@@ -17,6 +17,7 @@
#include <linux/errno.h>
#include <linux/types.h>
#include <linux/rcupdate.h>
+#include <linux/rcupdate_trace.h>
#include <linux/tracepoint-defs.h>
#include <linux/static_call.h>
@@ -107,6 +108,7 @@ void for_each_tracepoint_in_module(struct module *mod,
#ifdef CONFIG_TRACEPOINTS
static inline void tracepoint_synchronize_unregister(void)
{
+ synchronize_rcu_tasks_trace();
synchronize_rcu();
}
#else
@@ -197,18 +199,24 @@ 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) \
+#define __DO_TRACE(name, args, cond, syscall) \
do { \
int __maybe_unused __idx = 0; \
\
if (!(cond)) \
return; \
\
- preempt_disable_notrace(); \
+ if (syscall) \
+ rcu_read_lock_trace(); \
+ else \
+ preempt_disable_notrace(); \
\
__DO_TRACE_CALL(name, TP_ARGS(args)); \
\
- preempt_enable_notrace(); \
+ if (syscall) \
+ rcu_read_unlock_trace(); \
+ else \
+ preempt_enable_notrace(); \
} while (0)
/*
@@ -238,7 +246,7 @@ 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)); \
+ TP_CONDITION(cond), 0); \
if (IS_ENABLED(CONFIG_LOCKDEP) && (cond)) { \
WARN_ONCE(!rcu_is_watching(), \
"RCU not watching for tracepoint"); \
@@ -276,7 +284,7 @@ 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), 1); \
if (IS_ENABLED(CONFIG_LOCKDEP) && (cond)) { \
WARN_ONCE(!rcu_is_watching(), \
"RCU not watching for tracepoint"); \
@@ -1984,6 +1984,7 @@ config BINDGEN_VERSION_TEXT
#
config TRACEPOINTS
bool
+ select TASKS_TRACE_RCU
source "kernel/Kconfig.kexec"
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 | 18 +++++++++++++----- init/Kconfig | 1 + 2 files changed, 14 insertions(+), 5 deletions(-)