From nobody Mon Feb 9 00:03:14 2026 Received: from smtp.kernel.org (aws-us-west-2-korg-mail-1.web.codeaurora.org [10.30.226.201]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 3E3CA19CC31 for ; Wed, 8 Jan 2025 03:35:33 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=10.30.226.201 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1736307334; cv=none; b=fZmWxoSeM8+ekWNKs0UtKGLKW7xBMElHB5RDeDo8LUkFKvML3T/XyVI3+d9qc+h6zPv1QNINE5zK2wjil157fHy1eTqSjBA052RScveDy/ZYMZS+worsriSIujSxTr8d7CluVgqcoI4Z0kC+YEdntFLvuJHKUcWVIpSq3Q/hTJ0= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1736307334; c=relaxed/simple; bh=51eBQ3gSyp1J4JPo7RTnRw31KgT6LtgtC5UuDUXBAM8=; h=Message-ID:Date:From:To:Cc:Subject:References:MIME-Version: Content-Type; b=dps3GCSh5fkTEwBzEBewnw7om4K0wnL4djfZimsZYw3qjD2I/EOeiDQA4++3MAFDdneV1aGeBjsRZyF9qKKVy1YmFyxp9jUDBjdauTZOdy60P7Turq4h+3bEeyNfqWjvSPVHr0B7P1waSx3QfkXsDwzkmBCSzVtSdVMCUMch3kk= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; arc=none smtp.client-ip=10.30.226.201 Received: by smtp.kernel.org (Postfix) with ESMTPSA id 92498C4CEE4; Wed, 8 Jan 2025 03:35:33 +0000 (UTC) Received: from rostedt by gandalf with local (Exim 4.98) (envelope-from ) id 1tVMsR-0000000ApB7-3WIQ; Tue, 07 Jan 2025 22:37:03 -0500 Message-ID: <20250108033703.690400772@goodmis.org> User-Agent: quilt/0.68 Date: Tue, 07 Jan 2025 22:36:49 -0500 From: Steven Rostedt To: linux-kernel@vger.kernel.org Cc: Masami Hiramatsu , Mark Rutland , Mathieu Desnoyers , Andrew Morton , Shuah Khan , Tom Zanussi Subject: [for-next][PATCH 2/4] tracing/hist: Add poll(POLLIN) support on hist file References: <20250108033647.656576164@goodmis.org> Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset="utf-8" From: "Masami Hiramatsu (Google)" Add poll syscall support on the `hist` file. The Waiter will be waken up when the histogram is updated with POLLIN. Currently, there is no way to wait for a specific event in userspace. So user needs to peek the `trace` periodicaly, or wait on `trace_pipe`. But it is not a good idea to peek at the `trace` for an event that randomly happens. And `trace_pipe` is not coming back until a page is filled with events. This allows a user to wait for a specific event on the `hist` file. User can set a histogram trigger on the event which they want to monitor and poll() on its `hist` file. Since this poll() returns POLLIN, the next poll() will return soon unless a read() happens on that hist file. NOTE: To read the hist file again, you must set the file offset to 0, but just for monitoring the event, you may not need to read the histogram. Cc: Shuah Khan Cc: Mathieu Desnoyers Link: https://lore.kernel.org/173527247756.464571.14236296701625509931.stgi= t@devnote2 Signed-off-by: Masami Hiramatsu (Google) Reviewed-by: Tom Zanussi Signed-off-by: Steven Rostedt (Google) --- include/linux/trace_events.h | 14 +++++++ kernel/trace/trace_events.c | 14 +++++++ kernel/trace/trace_events_hist.c | 70 ++++++++++++++++++++++++++++++-- 3 files changed, 95 insertions(+), 3 deletions(-) diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 91b8ffbdfa8c..02cde1174487 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -673,6 +673,20 @@ struct trace_event_file { atomic_t tm_ref; /* trigger-mode reference counter */ }; =20 +#ifdef CONFIG_HIST_TRIGGERS +extern struct irq_work hist_poll_work; +extern wait_queue_head_t hist_poll_wq; + +static inline void hist_poll_wakeup(void) +{ + if (wq_has_sleeper(&hist_poll_wq)) + irq_work_queue(&hist_poll_work); +} + +#define hist_poll_wait(file, wait) \ + poll_wait(file, &hist_poll_wq, wait) +#endif + #define __TRACE_EVENT_FLAGS(name, value) \ static int __init trace_init_flags_##name(void) \ { \ diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 047d2775184b..2b9222e7bd5a 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -3094,6 +3094,20 @@ static bool event_in_systems(struct trace_event_call= *call, return !*p || isspace(*p) || *p =3D=3D ','; } =20 +#ifdef CONFIG_HIST_TRIGGERS +/* + * Wake up waiter on the hist_poll_wq from irq_work because the hist trigg= er + * may happen in any context. + */ +static void hist_poll_event_irq_work(struct irq_work *work) +{ + wake_up_all(&hist_poll_wq); +} + +DEFINE_IRQ_WORK(hist_poll_work, hist_poll_event_irq_work); +DECLARE_WAIT_QUEUE_HEAD(hist_poll_wq); +#endif + static struct trace_event_file * trace_create_new_event(struct trace_event_call *call, struct trace_array *tr) diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_h= ist.c index 879b58892b9d..af4be28f01e0 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -5311,6 +5311,8 @@ static void event_hist_trigger(struct event_trigger_d= ata *data, =20 if (resolve_var_refs(hist_data, key, var_ref_vals, true)) hist_trigger_actions(hist_data, elt, buffer, rec, rbe, key, var_ref_vals= ); + + hist_poll_wakeup(); } =20 static void hist_trigger_stacktrace_print(struct seq_file *m, @@ -5590,15 +5592,36 @@ static void hist_trigger_show(struct seq_file *m, n_entries, (u64)atomic64_read(&hist_data->map->drops)); } =20 +struct hist_file_data { + struct file *file; + u64 last_read; +}; + +static u64 get_hist_hit_count(struct trace_event_file *event_file) +{ + struct hist_trigger_data *hist_data; + struct event_trigger_data *data; + u64 ret =3D 0; + + list_for_each_entry(data, &event_file->triggers, list) { + if (data->cmd_ops->trigger_type =3D=3D ETT_EVENT_HIST) { + hist_data =3D data->private_data; + ret +=3D atomic64_read(&hist_data->map->hits); + } + } + return ret; +} + static int hist_show(struct seq_file *m, void *v) { + struct hist_file_data *hist_file =3D m->private; struct event_trigger_data *data; struct trace_event_file *event_file; int n =3D 0; =20 guard(mutex)(&event_mutex); =20 - event_file =3D event_file_file(m->private); + event_file =3D event_file_file(hist_file->file); if (unlikely(!event_file)) return -ENODEV; =20 @@ -5606,27 +5629,68 @@ static int hist_show(struct seq_file *m, void *v) if (data->cmd_ops->trigger_type =3D=3D ETT_EVENT_HIST) hist_trigger_show(m, data, n++); } + hist_file->last_read =3D get_hist_hit_count(event_file); + return 0; } =20 +static __poll_t event_hist_poll(struct file *file, struct poll_table_struc= t *wait) +{ + struct trace_event_file *event_file; + struct seq_file *m =3D file->private_data; + struct hist_file_data *hist_file =3D m->private; + + guard(mutex)(&event_mutex); + + event_file =3D event_file_data(file); + if (!event_file) + return EPOLLERR; + + hist_poll_wait(file, wait); + + if (hist_file->last_read !=3D get_hist_hit_count(event_file)) + return EPOLLIN | EPOLLRDNORM; + + return 0; +} + +static int event_hist_release(struct inode *inode, struct file *file) +{ + struct seq_file *m =3D file->private_data; + struct hist_file_data *hist_file =3D m->private; + + kfree(hist_file); + return tracing_single_release_file_tr(inode, file); +} + static int event_hist_open(struct inode *inode, struct file *file) { + struct hist_file_data *hist_file; int ret; =20 ret =3D tracing_open_file_tr(inode, file); if (ret) return ret; =20 + hist_file =3D kzalloc(sizeof(*hist_file), GFP_KERNEL); + if (!hist_file) + return -ENOMEM; + hist_file->file =3D file; + /* Clear private_data to avoid warning in single_open() */ file->private_data =3D NULL; - return single_open(file, hist_show, file); + ret =3D single_open(file, hist_show, hist_file); + if (ret) + kfree(hist_file); + return ret; } =20 const struct file_operations event_hist_fops =3D { .open =3D event_hist_open, .read =3D seq_read, .llseek =3D seq_lseek, - .release =3D tracing_single_release_file_tr, + .release =3D event_hist_release, + .poll =3D event_hist_poll, }; =20 #ifdef CONFIG_HIST_TRIGGERS_DEBUG --=20 2.45.2