From ead6ecfddea54f4754c97f64ab7198cc1d8c0daa Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Tue, 17 Mar 2020 17:32:24 -0400 Subject: ring-buffer: Have ring_buffer_empty() not depend on tracing stopped It was complained about that when the trace file is read, that the tracing is disabled, as the iterator expects writing to the buffer it reads is not updated. Several steps are needed to make the iterator handle a writer, by testing if things have changed as it reads. This step is to make ring_buffer_empty() expect the buffer to be changing. Note if the current location of the iterator is overwritten, then it will return false as new data is being added. Note, that this means that data will be skipped. Link: http://lkml.kernel.org/r/20200317213415.870741809@goodmis.org Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/ring_buffer.c | 25 +++++++++++++++++++++++-- 1 file changed, 23 insertions(+), 2 deletions(-) (limited to 'kernel/trace/ring_buffer.c') diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 61f0e92ace99..1718520a2809 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -3590,16 +3590,37 @@ int ring_buffer_iter_empty(struct ring_buffer_iter *iter) struct buffer_page *reader; struct buffer_page *head_page; struct buffer_page *commit_page; + struct buffer_page *curr_commit_page; unsigned commit; + u64 curr_commit_ts; + u64 commit_ts; cpu_buffer = iter->cpu_buffer; - - /* Remember, trace recording is off when iterator is in use */ reader = cpu_buffer->reader_page; head_page = cpu_buffer->head_page; commit_page = cpu_buffer->commit_page; + commit_ts = commit_page->page->time_stamp; + + /* + * When the writer goes across pages, it issues a cmpxchg which + * is a mb(), which will synchronize with the rmb here. + * (see rb_tail_page_update()) + */ + smp_rmb(); commit = rb_page_commit(commit_page); + /* We want to make sure that the commit page doesn't change */ + smp_rmb(); + + /* Make sure commit page didn't change */ + curr_commit_page = READ_ONCE(cpu_buffer->commit_page); + curr_commit_ts = READ_ONCE(curr_commit_page->page->time_stamp); + + /* If the commit page changed, then there's more data */ + if (curr_commit_page != commit_page || + curr_commit_ts != commit_ts) + return 0; + /* Still racy, as it may return a false positive, but that's OK */ return ((iter->head_page == commit_page && iter->head == commit) || (iter->head_page == reader && commit_page == head_page && head_page->read == commit && -- cgit v1.2.3 From bc1a72afdc4a91844928831cac85731566e03bc6 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Tue, 17 Mar 2020 17:32:25 -0400 Subject: ring-buffer: Rename ring_buffer_read() to read_buffer_iter_advance() When the ring buffer was first created, the iterator followed the normal producer/consumer operations where it had both a peek() operation, that just returned the event at the current location, and a read(), that would return the event at the current location and also increment the iterator such that the next peek() or read() will return the next event. The only use of the ring_buffer_read() is currently to move the iterator to the next location and nothing now actually reads the event it returns. Rename this function to its actual use case to ring_buffer_iter_advance(), which also adds the "iter" part to the name, which is more meaningful. As the timestamp returned by ring_buffer_read() was never used, there's no reason that this new version should bother having returning it. It will also become a void function. Link: http://lkml.kernel.org/r/20200317213416.018928618@goodmis.org Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/ring_buffer.c | 23 ++++++----------------- 1 file changed, 6 insertions(+), 17 deletions(-) (limited to 'kernel/trace/ring_buffer.c') diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 1718520a2809..f57eeaa80e3e 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -4318,35 +4318,24 @@ ring_buffer_read_finish(struct ring_buffer_iter *iter) EXPORT_SYMBOL_GPL(ring_buffer_read_finish); /** - * ring_buffer_read - read the next item in the ring buffer by the iterator + * ring_buffer_iter_advance - advance the iterator to the next location * @iter: The ring buffer iterator - * @ts: The time stamp of the event read. * - * This reads the next event in the ring buffer and increments the iterator. + * Move the location of the iterator such that the next read will + * be the next location of the iterator. */ -struct ring_buffer_event * -ring_buffer_read(struct ring_buffer_iter *iter, u64 *ts) +void ring_buffer_iter_advance(struct ring_buffer_iter *iter) { - struct ring_buffer_event *event; struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer; unsigned long flags; raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); - again: - event = rb_iter_peek(iter, ts); - if (!event) - goto out; - - if (event->type_len == RINGBUF_TYPE_PADDING) - goto again; rb_advance_iter(iter); - out: - raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); - return event; + raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); } -EXPORT_SYMBOL_GPL(ring_buffer_read); +EXPORT_SYMBOL_GPL(ring_buffer_iter_advance); /** * ring_buffer_size - return the size of the ring buffer (in bytes) -- cgit v1.2.3 From 28e3fc56a471bbac39d24571e11dde64b15de988 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Tue, 17 Mar 2020 17:32:26 -0400 Subject: ring-buffer: Add page_stamp to iterator for synchronization Have the ring_buffer_iter structure contain a page_stamp, such that it can be used to see if the writer entered the page the iterator is on. When going to a new page, the iterator will record the time stamp of that page. When reading events, it can copy the event to an internal buffer on the iterator (to be implemented later), then check the page's time stamp with its own to see if the writer entered the page. If so, it will need to try to read the event again. Link: http://lkml.kernel.org/r/20200317213416.163549674@goodmis.org Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/ring_buffer.c | 10 +++++++--- 1 file changed, 7 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 f57eeaa80e3e..e689bdcb53e8 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -507,6 +507,7 @@ struct ring_buffer_iter { struct buffer_page *cache_reader_page; unsigned long cache_read; u64 read_stamp; + u64 page_stamp; }; /** @@ -1959,7 +1960,7 @@ static void rb_inc_iter(struct ring_buffer_iter *iter) else rb_inc_page(cpu_buffer, &iter->head_page); - iter->read_stamp = iter->head_page->page->time_stamp; + iter->page_stamp = iter->read_stamp = iter->head_page->page->time_stamp; iter->head = 0; } @@ -3551,10 +3552,13 @@ static void rb_iter_reset(struct ring_buffer_iter *iter) iter->cache_reader_page = iter->head_page; iter->cache_read = cpu_buffer->read; - if (iter->head) + if (iter->head) { iter->read_stamp = cpu_buffer->read_stamp; - else + iter->page_stamp = cpu_buffer->reader_page->page->time_stamp; + } else { iter->read_stamp = iter->head_page->page->time_stamp; + iter->page_stamp = iter->read_stamp; + } } /** -- cgit v1.2.3 From 785888c544e0433f601df18ff98a3215b380b9c3 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Tue, 17 Mar 2020 17:32:27 -0400 Subject: ring-buffer: Have rb_iter_head_event() handle concurrent writer Have the ring_buffer_iter structure have a place to store an event, such that it can not be overwritten by a writer, and load it in such a way via rb_iter_head_event() that it will return NULL and reset the iter to the start of the current page if a writer updated the page. Link: http://lkml.kernel.org/r/20200317213416.306959216@goodmis.org Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/ring_buffer.c | 106 ++++++++++++++++++++++++++++++++------------- 1 file changed, 75 insertions(+), 31 deletions(-) (limited to 'kernel/trace/ring_buffer.c') diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index e689bdcb53e8..3d718add73c1 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -503,11 +503,13 @@ struct trace_buffer { struct ring_buffer_iter { struct ring_buffer_per_cpu *cpu_buffer; unsigned long head; + unsigned long next_event; struct buffer_page *head_page; struct buffer_page *cache_reader_page; unsigned long cache_read; u64 read_stamp; u64 page_stamp; + struct ring_buffer_event *event; }; /** @@ -1914,15 +1916,59 @@ rb_reader_event(struct ring_buffer_per_cpu *cpu_buffer) cpu_buffer->reader_page->read); } -static __always_inline struct ring_buffer_event * -rb_iter_head_event(struct ring_buffer_iter *iter) +static __always_inline unsigned rb_page_commit(struct buffer_page *bpage) { - return __rb_page_index(iter->head_page, iter->head); + return local_read(&bpage->page->commit); } -static __always_inline unsigned rb_page_commit(struct buffer_page *bpage) +static struct ring_buffer_event * +rb_iter_head_event(struct ring_buffer_iter *iter) { - return local_read(&bpage->page->commit); + struct ring_buffer_event *event; + struct buffer_page *iter_head_page = iter->head_page; + unsigned long commit; + unsigned length; + + /* + * When the writer goes across pages, it issues a cmpxchg which + * is a mb(), which will synchronize with the rmb here. + * (see rb_tail_page_update() and __rb_reserve_next()) + */ + commit = rb_page_commit(iter_head_page); + smp_rmb(); + event = __rb_page_index(iter_head_page, iter->head); + length = rb_event_length(event); + + /* + * READ_ONCE() doesn't work on functions and we don't want the + * compiler doing any crazy optimizations with length. + */ + barrier(); + + if ((iter->head + length) > commit || length > BUF_MAX_DATA_SIZE) + /* Writer corrupted the read? */ + goto reset; + + memcpy(iter->event, event, length); + /* + * If the page stamp is still the same after this rmb() then the + * event was safely copied without the writer entering the page. + */ + smp_rmb(); + + /* Make sure the page didn't change since we read this */ + if (iter->page_stamp != iter_head_page->page->time_stamp || + commit > rb_page_commit(iter_head_page)) + goto reset; + + iter->next_event = iter->head + length; + return iter->event; + reset: + /* Reset to the beginning */ + iter->page_stamp = iter->read_stamp = iter->head_page->page->time_stamp; + iter->head = 0; + iter->next_event = 0; + return NULL; } /* Size is determined by what has been committed */ @@ -1962,6 +2008,7 @@ static void rb_inc_iter(struct ring_buffer_iter *iter) iter->page_stamp = iter->read_stamp = iter->head_page->page->time_stamp; iter->head = 0; + iter->next_event = 0; } /* @@ -3548,6 +3595,7 @@ static void rb_iter_reset(struct ring_buffer_iter *iter) /* Iterator usage is expected to have record disabled */ iter->head_page = cpu_buffer->reader_page; iter->head = cpu_buffer->reader_page->read; + iter->next_event = iter->head; iter->cache_reader_page = iter->head_page; iter->cache_read = cpu_buffer->read; @@ -3625,7 +3673,7 @@ int ring_buffer_iter_empty(struct ring_buffer_iter *iter) return 0; /* Still racy, as it may return a false positive, but that's OK */ - return ((iter->head_page == commit_page && iter->head == commit) || + return ((iter->head_page == commit_page && iter->head >= commit) || (iter->head_page == reader && commit_page == head_page && head_page->read == commit && iter->head == rb_page_commit(cpu_buffer->reader_page))); @@ -3853,15 +3901,22 @@ static void rb_advance_reader(struct ring_buffer_per_cpu *cpu_buffer) static void rb_advance_iter(struct ring_buffer_iter *iter) { struct ring_buffer_per_cpu *cpu_buffer; - struct ring_buffer_event *event; - unsigned length; cpu_buffer = iter->cpu_buffer; + /* If head == next_event then we need to jump to the next event */ + if (iter->head == iter->next_event) { + /* If the event gets overwritten again, there's nothing to do */ + if (rb_iter_head_event(iter) == NULL) + return; + } + + iter->head = iter->next_event; + /* * Check if we are at the end of the buffer. */ - if (iter->head >= rb_page_size(iter->head_page)) { + if (iter->next_event >= rb_page_size(iter->head_page)) { /* discarded commits can make the page empty */ if (iter->head_page == cpu_buffer->commit_page) return; @@ -3869,27 +3924,7 @@ static void rb_advance_iter(struct ring_buffer_iter *iter) return; } - event = rb_iter_head_event(iter); - - length = rb_event_length(event); - - /* - * This should not be called to advance the header if we are - * at the tail of the buffer. - */ - if (RB_WARN_ON(cpu_buffer, - (iter->head_page == cpu_buffer->commit_page) && - (iter->head + length > rb_commit_index(cpu_buffer)))) - return; - - rb_update_iter_read_stamp(iter, event); - - iter->head += length; - - /* check for end of page padding */ - if ((iter->head >= rb_page_size(iter->head_page)) && - (iter->head_page != cpu_buffer->commit_page)) - rb_inc_iter(iter); + rb_update_iter_read_stamp(iter, iter->event); } static int rb_lost_events(struct ring_buffer_per_cpu *cpu_buffer) @@ -4017,6 +4052,8 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts) } event = rb_iter_head_event(iter); + if (!event) + goto again; switch (event->type_len) { case RINGBUF_TYPE_PADDING: @@ -4233,10 +4270,16 @@ ring_buffer_read_prepare(struct trace_buffer *buffer, int cpu, gfp_t flags) if (!cpumask_test_cpu(cpu, buffer->cpumask)) return NULL; - iter = kmalloc(sizeof(*iter), flags); + iter = kzalloc(sizeof(*iter), flags); if (!iter) return NULL; + iter->event = kmalloc(BUF_MAX_DATA_SIZE, flags); + if (!iter->event) { + kfree(iter); + return NULL; + } + cpu_buffer = buffer->buffers[cpu]; iter->cpu_buffer = cpu_buffer; @@ -4317,6 +4360,7 @@ ring_buffer_read_finish(struct ring_buffer_iter *iter) atomic_dec(&cpu_buffer->record_disabled); atomic_dec(&cpu_buffer->buffer->resize_disabled); + kfree(iter->event); kfree(iter); } EXPORT_SYMBOL_GPL(ring_buffer_read_finish); -- cgit v1.2.3 From ff84c50cfb4b8dc68c982fb6c05a524e1539ee2f Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Tue, 17 Mar 2020 17:32:28 -0400 Subject: ring-buffer: Do not die if rb_iter_peek() fails more than thrice As the iterator will be reading a live buffer, and if the event being read is on a page that a writer crosses, it will fail and try again, the condition in rb_iter_peek() that only allows a retry to happen three times is no longer valid. Allow rb_iter_peek() to retry more than three times without killing the ring buffer, but only if rb_iter_head_event() had failed at least once. Link: http://lkml.kernel.org/r/20200317213416.452888193@goodmis.org Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/ring_buffer.c | 13 ++++++++++--- 1 file changed, 10 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 3d718add73c1..475338fda969 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -4012,6 +4012,7 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts) struct ring_buffer_per_cpu *cpu_buffer; struct ring_buffer_event *event; int nr_loops = 0; + bool failed = false; if (ts) *ts = 0; @@ -4038,10 +4039,14 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts) * to a data event, we should never loop more than three times. * Once for going to next page, once on time extend, and * finally once to get the event. - * (We never hit the following condition more than thrice). + * We should never hit the following condition more than thrice, + * unless the buffer is very small, and there's a writer + * that is causing the reader to fail getting an event. */ - if (RB_WARN_ON(cpu_buffer, ++nr_loops > 3)) + if (++nr_loops > 3) { + RB_WARN_ON(cpu_buffer, !failed); return NULL; + } if (rb_per_cpu_empty(cpu_buffer)) return NULL; @@ -4052,8 +4057,10 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts) } event = rb_iter_head_event(iter); - if (!event) + if (!event) { + failed = true; goto again; + } switch (event->type_len) { case RINGBUF_TYPE_PADDING: -- cgit v1.2.3 From 153368ce1bd0ccb47812a3185e824445a7024ea5 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Tue, 17 Mar 2020 17:32:29 -0400 Subject: ring-buffer: Optimize rb_iter_head_event() As it is fine to perform several "peeks" of event data in the ring buffer via the iterator before moving it forward, do not re-read the event, just return what was read before. Otherwise, it can cause inconsistent results, especially when testing multiple CPU buffers to interleave them. Link: http://lkml.kernel.org/r/20200317213416.592032170@goodmis.org Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/ring_buffer.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'kernel/trace/ring_buffer.c') diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 475338fda969..5979327254f9 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -1929,6 +1929,9 @@ rb_iter_head_event(struct ring_buffer_iter *iter) unsigned long commit; unsigned length; + if (iter->head != iter->next_event) + return iter->event; + /* * When the writer goes across pages, it issues a cmpxchg which * is a mb(), which will synchronize with the rmb here. -- cgit v1.2.3 From 07b8b10ec94f852502db739047a2803ed36ccf46 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Fri, 27 Mar 2020 16:21:22 -0400 Subject: ring-buffer: Make resize disable per cpu buffer instead of total buffer When the ring buffer becomes writable for even when the trace file is read, it must still not be resized. But since tracers can be activated while the trace file is being read, the irqsoff tracer can modify the per CPU buffers, and this can cause the reader of the trace file to update the wrong buffer's resize disable bit, as the irqsoff tracer swaps out cpu buffers. By making the resize disable per cpu_buffer, it makes the update follow the per cpu_buffer even if it's swapped out with the snapshot buffer and keeps the release of the trace file modifying the same data as the open did. Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/ring_buffer.c | 43 ++++++++++++++++++++++++++++++------------- 1 file changed, 30 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 5979327254f9..e2de5b448c91 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -441,6 +441,7 @@ enum { struct ring_buffer_per_cpu { int cpu; atomic_t record_disabled; + atomic_t resize_disabled; struct trace_buffer *buffer; raw_spinlock_t reader_lock; /* serialize readers */ arch_spinlock_t lock; @@ -484,7 +485,6 @@ struct trace_buffer { unsigned flags; int cpus; atomic_t record_disabled; - atomic_t resize_disabled; cpumask_var_t cpumask; struct lock_class_key *reader_lock_key; @@ -1740,18 +1740,24 @@ int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size, size = nr_pages * BUF_PAGE_SIZE; - /* - * Don't succeed if resizing is disabled, as a reader might be - * manipulating the ring buffer and is expecting a sane state while - * this is true. - */ - if (atomic_read(&buffer->resize_disabled)) - return -EBUSY; - /* prevent another thread from changing buffer sizes */ mutex_lock(&buffer->mutex); + if (cpu_id == RING_BUFFER_ALL_CPUS) { + /* + * Don't succeed if resizing is disabled, as a reader might be + * manipulating the ring buffer and is expecting a sane state while + * this is true. + */ + for_each_buffer_cpu(buffer, cpu) { + cpu_buffer = buffer->buffers[cpu]; + if (atomic_read(&cpu_buffer->resize_disabled)) { + err = -EBUSY; + goto out_err_unlock; + } + } + /* calculate the pages to update */ for_each_buffer_cpu(buffer, cpu) { cpu_buffer = buffer->buffers[cpu]; @@ -1819,6 +1825,16 @@ int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size, if (nr_pages == cpu_buffer->nr_pages) goto out; + /* + * Don't succeed if resizing is disabled, as a reader might be + * manipulating the ring buffer and is expecting a sane state while + * this is true. + */ + if (atomic_read(&cpu_buffer->resize_disabled)) { + err = -EBUSY; + goto out_err_unlock; + } + cpu_buffer->nr_pages_to_update = nr_pages - cpu_buffer->nr_pages; @@ -1888,6 +1904,7 @@ int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size, free_buffer_page(bpage); } } + out_err_unlock: mutex_unlock(&buffer->mutex); return err; } @@ -4294,7 +4311,7 @@ ring_buffer_read_prepare(struct trace_buffer *buffer, int cpu, gfp_t flags) iter->cpu_buffer = cpu_buffer; - atomic_inc(&buffer->resize_disabled); + atomic_inc(&cpu_buffer->resize_disabled); atomic_inc(&cpu_buffer->record_disabled); return iter; @@ -4369,7 +4386,7 @@ ring_buffer_read_finish(struct ring_buffer_iter *iter) raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); atomic_dec(&cpu_buffer->record_disabled); - atomic_dec(&cpu_buffer->buffer->resize_disabled); + atomic_dec(&cpu_buffer->resize_disabled); kfree(iter->event); kfree(iter); } @@ -4474,7 +4491,7 @@ void ring_buffer_reset_cpu(struct trace_buffer *buffer, int cpu) if (!cpumask_test_cpu(cpu, buffer->cpumask)) return; - atomic_inc(&buffer->resize_disabled); + atomic_inc(&cpu_buffer->resize_disabled); atomic_inc(&cpu_buffer->record_disabled); /* Make sure all commits have finished */ @@ -4495,7 +4512,7 @@ void ring_buffer_reset_cpu(struct trace_buffer *buffer, int cpu) raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); atomic_dec(&cpu_buffer->record_disabled); - atomic_dec(&buffer->resize_disabled); + atomic_dec(&cpu_buffer->resize_disabled); } EXPORT_SYMBOL_GPL(ring_buffer_reset_cpu); -- cgit v1.2.3 From 1039221cc2787dee51a7ffbf9b0e79d192dadf76 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Tue, 17 Mar 2020 17:32:30 -0400 Subject: ring-buffer: Do not disable recording when there is an iterator Now that the iterator can handle a concurrent writer, do not disable writing to the ring buffer when there is an iterator present. Link: http://lkml.kernel.org/r/20200317213416.759770696@goodmis.org Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/ring_buffer.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'kernel/trace/ring_buffer.c') diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index e2de5b448c91..af2f10d9f3f1 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -4312,7 +4312,6 @@ ring_buffer_read_prepare(struct trace_buffer *buffer, int cpu, gfp_t flags) iter->cpu_buffer = cpu_buffer; atomic_inc(&cpu_buffer->resize_disabled); - atomic_inc(&cpu_buffer->record_disabled); return iter; } @@ -4385,7 +4384,6 @@ ring_buffer_read_finish(struct ring_buffer_iter *iter) rb_check_pages(cpu_buffer); raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); - atomic_dec(&cpu_buffer->record_disabled); atomic_dec(&cpu_buffer->resize_disabled); kfree(iter->event); kfree(iter); -- cgit v1.2.3 From c9b7a4a72ff64e67b7e877a99fd652230dc26058 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Tue, 17 Mar 2020 17:32:32 -0400 Subject: ring-buffer/tracing: Have iterator acknowledge dropped events Have the ring_buffer_iterator set a flag if events were dropped as it were to go and peek at the next event. Have the trace file display this fact if it happened with a "LOST EVENTS" message. Link: http://lkml.kernel.org/r/20200317213417.045858900@goodmis.org Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/ring_buffer.c | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'kernel/trace/ring_buffer.c') diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index af2f10d9f3f1..6f0b42ceeb00 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -510,6 +510,7 @@ struct ring_buffer_iter { u64 read_stamp; u64 page_stamp; struct ring_buffer_event *event; + int missed_events; }; /** @@ -1988,6 +1989,7 @@ rb_iter_head_event(struct ring_buffer_iter *iter) iter->page_stamp = iter->read_stamp = iter->head_page->page->time_stamp; iter->head = 0; iter->next_event = 0; + iter->missed_events = 1; return NULL; } @@ -4191,6 +4193,20 @@ ring_buffer_peek(struct trace_buffer *buffer, int cpu, u64 *ts, return event; } +/** ring_buffer_iter_dropped - report if there are dropped events + * @iter: The ring buffer iterator + * + * Returns true if there was dropped events since the last peek. + */ +bool ring_buffer_iter_dropped(struct ring_buffer_iter *iter) +{ + bool ret = iter->missed_events != 0; + + iter->missed_events = 0; + return ret; +} +EXPORT_SYMBOL_GPL(ring_buffer_iter_dropped); + /** * ring_buffer_iter_peek - peek at the next event to be read * @iter: The ring buffer iterator -- cgit v1.2.3