From: Steven Rostedt <rostedt@goodmis.org>
To: linux-kernel@vger.kernel.org
Cc: Ingo Molnar <mingo@kernel.org>,
Andrew Morton <akpm@linux-foundation.org>,
Peter Zijlstra <peterz@infradead.org>,
Josh Poimboeuf <jpoimboe@redhat.com>,
Jiri Kosina <jikos@kernel.org>, Miroslav Benes <mbenes@suse.cz>,
Petr Mladek <pmladek@suse.com>,
Masami Hiramatsu <mhiramat@kernel.org>,
Jiri Olsa <jolsa@redhat.com>
Subject: [for-next][PATCH 09/17] perf/ftrace: Check for rcu_is_watching() in callback function
Date: Wed, 11 Nov 2020 19:32:53 -0500 [thread overview]
Message-ID: <20201112003334.462728155@goodmis.org> (raw)
In-Reply-To: 20201112003244.764326960@goodmis.org
From: "Steven Rostedt (VMware)" <rostedt@goodmis.org>
If a ftrace callback requires "rcu_is_watching", then it adds the
FTRACE_OPS_FL_RCU flag and it will not be called if RCU is not "watching".
But this means that it will use a trampoline when called, and this slows
down the function tracing a tad. By checking rcu_is_watching() from within
the callback, it no longer needs the RCU flag set in the ftrace_ops and it
can be safely called directly.
Link: https://lkml.kernel.org/r/20201028115613.591878956@goodmis.org
Link: https://lkml.kernel.org/r/20201106023547.711035826@goodmis.org
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Jiri Kosina <jikos@kernel.org>
Cc: Miroslav Benes <mbenes@suse.cz>
Cc: Petr Mladek <pmladek@suse.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
kernel/trace/trace_event_perf.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index fd58d83861d8..a2b9fddb8148 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -441,6 +441,9 @@ perf_ftrace_function_call(unsigned long ip, unsigned long parent_ip,
int rctx;
int bit;
+ if (!rcu_is_watching())
+ return;
+
if ((unsigned long)ops->private != smp_processor_id())
return;
@@ -484,7 +487,6 @@ static int perf_ftrace_function_register(struct perf_event *event)
{
struct ftrace_ops *ops = &event->ftrace_ops;
- ops->flags = FTRACE_OPS_FL_RCU;
ops->func = perf_ftrace_function_call;
ops->private = (void *)(unsigned long)nr_cpu_ids;
--
2.28.0
next prev parent reply other threads:[~2020-11-12 1:38 UTC|newest]
Thread overview: 20+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-11-12 0:32 [for-next][PATCH 00/17] tracing: Updates for 5.11 Steven Rostedt
2020-11-12 0:32 ` [for-next][PATCH 01/17] ftrace: Move the recursion testing into global headers Steven Rostedt
2020-11-12 0:32 ` [for-next][PATCH 02/17] ftrace: Add ftrace_test_recursion_trylock() helper function Steven Rostedt
2020-11-12 0:32 ` [for-next][PATCH 03/17] ftrace: Optimize testing what context current is in Steven Rostedt
2020-11-12 0:32 ` [for-next][PATCH 04/17] pstore/ftrace: Add recursion protection to the ftrace callback Steven Rostedt
2020-11-12 0:32 ` [for-next][PATCH 05/17] kprobes/ftrace: " Steven Rostedt
2020-11-12 0:32 ` [for-next][PATCH 06/17] livepatch/ftrace: " Steven Rostedt
2020-11-12 0:32 ` [for-next][PATCH 07/17] livepatch: Trigger WARNING if livepatch function fails due to recursion Steven Rostedt
2020-11-12 0:32 ` [for-next][PATCH 08/17] perf/ftrace: Add recursion protection to the ftrace callback Steven Rostedt
2020-11-12 0:32 ` Steven Rostedt [this message]
2020-11-12 0:32 ` [for-next][PATCH 10/17] ftrace: Reverse what the RECURSION flag means in the ftrace_ops Steven Rostedt
2020-11-12 0:32 ` [for-next][PATCH 11/17] ftrace: Add recording of functions that caused recursion Steven Rostedt
2020-11-12 0:32 ` [for-next][PATCH 12/17] fgraph: Make overruns 4 bytes in graph stack structure Steven Rostedt
2020-11-12 9:18 ` David Laight
2020-11-12 14:39 ` Steven Rostedt
2020-11-12 0:32 ` [for-next][PATCH 13/17] ftrace: Clean up the recursion code a bit Steven Rostedt
2020-11-12 0:32 ` [for-next][PATCH 14/17] ring-buffer: Add recording of ring buffer recursion into recursed_functions Steven Rostedt
2020-11-12 0:32 ` [for-next][PATCH 15/17] ftrace: Remove unused varible ret Steven Rostedt
2020-11-12 0:33 ` [for-next][PATCH 16/17] tracing: Fix some typos in comments Steven Rostedt
2020-11-12 0:33 ` [for-next][PATCH 17/17] MAINTAINERS: assign ./fs/tracefs to TRACING Steven Rostedt
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=20201112003334.462728155@goodmis.org \
--to=rostedt@goodmis.org \
--cc=akpm@linux-foundation.org \
--cc=jikos@kernel.org \
--cc=jolsa@redhat.com \
--cc=jpoimboe@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mbenes@suse.cz \
--cc=mhiramat@kernel.org \
--cc=mingo@kernel.org \
--cc=peterz@infradead.org \
--cc=pmladek@suse.com \
/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;
as well as URLs for NNTP newsgroup(s).