All of lore.kernel.org
 help / color / mirror / Atom feed
From: "Masami Hiramatsu (Google)" <mhiramat@kernel.org>
To: Steven Rostedt <rostedt@goodmis.org>, Shuah Khan <shuah@kernel.org>
Cc: Masami Hiramatsu <mhiramat@kernel.org>,
	Tom Zanussi <zanussi@kernel.org>,
	Mathieu Desnoyers <mathieu.desnoyers@efficios.com>,
	linux-kernel@vger.kernel.org, linux-trace-kernel@vger.kernel.org,
	linux-kselftest@vger.kernel.org
Subject: [PATCH v7 1/3] tracing/hist: Add poll(POLLIN) support on hist file
Date: Fri, 27 Dec 2024 13:07:57 +0900	[thread overview]
Message-ID: <173527247756.464571.14236296701625509931.stgit@devnote2> (raw)
In-Reply-To: <173527246726.464571.11533527581374142406.stgit@devnote2>

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

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.

Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Reviewed-by: Tom Zanussi <zanussi@kernel.org>
---
 Changes in v7:
   - Reword description according to Steve's comment.
   - Use guard() for mutex.
---
 include/linux/trace_events.h     |   14 ++++++++
 kernel/trace/trace_events.c      |   14 ++++++++
 kernel/trace/trace_events_hist.c |   69 ++++++++++++++++++++++++++++++++++++--
 3 files changed, 94 insertions(+), 3 deletions(-)

diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h
index 2a5df5b62cfc..47caca4e7ff4 100644
--- a/include/linux/trace_events.h
+++ b/include/linux/trace_events.h
@@ -669,6 +669,20 @@ struct trace_event_file {
 	atomic_t		tm_ref;	/* trigger-mode reference counter */
 };
 
+#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 77e68efbd43e..e34b4a88d8ec 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -2972,6 +2972,20 @@ static bool event_in_systems(struct trace_event_call *call,
 	return !*p || isspace(*p) || *p == ',';
 }
 
+#ifdef CONFIG_HIST_TRIGGERS
+/*
+ * Wake up waiter on the hist_poll_wq from irq_work because the hist trigger
+ * 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_hist.c
index 9c058aa8baf3..e169f67c6088 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_data *data,
 
 	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();
 }
 
 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));
 }
 
+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 = 0;
+
+	list_for_each_entry(data, &event_file->triggers, list) {
+		if (data->cmd_ops->trigger_type == ETT_EVENT_HIST) {
+			hist_data = data->private_data;
+			ret += atomic64_read(&hist_data->map->hits);
+		}
+	}
+	return ret;
+}
+
 static int hist_show(struct seq_file *m, void *v)
 {
+	struct hist_file_data *hist_file = m->private;
 	struct event_trigger_data *data;
 	struct trace_event_file *event_file;
 	int n = 0, ret = 0;
 
 	mutex_lock(&event_mutex);
 
-	event_file = event_file_file(m->private);
+	event_file = event_file_file(hist_file->file);
 	if (unlikely(!event_file)) {
 		ret = -ENODEV;
 		goto out_unlock;
@@ -5608,6 +5631,7 @@ static int hist_show(struct seq_file *m, void *v)
 		if (data->cmd_ops->trigger_type == ETT_EVENT_HIST)
 			hist_trigger_show(m, data, n++);
 	}
+	hist_file->last_read = get_hist_hit_count(event_file);
 
  out_unlock:
 	mutex_unlock(&event_mutex);
@@ -5615,24 +5639,63 @@ static int hist_show(struct seq_file *m, void *v)
 	return ret;
 }
 
+static __poll_t event_hist_poll(struct file *file, struct poll_table_struct *wait)
+{
+	struct trace_event_file *event_file;
+	struct seq_file *m = file->private_data;
+	struct hist_file_data *hist_file = m->private;
+
+	guard(mutex)(&event_mutex);
+
+	event_file = event_file_data(file);
+	if (!event_file)
+		return EPOLLERR;
+
+	hist_poll_wait(file, wait);
+
+	if (hist_file->last_read != 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 = file->private_data;
+	struct hist_file_data *hist_file = 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;
 
 	ret = tracing_open_file_tr(inode, file);
 	if (ret)
 		return ret;
 
+	hist_file = kzalloc(sizeof(*hist_file), GFP_KERNEL);
+	if (!hist_file)
+		return -ENOMEM;
+	hist_file->file = file;
+
 	/* Clear private_data to avoid warning in single_open() */
 	file->private_data = NULL;
-	return single_open(file, hist_show, file);
+	ret = single_open(file, hist_show, hist_file);
+	if (ret)
+		kfree(hist_file);
+	return ret;
 }
 
 const struct file_operations event_hist_fops = {
 	.open = event_hist_open,
 	.read = seq_read,
 	.llseek = seq_lseek,
-	.release = tracing_single_release_file_tr,
+	.release = event_hist_release,
+	.poll = event_hist_poll,
 };
 
 #ifdef CONFIG_HIST_TRIGGERS_DEBUG


  reply	other threads:[~2024-12-27  4:08 UTC|newest]

Thread overview: 6+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-12-27  4:07 [PATCH v7 0/3] tracing: Support poll on event hist file Masami Hiramatsu (Google)
2024-12-27  4:07 ` Masami Hiramatsu (Google) [this message]
2024-12-27  4:08 ` [PATCH v7 2/3] tracing/hist: Support POLLPRI event for poll on histogram Masami Hiramatsu (Google)
2024-12-27  4:08 ` [PATCH v7 3/3] selftests/tracing: Add hist poll() support test Masami Hiramatsu (Google)
2024-12-29 13:08   ` Masami Hiramatsu
2024-12-29 13:24   ` [PATCH v7.1 " Masami Hiramatsu (Google)

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=173527247756.464571.14236296701625509931.stgit@devnote2 \
    --to=mhiramat@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-kselftest@vger.kernel.org \
    --cc=linux-trace-kernel@vger.kernel.org \
    --cc=mathieu.desnoyers@efficios.com \
    --cc=rostedt@goodmis.org \
    --cc=shuah@kernel.org \
    --cc=zanussi@kernel.org \
    /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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.