trace: propagate registration failure from tracing_start_*_record()
PATCH 1/1 trace: propagate registration failure from tracing_start_*_record()
syzbot reported a WARN in tracepoint_probe_unregister():
tracing_start_sched_switch() increments sched_cmdline_ref / sched_tgid_ref before calling tracing_sched_register(), and its return value is discarded because the API is void. When the first register_trace_sched_*() fails (e.g. kmalloc under memory pressure or failslab), the function's fail_deprobe* labels roll back any partial probe registration, but the caller's refcount has already been bumped. The state is now desynced: refs > 0 but no probes in tp->funcs.
Later, when the caller pairs the start with a stop, the refcount walks back to 0 and tracing_sched_unregister() calls unregister_trace_sched_*() against an empty tp->funcs. func_remove() returns -ENOENT and the WARN_ON_ONCE(IS_ERR(old)) in tracepoint_remove_func() fires.
Fix: make tracing_start_sched_switch() and the two exported wrappers, tracing_start_cmdline_record() and tracing_start_tgid_record(), return int; register the probes before bumping the refcount; and propagate the error to callers so refs are only held on behalf of a caller whose registration actually succeeded.
--- kernel/trace/trace.c | 6 +++--- kernel/trace/trace.h | 4 ++-- kernel/trace/trace_events.c | 28 +++++++++++++++++++-------- kernel/trace/trace_functions.c | 8 +++++++- kernel/trace/trace_functions_graph.c | 6 +++++- kernel/trace/trace_sched_switch.c | 29 ++++++++++++++++++---------- kernel/trace/trace_selftest.c | 7 ++++++- 7 files changed, 62 insertions(+), 26 deletions(-)
kernel/trace/trace.c +3 -3
@@ -3320,7 +3320,7 @@ void trace_printk_init_buffers(void)* allocated here, then this was called by module code. */ if (global_trace.array_buffer.buffer) -tracing_start_cmdline_record (); + (void )tracing_start_cmdline_record (); }EXPORT_SYMBOL_GPL (trace_printk_init_buffers);
@@ -3329,7 +3329,7 @@ void trace_printk_start_comm(void)/* Start tracing comms if trace printk is set */ if (!buffers_allocated)return ; -tracing_start_cmdline_record (); + (void )tracing_start_cmdline_record (); }static void trace_printk_start_stop_comm (int enabled)
@@ -3338,7 +3338,7 @@ static void trace_printk_start_stop_comm(int enabled)return ;if (enabled) -tracing_start_cmdline_record (); + (void )tracing_start_cmdline_record ();else tracing_stop_cmdline_record (); }
kernel/trace/trace.h +2 -2
@@ -751,9 +751,9 @@ void trace_graph_return(struct ftrace_graph_ret *trace, struct fgraph_ops *gops,int trace_graph_entry (struct ftrace_graph_ent *trace,struct fgraph_ops *gops,struct ftrace_regs *fregs); -void tracing_start_cmdline_record (void ); +int tracing_start_cmdline_record (void );void tracing_stop_cmdline_record (void ); -void tracing_start_tgid_record (void ); +int tracing_start_tgid_record (void );void tracing_stop_tgid_record (void );int register_tracer (struct tracer *type);
kernel/trace/trace_events.c +20 -8
@@ -734,9 +734,9 @@ void trace_event_enable_cmd_record(bool enable)continue ;if (enable) { -tracing_start_cmdline_record (); -set_bit (EVENT_FILE_FL_RECORDED_CMD_BIT , &file->flags); - }else { +if (!tracing_start_cmdline_record ()) +set_bit (EVENT_FILE_FL_RECORDED_CMD_BIT , &file->flags); + }else if (file->flags &EVENT_FILE_FL_RECORDED_CMD ) {tracing_stop_cmdline_record ();clear_bit (EVENT_FILE_FL_RECORDED_CMD_BIT , &file->flags); }
@@ -755,9 +755,9 @@ void trace_event_enable_tgid_record(bool enable)continue ;if (enable) { -tracing_start_tgid_record (); -set_bit (EVENT_FILE_FL_RECORDED_TGID_BIT , &file->flags); - }else { +if (!tracing_start_tgid_record ()) +set_bit (EVENT_FILE_FL_RECORDED_TGID_BIT , &file->flags); + }else if (file->flags &EVENT_FILE_FL_RECORDED_TGID ) {tracing_stop_tgid_record ();clear_bit (EVENT_FILE_FL_RECORDED_TGID_BIT , &file->flags);
@@ -847,14 +847,26 @@ static int __ftrace_event_enable_disable(struct trace_event_file *file,set_bit (EVENT_FILE_FL_SOFT_DISABLED_BIT , &file->flags);if (tr->trace_flags &TRACE_ITER (RECORD_CMD )) { + ret =tracing_start_cmdline_record (); +if (ret) { +pr_info ("event trace: Could not enable event %s\n" , +trace_event_name (call)); +break ; + } cmd = true; -tracing_start_cmdline_record ();set_bit (EVENT_FILE_FL_RECORDED_CMD_BIT , &file->flags); }if (tr->trace_flags &TRACE_ITER (RECORD_TGID )) { + ret =tracing_start_tgid_record (); +if (ret) { +if (cmd) +tracing_stop_cmdline_record (); +pr_info ("event trace: Could not enable event %s\n" , +trace_event_name (call)); +break ; + } tgid = true; -tracing_start_tgid_record ();set_bit (EVENT_FILE_FL_RECORDED_TGID_BIT , &file->flags); }
kernel/trace/trace_functions.c +7 -1
@@ -146,6 +146,8 @@ static bool handle_func_repeats(struct trace_array *tr, u32 flags_val)static int function_trace_init (struct trace_array *tr) {ftrace_func_t func; +int ret; +/* * Instance trace_arrays get their ops allocated * at instance creation. Unless it failed
@@ -165,7 +167,11 @@ static int function_trace_init(struct trace_array *tr) tr->array_buffer.cpu =raw_smp_processor_id (); -tracing_start_cmdline_record (); + ret =tracing_start_cmdline_record (); +if (ret) { +ftrace_reset_array_ops (tr); +return ret; + }tracing_start_function_trace (tr);return 0 ; }
kernel/trace/trace_functions_graph.c +5 -1
@@ -487,7 +487,11 @@ static int graph_trace_init(struct trace_array *tr) ret =register_ftrace_graph (tr->gops);if (ret)return ret; -tracing_start_cmdline_record (); + ret =tracing_start_cmdline_record (); +if (ret) { +unregister_ftrace_graph (tr->gops); +return ret; + }return 0 ; }
kernel/trace/trace_sched_switch.c +19 -10
@@ -89,12 +89,22 @@ static void tracing_sched_unregister(void)unregister_trace_sched_wakeup (probe_sched_wakeup,NULL ); } -static void tracing_start_sched_switch (int ops) +static int tracing_start_sched_switch (int ops) { -bool sched_register; +int ret =0 ;mutex_lock (&sched_register_mutex); - sched_register = (!sched_cmdline_ref && !sched_tgid_ref); + +/* +* If the registration fails, do not bump the reference count : the +* caller must observe the failure so it can avoid a later matching +* stop that would otherwise unregister probes that were never added. +*/ +if (!sched_cmdline_ref && !sched_tgid_ref) { + ret =tracing_sched_register (); +if (ret) + goto out; + }switch (ops) {case RECORD_CMDLINE :
@@ -105,10 +115,9 @@ static void tracing_start_sched_switch(int ops) sched_tgid_ref++;break ; } - -if (sched_register && (sched_cmdline_ref || sched_tgid_ref)) -tracing_sched_register (); +out:mutex_unlock (&sched_register_mutex); +return ret; }static void tracing_stop_sched_switch (int ops)
@@ -130,9 +139,9 @@ static void tracing_stop_sched_switch(int ops)mutex_unlock (&sched_register_mutex); } -void tracing_start_cmdline_record (void ) +int tracing_start_cmdline_record (void ) { -tracing_start_sched_switch (RECORD_CMDLINE ); +return tracing_start_sched_switch (RECORD_CMDLINE ); }void tracing_stop_cmdline_record (void )
@@ -140,9 +149,9 @@ void tracing_stop_cmdline_record(void)tracing_stop_sched_switch (RECORD_CMDLINE ); } -void tracing_start_tgid_record (void ) +int tracing_start_tgid_record (void ) { -tracing_start_sched_switch (RECORD_TGID ); +return tracing_start_sched_switch (RECORD_TGID ); }void tracing_stop_tgid_record (void )
kernel/trace/trace_selftest.c +6 -1
@@ -1084,7 +1084,12 @@ trace_selftest_startup_function_graph(struct tracer *trace,warn_failed_init_tracer (trace, ret); goto out; } -tracing_start_cmdline_record (); + ret =tracing_start_cmdline_record (); +if (ret) { +unregister_ftrace_graph (&fgraph_ops); +warn_failed_init_tracer (trace, ret); + goto out; + }/* Sleep for a 1/10 of a second */ msleep (100 );
Signature · 1 line
2.43.0
Steven Rostedt
maintainerQuoted 24 lines · On Fri, 17 Apr 2026 12:08:27 +0530 Yash Suthar <[email protected]> wrote:
syzbot reported a WARN in
tracepoint_probe_unregister():
tracing_start_sched_switch()incrementssched_cmdline_ref/sched_tgid_refbefore callingtracing_sched_register(), and its return value is discarded because the API is void. When the first register_trace_sched_*() fails (e.g. kmalloc under memory pressure or failslab), the function's fail_deprobe* labels roll back any partial probe registration, but the caller's refcount has already been bumped. The state is now desynced: refs > 0 but no probes intp->funcs.Later, when the caller pairs the start with a stop, the refcount walks back to 0 and
tracing_sched_unregister()calls unregister_trace_sched_*() against an emptytp->funcs.func_remove()returns-ENOENTand the WARN_ON_ONCE(IS_ERR(old)) intracepoint_remove_func()fires.Fix: make
tracing_start_sched_switch()and the two exported wrappers,tracing_start_cmdline_record()andtracing_start_tgid_record(), return int; register the probes before bumping the refcount; and propagate the error to callers so refs are only held on behalf of a caller whose registration actually succeeded.
Quoted 3 lines
Fixes d914ba37d714 ("tracing: Add support for recording tgid of tasks")Reported-by [email protected]
Did you use AI to create any of this? If so you must disclose it. This reads very much like an AI patch.
Quoted 11 lines
Signed-off-by Yash Suthar <[email protected]>--- kernel/trace/trace.c | 6 +++--- kernel/trace/trace.h | 4 ++-- kernel/trace/trace_events.c | 28 +++++++++++++++++++-------- kernel/trace/trace_functions.c | 8 +++++++- kernel/trace/trace_functions_graph.c | 6 +++++- kernel/trace/trace_sched_switch.c | 29 ++++++++++++++++++---------- kernel/trace/trace_selftest.c | 7 ++++++- 7 files changed, 62 insertions(+), 26 deletions(-)
NAK on all this. If you are under severe memory constraints that causes this to fail, then you'll be hitting a bunch more errors.
kernel/trace/trace.c void trace_printk_init_buffers(void) · line 3323
Quoted 11 lines
kernel/trace/trace.c +1
-1@@ -3320,7 +3320,7 @@ void trace_printk_init_buffers(void)* allocated here, then this was called by module code. */ if (global_trace.array_buffer.buffer) -tracing_start_cmdline_record (); + (void )tracing_start_cmdline_record ();
WTF??? Why are you adding the typecast of (void) here? Don't do that!
Quoted 170 lines
kernel/trace/trace.c +2
-2}EXPORT_SYMBOL_GPL (trace_printk_init_buffers);@@ -3329,7 +3329,7 @@ void trace_printk_start_comm(void)/* Start tracing comms if trace printk is set */ if (!buffers_allocated)return ; -tracing_start_cmdline_record (); + (void )tracing_start_cmdline_record (); }static void trace_printk_start_stop_comm (int enabled)@@ -3338,7 +3338,7 @@ static void trace_printk_start_stop_comm(int enabled)return ;if (enabled) -tracing_start_cmdline_record (); + (void )tracing_start_cmdline_record ();else tracing_stop_cmdline_record (); }kernel/trace/trace.h +2
-2@@ -751,9 +751,9 @@ void trace_graph_return(struct ftrace_graph_ret *trace, struct fgraph_ops *gops,int trace_graph_entry (struct ftrace_graph_ent *trace,struct fgraph_ops *gops,struct ftrace_regs *fregs); -void tracing_start_cmdline_record (void ); +int tracing_start_cmdline_record (void );void tracing_stop_cmdline_record (void ); -void tracing_start_tgid_record (void ); +int tracing_start_tgid_record (void );void tracing_stop_tgid_record (void );int register_tracer (struct tracer *type);kernel/trace/trace_events.c +20
-8@@ -734,9 +734,9 @@ void trace_event_enable_cmd_record(bool enable)continue ;if (enable) { -tracing_start_cmdline_record (); -set_bit (EVENT_FILE_FL_RECORDED_CMD_BIT , &file->flags); - }else { +if (!tracing_start_cmdline_record ()) +set_bit (EVENT_FILE_FL_RECORDED_CMD_BIT , &file->flags); + }else if (file->flags &EVENT_FILE_FL_RECORDED_CMD ) {tracing_stop_cmdline_record ();clear_bit (EVENT_FILE_FL_RECORDED_CMD_BIT , &file->flags); }@@ -755,9 +755,9 @@ void trace_event_enable_tgid_record(bool enable)continue ;if (enable) { -tracing_start_tgid_record (); -set_bit (EVENT_FILE_FL_RECORDED_TGID_BIT , &file->flags); - }else { +if (!tracing_start_tgid_record ()) +set_bit (EVENT_FILE_FL_RECORDED_TGID_BIT , &file->flags); + }else if (file->flags &EVENT_FILE_FL_RECORDED_TGID ) {tracing_stop_tgid_record ();clear_bit (EVENT_FILE_FL_RECORDED_TGID_BIT , &file->flags);@@ -847,14 +847,26 @@ static int __ftrace_event_enable_disable(struct trace_event_file *file,set_bit (EVENT_FILE_FL_SOFT_DISABLED_BIT , &file->flags);if (tr->trace_flags &TRACE_ITER (RECORD_CMD )) { + ret =tracing_start_cmdline_record (); +if (ret) { +pr_info ("event trace: Could not enable event %s\n" , +trace_event_name (call)); +break ; + } cmd = true; -tracing_start_cmdline_record ();set_bit (EVENT_FILE_FL_RECORDED_CMD_BIT , &file->flags); }if (tr->trace_flags &TRACE_ITER (RECORD_TGID )) { + ret =tracing_start_tgid_record (); +if (ret) { +if (cmd) +tracing_stop_cmdline_record (); +pr_info ("event trace: Could not enable event %s\n" , +trace_event_name (call)); +break ; + } tgid = true; -tracing_start_tgid_record ();set_bit (EVENT_FILE_FL_RECORDED_TGID_BIT , &file->flags); }kernel/trace/trace_functions.c +7
-1@@ -146,6 +146,8 @@ static bool handle_func_repeats(struct trace_array *tr, u32 flags_val)static int function_trace_init (struct trace_array *tr) {ftrace_func_t func; +int ret; +/* * Instance trace_arrays get their ops allocated * at instance creation. Unless it failed @@ -165,7 +167,11 @@ static int function_trace_init(struct trace_array *tr) tr->array_buffer.cpu =raw_smp_processor_id (); -tracing_start_cmdline_record (); + ret =tracing_start_cmdline_record (); +if (ret) { +ftrace_reset_array_ops (tr); +return ret; + }tracing_start_function_trace (tr);return 0 ; }kernel/trace/trace_functions_graph.c +5
-1@@ -487,7 +487,11 @@ static int graph_trace_init(struct trace_array *tr) ret =register_ftrace_graph (tr->gops);if (ret)return ret; -tracing_start_cmdline_record (); + ret =tracing_start_cmdline_record (); +if (ret) { +unregister_ftrace_graph (tr->gops); +return ret; + }return 0 ; }kernel/trace/trace_sched_switch.c +13
-3@@ -89,12 +89,22 @@ static void tracing_sched_unregister(void)unregister_trace_sched_wakeup (probe_sched_wakeup,NULL ); } -static void tracing_start_sched_switch (int ops) +static int tracing_start_sched_switch (int ops) { -bool sched_register; +int ret =0 ;mutex_lock (&sched_register_mutex); - sched_register = (!sched_cmdline_ref && !sched_tgid_ref); + +/* +* If the registration fails, do not bump the reference count : the +* caller must observe the failure so it can avoid a later matching +* stop that would otherwise unregister probes that were never added. +*/ +if (!sched_cmdline_ref && !sched_tgid_ref) { + ret =tracing_sched_register (); +if (ret) + goto out; + }switch (ops) {case RECORD_CMDLINE :
kernel/trace/trace_sched_switch.c static void tracing_start_sched_switch(int ops) · line 110
Quoted 6 lines
kernel/trace/trace_sched_switch.c +0
-3@@ -105,10 +115,9 @@ static void tracing_start_sched_switch(int ops) sched_tgid_ref++;break ; } - -if (sched_register && (sched_cmdline_ref || sched_tgid_ref)) -tracing_sched_register ();
The only change that should deal with this would be:
if (sched_register && (sched_cmdline_ref || sched_tgid_ref)) {
WARN_ONCE(tracing_sched_register() < 0,
"Failed to register trace command line caching. Requires reboot to fix");
}-- Steve
Quoted 48 lines
kernel/trace/trace_sched_switch.c +6
-4+out:mutex_unlock (&sched_register_mutex); +return ret; }static void tracing_stop_sched_switch (int ops)@@ -130,9 +139,9 @@ static void tracing_stop_sched_switch(int ops)mutex_unlock (&sched_register_mutex); } -void tracing_start_cmdline_record (void ) +int tracing_start_cmdline_record (void ) { -tracing_start_sched_switch (RECORD_CMDLINE ); +return tracing_start_sched_switch (RECORD_CMDLINE ); }void tracing_stop_cmdline_record (void )@@ -140,9 +149,9 @@ void tracing_stop_cmdline_record(void)tracing_stop_sched_switch (RECORD_CMDLINE ); } -void tracing_start_tgid_record (void ) +int tracing_start_tgid_record (void ) { -tracing_start_sched_switch (RECORD_TGID ); +return tracing_start_sched_switch (RECORD_TGID ); }void tracing_stop_tgid_record (void )kernel/trace/trace_selftest.c +6
-1@@ -1084,7 +1084,12 @@ trace_selftest_startup_function_graph(struct tracer *trace,warn_failed_init_tracer (trace, ret); goto out; } -tracing_start_cmdline_record (); + ret =tracing_start_cmdline_record (); +if (ret) { +unregister_ftrace_graph (&fgraph_ops); +warn_failed_init_tracer (trace, ret); + goto out; + }/* Sleep for a 1/10 of a second */ msleep (100 );
Hello Steven,
Thank you for taking a look and really sorry.
I did use ai assistance for commit message, but I reviewed, modified and tested(with syzbot locally) the code myself. I should have disclosed really sorry.
One thing I want to know (or I am still missing something):sched_cmdline_ref is incremented before tracing_sched_register() and register fails, but sched_cmdline_ref stays at 1 and on disable tracepoint_remove_func() sees NULL and return error (as syzbot reported and reproduce also locally).
your suggestion WARN_ONCE correctly flags the upstream failure, but the secondary WARN at tracepoint.c:358 will still fire on the next disable, since the refcount desync isn't addressed. Was that intentional ?
in my earlier approach, I tried to propagate the error and handle this desync under fault injection. I understand this may not align with the preferred direction, but that was the motivation behind the change.
If you think it makes sense, I can prepare a v2 with your suggestion while also addressing the refcount consistency.
Thank you
Quoted 302 lines · Steven Rostedt
Quoted 24 lines · On Fri, 17 Apr 2026 12:08:27 +0530 Yash Suthar <[email protected]> wrote:
syzbot reported a WARN in
tracepoint_probe_unregister():
tracing_start_sched_switch()incrementssched_cmdline_ref/sched_tgid_refbefore callingtracing_sched_register(), and its return value is discarded because the API is void. When the first register_trace_sched_*() fails (e.g. kmalloc under memory pressure or failslab), the function's fail_deprobe* labels roll back any partial probe registration, but the caller's refcount has already been bumped. The state is now desynced: refs > 0 but no probes intp->funcs.Later, when the caller pairs the start with a stop, the refcount walks back to 0 and
tracing_sched_unregister()calls unregister_trace_sched_*() against an emptytp->funcs.func_remove()returns-ENOENTand the WARN_ON_ONCE(IS_ERR(old)) intracepoint_remove_func()fires.Fix: make
tracing_start_sched_switch()and the two exported wrappers,tracing_start_cmdline_record()andtracing_start_tgid_record(), return int; register the probes before bumping the refcount; and propagate the error to callers so refs are only held on behalf of a caller whose registration actually succeeded.Quoted 3 lines
Fixes d914ba37d714 ("tracing: Add support for recording tgid of tasks")Reported-by [email protected]Did you use AI to create any of this? If so you must disclose it. This reads very much like an AI patch.
Quoted 11 lines
Signed-off-by Yash Suthar <[email protected]>--- kernel/trace/trace.c | 6 +++--- kernel/trace/trace.h | 4 ++-- kernel/trace/trace_events.c | 28 +++++++++++++++++++-------- kernel/trace/trace_functions.c | 8 +++++++- kernel/trace/trace_functions_graph.c | 6 +++++- kernel/trace/trace_sched_switch.c | 29 ++++++++++++++++++---------- kernel/trace/trace_selftest.c | 7 ++++++- 7 files changed, 62 insertions(+), 26 deletions(-)NAK on all this. If you are under severe memory constraints that causes this to fail, then you'll be hitting a bunch more errors.
kernel/trace/trace.c void trace_printk_init_buffers(void) · line 3323
Quoted 11 lines
kernel/trace/trace.c +1
-1@@ -3320,7 +3320,7 @@ void trace_printk_init_buffers(void)* allocated here, then this was called by module code. */ if (global_trace.array_buffer.buffer) -tracing_start_cmdline_record (); + (void )tracing_start_cmdline_record ();WTF??? Why are you adding the typecast of (void) here? Don't do that!
Quoted 170 lines
kernel/trace/trace.c +2
-2}EXPORT_SYMBOL_GPL (trace_printk_init_buffers);@@ -3329,7 +3329,7 @@ void trace_printk_start_comm(void)/* Start tracing comms if trace printk is set */ if (!buffers_allocated)return ; -tracing_start_cmdline_record (); + (void )tracing_start_cmdline_record (); }static void trace_printk_start_stop_comm (int enabled)@@ -3338,7 +3338,7 @@ static void trace_printk_start_stop_comm(int enabled)return ;if (enabled) -tracing_start_cmdline_record (); + (void )tracing_start_cmdline_record ();else tracing_stop_cmdline_record (); }kernel/trace/trace.h +2
-2@@ -751,9 +751,9 @@ void trace_graph_return(struct ftrace_graph_ret *trace, struct fgraph_ops *gops,int trace_graph_entry (struct ftrace_graph_ent *trace,struct fgraph_ops *gops,struct ftrace_regs *fregs); -void tracing_start_cmdline_record (void ); +int tracing_start_cmdline_record (void );void tracing_stop_cmdline_record (void ); -void tracing_start_tgid_record (void ); +int tracing_start_tgid_record (void );void tracing_stop_tgid_record (void );int register_tracer (struct tracer *type);kernel/trace/trace_events.c +20
-8@@ -734,9 +734,9 @@ void trace_event_enable_cmd_record(bool enable)continue ;if (enable) { -tracing_start_cmdline_record (); -set_bit (EVENT_FILE_FL_RECORDED_CMD_BIT , &file->flags); - }else { +if (!tracing_start_cmdline_record ()) +set_bit (EVENT_FILE_FL_RECORDED_CMD_BIT , &file->flags); + }else if (file->flags &EVENT_FILE_FL_RECORDED_CMD ) {tracing_stop_cmdline_record ();clear_bit (EVENT_FILE_FL_RECORDED_CMD_BIT , &file->flags); }@@ -755,9 +755,9 @@ void trace_event_enable_tgid_record(bool enable)continue ;if (enable) { -tracing_start_tgid_record (); -set_bit (EVENT_FILE_FL_RECORDED_TGID_BIT , &file->flags); - }else { +if (!tracing_start_tgid_record ()) +set_bit (EVENT_FILE_FL_RECORDED_TGID_BIT , &file->flags); + }else if (file->flags &EVENT_FILE_FL_RECORDED_TGID ) {tracing_stop_tgid_record ();clear_bit (EVENT_FILE_FL_RECORDED_TGID_BIT , &file->flags);@@ -847,14 +847,26 @@ static int __ftrace_event_enable_disable(struct trace_event_file *file,set_bit (EVENT_FILE_FL_SOFT_DISABLED_BIT , &file->flags);if (tr->trace_flags &TRACE_ITER (RECORD_CMD )) { + ret =tracing_start_cmdline_record (); +if (ret) { +pr_info ("event trace: Could not enable event %s\n" , +trace_event_name (call)); +break ; + } cmd = true; -tracing_start_cmdline_record ();set_bit (EVENT_FILE_FL_RECORDED_CMD_BIT , &file->flags); }if (tr->trace_flags &TRACE_ITER (RECORD_TGID )) { + ret =tracing_start_tgid_record (); +if (ret) { +if (cmd) +tracing_stop_cmdline_record (); +pr_info ("event trace: Could not enable event %s\n" , +trace_event_name (call)); +break ; + } tgid = true; -tracing_start_tgid_record ();set_bit (EVENT_FILE_FL_RECORDED_TGID_BIT , &file->flags); }kernel/trace/trace_functions.c +7
-1@@ -146,6 +146,8 @@ static bool handle_func_repeats(struct trace_array *tr, u32 flags_val)static int function_trace_init (struct trace_array *tr) {ftrace_func_t func; +int ret; +/* * Instance trace_arrays get their ops allocated * at instance creation. Unless it failed @@ -165,7 +167,11 @@ static int function_trace_init(struct trace_array *tr) tr->array_buffer.cpu =raw_smp_processor_id (); -tracing_start_cmdline_record (); + ret =tracing_start_cmdline_record (); +if (ret) { +ftrace_reset_array_ops (tr); +return ret; + }tracing_start_function_trace (tr);return 0 ; }kernel/trace/trace_functions_graph.c +5
-1@@ -487,7 +487,11 @@ static int graph_trace_init(struct trace_array *tr) ret =register_ftrace_graph (tr->gops);if (ret)return ret; -tracing_start_cmdline_record (); + ret =tracing_start_cmdline_record (); +if (ret) { +unregister_ftrace_graph (tr->gops); +return ret; + }return 0 ; }kernel/trace/trace_sched_switch.c +13
-3@@ -89,12 +89,22 @@ static void tracing_sched_unregister(void)unregister_trace_sched_wakeup (probe_sched_wakeup,NULL ); } -static void tracing_start_sched_switch (int ops) +static int tracing_start_sched_switch (int ops) { -bool sched_register; +int ret =0 ;mutex_lock (&sched_register_mutex); - sched_register = (!sched_cmdline_ref && !sched_tgid_ref); + +/* +* If the registration fails, do not bump the reference count : the +* caller must observe the failure so it can avoid a later matching +* stop that would otherwise unregister probes that were never added. +*/ +if (!sched_cmdline_ref && !sched_tgid_ref) { + ret =tracing_sched_register (); +if (ret) + goto out; + }switch (ops) {case RECORD_CMDLINE :kernel/trace/trace_sched_switch.c static void tracing_start_sched_switch(int ops) · line 110
Quoted 6 lines
kernel/trace/trace_sched_switch.c +0
-3@@ -105,10 +115,9 @@ static void tracing_start_sched_switch(int ops) sched_tgid_ref++;break ; } - -if (sched_register && (sched_cmdline_ref || sched_tgid_ref)) -tracing_sched_register ();The only change that should deal with this would be:
if (sched_register && (sched_cmdline_ref || sched_tgid_ref)) { WARN_ONCE(tracing_sched_register() < 0, "Failed to register trace command line caching. Requires reboot to fix"); }-- Steve
Quoted 48 lines
kernel/trace/trace_sched_switch.c +6
-4+out:mutex_unlock (&sched_register_mutex); +return ret; }static void tracing_stop_sched_switch (int ops)@@ -130,9 +139,9 @@ static void tracing_stop_sched_switch(int ops)mutex_unlock (&sched_register_mutex); } -void tracing_start_cmdline_record (void ) +int tracing_start_cmdline_record (void ) { -tracing_start_sched_switch (RECORD_CMDLINE ); +return tracing_start_sched_switch (RECORD_CMDLINE ); }void tracing_stop_cmdline_record (void )@@ -140,9 +149,9 @@ void tracing_stop_cmdline_record(void)tracing_stop_sched_switch (RECORD_CMDLINE ); } -void tracing_start_tgid_record (void ) +int tracing_start_tgid_record (void ) { -tracing_start_sched_switch (RECORD_TGID ); +return tracing_start_sched_switch (RECORD_TGID ); }void tracing_stop_tgid_record (void )kernel/trace/trace_selftest.c +6
-1@@ -1084,7 +1084,12 @@ trace_selftest_startup_function_graph(struct tracer *trace,warn_failed_init_tracer (trace, ret); goto out; } -tracing_start_cmdline_record (); + ret =tracing_start_cmdline_record (); +if (ret) { +unregister_ftrace_graph (&fgraph_ops); +warn_failed_init_tracer (trace, ret); + goto out; + }/* Sleep for a 1/10 of a second */ msleep (100 );
Steven Rostedt
maintainerQuoted 7 lines · On Sat, 18 Apr 2026 11:08:42 +0530 Yash Suthar <[email protected]> wrote:
Hello Steven,
Thank you for taking a look and really sorry.I did use ai assistance for commit message, but I reviewed, modified and tested(with syzbot locally) the code myself. I should have disclosed really sorry.
Quoted 9 lines
One thing I want to know (or I am still missing something):
sched_cmdline_refis incremented beforetracing_sched_register()and register fails, butsched_cmdline_refstays at 1 and on disabletracepoint_remove_func()sees NULL and return error (as syzbot reported and reproduce also locally).
your suggestionWARN_ONCEcorrectly flags the upstream failure, but the secondary WARN at tracepoint.c:358 will still fire on the next disable, since the refcount desync isn't addressed. Was that intentional ?
Yes.
This is why I'm not too thrilled about syzbot injecting kmalloc failures. These injections are for one page or less, in which case the system is in pretty much a failed state anyway.
I don't care about warnings being triggering due to kmalloc failures. I'll fix UAF or NULL pointer dereferences, but warnings? No!
If you fail to alloc a single page, expect a lot of warnings to happen. That is intentional. syzbot should not flag an error for a warning that was triggered due to a single page memory failure, unless that memory was allocated by in atomic or something where it can't do reclaim.
-- Steve