From: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
To: Steven Rostedt <rostedt@goodmis.org>,
Masami Hiramatsu <mhiramat@kernel.org>
Cc: linux-kernel@vger.kernel.org,
Mathieu Desnoyers <mathieu.desnoyers@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>,
Mark Rutland <mark.rutland@arm.com>,
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>,
linux-trace-kernel@vger.kernel.org,
Michael Jeanson <mjeanson@efficios.com>
Subject: [PATCH 5/8] tracing: Allow system call tracepoints to handle page faults
Date: Mon, 9 Sep 2024 16:16:49 -0400 [thread overview]
Message-ID: <20240909201652.319406-6-mathieu.desnoyers@efficios.com> (raw)
In-Reply-To: <20240909201652.319406-1-mathieu.desnoyers@efficios.com>
Use Tasks Trace RCU to protect iteration of system call enter/exit
tracepoint probes to allow those probes to handle page faults.
In preparation for this change, all tracers registering to system call
enter/exit tracepoints should expect those to be called with preemption
enabled.
This allows tracers to fault-in userspace system call arguments such as
path strings within their probe callbacks.
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Michael Jeanson <mjeanson@efficios.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
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>
---
include/linux/tracepoint.h | 25 +++++++++++++++++--------
init/Kconfig | 1 +
2 files changed, 18 insertions(+), 8 deletions(-)
diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index b2cfe6a9097c..005ede3b1afa 100644
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -18,6 +18,7 @@
#include <linux/types.h>
#include <linux/cpumask.h>
#include <linux/rcupdate.h>
+#include <linux/rcupdate_trace.h>
#include <linux/tracepoint-defs.h>
#include <linux/static_call.h>
@@ -90,6 +91,7 @@ int unregister_tracepoint_module_notifier(struct notifier_block *nb)
#ifdef CONFIG_TRACEPOINTS
static inline void tracepoint_synchronize_unregister(void)
{
+ synchronize_rcu_tasks_trace();
synchronize_srcu(&tracepoint_srcu);
synchronize_rcu();
}
@@ -192,7 +194,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p)
* it_func[0] is never NULL because there is at least one element in the array
* when the array itself is non NULL.
*/
-#define __DO_TRACE(name, args, cond, rcuidle) \
+#define __DO_TRACE(name, args, cond, rcuidle, syscall) \
do { \
int __maybe_unused __idx = 0; \
\
@@ -203,8 +205,12 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p)
"Bad RCU usage for tracepoint")) \
return; \
\
- /* keep srcu and sched-rcu usage consistent */ \
- preempt_disable_notrace(); \
+ if (syscall) { \
+ rcu_read_lock_trace(); \
+ } else { \
+ /* keep srcu and sched-rcu usage consistent */ \
+ preempt_disable_notrace(); \
+ } \
\
/* \
* For rcuidle callers, use srcu since sched-rcu \
@@ -222,7 +228,10 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p)
srcu_read_unlock_notrace(&tracepoint_srcu, __idx);\
} \
\
- preempt_enable_notrace(); \
+ if (syscall) \
+ rcu_read_unlock_trace(); \
+ else \
+ preempt_enable_notrace(); \
} while (0)
#ifndef MODULE
@@ -232,7 +241,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p)
if (static_key_false(&__tracepoint_##name.key)) \
__DO_TRACE(name, \
TP_ARGS(args), \
- TP_CONDITION(cond), 1); \
+ TP_CONDITION(cond), 1, 0); \
}
#else
#define __DECLARE_TRACE_RCU(name, proto, args, cond)
@@ -276,7 +285,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p)
if (static_key_false(&__tracepoint_##name.key)) \
__DO_TRACE(name, \
TP_ARGS(args), \
- TP_CONDITION(cond), 0); \
+ TP_CONDITION(cond), 0, 0); \
if (IS_ENABLED(CONFIG_LOCKDEP) && (cond)) { \
WARN_ONCE(!rcu_is_watching(), \
"RCU not watching for tracepoint"); \
@@ -287,7 +296,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p)
if (static_key_false(&__tracepoint_##name.key)) \
__DO_TRACE(name, \
TP_ARGS(args), \
- TP_CONDITION(cond), 1); \
+ TP_CONDITION(cond), 1, 0); \
} \
static inline int \
register_trace_##name(void (*probe)(data_proto), void *data) \
@@ -310,7 +319,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p)
if (static_key_false(&__tracepoint_##name.key)) \
__DO_TRACE(name, \
TP_ARGS(args), \
- TP_CONDITION(cond), 0); \
+ TP_CONDITION(cond), 0, 1); \
if (IS_ENABLED(CONFIG_LOCKDEP) && (cond)) { \
WARN_ONCE(!rcu_is_watching(), \
"RCU not watching for tracepoint"); \
diff --git a/init/Kconfig b/init/Kconfig
index d8a971b804d3..c854b2887e7f 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1937,6 +1937,7 @@ config BINDGEN_VERSION_TEXT
#
config TRACEPOINTS
bool
+ select TASKS_TRACE_RCU
source "kernel/Kconfig.kexec"
--
2.39.2
next prev parent reply other threads:[~2024-09-09 20:17 UTC|newest]
Thread overview: 17+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-09-09 20:16 [PATCH 0/8] tracing: Allow system call tracepoints to handle page faults Mathieu Desnoyers
2024-09-09 20:16 ` [PATCH 1/8] tracing: Declare system call tracepoints with TRACE_EVENT_SYSCALL Mathieu Desnoyers
2024-09-09 20:16 ` [PATCH 2/8] tracing/ftrace: guard syscall probe with preempt_notrace Mathieu Desnoyers
2024-09-16 18:47 ` Masami Hiramatsu
2024-09-09 20:16 ` [PATCH 3/8] tracing/perf: " Mathieu Desnoyers
2024-09-09 20:16 ` [PATCH 4/8] tracing/bpf: " Mathieu Desnoyers
2024-09-10 0:03 ` Andrii Nakryiko
2024-09-09 20:16 ` Mathieu Desnoyers [this message]
2024-09-09 20:16 ` [PATCH 6/8] tracing/ftrace: Add might_fault check to syscall probes Mathieu Desnoyers
2024-09-09 20:16 ` [PATCH 7/8] tracing/perf: " Mathieu Desnoyers
2024-09-09 20:16 ` [PATCH 8/8] tracing/bpf: " Mathieu Desnoyers
2024-09-10 0:02 ` Andrii Nakryiko
2024-09-09 23:53 ` [PATCH 0/8] tracing: Allow system call tracepoints to handle page faults Andrii Nakryiko
2024-09-10 0:36 ` Mathieu Desnoyers
2024-09-11 23:08 ` Andrii Nakryiko
2024-09-16 19:49 ` Masami Hiramatsu
2024-09-17 9:54 ` Mathieu Desnoyers
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=20240909201652.319406-6-mathieu.desnoyers@efficios.com \
--to=mathieu.desnoyers@efficios.com \
--cc=acme@kernel.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=linux-trace-kernel@vger.kernel.org \
--cc=mark.rutland@arm.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=rostedt@goodmis.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