(p); cgroup_post_fork(p, cgrp_ss_priv); - if (clone_flags & CLONE_THREAD) - threadgroup_change_end(current); + threadgroup_change_end(current); perf_event_fork(p); trace_task_newtask(p, clone_flags); @@ -1652,8 +1650,7 @@ bad_fork_cleanup_policy: mpol_put(p->mempolicy); bad_fork_cleanup_threadgroup_lock: #endif - if (clone_flags & CLONE_THREAD) - threadgroup_change_end(current); + threadgroup_change_end(current); delayacct_tsk_free(p); bad_fork_cleanup_count: atomic_dec(&p->cred->user->processes); -- cgit v1.2.2 From afbcb364bee9e7cf46c94257a82cb9760b6d254f Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Fri, 27 Nov 2015 19:57:22 +0100 Subject: cgroup: pids: kill pids_fork(), simplify pids_can_fork() and pids_cancel_fork() Now that we know that the forking task can't migrate amd the child is always moved to the same cgroup by cgroup_post_fork()->css_set_move_task() we can change pids_can_fork() and pids_cancel_fork() to just use task_css(current). And since we no longer need to pin this css, we can remove pid_fork(). Note: the patch uses task_css_check(true), perhaps it makes sense to add a helper or change task_css_set_check() to take cgroup_threadgroup_rwsem into account. Signed-off-by: Oleg Nesterov Acked-by: Zefan Li Signed-off-by: Tejun Heo --- kernel/cgroup_pids.c | 41 ++++++++++------------------------------- 1 file changed, 10 insertions(+), 31 deletions(-) (limited to 'kernel') diff --git a/kernel/cgroup_pids.c b/kernel/cgroup_pids.c index 15ef2e46c396..de3359a48dbb 100644 --- a/kernel/cgroup_pids.c +++ b/kernel/cgroup_pids.c @@ -205,48 +205,28 @@ static void pids_cancel_attach(struct cgroup_subsys_state *css, } } +/* + * task_css_check(true) in pids_can_fork() and pids_cancel_fork() relies + * on threadgroup_change_begin() held by the copy_process(). + */ static int pids_can_fork(struct task_struct *task, void **priv_p) { struct cgroup_subsys_state *css; struct pids_cgroup *pids; - int err; - /* - * Use the "current" task_css for the pids subsystem as the tentative - * css. It is possible we will charge the wrong hierarchy, in which - * case we will forcefully revert/reapply the charge on the right - * hierarchy after it is committed to the task proper. - */ - css = task_get_css(current, pids_cgrp_id); + css = task_css_check(current, pids_cgrp_id, true); pids = css_pids(css); - - err = pids_try_charge(pids, 1); - if (err) - goto err_css_put; - - *priv_p = css; - return 0; - -err_css_put: - css_put(css); - return err; + return pids_try_charge(pids, 1); } static void pids_cancel_fork(struct task_struct *task, void *priv) { - struct cgroup_subsys_state *css = priv; - struct pids_cgroup *pids = css_pids(css); + struct cgroup_subsys_state *css; + struct pids_cgroup *pids; + css = task_css_check(current, pids_cgrp_id, true); + pids = css_pids(css); pids_uncharge(pids, 1); - css_put(css); -} - -static void pids_fork(struct task_struct *task, void *priv) -{ - struct cgroup_subsys_state *css = priv; - - WARN_ON(task_css_check(task, pids_cgrp_id, true) != css); - css_put(css); } static void pids_free(struct task_struct *task) @@ -329,7 +309,6 @@ struct cgroup_subsys pids_cgrp_subsys = { .cancel_attach = pids_cancel_attach, .can_fork = pids_can_fork, .cancel_fork = pids_cancel_fork, - .fork = pids_fork, .free = pids_free, .legacy_cftypes = pids_files, .dfl_cftypes = pids_files, -- cgit v1.2.2 From 0f72e37e42a8ce427caa1b96f7f51e450f2ecb82 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Tue, 1 Dec 2015 16:08:05 -0500 Subject: tracing: Add sched_wakeup_new and sched_waking tracepoints for pid filter The set_event_pid filter relies on attaching to the sched_switch and sched_wakeup tracepoints to see if it should filter the tracing on schedule tracepoints. By adding the callbacks to sched_wakeup, pids in the set_event_pid file will trace the wakeups of those tasks with those pids. But sched_wakeup_new and sched_waking were missed. These two should also be traced. Luckily, these tracepoints share the same class as sched_wakeup which means they can use the same pre and post callbacks as sched_wakeup does. Signed-off-by: Steven Rostedt --- kernel/trace/trace_events.c | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'kernel') diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 6bbc5f652355..4f6ef6912e00 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -582,6 +582,12 @@ static void __ftrace_clear_event_pids(struct trace_array *tr) unregister_trace_sched_wakeup(event_filter_pid_sched_wakeup_probe_pre, tr); unregister_trace_sched_wakeup(event_filter_pid_sched_wakeup_probe_post, tr); + unregister_trace_sched_wakeup_new(event_filter_pid_sched_wakeup_probe_pre, tr); + unregister_trace_sched_wakeup_new(event_filter_pid_sched_wakeup_probe_post, tr); + + unregister_trace_sched_waking(event_filter_pid_sched_wakeup_probe_pre, tr); + unregister_trace_sched_waking(event_filter_pid_sched_wakeup_probe_post, tr); + list_for_each_entry(file, &tr->events, list) { clear_bit(EVENT_FILE_FL_PID_FILTER_BIT, &file->flags); } @@ -1729,6 +1735,16 @@ ftrace_event_pid_write(struct file *filp, const char __user *ubuf, tr, INT_MAX); register_trace_prio_sched_wakeup(event_filter_pid_sched_wakeup_probe_post, tr, 0); + + register_trace_prio_sched_wakeup_new(event_filter_pid_sched_wakeup_probe_pre, + tr, INT_MAX); + register_trace_prio_sched_wakeup_new(event_filter_pid_sched_wakeup_probe_post, + tr, 0); + + register_trace_prio_sched_waking(event_filter_pid_sched_wakeup_probe_pre, + tr, INT_MAX); + register_trace_prio_sched_waking(event_filter_pid_sched_wakeup_probe_post, + tr, 0); } /* -- cgit v1.2.2 From fbca9d2d35c6ef1b323fae75cc9545005ba25097 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Mon, 30 Nov 2015 13:02:56 +0100 Subject: bpf, array: fix heap out-of-bounds access when updating elements During own review but also reported by Dmitry's syzkaller [1] it has been noticed that we trigger a heap out-of-bounds access on eBPF array maps when updating elements. This happens with each map whose map->value_size (specified during map creation time) is not multiple of 8 bytes. In array_map_alloc(), elem_size is round_up(attr->value_size, 8) and used to align array map slots for faster access. However, in function array_map_update_elem(), we update the element as ... memcpy(array->value + array->elem_size * index, value, array->elem_size); ... where we access 'value' out-of-bounds, since it was allocated from map_update_elem() from syscall side as kmalloc(map->value_size, GFP_USER) and later on copied through copy_from_user(value, uvalue, map->value_size). Thus, up to 7 bytes, we can access out-of-bounds. Same could happen from within an eBPF program, where in worst case we access beyond an eBPF program's designated stack. Since 1be7f75d1668 ("bpf: enable non-root eBPF programs") didn't hit an official release yet, it only affects priviledged users. In case of array_map_lookup_elem(), the verifier prevents eBPF programs from accessing beyond map->value_size through check_map_access(). Also from syscall side map_lookup_elem() only copies map->value_size back to user, so nothing could leak. [1] http://github.com/google/syzkaller Fixes: 28fbcfa08d8e ("bpf: add array type of eBPF maps") Reported-by: Dmitry Vyukov Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- kernel/bpf/arraymap.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 3f4c99e06c6b..4c67ce39732e 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -105,7 +105,7 @@ static int array_map_update_elem(struct bpf_map *map, void *key, void *value, /* all elements already exist */ return -EEXIST; - memcpy(array->value + array->elem_size * index, value, array->elem_size); + memcpy(array->value + array->elem_size * index, value, map->value_size); return 0; } -- cgit v1.2.2 From 01b3f52157ff5a47d6d8d796f396a4b34a53c61d Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Sun, 29 Nov 2015 16:59:35 -0800 Subject: bpf: fix allocation warnings in bpf maps and integer overflow For large map->value_size the user space can trigger memory allocation warnings like: WARNING: CPU: 2 PID: 11122 at mm/page_alloc.c:2989 __alloc_pages_nodemask+0x695/0x14e0() Call Trace: [< inline >] __dump_stack lib/dump_stack.c:15 [] dump_stack+0x68/0x92 lib/dump_stack.c:50 [] warn_slowpath_common+0xd9/0x140 kernel/panic.c:460 [] warn_slowpath_null+0x29/0x30 kernel/panic.c:493 [< inline >] __alloc_pages_slowpath mm/page_alloc.c:2989 [] __alloc_pages_nodemask+0x695/0x14e0 mm/page_alloc.c:3235 [] alloc_pages_current+0xee/0x340 mm/mempolicy.c:2055 [< inline >] alloc_pages include/linux/gfp.h:451 [] alloc_kmem_pages+0x16/0xf0 mm/page_alloc.c:3414 [] kmalloc_order+0x19/0x60 mm/slab_common.c:1007 [] kmalloc_order_trace+0x1f/0xa0 mm/slab_common.c:1018 [< inline >] kmalloc_large include/linux/slab.h:390 [] __kmalloc+0x234/0x250 mm/slub.c:3525 [< inline >] kmalloc include/linux/slab.h:463 [< inline >] map_update_elem kernel/bpf/syscall.c:288 [< inline >] SYSC_bpf kernel/bpf/syscall.c:744 To avoid never succeeding kmalloc with order >= MAX_ORDER check that elem->value_size and computed elem_size are within limits for both hash and array type maps. Also add __GFP_NOWARN to kmalloc(value_size | elem_size) to avoid OOM warnings. Note kmalloc(key_size) is highly unlikely to trigger OOM, since key_size <= 512, so keep those kmalloc-s as-is. Large value_size can cause integer overflows in elem_size and map.pages formulas, so check for that as well. Fixes: aaac3ba95e4c ("bpf: charge user for creation of BPF maps and programs") Reported-by: Dmitry Vyukov Signed-off-by: Alexei Starovoitov Signed-off-by: David S. Miller --- kernel/bpf/arraymap.c | 8 +++++++- kernel/bpf/hashtab.c | 34 +++++++++++++++++++++++++--------- kernel/bpf/syscall.c | 4 ++-- 3 files changed, 34 insertions(+), 12 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 4c67ce39732e..b0799bced518 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -28,11 +28,17 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr) attr->value_size == 0) return ERR_PTR(-EINVAL); + if (attr->value_size >= 1 << (KMALLOC_SHIFT_MAX - 1)) + /* if value_size is bigger, the user space won't be able to + * access the elements. + */ + return ERR_PTR(-E2BIG); + elem_size = round_up(attr->value_size, 8); /* check round_up into zero and u32 overflow */ if (elem_size == 0 || - attr->max_entries > (U32_MAX - sizeof(*array)) / elem_size) + attr->max_entries > (U32_MAX - PAGE_SIZE - sizeof(*array)) / elem_size) return ERR_PTR(-ENOMEM); array_size = sizeof(*array) + attr->max_entries * elem_size; diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 19909b22b4f8..34777b3746fa 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -64,12 +64,35 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) */ goto free_htab; - err = -ENOMEM; + if (htab->map.value_size >= (1 << (KMALLOC_SHIFT_MAX - 1)) - + MAX_BPF_STACK - sizeof(struct htab_elem)) + /* if value_size is bigger, the user space won't be able to + * access the elements via bpf syscall. This check also makes + * sure that the elem_size doesn't overflow and it's + * kmalloc-able later in htab_map_update_elem() + */ + goto free_htab; + + htab->elem_size = sizeof(struct htab_elem) + + round_up(htab->map.key_size, 8) + + htab->map.value_size; + /* prevent zero size kmalloc and check for u32 overflow */ if (htab->n_buckets == 0 || htab->n_buckets > U32_MAX / sizeof(struct hlist_head)) goto free_htab; + if ((u64) htab->n_buckets * sizeof(struct hlist_head) + + (u64) htab->elem_size * htab->map.max_entries >= + U32_MAX - PAGE_SIZE) + /* make sure page count doesn't overflow */ + goto free_htab; + + htab->map.pages = round_up(htab->n_buckets * sizeof(struct hlist_head) + + htab->elem_size * htab->map.max_entries, + PAGE_SIZE) >> PAGE_SHIFT; + + err = -ENOMEM; htab->buckets = kmalloc_array(htab->n_buckets, sizeof(struct hlist_head), GFP_USER | __GFP_NOWARN); @@ -85,13 +108,6 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) raw_spin_lock_init(&htab->lock); htab->count = 0; - htab->elem_size = sizeof(struct htab_elem) + - round_up(htab->map.key_size, 8) + - htab->map.value_size; - - htab->map.pages = round_up(htab->n_buckets * sizeof(struct hlist_head) + - htab->elem_size * htab->map.max_entries, - PAGE_SIZE) >> PAGE_SHIFT; return &htab->map; free_htab: @@ -222,7 +238,7 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value, WARN_ON_ONCE(!rcu_read_lock_held()); /* allocate new element outside of lock */ - l_new = kmalloc(htab->elem_size, GFP_ATOMIC); + l_new = kmalloc(htab->elem_size, GFP_ATOMIC | __GFP_NOWARN); if (!l_new) return -ENOMEM; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 4a8f3c1d7da6..3b39550d8485 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -240,7 +240,7 @@ static int map_lookup_elem(union bpf_attr *attr) goto free_key; err = -ENOMEM; - value = kmalloc(map->value_size, GFP_USER); + value = kmalloc(map->value_size, GFP_USER | __GFP_NOWARN); if (!value) goto free_key; @@ -299,7 +299,7 @@ static int map_update_elem(union bpf_attr *attr) goto free_key; err = -ENOMEM; - value = kmalloc(map->value_size, GFP_USER); + value = kmalloc(map->value_size, GFP_USER | __GFP_NOWARN); if (!value) goto free_key; -- cgit v1.2.2 From 599c963a0f19b14132065788322207eaa58bc7f8 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 3 Dec 2015 10:18:21 -0500 Subject: cgroup_freezer: simplify propagation of CGROUP_FROZEN clearing in freezer_attach() If one or more tasks get moved into a frozen css, the frozen state is cleared up from the destination css so that it can be reasserted once the migrated tasks are frozen. freezer_attach() implements this in two separate steps - clearing CGROUP_FROZEN on the target css while processing each task and propagating the clearing upwards after the task loop is done if necessary. This patch merges the two steps. Propagation now takes place inside the task loop. This simplifies the code and prepares it for the fix of multi-destination migration. Signed-off-by: Tejun Heo --- kernel/cgroup_freezer.c | 17 +++++++---------- 1 file changed, 7 insertions(+), 10 deletions(-) (limited to 'kernel') diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c index f1b30ad5dc6d..ff02a8e51bb3 100644 --- a/kernel/cgroup_freezer.c +++ b/kernel/cgroup_freezer.c @@ -158,9 +158,7 @@ static void freezer_css_free(struct cgroup_subsys_state *css) static void freezer_attach(struct cgroup_subsys_state *new_css, struct cgroup_taskset *tset) { - struct freezer *freezer = css_freezer(new_css); struct task_struct *task; - bool clear_frozen = false; mutex_lock(&freezer_mutex); @@ -175,21 +173,20 @@ static void freezer_attach(struct cgroup_subsys_state *new_css, * be visible in a FROZEN cgroup and frozen tasks in a THAWED one. */ cgroup_taskset_for_each(task, tset) { + struct freezer *freezer = css_freezer(new_css); + if (!(freezer->state & CGROUP_FREEZING)) { __thaw_task(task); } else { freeze_task(task); - freezer->state &= ~CGROUP_FROZEN; - clear_frozen = true; + /* clear FROZEN and propagate upwards */ + while (freezer && (freezer->state & CGROUP_FROZEN)) { + freezer->state &= ~CGROUP_FROZEN; + freezer = parent_freezer(freezer); + } } } - /* propagate FROZEN clearing upwards */ - while (clear_frozen && (freezer = parent_freezer(freezer))) { - freezer->state &= ~CGROUP_FROZEN; - clear_frozen = freezer->state & CGROUP_FREEZING; - } - mutex_unlock(&freezer_mutex); } -- cgit v1.2.2 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 --- 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 ++++++------ 6 files changed, 75 insertions(+), 41 deletions(-) (limited to 'kernel') 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); } -- cgit v1.2.2 From 67cde9c4938945b9510730c64e68d2f1dd7bc0aa Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 3 Dec 2015 10:18:21 -0500 Subject: cgroup_pids: don't account for the root cgroup Because accounting resources for the root cgroup sometimes incurs measureable overhead for workloads which don't care about cgroup and often ends up calculating a number which is available elsewhere in a slightly different form, cgroup is not in the business of providing system-wide statistics. The pids controller which was introduced recently was exposing "pids.current" at the root. This patch disable accounting for root cgroup and removes the file from the root directory. While this is a userland visible behavior change, pids has been available only in one version and was badly broken there, so I don't think this will be noticeable. If it turns out to be a problem, we can reinstate it for v1 hierarchies. Signed-off-by: Tejun Heo Cc: Aleksa Sarai --- kernel/cgroup_pids.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/cgroup_pids.c b/kernel/cgroup_pids.c index 8e27fc5dbb20..b50d5a167fda 100644 --- a/kernel/cgroup_pids.c +++ b/kernel/cgroup_pids.c @@ -106,7 +106,7 @@ static void pids_uncharge(struct pids_cgroup *pids, int num) { struct pids_cgroup *p; - for (p = pids; p; p = parent_pids(p)) + for (p = pids; parent_pids(p); p = parent_pids(p)) pids_cancel(p, num); } @@ -123,7 +123,7 @@ static void pids_charge(struct pids_cgroup *pids, int num) { struct pids_cgroup *p; - for (p = pids; p; p = parent_pids(p)) + for (p = pids; parent_pids(p); p = parent_pids(p)) atomic64_add(num, &p->counter); } @@ -140,7 +140,7 @@ static int pids_try_charge(struct pids_cgroup *pids, int num) { struct pids_cgroup *p, *q; - for (p = pids; p; p = parent_pids(p)) { + for (p = pids; parent_pids(p); p = parent_pids(p)) { int64_t new = atomic64_add_return(num, &p->counter); /* @@ -298,6 +298,7 @@ static struct cftype pids_files[] = { { .name = "current", .read_s64 = pids_current_read, + .flags = CFTYPE_NOT_ON_ROOT, }, { } /* terminate */ }; -- cgit v1.2.2 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') 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 v1.2.2 From 68985633bccb6066bf1803e316fbc6c1f5b796d6 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 1 Dec 2015 14:04:04 +0100 Subject: sched/wait: Fix signal handling in bit wait helpers Vladimir reported getting RCU stall warnings and bisected it back to commit: 743162013d40 ("sched: Remove proliferation of wait_on_bit() action functions") That commit inadvertently reversed the calls to schedule() and signal_pending(), thereby not handling the case where the signal receives while we sleep. Reported-by: Vladimir Murzin Tested-by: Vladimir Murzin Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: mark.rutland@arm.com Cc: neilb@suse.de Cc: oleg@redhat.com Fixes: 743162013d40 ("sched: Remove proliferation of wait_on_bit() action functions") Fixes: cbbce8220949 ("SCHED: add some "wait..on_bit...timeout()" interfaces.") Link: http://lkml.kernel.org/r/20151201130404.GL3816@twins.programming.kicks-ass.net Signed-off-by: Ingo Molnar --- kernel/sched/wait.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'kernel') diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c index 052e02672d12..f10bd873e684 100644 --- a/kernel/sched/wait.c +++ b/kernel/sched/wait.c @@ -583,18 +583,18 @@ EXPORT_SYMBOL(wake_up_atomic_t); __sched int bit_wait(struct wait_bit_key *word) { - if (signal_pending_state(current->state, current)) - return 1; schedule(); + if (signal_pending(current)) + return -EINTR; return 0; } EXPORT_SYMBOL(bit_wait); __sched int bit_wait_io(struct wait_bit_key *word) { - if (signal_pending_state(current->state, current)) - return 1; io_schedule(); + if (signal_pending(current)) + return -EINTR; return 0; } EXPORT_SYMBOL(bit_wait_io); @@ -602,11 +602,11 @@ EXPORT_SYMBOL(bit_wait_io); __sched int bit_wait_timeout(struct wait_bit_key *word) { unsigned long now = READ_ONCE(jiffies); - if (signal_pending_state(current->state, current)) - return 1; if (time_after_eq(now, word->timeout)) return -EAGAIN; schedule_timeout(word->timeout - now); + if (signal_pending(current)) + return -EINTR; return 0; } EXPORT_SYMBOL_GPL(bit_wait_timeout); @@ -614,11 +614,11 @@ EXPORT_SYMBOL_GPL(bit_wait_timeout); __sched int bit_wait_io_timeout(struct wait_bit_key *word) { unsigned long now = READ_ONCE(jiffies); - if (signal_pending_state(current->state, current)) - return 1; if (time_after_eq(now, word->timeout)) return -EAGAIN; io_schedule_timeout(word->timeout - now); + if (signal_pending(current)) + return -EINTR; return 0; } EXPORT_SYMBOL_GPL(bit_wait_io_timeout); -- cgit v1.2.2 From 119d6f6a3be8b424b200dcee56e74484d5445f7e Mon Sep 17 00:00:00 2001 From: Sasha Levin Date: Mon, 30 Nov 2015 20:34:20 -0500 Subject: sched/core: Remove false-positive warning from wake_up_process() Because wakeups can (fundamentally) be late, a task might not be in the expected state. Therefore testing against a task's state is racy, and can yield false positives. Signed-off-by: Sasha Levin Signed-off-by: Peter Zijlstra (Intel) Acked-by: Linus Torvalds Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: oleg@redhat.com Fixes: 9067ac85d533 ("wake_up_process() should be never used to wakeup a TASK_STOPPED/TRACED task") Link: http://lkml.kernel.org/r/1448933660-23082-1-git-send-email-sasha.levin@oracle.com Signed-off-by: Ingo Molnar --- kernel/sched/core.c | 1 - 1 file changed, 1 deletion(-) (limited to 'kernel') diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 4d568ac9319e..fc8c9879113c 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -2039,7 +2039,6 @@ out: */ int wake_up_process(struct task_struct *p) { - WARN_ON(task_is_stopped_or_traced(p)); return try_to_wake_up(p, TASK_NORMAL, 0); } EXPORT_SYMBOL(wake_up_process); -- cgit v1.2.2 From 8295c69925ad53ec32ca54ac9fc194ff21bc40e2 Mon Sep 17 00:00:00 2001 From: Xunlei Pang Date: Wed, 2 Dec 2015 19:52:59 +0800 Subject: sched/core: Clear the root_domain cpumasks in init_rootdomain() root_domain::rto_mask allocated through alloc_cpumask_var() contains garbage data, this may cause problems. For instance, When doing pull_rt_task(), it may do useless iterations if rto_mask retains some extra garbage bits. Worse still, this violates the isolated domain rule for clustered scheduling using cpuset, because the tasks(with all the cpus allowed) belongs to one root domain can be pulled away into another root domain. The patch cleans the garbage by using zalloc_cpumask_var() instead of alloc_cpumask_var() for root_domain::rto_mask allocation, thereby addressing the issues. Do the same thing for root_domain's other cpumask memembers: dlo_mask, span, and online. Signed-off-by: Xunlei Pang Signed-off-by: Peter Zijlstra (Intel) Cc: Cc: Linus Torvalds Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Steven Rostedt Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1449057179-29321-1-git-send-email-xlpang@redhat.com Signed-off-by: Ingo Molnar --- kernel/sched/core.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/sched/core.c b/kernel/sched/core.c index fc8c9879113c..eee4ee655db2 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -5846,13 +5846,13 @@ static int init_rootdomain(struct root_domain *rd) { memset(rd, 0, sizeof(*rd)); - if (!alloc_cpumask_var(&rd->span, GFP_KERNEL)) + if (!zalloc_cpumask_var(&rd->span, GFP_KERNEL)) goto out; - if (!alloc_cpumask_var(&rd->online, GFP_KERNEL)) + if (!zalloc_cpumask_var(&rd->online, GFP_KERNEL)) goto free_span; - if (!alloc_cpumask_var(&rd->dlo_mask, GFP_KERNEL)) + if (!zalloc_cpumask_var(&rd->dlo_mask, GFP_KERNEL)) goto free_online; - if (!alloc_cpumask_var(&rd->rto_mask, GFP_KERNEL)) + if (!zalloc_cpumask_var(&rd->rto_mask, GFP_KERNEL)) goto free_dlo_mask; init_dl_bw(&rd->dl_bw); -- cgit v1.2.2 From 2541117b0cf79977fa11a0d6e17d61010677bd7b Mon Sep 17 00:00:00 2001 From: Hiroshi Shimamoto Date: Thu, 19 Nov 2015 16:47:28 +0100 Subject: sched/cputime: Fix invalid gtime in proc /proc/stats shows invalid gtime when the thread is running in guest. When vtime accounting is not enabled, we cannot get a valid delta. The delta is calculated with now - tsk->vtime_snap, but tsk->vtime_snap is only updated when vtime accounting is runtime enabled. This patch makes task_gtime() just return gtime without computing the buggy non-existing tickless delta when vtime accounting is not enabled. Use context_tracking_is_enabled() to check if vtime is accounting on some cpu, in which case only we need to check the tickless delta. This way we fix the gtime value regression on machines not running nohz full. The kernel config contains CONFIG_VIRT_CPU_ACCOUNTING_GEN=y and CONFIG_NO_HZ_FULL_ALL=n and boot without nohz_full. I ran and stop a busy loop in VM and see the gtime in host. Dump the 43rd field which shows the gtime in every second: # while :; do awk '{print $3" "$43}' /proc/3955/task/4014/stat; sleep 1; done S 4348 R 7064566 R 7064766 R 7064967 R 7065168 S 4759 S 4759 During running busy loop, it returns large value. After applying this patch, we can see right gtime. # while :; do awk '{print $3" "$43}' /proc/10913/task/10956/stat; sleep 1; done S 5338 R 5365 R 5465 R 5566 R 5666 S 5726 S 5726 Signed-off-by: Hiroshi Shimamoto Signed-off-by: Frederic Weisbecker Signed-off-by: Peter Zijlstra (Intel) Cc: Chris Metcalf Cc: Christoph Lameter Cc: Linus Torvalds Cc: Luiz Capitulino Cc: Mike Galbraith Cc: Paul E . McKenney Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Rik van Riel Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1447948054-28668-2-git-send-email-fweisbec@gmail.com Signed-off-by: Ingo Molnar --- kernel/sched/cputime.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'kernel') diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index 26a54461bf59..05de80b48586 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -788,6 +788,9 @@ cputime_t task_gtime(struct task_struct *t) unsigned int seq; cputime_t gtime; + if (!context_tracking_is_enabled()) + return t->gtime; + do { seq = read_seqbegin(&t->vtime_seqlock); -- cgit v1.2.2 From b75a22531588e77aa8c2daf228c9723916ae2cd0 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 6 Oct 2015 14:36:17 +0200 Subject: sched/core: Better document the try_to_wake_up() barriers Explain how the control dependency and smp_rmb() end up providing ACQUIRE semantics and pair with smp_store_release() in finish_lock_switch(). Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Mike Galbraith Cc: Oleg Nesterov Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Thomas Gleixner Signed-off-by: Ingo Molnar --- kernel/sched/core.c | 8 +++++++- kernel/sched/sched.h | 3 +++ 2 files changed, 10 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/sched/core.c b/kernel/sched/core.c index eee4ee655db2..b64f163d512c 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1953,7 +1953,13 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) while (p->on_cpu) cpu_relax(); /* - * Pairs with the smp_wmb() in finish_lock_switch(). + * Combined with the control dependency above, we have an effective + * smp_load_acquire() without the need for full barriers. + * + * Pairs with the smp_store_release() in finish_lock_switch(). + * + * This ensures that tasks getting woken will be fully ordered against + * their previous state and preserve Program Order. */ smp_rmb(); diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index efd3bfc7e347..b242775bf670 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -1073,6 +1073,9 @@ static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev) * We must ensure this doesn't happen until the switch is completely * finished. * + * In particular, the load of prev->state in finish_task_switch() must + * happen before this. + * * Pairs with the control dependency and rmb in try_to_wake_up(). */ smp_store_release(&prev->on_cpu, 0); -- cgit v1.2.2 From ecf7d01c229d11a44609c0067889372c91fb4f36 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 7 Oct 2015 14:14:13 +0200 Subject: sched/core: Fix an SMP ordering race in try_to_wake_up() vs. schedule() Oleg noticed that its possible to falsely observe p->on_cpu == 0 such that we'll prematurely continue with the wakeup and effectively run p on two CPUs at the same time. Even though the overlap is very limited; the task is in the middle of being scheduled out; it could still result in corruption of the scheduler data structures. CPU0 CPU1 set_current_state(...) context_switch(X, Y) prepare_lock_switch(Y) Y->on_cpu = 1; finish_lock_switch(X) store_release(X->on_cpu, 0); try_to_wake_up(X) LOCK(p->pi_lock); t = X->on_cpu; // 0 context_switch(Y, X) prepare_lock_switch(X) X->on_cpu = 1; finish_lock_switch(Y) store_release(Y->on_cpu, 0); schedule(); deactivate_task(X); X->on_rq = 0; if (X->on_rq) // false if (t) while (X->on_cpu) cpu_relax(); context_switch(X, ..) finish_lock_switch(X) store_release(X->on_cpu, 0); Avoid the load of X->on_cpu being hoisted over the X->on_rq load. Reported-by: Oleg Nesterov Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Thomas Gleixner Signed-off-by: Ingo Molnar --- kernel/sched/core.c | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'kernel') diff --git a/kernel/sched/core.c b/kernel/sched/core.c index b64f163d512c..7063c6a07440 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1946,6 +1946,25 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) goto stat; #ifdef CONFIG_SMP + /* + * Ensure we load p->on_cpu _after_ p->on_rq, otherwise it would be + * possible to, falsely, observe p->on_cpu == 0. + * + * One must be running (->on_cpu == 1) in order to remove oneself + * from the runqueue. + * + * [S] ->on_cpu = 1; [L] ->on_rq + * UNLOCK rq->lock + * RMB + * LOCK rq->lock + * [S] ->on_rq = 0; [L] ->on_cpu + * + * Pairs with the full barrier implied in the UNLOCK+LOCK on rq->lock + * from the consecutive calls to schedule(); the first switching to our + * task, the second putting it to sleep. + */ + smp_rmb(); + /* * If the owning (remote) cpu is still in the middle of schedule() with * this task as prev, wait until its done referencing the task. -- cgit v1.2.2 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') 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 v1.2.2 From 86fffe4a61dd972d5a4e23260d530be6da02f614 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Fri, 11 Dec 2015 13:40:46 -0800 Subject: kernel: remove stop_machine() Kconfig dependency Currently the full stop_machine() routine is only enabled on SMP if module unloading is enabled, or if the CPUs are hotpluggable. This leads to configurations where stop_machine() is broken as it will then only run the callback on the local CPU with irqs disabled, and not stop the other CPUs or run the callback on them. For example, this breaks MTRR setup on x86 in certain configs since ea8596bb2d8d379 ("kprobes/x86: Remove unused text_poke_smp() and text_poke_smp_batch() functions") as the MTRR is only established on the boot CPU. This patch removes the Kconfig option for STOP_MACHINE and uses the SMP and HOTPLUG_CPU config options to compile the correct stop_machine() for the architecture, removing the false dependency on MODULE_UNLOAD in the process. Link: https://lkml.org/lkml/2014/10/8/124 References: https://bugs.freedesktop.org/show_bug.cgi?id=84794 Signed-off-by: Chris Wilson Acked-by: Ingo Molnar Cc: "Paul E. McKenney" Cc: Pranith Kumar Cc: Michal Hocko Cc: Vladimir Davydov Cc: Johannes Weiner Cc: H. Peter Anvin Cc: Tejun Heo Cc: Iulia Manda Cc: Andy Lutomirski Cc: Rusty Russell Cc: Peter Zijlstra Cc: Chuck Ebbert Cc: Oleg Nesterov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/stop_machine.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c index 867bc20e1ef1..a3bbaee77c58 100644 --- a/kernel/stop_machine.c +++ b/kernel/stop_machine.c @@ -531,7 +531,7 @@ static int __init cpu_stop_init(void) } early_initcall(cpu_stop_init); -#ifdef CONFIG_STOP_MACHINE +#if defined(CONFIG_SMP) || defined(CONFIG_HOTPLUG_CPU) static int __stop_machine(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus) { @@ -631,4 +631,4 @@ int stop_machine_from_inactive_cpu(cpu_stop_fn_t fn, void *data, return ret ?: done.ret; } -#endif /* CONFIG_STOP_MACHINE */ +#endif /* CONFIG_SMP || CONFIG_HOTPLUG_CPU */ -- cgit v1.2.2 From dfd01f026058a59a513f8a365b439a0681b803af Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Sun, 13 Dec 2015 22:11:16 +0100 Subject: sched/wait: Fix the signal handling fix Jan Stancek reported that I wrecked things for him by fixing things for Vladimir :/ His report was due to an UNINTERRUPTIBLE wait getting -EINTR, which should not be possible, however my previous patch made this possible by unconditionally checking signal_pending(). We cannot use current->state as was done previously, because the instruction after the store to that variable it can be changed. We must instead pass the initial state along and use that. Fixes: 68985633bccb ("sched/wait: Fix signal handling in bit wait helpers") Reported-by: Jan Stancek Reported-by: Chris Mason Tested-by: Jan Stancek Tested-by: Vladimir Murzin Tested-by: Chris Mason Reviewed-by: Paul Turner Cc: Ingo Molnar Cc: tglx@linutronix.de Cc: Oleg Nesterov Cc: hpa@zytor.com Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Linus Torvalds --- kernel/sched/wait.c | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) (limited to 'kernel') diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c index f10bd873e684..f15d6b6a538a 100644 --- a/kernel/sched/wait.c +++ b/kernel/sched/wait.c @@ -392,7 +392,7 @@ __wait_on_bit(wait_queue_head_t *wq, struct wait_bit_queue *q, do { prepare_to_wait(wq, &q->wait, mode); if (test_bit(q->key.bit_nr, q->key.flags)) - ret = (*action)(&q->key); + ret = (*action)(&q->key, mode); } while (test_bit(q->key.bit_nr, q->key.flags) && !ret); finish_wait(wq, &q->wait); return ret; @@ -431,7 +431,7 @@ __wait_on_bit_lock(wait_queue_head_t *wq, struct wait_bit_queue *q, prepare_to_wait_exclusive(wq, &q->wait, mode); if (!test_bit(q->key.bit_nr, q->key.flags)) continue; - ret = action(&q->key); + ret = action(&q->key, mode); if (!ret) continue; abort_exclusive_wait(wq, &q->wait, mode, &q->key); @@ -581,43 +581,43 @@ void wake_up_atomic_t(atomic_t *p) } EXPORT_SYMBOL(wake_up_atomic_t); -__sched int bit_wait(struct wait_bit_key *word) +__sched int bit_wait(struct wait_bit_key *word, int mode) { schedule(); - if (signal_pending(current)) + if (signal_pending_state(mode, current)) return -EINTR; return 0; } EXPORT_SYMBOL(bit_wait); -__sched int bit_wait_io(struct wait_bit_key *word) +__sched int bit_wait_io(struct wait_bit_key *word, int mode) { io_schedule(); - if (signal_pending(current)) + if (signal_pending_state(mode, current)) return -EINTR; return 0; } EXPORT_SYMBOL(bit_wait_io); -__sched int bit_wait_timeout(struct wait_bit_key *word) +__sched int bit_wait_timeout(struct wait_bit_key *word, int mode) { unsigned long now = READ_ONCE(jiffies); if (time_after_eq(now, word->timeout)) return -EAGAIN; schedule_timeout(word->timeout - now); - if (signal_pending(current)) + if (signal_pending_state(mode, current)) return -EINTR; return 0; } EXPORT_SYMBOL_GPL(bit_wait_timeout); -__sched int bit_wait_io_timeout(struct wait_bit_key *word) +__sched int bit_wait_io_timeout(struct wait_bit_key *word, int mode) { unsigned long now = READ_ONCE(jiffies); if (time_after_eq(now, word->timeout)) return -EAGAIN; io_schedule_timeout(word->timeout - now); - if (signal_pending(current)) + if (signal_pending_state(mode, current)) return -EINTR; return 0; } -- cgit v1.2.2 From b4b29f94856ad68329132c2306e9a114920643e3 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Fri, 11 Dec 2015 17:46:41 +0000 Subject: locking/osq: Fix ordering of node initialisation in osq_lock The Cavium guys reported a soft lockup on their arm64 machine, caused by commit c55a6ffa6285 ("locking/osq: Relax atomic semantics"): mutex_optimistic_spin+0x9c/0x1d0 __mutex_lock_slowpath+0x44/0x158 mutex_lock+0x54/0x58 kernfs_iop_permission+0x38/0x70 __inode_permission+0x88/0xd8 inode_permission+0x30/0x6c link_path_walk+0x68/0x4d4 path_openat+0xb4/0x2bc do_filp_open+0x74/0xd0 do_sys_open+0x14c/0x228 SyS_openat+0x3c/0x48 el0_svc_naked+0x24/0x28 This is because in osq_lock we initialise the node for the current CPU: node->locked = 0; node->next = NULL; node->cpu = curr; and then publish the current CPU in the lock tail: old = atomic_xchg_acquire(&lock->tail, curr); Once the update to lock->tail is visible to another CPU, the node is then live and can be both read and updated by concurrent lockers. Unfortunately, the ACQUIRE semantics of the xchg operation mean that there is no guarantee the contents of the node will be visible before lock tail is updated. This can lead to lock corruption when, for example, a concurrent locker races to set the next field. Fixes: c55a6ffa6285 ("locking/osq: Relax atomic semantics"): Reported-by: David Daney Reported-by: Andrew Pinski Tested-by: Andrew Pinski Acked-by: Davidlohr Bueso Signed-off-by: Will Deacon Signed-off-by: Peter Zijlstra (Intel) Link: http://lkml.kernel.org/r/1449856001-21177-1-git-send-email-will.deacon@arm.com Signed-off-by: Linus Torvalds --- kernel/locking/osq_lock.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/locking/osq_lock.c b/kernel/locking/osq_lock.c index d092a0c9c2d4..05a37857ab55 100644 --- a/kernel/locking/osq_lock.c +++ b/kernel/locking/osq_lock.c @@ -93,10 +93,12 @@ bool osq_lock(struct optimistic_spin_queue *lock) node->cpu = curr; /* - * ACQUIRE semantics, pairs with corresponding RELEASE - * in unlock() uncontended, or fastpath. + * We need both ACQUIRE (pairs with corresponding RELEASE in + * unlock() uncontended, or fastpath) and RELEASE (to publish + * the node fields we just initialised) semantics when updating + * the lock tail. */ - old = atomic_xchg_acquire(&lock->tail, curr); + old = atomic_xchg(&lock->tail, curr); if (old == OSQ_UNLOCKED_VAL) return true; -- cgit v1.2.2 From 1b9f23727abb92c5e58f139e7d180befcaa06fe0 Mon Sep 17 00:00:00 2001 From: Richard Cochran Date: Tue, 22 Dec 2015 22:19:58 +0100 Subject: posix-clock: Fix return code on the poll method's error path The posix_clock_poll function is supposed to return a bit mask of POLLxxx values. However, in case the hardware has disappeared (due to hot plugging for example) this code returns -ENODEV in a futile attempt to throw an error at the file descriptor level. The kernel's file_operations interface does not accept such error codes from the poll method. Instead, this function aught to return POLLERR. The value -ENODEV does, in fact, contain the POLLERR bit (and almost all the other POLLxxx bits as well), but only by chance. This patch fixes code to return a proper bit mask. Credit goes to Markus Elfring for pointing out the suspicious signed/unsigned mismatch. Reported-by: Markus Elfring igned-off-by: Richard Cochran Cc: John Stultz Cc: Julia Lawall Link: http://lkml.kernel.org/r/1450819198-17420-1-git-send-email-richardcochran@gmail.com Cc: stable@vger.kernel.org Signed-off-by: Thomas Gleixner --- kernel/time/posix-clock.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/time/posix-clock.c b/kernel/time/posix-clock.c index ce033c7aa2e8..9cff0ab82b63 100644 --- a/kernel/time/posix-clock.c +++ b/kernel/time/posix-clock.c @@ -69,10 +69,10 @@ static ssize_t posix_clock_read(struct file *fp, char __user *buf, static unsigned int posix_clock_poll(struct file *fp, poll_table *wait) { struct posix_clock *clk = get_posix_clock(fp); - int result = 0; + unsigned int result = 0; if (!clk) - return -ENODEV; + return POLLERR; if (clk->ops.poll) result = clk->ops.poll(clk, fp, wait); -- cgit v1.2.2