tracing: ring_buffer: Rewind persistent ring buffer on reboot

Rewind persistent ring buffer pages which have been read in the previous
boot. Those pages are highly possible to be lost before writing it to the
disk if the previous kernel crashed. In this case, the trace data is kept
on the persistent ring buffer, but it can not be read because its commit
size has been reset after read.  This skips clearing the commit size of
each sub-buffer and recover it after reboot.

Note: If you read the previous boot data via trace_pipe, that is not
accessible in that time. But reboot without clearing (or reusing) the read
data, the read data is recovered again in the next boot.

Thus, when you read the previous boot data, clear it by `echo > trace`.

Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Link: https://lore.kernel.org/174899582116.955054.773265393511190051.stgit@mhiramat.tok.corp.google.com
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>

diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 00fc38d70e868adff3716f2a488ce4aea76c5609..a99ed4716de9cabd7bf486b2470b6cda475bedf8 100644 (file)
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -1358,6 +1358,13 @@ static inline void rb_inc_page(struct buffer_page **bpage)
        *bpage = list_entry(p, struct buffer_page, list);
 }
 
+static inline void rb_dec_page(struct buffer_page **bpage)
+{
+       struct list_head *p = rb_list_head((*bpage)->list.prev);
+
+       *bpage = list_entry(p, struct buffer_page, list);
+}
+
 static struct buffer_page *
 rb_set_head_page(struct ring_buffer_per_cpu *cpu_buffer)
 {
@@ -1866,10 +1873,11 @@ static int rb_validate_buffer(struct buffer_data_page *dpage, int cpu)
 static void rb_meta_validate_events(struct ring_buffer_per_cpu *cpu_buffer)
 {
        struct ring_buffer_cpu_meta *meta = cpu_buffer->ring_meta;
-       struct buffer_page *head_page;
+       struct buffer_page *head_page, *orig_head;
        unsigned long entry_bytes = 0;
        unsigned long entries = 0;
        int ret;
+       u64 ts;
        int i;
 
        if (!meta || !meta->head_buffer)
@@ -1885,8 +1893,98 @@ static void rb_meta_validate_events(struct ring_buffer_per_cpu *cpu_buffer)
        entry_bytes += local_read(&cpu_buffer->reader_page->page->commit);
        local_set(&cpu_buffer->reader_page->entries, ret);
 
-       head_page = cpu_buffer->head_page;
+       orig_head = head_page = cpu_buffer->head_page;
+       ts = head_page->page->time_stamp;
+
+       /*
+        * Try to rewind the head so that we can read the pages which already
+        * read in the previous boot.
+        */
+       if (head_page == cpu_buffer->tail_page)
+               goto skip_rewind;
+
+       rb_dec_page(&head_page);
+       for (i = 0; i < meta->nr_subbufs + 1; i++, rb_dec_page(&head_page)) {
+
+               /* Rewind until tail (writer) page. */
+               if (head_page == cpu_buffer->tail_page)
+                       break;
+
+               /* Ensure the page has older data than head. */
+               if (ts < head_page->page->time_stamp)
+                       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);
+               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_commit(head_page);
+       }
+       if (i)
+               pr_info("Ring buffer [%d] rewound %d pages\n", cpu_buffer->cpu, i);
+
+       /* The last rewound page must be skipped. */
+       if (head_page != orig_head)
+               rb_inc_page(&head_page);
+
+       /*
+        * If the ring buffer was rewound, then inject the reader page
+        * into the location just before the original head page.
+        */
+       if (head_page != orig_head) {
+               struct buffer_page *bpage = orig_head;
+
+               rb_dec_page(&bpage);
+               /*
+                * Insert the reader_page before the original head page.
+                * Since the list encode RB_PAGE flags, general list
+                * operations should be avoided.
+                */
+               cpu_buffer->reader_page->list.next = &orig_head->list;
+               cpu_buffer->reader_page->list.prev = orig_head->list.prev;
+               orig_head->list.prev = &cpu_buffer->reader_page->list;
+               bpage->list.next = &cpu_buffer->reader_page->list;
+
+               /* Make the head_page the reader page */
+               cpu_buffer->reader_page = head_page;
+               bpage = head_page;
+               rb_inc_page(&head_page);
+               head_page->list.prev = bpage->list.prev;
+               rb_dec_page(&bpage);
+               bpage->list.next = &head_page->list;
+               rb_set_list_to_head(&bpage->list);
+               cpu_buffer->pages = &head_page->list;
+
+               cpu_buffer->head_page = head_page;
+               meta->head_buffer = (unsigned long)head_page->page;
+
+               /* Reset all the indexes */
+               bpage = cpu_buffer->reader_page;
+               meta->buffers[0] = rb_meta_subbuf_idx(meta, bpage->page);
+               bpage->id = 0;
+
+               for (i = 1, bpage = head_page; i < meta->nr_subbufs;
+                    i++, rb_inc_page(&bpage)) {
+                       meta->buffers[i] = rb_meta_subbuf_idx(meta, bpage->page);
+                       bpage->id = i;
+               }
+
+               /* We'll restart verifying from orig_head */
+               head_page = orig_head;
+       }
+
+ skip_rewind:
        /* If the commit_buffer is the reader page, update the commit page */
        if (meta->commit_buffer == (unsigned long)cpu_buffer->reader_page->page) {
                cpu_buffer->commit_page = cpu_buffer->reader_page;
@@ -5342,7 +5440,6 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
         */
        local_set(&cpu_buffer->reader_page->write, 0);
        local_set(&cpu_buffer->reader_page->entries, 0);
-       local_set(&cpu_buffer->reader_page->page->commit, 0);
        cpu_buffer->reader_page->real_end = 0;
 
  spin: