From bf5015a50f1fdb248b48405b67cae24dc02605d6 Mon Sep 17 00:00:00 2001 From: Juri Lelli Date: Thu, 24 May 2018 17:29:36 +0200 Subject: sched/topology: Clarify root domain(s) debug string When scheduler debug is enabled, building scheduling domains outputs information about how the domains are laid out and to which root domain each CPU (or sets of CPUs) belongs, e.g.: CPU0 attaching sched-domain(s): domain-0: span=0-5 level=MC groups: 0:{ span=0 }, 1:{ span=1 }, 2:{ span=2 }, 3:{ span=3 }, 4:{ span=4 }, 5:{ span=5 } CPU1 attaching sched-domain(s): domain-0: span=0-5 level=MC groups: 1:{ span=1 }, 2:{ span=2 }, 3:{ span=3 }, 4:{ span=4 }, 5:{ span=5 }, 0:{ span=0 } [...] span: 0-5 (max cpu_capacity = 1024) The fact that latest line refers to CPUs 0-5 root domain doesn't however look immediately obvious to me: one might wonder why span 0-5 is reported "again". Make it more clear by adding "root domain" to it, as to end with the following: CPU0 attaching sched-domain(s): domain-0: span=0-5 level=MC groups: 0:{ span=0 }, 1:{ span=1 }, 2:{ span=2 }, 3:{ span=3 }, 4:{ span=4 }, 5:{ span=5 } CPU1 attaching sched-domain(s): domain-0: span=0-5 level=MC groups: 1:{ span=1 }, 2:{ span=2 }, 3:{ span=3 }, 4:{ span=4 }, 5:{ span=5 }, 0:{ span=0 } [...] root domain span: 0-5 (max cpu_capacity = 1024) Signed-off-by: Juri Lelli Signed-off-by: Peter Zijlstra (Intel) Cc: Dietmar Eggemann Cc: Linus Torvalds Cc: Patrick Bellasi Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20180524152936.17611-1-juri.lelli@redhat.com Signed-off-by: Ingo Molnar --- kernel/sched/topology.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index 64cc564f5255..61a1125c1ae4 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -1708,7 +1708,7 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att rcu_read_unlock(); if (rq && sched_debug_enabled) { - pr_info("span: %*pbl (max cpu_capacity = %lu)\n", + pr_info("root domain span: %*pbl (max cpu_capacity = %lu)\n", cpumask_pr_args(cpu_map), rq->rd->max_cpu_capacity); } -- cgit v1.2.3 From b1f5b378e126133521df668379249fb8265121f1 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 4 May 2018 11:11:42 +0200 Subject: kthread: Allow kthread_park() on a parked kthread The following commit: 85f1abe0019f ("kthread, sched/wait: Fix kthread_parkme() completion issue") added a WARN() in the case where we call kthread_park() on an already parked thread, because the old code wasn't doing the right thing there and it wasn't at all clear that would happen. It turns out, this does in fact happen, so we have to deal with it. Instead of potentially returning early, also wait for the completion. This does however mean we have to use complete_all() and re-initialize the completion on re-use. Reported-by: LKP Tested-by: Meelis Roos Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: kernel test robot Cc: wfg@linux.intel.com Cc: Thomas Gleixner Fixes: 85f1abe0019f ("kthread, sched/wait: Fix kthread_parkme() completion issue") Link: http://lkml.kernel.org/r/20180504091142.GI12235@hirez.programming.kicks-ass.net Signed-off-by: Ingo Molnar --- kernel/kthread.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/kthread.c b/kernel/kthread.c index 2017a39ab490..481951bf091d 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -193,7 +193,7 @@ EXPORT_SYMBOL_GPL(kthread_parkme); void kthread_park_complete(struct task_struct *k) { - complete(&to_kthread(k)->parked); + complete_all(&to_kthread(k)->parked); } static int kthread(void *_create) @@ -459,6 +459,7 @@ void kthread_unpark(struct task_struct *k) if (test_bit(KTHREAD_IS_PER_CPU, &kthread->flags)) __kthread_bind(k, kthread->cpu, TASK_PARKED); + reinit_completion(&kthread->parked); clear_bit(KTHREAD_SHOULD_PARK, &kthread->flags); wake_up_state(k, TASK_PARKED); } @@ -483,9 +484,6 @@ int kthread_park(struct task_struct *k) if (WARN_ON(k->flags & PF_EXITING)) return -ENOSYS; - if (WARN_ON_ONCE(test_bit(KTHREAD_SHOULD_PARK, &kthread->flags))) - return -EBUSY; - set_bit(KTHREAD_SHOULD_PARK, &kthread->flags); if (k != current) { wake_up_process(k); -- cgit v1.2.3 From 86b389ff22bd6ad8fd3cb98e41cd271886c6d023 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Sun, 27 May 2018 20:54:44 -0400 Subject: tracing: Fix crash when freeing instances with event triggers If a instance has an event trigger enabled when it is freed, it could cause an access of free memory. Here's the case that crashes: # cd /sys/kernel/tracing # mkdir instances/foo # echo snapshot > instances/foo/events/initcall/initcall_start/trigger # rmdir instances/foo Would produce: general protection fault: 0000 [#1] PREEMPT SMP PTI Modules linked in: tun bridge ... CPU: 5 PID: 6203 Comm: rmdir Tainted: G W 4.17.0-rc4-test+ #933 Hardware name: Hewlett-Packard HP Compaq Pro 6300 SFF/339A, BIOS K01 v03.03 07/14/2016 RIP: 0010:clear_event_triggers+0x3b/0x70 RSP: 0018:ffffc90003783de0 EFLAGS: 00010286 RAX: 0000000000000000 RBX: 6b6b6b6b6b6b6b2b RCX: 0000000000000000 RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffff8800c7130ba0 RBP: ffffc90003783e00 R08: ffff8801131993f8 R09: 0000000100230016 R10: ffffc90003783d80 R11: 0000000000000000 R12: ffff8800c7130ba0 R13: ffff8800c7130bd8 R14: ffff8800cc093768 R15: 00000000ffffff9c FS: 00007f6f4aa86700(0000) GS:ffff88011eb40000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f6f4a5aed60 CR3: 00000000cd552001 CR4: 00000000001606e0 Call Trace: event_trace_del_tracer+0x2a/0xc5 instance_rmdir+0x15c/0x200 tracefs_syscall_rmdir+0x52/0x90 vfs_rmdir+0xdb/0x160 do_rmdir+0x16d/0x1c0 __x64_sys_rmdir+0x17/0x20 do_syscall_64+0x55/0x1a0 entry_SYSCALL_64_after_hwframe+0x49/0xbe This was due to the call the clears out the triggers when an instance is being deleted not removing the trigger from the link list. Cc: stable@vger.kernel.org Fixes: 85f2b08268c01 ("tracing: Add basic event trigger framework") Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace_events_trigger.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c index d251cabcf69a..9be317d388c5 100644 --- a/kernel/trace/trace_events_trigger.c +++ b/kernel/trace/trace_events_trigger.c @@ -483,9 +483,10 @@ clear_event_triggers(struct trace_array *tr) struct trace_event_file *file; list_for_each_entry(file, &tr->events, list) { - struct event_trigger_data *data; - list_for_each_entry_rcu(data, &file->triggers, list) { + struct event_trigger_data *data, *n; + list_for_each_entry_safe(data, n, &file->triggers, list) { trace_event_trigger_enable_disable(file, 0); + list_del_rcu(&data->list); if (data->ops->free) data->ops->free(data->ops, data); } -- cgit v1.2.3 From 2824f5033248600673e3e126a4d135363cbfd9ac Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Mon, 28 May 2018 10:56:36 -0400 Subject: tracing: Make the snapshot trigger work with instances The snapshot trigger currently only affects the main ring buffer, even when it is used by the instances. This can be confusing as the snapshot trigger is listed in the instance. > # cd /sys/kernel/tracing > # mkdir instances/foo > # echo snapshot > instances/foo/events/syscalls/sys_enter_fchownat/trigger > # echo top buffer > trace_marker > # echo foo buffer > instances/foo/trace_marker > # touch /tmp/bar > # chown rostedt /tmp/bar > # cat instances/foo/snapshot # tracer: nop # # # * Snapshot is freed * # # Snapshot commands: # echo 0 > snapshot : Clears and frees snapshot buffer # echo 1 > snapshot : Allocates snapshot buffer, if not already allocated. # Takes a snapshot of the main buffer. # echo 2 > snapshot : Clears snapshot buffer (but does not allocate or free) # (Doesn't have to be '2' works with any number that # is not a '0' or '1') > # cat snapshot # tracer: nop # # _-----=> irqs-off # / _----=> need-resched # | / _---=> hardirq/softirq # || / _--=> preempt-depth # ||| / delay # TASK-PID CPU# |||| TIMESTAMP FUNCTION # | | | |||| | | bash-1189 [000] .... 111.488323: tracing_mark_write: top buffer Not only did the snapshot occur in the top level buffer, but the instance snapshot buffer should have been allocated, and it is still free. Cc: stable@vger.kernel.org Fixes: 85f2b08268c01 ("tracing: Add basic event trigger framework") Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace.c | 12 ++++++------ kernel/trace/trace.h | 11 +++++++++++ kernel/trace/trace_events_trigger.c | 10 ++++++++-- 3 files changed, 25 insertions(+), 8 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 414d7210b2ec..bcd93031d042 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -893,7 +893,7 @@ int __trace_bputs(unsigned long ip, const char *str) EXPORT_SYMBOL_GPL(__trace_bputs); #ifdef CONFIG_TRACER_SNAPSHOT -static void tracing_snapshot_instance(struct trace_array *tr) +void tracing_snapshot_instance(struct trace_array *tr) { struct tracer *tracer = tr->current_trace; unsigned long flags; @@ -949,7 +949,7 @@ static int resize_buffer_duplicate_size(struct trace_buffer *trace_buf, struct trace_buffer *size_buf, int cpu_id); static void set_buffer_entries(struct trace_buffer *buf, unsigned long val); -static int alloc_snapshot(struct trace_array *tr) +int tracing_alloc_snapshot_instance(struct trace_array *tr) { int ret; @@ -995,7 +995,7 @@ int tracing_alloc_snapshot(void) struct trace_array *tr = &global_trace; int ret; - ret = alloc_snapshot(tr); + ret = tracing_alloc_snapshot_instance(tr); WARN_ON(ret < 0); return ret; @@ -5408,7 +5408,7 @@ static int tracing_set_tracer(struct trace_array *tr, const char *buf) #ifdef CONFIG_TRACER_MAX_TRACE if (t->use_max_tr && !had_max_tr) { - ret = alloc_snapshot(tr); + ret = tracing_alloc_snapshot_instance(tr); if (ret < 0) goto out; } @@ -6451,7 +6451,7 @@ tracing_snapshot_write(struct file *filp, const char __user *ubuf, size_t cnt, } #endif if (!tr->allocated_snapshot) { - ret = alloc_snapshot(tr); + ret = tracing_alloc_snapshot_instance(tr); if (ret < 0) break; } @@ -7179,7 +7179,7 @@ ftrace_trace_snapshot_callback(struct trace_array *tr, struct ftrace_hash *hash, return ret; out_reg: - ret = alloc_snapshot(tr); + ret = tracing_alloc_snapshot_instance(tr); if (ret < 0) goto out; diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 6fb46a06c9dc..507954b4e058 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -1817,6 +1817,17 @@ static inline void __init trace_event_init(void) { } static inline void trace_event_eval_update(struct trace_eval_map **map, int len) { } #endif +#ifdef CONFIG_TRACER_SNAPSHOT +void tracing_snapshot_instance(struct trace_array *tr); +int tracing_alloc_snapshot_instance(struct trace_array *tr); +#else +static inline void tracing_snapshot_instance(struct trace_array *tr) { } +static inline int tracing_alloc_snapshot_instance(struct trace_array *tr) +{ + return 0; +} +#endif + extern struct trace_iterator *tracepoint_print_iter; #endif /* _LINUX_KERNEL_TRACE_H */ diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c index 9be317d388c5..8b5bdcf64871 100644 --- a/kernel/trace/trace_events_trigger.c +++ b/kernel/trace/trace_events_trigger.c @@ -643,6 +643,7 @@ event_trigger_callback(struct event_command *cmd_ops, trigger_data->count = -1; trigger_data->ops = trigger_ops; trigger_data->cmd_ops = cmd_ops; + trigger_data->private_data = file; INIT_LIST_HEAD(&trigger_data->list); INIT_LIST_HEAD(&trigger_data->named_list); @@ -1054,7 +1055,12 @@ static void snapshot_trigger(struct event_trigger_data *data, void *rec, struct ring_buffer_event *event) { - tracing_snapshot(); + struct trace_event_file *file = data->private_data; + + if (file) + tracing_snapshot_instance(file->tr); + else + tracing_snapshot(); } static void @@ -1077,7 +1083,7 @@ register_snapshot_trigger(char *glob, struct event_trigger_ops *ops, { int ret = register_trigger(glob, ops, data, file); - if (ret > 0 && tracing_alloc_snapshot() != 0) { + if (ret > 0 && tracing_alloc_snapshot_instance(file->tr) != 0) { unregister_trigger(glob, ops, data, file); ret = 0; } -- cgit v1.2.3