From: Masami Hiramatsu (Google) <[email protected]> Skip invalid sub-buffers when rewinding the persistent ring buffer instead of stopping the rewinding the ring buffer. The skipped buffers are cleared.
To ensure the rewinding stops at the unused page, this also clears buffer_data_page::time_stamp when tracing resets the buffer. This allows us to identify unused pages and empty pages. Signed-off-by: Masami Hiramatsu (Google) <[email protected]> --- Changes in v19: - Cleanup rb_validate_buffer() so that it is more readable, and add a comment about the timestamp validation. Changes in v18: - Reset timestamp of reader_page when the entire cpu_buffer is invalid. - Minor update by new fix. Changes in v17: - Fix to verify head_page at first before using its timestamp. - Reset timestamp if the page is invalid. Changes in v12: - Fix build error. Changes in v11: - Reset timestamp when the buffer is invalid. - When rewinding, skip subbuf page if timestamp is wrong and check timestamp after validating buffer data page. Changes in v10: - Newly added. --- kernel/trace/ring_buffer.c | 102 +++++++++++++++++++++++++++----------------- 1 file changed, 63 insertions(+), 39 deletions(-) diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 2ac09b1abe9f..9a82eaa684c1 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -363,6 +363,7 @@ struct buffer_page { static void rb_init_page(struct buffer_data_page *bpage) { local_set(&bpage->commit, 0); + bpage->time_stamp = 0; } static __always_inline unsigned int rb_page_commit(struct buffer_page *bpage) @@ -1878,12 +1879,14 @@ static int rb_read_data_buffer(struct buffer_data_page *dpage, int tail, int cpu return events; } -static int rb_validate_buffer(struct buffer_data_page *dpage, int cpu, - struct ring_buffer_cpu_meta *meta) +static int rb_validate_buffer(struct buffer_page *bpage, int cpu, + struct ring_buffer_cpu_meta *meta, u64 prev_ts, u64 next_ts) { + struct buffer_data_page *dpage = bpage->page; unsigned long long ts; unsigned long tail; u64 delta; + int ret; /* * When a sub-buffer is recovered from a read, the commit value may @@ -1892,9 +1895,27 @@ static int rb_validate_buffer(struct buffer_data_page *dpage, int cpu, * subbuf_size is considered invalid. */ tail = local_read(&dpage->commit) & ~RB_MISSED_MASK; - if (tail > meta->subbuf_size - BUF_PAGE_HDR_SIZE) - return -1; - return rb_read_data_buffer(dpage, tail, cpu, &ts, &delta); + if (tail <= meta->subbuf_size - BUF_PAGE_HDR_SIZE) + ret = rb_read_data_buffer(dpage, tail, cpu, &ts, &delta); + else + ret = -1; + + /* + * The timestamp must be greater than @prev_ts and smaller than @next_ts. + * Since this function works in both forward (verify) and reverse (unwind) + * loop, we don't know both @prev_ts and @next_ts at the same time. + * So use the known boundary as the boundary. + */ + if (ret < 0 || (prev_ts && prev_ts > ts) || (next_ts && ts > next_ts)) { + local_set(&bpage->entries, 0); + local_set(&dpage->commit, 0); + dpage->time_stamp = prev_ts ? prev_ts : next_ts; + ret = -1; + } else { + local_set(&bpage->entries, ret); + } + + return ret; } /* If the meta data has been validated, now validate the events */ @@ -1915,25 +1936,29 @@ static void rb_meta_validate_events(struct ring_buffer_per_cpu *cpu_buffer) orig_head = head_page = cpu_buffer->head_page; orig_reader = cpu_buffer->reader_page; - /* Do the reader page first */ - ret = rb_validate_buffer(orig_reader->page, cpu_buffer->cpu, meta); + /* Do the head page first */ + ret = rb_validate_buffer(head_page, cpu_buffer->cpu, meta, 0, 0); + if (ret < 0) { + pr_info("Ring buffer meta [%d] invalid head page detected\n", + cpu_buffer->cpu); + goto skip_rewind; + } + ts = head_page->page->time_stamp; + + /* Do the reader page - reader must be previous to head. */ + ret = rb_validate_buffer(orig_reader, cpu_buffer->cpu, meta, 0, ts); if (ret < 0) { pr_info("Ring buffer meta [%d] invalid reader page detected\n", cpu_buffer->cpu); discarded++; - /* Instead of discard whole ring buffer, discard only this sub-buffer. */ - local_set(&orig_reader->entries, 0); - local_set(&orig_reader->page->commit, 0); } else { entries += ret; entry_bytes += rb_page_size(orig_reader); - local_set(&orig_reader->entries, ret); + ts = orig_reader->page->time_stamp; } - ts = head_page->page->time_stamp; - /* - * Try to rewind the head so that we can read the pages which already + * Try to rewind the head so that we can read the pages which are already * read in the previous boot. */ if (head_page == cpu_buffer->tail_page) @@ -1946,26 +1971,27 @@ static void rb_meta_validate_events(struct ring_buffer_per_cpu *cpu_buffer) if (head_page == cpu_buffer->tail_page) break; - /* Ensure the page has older data than head. */ - if (ts < head_page->page->time_stamp) + /* Rewind until unused page (no timestamp, no commit). */ + if (!head_page->page->time_stamp && rb_page_commit(head_page) == 0) break; - ts = head_page->page->time_stamp; - /* Ensure the page has correct timestamp and some data. */ - if (!ts || rb_page_commit(head_page) == 0) - break; - - /* Stop rewind if the page is invalid. */ - ret = rb_validate_buffer(head_page->page, cpu_buffer->cpu, meta); - if (ret < 0) - break; - - /* Recover the number of entries and update stats. */ - local_set(&head_page->entries, ret); - if (ret) - local_inc(&cpu_buffer->pages_touched); - entries += ret; - entry_bytes += rb_page_size(head_page); + /* + * Skip if the page is invalid, or its timestamp is newer than the + * previous valid page. + */ + ret = rb_validate_buffer(head_page, cpu_buffer->cpu, meta, 0, ts); + if (ret < 0) { + if (!discarded) + pr_info("Ring buffer meta [%d] invalid buffer page detected\n", + cpu_buffer->cpu); + discarded++; + } else { + entries += ret; + entry_bytes += rb_page_size(head_page); + if (ret > 0) + local_inc(&cpu_buffer->pages_touched); + ts = head_page->page->time_stamp; + } } if (i) pr_info("Ring buffer [%d] rewound %d pages\n", cpu_buffer->cpu, i); @@ -2027,6 +2053,7 @@ static void rb_meta_validate_events(struct ring_buffer_per_cpu *cpu_buffer) /* Nothing more to do, the only page is the reader page */ goto done; } + ts = head_page->page->time_stamp; /* Iterate until finding the commit page */ for (i = 0; i < meta->nr_subbufs + 1; i++, rb_inc_page(&head_page)) { @@ -2035,15 +2062,12 @@ static void rb_meta_validate_events(struct ring_buffer_per_cpu *cpu_buffer) if (head_page == orig_reader) continue; - ret = rb_validate_buffer(head_page->page, cpu_buffer->cpu, meta); + ret = rb_validate_buffer(head_page, cpu_buffer->cpu, meta, ts, 0); if (ret < 0) { if (!discarded) pr_info("Ring buffer meta [%d] invalid buffer page detected\n", cpu_buffer->cpu); discarded++; - /* Instead of discard whole ring buffer, discard only this sub-buffer. */ - local_set(&head_page->entries, 0); - local_set(&head_page->page->commit, 0); } else { /* If the buffer has content, update pages_touched */ if (ret) @@ -2051,7 +2075,7 @@ static void rb_meta_validate_events(struct ring_buffer_per_cpu *cpu_buffer) entries += ret; entry_bytes += rb_page_size(head_page); - local_set(&head_page->entries, ret); + ts = head_page->page->time_stamp; } if (head_page == cpu_buffer->commit_page) break; @@ -2079,12 +2103,12 @@ static void rb_meta_validate_events(struct ring_buffer_per_cpu *cpu_buffer) /* Reset the reader page */ local_set(&cpu_buffer->reader_page->entries, 0); - local_set(&cpu_buffer->reader_page->page->commit, 0); + rb_init_page(cpu_buffer->reader_page->page); /* Reset all the subbuffers */ for (i = 0; i < meta->nr_subbufs - 1; i++, rb_inc_page(&head_page)) { local_set(&head_page->entries, 0); - local_set(&head_page->page->commit, 0); + rb_init_page(head_page->page); } }
