From: Usama Arif <usama.arif@linux.dev>
To: Peter Zijlstra <peterz@infradead.org>
Cc: mingo@redhat.com, acme@kernel.org, namhyung@kernel.org,
mark.rutland@arm.com, alexander.shishkin@linux.intel.com,
jolsa@kernel.org, irogers@google.com, adrian.hunter@intel.com,
james.clark@linaro.org, linux-perf-users@vger.kernel.org,
linux-kernel@vger.kernel.org, bpf@vger.kernel.org,
rkeilty@meta.com, atish.patra@linux.dev, dgreid@meta.com,
riel@surriel.com, shakeel.butt@linux.dev, kernel-team@meta.com
Subject: Re: [PATCH 3/3] perf/core: Don't zero perf_sample_data in do_perf_sw_event()
Date: Fri, 20 Nov 2026 20:02:37 +0000 [thread overview]
Message-ID: <e0a15bd8-c37e-4736-913e-e926bdbd12e5@linux.dev> (raw)
In-Reply-To: <20261120091150.GN2668564@noisy.programming.kicks-ass.net>
On 20/11/2026 01:11, Peter Zijlstra wrote:
> On Thu, Nov 19, 2026 at 01:10:46PM -0800, Usama Arif wrote:
>
>> kernel/events/core.c | 2 +-
>> 1 file changed, 1 insertion(+), 1 deletion(-)
>>
>> diff --git a/kernel/events/core.c b/kernel/events/core.c
>> index 57ea7e3c01a025..fa10ad7cfd99af 100644
>> --- a/kernel/events/core.c
>> +++ b/kernel/events/core.c
>> @@ -11212,7 +11212,7 @@ static void do_perf_sw_event(enum perf_type_id type, u32 event_id,
>> u64 nr, struct pt_regs *regs, u64 addr)
>> {
>> struct swevent_htable *swhash = this_cpu_ptr(&swevent_htable);
>> - struct perf_sample_data data;
>> + struct perf_sample_data data __uninitialized;
>> struct perf_event *event;
>> struct hlist_head *head;
>>
>
> I like this one, didn't know about the __uninitialized thing. But I
> think we wants to be more consistent with this.
>
> A little git-grep seems to suggest we ought to do the same elsewhere.
> Shall I fold the little something below in this patch?
>
Thanks! I went through the below. perf_tp_event(), perf_bp_event()
and perf_swevent_hrtimer() call perf_sample_data_init() for each event,
like do_perf_sw_event() does. The side-band emitters only use the
sample ID fields, which perf_event_header__init() writes and
perf_event__output_id_sample() reads under the same sample_id_all
check. So they are all fine to do.
But they do need the fix in patch 2 to work.
There is another fix that I found looking at your next reply.
Would you like me to send all the fixes and you can then send
the below patch (and the next one?)
>
> --- a/kernel/events/core.c
> +++ b/kernel/events/core.c
> @@ -9123,7 +9123,7 @@ perf_event_read_event(struct perf_event
> struct task_struct *task)
> {
> struct perf_output_handle handle;
> - struct perf_sample_data sample;
> + struct perf_sample_data sample __uninitialized;
> struct perf_read_event read_event = {
> .pid = perf_event_pid(event, task),
> .tid = perf_event_tid(event, task),
> @@ -9390,7 +9390,7 @@ static void perf_event_task_output(struc
> {
> struct perf_task_event *task_event = data;
> struct perf_output_handle handle;
> - struct perf_sample_data sample;
> + struct perf_sample_data sample __uninitialized;
> struct task_struct *task = task_event->task;
> int ret;
>
> @@ -9534,7 +9534,7 @@ static void perf_event_comm_output(struc
> {
> struct perf_comm_event *comm_event = data;
> struct perf_output_handle handle;
> - struct perf_sample_data sample;
> + struct perf_sample_data sample __uninitialized;
> int ret;
>
> if (!perf_event_comm_match(event))
> @@ -9625,7 +9625,7 @@ static void perf_event_namespaces_output
> {
> struct perf_namespaces_event *namespaces_event = data;
> struct perf_output_handle handle;
> - struct perf_sample_data sample;
> + struct perf_sample_data sample __uninitialized;
> int ret;
>
> if (!perf_event_namespaces_match(event))
> @@ -9748,7 +9748,7 @@ static void perf_event_cgroup_output(str
> {
> struct perf_cgroup_event *cgroup_event = data;
> struct perf_output_handle handle;
> - struct perf_sample_data sample;
> + struct perf_sample_data sample __uninitialized;
> int ret;
> u16 size = sizeof(cgroup_event->event_id) + cgroup_event->path_size;
>
> @@ -9859,7 +9859,7 @@ static void perf_event_mmap_output(struc
> {
> struct perf_mmap_event *mmap_event = data;
> struct perf_output_handle handle;
> - struct perf_sample_data sample;
> + struct perf_sample_data sample __uninitialized;
> int size = sizeof(mmap_event->event_id) + mmap_event->file_size;
> u32 type = PERF_RECORD_MMAP;
> u16 misc = PERF_RECORD_MISC_USER;
> @@ -10155,7 +10155,7 @@ void perf_event_aux_event(struct perf_ev
> unsigned long size, u64 flags)
> {
> struct perf_output_handle handle;
> - struct perf_sample_data sample;
> + struct perf_sample_data sample __uninitialized;
> struct perf_aux_event {
> struct perf_event_header header;
> u64 offset;
> @@ -10188,7 +10188,7 @@ void perf_event_aux_event(struct perf_ev
> void perf_log_lost_samples(struct perf_event *event, u64 lost)
> {
> struct perf_output_handle handle;
> - struct perf_sample_data sample;
> + struct perf_sample_data sample __uninitialized;
> int ret;
>
> struct {
> @@ -10240,7 +10240,7 @@ static void perf_event_switch_output(str
> {
> struct perf_switch_event *se = data;
> struct perf_output_handle handle;
> - struct perf_sample_data sample;
> + struct perf_sample_data sample __uninitialized;
> u32 type;
> u16 misc;
> u16 size;
> @@ -10307,7 +10307,7 @@ static void perf_event_switch(struct tas
> static void perf_log_throttle(struct perf_event *event, int enable)
> {
> struct perf_output_handle handle;
> - struct perf_sample_data sample;
> + struct perf_sample_data sample __uninitialized;
> int ret;
>
> struct {
> @@ -10363,7 +10363,7 @@ static void perf_event_ksymbol_output(st
> {
> struct perf_ksymbol_event *ksymbol_event = data;
> struct perf_output_handle handle;
> - struct perf_sample_data sample;
> + struct perf_sample_data sample __uninitialized;
> int ret;
> u16 size = sizeof(ksymbol_event->event_id) + ksymbol_event->name_len;
>
> @@ -10450,7 +10450,7 @@ static void perf_event_bpf_output(struct
> {
> struct perf_bpf_event *bpf_event = data;
> struct perf_output_handle handle;
> - struct perf_sample_data sample;
> + struct perf_sample_data sample __uninitialized;
> int ret;
>
> if (!perf_event_bpf_match(event))
> @@ -10540,7 +10540,7 @@ static void perf_callchain_deferred_outp
> {
> struct perf_callchain_deferred_event *deferred_event = data;
> struct perf_output_handle handle;
> - struct perf_sample_data sample;
> + struct perf_sample_data sample __uninitialized;
> u64 nr = deferred_event->trace->nr;
> u16 size, id_size, max_payload;
> int ret;
> @@ -10615,7 +10615,7 @@ static void perf_event_text_poke_output(
> {
> struct perf_text_poke_event *text_poke_event = data;
> struct perf_output_handle handle;
> - struct perf_sample_data sample;
> + struct perf_sample_data sample __uninitialized;
> u16 size = sizeof(text_poke_event->event_id) + text_poke_event->tot + text_poke_event->pad;
> u64 padding = 0;
> int ret;
> @@ -10686,7 +10686,7 @@ EXPORT_SYMBOL_GPL(perf_event_itrace_star
> static void perf_log_itrace_start(struct perf_event *event)
> {
> struct perf_output_handle handle;
> - struct perf_sample_data sample;
> + struct perf_sample_data sample __uninitialized;
> struct perf_aux_event {
> struct perf_event_header header;
> u32 pid;
> @@ -10721,7 +10721,7 @@ static void perf_log_itrace_start(struct
> void perf_report_aux_output_id(struct perf_event *event, u64 hw_id)
> {
> struct perf_output_handle handle;
> - struct perf_sample_data sample;
> + struct perf_sample_data sample __uninitialized;
> struct perf_aux_event {
> struct perf_event_header header;
> u64 hw_id;
> @@ -11603,7 +11603,7 @@ void perf_tp_event(u16 event_type, u64 c
> struct pt_regs *regs, struct hlist_head *head, int rctx,
> struct task_struct *task)
> {
> - struct perf_sample_data data;
> + struct perf_sample_data data __uninitialized;
> struct perf_event *event;
>
> /*
> @@ -11949,7 +11949,7 @@ void perf_event_free_bpf_prog(struct per
> #ifdef CONFIG_HAVE_HW_BREAKPOINT
> void perf_bp_event(struct perf_event *bp, void *data)
> {
> - struct perf_sample_data sample;
> + struct perf_sample_data sample __uninitialized;
> struct pt_regs *regs = data;
>
> /*
> @@ -12403,7 +12403,7 @@ static int perf_event_set_filter(struct
> static enum hrtimer_restart perf_swevent_hrtimer(struct hrtimer *hrtimer)
> {
> enum hrtimer_restart ret = HRTIMER_RESTART;
> - struct perf_sample_data data;
> + struct perf_sample_data data __uninitialized;
> struct pt_regs *regs;
> struct perf_event *event;
> u64 period;
prev parent reply other threads:[~2026-11-20 20:02 UTC|newest]
Thread overview: 8+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-11-19 21:10 [PATCH 0/3] perf/core: Fix software event sample data, then stop zeroing it Usama Arif
2026-11-19 21:10 ` [PATCH 1/3] perf/core: Fix perf_sample_data reuse across software events Usama Arif
2026-11-19 21:10 ` [PATCH 2/3] perf/core: Don't let BPF programs read an uninitialized sample address Usama Arif
2026-11-19 21:10 ` [PATCH 3/3] perf/core: Don't zero perf_sample_data in do_perf_sw_event() Usama Arif
2026-11-20 9:11 ` Peter Zijlstra
2026-11-20 9:12 ` Peter Zijlstra
2026-11-20 20:05 ` Usama Arif
2026-11-20 20:02 ` Usama Arif [this message]
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=e0a15bd8-c37e-4736-913e-e926bdbd12e5@linux.dev \
--to=usama.arif@linux.dev \
--cc=acme@kernel.org \
--cc=adrian.hunter@intel.com \
--cc=alexander.shishkin@linux.intel.com \
--cc=atish.patra@linux.dev \
--cc=bpf@vger.kernel.org \
--cc=dgreid@meta.com \
--cc=irogers@google.com \
--cc=james.clark@linaro.org \
--cc=jolsa@kernel.org \
--cc=kernel-team@meta.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-perf-users@vger.kernel.org \
--cc=mark.rutland@arm.com \
--cc=mingo@redhat.com \
--cc=namhyung@kernel.org \
--cc=peterz@infradead.org \
--cc=riel@surriel.com \
--cc=rkeilty@meta.com \
--cc=shakeel.butt@linux.dev \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox