From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from smtp.kernel.org (aws-us-west-2-korg-mail-alma10-1.taild15c8.ts.net [100.103.45.18]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 792CE403E92; Wed, 20 May 2026 18:49:58 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=100.103.45.18 ARC-Seal:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1779303003; cv=none; b=KXgrBmdiR7Mt8LdD6EPQH25T7cZYXiOmLzlEKFgoeEYzFxLW/g91oOwAoyshQKW2vuM+GawzcMqN9gc2qpBcwWh/fuw+x5Q2DOGsRFc6HngLE458ztR1B6kP64XCciLF4kwK/QoGVIty35v1NuaAEG+3ZWYpdIfAV325LqTwfz4= ARC-Message-Signature:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1779303003; c=relaxed/simple; bh=dTfWW0EGfppg5wQA5TLVkE+qRLXWKwOSDXCU2P5YglU=; h=Message-ID:Date:From:To:Cc:Subject:References:MIME-Version: Content-Type; b=G9fAVnPYZBAll8Mqtrc8E/ESewzDrD/ztysZOAFGpQAHiS6I14vJe4zqqKdMTWHc0TH+mEYKtZzku/LPuYjzRBwaqSsBpY7jUTGIvWKOEv8sHNmyPrdFD1UPGoQZke+5PS9WDHHk9u31WqqQOaHyzFVpHaHJjSf3rnx+RLBls5U= ARC-Authentication-Results:i=1; smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b=o21BohyJ; arc=none smtp.client-ip=100.103.45.18 Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b="o21BohyJ" Received: by smtp.kernel.org (Postfix) with ESMTPSA id CD27B1F0089C; Wed, 20 May 2026 18:49:57 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=kernel.org; s=k20260515; t=1779302997; bh=Tz4o0IPUFGlacSMFrrih4D6KtT8s8pgNnzQswDMjuFw=; h=Date:From:To:Cc:Subject:References; b=o21BohyJrRyyPHVrnJINDVCyPm5k2nGToOEhCaWvaJ3FegCDxsuuvuPmT+yU5TuNT Xup/6XhB/sOS1i8x6OmXgzY9Rr29vbRNr8LiV0zBafKHFEUmnApugA/ao/VLT9pfqQ VPKE14xYmwz27aVNXj9qVeEEoIKdBxT61uPgFSOplKzdkRfhl6mZqY/qnsvdMy93IF Zry9YGUGaeyVusr87jK3jheky85O3ghBpBtfLiPJi19bqe6+7JCyNS1I5ro+jxyFAx 9aK4npNhIPGSZCSHgu9ZW3UyWnD3hkJF7B21cvfj+1XOn2hDU/ev5zFZSJ/5jv4/EG x3YGkJFZlIsxQ== Received: from rostedt by gandalf with local (Exim 4.99.2) (envelope-from ) id 1wPlzl-00000004qRK-1d8L; Wed, 20 May 2026 14:50:17 -0400 Message-ID: <20260520185017.219342323@kernel.org> User-Agent: quilt/0.69 Date: Wed, 20 May 2026 14:49:40 -0400 From: Steven Rostedt To: linux-kernel@vger.kernel.org, linux-trace-kernel@vger.kernel.org Cc: Masami Hiramatsu , Mathieu Desnoyers , Catalin Marinas , Will Deacon , Ian Rogers Subject: [PATCH v20 02/10] ring-buffer: Skip invalid sub-buffers when rewinding persistent ring buffer References: <20260520184938.749337513@kernel.org> Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 From: "Masami Hiramatsu (Google)" 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) Signed-off-by: Steven Rostedt --- 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 97ef702655f5..dca27ed6a3a1 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); } } -- 2.53.0