From aefb2f2e619b6c334bcb31de830aa00ba0b11129 Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Tue, 21 Nov 2023 08:07:32 -0800 Subject: x86/bugs: Rename CONFIG_RETPOLINE => CONFIG_MITIGATION_RETPOLINE Step 5/10 of the namespace unification of CPU mitigations related Kconfig options. [ mingo: Converted a few more uses in comments/messages as well. ] Suggested-by: Josh Poimboeuf Signed-off-by: Breno Leitao Signed-off-by: Ingo Molnar Reviewed-by: Ariel Miculas Acked-by: Josh Poimboeuf Cc: Linus Torvalds Link: https://lore.kernel.org/r/20231121160740.1249350-6-leitao@debian.org --- kernel/trace/ring_buffer.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/trace/ring_buffer.c') diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 9286f88fcd32..9cb69332921d 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -1156,7 +1156,7 @@ static inline u64 rb_time_stamp(struct trace_buffer *buffer) u64 ts; /* Skip retpolines :-( */ - if (IS_ENABLED(CONFIG_RETPOLINE) && likely(buffer->clock == trace_clock_local)) + if (IS_ENABLED(CONFIG_MITIGATION_RETPOLINE) && likely(buffer->clock == trace_clock_local)) ts = trace_clock_local(); else ts = buffer->clock(); -- cgit v1.2.3 From b3594573681b53316ec0365332681a30463edfd6 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Google)" Date: Fri, 8 Mar 2024 15:24:03 -0500 Subject: ring-buffer: Fix waking up ring buffer readers A task can wait on a ring buffer for when it fills up to a specific watermark. The writer will check the minimum watermark that waiters are waiting for and if the ring buffer is past that, it will wake up all the waiters. The waiters are in a wait loop, and will first check if a signal is pending and then check if the ring buffer is at the desired level where it should break out of the loop. If a file that uses a ring buffer closes, and there's threads waiting on the ring buffer, it needs to wake up those threads. To do this, a "wait_index" was used. Before entering the wait loop, the waiter will read the wait_index. On wakeup, it will check if the wait_index is different than when it entered the loop, and will exit the loop if it is. The waker will only need to update the wait_index before waking up the waiters. This had a couple of bugs. One trivial one and one broken by design. The trivial bug was that the waiter checked the wait_index after the schedule() call. It had to be checked between the prepare_to_wait() and the schedule() which it was not. The main bug is that the first check to set the default wait_index will always be outside the prepare_to_wait() and the schedule(). That's because the ring_buffer_wait() doesn't have enough context to know if it should break out of the loop. The loop itself is not needed, because all the callers to the ring_buffer_wait() also has their own loop, as the callers have a better sense of what the context is to decide whether to break out of the loop or not. Just have the ring_buffer_wait() block once, and if it gets woken up, exit the function and let the callers decide what to do next. Link: https://lore.kernel.org/all/CAHk-=whs5MdtNjzFkTyaUy=vHi=qwWgPi0JgTe6OYUYMNSRZfg@mail.gmail.com/ Link: https://lore.kernel.org/linux-trace-kernel/20240308202431.792933613@goodmis.org Cc: stable@vger.kernel.org Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Andrew Morton Cc: Linus Torvalds Cc: linke li Cc: Rabin Vincent Fixes: e30f53aad2202 ("tracing: Do not busy wait in buffer splice") Signed-off-by: Steven Rostedt (Google) --- kernel/trace/ring_buffer.c | 139 ++++++++++++++++++++++----------------------- 1 file changed, 68 insertions(+), 71 deletions(-) (limited to 'kernel/trace/ring_buffer.c') diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 0699027b4f4c..3400f11286e3 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -384,7 +384,6 @@ struct rb_irq_work { struct irq_work work; wait_queue_head_t waiters; wait_queue_head_t full_waiters; - long wait_index; bool waiters_pending; bool full_waiters_pending; bool wakeup_full; @@ -798,14 +797,40 @@ void ring_buffer_wake_waiters(struct trace_buffer *buffer, int cpu) rbwork = &cpu_buffer->irq_work; } - rbwork->wait_index++; - /* make sure the waiters see the new index */ - smp_wmb(); - /* This can be called in any context */ irq_work_queue(&rbwork->work); } +static bool rb_watermark_hit(struct trace_buffer *buffer, int cpu, int full) +{ + struct ring_buffer_per_cpu *cpu_buffer; + bool ret = false; + + /* Reads of all CPUs always waits for any data */ + if (cpu == RING_BUFFER_ALL_CPUS) + return !ring_buffer_empty(buffer); + + cpu_buffer = buffer->buffers[cpu]; + + if (!ring_buffer_empty_cpu(buffer, cpu)) { + unsigned long flags; + bool pagebusy; + + if (!full) + return true; + + raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); + pagebusy = cpu_buffer->reader_page == cpu_buffer->commit_page; + ret = !pagebusy && full_hit(buffer, cpu, full); + + if (!cpu_buffer->shortest_full || + cpu_buffer->shortest_full > full) + cpu_buffer->shortest_full = full; + raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); + } + return ret; +} + /** * ring_buffer_wait - wait for input to the ring buffer * @buffer: buffer to wait on @@ -821,7 +846,6 @@ int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full) struct ring_buffer_per_cpu *cpu_buffer; DEFINE_WAIT(wait); struct rb_irq_work *work; - long wait_index; int ret = 0; /* @@ -840,81 +864,54 @@ int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full) work = &cpu_buffer->irq_work; } - wait_index = READ_ONCE(work->wait_index); - - while (true) { - if (full) - prepare_to_wait(&work->full_waiters, &wait, TASK_INTERRUPTIBLE); - else - prepare_to_wait(&work->waiters, &wait, TASK_INTERRUPTIBLE); - - /* - * The events can happen in critical sections where - * checking a work queue can cause deadlocks. - * After adding a task to the queue, this flag is set - * only to notify events to try to wake up the queue - * using irq_work. - * - * We don't clear it even if the buffer is no longer - * empty. The flag only causes the next event to run - * irq_work to do the work queue wake up. The worse - * that can happen if we race with !trace_empty() is that - * an event will cause an irq_work to try to wake up - * an empty queue. - * - * There's no reason to protect this flag either, as - * the work queue and irq_work logic will do the necessary - * synchronization for the wake ups. The only thing - * that is necessary is that the wake up happens after - * a task has been queued. It's OK for spurious wake ups. - */ - if (full) - work->full_waiters_pending = true; - else - work->waiters_pending = true; - - if (signal_pending(current)) { - ret = -EINTR; - break; - } - - if (cpu == RING_BUFFER_ALL_CPUS && !ring_buffer_empty(buffer)) - break; - - if (cpu != RING_BUFFER_ALL_CPUS && - !ring_buffer_empty_cpu(buffer, cpu)) { - unsigned long flags; - bool pagebusy; - bool done; - - if (!full) - break; - - raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); - pagebusy = cpu_buffer->reader_page == cpu_buffer->commit_page; - done = !pagebusy && full_hit(buffer, cpu, full); + if (full) + prepare_to_wait(&work->full_waiters, &wait, TASK_INTERRUPTIBLE); + else + prepare_to_wait(&work->waiters, &wait, TASK_INTERRUPTIBLE); - if (!cpu_buffer->shortest_full || - cpu_buffer->shortest_full > full) - cpu_buffer->shortest_full = full; - raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); - if (done) - break; - } + /* + * The events can happen in critical sections where + * checking a work queue can cause deadlocks. + * After adding a task to the queue, this flag is set + * only to notify events to try to wake up the queue + * using irq_work. + * + * We don't clear it even if the buffer is no longer + * empty. The flag only causes the next event to run + * irq_work to do the work queue wake up. The worse + * that can happen if we race with !trace_empty() is that + * an event will cause an irq_work to try to wake up + * an empty queue. + * + * There's no reason to protect this flag either, as + * the work queue and irq_work logic will do the necessary + * synchronization for the wake ups. The only thing + * that is necessary is that the wake up happens after + * a task has been queued. It's OK for spurious wake ups. + */ + if (full) + work->full_waiters_pending = true; + else + work->waiters_pending = true; - schedule(); + if (rb_watermark_hit(buffer, cpu, full)) + goto out; - /* Make sure to see the new wait index */ - smp_rmb(); - if (wait_index != work->wait_index) - break; + if (signal_pending(current)) { + ret = -EINTR; + goto out; } + schedule(); + out: if (full) finish_wait(&work->full_waiters, &wait); else finish_wait(&work->waiters, &wait); + if (!ret && !rb_watermark_hit(buffer, cpu, full) && signal_pending(current)) + ret = -EINTR; + return ret; } -- cgit v1.2.3 From 68282dd930ea38b068ce2c109d12405f40df3f93 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Google)" Date: Fri, 8 Mar 2024 15:24:04 -0500 Subject: ring-buffer: Fix resetting of shortest_full The "shortest_full" variable is used to keep track of the waiter that is waiting for the smallest amount on the ring buffer before being woken up. When a tasks waits on the ring buffer, it passes in a "full" value that is a percentage. 0 means wake up on any data. 1-100 means wake up from 1% to 100% full buffer. As all waiters are on the same wait queue, the wake up happens for the waiter with the smallest percentage. The problem is that the smallest_full on the cpu_buffer that stores the smallest amount doesn't get reset when all the waiters are woken up. It does get reset when the ring buffer is reset (echo > /sys/kernel/tracing/trace). This means that tasks may be woken up more often then when they want to be. Instead, have the shortest_full field get reset just before waking up all the tasks. If the tasks wait again, they will update the shortest_full before sleeping. Also add locking around setting of shortest_full in the poll logic, and change "work" to "rbwork" to match the variable name for rb_irq_work structures that are used in other places. Link: https://lore.kernel.org/linux-trace-kernel/20240308202431.948914369@goodmis.org Cc: stable@vger.kernel.org Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Andrew Morton Cc: Linus Torvalds Cc: linke li Cc: Rabin Vincent Fixes: 2c2b0a78b3739 ("ring-buffer: Add percentage of ring buffer full to wake up reader") Signed-off-by: Steven Rostedt (Google) --- kernel/trace/ring_buffer.c | 30 +++++++++++++++++++++++------- 1 file changed, 23 insertions(+), 7 deletions(-) (limited to 'kernel/trace/ring_buffer.c') diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 3400f11286e3..aa332ace108b 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -755,8 +755,19 @@ static void rb_wake_up_waiters(struct irq_work *work) wake_up_all(&rbwork->waiters); if (rbwork->full_waiters_pending || rbwork->wakeup_full) { + /* Only cpu_buffer sets the above flags */ + struct ring_buffer_per_cpu *cpu_buffer = + container_of(rbwork, struct ring_buffer_per_cpu, irq_work); + + /* Called from interrupt context */ + raw_spin_lock(&cpu_buffer->reader_lock); rbwork->wakeup_full = false; rbwork->full_waiters_pending = false; + + /* Waking up all waiters, they will reset the shortest full */ + cpu_buffer->shortest_full = 0; + raw_spin_unlock(&cpu_buffer->reader_lock); + wake_up_all(&rbwork->full_waiters); } } @@ -934,28 +945,33 @@ __poll_t ring_buffer_poll_wait(struct trace_buffer *buffer, int cpu, struct file *filp, poll_table *poll_table, int full) { struct ring_buffer_per_cpu *cpu_buffer; - struct rb_irq_work *work; + struct rb_irq_work *rbwork; if (cpu == RING_BUFFER_ALL_CPUS) { - work = &buffer->irq_work; + rbwork = &buffer->irq_work; full = 0; } else { if (!cpumask_test_cpu(cpu, buffer->cpumask)) return EPOLLERR; cpu_buffer = buffer->buffers[cpu]; - work = &cpu_buffer->irq_work; + rbwork = &cpu_buffer->irq_work; } if (full) { - poll_wait(filp, &work->full_waiters, poll_table); - work->full_waiters_pending = true; + unsigned long flags; + + poll_wait(filp, &rbwork->full_waiters, poll_table); + + raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); + rbwork->full_waiters_pending = true; if (!cpu_buffer->shortest_full || cpu_buffer->shortest_full > full) cpu_buffer->shortest_full = full; + raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); } else { - poll_wait(filp, &work->waiters, poll_table); - work->waiters_pending = true; + poll_wait(filp, &rbwork->waiters, poll_table); + rbwork->waiters_pending = true; } /* -- cgit v1.2.3 From 761d9473e27f0c8782895013a3e7b52a37c8bcfc Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Google)" Date: Tue, 12 Mar 2024 11:56:41 -0400 Subject: ring-buffer: Do not set shortest_full when full target is hit The rb_watermark_hit() checks if the amount of data in the ring buffer is above the percentage level passed in by the "full" variable. If it is, it returns true. But it also sets the "shortest_full" field of the cpu_buffer that informs writers that it needs to call the irq_work if the amount of data on the ring buffer is above the requested amount. The rb_watermark_hit() always sets the shortest_full even if the amount in the ring buffer is what it wants. As it is not going to wait, because it has what it wants, there's no reason to set shortest_full. Link: https://lore.kernel.org/linux-trace-kernel/20240312115641.6aa8ba08@gandalf.local.home Cc: stable@vger.kernel.org Cc: Mathieu Desnoyers Fixes: 42fb0a1e84ff5 ("tracing/ring-buffer: Have polling block on watermark") Reviewed-by: Masami Hiramatsu (Google) Signed-off-by: Steven Rostedt (Google) --- kernel/trace/ring_buffer.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'kernel/trace/ring_buffer.c') diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index aa332ace108b..6ffbccb9bcf0 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -834,9 +834,10 @@ static bool rb_watermark_hit(struct trace_buffer *buffer, int cpu, int full) pagebusy = cpu_buffer->reader_page == cpu_buffer->commit_page; ret = !pagebusy && full_hit(buffer, cpu, full); - if (!cpu_buffer->shortest_full || - cpu_buffer->shortest_full > full) - cpu_buffer->shortest_full = full; + if (!ret && (!cpu_buffer->shortest_full || + cpu_buffer->shortest_full > full)) { + cpu_buffer->shortest_full = full; + } raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); } return ret; -- cgit v1.2.3 From 8145f1c35fa648da662078efab299c4467b85ad5 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Google)" Date: Tue, 12 Mar 2024 09:19:20 -0400 Subject: ring-buffer: Fix full_waiters_pending in poll If a reader of the ring buffer is doing a poll, and waiting for the ring buffer to hit a specific watermark, there could be a case where it gets into an infinite ping-pong loop. The poll code has: rbwork->full_waiters_pending = true; if (!cpu_buffer->shortest_full || cpu_buffer->shortest_full > full) cpu_buffer->shortest_full = full; The writer will see full_waiters_pending and check if the ring buffer is filled over the percentage of the shortest_full value. If it is, it calls an irq_work to wake up all the waiters. But the code could get into a circular loop: CPU 0 CPU 1 ----- ----- [ Poll ] [ shortest_full = 0 ] rbwork->full_waiters_pending = true; if (rbwork->full_waiters_pending && [ buffer percent ] > shortest_full) { rbwork->wakeup_full = true; [ queue_irqwork ] cpu_buffer->shortest_full = full; [ IRQ work ] if (rbwork->wakeup_full) { cpu_buffer->shortest_full = 0; wakeup poll waiters; [woken] if ([ buffer percent ] > full) break; rbwork->full_waiters_pending = true; if (rbwork->full_waiters_pending && [ buffer percent ] > shortest_full) { rbwork->wakeup_full = true; [ queue_irqwork ] cpu_buffer->shortest_full = full; [ IRQ work ] if (rbwork->wakeup_full) { cpu_buffer->shortest_full = 0; wakeup poll waiters; [woken] [ Wash, rinse, repeat! ] In the poll, the shortest_full needs to be set before the full_pending_waiters, as once that is set, the writer will compare the current shortest_full (which is incorrect) to decide to call the irq_work, which will reset the shortest_full (expecting the readers to update it). Also move the setting of full_waiters_pending after the check if the ring buffer has the required percentage filled. There's no reason to tell the writer to wake up waiters if there are no waiters. Link: https://lore.kernel.org/linux-trace-kernel/20240312131952.630922155@goodmis.org Cc: stable@vger.kernel.org Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Andrew Morton Fixes: 42fb0a1e84ff5 ("tracing/ring-buffer: Have polling block on watermark") Reviewed-by: Masami Hiramatsu (Google) Signed-off-by: Steven Rostedt (Google) --- kernel/trace/ring_buffer.c | 27 ++++++++++++++++++++------- 1 file changed, 20 insertions(+), 7 deletions(-) (limited to 'kernel/trace/ring_buffer.c') diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 6ffbccb9bcf0..99fdda29ce4e 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -965,16 +965,32 @@ __poll_t ring_buffer_poll_wait(struct trace_buffer *buffer, int cpu, poll_wait(filp, &rbwork->full_waiters, poll_table); raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); - rbwork->full_waiters_pending = true; if (!cpu_buffer->shortest_full || cpu_buffer->shortest_full > full) cpu_buffer->shortest_full = full; raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); - } else { - poll_wait(filp, &rbwork->waiters, poll_table); - rbwork->waiters_pending = true; + if (full_hit(buffer, cpu, full)) + return EPOLLIN | EPOLLRDNORM; + /* + * Only allow full_waiters_pending update to be seen after + * the shortest_full is set. If the writer sees the + * full_waiters_pending flag set, it will compare the + * amount in the ring buffer to shortest_full. If the amount + * in the ring buffer is greater than the shortest_full + * percent, it will call the irq_work handler to wake up + * this list. The irq_handler will reset shortest_full + * back to zero. That's done under the reader_lock, but + * the below smp_mb() makes sure that the update to + * full_waiters_pending doesn't leak up into the above. + */ + smp_mb(); + rbwork->full_waiters_pending = true; + return 0; } + poll_wait(filp, &rbwork->waiters, poll_table); + rbwork->waiters_pending = true; + /* * There's a tight race between setting the waiters_pending and * checking if the ring buffer is empty. Once the waiters_pending bit @@ -990,9 +1006,6 @@ __poll_t ring_buffer_poll_wait(struct trace_buffer *buffer, int cpu, */ smp_mb(); - if (full) - return full_hit(buffer, cpu, full) ? EPOLLIN | EPOLLRDNORM : 0; - if ((cpu == RING_BUFFER_ALL_CPUS && !ring_buffer_empty(buffer)) || (cpu != RING_BUFFER_ALL_CPUS && !ring_buffer_empty_cpu(buffer, cpu))) return EPOLLIN | EPOLLRDNORM; -- cgit v1.2.3 From e36f19a6457b2c0dfa4a7d19153ef0fda4bf5634 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Google)" Date: Tue, 12 Mar 2024 09:19:21 -0400 Subject: ring-buffer: Reuse rb_watermark_hit() for the poll logic The check for knowing if the poll should wait or not is basically the exact same logic as rb_watermark_hit(). The only difference is that rb_watermark_hit() also handles the !full case. But for the full case, the logic is the same. Just call that instead of duplicating the code in ring_buffer_poll_wait(). Link: https://lore.kernel.org/linux-trace-kernel/20240312131952.802267543@goodmis.org Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Andrew Morton Reviewed-by: Masami Hiramatsu (Google) Signed-off-by: Steven Rostedt (Google) --- kernel/trace/ring_buffer.c | 21 +++++++-------------- 1 file changed, 7 insertions(+), 14 deletions(-) (limited to 'kernel/trace/ring_buffer.c') diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 99fdda29ce4e..8c3730a88662 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -960,25 +960,18 @@ __poll_t ring_buffer_poll_wait(struct trace_buffer *buffer, int cpu, } if (full) { - unsigned long flags; - poll_wait(filp, &rbwork->full_waiters, poll_table); - raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); - if (!cpu_buffer->shortest_full || - cpu_buffer->shortest_full > full) - cpu_buffer->shortest_full = full; - raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); - if (full_hit(buffer, cpu, full)) + if (rb_watermark_hit(buffer, cpu, full)) return EPOLLIN | EPOLLRDNORM; /* * Only allow full_waiters_pending update to be seen after - * the shortest_full is set. If the writer sees the - * full_waiters_pending flag set, it will compare the - * amount in the ring buffer to shortest_full. If the amount - * in the ring buffer is greater than the shortest_full - * percent, it will call the irq_work handler to wake up - * this list. The irq_handler will reset shortest_full + * the shortest_full is set (in rb_watermark_hit). If the + * writer sees the full_waiters_pending flag set, it will + * compare the amount in the ring buffer to shortest_full. + * If the amount in the ring buffer is greater than the + * shortest_full percent, it will call the irq_work handler + * to wake up this list. The irq_handler will reset shortest_full * back to zero. That's done under the reader_lock, but * the below smp_mb() makes sure that the update to * full_waiters_pending doesn't leak up into the above. -- cgit v1.2.3 From 7af9ded0c2caac0a95f33df5cb04706b0f502588 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Google)" Date: Tue, 12 Mar 2024 08:15:07 -0400 Subject: ring-buffer: Use wait_event_interruptible() in ring_buffer_wait() Convert ring_buffer_wait() over to wait_event_interruptible(). The default condition is to execute the wait loop inside __wait_event() just once. This does not change the ring_buffer_wait() prototype yet, but restructures the code so that it can take a "cond" and "data" parameter and will call wait_event_interruptible() with a helper function as the condition. The helper function (rb_wait_cond) takes the cond function and data parameters. It will first check if the buffer hit the watermark defined by the "full" parameter and then call the passed in condition parameter. If either are true, it returns true. If rb_wait_cond() does not return true, it will set the appropriate "waiters_pending" flag and returns false. Link: https://lore.kernel.org/linux-trace-kernel/CAHk-=wgsNgewHFxZAJiAQznwPMqEtQmi1waeS2O1v6L4c_Um5A@mail.gmail.com/ Link: https://lore.kernel.org/linux-trace-kernel/20240312121703.399598519@goodmis.org Cc: stable@vger.kernel.org Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Andrew Morton Cc: Linus Torvalds Cc: linke li Cc: Rabin Vincent Fixes: f3ddb74ad0790 ("tracing: Wake up ring buffer waiters on closing of the file") Signed-off-by: Steven Rostedt (Google) --- include/linux/ring_buffer.h | 1 + kernel/trace/ring_buffer.c | 116 ++++++++++++++++++++++++++------------------ 2 files changed, 69 insertions(+), 48 deletions(-) (limited to 'kernel/trace/ring_buffer.c') diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h index fa802db216f9..338a33db1577 100644 --- a/include/linux/ring_buffer.h +++ b/include/linux/ring_buffer.h @@ -98,6 +98,7 @@ __ring_buffer_alloc(unsigned long size, unsigned flags, struct lock_class_key *k __ring_buffer_alloc((size), (flags), &__key); \ }) +typedef bool (*ring_buffer_cond_fn)(void *data); int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full); __poll_t ring_buffer_poll_wait(struct trace_buffer *buffer, int cpu, struct file *filp, poll_table *poll_table, int full); diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 8c3730a88662..f4c34b7c7e1e 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -843,43 +843,15 @@ static bool rb_watermark_hit(struct trace_buffer *buffer, int cpu, int full) return ret; } -/** - * ring_buffer_wait - wait for input to the ring buffer - * @buffer: buffer to wait on - * @cpu: the cpu buffer to wait on - * @full: wait until the percentage of pages are available, if @cpu != RING_BUFFER_ALL_CPUS - * - * If @cpu == RING_BUFFER_ALL_CPUS then the task will wake up as soon - * as data is added to any of the @buffer's cpu buffers. Otherwise - * it will wait for data to be added to a specific cpu buffer. - */ -int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full) +static inline bool +rb_wait_cond(struct rb_irq_work *rbwork, struct trace_buffer *buffer, + int cpu, int full, ring_buffer_cond_fn cond, void *data) { - struct ring_buffer_per_cpu *cpu_buffer; - DEFINE_WAIT(wait); - struct rb_irq_work *work; - int ret = 0; - - /* - * Depending on what the caller is waiting for, either any - * data in any cpu buffer, or a specific buffer, put the - * caller on the appropriate wait queue. - */ - if (cpu == RING_BUFFER_ALL_CPUS) { - work = &buffer->irq_work; - /* Full only makes sense on per cpu reads */ - full = 0; - } else { - if (!cpumask_test_cpu(cpu, buffer->cpumask)) - return -ENODEV; - cpu_buffer = buffer->buffers[cpu]; - work = &cpu_buffer->irq_work; - } + if (rb_watermark_hit(buffer, cpu, full)) + return true; - if (full) - prepare_to_wait(&work->full_waiters, &wait, TASK_INTERRUPTIBLE); - else - prepare_to_wait(&work->waiters, &wait, TASK_INTERRUPTIBLE); + if (cond(data)) + return true; /* * The events can happen in critical sections where @@ -902,27 +874,75 @@ int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full) * a task has been queued. It's OK for spurious wake ups. */ if (full) - work->full_waiters_pending = true; + rbwork->full_waiters_pending = true; else - work->waiters_pending = true; + rbwork->waiters_pending = true; - if (rb_watermark_hit(buffer, cpu, full)) - goto out; + return false; +} - if (signal_pending(current)) { - ret = -EINTR; - goto out; +/* + * The default wait condition for ring_buffer_wait() is to just to exit the + * wait loop the first time it is woken up. + */ +static bool rb_wait_once(void *data) +{ + long *once = data; + + /* wait_event() actually calls this twice before scheduling*/ + if (*once > 1) + return true; + + (*once)++; + return false; +} + +/** + * ring_buffer_wait - wait for input to the ring buffer + * @buffer: buffer to wait on + * @cpu: the cpu buffer to wait on + * @full: wait until the percentage of pages are available, if @cpu != RING_BUFFER_ALL_CPUS + * + * If @cpu == RING_BUFFER_ALL_CPUS then the task will wake up as soon + * as data is added to any of the @buffer's cpu buffers. Otherwise + * it will wait for data to be added to a specific cpu buffer. + */ +int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full) +{ + struct ring_buffer_per_cpu *cpu_buffer; + struct wait_queue_head *waitq; + ring_buffer_cond_fn cond; + struct rb_irq_work *rbwork; + void *data; + long once = 0; + int ret = 0; + + cond = rb_wait_once; + data = &once; + + /* + * Depending on what the caller is waiting for, either any + * data in any cpu buffer, or a specific buffer, put the + * caller on the appropriate wait queue. + */ + if (cpu == RING_BUFFER_ALL_CPUS) { + rbwork = &buffer->irq_work; + /* Full only makes sense on per cpu reads */ + full = 0; + } else { + if (!cpumask_test_cpu(cpu, buffer->cpumask)) + return -ENODEV; + cpu_buffer = buffer->buffers[cpu]; + rbwork = &cpu_buffer->irq_work; } - schedule(); - out: if (full) - finish_wait(&work->full_waiters, &wait); + waitq = &rbwork->full_waiters; else - finish_wait(&work->waiters, &wait); + waitq = &rbwork->waiters; - if (!ret && !rb_watermark_hit(buffer, cpu, full) && signal_pending(current)) - ret = -EINTR; + ret = wait_event_interruptible((*waitq), + rb_wait_cond(rbwork, buffer, cpu, full, cond, data)); return ret; } -- cgit v1.2.3 From 2aa043a55b9a764c9cbde5a8c654eeaaffe224cf Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Google)" Date: Tue, 12 Mar 2024 08:15:08 -0400 Subject: tracing/ring-buffer: Fix wait_on_pipe() race When the trace_pipe_raw file is closed, there should be no new readers on the file descriptor. This is mostly handled with the waking and wait_index fields of the iterator. But there's still a slight race. CPU 0 CPU 1 ----- ----- wait_index++; index = wait_index; ring_buffer_wake_waiters(); wait_on_pipe() ring_buffer_wait(); The ring_buffer_wait() will miss the wakeup from CPU 1. The problem is that the ring_buffer_wait() needs the logic of: prepare_to_wait(); if (!condition) schedule(); Where the missing condition check is the iter->wait_index update. Have the ring_buffer_wait() take a conditional callback function and a data parameter that can be used within the wait_event_interruptible() of the ring_buffer_wait() function. In wait_on_pipe(), pass a condition function that will check if the wait_index has been updated, if it has, it will return true to break out of the wait_event_interruptible() loop. Create a new field "closed" in the trace_iterator and set it in the .flush() callback before calling ring_buffer_wake_waiters(). This will keep any new readers from waiting on a closed file descriptor. Have the wait_on_pipe() condition callback also check the closed field. Change the wait_index field of the trace_iterator to atomic_t. There's no reason it needs to be 'long' and making it atomic and using atomic_read_acquire() and atomic_fetch_inc_release() will provide the necessary memory barriers. Add a "woken" flag to tracing_buffers_splice_read() to exit the loop after one more try to fetch data. That is, if it waited for data and something woke it up, it should try to collect any new data and then exit back to user space. Link: https://lore.kernel.org/linux-trace-kernel/CAHk-=wgsNgewHFxZAJiAQznwPMqEtQmi1waeS2O1v6L4c_Um5A@mail.gmail.com/ Link: https://lore.kernel.org/linux-trace-kernel/20240312121703.557950713@goodmis.org Cc: stable@vger.kernel.org Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Andrew Morton Cc: Linus Torvalds Cc: linke li Cc: Rabin Vincent Fixes: f3ddb74ad0790 ("tracing: Wake up ring buffer waiters on closing of the file") Signed-off-by: Steven Rostedt (Google) --- include/linux/ring_buffer.h | 3 ++- include/linux/trace_events.h | 5 ++++- kernel/trace/ring_buffer.c | 13 ++++++++----- kernel/trace/trace.c | 43 +++++++++++++++++++++++++++++++------------ 4 files changed, 45 insertions(+), 19 deletions(-) (limited to 'kernel/trace/ring_buffer.c') diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h index 338a33db1577..dc5ae4e96aee 100644 --- a/include/linux/ring_buffer.h +++ b/include/linux/ring_buffer.h @@ -99,7 +99,8 @@ __ring_buffer_alloc(unsigned long size, unsigned flags, struct lock_class_key *k }) typedef bool (*ring_buffer_cond_fn)(void *data); -int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full); +int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full, + ring_buffer_cond_fn cond, void *data); __poll_t ring_buffer_poll_wait(struct trace_buffer *buffer, int cpu, struct file *filp, poll_table *poll_table, int full); void ring_buffer_wake_waiters(struct trace_buffer *buffer, int cpu); diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index d68ff9b1247f..fc6d0af56bb1 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -103,13 +103,16 @@ struct trace_iterator { unsigned int temp_size; char *fmt; /* modified format holder */ unsigned int fmt_size; - long wait_index; + atomic_t wait_index; /* trace_seq for __print_flags() and __print_symbolic() etc. */ struct trace_seq tmp_seq; cpumask_var_t started; + /* Set when the file is closed to prevent new waiters */ + bool closed; + /* it's true when current open file is snapshot */ bool snapshot; diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index f4c34b7c7e1e..350607cce869 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -902,23 +902,26 @@ static bool rb_wait_once(void *data) * @buffer: buffer to wait on * @cpu: the cpu buffer to wait on * @full: wait until the percentage of pages are available, if @cpu != RING_BUFFER_ALL_CPUS + * @cond: condition function to break out of wait (NULL to run once) + * @data: the data to pass to @cond. * * If @cpu == RING_BUFFER_ALL_CPUS then the task will wake up as soon * as data is added to any of the @buffer's cpu buffers. Otherwise * it will wait for data to be added to a specific cpu buffer. */ -int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full) +int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full, + ring_buffer_cond_fn cond, void *data) { struct ring_buffer_per_cpu *cpu_buffer; struct wait_queue_head *waitq; - ring_buffer_cond_fn cond; struct rb_irq_work *rbwork; - void *data; long once = 0; int ret = 0; - cond = rb_wait_once; - data = &once; + if (!cond) { + cond = rb_wait_once; + data = &once; + } /* * Depending on what the caller is waiting for, either any diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index c9c898307348..d390fea3a6a5 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1955,15 +1955,36 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu) #endif /* CONFIG_TRACER_MAX_TRACE */ +struct pipe_wait { + struct trace_iterator *iter; + int wait_index; +}; + +static bool wait_pipe_cond(void *data) +{ + struct pipe_wait *pwait = data; + struct trace_iterator *iter = pwait->iter; + + if (atomic_read_acquire(&iter->wait_index) != pwait->wait_index) + return true; + + return iter->closed; +} + static int wait_on_pipe(struct trace_iterator *iter, int full) { + struct pipe_wait pwait; int ret; /* Iterators are static, they should be filled or empty */ if (trace_buffer_iter(iter, iter->cpu_file)) return 0; - ret = ring_buffer_wait(iter->array_buffer->buffer, iter->cpu_file, full); + pwait.wait_index = atomic_read_acquire(&iter->wait_index); + pwait.iter = iter; + + ret = ring_buffer_wait(iter->array_buffer->buffer, iter->cpu_file, full, + wait_pipe_cond, &pwait); #ifdef CONFIG_TRACER_MAX_TRACE /* @@ -8398,9 +8419,9 @@ static int tracing_buffers_flush(struct file *file, fl_owner_t id) struct ftrace_buffer_info *info = file->private_data; struct trace_iterator *iter = &info->iter; - iter->wait_index++; + iter->closed = true; /* Make sure the waiters see the new wait_index */ - smp_wmb(); + (void)atomic_fetch_inc_release(&iter->wait_index); ring_buffer_wake_waiters(iter->array_buffer->buffer, iter->cpu_file); @@ -8500,6 +8521,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, .spd_release = buffer_spd_release, }; struct buffer_ref *ref; + bool woken = false; int page_size; int entries, i; ssize_t ret = 0; @@ -8573,17 +8595,17 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, /* did we read anything? */ if (!spd.nr_pages) { - long wait_index; if (ret) goto out; + if (woken) + goto out; + ret = -EAGAIN; if ((file->f_flags & O_NONBLOCK) || (flags & SPLICE_F_NONBLOCK)) goto out; - wait_index = READ_ONCE(iter->wait_index); - ret = wait_on_pipe(iter, iter->snapshot ? 0 : iter->tr->buffer_percent); if (ret) goto out; @@ -8592,10 +8614,8 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, if (!tracer_tracing_is_on(iter->tr)) goto out; - /* Make sure we see the new wait_index */ - smp_rmb(); - if (wait_index != iter->wait_index) - goto out; + /* Iterate one more time to collect any new data then exit */ + woken = true; goto again; } @@ -8618,9 +8638,8 @@ static long tracing_buffers_ioctl(struct file *file, unsigned int cmd, unsigned mutex_lock(&trace_types_lock); - iter->wait_index++; /* Make sure the waiters see the new wait_index */ - smp_wmb(); + (void)atomic_fetch_inc_release(&iter->wait_index); ring_buffer_wake_waiters(iter->array_buffer->buffer, iter->cpu_file); -- cgit v1.2.3 From 6b76323e5a483e53568254146c3d141123f3b839 Mon Sep 17 00:00:00 2001 From: Vincent Donnefort Date: Tue, 20 Feb 2024 20:23:05 +0000 Subject: ring-buffer: Zero ring-buffer sub-buffers In preparation for the ring-buffer memory mapping where each subbuf will be accessible to user-space, zero all the page allocations. Link: https://lore.kernel.org/linux-trace-kernel/20240220202310.2489614-2-vdonnefort@google.com Signed-off-by: Vincent Donnefort Reviewed-by: Masami Hiramatsu (Google) Signed-off-by: Steven Rostedt (Google) --- kernel/trace/ring_buffer.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'kernel/trace/ring_buffer.c') diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 09df645ab9c7..67d32af48640 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -1515,7 +1515,8 @@ static int __rb_allocate_pages(struct ring_buffer_per_cpu *cpu_buffer, list_add(&bpage->list, pages); - page = alloc_pages_node(cpu_to_node(cpu_buffer->cpu), mflags, + page = alloc_pages_node(cpu_to_node(cpu_buffer->cpu), + mflags | __GFP_ZERO, cpu_buffer->buffer->subbuf_order); if (!page) goto free_pages; @@ -1600,7 +1601,8 @@ rb_allocate_cpu_buffer(struct trace_buffer *buffer, long nr_pages, int cpu) cpu_buffer->reader_page = bpage; - page = alloc_pages_node(cpu_to_node(cpu), GFP_KERNEL, cpu_buffer->buffer->subbuf_order); + page = alloc_pages_node(cpu_to_node(cpu), GFP_KERNEL | __GFP_ZERO, + cpu_buffer->buffer->subbuf_order); if (!page) goto fail_free_reader; bpage->page = page_address(page); @@ -5568,7 +5570,8 @@ ring_buffer_alloc_read_page(struct trace_buffer *buffer, int cpu) if (bpage->data) goto out; - page = alloc_pages_node(cpu_to_node(cpu), GFP_KERNEL | __GFP_NORETRY, + page = alloc_pages_node(cpu_to_node(cpu), + GFP_KERNEL | __GFP_NORETRY | __GFP_ZERO, cpu_buffer->buffer->subbuf_order); if (!page) { kfree(bpage); -- cgit v1.2.3 From f1e30cb6369251c03f63c564006f96a54197dcc4 Mon Sep 17 00:00:00 2001 From: linke li Date: Sat, 2 Mar 2024 12:42:21 +0800 Subject: ring-buffer: use READ_ONCE() to read cpu_buffer->commit_page in concurrent environment In function ring_buffer_iter_empty(), cpu_buffer->commit_page is read while other threads may change it. It may cause the time_stamp that read in the next line come from a different page. Use READ_ONCE() to avoid having to reason about compiler optimizations now and in future. Link: https://lore.kernel.org/linux-trace-kernel/tencent_DFF7D3561A0686B5E8FC079150A02505180A@qq.com Cc: Masami Hiramatsu Cc: Mathieu Desnoyers Signed-off-by: linke li Signed-off-by: Steven Rostedt (Google) --- kernel/trace/ring_buffer.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/trace/ring_buffer.c') diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 67d32af48640..788d321036bd 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -4382,7 +4382,7 @@ int ring_buffer_iter_empty(struct ring_buffer_iter *iter) cpu_buffer = iter->cpu_buffer; reader = cpu_buffer->reader_page; head_page = cpu_buffer->head_page; - commit_page = cpu_buffer->commit_page; + commit_page = READ_ONCE(cpu_buffer->commit_page); commit_ts = commit_page->page->time_stamp; /* -- cgit v1.2.3 From b70f2938242a028f8e9473781ede175486a59dc8 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Google)" Date: Fri, 15 Mar 2024 06:31:15 -0400 Subject: ring-buffer: Make wake once of ring_buffer_wait() more robust The default behavior of ring_buffer_wait() when passed a NULL "cond" parameter is to exit the function the first time it is woken up. The current implementation uses a counter that starts at zero and when it is greater than one it exits the wait_event_interruptible(). But this relies on the internal working of wait_event_interruptible() as that code basically has: if (cond) return; prepare_to_wait(); if (!cond) schedule(); finish_wait(); That is, cond is called twice before it sleeps. The default cond of ring_buffer_wait() needs to account for that and wait for its counter to increment twice before exiting. Instead, use the seq/atomic_inc logic that is used by the tracing code that calls this function. Add an atomic_t seq to rb_irq_work and when cond is NULL, have the default callback take a descriptor as its data that holds the rbwork and the value of the seq when it started. The wakeups will now increment the rbwork->seq and the cond callback will simply check if that number is different, and no longer have to rely on the implementation of wait_event_interruptible(). Link: https://lore.kernel.org/linux-trace-kernel/20240315063115.6cb5d205@gandalf.local.home Cc: Masami Hiramatsu Cc: Mathieu Desnoyers Fixes: 7af9ded0c2ca ("ring-buffer: Use wait_event_interruptible() in ring_buffer_wait()") Signed-off-by: Steven Rostedt (Google) --- kernel/trace/ring_buffer.c | 34 +++++++++++++++++++++------------- 1 file changed, 21 insertions(+), 13 deletions(-) (limited to 'kernel/trace/ring_buffer.c') diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 788d321036bd..25476ead681b 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -384,6 +384,7 @@ struct rb_irq_work { struct irq_work work; wait_queue_head_t waiters; wait_queue_head_t full_waiters; + atomic_t seq; bool waiters_pending; bool full_waiters_pending; bool wakeup_full; @@ -753,6 +754,9 @@ static void rb_wake_up_waiters(struct irq_work *work) { struct rb_irq_work *rbwork = container_of(work, struct rb_irq_work, work); + /* For waiters waiting for the first wake up */ + (void)atomic_fetch_inc_release(&rbwork->seq); + wake_up_all(&rbwork->waiters); if (rbwork->full_waiters_pending || rbwork->wakeup_full) { /* Only cpu_buffer sets the above flags */ @@ -881,20 +885,21 @@ rb_wait_cond(struct rb_irq_work *rbwork, struct trace_buffer *buffer, return false; } +struct rb_wait_data { + struct rb_irq_work *irq_work; + int seq; +}; + /* * The default wait condition for ring_buffer_wait() is to just to exit the * wait loop the first time it is woken up. */ static bool rb_wait_once(void *data) { - long *once = data; + struct rb_wait_data *rdata = data; + struct rb_irq_work *rbwork = rdata->irq_work; - /* wait_event() actually calls this twice before scheduling*/ - if (*once > 1) - return true; - - (*once)++; - return false; + return atomic_read_acquire(&rbwork->seq) != rdata->seq; } /** @@ -915,14 +920,9 @@ int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full, struct ring_buffer_per_cpu *cpu_buffer; struct wait_queue_head *waitq; struct rb_irq_work *rbwork; - long once = 0; + struct rb_wait_data rdata; int ret = 0; - if (!cond) { - cond = rb_wait_once; - data = &once; - } - /* * Depending on what the caller is waiting for, either any * data in any cpu buffer, or a specific buffer, put the @@ -944,6 +944,14 @@ int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full, else waitq = &rbwork->waiters; + /* Set up to exit loop as soon as it is woken */ + if (!cond) { + cond = rb_wait_once; + rdata.irq_work = rbwork; + rdata.seq = atomic_read_acquire(&rbwork->seq); + data = &rdata; + } + ret = wait_event_interruptible((*waitq), rb_wait_cond(rbwork, buffer, cpu, full, cond, data)); -- cgit v1.2.3