* Re: [PATCH v14 1/5] ring-buffer: Flush and stop persistent ring buffer on panic
From: Steven Rostedt @ 2026-03-30 17:54 UTC (permalink / raw)
To: Masami Hiramatsu (Google)
Cc: Mathieu Desnoyers, linux-kernel, linux-trace-kernel, Ian Rogers
In-Reply-To: <177487499643.3463592.15413057950716995168.stgit@mhiramat.tok.corp.google.com>
On Mon, 30 Mar 2026 21:49:56 +0900
"Masami Hiramatsu (Google)" <mhiramat@kernel.org> wrote:
> diff --git a/arch/arm64/include/asm/ring_buffer.h b/arch/arm64/include/asm/ring_buffer.h
> new file mode 100644
> index 000000000000..62316c406888
> --- /dev/null
> +++ b/arch/arm64/include/asm/ring_buffer.h
> @@ -0,0 +1,10 @@
> +/* SPDX-License-Identifier: GPL-2.0-only */
> +#ifndef _ASM_ARM64_RING_BUFFER_H
> +#define _ASM_ARM64_RING_BUFFER_H
> +
> +#include <asm/cacheflush.h>
> +
> +/* Flush D-cache on persistent ring buffer */
> +#define arch_ring_buffer_flush_range(start, end) dcache_clean_pop(start, end)
> +
> +#endif /* _ASM_ARM64_RING_BUFFER_H */
You probably need to get an ack from the arm64 folks.
-- Steve
^ permalink raw reply
* [PATCH v7 1/2] tracing: Append repeated boot-time tracing parameters
From: Wesley Atwell @ 2026-03-30 18:11 UTC (permalink / raw)
To: rostedt, mhiramat
Cc: mark.rutland, mathieu.desnoyers, linux-kernel, linux-trace-kernel,
Wesley Atwell
Some tracing boot parameters already accept delimited value lists, but
their __setup() handlers keep only the last instance seen at boot.
Make repeated instances append to the same boot-time buffer in the
format each parser already consumes.
Use a shared trace_append_boot_param() helper for the ftrace filters,
trace_options, and kprobe_event boot parameters.
This also lets Bootconfig array values work naturally when they expand
to repeated param=value entries.
Before this change, only the last instance from each repeated
parameter survived boot.
Signed-off-by: Wesley Atwell <atwellwea@gmail.com>
---
Changes since v6: https://lore.kernel.org/all/20260329184254.1813273-1-atwellwea@gmail.com/
- split trace_trigger= handling into a separate patch
- add the requested blank line in trace_append_boot_param()
---
kernel/trace/ftrace.c | 12 ++++++++----
kernel/trace/trace.c | 31 ++++++++++++++++++++++++++++++-
kernel/trace/trace.h | 2 ++
kernel/trace/trace_kprobe.c | 3 ++-
4 files changed, 42 insertions(+), 6 deletions(-)
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 413310912609..8bd3dd1d549c 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -6841,7 +6841,8 @@ bool ftrace_filter_param __initdata;
static int __init set_ftrace_notrace(char *str)
{
ftrace_filter_param = true;
- strscpy(ftrace_notrace_buf, str, FTRACE_FILTER_SIZE);
+ trace_append_boot_param(ftrace_notrace_buf, str, ',',
+ FTRACE_FILTER_SIZE);
return 1;
}
__setup("ftrace_notrace=", set_ftrace_notrace);
@@ -6849,7 +6850,8 @@ __setup("ftrace_notrace=", set_ftrace_notrace);
static int __init set_ftrace_filter(char *str)
{
ftrace_filter_param = true;
- strscpy(ftrace_filter_buf, str, FTRACE_FILTER_SIZE);
+ trace_append_boot_param(ftrace_filter_buf, str, ',',
+ FTRACE_FILTER_SIZE);
return 1;
}
__setup("ftrace_filter=", set_ftrace_filter);
@@ -6861,14 +6863,16 @@ static int ftrace_graph_set_hash(struct ftrace_hash *hash, char *buffer);
static int __init set_graph_function(char *str)
{
- strscpy(ftrace_graph_buf, str, FTRACE_FILTER_SIZE);
+ trace_append_boot_param(ftrace_graph_buf, str, ',',
+ FTRACE_FILTER_SIZE);
return 1;
}
__setup("ftrace_graph_filter=", set_graph_function);
static int __init set_graph_notrace_function(char *str)
{
- strscpy(ftrace_graph_notrace_buf, str, FTRACE_FILTER_SIZE);
+ trace_append_boot_param(ftrace_graph_notrace_buf, str, ',',
+ FTRACE_FILTER_SIZE);
return 1;
}
__setup("ftrace_graph_notrace=", set_graph_notrace_function);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index a626211ceb9a..652d9f4e7943 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -228,6 +228,34 @@ static int boot_instance_index;
static char boot_snapshot_info[COMMAND_LINE_SIZE] __initdata;
static int boot_snapshot_index;
+/*
+ * Repeated boot parameters, including Bootconfig array expansions, need
+ * to stay in the delimiter form that the existing parser consumes.
+ */
+void __init trace_append_boot_param(char *buf, const char *str, char sep,
+ int size)
+{
+ int len, needed, str_len;
+
+ if (!*str)
+ return;
+
+ len = strlen(buf);
+ str_len = strlen(str);
+ needed = len + str_len + 1;
+
+ /* For continuation, account for the separator. */
+ if (len)
+ needed++;
+ if (needed > size)
+ return;
+
+ if (len)
+ buf[len++] = sep;
+
+ strscpy(buf + len, str, size - len);
+}
+
static int __init set_cmdline_ftrace(char *str)
{
strscpy(bootup_tracer_buf, str, MAX_TRACER_SIZE);
@@ -329,7 +357,8 @@ static char trace_boot_options_buf[MAX_TRACER_SIZE] __initdata;
static int __init set_trace_boot_options(char *str)
{
- strscpy(trace_boot_options_buf, str, MAX_TRACER_SIZE);
+ trace_append_boot_param(trace_boot_options_buf, str, ',',
+ MAX_TRACER_SIZE);
return 1;
}
__setup("trace_options=", set_trace_boot_options);
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index b8f3804586a0..1579cdec3f56 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -862,6 +862,8 @@ extern int DYN_FTRACE_TEST_NAME(void);
#define DYN_FTRACE_TEST_NAME2 trace_selftest_dynamic_test_func2
extern int DYN_FTRACE_TEST_NAME2(void);
+void __init trace_append_boot_param(char *buf, const char *str,
+ char sep, int size);
extern void trace_set_ring_buffer_expanded(struct trace_array *tr);
extern bool tracing_selftest_disabled;
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index a5dbb72528e0..e9f1c55aea64 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -31,7 +31,8 @@ static char kprobe_boot_events_buf[COMMAND_LINE_SIZE] __initdata;
static int __init set_kprobe_boot_events(char *str)
{
- strscpy(kprobe_boot_events_buf, str, COMMAND_LINE_SIZE);
+ trace_append_boot_param(kprobe_boot_events_buf, str, ';',
+ COMMAND_LINE_SIZE);
disable_tracing_selftest("running kprobe events");
return 1;
base-commit: e3c33bc767b5512dbfec643a02abf58ce608f3b2
--
2.43.0
^ permalink raw reply related
* [PATCH v7 2/2] tracing: Preserve repeated trace_trigger boot parameters
From: Wesley Atwell @ 2026-03-30 18:11 UTC (permalink / raw)
To: rostedt, mhiramat
Cc: mark.rutland, mathieu.desnoyers, linux-kernel, linux-trace-kernel,
Wesley Atwell
In-Reply-To: <20260330181103.1851230-1-atwellwea@gmail.com>
trace_trigger= tokenizes bootup_trigger_buf in place and stores pointers
into that buffer for later trigger registration. Repeated trace_trigger=
parameters overwrite the buffer contents from earlier calls, leaving
only the last set of parsed event and trigger strings.
Keep each new trace_trigger= string at the end of bootup_trigger_buf and
parse only the appended range. That preserves the earlier event and
trigger strings while still letting repeated parameters queue additional
boot-time triggers.
This also lets Bootconfig array values work naturally when they expand
to repeated trace_trigger= entries.
Before this change, only the last trace_trigger= instance survived boot.
Signed-off-by: Wesley Atwell <atwellwea@gmail.com>
---
Changes since v6: https://lore.kernel.org/all/20260329184254.1813273-1-atwellwea@gmail.com/
- split trace_trigger= handling into its own patch
- follow Steven Rostedt's suggested bootup_trigger_buf offset approach
- account for the terminating NUL when advancing boot_trigger_buf_len
---
kernel/trace/trace_events.c | 13 ++++++++++---
1 file changed, 10 insertions(+), 3 deletions(-)
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 249d1cba72c0..dd26e838d4de 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -3679,20 +3679,27 @@ static struct boot_triggers {
} bootup_triggers[MAX_BOOT_TRIGGERS];
static char bootup_trigger_buf[COMMAND_LINE_SIZE];
+static int boot_trigger_buf_len;
static int nr_boot_triggers;
static __init int setup_trace_triggers(char *str)
{
char *trigger;
char *buf;
+ int len = boot_trigger_buf_len;
int i;
- strscpy(bootup_trigger_buf, str, COMMAND_LINE_SIZE);
+ if (len >= COMMAND_LINE_SIZE)
+ return 1;
+
+ strscpy(bootup_trigger_buf + len, str, COMMAND_LINE_SIZE - len);
trace_set_ring_buffer_expanded(NULL);
disable_tracing_selftest("running event triggers");
- buf = bootup_trigger_buf;
- for (i = 0; i < MAX_BOOT_TRIGGERS; i++) {
+ buf = bootup_trigger_buf + len;
+ boot_trigger_buf_len += strlen(buf) + 1;
+
+ for (i = nr_boot_triggers; i < MAX_BOOT_TRIGGERS; i++) {
trigger = strsep(&buf, ",");
if (!trigger)
break;
--
2.43.0
^ permalink raw reply related
* Re: [PATCH v14 4/5] ring-buffer: Reset RB_MISSED_* flags on persistent ring buffer
From: Steven Rostedt @ 2026-03-30 18:36 UTC (permalink / raw)
To: Masami Hiramatsu (Google)
Cc: Mathieu Desnoyers, linux-kernel, linux-trace-kernel, Ian Rogers
In-Reply-To: <177487501981.3463592.2886576368556755178.stgit@mhiramat.tok.corp.google.com>
On Mon, 30 Mar 2026 21:50:20 +0900
"Masami Hiramatsu (Google)" <mhiramat@kernel.org> wrote:
> From: Masami Hiramatsu (Google) <mhiramat@kernel.org>
>
> Reset RB_MISSED_* flags when the persistent ring buffer is
> validated at boot. Since these flags are used only in reading
> process, such process should be stopped when reboot and never
> be restarted. Thus, these flags are meaningless in the next
> boot. Moreover, it can confuse the read process after reboot.
Is it meaningless on a second boot?
Let's say you have a crash, and there's an invalid buffer. On the next boot
it is flagged as invalid with the RB_MISSED flag. But then you reboot again
before looking at the buffer. The next boot will clear this flag. Now
looking at the persistent ring buffer will not show any missed events.
Ideally, it shouldn't matter how many reboots are made. If the persistent
ring buffer hasn't started again, it should always show the same output.
-- Steve
>
> Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
> ---
> Changes in v14:
> - Newly added.
> ---
> kernel/trace/ring_buffer.c | 1 +
> 1 file changed, 1 insertion(+)
>
> diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
> index e5178239f2f9..5049cf13021e 100644
> --- a/kernel/trace/ring_buffer.c
> +++ b/kernel/trace/ring_buffer.c
> @@ -1903,6 +1903,7 @@ static int rb_validate_buffer(struct buffer_page *bpage, int cpu,
> local_set(&bpage->page->commit, 0);
> } else {
> local_set(&bpage->entries, ret);
> + local_set(&bpage->page->commit, tail);
> }
>
> return ret;
^ permalink raw reply
* Re: [PATCH v2] tracing/osnoise: Add option to align tlat threads
From: Crystal Wood @ 2026-03-30 19:43 UTC (permalink / raw)
To: Tomas Glozar, Steven Rostedt, Masami Hiramatsu
Cc: Mathieu Desnoyers, John Kacur, Luis Goncalves, Costa Shulyupin,
Wander Lairson Costa, LKML, linux-trace-kernel
In-Reply-To: <20260302131316.385987-1-tglozar@redhat.com>
On Mon, 2026-03-02 at 14:13 +0100, Tomas Glozar wrote:
> Add an option called TIMERLAT_ALIGN to osnoise/options, together with a
> corresponding setting osnoise/timerlat_align_us.
>
> This option sets the alignment of wakeup times between different
> timerlat threads, similarly to cyclictest's -A/--aligned option. If
> TIMERLAT_ALIGN is set, the first thread that reaches the first cycle
> records its first wake-up time. Each following thread sets its first
> wake-up time to a fixed offset from the recorded time, and increments
> it by the same offset.
>
> Example:
>
> osnoise/timerlat_period is set to 1000, osnoise/timerlat_align_us is
> set to 20. There are four threads, on CPUs 1 to 4.
>
> - CPU 4 enters first cycle first. The current time is 20000us, so
> the wake-up of the first cycle is set to 21000us. This time is recorded.
> - CPU 2 enter first cycle next. It reads the recorded time, increments
> it to 21020us, and uses this value as its own wake-up time for the first
> cycle.
> - CPU 3 enters first cycle next. It reads the recorded time, increments
> it to 21040 us, and uses the value as its own wake-up time.
> - CPU 1 proceeds analogically.
>
> In each next cycle, the wake-up time (called "absolute period" in
> timerlat code) is incremented by the (relative) period of 1000us. Thus,
> the wake-ups in the following cycles (provided the times are reached and
> not in the past) will be as follows:
>
> CPU 1 CPU 2 CPU 3 CPU 4
> 21080us 21020us 21040us 21000us
> 22080us 22020us 22040us 22000us
> ... ... ... ...
>
> Even if any cycle is skipped due to e.g. the first cycle calculation
> happening later, the alignment stays in place.
>
> Signed-off-by: Tomas Glozar <tglozar@redhat.com>
Reviewed-by: Crystal Wood <crwood@redhat.com>
-Crystal
^ permalink raw reply
* Re: [PATCH v14 2/5] ring-buffer: Skip invalid sub-buffers when validating persistent ring buffer
From: Steven Rostedt @ 2026-03-30 20:22 UTC (permalink / raw)
To: Masami Hiramatsu (Google)
Cc: Mathieu Desnoyers, linux-kernel, linux-trace-kernel, Ian Rogers
In-Reply-To: <177487500432.3463592.13753720277119177967.stgit@mhiramat.tok.corp.google.com>
On Mon, 30 Mar 2026 21:50:04 +0900
"Masami Hiramatsu (Google)" <mhiramat@kernel.org> wrote:
> @@ -2042,7 +2065,8 @@ 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! (%d pages discarded)\n",
> + cpu_buffer->cpu, discarded);
As pages should never be discarded unless something went wrong, let's only
print that if there were discarded pages.
if (discarded) {
pr_info("Ring buffer meta [%d] is from previous boot! (%d pages discarded)\n",
cpu_buffer->cpu, discarded);
} else {
pr_info("Ring buffer meta [%d] is from previous boot!\n", cpu_buffer->cpu);
}
-- Steve
> return;
>
> invalid:
^ permalink raw reply
* Re: [PATCH v14 5/5] ring-buffer: Add persistent ring buffer selftest
From: Steven Rostedt @ 2026-03-30 20:24 UTC (permalink / raw)
To: Masami Hiramatsu (Google)
Cc: Mathieu Desnoyers, linux-kernel, linux-trace-kernel, Ian Rogers
In-Reply-To: <177487502763.3463592.7901517545360137050.stgit@mhiramat.tok.corp.google.com>
On Mon, 30 Mar 2026 21:50:27 +0900
"Masami Hiramatsu (Google)" <mhiramat@kernel.org> wrote:
> @@ -2558,12 +2577,64 @@ static void rb_free_cpu_buffer(struct ring_buffer_per_cpu *cpu_buffer)
> kfree(cpu_buffer);
> }
>
> +#ifdef CONFIG_RING_BUFFER_PERSISTENT_INJECT
> +static void rb_test_inject_invalid_pages(struct trace_buffer *buffer)
> +{
> + struct ring_buffer_per_cpu *cpu_buffer;
> + struct ring_buffer_cpu_meta *meta;
> + struct buffer_data_page *dpage;
> + u32 entry_bytes = 0;
> + unsigned long ptr;
> + int subbuf_size;
> + int invalid = 0;
> + int cpu;
> + int i;
> +
> + if (!(buffer->flags & RB_FL_TESTING))
> + return;
> +
> + guard(preempt)();
> + cpu = smp_processor_id();
> +
> + cpu_buffer = buffer->buffers[cpu];
> + meta = cpu_buffer->ring_meta;
> + ptr = (unsigned long)rb_subbufs_from_meta(meta);
> + subbuf_size = meta->subbuf_size;
> +
> + for (i = 0; i < meta->nr_subbufs; i++) {
> + int idx = meta->buffers[i];
> +
> + dpage = (void *)(ptr + idx * subbuf_size);
> + /* Skip unused pages */
> + if (!local_read(&dpage->commit))
> + continue;
> +
> + /* Invalidate even pages. */
> + if (!(i & 0x1)) {
> + local_add(subbuf_size + 1, &dpage->commit);
> + invalid++;
> + } else {
> + /* Count total commit bytes. */
> + entry_bytes += local_read(&dpage->commit);
> + }
> + }
> +
> + pr_info("Inject invalidated %d pages on CPU%d, total size: %ld\n",
> + invalid, cpu, (long)entry_bytes);
This is only enabled when testing. Let's make that a pr_warn() as we really
do want to be able to see it. And it should warn that it is invalidating pages!
(warn as in pr_warn, it doesn't need a warn as in WARN()).
-- Steve
> + meta->nr_invalid = invalid;
> + meta->entry_bytes = entry_bytes;
> +}
> +#else /* !CONFIG_RING_BUFFER_PERSISTENT_INJECT */
> +#define rb_test_inject_invalid_pages(buffer) do { } while (0)
> +#endif
> +
> /* Stop recording on a persistent buffer and flush cache if needed. */
> static int rb_flush_buffer_cb(struct notifier_block *nb, unsigned long event, void *data)
> {
> struct trace_buffer *buffer = container_of(nb, struct trace_buffer, flush_nb);
>
> ring_buffer_record_off(buffer);
> + rb_test_inject_invalid_pages(buffer);
> arch_ring_buffer_flush_range(buffer->range_addr_start, buffer->range_addr_end);
> return NOTIFY_DONE;
> }
^ permalink raw reply
* Re: [PATCH v14 2/5] ring-buffer: Skip invalid sub-buffers when validating persistent ring buffer
From: Steven Rostedt @ 2026-03-30 20:28 UTC (permalink / raw)
To: Masami Hiramatsu (Google)
Cc: Mathieu Desnoyers, linux-kernel, linux-trace-kernel, Ian Rogers
In-Reply-To: <20260330162210.5e37b0c3@gandalf.local.home>
On Mon, 30 Mar 2026 16:22:10 -0400
Steven Rostedt <rostedt@goodmis.org> wrote:
> On Mon, 30 Mar 2026 21:50:04 +0900
> "Masami Hiramatsu (Google)" <mhiramat@kernel.org> wrote:
>
> > @@ -2042,7 +2065,8 @@ 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! (%d pages discarded)\n",
> > + cpu_buffer->cpu, discarded);
>
> As pages should never be discarded unless something went wrong, let's only
> print that if there were discarded pages.
>
> if (discarded) {
> pr_info("Ring buffer meta [%d] is from previous boot! (%d pages discarded)\n",
> cpu_buffer->cpu, discarded);
> } else {
> pr_info("Ring buffer meta [%d] is from previous boot!\n", cpu_buffer->cpu);
> }
Or perhaps:
pr_info("Ring buffer meta [%d] is from previous boot!", cpu_buffer->cpu);
if (discarded)
pr_cont(" (%d pages discarded)", discarded);
pr_cont("\n");
-- Steve
^ permalink raw reply
* Re: [PATCH v2] bootconfig: Apply early options from embedded config
From: Masami Hiramatsu @ 2026-03-31 0:00 UTC (permalink / raw)
To: Breno Leitao
Cc: Jonathan Corbet, Shuah Khan, linux-kernel, linux-trace-kernel,
linux-doc, oss, paulmck, rostedt, kernel-team
In-Reply-To: <acpzhCBEPh-tKVqg@gmail.com>
On Mon, 30 Mar 2026 06:15:17 -0700
Breno Leitao <leitao@debian.org> wrote:
> On Fri, Mar 27, 2026 at 10:37:44PM +0900, Masami Hiramatsu wrote:
> > On Fri, 27 Mar 2026 03:06:41 -0700
> > Breno Leitao <leitao@debian.org> wrote:
>
> > > > To fix this, we need to change setup_arch() for each architecture so
> > > > that it calls this bootconfig_apply_early_params().
> > >
> > > Could we instead integrate this into parse_early_param() itself? That
> > > approach would avoid the need to modify each architecture individually.
> >
> > Ah, indeed.
>
> I investigated integrating bootconfig into parse_early_param() and hit a
> blocker: xbc_init() and xbc_make_cmdline() depend on memblock_alloc(), but on
> most architectures (x86, arm64, arm, s390, riscv) parse_early_param() is called
> from setup_arch() _before_ memblock is initialized.
Yeah, that's right.
>
> So, bootconfig will not be available as early as parse_early_param().
>
> An alternative is replace memblock allocations in lib/bootconfig.c with static
> __initdata buffers, similar to Petr's approach in 2023:
>
> https://lore.kernel.org/all/20231121231342.193646-3-oss@malat.biz/
>
> But, there was concerns about the allocation size:
>
> Petr Malat <oss@malat.biz> wrote:
> > To allow handling of early options, it's necessary to eliminate allocations
> > from embedded bootconfig handling
>
> "Hm, my concern is that this can introduce some sort of overhead to parse the bootconfig."
>
As far as we can correctly handle the early params and it is limited only
with the embedded bootconfig, I think it is OK to allocate it statically.
Thank you,
--
Masami Hiramatsu (Google) <mhiramat@kernel.org>
^ permalink raw reply
* Re: [PATCH v14 1/5] ring-buffer: Flush and stop persistent ring buffer on panic
From: Masami Hiramatsu @ 2026-03-31 0:29 UTC (permalink / raw)
To: Steven Rostedt
Cc: Mathieu Desnoyers, linux-kernel, linux-trace-kernel, Ian Rogers
In-Reply-To: <20260330135447.423bc070@gandalf.local.home>
On Mon, 30 Mar 2026 13:54:47 -0400
Steven Rostedt <rostedt@goodmis.org> wrote:
> On Mon, 30 Mar 2026 21:49:56 +0900
> "Masami Hiramatsu (Google)" <mhiramat@kernel.org> wrote:
>
> > diff --git a/arch/arm64/include/asm/ring_buffer.h b/arch/arm64/include/asm/ring_buffer.h
> > new file mode 100644
> > index 000000000000..62316c406888
> > --- /dev/null
> > +++ b/arch/arm64/include/asm/ring_buffer.h
> > @@ -0,0 +1,10 @@
> > +/* SPDX-License-Identifier: GPL-2.0-only */
> > +#ifndef _ASM_ARM64_RING_BUFFER_H
> > +#define _ASM_ARM64_RING_BUFFER_H
> > +
> > +#include <asm/cacheflush.h>
> > +
> > +/* Flush D-cache on persistent ring buffer */
> > +#define arch_ring_buffer_flush_range(start, end) dcache_clean_pop(start, end)
> > +
> > +#endif /* _ASM_ARM64_RING_BUFFER_H */
>
> You probably need to get an ack from the arm64 folks.
OK, I will add them in loop.
Thank you,
--
Masami Hiramatsu (Google) <mhiramat@kernel.org>
^ permalink raw reply
* [PATCH] tracing: Remove duplicate latency_fsnotify() stub
From: Steven Rostedt @ 2026-03-31 0:58 UTC (permalink / raw)
To: LKML, Linux Trace Kernel; +Cc: Masami Hiramatsu, Mathieu Desnoyers
From: Steven Rostedt <rostedt@goodmis.org>
When the SNAPSHOT is defined but FSNOTIFY is not the latency_fsnotify()
function is turned into a static inline stub. But this stub was defined in
both trace.h and trace_snapshot.c causing a error in build when
CONFIG_SNAPSHOT is defined but FSNOTIFY is not. The stub is not needed in
trace_snapshot.c as it will be defined in trace.h, remove it from the C
file.
Fixes: bade44fe5462 ("tracing: Move snapshot code out of trace.c and into trace_snapshot.c")
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202603310604.lGE9LDBK-lkp@intel.com/
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
kernel/trace/trace.h | 2 +-
kernel/trace/trace_snapshot.c | 3 +--
2 files changed, 2 insertions(+), 3 deletions(-)
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index a3ea735a9ef6..a59d6acdf95d 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -845,13 +845,13 @@ void update_max_tr_single(struct trace_array *tr,
#if defined(CONFIG_TRACER_MAX_TRACE) && defined(CONFIG_FSNOTIFY)
# define LATENCY_FS_NOTIFY
#endif
+#endif /* CONFIG_TRACER_SNAPSHOT */
#ifdef LATENCY_FS_NOTIFY
void latency_fsnotify(struct trace_array *tr);
#else
static inline void latency_fsnotify(struct trace_array *tr) { }
#endif
-#endif /* CONFIG_TRACER_SNAPSHOT */
#ifdef CONFIG_STACKTRACE
void __trace_stack(struct trace_array *tr, unsigned int trace_ctx, int skip);
diff --git a/kernel/trace/trace_snapshot.c b/kernel/trace/trace_snapshot.c
index 8865b2ef2264..07b43c9863a2 100644
--- a/kernel/trace/trace_snapshot.c
+++ b/kernel/trace/trace_snapshot.c
@@ -391,9 +391,8 @@ void latency_fsnotify(struct trace_array *tr)
*/
irq_work_queue(&tr->fsnotify_irqwork);
}
-#else
-static inline void latency_fsnotify(struct trace_array *tr) { }
#endif /* LATENCY_FS_NOTIFY */
+
static const struct file_operations tracing_max_lat_fops;
void trace_create_maxlat_file(struct trace_array *tr,
--
2.51.0
^ permalink raw reply related
* Re: [PATCH v14 2/5] ring-buffer: Skip invalid sub-buffers when validating persistent ring buffer
From: Masami Hiramatsu @ 2026-03-31 1:24 UTC (permalink / raw)
To: Steven Rostedt
Cc: Mathieu Desnoyers, linux-kernel, linux-trace-kernel, Ian Rogers
In-Reply-To: <20260330162822.54f6bd02@gandalf.local.home>
On Mon, 30 Mar 2026 16:28:22 -0400
Steven Rostedt <rostedt@goodmis.org> wrote:
> On Mon, 30 Mar 2026 16:22:10 -0400
> Steven Rostedt <rostedt@goodmis.org> wrote:
>
> > On Mon, 30 Mar 2026 21:50:04 +0900
> > "Masami Hiramatsu (Google)" <mhiramat@kernel.org> wrote:
> >
> > > @@ -2042,7 +2065,8 @@ 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! (%d pages discarded)\n",
> > > + cpu_buffer->cpu, discarded);
> >
> > As pages should never be discarded unless something went wrong, let's only
> > print that if there were discarded pages.
> >
> > if (discarded) {
> > pr_info("Ring buffer meta [%d] is from previous boot! (%d pages discarded)\n",
> > cpu_buffer->cpu, discarded);
> > } else {
> > pr_info("Ring buffer meta [%d] is from previous boot!\n", cpu_buffer->cpu);
> > }
>
> Or perhaps:
>
> pr_info("Ring buffer meta [%d] is from previous boot!", cpu_buffer->cpu);
> if (discarded)
> pr_cont(" (%d pages discarded)", discarded);
> pr_cont("\n");
OK. I'll do this.
Thanks for the comment!
>
> -- Steve
>
--
Masami Hiramatsu (Google) <mhiramat@kernel.org>
^ permalink raw reply
* Re: [PATCH v14 4/5] ring-buffer: Reset RB_MISSED_* flags on persistent ring buffer
From: Masami Hiramatsu @ 2026-03-31 1:43 UTC (permalink / raw)
To: Steven Rostedt
Cc: Mathieu Desnoyers, linux-kernel, linux-trace-kernel, Ian Rogers
In-Reply-To: <20260330143613.42fe5640@gandalf.local.home>
On Mon, 30 Mar 2026 14:36:13 -0400
Steven Rostedt <rostedt@goodmis.org> wrote:
> On Mon, 30 Mar 2026 21:50:20 +0900
> "Masami Hiramatsu (Google)" <mhiramat@kernel.org> wrote:
>
> > From: Masami Hiramatsu (Google) <mhiramat@kernel.org>
> >
> > Reset RB_MISSED_* flags when the persistent ring buffer is
> > validated at boot. Since these flags are used only in reading
> > process, such process should be stopped when reboot and never
> > be restarted. Thus, these flags are meaningless in the next
> > boot. Moreover, it can confuse the read process after reboot.
>
> Is it meaningless on a second boot?
>
> Let's say you have a crash, and there's an invalid buffer. On the next boot
> it is flagged as invalid with the RB_MISSED flag. But then you reboot again
> before looking at the buffer. The next boot will clear this flag. Now
> looking at the persistent ring buffer will not show any missed events.
>
> Ideally, it shouldn't matter how many reboots are made. If the persistent
> ring buffer hasn't started again, it should always show the same output.
Hmm, OK. I'll drop this.
Thanks!
>
> -- Steve
>
>
> >
> > Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
> > ---
> > Changes in v14:
> > - Newly added.
> > ---
> > kernel/trace/ring_buffer.c | 1 +
> > 1 file changed, 1 insertion(+)
> >
> > diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
> > index e5178239f2f9..5049cf13021e 100644
> > --- a/kernel/trace/ring_buffer.c
> > +++ b/kernel/trace/ring_buffer.c
> > @@ -1903,6 +1903,7 @@ static int rb_validate_buffer(struct buffer_page *bpage, int cpu,
> > local_set(&bpage->page->commit, 0);
> > } else {
> > local_set(&bpage->entries, ret);
> > + local_set(&bpage->page->commit, tail);
> > }
> >
> > return ret;
>
>
--
Masami Hiramatsu (Google) <mhiramat@kernel.org>
^ permalink raw reply
* Re: [PATCH v13 4/4] ring-buffer: Add persistent ring buffer selftest
From: Masami Hiramatsu @ 2026-03-31 1:54 UTC (permalink / raw)
To: Steven Rostedt
Cc: Mathieu Desnoyers, linux-kernel, linux-trace-kernel, Ian Rogers
In-Reply-To: <20260327164748.67b6453d@gandalf.local.home>
On Fri, 27 Mar 2026 16:47:48 -0400
Steven Rostedt <rostedt@goodmis.org> wrote:
> On Fri, 27 Mar 2026 16:25:08 -0400
> Steven Rostedt <rostedt@goodmis.org> wrote:
>
> > Also, I noticed that there's nothing that reads the RB_MISSING as I thought
> > it might. I'll have to look into how to pass that info to the trace output.
>
> And when I cat /sys/kernel/tracing/instances/ptracingtest/per_cpu/cpuX/trace_pipe
>
> (where X is the failed buffer)
>
> It triggered an infinite loop of:
>
> [ 206.549217] ------------[ cut here ]------------
> [ 206.550907] WARNING: kernel/trace/ring_buffer.c:5751 at __rb_get_reader_page+0xa6b/0x1040, CPU#2: cat/1197
> [ 206.554111] Modules linked in:
> [ 206.555331] CPU: 2 UID: 0 PID: 1197 Comm: cat Tainted: G W 7.0.0-rc4-test-00028-g7b37f48b2c57-dirty #276 PREEMPT(full)
> [ 206.559048] Tainted: [W]=WARN
> [ 206.560244] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.17.0-debian-1.17.0-1 04/01/2014
> [ 206.563212] RIP: 0010:__rb_get_reader_page+0xa6b/0x1040
> [ 206.564964] Code: ff df 48 c1 ea 03 80 3c 02 00 0f 85 4a 05 00 00 48 8b 43 10 be 04 00 00 00 4c 8d 60 08 4c 89 e7 e8 9a 2d 63 00 f0 41 ff 04 24 <0f> 0b e9 36 fb ff ff e8 29 39 05 00 fb 0f 1f 44 00 00 4d 85 f6 0f
> [ 206.572295] RSP: 0018:ffff888112a77938 EFLAGS: 00010006
> [ 206.574095] RAX: 0000000000000001 RBX: ffff888100d6e000 RCX: 0000000000000001
> [ 206.576458] RDX: 0000000000000001 RSI: 0000000000000004 RDI: ffff88810027b808
> [ 206.578749] RBP: 1ffff1102254ef34 R08: ffffffff909a1556 R09: ffffed102004f701
> [ 206.581020] R10: ffffed102004f702 R11: ffff88823443a000 R12: ffff88810027b808
> [ 206.583312] R13: ffff888100f65f00 R14: ffff888100f65f00 R15: dffffc0000000000
> [ 206.585647] FS: 00007f98e4d80780(0000) GS:ffff88829e3c2000(0000) knlGS:0000000000000000
> [ 206.588246] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
> [ 206.590179] CR2: 00007f98e4d3e000 CR3: 000000012272e006 CR4: 0000000000172ef0
> [ 206.592444] Call Trace:
> [ 206.593518] <TASK>
> [ 206.594436] ? __pfx___rb_get_reader_page+0x10/0x10
> [ 206.596148] ? lock_acquire+0x1b2/0x340
> [ 206.597599] rb_buffer_peek+0x37e/0x520
> [ 206.598954] ring_buffer_peek+0xe9/0x310
> [ 206.601956] peek_next_entry+0x15a/0x280
> [ 206.603420] __find_next_entry+0x39f/0x530
> [ 206.604918] ? __pfx___mutex_lock+0x10/0x10
> [ 206.606474] ? rcu_is_watching+0x15/0xb0
> [ 206.616049] ? __pfx___find_next_entry+0x10/0x10
> [ 206.617741] ? preempt_count_sub+0x10c/0x1c0
> [ 206.619242] ? __pfx_down_read+0x10/0x10
> [ 206.620687] trace_find_next_entry_inc+0x2f/0x240
> [ 206.622351] tracing_read_pipe+0x4e7/0xc60
> [ 206.623852] ? rw_verify_area+0x353/0x5f0
> [ 206.625325] vfs_read+0x171/0xb20
> [ 206.626592] ? __lock_acquire+0x487/0x2220
> [ 206.628135] ? __pfx___handle_mm_fault+0x10/0x10
> [ 206.629784] ? __pfx_vfs_read+0x10/0x10
> [ 206.632696] ? __pfx_css_rstat_updated+0x10/0x10
> [ 206.634351] ? rcu_is_watching+0x15/0xb0
> [ 206.635835] ? trace_preempt_on+0x126/0x160
> [ 206.637362] ? preempt_count_sub+0x10c/0x1c0
> [ 206.638880] ? count_memcg_events+0x10a/0x4b0
> [ 206.640455] ? find_held_lock+0x2b/0x80
> [ 206.641908] ? rcu_read_unlock+0x17/0x60
> [ 206.643340] ? lock_release+0x1ab/0x320
> [ 206.644812] ksys_read+0xff/0x200
> [ 206.646127] ? __pfx_ksys_read+0x10/0x10
> [ 206.647651] do_syscall_64+0x117/0x16c0
> [ 206.649035] ? irqentry_exit+0xd9/0x690
> [ 206.650548] entry_SYSCALL_64_after_hwframe+0x76/0x7e
> [ 206.652331] RIP: 0033:0x7f98e4e14eb2
> [ 206.653743] Code: 18 41 8b 93 08 03 00 00 59 5e 48 83 f8 fc 75 1a 83 e2 39 83 fa 08 75 12 e8 2b ff ff ff 0f 1f 00 49 89 ca 48 8b 44 24 20 0f 05 <48> 83 c4 18 c3 66 0f 1f 84 00 00 00 00 00 48 83 ec 10 ff 74 24 18
> [ 206.659364] RSP: 002b:00007ffdc0a8d930 EFLAGS: 00000202 ORIG_RAX: 0000000000000000
> [ 206.663251] RAX: ffffffffffffffda RBX: 0000000000040000 RCX: 00007f98e4e14eb2
> [ 206.665614] RDX: 0000000000040000 RSI: 00007f98e4d3f000 RDI: 0000000000000003
> [ 206.668022] RBP: 0000000000040000 R08: 0000000000000000 R09: 0000000000000000
> [ 206.670306] R10: 0000000000000000 R11: 0000000000000202 R12: 00007f98e4d3f000
> [ 206.672624] R13: 0000000000000003 R14: 0000000000000000 R15: 0000000000040000
> [ 206.674941] </TASK>
> [ 206.675927] irq event stamp: 7898
> [ 206.677154] hardirqs last enabled at (7897): [<ffffffff90991f6f>] ring_buffer_empty_cpu+0x19f/0x2f0
> [ 206.680088] hardirqs last disabled at (7898): [<ffffffff909a277d>] ring_buffer_peek+0x17d/0x310
> [ 206.682881] softirqs last enabled at (7888): [<ffffffff9056cffc>] handle_softirqs+0x5bc/0x7c0
> [ 206.685710] softirqs last disabled at (7879): [<ffffffff9056d322>] __irq_exit_rcu+0x112/0x230
> [ 206.688483] ---[ end trace 0000000000000000 ]---
>
> OK, that RB_MISSED_EVENTS is causing an issue. Something else we need to
> look into. The warning is that __rb_get_reader_page() is trying more than 3
> times. Thus I think it's constantly swapping the head page and the reader
> page. Something to investigate.
I think this happens because invalidated buffer is empty. After recovering
persistent ring buffer, there can be contiguous empty buffers on the
ring buffer. Thus the reader needs to find next non-empty buffer
on the list.
Thank you,
>
> So, I'm holding off pulling in these patches. I may take the first one
> though.
>
> -- Steve
--
Masami Hiramatsu (Google) <mhiramat@kernel.org>
^ permalink raw reply
* Re: [PATCH v2] bootconfig: Apply early options from embedded config
From: Masami Hiramatsu @ 2026-03-31 3:58 UTC (permalink / raw)
To: Breno Leitao
Cc: Jonathan Corbet, Shuah Khan, linux-kernel, linux-trace-kernel,
linux-doc, oss, paulmck, rostedt, kernel-team
In-Reply-To: <acqJk-zbyjIiy6hJ@gmail.com>
On Mon, 30 Mar 2026 08:04:23 -0700
Breno Leitao <leitao@debian.org> wrote:
> On Mon, Mar 30, 2026 at 06:15:17AM -0700, Breno Leitao wrote:
> > On Fri, Mar 27, 2026 at 10:37:44PM +0900, Masami Hiramatsu wrote:
> > > On Fri, 27 Mar 2026 03:06:41 -0700
> > > Breno Leitao <leitao@debian.org> wrote:
> >
> > > > > To fix this, we need to change setup_arch() for each architecture so
> > > > > that it calls this bootconfig_apply_early_params().
> > > >
> > > > Could we instead integrate this into parse_early_param() itself? That
> > > > approach would avoid the need to modify each architecture individually.
> > >
> > > Ah, indeed.
> >
> > I investigated integrating bootconfig into parse_early_param() and hit a
> > blocker: xbc_init() and xbc_make_cmdline() depend on memblock_alloc(), but on
> > most architectures (x86, arm64, arm, s390, riscv) parse_early_param() is called
> > from setup_arch() _before_ memblock is initialized.
>
> That said, I'd like to propose a simpler approach as a first step:
>
> 1) Keep calling bootconfig_apply_early_params() from setup_boot_config().
> This is the least intrusive approach and expands bootconfig support to
> additional early boot parameters.
>
> 2) Document that architecture-specific early parameters might be ignored.
> If a parameter is consumed early enough (during setup_arch()), it will
> not see the bootconfig value.
We have to carefully do this because what parameter is arch specific or not
depends on architecture and undocumented.
How about introducing a new Kconfig, which supports early params by
embedded bootconfig?
>
> 3) Ensure that early bootconfig parameters don't overwrite the boot command
> line. For example, if the boot command line has foo=bar and bootconfig
> later has foo=baz, the command line value should take precedence.
> This prevents early boot code (in setup_arch()) from seeing a parameter
> value that will be changed later.
OK, this also needs to be considered. Currently we just pass the bootconfig
parameters right before bootloader given parameters as "extra_command_line"
if "bootconfig" in cmdline or CONFIG_BOOT_CONFIG_FORCE=y.
[boot_config(.kernel)]<command_line>[ -- [boot_config(.init)][init_command_line]]
This is currently expected behavior. The bootconfig parameters are
expected to be overridden by command_line or command_line are appended.
If we change this for early params, we also should change the expected
output of /proc/cmdline too. I think we have 2 options;
- As before, we expect the parameters provided by the boot configuration
to be processed first and then overridden later by the command line.
Or,
- ignore all parameters which is given from the command line, this also
updates existing setup_boot_config() (means xbc_snprint_cmdline() ).
Anyway, this behavior change will also be a bit critical... We have
to announce it.
>
>
> If that is OK, that is what I have right now:
Let me comment on it.
> diff --git a/Documentation/admin-guide/bootconfig.rst b/Documentation/admin-guide/bootconfig.rst
> index f712758472d5c..6ed852a0c66d8 100644
> --- a/Documentation/admin-guide/bootconfig.rst
> +++ b/Documentation/admin-guide/bootconfig.rst
> @@ -169,6 +169,15 @@ Boot Kernel With a Boot Config
> There are two options to boot the kernel with bootconfig: attaching the
> bootconfig to the initrd image or embedding it in the kernel itself.
>
> +Early options (those registered with ``early_param()``) may only be
> +specified in the embedded bootconfig, because the initrd is not yet
> +available when early parameters are processed.
> +
> +Note that embedded bootconfig is parsed after ``setup_arch()``, so
> +early options that are consumed during architecture initialization
> +(e.g., ``mem=``, ``memmap=``, ``earlycon``, ``noapic``, ``nolapic``,
> +``acpi=``, ``numa=``, ``iommu=``) may not take effect from bootconfig.
> +
This is easy to explain, but it's quite troublesome for users to
determine which parameters are unavailable. Currently we can identify
it by `git grep early_param -- arch/${ARCH}`. But it is setup in
setup_arch() we need to track the source code. (Or ask AI :))
> Attaching a Boot Config to Initrd
> ---------------------------------
>
> diff --git a/init/Kconfig b/init/Kconfig
> index 7484cd703bc1a..34adcc1feb9b6 100644
> --- a/init/Kconfig
> +++ b/init/Kconfig
> @@ -1525,6 +1525,16 @@ config BOOT_CONFIG_EMBED
> image. But if the system doesn't support initrd, this option will
> help you by embedding a bootconfig file while building the kernel.
>
> + Unlike bootconfig attached to initrd, the embedded bootconfig also
> + supports early options (those registered with early_param()). Any
> + kernel.* key in the embedded bootconfig is applied before
> + parse_early_param() runs. Early options in initrd bootconfig will
> + not be applied. Early options consumed during setup_arch() (e.g.
> + mem=, memmap=, earlycon, noapic, acpi=, numa=, iommu=) may not
> + take effect. If the same early option
> + appears in both bootconfig and the kernel command line, the
> + command line value takes precedence.
> +
As a compromise, how about making this a separate Kconfig?
config BOOT_CONFIG_EMBED_EARLY_PARAM
bool "Support early_params in embedded bootconfig"
and afterwards, we can introduce
depends on ARCH_BOOT_CONFIG_EMBED_EARLY_PARAM
Thank you,
--
Masami Hiramatsu (Google) <mhiramat@kernel.org>
^ permalink raw reply
* Re: [PATCH v14 5/5] ring-buffer: Add persistent ring buffer selftest
From: Masami Hiramatsu @ 2026-03-31 4:12 UTC (permalink / raw)
To: Steven Rostedt
Cc: Mathieu Desnoyers, linux-kernel, linux-trace-kernel, Ian Rogers
In-Reply-To: <20260330162419.5e4708fb@gandalf.local.home>
On Mon, 30 Mar 2026 16:24:19 -0400
Steven Rostedt <rostedt@goodmis.org> wrote:
> On Mon, 30 Mar 2026 21:50:27 +0900
> "Masami Hiramatsu (Google)" <mhiramat@kernel.org> wrote:
>
> > @@ -2558,12 +2577,64 @@ static void rb_free_cpu_buffer(struct ring_buffer_per_cpu *cpu_buffer)
> > kfree(cpu_buffer);
> > }
> >
> > +#ifdef CONFIG_RING_BUFFER_PERSISTENT_INJECT
> > +static void rb_test_inject_invalid_pages(struct trace_buffer *buffer)
> > +{
> > + struct ring_buffer_per_cpu *cpu_buffer;
> > + struct ring_buffer_cpu_meta *meta;
> > + struct buffer_data_page *dpage;
> > + u32 entry_bytes = 0;
> > + unsigned long ptr;
> > + int subbuf_size;
> > + int invalid = 0;
> > + int cpu;
> > + int i;
> > +
> > + if (!(buffer->flags & RB_FL_TESTING))
> > + return;
> > +
> > + guard(preempt)();
> > + cpu = smp_processor_id();
> > +
> > + cpu_buffer = buffer->buffers[cpu];
> > + meta = cpu_buffer->ring_meta;
> > + ptr = (unsigned long)rb_subbufs_from_meta(meta);
> > + subbuf_size = meta->subbuf_size;
> > +
> > + for (i = 0; i < meta->nr_subbufs; i++) {
> > + int idx = meta->buffers[i];
> > +
> > + dpage = (void *)(ptr + idx * subbuf_size);
> > + /* Skip unused pages */
> > + if (!local_read(&dpage->commit))
> > + continue;
> > +
> > + /* Invalidate even pages. */
> > + if (!(i & 0x1)) {
> > + local_add(subbuf_size + 1, &dpage->commit);
> > + invalid++;
> > + } else {
> > + /* Count total commit bytes. */
> > + entry_bytes += local_read(&dpage->commit);
> > + }
> > + }
> > +
> > + pr_info("Inject invalidated %d pages on CPU%d, total size: %ld\n",
> > + invalid, cpu, (long)entry_bytes);
>
> This is only enabled when testing. Let's make that a pr_warn() as we really
> do want to be able to see it. And it should warn that it is invalidating pages!
> (warn as in pr_warn, it doesn't need a warn as in WARN()).
OK. Let me update it.
Thanks!
>
> -- Steve
>
>
> > + meta->nr_invalid = invalid;
> > + meta->entry_bytes = entry_bytes;
> > +}
> > +#else /* !CONFIG_RING_BUFFER_PERSISTENT_INJECT */
> > +#define rb_test_inject_invalid_pages(buffer) do { } while (0)
> > +#endif
> > +
> > /* Stop recording on a persistent buffer and flush cache if needed. */
> > static int rb_flush_buffer_cb(struct notifier_block *nb, unsigned long event, void *data)
> > {
> > struct trace_buffer *buffer = container_of(nb, struct trace_buffer, flush_nb);
> >
> > ring_buffer_record_off(buffer);
> > + rb_test_inject_invalid_pages(buffer);
> > arch_ring_buffer_flush_range(buffer->range_addr_start, buffer->range_addr_end);
> > return NOTIFY_DONE;
> > }
--
Masami Hiramatsu (Google) <mhiramat@kernel.org>
^ permalink raw reply
* [PATCH] tracing: always provide a prototype for tracing_alloc_snapshot()
From: Bartosz Golaszewski @ 2026-03-31 8:20 UTC (permalink / raw)
To: Steven Rostedt, Masami Hiramatsu, Mathieu Desnoyers
Cc: linux-kernel, linux-trace-kernel, Bartosz Golaszewski
The tracing_alloc_snapshot() symbol is always exported even with
!CONFIG_TRACER_SNAPSHOT so the prototype too must be always visible or
we'll see the following warning:
kernel/trace/trace.c:820:5: warning: no previous prototype for ‘tracing_alloc_snapshot’ [-Wmissing-prototypes]
820 | int tracing_alloc_snapshot(void)
| ^~~~~~~~~~~~~~~~~~~~~~
Fixes: bade44fe5462 ("tracing: Move snapshot code out of trace.c and into trace_snapshot.c")
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@oss.qualcomm.com>
---
kernel/trace/trace.h | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 6abd9e16ef21..e8612b8b0a34 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -2275,6 +2275,8 @@ static inline void __init trace_event_init(void) { }
static inline void trace_event_update_all(struct trace_eval_map **map, int len) { }
#endif
+int tracing_alloc_snapshot(void);
+
#ifdef CONFIG_TRACER_SNAPSHOT
extern const struct file_operations snapshot_fops;
extern const struct file_operations snapshot_raw_fops;
@@ -2282,7 +2284,6 @@ extern const struct file_operations snapshot_raw_fops;
/* Used when creating instances */
int trace_allocate_snapshot(struct trace_array *tr, int size);
-int tracing_alloc_snapshot(void);
void tracing_snapshot_cond(struct trace_array *tr, void *cond_data);
int tracing_snapshot_cond_enable(struct trace_array *tr, void *cond_data, cond_update_fn_t update);
int tracing_snapshot_cond_disable(struct trace_array *tr);
--
2.47.3
^ permalink raw reply related
* [PATCH v15 0/5] ring-buffer: Making persistent ring buffers robust
From: Masami Hiramatsu (Google) @ 2026-03-31 8:35 UTC (permalink / raw)
To: Steven Rostedt, Catalin Marinas, Will Deacon
Cc: Masami Hiramatsu, Mathieu Desnoyers, linux-kernel,
linux-trace-kernel, Ian Rogers, linux-arm-kernel
Hi,
Here is the 15th version of improvement patches for making persistent
ring buffers robust to failures.
The previous version is here:
https://lore.kernel.org/all/177487498530.3463592.12715592581212799257.stgit@mhiramat.tok.corp.google.com/
This version fixes warning if reader see contiguous multiple
empty (invalidated) pages on the recovered persistent ring buffer
[2/5], do not show discarded pages if it is 0 [2/5], use pr_warn()
for showing test result [4/5], and inject errors to the pages which
is multiples of 5 too[4/5].
This also drops "Reset RB_MISSED_* flags" patch, and add a patch
to show commit number on each data page [5/5] for debugging.
In this version, I added arm64 maitainers to request their
review for [1/5], which introduces asm/ring_buffer.h for flushing
the cache before reboot.
Thank you,
---
Masami Hiramatsu (Google) (5):
ring-buffer: Flush and stop persistent ring buffer on panic
ring-buffer: Skip invalid sub-buffers when validating persistent ring buffer
ring-buffer: Skip invalid sub-buffers when rewinding persistent ring buffer
ring-buffer: Add persistent ring buffer invalid-page inject test
ring-buffer: Show commit numbers in buffer_meta file
arch/alpha/include/asm/Kbuild | 1
arch/arc/include/asm/Kbuild | 1
arch/arm/include/asm/Kbuild | 1
arch/arm64/include/asm/ring_buffer.h | 10 +
arch/csky/include/asm/Kbuild | 1
arch/hexagon/include/asm/Kbuild | 1
arch/loongarch/include/asm/Kbuild | 1
arch/m68k/include/asm/Kbuild | 1
arch/microblaze/include/asm/Kbuild | 1
arch/mips/include/asm/Kbuild | 1
arch/nios2/include/asm/Kbuild | 1
arch/openrisc/include/asm/Kbuild | 1
arch/parisc/include/asm/Kbuild | 1
arch/powerpc/include/asm/Kbuild | 1
arch/riscv/include/asm/Kbuild | 1
arch/s390/include/asm/Kbuild | 1
arch/sh/include/asm/Kbuild | 1
arch/sparc/include/asm/Kbuild | 1
arch/um/include/asm/Kbuild | 1
arch/x86/include/asm/Kbuild | 1
arch/xtensa/include/asm/Kbuild | 1
include/asm-generic/ring_buffer.h | 13 ++
include/linux/ring_buffer.h | 1
kernel/trace/Kconfig | 31 ++++
kernel/trace/ring_buffer.c | 258 ++++++++++++++++++++++++++--------
kernel/trace/trace.c | 4 +
26 files changed, 273 insertions(+), 64 deletions(-)
create mode 100644 arch/arm64/include/asm/ring_buffer.h
create mode 100644 include/asm-generic/ring_buffer.h
--
Masami Hiramatsu (Google) <mhiramat@kernel.org>
^ permalink raw reply
* [PATCH v15 1/5] ring-buffer: Flush and stop persistent ring buffer on panic
From: Masami Hiramatsu (Google) @ 2026-03-31 8:36 UTC (permalink / raw)
To: Steven Rostedt, Catalin Marinas, Will Deacon
Cc: Masami Hiramatsu, Mathieu Desnoyers, linux-kernel,
linux-trace-kernel, Ian Rogers, linux-arm-kernel
In-Reply-To: <177494615421.71933.3679132057004156013.stgit@mhiramat.tok.corp.google.com>
From: Masami Hiramatsu (Google) <mhiramat@kernel.org>
On real hardware, panic and machine reboot may not flush hardware cache
to memory. This means the persistent ring buffer, which relies on a
coherent state of memory, may not have its events written to the buffer
and they may be lost. Moreover, there may be inconsistency with the
counters which are used for validation of the integrity of the
persistent ring buffer which may cause all data to be discarded.
To avoid this issue, stop recording of the ring buffer on panic and
flush the cache of the ring buffer's memory.
Fixes: e645535a954a ("tracing: Add option to use memmapped memory for trace boot instance")
Cc: stable@vger.kernel.org
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
---
Changes in v13:
- Fix a rebase conflict.
Changes in v11:
- Do nothing by default since flush_cache_vmap() does nothing on x86
but it can cause deadlock on some architectures via on_each_cpu()
because other CPUs will be stoppped when panic notifier is called.
Changes in v9:
- Fix typo of & to &&.
- Fix typo of "Generic"
Changes in v6:
- Introduce asm/ring_buffer.h for arch_ring_buffer_flush_range().
- Use flush_cache_vmap() instead of flush_cache_all().
Changes in v5:
- Use ring_buffer_record_off() instead of ring_buffer_record_disable().
- Use flush_cache_all() to ensure flush all cache.
Changes in v3:
- update patch description.
---
arch/alpha/include/asm/Kbuild | 1 +
arch/arc/include/asm/Kbuild | 1 +
arch/arm/include/asm/Kbuild | 1 +
arch/arm64/include/asm/ring_buffer.h | 10 ++++++++++
arch/csky/include/asm/Kbuild | 1 +
arch/hexagon/include/asm/Kbuild | 1 +
arch/loongarch/include/asm/Kbuild | 1 +
arch/m68k/include/asm/Kbuild | 1 +
arch/microblaze/include/asm/Kbuild | 1 +
arch/mips/include/asm/Kbuild | 1 +
arch/nios2/include/asm/Kbuild | 1 +
arch/openrisc/include/asm/Kbuild | 1 +
arch/parisc/include/asm/Kbuild | 1 +
arch/powerpc/include/asm/Kbuild | 1 +
arch/riscv/include/asm/Kbuild | 1 +
arch/s390/include/asm/Kbuild | 1 +
arch/sh/include/asm/Kbuild | 1 +
arch/sparc/include/asm/Kbuild | 1 +
arch/um/include/asm/Kbuild | 1 +
arch/x86/include/asm/Kbuild | 1 +
arch/xtensa/include/asm/Kbuild | 1 +
include/asm-generic/ring_buffer.h | 13 +++++++++++++
kernel/trace/ring_buffer.c | 22 ++++++++++++++++++++++
23 files changed, 65 insertions(+)
create mode 100644 arch/arm64/include/asm/ring_buffer.h
create mode 100644 include/asm-generic/ring_buffer.h
diff --git a/arch/alpha/include/asm/Kbuild b/arch/alpha/include/asm/Kbuild
index 483965c5a4de..b154b4e3dfa8 100644
--- a/arch/alpha/include/asm/Kbuild
+++ b/arch/alpha/include/asm/Kbuild
@@ -5,4 +5,5 @@ generic-y += agp.h
generic-y += asm-offsets.h
generic-y += kvm_para.h
generic-y += mcs_spinlock.h
+generic-y += ring_buffer.h
generic-y += text-patching.h
diff --git a/arch/arc/include/asm/Kbuild b/arch/arc/include/asm/Kbuild
index 4c69522e0328..483caacc6988 100644
--- a/arch/arc/include/asm/Kbuild
+++ b/arch/arc/include/asm/Kbuild
@@ -5,5 +5,6 @@ generic-y += extable.h
generic-y += kvm_para.h
generic-y += mcs_spinlock.h
generic-y += parport.h
+generic-y += ring_buffer.h
generic-y += user.h
generic-y += text-patching.h
diff --git a/arch/arm/include/asm/Kbuild b/arch/arm/include/asm/Kbuild
index 03657ff8fbe3..decad5f2c826 100644
--- a/arch/arm/include/asm/Kbuild
+++ b/arch/arm/include/asm/Kbuild
@@ -3,6 +3,7 @@ generic-y += early_ioremap.h
generic-y += extable.h
generic-y += flat.h
generic-y += parport.h
+generic-y += ring_buffer.h
generated-y += mach-types.h
generated-y += unistd-nr.h
diff --git a/arch/arm64/include/asm/ring_buffer.h b/arch/arm64/include/asm/ring_buffer.h
new file mode 100644
index 000000000000..62316c406888
--- /dev/null
+++ b/arch/arm64/include/asm/ring_buffer.h
@@ -0,0 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef _ASM_ARM64_RING_BUFFER_H
+#define _ASM_ARM64_RING_BUFFER_H
+
+#include <asm/cacheflush.h>
+
+/* Flush D-cache on persistent ring buffer */
+#define arch_ring_buffer_flush_range(start, end) dcache_clean_pop(start, end)
+
+#endif /* _ASM_ARM64_RING_BUFFER_H */
diff --git a/arch/csky/include/asm/Kbuild b/arch/csky/include/asm/Kbuild
index 3a5c7f6e5aac..7dca0c6cdc84 100644
--- a/arch/csky/include/asm/Kbuild
+++ b/arch/csky/include/asm/Kbuild
@@ -9,6 +9,7 @@ generic-y += qrwlock.h
generic-y += qrwlock_types.h
generic-y += qspinlock.h
generic-y += parport.h
+generic-y += ring_buffer.h
generic-y += user.h
generic-y += vmlinux.lds.h
generic-y += text-patching.h
diff --git a/arch/hexagon/include/asm/Kbuild b/arch/hexagon/include/asm/Kbuild
index 1efa1e993d4b..0f887d4238ed 100644
--- a/arch/hexagon/include/asm/Kbuild
+++ b/arch/hexagon/include/asm/Kbuild
@@ -5,4 +5,5 @@ generic-y += extable.h
generic-y += iomap.h
generic-y += kvm_para.h
generic-y += mcs_spinlock.h
+generic-y += ring_buffer.h
generic-y += text-patching.h
diff --git a/arch/loongarch/include/asm/Kbuild b/arch/loongarch/include/asm/Kbuild
index 9034b583a88a..7e92957baf6a 100644
--- a/arch/loongarch/include/asm/Kbuild
+++ b/arch/loongarch/include/asm/Kbuild
@@ -10,5 +10,6 @@ generic-y += qrwlock.h
generic-y += user.h
generic-y += ioctl.h
generic-y += mmzone.h
+generic-y += ring_buffer.h
generic-y += statfs.h
generic-y += text-patching.h
diff --git a/arch/m68k/include/asm/Kbuild b/arch/m68k/include/asm/Kbuild
index b282e0dd8dc1..62543bf305ff 100644
--- a/arch/m68k/include/asm/Kbuild
+++ b/arch/m68k/include/asm/Kbuild
@@ -3,5 +3,6 @@ generated-y += syscall_table.h
generic-y += extable.h
generic-y += kvm_para.h
generic-y += mcs_spinlock.h
+generic-y += ring_buffer.h
generic-y += spinlock.h
generic-y += text-patching.h
diff --git a/arch/microblaze/include/asm/Kbuild b/arch/microblaze/include/asm/Kbuild
index 7178f990e8b3..0030309b47ad 100644
--- a/arch/microblaze/include/asm/Kbuild
+++ b/arch/microblaze/include/asm/Kbuild
@@ -5,6 +5,7 @@ generic-y += extable.h
generic-y += kvm_para.h
generic-y += mcs_spinlock.h
generic-y += parport.h
+generic-y += ring_buffer.h
generic-y += syscalls.h
generic-y += tlb.h
generic-y += user.h
diff --git a/arch/mips/include/asm/Kbuild b/arch/mips/include/asm/Kbuild
index 684569b2ecd6..9771c3d85074 100644
--- a/arch/mips/include/asm/Kbuild
+++ b/arch/mips/include/asm/Kbuild
@@ -12,5 +12,6 @@ generic-y += mcs_spinlock.h
generic-y += parport.h
generic-y += qrwlock.h
generic-y += qspinlock.h
+generic-y += ring_buffer.h
generic-y += user.h
generic-y += text-patching.h
diff --git a/arch/nios2/include/asm/Kbuild b/arch/nios2/include/asm/Kbuild
index 28004301c236..0a2530964413 100644
--- a/arch/nios2/include/asm/Kbuild
+++ b/arch/nios2/include/asm/Kbuild
@@ -5,6 +5,7 @@ generic-y += cmpxchg.h
generic-y += extable.h
generic-y += kvm_para.h
generic-y += mcs_spinlock.h
+generic-y += ring_buffer.h
generic-y += spinlock.h
generic-y += user.h
generic-y += text-patching.h
diff --git a/arch/openrisc/include/asm/Kbuild b/arch/openrisc/include/asm/Kbuild
index cef49d60d74c..8aa34621702d 100644
--- a/arch/openrisc/include/asm/Kbuild
+++ b/arch/openrisc/include/asm/Kbuild
@@ -8,4 +8,5 @@ generic-y += spinlock_types.h
generic-y += spinlock.h
generic-y += qrwlock_types.h
generic-y += qrwlock.h
+generic-y += ring_buffer.h
generic-y += user.h
diff --git a/arch/parisc/include/asm/Kbuild b/arch/parisc/include/asm/Kbuild
index 4fb596d94c89..d48d158f7241 100644
--- a/arch/parisc/include/asm/Kbuild
+++ b/arch/parisc/include/asm/Kbuild
@@ -4,4 +4,5 @@ generated-y += syscall_table_64.h
generic-y += agp.h
generic-y += kvm_para.h
generic-y += mcs_spinlock.h
+generic-y += ring_buffer.h
generic-y += user.h
diff --git a/arch/powerpc/include/asm/Kbuild b/arch/powerpc/include/asm/Kbuild
index 2e23533b67e3..805b5aeebb6f 100644
--- a/arch/powerpc/include/asm/Kbuild
+++ b/arch/powerpc/include/asm/Kbuild
@@ -5,4 +5,5 @@ generated-y += syscall_table_spu.h
generic-y += agp.h
generic-y += mcs_spinlock.h
generic-y += qrwlock.h
+generic-y += ring_buffer.h
generic-y += early_ioremap.h
diff --git a/arch/riscv/include/asm/Kbuild b/arch/riscv/include/asm/Kbuild
index bd5fc9403295..7721b63642f4 100644
--- a/arch/riscv/include/asm/Kbuild
+++ b/arch/riscv/include/asm/Kbuild
@@ -14,5 +14,6 @@ generic-y += ticket_spinlock.h
generic-y += qrwlock.h
generic-y += qrwlock_types.h
generic-y += qspinlock.h
+generic-y += ring_buffer.h
generic-y += user.h
generic-y += vmlinux.lds.h
diff --git a/arch/s390/include/asm/Kbuild b/arch/s390/include/asm/Kbuild
index 80bad7de7a04..0c1fc47c3ba0 100644
--- a/arch/s390/include/asm/Kbuild
+++ b/arch/s390/include/asm/Kbuild
@@ -7,3 +7,4 @@ generated-y += unistd_nr.h
generic-y += asm-offsets.h
generic-y += mcs_spinlock.h
generic-y += mmzone.h
+generic-y += ring_buffer.h
diff --git a/arch/sh/include/asm/Kbuild b/arch/sh/include/asm/Kbuild
index 4d3f10ed8275..f0403d3ee8ab 100644
--- a/arch/sh/include/asm/Kbuild
+++ b/arch/sh/include/asm/Kbuild
@@ -3,4 +3,5 @@ generated-y += syscall_table.h
generic-y += kvm_para.h
generic-y += mcs_spinlock.h
generic-y += parport.h
+generic-y += ring_buffer.h
generic-y += text-patching.h
diff --git a/arch/sparc/include/asm/Kbuild b/arch/sparc/include/asm/Kbuild
index 17ee8a273aa6..49c6bb326b75 100644
--- a/arch/sparc/include/asm/Kbuild
+++ b/arch/sparc/include/asm/Kbuild
@@ -4,4 +4,5 @@ generated-y += syscall_table_64.h
generic-y += agp.h
generic-y += kvm_para.h
generic-y += mcs_spinlock.h
+generic-y += ring_buffer.h
generic-y += text-patching.h
diff --git a/arch/um/include/asm/Kbuild b/arch/um/include/asm/Kbuild
index 1b9b82bbe322..2a1629ba8140 100644
--- a/arch/um/include/asm/Kbuild
+++ b/arch/um/include/asm/Kbuild
@@ -17,6 +17,7 @@ generic-y += module.lds.h
generic-y += parport.h
generic-y += percpu.h
generic-y += preempt.h
+generic-y += ring_buffer.h
generic-y += runtime-const.h
generic-y += softirq_stack.h
generic-y += switch_to.h
diff --git a/arch/x86/include/asm/Kbuild b/arch/x86/include/asm/Kbuild
index 4566000e15c4..078fd2c0d69d 100644
--- a/arch/x86/include/asm/Kbuild
+++ b/arch/x86/include/asm/Kbuild
@@ -14,3 +14,4 @@ generic-y += early_ioremap.h
generic-y += fprobe.h
generic-y += mcs_spinlock.h
generic-y += mmzone.h
+generic-y += ring_buffer.h
diff --git a/arch/xtensa/include/asm/Kbuild b/arch/xtensa/include/asm/Kbuild
index 13fe45dea296..e57af619263a 100644
--- a/arch/xtensa/include/asm/Kbuild
+++ b/arch/xtensa/include/asm/Kbuild
@@ -6,5 +6,6 @@ generic-y += mcs_spinlock.h
generic-y += parport.h
generic-y += qrwlock.h
generic-y += qspinlock.h
+generic-y += ring_buffer.h
generic-y += user.h
generic-y += text-patching.h
diff --git a/include/asm-generic/ring_buffer.h b/include/asm-generic/ring_buffer.h
new file mode 100644
index 000000000000..201d2aee1005
--- /dev/null
+++ b/include/asm-generic/ring_buffer.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Generic arch dependent ring_buffer macros.
+ */
+#ifndef __ASM_GENERIC_RING_BUFFER_H__
+#define __ASM_GENERIC_RING_BUFFER_H__
+
+#include <linux/cacheflush.h>
+
+/* Flush cache on ring buffer range if needed. Do nothing by default. */
+#define arch_ring_buffer_flush_range(start, end) do { } while (0)
+
+#endif /* __ASM_GENERIC_RING_BUFFER_H__ */
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 8b6c39bba56d..3e793bd1c134 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -7,6 +7,7 @@
#include <linux/ring_buffer_types.h>
#include <linux/sched/isolation.h>
#include <linux/trace_recursion.h>
+#include <linux/panic_notifier.h>
#include <linux/trace_events.h>
#include <linux/ring_buffer.h>
#include <linux/trace_clock.h>
@@ -31,6 +32,7 @@
#include <linux/oom.h>
#include <linux/mm.h>
+#include <asm/ring_buffer.h>
#include <asm/local64.h>
#include <asm/local.h>
#include <asm/setup.h>
@@ -559,6 +561,7 @@ struct trace_buffer {
unsigned long range_addr_start;
unsigned long range_addr_end;
+ struct notifier_block flush_nb;
struct ring_buffer_meta *meta;
@@ -2520,6 +2523,16 @@ static void rb_free_cpu_buffer(struct ring_buffer_per_cpu *cpu_buffer)
kfree(cpu_buffer);
}
+/* Stop recording on a persistent buffer and flush cache if needed. */
+static int rb_flush_buffer_cb(struct notifier_block *nb, unsigned long event, void *data)
+{
+ struct trace_buffer *buffer = container_of(nb, struct trace_buffer, flush_nb);
+
+ ring_buffer_record_off(buffer);
+ arch_ring_buffer_flush_range(buffer->range_addr_start, buffer->range_addr_end);
+ return NOTIFY_DONE;
+}
+
static struct trace_buffer *alloc_buffer(unsigned long size, unsigned flags,
int order, unsigned long start,
unsigned long end,
@@ -2650,6 +2663,12 @@ static struct trace_buffer *alloc_buffer(unsigned long size, unsigned flags,
mutex_init(&buffer->mutex);
+ /* Persistent ring buffer needs to flush cache before reboot. */
+ if (start && end) {
+ buffer->flush_nb.notifier_call = rb_flush_buffer_cb;
+ atomic_notifier_chain_register(&panic_notifier_list, &buffer->flush_nb);
+ }
+
return_ptr(buffer);
fail_free_buffers:
@@ -2748,6 +2767,9 @@ ring_buffer_free(struct trace_buffer *buffer)
{
int cpu;
+ if (buffer->range_addr_start && buffer->range_addr_end)
+ atomic_notifier_chain_unregister(&panic_notifier_list, &buffer->flush_nb);
+
cpuhp_state_remove_instance(CPUHP_TRACE_RB_PREPARE, &buffer->node);
irq_work_sync(&buffer->irq_work.work);
^ permalink raw reply related
* [PATCH v15 2/5] ring-buffer: Skip invalid sub-buffers when validating persistent ring buffer
From: Masami Hiramatsu (Google) @ 2026-03-31 8:36 UTC (permalink / raw)
To: Steven Rostedt, Catalin Marinas, Will Deacon
Cc: Masami Hiramatsu, Mathieu Desnoyers, linux-kernel,
linux-trace-kernel, Ian Rogers, linux-arm-kernel
In-Reply-To: <177494615421.71933.3679132057004156013.stgit@mhiramat.tok.corp.google.com>
From: Masami Hiramatsu (Google) <mhiramat@kernel.org>
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.
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
---
Changes in v15:
- Skip reader_page loop check on persistent ring buffer because
there can be contiguous empty(invalidated) pages.
- Do not show discarded page number information if it is 0.
Changes in v11:
- Fix a typo.
Changes in v9:
- Add meta->subbuf_size check.
- Fix a typo.
- Handle invalid reader_page case.
Changes in v8:
- Add comment in rb_valudate_buffer()
- Clear the RB_MISSED_* flags in rb_valudate_buffer() instead of
skipping subbuf.
- Remove unused subbuf local variable from rb_cpu_meta_valid().
Changes in v7:
- Combined with Handling RB_MISSED_* flags patch, focus on validation at boot.
- Remove checking subbuffer data when validating metadata, because it should be done
later.
- Do not mark the discarded sub buffer page but just reset it.
Changes in v6:
- Show invalid page detection message once per CPU.
Changes in v5:
- Instead of showing errors for each page, just show the number
of discarded pages at last.
Changes in v3:
- Record missed data event on commit.
---
kernel/trace/ring_buffer.c | 109 ++++++++++++++++++++++++++------------------
1 file changed, 65 insertions(+), 44 deletions(-)
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 3e793bd1c134..2a6254edae5f 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -370,6 +370,12 @@ static __always_inline unsigned int rb_page_commit(struct buffer_page *bpage)
return local_read(&bpage->page->commit);
}
+/* 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 */
@@ -1762,7 +1768,6 @@ 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;
@@ -1770,6 +1775,11 @@ 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);
@@ -1786,11 +1796,12 @@ 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) {
@@ -1798,18 +1809,12 @@ 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;
@@ -1873,13 +1878,22 @@ 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)
+ return -1;
return rb_read_data_buffer(dpage, tail, cpu, &ts, &delta);
}
@@ -1890,6 +1904,7 @@ static void rb_meta_validate_events(struct ring_buffer_per_cpu *cpu_buffer)
struct buffer_page *head_page, *orig_head;
unsigned long entry_bytes = 0;
unsigned long entries = 0;
+ int discarded = 0;
int ret;
u64 ts;
int i;
@@ -1900,14 +1915,19 @@ static void rb_meta_validate_events(struct ring_buffer_per_cpu *cpu_buffer)
orig_head = head_page = cpu_buffer->head_page;
/* Do the reader page first */
- ret = rb_validate_buffer(cpu_buffer->reader_page->page, cpu_buffer->cpu);
+ ret = rb_validate_buffer(cpu_buffer->reader_page->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(&cpu_buffer->reader_page->entries, 0);
+ local_set(&cpu_buffer->reader_page->page->commit, 0);
+ } else {
+ entries += ret;
+ entry_bytes += rb_page_size(cpu_buffer->reader_page);
+ local_set(&cpu_buffer->reader_page->entries, ret);
}
- entries += ret;
- entry_bytes += local_read(&cpu_buffer->reader_page->page->commit);
- local_set(&cpu_buffer->reader_page->entries, ret);
ts = head_page->page->time_stamp;
@@ -1935,7 +1955,7 @@ 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;
@@ -2014,21 +2034,24 @@ static void rb_meta_validate_events(struct ring_buffer_per_cpu *cpu_buffer)
if (head_page == cpu_buffer->reader_page)
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;
}
@@ -2042,7 +2065,10 @@ 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:
@@ -3329,12 +3355,6 @@ 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)
{
@@ -5647,11 +5667,12 @@ __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.
*/
- if (RB_WARN_ON(cpu_buffer, ++nr_loops > 3)) {
+ if (RB_WARN_ON(cpu_buffer, ++nr_loops > 3 && !cpu_buffer->ring_meta)) {
reader = NULL;
goto out;
}
^ permalink raw reply related
* [PATCH v15 3/5] ring-buffer: Skip invalid sub-buffers when rewinding persistent ring buffer
From: Masami Hiramatsu (Google) @ 2026-03-31 8:36 UTC (permalink / raw)
To: Steven Rostedt, Catalin Marinas, Will Deacon
Cc: Masami Hiramatsu, Mathieu Desnoyers, linux-kernel,
linux-trace-kernel, Ian Rogers, linux-arm-kernel
In-Reply-To: <177494615421.71933.3679132057004156013.stgit@mhiramat.tok.corp.google.com>
From: Masami Hiramatsu (Google) <mhiramat@kernel.org>
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) <mhiramat@kernel.org>
---
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 | 76 +++++++++++++++++++++++++-------------------
1 file changed, 43 insertions(+), 33 deletions(-)
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 2a6254edae5f..5ff632ca3858 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,
+static int rb_validate_buffer(struct buffer_page *bpage, int cpu,
struct ring_buffer_cpu_meta *meta)
{
+ struct buffer_data_page *dpage = bpage->page;
unsigned long long ts;
unsigned long tail;
u64 delta;
+ int ret = -1;
/*
* When a sub-buffer is recovered from a read, the commit value may
@@ -1892,9 +1895,17 @@ 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)
- return -1;
- return rb_read_data_buffer(dpage, tail, cpu, &ts, &delta);
+ if (tail <= meta->subbuf_size)
+ ret = rb_read_data_buffer(dpage, tail, cpu, &ts, &delta);
+
+ if (ret < 0) {
+ local_set(&bpage->entries, 0);
+ local_set(&bpage->page->commit, 0);
+ } else {
+ local_set(&bpage->entries, ret);
+ }
+
+ return ret;
}
/* If the meta data has been validated, now validate the events */
@@ -1915,18 +1926,14 @@ static void rb_meta_validate_events(struct ring_buffer_per_cpu *cpu_buffer)
orig_head = head_page = cpu_buffer->head_page;
/* Do the reader page first */
- ret = rb_validate_buffer(cpu_buffer->reader_page->page, cpu_buffer->cpu, meta);
+ ret = rb_validate_buffer(cpu_buffer->reader_page, cpu_buffer->cpu, meta);
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(&cpu_buffer->reader_page->entries, 0);
- local_set(&cpu_buffer->reader_page->page->commit, 0);
} else {
entries += ret;
entry_bytes += rb_page_size(cpu_buffer->reader_page);
- local_set(&cpu_buffer->reader_page->entries, ret);
}
ts = head_page->page->time_stamp;
@@ -1945,26 +1952,33 @@ 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)
- 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)
+ /* Rewind until unused page (no timestamp, no commit). */
+ if (!head_page->page->time_stamp && rb_page_commit(head_page) == 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);
+ /*
+ * 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);
+ if (ret >= 0 && ts < head_page->page->time_stamp) {
+ local_set(&head_page->entries, 0);
+ local_set(&head_page->page->commit, 0);
+ head_page->page->time_stamp = ts;
+ ret = -1;
+ }
+ 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);
@@ -2034,15 +2048,12 @@ static void rb_meta_validate_events(struct ring_buffer_per_cpu *cpu_buffer)
if (head_page == cpu_buffer->reader_page)
continue;
- ret = rb_validate_buffer(head_page->page, cpu_buffer->cpu, meta);
+ ret = rb_validate_buffer(head_page, cpu_buffer->cpu, meta);
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)
@@ -2050,7 +2061,6 @@ 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);
}
if (head_page == cpu_buffer->commit_page)
break;
@@ -2083,7 +2093,7 @@ static void rb_meta_validate_events(struct ring_buffer_per_cpu *cpu_buffer)
/* 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);
}
}
^ permalink raw reply related
* [PATCH v15 4/5] ring-buffer: Add persistent ring buffer invalid-page inject test
From: Masami Hiramatsu (Google) @ 2026-03-31 8:36 UTC (permalink / raw)
To: Steven Rostedt, Catalin Marinas, Will Deacon
Cc: Masami Hiramatsu, Mathieu Desnoyers, linux-kernel,
linux-trace-kernel, Ian Rogers, linux-arm-kernel
In-Reply-To: <177494615421.71933.3679132057004156013.stgit@mhiramat.tok.corp.google.com>
From: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Add a self-destractive test for the persistent ring buffer.
This will inject erroneous value to some sub-buffer pages (where
the index is even or multiples of 5) in the persistent ring buffer
when kernel gets panic, and check whether the number of detected
invalid pages and the total entry_bytes are the same as recorded
values after reboot.
This can ensure the kernel correctly recover partially corrupted
persistent ring buffer when boot.
The test only runs on the persistent ring buffer whose name is
"ptracingtest". And user has to fill it up with events before
kernel panics.
To run the test, enable CONFIG_RING_BUFFER_PERSISTENT_INJECT
and you have to setup the kernel cmdline;
reserve_mem=20M:2M:trace trace_instance=ptracingtest^traceoff@trace
panic=1
And run following commands after the 1st boot;
cd /sys/kernel/tracing/instances/ptracingtest
echo 1 > tracing_on
echo 1 > events/enable
sleep 3
echo c > /proc/sysrq-trigger
After panic message, the kernel will reboot and run the verification
on the persistent ring buffer, e.g.
Ring buffer meta [2] invalid buffer page detected
Ring buffer meta [2] is from previous boot! (318 pages discarded)
Ring buffer testing [2] invalid pages: PASSED (318/318)
Ring buffer testing [2] entry_bytes: PASSED (1300476/1300476)
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
---
Changes in v15:
- Use pr_warn() for test result.
- Inject errors on the page index is multiples of 5 so that
this can reproduce contiguous empty pages.
Changes in v14:
- Rename config to CONFIG_RING_BUFFER_PERSISTENT_INJECT.
- Clear meta->nr_invalid/entry_bytes after testing.
- Add test commands in config comment.
Changes in v10:
- Add entry_bytes test.
- Do not compile test code if CONFIG_RING_BUFFER_PERSISTENT_SELFTEST=n.
Changes in v9:
- Test also reader pages.
---
include/linux/ring_buffer.h | 1 +
kernel/trace/Kconfig | 31 ++++++++++++++++++
kernel/trace/ring_buffer.c | 74 +++++++++++++++++++++++++++++++++++++++++++
kernel/trace/trace.c | 4 ++
4 files changed, 110 insertions(+)
diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h
index 994f52b34344..0670742b2d60 100644
--- a/include/linux/ring_buffer.h
+++ b/include/linux/ring_buffer.h
@@ -238,6 +238,7 @@ int ring_buffer_subbuf_size_get(struct trace_buffer *buffer);
enum ring_buffer_flags {
RB_FL_OVERWRITE = 1 << 0,
+ RB_FL_TESTING = 1 << 1,
};
#ifdef CONFIG_RING_BUFFER
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index e130da35808f..07305ed6d745 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -1202,6 +1202,37 @@ config RING_BUFFER_VALIDATE_TIME_DELTAS
Only say Y if you understand what this does, and you
still want it enabled. Otherwise say N
+config RING_BUFFER_PERSISTENT_INJECT
+ bool "Enable persistent ring buffer error injection test"
+ depends on RING_BUFFER
+ help
+ Run a selftest on the persistent ring buffer which names
+ "ptracingtest" (and its backup) when panic_on_reboot by
+ invalidating ring buffer pages.
+ To use this, boot kernel with "ptracingtest" persistent
+ ring buffer, e.g.
+
+ reserve_mem=20M:2M:trace trace_instance=ptracingtest@trace panic=1
+
+ And after the 1st boot, run test command, like;
+
+ cd /sys/kernel/tracing/instances/ptracingtest
+ echo 1 > events/enable
+ echo 1 > tracing_on
+ sleep 3
+ echo c > /proc/sysrq-trigger
+
+ After panic message, the kernel reboots and show test results
+ on the boot log.
+
+ Note that user has to enable events on the persistent ring
+ buffer manually to fill up ring buffers before rebooting.
+ Since this invalidates the data on test target ring buffer,
+ "ptracingtest" persistent ring buffer must not be used for
+ actual tracing, but only for testing.
+
+ If unsure, say N
+
config MMIOTRACE_TEST
tristate "Test module for mmiotrace"
depends on MMIOTRACE && m
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 5ff632ca3858..fb098b0b4505 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -64,6 +64,10 @@ struct ring_buffer_cpu_meta {
unsigned long commit_buffer;
__u32 subbuf_size;
__u32 nr_subbufs;
+#ifdef CONFIG_RING_BUFFER_PERSISTENT_INJECT
+ __u32 nr_invalid;
+ __u32 entry_bytes;
+#endif
int buffers[];
};
@@ -2079,6 +2083,21 @@ static void rb_meta_validate_events(struct ring_buffer_per_cpu *cpu_buffer)
if (discarded)
pr_cont(" (%d pages discarded)", discarded);
pr_cont("\n");
+
+#ifdef CONFIG_RING_BUFFER_PERSISTENT_INJECT
+ if (meta->nr_invalid)
+ pr_warn("Ring buffer testing [%d] invalid pages: %s (%d/%d)\n",
+ cpu_buffer->cpu,
+ (discarded == meta->nr_invalid) ? "PASSED" : "FAILED",
+ discarded, meta->nr_invalid);
+ if (meta->entry_bytes)
+ pr_warn("Ring buffer testing [%d] entry_bytes: %s (%ld/%ld)\n",
+ cpu_buffer->cpu,
+ (entry_bytes == meta->entry_bytes) ? "PASSED" : "FAILED",
+ (long)entry_bytes, (long)meta->entry_bytes);
+ meta->nr_invalid = 0;
+ meta->entry_bytes = 0;
+#endif
return;
invalid:
@@ -2559,12 +2578,67 @@ static void rb_free_cpu_buffer(struct ring_buffer_per_cpu *cpu_buffer)
kfree(cpu_buffer);
}
+#ifdef CONFIG_RING_BUFFER_PERSISTENT_INJECT
+static void rb_test_inject_invalid_pages(struct trace_buffer *buffer)
+{
+ struct ring_buffer_per_cpu *cpu_buffer;
+ struct ring_buffer_cpu_meta *meta;
+ struct buffer_data_page *dpage;
+ u32 entry_bytes = 0;
+ unsigned long ptr;
+ int subbuf_size;
+ int invalid = 0;
+ int cpu;
+ int i;
+
+ if (!(buffer->flags & RB_FL_TESTING))
+ return;
+
+ guard(preempt)();
+ cpu = smp_processor_id();
+
+ cpu_buffer = buffer->buffers[cpu];
+ meta = cpu_buffer->ring_meta;
+ ptr = (unsigned long)rb_subbufs_from_meta(meta);
+ subbuf_size = meta->subbuf_size;
+
+ for (i = 0; i < meta->nr_subbufs; i++) {
+ int idx = meta->buffers[i];
+
+ dpage = (void *)(ptr + idx * subbuf_size);
+ /* Skip unused pages */
+ if (!local_read(&dpage->commit))
+ continue;
+
+ /*
+ * Invalidate even pages or multiples of 5. This will lead 3
+ * contiguous invalidated(empty) pages.
+ */
+ if (!(i & 0x1) || !(i % 5)) {
+ local_add(subbuf_size + 1, &dpage->commit);
+ invalid++;
+ } else {
+ /* Count total commit bytes. */
+ entry_bytes += local_read(&dpage->commit);
+ }
+ }
+
+ pr_info("Inject invalidated %d pages on CPU%d, total size: %ld\n",
+ invalid, cpu, (long)entry_bytes);
+ meta->nr_invalid = invalid;
+ meta->entry_bytes = entry_bytes;
+}
+#else /* !CONFIG_RING_BUFFER_PERSISTENT_INJECT */
+#define rb_test_inject_invalid_pages(buffer) do { } while (0)
+#endif
+
/* Stop recording on a persistent buffer and flush cache if needed. */
static int rb_flush_buffer_cb(struct notifier_block *nb, unsigned long event, void *data)
{
struct trace_buffer *buffer = container_of(nb, struct trace_buffer, flush_nb);
ring_buffer_record_off(buffer);
+ rb_test_inject_invalid_pages(buffer);
arch_ring_buffer_flush_range(buffer->range_addr_start, buffer->range_addr_end);
return NOTIFY_DONE;
}
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 4189ec9df6a5..108b0d16badf 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -9366,6 +9366,8 @@ static void setup_trace_scratch(struct trace_array *tr,
memset(tscratch, 0, size);
}
+#define TRACE_TEST_PTRACING_NAME "ptracingtest"
+
static int
allocate_trace_buffer(struct trace_array *tr, struct array_buffer *buf, unsigned long size)
{
@@ -9378,6 +9380,8 @@ allocate_trace_buffer(struct trace_array *tr, struct array_buffer *buf, unsigned
buf->tr = tr;
if (tr->range_addr_start && tr->range_addr_size) {
+ if (!strcmp(tr->name, TRACE_TEST_PTRACING_NAME))
+ rb_flags |= RB_FL_TESTING;
/* Add scratch buffer to handle 128 modules */
buf->buffer = ring_buffer_alloc_range(size, rb_flags, 0,
tr->range_addr_start,
^ permalink raw reply related
* [PATCH v15 5/5] ring-buffer: Show commit numbers in buffer_meta file
From: Masami Hiramatsu (Google) @ 2026-03-31 8:36 UTC (permalink / raw)
To: Steven Rostedt, Catalin Marinas, Will Deacon
Cc: Masami Hiramatsu, Mathieu Desnoyers, linux-kernel,
linux-trace-kernel, Ian Rogers, linux-arm-kernel
In-Reply-To: <177494615421.71933.3679132057004156013.stgit@mhiramat.tok.corp.google.com>
From: Masami Hiramatsu (Google) <mhiramat@kernel.org>
In addition to the index number, show the commit numbers of
each data page in per_cpu buffer_meta file.
This is useful for understanding the current status of the
persistent ring buffer. (Note that this file is shown
only for persistent ring buffer and its backup instance)
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
---
kernel/trace/ring_buffer.c | 5 ++++-
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index fb098b0b4505..5b40fea6b15d 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -2209,6 +2209,7 @@ static int rbm_show(struct seq_file *m, void *v)
struct ring_buffer_per_cpu *cpu_buffer = m->private;
struct ring_buffer_cpu_meta *meta = cpu_buffer->ring_meta;
unsigned long val = (unsigned long)v;
+ struct buffer_data_page *dpage;
if (val == 1) {
seq_printf(m, "head_buffer: %d\n",
@@ -2221,7 +2222,9 @@ static int rbm_show(struct seq_file *m, void *v)
}
val -= 2;
- seq_printf(m, "buffer[%ld]: %d\n", val, meta->buffers[val]);
+ dpage = rb_range_buffer(cpu_buffer, val);
+ seq_printf(m, "buffer[%ld]: %d (commit: %ld)\n",
+ val, meta->buffers[val], local_read(&dpage->commit));
return 0;
}
^ permalink raw reply related
* Re: [PATCH] blktrace: reject buf_size smaller than blk_io_trace
From: Deepanshu Kartikey @ 2026-03-31 8:47 UTC (permalink / raw)
To: axboe, rostedt, mhiramat, mathieu.desnoyers
Cc: linux-block, linux-kernel, linux-trace-kernel,
syzbot+ed8bc247f231c1a48e21
In-Reply-To: <20260322051838.1137822-1-kartikey406@gmail.com>
On Sun, Mar 22, 2026 at 10:48 AM Deepanshu Kartikey
<kartikey406@gmail.com> wrote:
>
> blk_trace_setup() accepts any non-zero buf_size.
> If buf_size < sizeof(struct blk_io_trace), relay_reserve()
> always returns NULL and all trace events are silently dropped.
>
> Reject such values early with -EINVAL.
>
> Reported-by: syzbot+ed8bc247f231c1a48e21@syzkaller.appspotmail.com
> Closes: https://syzkaller.appspot.com/bug?extid=ed8bc247f231c1a48e21
> Signed-off-by: Deepanshu Kartikey <Kartikey406@gmail.com>
> ---
> kernel/trace/blktrace.c | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
> index 8cd2520b4c99..6cc7d83ed1c2 100644
> --- a/kernel/trace/blktrace.c
> +++ b/kernel/trace/blktrace.c
> @@ -773,7 +773,7 @@ int blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
> if (ret)
> return -EFAULT;
>
> - if (!buts.buf_size || !buts.buf_nr)
> + if (buts.buf_size < sizeof(struct blk_io_trace) || !buts.buf_nr)
> return -EINVAL;
>
> buts2 = (struct blk_user_trace_setup2) {
> --
> 2.43.0
>
Gentle ping on this patch . Let me know if anything else required
Thanks
^ permalink raw reply
* Re: [PATCH] tracing: always provide a prototype for tracing_alloc_snapshot()
From: Masami Hiramatsu @ 2026-03-31 9:20 UTC (permalink / raw)
To: Bartosz Golaszewski
Cc: Steven Rostedt, Mathieu Desnoyers, linux-kernel,
linux-trace-kernel
In-Reply-To: <20260331082001.31345-1-bartosz.golaszewski@oss.qualcomm.com>
On Tue, 31 Mar 2026 10:20:01 +0200
Bartosz Golaszewski <bartosz.golaszewski@oss.qualcomm.com> wrote:
> The tracing_alloc_snapshot() symbol is always exported even with
> !CONFIG_TRACER_SNAPSHOT so the prototype too must be always visible or
> we'll see the following warning:
>
> kernel/trace/trace.c:820:5: warning: no previous prototype for ‘tracing_alloc_snapshot’ [-Wmissing-prototypes]
> 820 | int tracing_alloc_snapshot(void)
> | ^~~~~~~~~~~~~~~~~~~~~~
>
> Fixes: bade44fe5462 ("tracing: Move snapshot code out of trace.c and into trace_snapshot.c")
> Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@oss.qualcomm.com>
Good catch!
Acked-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Thanks!
> ---
> kernel/trace/trace.h | 3 ++-
> 1 file changed, 2 insertions(+), 1 deletion(-)
>
> diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
> index 6abd9e16ef21..e8612b8b0a34 100644
> --- a/kernel/trace/trace.h
> +++ b/kernel/trace/trace.h
> @@ -2275,6 +2275,8 @@ static inline void __init trace_event_init(void) { }
> static inline void trace_event_update_all(struct trace_eval_map **map, int len) { }
> #endif
>
> +int tracing_alloc_snapshot(void);
> +
> #ifdef CONFIG_TRACER_SNAPSHOT
> extern const struct file_operations snapshot_fops;
> extern const struct file_operations snapshot_raw_fops;
> @@ -2282,7 +2284,6 @@ extern const struct file_operations snapshot_raw_fops;
> /* Used when creating instances */
> int trace_allocate_snapshot(struct trace_array *tr, int size);
>
> -int tracing_alloc_snapshot(void);
> void tracing_snapshot_cond(struct trace_array *tr, void *cond_data);
> int tracing_snapshot_cond_enable(struct trace_array *tr, void *cond_data, cond_update_fn_t update);
> int tracing_snapshot_cond_disable(struct trace_array *tr);
> --
> 2.47.3
>
--
Masami Hiramatsu (Google) <mhiramat@kernel.org>
^ permalink raw reply
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox