public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Steven Rostedt <rostedt@goodmis.org>
To: linux-kernel@vger.kernel.org
Cc: Masami Hiramatsu <mhiramat@kernel.org>,
	Mark Rutland <mark.rutland@arm.com>,
	Mathieu Desnoyers <mathieu.desnoyers@efficios.com>,
	Andrew Morton <akpm@linux-foundation.org>,
	Michael Jeanson <mjeanson@efficios.com>,
	Peter Zijlstra <peterz@infradead.org>,
	Alexei Starovoitov <ast@kernel.org>, Yonghong Song <yhs@fb.com>,
	"Paul E. McKenney" <paulmck@kernel.org>,
	Ingo Molnar <mingo@redhat.com>,
	Arnaldo Carvalho de Melo <acme@kernel.org>,
	Alexander Shishkin <alexander.shishkin@linux.intel.com>,
	Namhyung Kim <namhyung@kernel.org>,
	Andrii Nakryiko <andrii.nakryiko@gmail.com>,
	bpf@vger.kernel.org, Joel Fernandes <joel@joelfernandes.org>
Subject: [for-next][PATCH 02/10] tracing/ftrace: disable preemption in syscall probe
Date: Thu, 10 Oct 2024 10:25:39 -0400	[thread overview]
Message-ID: <20241010142549.865215981@goodmis.org> (raw)
In-Reply-To: 20241010142537.255433162@goodmis.org

From: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>

In preparation for allowing system call enter/exit instrumentation to
handle page faults, make sure that ftrace can handle this change by
explicitly disabling preemption within the ftrace system call tracepoint
probes to respect the current expectations within ftrace ring buffer
code.

This change does not yet allow ftrace to take page faults per se within
its probe, but allows its existing probes to adapt to the upcoming
change.

Cc: Michael Jeanson <mjeanson@efficios.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Yonghong Song <yhs@fb.com>
Cc: Paul E. McKenney <paulmck@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Andrii Nakryiko <andrii.nakryiko@gmail.com>
Cc: bpf@vger.kernel.org
Cc: Joel Fernandes <joel@joelfernandes.org>
Link: https://lore.kernel.org/20241009010718.2050182-3-mathieu.desnoyers@efficios.com
Acked-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 include/trace/trace_events.h  | 39 ++++++++++++++++++++++++++++-------
 kernel/trace/trace_syscalls.c | 12 +++++++++++
 2 files changed, 44 insertions(+), 7 deletions(-)

diff --git a/include/trace/trace_events.h b/include/trace/trace_events.h
index 8bcbb9ee44de..63071aa5923d 100644
--- a/include/trace/trace_events.h
+++ b/include/trace/trace_events.h
@@ -263,6 +263,9 @@ static struct trace_event_fields trace_event_fields_##call[] = {	\
 	tstruct								\
 	{} };
 
+#undef DECLARE_EVENT_SYSCALL_CLASS
+#define DECLARE_EVENT_SYSCALL_CLASS DECLARE_EVENT_CLASS
+
 #undef DEFINE_EVENT_PRINT
 #define DEFINE_EVENT_PRINT(template, name, proto, args, print)
 
@@ -396,11 +399,11 @@ static inline notrace int trace_event_get_offsets_##call(		\
 
 #include "stages/stage6_event_callback.h"
 
-#undef DECLARE_EVENT_CLASS
-#define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print)	\
-									\
+
+#undef __DECLARE_EVENT_CLASS
+#define __DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print) \
 static notrace void							\
-trace_event_raw_event_##call(void *__data, proto)			\
+do_trace_event_raw_event_##call(void *__data, proto)			\
 {									\
 	struct trace_event_file *trace_file = __data;			\
 	struct trace_event_data_offsets_##call __maybe_unused __data_offsets;\
@@ -425,15 +428,35 @@ trace_event_raw_event_##call(void *__data, proto)			\
 									\
 	trace_event_buffer_commit(&fbuffer);				\
 }
+
+#undef DECLARE_EVENT_CLASS
+#define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print)	\
+__DECLARE_EVENT_CLASS(call, PARAMS(proto), PARAMS(args), PARAMS(tstruct), \
+		      PARAMS(assign), PARAMS(print))			\
+static notrace void							\
+trace_event_raw_event_##call(void *__data, proto)			\
+{									\
+	do_trace_event_raw_event_##call(__data, args);			\
+}
+
+#undef DECLARE_EVENT_SYSCALL_CLASS
+#define DECLARE_EVENT_SYSCALL_CLASS(call, proto, args, tstruct, assign, print) \
+__DECLARE_EVENT_CLASS(call, PARAMS(proto), PARAMS(args), PARAMS(tstruct), \
+		      PARAMS(assign), PARAMS(print))			\
+static notrace void							\
+trace_event_raw_event_##call(void *__data, proto)			\
+{									\
+	preempt_disable_notrace();					\
+	do_trace_event_raw_event_##call(__data, args);			\
+	preempt_enable_notrace();					\
+}
+
 /*
  * The ftrace_test_probe is compiled out, it is only here as a build time check
  * to make sure that if the tracepoint handling changes, the ftrace probe will
  * fail to compile unless it too is updated.
  */
 
-#undef DECLARE_EVENT_SYSCALL_CLASS
-#define DECLARE_EVENT_SYSCALL_CLASS DECLARE_EVENT_CLASS
-
 #undef DEFINE_EVENT
 #define DEFINE_EVENT(template, call, proto, args)			\
 static inline void ftrace_test_probe_##call(void)			\
@@ -443,6 +466,8 @@ static inline void ftrace_test_probe_##call(void)			\
 
 #include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
 
+#undef __DECLARE_EVENT_CLASS
+
 #include "stages/stage7_class_define.h"
 
 #undef DECLARE_EVENT_CLASS
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index 785733245ead..f9b21bac9d45 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -299,6 +299,12 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id)
 	int syscall_nr;
 	int size;
 
+	/*
+	 * Syscall probe called with preemption enabled, but the ring
+	 * buffer and per-cpu data require preemption to be disabled.
+	 */
+	guard(preempt_notrace)();
+
 	syscall_nr = trace_get_syscall_nr(current, regs);
 	if (syscall_nr < 0 || syscall_nr >= NR_syscalls)
 		return;
@@ -338,6 +344,12 @@ static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret)
 	struct trace_event_buffer fbuffer;
 	int syscall_nr;
 
+	/*
+	 * Syscall probe called with preemption enabled, but the ring
+	 * buffer and per-cpu data require preemption to be disabled.
+	 */
+	guard(preempt_notrace)();
+
 	syscall_nr = trace_get_syscall_nr(current, regs);
 	if (syscall_nr < 0 || syscall_nr >= NR_syscalls)
 		return;
-- 
2.45.2



  parent reply	other threads:[~2024-10-10 14:25 UTC|newest]

Thread overview: 11+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-10-10 14:25 [for-next][PATCH 00/10] tracing: Updates for 6.13 Steven Rostedt
2024-10-10 14:25 ` [for-next][PATCH 01/10] tracing: Declare system call tracepoints with TRACE_EVENT_SYSCALL Steven Rostedt
2024-10-10 14:25 ` Steven Rostedt [this message]
2024-10-10 14:25 ` [for-next][PATCH 03/10] tracing/perf: disable preemption in syscall probe Steven Rostedt
2024-10-10 14:25 ` [for-next][PATCH 04/10] tracing/bpf: " Steven Rostedt
2024-10-10 14:25 ` [for-next][PATCH 05/10] tracing: Allow system call tracepoints to handle page faults Steven Rostedt
2024-10-10 14:25 ` [for-next][PATCH 06/10] tracing/ftrace: Add might_fault check to syscall probes Steven Rostedt
2024-10-10 14:25 ` [for-next][PATCH 07/10] tracing/perf: " Steven Rostedt
2024-10-10 14:25 ` [for-next][PATCH 08/10] tracing/bpf: " Steven Rostedt
2024-10-10 14:25 ` [for-next][PATCH 09/10] trace/trace_event_perf: remove duplicate samples on the first tracepoint event Steven Rostedt
2024-10-10 14:25 ` [for-next][PATCH 10/10] tracing: Use atomic64_inc_return() in trace_clock_counter() 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=20241010142549.865215981@goodmis.org \
    --to=rostedt@goodmis.org \
    --cc=acme@kernel.org \
    --cc=akpm@linux-foundation.org \
    --cc=alexander.shishkin@linux.intel.com \
    --cc=andrii.nakryiko@gmail.com \
    --cc=ast@kernel.org \
    --cc=bpf@vger.kernel.org \
    --cc=joel@joelfernandes.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mark.rutland@arm.com \
    --cc=mathieu.desnoyers@efficios.com \
    --cc=mhiramat@kernel.org \
    --cc=mingo@redhat.com \
    --cc=mjeanson@efficios.com \
    --cc=namhyung@kernel.org \
    --cc=paulmck@kernel.org \
    --cc=peterz@infradead.org \
    --cc=yhs@fb.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