queue-6.18/ring-buffer-skip-invalid-sub-buffers-when-validating.patch

From b96aeaf74e844796fdd5b68d65413a5e1434de0e Mon Sep 17 00:00:00 2001
From: Sasha Levin <sashal@kernel.org>
Date: Fri, 22 May 2026 13:08:58 -0400
Subject: ring-buffer: Skip invalid sub-buffers when validating persistent ring
 buffer

From: Masami Hiramatsu (Google) <mhiramat@kernel.org>

[ Upstream commit eb3bd277b37cd435d26a44a40d8f7c87ff16feb6 ]

Skip invalid sub-buffers when validating the persistent ring buffer
instead of discarding the entire ring buffer. Only skipped buffers
are invalidated (cleared).

If the cache data in memory fails to be synchronized during a reboot,
the persistent ring buffer may become partially corrupted, but other
sub-buffers may still contain readable event data. Only discard the
subbuffers that are found to be corrupted.

Link: https://lore.kernel.org/all/20260520185018.051228084@kernel.org/

Link: https://patch.msgid.link/20260522171050.914418536@kernel.org
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
[SDR: Fixed max_loops in rb_iter_peek() as well ]
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Stable-dep-of: 6c001a62c34f ("ring-buffer: Add checking nr_subbufs to persistent ring buffer validation")
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 kernel/trace/ring_buffer.c | 118 ++++++++++++++++++++++---------------
 1 file changed, 72 insertions(+), 46 deletions(-)

diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index fc1c0034bc985..eed5c45b86ae6 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -412,6 +412,12 @@ static __always_inline unsigned int rb_page_capacity(struct buffer_page *bpage)
 	return (PAGE_SIZE << bpage->order) - BUF_PAGE_HDR_SIZE;
 }
 
+/* Size is determined by what has been committed */
+static __always_inline unsigned int rb_page_size(struct buffer_page *bpage)
+{
+	return rb_page_commit(bpage) & ~RB_MISSED_MASK;
+}
+
 static void free_buffer_page(struct buffer_page *bpage)
 {
 	/* Range pages are not to be freed */
@@ -1836,7 +1842,6 @@ static bool rb_cpu_meta_valid(struct ring_buffer_cpu_meta *meta, int cpu,
 			      unsigned long *subbuf_mask)
 {
 	int subbuf_size = PAGE_SIZE;
-	struct buffer_data_page *subbuf;
 	unsigned long buffers_start;
 	unsigned long buffers_end;
 	int i;
@@ -1844,6 +1849,11 @@ static bool rb_cpu_meta_valid(struct ring_buffer_cpu_meta *meta, int cpu,
 	if (!subbuf_mask)
 		return false;
 
+	if (meta->subbuf_size != PAGE_SIZE) {
+		pr_info("Ring buffer boot meta [%d] invalid subbuf_size\n", cpu);
+		return false;
+	}
+
 	buffers_start = meta->first_buffer;
 	buffers_end = meta->first_buffer + (subbuf_size * meta->nr_subbufs);
 
@@ -1860,11 +1870,12 @@ static bool rb_cpu_meta_valid(struct ring_buffer_cpu_meta *meta, int cpu,
 		return false;
 	}
 
-	subbuf = rb_subbufs_from_meta(meta);
-
 	bitmap_clear(subbuf_mask, 0, meta->nr_subbufs);
 
-	/* Is the meta buffers and the subbufs themselves have correct data? */
+	/*
+	 * Ensure the meta::buffers array has correct data. The data in each subbufs
+	 * are checked later in rb_meta_validate_events().
+	 */
 	for (i = 0; i < meta->nr_subbufs; i++) {
 		if (meta->buffers[i] < 0 ||
 		    meta->buffers[i] >= meta->nr_subbufs) {
@@ -1872,18 +1883,12 @@ static bool rb_cpu_meta_valid(struct ring_buffer_cpu_meta *meta, int cpu,
 			return false;
 		}
 
-		if ((unsigned)local_read(&subbuf->commit) > subbuf_size) {
-			pr_info("Ring buffer boot meta [%d] buffer invalid commit\n", cpu);
-			return false;
-		}
-
 		if (test_bit(meta->buffers[i], subbuf_mask)) {
 			pr_info("Ring buffer boot meta [%d] array has duplicates\n", cpu);
 			return false;
 		}
 
 		set_bit(meta->buffers[i], subbuf_mask);
-		subbuf = (void *)subbuf + subbuf_size;
 	}
 
 	return true;
@@ -1947,13 +1952,22 @@ 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)
+static int rb_validate_buffer(struct buffer_data_page *dpage, int cpu,
+			      struct ring_buffer_cpu_meta *meta)
 {
 	unsigned long long ts;
+	unsigned long tail;
 	u64 delta;
-	int tail;
 
-	tail = local_read(&dpage->commit);
+	/*
+	 * When a sub-buffer is recovered from a read, the commit value may
+	 * have RB_MISSED_* bits set, as these bits are reset on reuse.
+	 * Even after clearing these bits, a commit value greater than the
+	 * 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);
 }
 
@@ -1964,6 +1978,7 @@ static void rb_meta_validate_events(struct ring_buffer_per_cpu *cpu_buffer)
 	struct buffer_page *head_page, *orig_head, *orig_reader;
 	unsigned long entry_bytes = 0;
 	unsigned long entries = 0;
+	int discarded = 0;
 	int ret;
 	u64 ts;
 	int i;
@@ -1975,14 +1990,19 @@ static void rb_meta_validate_events(struct ring_buffer_per_cpu *cpu_buffer)
 	orig_reader = cpu_buffer->reader_page;
 
 	/* Do the reader page first */
-	ret = rb_validate_buffer(orig_reader->page, cpu_buffer->cpu);
+	ret = rb_validate_buffer(orig_reader->page, cpu_buffer->cpu, meta);
 	if (ret < 0) {
-		pr_info("Ring buffer reader page is invalid\n");
-		goto invalid;
+		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);
 	}
-	entries += ret;
-	entry_bytes += local_read(&orig_reader->page->commit);
-	local_set(&orig_reader->entries, ret);
 
 	ts = head_page->page->time_stamp;
 
@@ -2010,7 +2030,7 @@ static void rb_meta_validate_events(struct ring_buffer_per_cpu *cpu_buffer)
 			break;
 
 		/* Stop rewind if the page is invalid. */
-		ret = rb_validate_buffer(head_page->page, cpu_buffer->cpu);
+		ret = rb_validate_buffer(head_page->page, cpu_buffer->cpu, meta);
 		if (ret < 0)
 			break;
 
@@ -2019,7 +2039,7 @@ static void rb_meta_validate_events(struct ring_buffer_per_cpu *cpu_buffer)
 		if (ret)
 			local_inc(&cpu_buffer->pages_touched);
 		entries += ret;
-		entry_bytes += rb_page_commit(head_page);
+		entry_bytes += rb_page_size(head_page);
 	}
 	if (i)
 		pr_info("Ring buffer [%d] rewound %d pages\n", cpu_buffer->cpu, i);
@@ -2089,21 +2109,24 @@ 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);
+		ret = rb_validate_buffer(head_page->page, cpu_buffer->cpu, meta);
 		if (ret < 0) {
-			pr_info("Ring buffer meta [%d] invalid buffer page\n",
-				cpu_buffer->cpu);
-			goto invalid;
-		}
-
-		/* If the buffer has content, update pages_touched */
-		if (ret)
-			local_inc(&cpu_buffer->pages_touched);
-
-		entries += ret;
-		entry_bytes += local_read(&head_page->page->commit);
-		local_set(&head_page->entries, ret);
+			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)
+				local_inc(&cpu_buffer->pages_touched);
 
+			entries += ret;
+			entry_bytes += rb_page_size(head_page);
+			local_set(&head_page->entries, ret);
+		}
 		if (head_page == cpu_buffer->commit_page)
 			break;
 	}
@@ -2117,7 +2140,10 @@ static void rb_meta_validate_events(struct ring_buffer_per_cpu *cpu_buffer)
 	local_set(&cpu_buffer->entries, entries);
 	local_set(&cpu_buffer->entries_bytes, entry_bytes);
 
-	pr_info("Ring buffer meta [%d] is from previous boot!\n", cpu_buffer->cpu);
+	pr_info("Ring buffer meta [%d] is from previous boot!", cpu_buffer->cpu);
+	if (discarded)
+		pr_cont(" (%d pages discarded)", discarded);
+	pr_cont("\n");
 	return;
 
  invalid:
@@ -3303,12 +3329,6 @@ rb_iter_head_event(struct ring_buffer_iter *iter)
 	return NULL;
 }
 
-/* Size is determined by what has been committed */
-static __always_inline unsigned rb_page_size(struct buffer_page *bpage)
-{
-	return rb_page_commit(bpage) & ~RB_MISSED_MASK;
-}
-
 static __always_inline unsigned
 rb_commit_index(struct ring_buffer_per_cpu *cpu_buffer)
 {
@@ -5480,6 +5500,7 @@ rb_update_iter_read_stamp(struct ring_buffer_iter *iter,
 static struct buffer_page *
 rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
 {
+	int max_loops = cpu_buffer->ring_meta ? cpu_buffer->nr_pages : 3;
 	struct buffer_page *reader = NULL;
 	unsigned long overwrite;
 	unsigned long flags;
@@ -5492,11 +5513,14 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
  again:
 	/*
 	 * This should normally only loop twice. But because the
-	 * start of the reader inserts an empty page, it causes
-	 * a case where we will loop three times. There should be no
-	 * reason to loop four times (that I know of).
+	 * start of the reader inserts an empty page, it causes a
+	 * case where we will loop three times. There should be no
+	 * reason to loop four times unless the ring buffer is a
+	 * recovered persistent ring buffer. For persistent ring buffers,
+	 * invalid pages are reset during recovery, so there may be more
+	 * than 3 contiguous pages can be empty, but less than nr_pages.
 	 */
-	if (RB_WARN_ON(cpu_buffer, ++nr_loops > 3)) {
+	if (RB_WARN_ON(cpu_buffer, ++nr_loops > max_loops)) {
 		reader = NULL;
 		goto out;
 	}
@@ -5786,12 +5810,14 @@ 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;
+	int max_loops;
 
 	if (ts)
 		*ts = 0;
 
 	cpu_buffer = iter->cpu_buffer;
 	buffer = cpu_buffer->buffer;
+	max_loops = cpu_buffer->ring_meta ? cpu_buffer->nr_pages : 3;
 
 	/*
 	 * Check if someone performed a consuming read to the buffer
@@ -5814,7 +5840,7 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
 	 * the ring buffer with an active write as the consumer is.
 	 * Do not warn if the three failures is reached.
 	 */
-	if (++nr_loops > 3)
+	if (++nr_loops > max_loops)
 		return NULL;
 
 	if (rb_per_cpu_empty(cpu_buffer))
-- 
2.53.0