From 2cddfc2e8fc78c13b0f5286ea5dd48cdf527ad41 Mon Sep 17 00:00:00 2001 From: Aaron Tomlin Date: Fri, 26 Dec 2025 11:07:24 -0500 Subject: tracing: Add bitmask-list option for human-readable bitmask display Add support for displaying bitmasks in human-readable list format (e.g., 0,2-5,7) in addition to the default hexadecimal bitmap representation. This is particularly useful when tracing CPU masks and other large bitmasks where individual bit positions are more meaningful than their hexadecimal encoding. When the "bitmask-list" option is enabled, the printk "%*pbl" format specifier is used to render bitmasks as comma-separated ranges, making trace output easier to interpret for complex CPU configurations and large bitmask values. Link: https://patch.msgid.link/20251226160724.2246493-2-atomlin@atomlin.com Signed-off-by: Aaron Tomlin Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace.h | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel/trace/trace.h') diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index b6d42fe06115..8888fc9335b6 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -1411,6 +1411,7 @@ extern int trace_get_user(struct trace_parser *parser, const char __user *ubuf, C(COPY_MARKER, "copy_trace_marker"), \ C(PAUSE_ON_TRACE, "pause-on-trace"), \ C(HASH_PTR, "hash-ptr"), /* Print hashed pointer */ \ + C(BITMASK_LIST, "bitmask-list"), \ FUNCTION_FLAGS \ FGRAPH_FLAGS \ STACK_FLAGS \ -- cgit v1.2.3 From e62750b6ab4d57f6cf4ea1550de8d2e111adb675 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 23 Jan 2026 10:54:15 -0500 Subject: tracing: Up the hist stacktrace size from 16 to 31 Recording stacktraces is very useful, but the size of 16 deep is very restrictive. For example, in seeing where tasks schedule out in a non running state, the following can be used: ~# cd /sys/kernel/tracing ~# echo 'hist:keys=common_stacktrace:vals=hitcount if prev_state & 3' > events/sched/sched_switch/trigger ~# cat events/sched/sched_switch/hist [..] { common_stacktrace: __schedule+0xdc0/0x1860 schedule+0x27/0xd0 schedule_timeout+0xb5/0x100 wait_for_completion+0x8a/0x140 xfs_buf_iowait+0x20/0xd0 [xfs] xfs_buf_read_map+0x103/0x250 [xfs] xfs_trans_read_buf_map+0x161/0x310 [xfs] xfs_btree_read_buf_block+0xa0/0x120 [xfs] xfs_btree_lookup_get_block+0xa3/0x1e0 [xfs] xfs_btree_lookup+0xea/0x530 [xfs] xfs_alloc_fixup_trees+0x72/0x570 [xfs] xfs_alloc_ag_vextent_size+0x67f/0x800 [xfs] xfs_alloc_vextent_iterate_ags.constprop.0+0x52/0x230 [xfs] xfs_alloc_vextent_start_ag+0x9d/0x1b0 [xfs] xfs_bmap_btalloc+0x2af/0x680 [xfs] xfs_bmapi_allocate+0xdb/0x2c0 [xfs] } hitcount: 1 [..] The above stops at 16 functions where knowing more would be useful. As the allocated storage for stacks is the same for strings, and that size is 256 bytes, there is a lot of space not being used for stacktraces. 16 * 8 = 128 Up the size to 31 (it requires the last slot to be zero, so it can't be 32). Also change the BUILD_BUG_ON() to allow the size of the stacktrace storage to be equal to the max size. One slot is used to hold the number of elements in the stack. BUILD_BUG_ON((HIST_STACKTRACE_DEPTH + 1) * sizeof(long) >= STR_VAR_LEN_MAX); Change that from ">=" to just ">", as now they are equal. Cc: Masami Hiramatsu Cc: Mathieu Desnoyers Link: https://patch.msgid.link/20260123105415.2be26bf4@gandalf.local.home Reviewed-by: Tom Zanussi Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace.h | 2 +- kernel/trace/trace_events_hist.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel/trace/trace.h') diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 8888fc9335b6..69e7defba6c6 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -128,7 +128,7 @@ enum trace_type { #define FAULT_STRING "(fault)" -#define HIST_STACKTRACE_DEPTH 16 +#define HIST_STACKTRACE_DEPTH 31 #define HIST_STACKTRACE_SIZE (HIST_STACKTRACE_DEPTH * sizeof(unsigned long)) #define HIST_STACKTRACE_SKIP 5 diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index e245446a8cf7..0fc641461be5 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -3163,7 +3163,7 @@ static inline void __update_field_vars(struct tracing_map_elt *elt, u64 var_val; /* Make sure stacktrace can fit in the string variable length */ - BUILD_BUG_ON((HIST_STACKTRACE_DEPTH + 1) * sizeof(long) >= STR_VAR_LEN_MAX); + BUILD_BUG_ON((HIST_STACKTRACE_DEPTH + 1) * sizeof(long) > STR_VAR_LEN_MAX); for (i = 0, j = field_var_str_start; i < n_field_vars; i++) { struct field_var *field_var = field_vars[i]; -- cgit v1.2.3 From 1c48f7ab72a8c9d6419622931e622e5247e979f5 Mon Sep 17 00:00:00 2001 From: Yaxiong Tian Date: Wed, 4 Feb 2026 09:53:44 +0800 Subject: tracing: Rename `eval_map_wq` and allow other parts of tracing use it The eval_map_work_func() function, though queued in eval_map_wq, holds the trace_event_sem read-write lock for a long time during kernel boot. This causes blocking issues for other functions. Rename eval_map_wq to trace_init_wq and make it global, thereby allowing other parts of tracing to schedule work on this queue asynchronously and avoiding blockage of the main boot thread. Link: https://patch.msgid.link/20260204015344.162818-1-tianyaxiong@kylinos.cn Suggested-by: Steven Rostedt Acked-by: Masami Hiramatsu (Google) Signed-off-by: Yaxiong Tian Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace.c | 18 +++++++++--------- kernel/trace/trace.h | 1 + 2 files changed, 10 insertions(+), 9 deletions(-) (limited to 'kernel/trace/trace.h') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 396d59202438..8c0f3cfd196b 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -10785,7 +10785,7 @@ int tracing_init_dentry(void) extern struct trace_eval_map *__start_ftrace_eval_maps[]; extern struct trace_eval_map *__stop_ftrace_eval_maps[]; -static struct workqueue_struct *eval_map_wq __initdata; +struct workqueue_struct *trace_init_wq __initdata; static struct work_struct eval_map_work __initdata; static struct work_struct tracerfs_init_work __initdata; @@ -10801,15 +10801,15 @@ static int __init trace_eval_init(void) { INIT_WORK(&eval_map_work, eval_map_work_func); - eval_map_wq = alloc_workqueue("eval_map_wq", WQ_UNBOUND, 0); - if (!eval_map_wq) { - pr_err("Unable to allocate eval_map_wq\n"); + trace_init_wq = alloc_workqueue("trace_init_wq", WQ_UNBOUND, 0); + if (!trace_init_wq) { + pr_err("Unable to allocate trace_init_wq\n"); /* Do work here */ eval_map_work_func(&eval_map_work); return -ENOMEM; } - queue_work(eval_map_wq, &eval_map_work); + queue_work(trace_init_wq, &eval_map_work); return 0; } @@ -10818,8 +10818,8 @@ subsys_initcall(trace_eval_init); static int __init trace_eval_sync(void) { /* Make sure the eval map updates are finished */ - if (eval_map_wq) - destroy_workqueue(eval_map_wq); + if (trace_init_wq) + destroy_workqueue(trace_init_wq); return 0; } @@ -10980,9 +10980,9 @@ static __init int tracer_init_tracefs(void) if (ret) return 0; - if (eval_map_wq) { + if (trace_init_wq) { INIT_WORK(&tracerfs_init_work, tracer_init_tracefs_work_func); - queue_work(eval_map_wq, &tracerfs_init_work); + queue_work(trace_init_wq, &tracerfs_init_work); } else { tracer_init_tracefs_work_func(NULL); } diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 69e7defba6c6..bb68539c64b7 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -769,6 +769,7 @@ extern cpumask_var_t __read_mostly tracing_buffer_mask; extern unsigned long nsecs_to_usecs(unsigned long nsecs); extern unsigned long tracing_thresh; +extern struct workqueue_struct *trace_init_wq __initdata; /* PID filtering */ -- cgit v1.2.3 From 326669faf3cbfda31b2203f0a66aa87812062e5f Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 6 Feb 2026 14:37:52 -0500 Subject: tracing: Move tracing_set_filter_buffering() into trace_events_hist.c The function tracing_set_filter_buffering() is only used in trace_events_hist.c. Move it to that file and make it static. Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Andrew Morton Link: https://patch.msgid.link/20260206195936.617080218@kernel.org Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace.c | 20 -------------------- kernel/trace/trace.h | 1 - kernel/trace/trace_events_hist.c | 20 ++++++++++++++++++++ 3 files changed, 20 insertions(+), 21 deletions(-) (limited to 'kernel/trace/trace.h') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 8c0f3cfd196b..702ef851db45 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -7891,26 +7891,6 @@ u64 tracing_event_time_stamp(struct trace_buffer *buffer, struct ring_buffer_eve return ring_buffer_event_time_stamp(buffer, rbe); } -/* - * Set or disable using the per CPU trace_buffer_event when possible. - */ -int tracing_set_filter_buffering(struct trace_array *tr, bool set) -{ - guard(mutex)(&trace_types_lock); - - if (set && tr->no_filter_buffering_ref++) - return 0; - - if (!set) { - if (WARN_ON_ONCE(!tr->no_filter_buffering_ref)) - return -EINVAL; - - --tr->no_filter_buffering_ref; - } - - return 0; -} - struct ftrace_buffer_info { struct trace_iterator iter; void *spare; diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index bb68539c64b7..31fb137e1c66 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -476,7 +476,6 @@ extern struct trace_array *trace_array_find(const char *instance); extern struct trace_array *trace_array_find_get(const char *instance); extern u64 tracing_event_time_stamp(struct trace_buffer *buffer, struct ring_buffer_event *rbe); -extern int tracing_set_filter_buffering(struct trace_array *tr, bool set); extern int tracing_set_clock(struct trace_array *tr, const char *clockstr); extern bool trace_clock_in_ns(struct trace_array *tr); diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 0fc641461be5..e6f449f53afc 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -6531,6 +6531,26 @@ static bool existing_hist_update_only(char *glob, return updated; } +/* + * Set or disable using the per CPU trace_buffer_event when possible. + */ +static int tracing_set_filter_buffering(struct trace_array *tr, bool set) +{ + guard(mutex)(&trace_types_lock); + + if (set && tr->no_filter_buffering_ref++) + return 0; + + if (!set) { + if (WARN_ON_ONCE(!tr->no_filter_buffering_ref)) + return -EINVAL; + + --tr->no_filter_buffering_ref; + } + + return 0; +} + static int hist_register_trigger(char *glob, struct event_trigger_data *data, struct trace_event_file *file) -- cgit v1.2.3 From 64dee86ad7de3d59bae041e0d8f80ef89ddc4cf6 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Sat, 7 Feb 2026 22:24:18 -0500 Subject: tracing: Make tracing_disabled global for tracing system The tracing_disabled variable is set to one on boot up to prevent some parts of tracing to access the tracing infrastructure before it is set up. It also can be set after boot if an anomaly is discovered. It is currently a static variable in trace.c and can be accessed via a function call trace_is_disabled(). There's really no reason to use a function call as the tracing subsystem should be able to access it directly. By making the variable accessed directly, code can be moved out of trace.c without adding overhead of a function call to see if tracing is disabled or not. Make tracing_disabled global and remove the tracing_is_disabled() helper function. Also add some "unlikely()"s around tracing_disabled where it's checked in hot paths. Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Andrew Morton Link: https://patch.msgid.link/20260208032449.483690153@kernel.org Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace.c | 13 ++++--------- kernel/trace/trace.h | 3 ++- kernel/trace/trace_events.c | 2 +- kernel/trace/trace_kprobe.c | 2 +- 4 files changed, 8 insertions(+), 12 deletions(-) (limited to 'kernel/trace/trace.h') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index d02c4004c718..1ff40c88e75c 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -114,7 +114,7 @@ DEFINE_PER_CPU(bool, trace_taskinfo_save); * of the tracer is successful. But that is the only place that sets * this back to zero. */ -static int tracing_disabled = 1; +int tracing_disabled = 1; cpumask_var_t __read_mostly tracing_buffer_mask; @@ -3423,7 +3423,7 @@ int __trace_array_vprintk(struct trace_buffer *buffer, unsigned int trace_ctx; char *tbuffer; - if (tracing_disabled) + if (unlikely(tracing_disabled)) return 0; /* Don't pollute graph traces with trace_vprintk internals */ @@ -4765,11 +4765,6 @@ int tracing_open_generic(struct inode *inode, struct file *filp) return 0; } -bool tracing_is_disabled(void) -{ - return (tracing_disabled) ? true: false; -} - /* * Open and update trace_array ref count. * Must have the current trace_array passed to it. @@ -7609,7 +7604,7 @@ tracing_mark_write(struct file *filp, const char __user *ubuf, unsigned long ip; char *buf; - if (tracing_disabled) + if (unlikely(tracing_disabled)) return -EINVAL; if (!(tr->trace_flags & TRACE_ITER(MARKERS))) @@ -7689,7 +7684,7 @@ tracing_mark_raw_write(struct file *filp, const char __user *ubuf, ssize_t written = -ENODEV; char *buf; - if (tracing_disabled) + if (unlikely(tracing_disabled)) return -EINVAL; if (!(tr->trace_flags & TRACE_ITER(MARKERS))) diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 31fb137e1c66..433705bef480 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -657,6 +657,8 @@ trace_buffer_iter(struct trace_iterator *iter, int cpu) return iter->buffer_iter ? iter->buffer_iter[cpu] : NULL; } +extern int tracing_disabled; + int tracer_init(struct tracer *t, struct trace_array *tr); int tracing_is_enabled(void); void tracing_reset_online_cpus(struct array_buffer *buf); @@ -668,7 +670,6 @@ int tracing_release_generic_tr(struct inode *inode, struct file *file); int tracing_open_file_tr(struct inode *inode, struct file *filp); int tracing_release_file_tr(struct inode *inode, struct file *filp); int tracing_single_release_file_tr(struct inode *inode, struct file *filp); -bool tracing_is_disabled(void); bool tracer_tracing_is_on(struct trace_array *tr); void tracer_tracing_on(struct trace_array *tr); void tracer_tracing_off(struct trace_array *tr); diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index af6d1fe5cab7..61fe01dce7a6 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -2268,7 +2268,7 @@ static int subsystem_open(struct inode *inode, struct file *filp) struct event_subsystem *system = NULL; int ret; - if (tracing_is_disabled()) + if (unlikely(tracing_disabled)) return -ENODEV; /* Make sure the system still exists */ diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 89d2740f7bb5..061658518605 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -2083,7 +2083,7 @@ static __init int kprobe_trace_self_tests_init(void) struct trace_kprobe *tk; struct trace_event_file *file; - if (tracing_is_disabled()) + if (unlikely(tracing_disabled)) return -ENODEV; if (tracing_selftest_disabled) -- cgit v1.2.3 From a4f77ffc8eb6247ad00c53d297a145e47594ce76 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Sat, 7 Feb 2026 22:24:19 -0500 Subject: tracing: Make tracing_selftest_running global to the tracing subsystem The file trace.c has become a catchall for most things tracing. Start making it smaller by breaking out various aspects into their own files. Make the variable tracing_selftest_running global so that it can be used by other files in the tracing subsystem and trace.c can be split up. Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Andrew Morton Link: https://patch.msgid.link/20260208032449.648932796@kernel.org Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace.c | 3 +-- kernel/trace/trace.h | 2 ++ 2 files changed, 3 insertions(+), 2 deletions(-) (limited to 'kernel/trace/trace.h') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 1ff40c88e75c..f040ee4fe101 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -67,7 +67,7 @@ * insertions into the ring-buffer such as trace_printk could occurred * at the same time, giving false positive or negative results. */ -static bool __read_mostly tracing_selftest_running; +bool __read_mostly tracing_selftest_running; /* * If boot-time tracing including tracers/events via kernel cmdline @@ -83,7 +83,6 @@ void __init disable_tracing_selftest(const char *reason) } } #else -#define tracing_selftest_running 0 #define tracing_selftest_disabled 0 #endif diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 433705bef480..19cffc7b5852 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -863,6 +863,7 @@ extern int trace_selftest_startup_nop(struct tracer *trace, struct trace_array *tr); extern int trace_selftest_startup_branch(struct tracer *trace, struct trace_array *tr); +extern bool __read_mostly tracing_selftest_running; /* * Tracer data references selftest functions that only occur * on boot up. These can be __init functions. Thus, when selftests @@ -875,6 +876,7 @@ static inline void __init disable_tracing_selftest(const char *reason) } /* Tracers are seldom changed. Optimize when selftests are disabled. */ #define __tracer_data __read_mostly +#define tracing_selftest_running 0 #endif /* CONFIG_FTRACE_STARTUP_TEST */ extern void *head_page(struct trace_array_cpu *data); -- cgit v1.2.3 From 0e730bc067e7a790d61344dbf6d9dfdce7f99ea3 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Sat, 7 Feb 2026 22:24:20 -0500 Subject: tracing: Move __trace_buffer_{un}lock_*() functions to trace.h The file trace.c has become a catchall for most things tracing. Start making it smaller by breaking out various aspects into their own files. Move the __always_inline functions __trace_buffer_lock_reserve(), __trace_buffer_unlock_commit() and trace_event_setup() into trace.h. The trace.c file will be split up and these functions will be used in more than one of these files. As they are already __always_inline they can easily be moved into the trace.h header file. Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Andrew Morton Link: https://patch.msgid.link/20260208032449.813550600@kernel.org Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace.c | 42 ------------------------------------------ kernel/trace/trace.h | 41 +++++++++++++++++++++++++++++++++++++++++ 2 files changed, 41 insertions(+), 42 deletions(-) (limited to 'kernel/trace/trace.h') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index f040ee4fe101..55cd0c774886 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1058,30 +1058,6 @@ static inline void ftrace_trace_stack(struct trace_array *tr, #endif -static __always_inline void -trace_event_setup(struct ring_buffer_event *event, - int type, unsigned int trace_ctx) -{ - struct trace_entry *ent = ring_buffer_event_data(event); - - tracing_generic_entry_update(ent, type, trace_ctx); -} - -static __always_inline struct ring_buffer_event * -__trace_buffer_lock_reserve(struct trace_buffer *buffer, - int type, - unsigned long len, - unsigned int trace_ctx) -{ - struct ring_buffer_event *event; - - event = ring_buffer_lock_reserve(buffer, len); - if (event != NULL) - trace_event_setup(event, type, trace_ctx); - - return event; -} - void tracer_tracing_on(struct trace_array *tr) { if (tr->array_buffer.buffer) @@ -1109,24 +1085,6 @@ void tracing_on(void) } EXPORT_SYMBOL_GPL(tracing_on); - -static __always_inline void -__buffer_unlock_commit(struct trace_buffer *buffer, struct ring_buffer_event *event) -{ - __this_cpu_write(trace_taskinfo_save, true); - - /* If this is the temp buffer, we need to commit fully */ - if (this_cpu_read(trace_buffered_event) == event) { - /* Length is in event->array[0] */ - ring_buffer_write(buffer, event->array[0], &event->array[1]); - /* Release the temp buffer */ - this_cpu_dec(trace_buffered_event_cnt); - /* ring_buffer_unlock_commit() enables preemption */ - preempt_enable_notrace(); - } else - ring_buffer_unlock_commit(buffer); -} - int __trace_array_puts(struct trace_array *tr, unsigned long ip, const char *str, int size) { diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 19cffc7b5852..c2beabe96952 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -1568,6 +1568,47 @@ char *trace_user_fault_read(struct trace_user_buf_info *tinfo, const char __user *ptr, size_t size, trace_user_buf_copy copy_func, void *data); +static __always_inline void +trace_event_setup(struct ring_buffer_event *event, + int type, unsigned int trace_ctx) +{ + struct trace_entry *ent = ring_buffer_event_data(event); + + tracing_generic_entry_update(ent, type, trace_ctx); +} + +static __always_inline struct ring_buffer_event * +__trace_buffer_lock_reserve(struct trace_buffer *buffer, + int type, + unsigned long len, + unsigned int trace_ctx) +{ + struct ring_buffer_event *event; + + event = ring_buffer_lock_reserve(buffer, len); + if (event != NULL) + trace_event_setup(event, type, trace_ctx); + + return event; +} + +static __always_inline void +__buffer_unlock_commit(struct trace_buffer *buffer, struct ring_buffer_event *event) +{ + __this_cpu_write(trace_taskinfo_save, true); + + /* If this is the temp buffer, we need to commit fully */ + if (this_cpu_read(trace_buffered_event) == event) { + /* Length is in event->array[0] */ + ring_buffer_write(buffer, event->array[0], &event->array[1]); + /* Release the temp buffer */ + this_cpu_dec(trace_buffered_event_cnt); + /* ring_buffer_unlock_commit() enables preemption */ + preempt_enable_notrace(); + } else + ring_buffer_unlock_commit(buffer); +} + static inline void __trace_event_discard_commit(struct trace_buffer *buffer, struct ring_buffer_event *event) -- cgit v1.2.3 From 3e6c8f80e5ddd0644e509547c61366a2c09117b0 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Sat, 7 Feb 2026 22:24:21 -0500 Subject: tracing: Move ftrace_trace_stack() out of trace.c and into trace.h The file trace.c has become a catchall for most things tracing. Start making it smaller by breaking out various aspects into their own files. Make ftrace_trace_stack() into a static inline that tests if stack tracing is enabled and if so to call __ftrace_trace_stack() to do the stack trace. This keeps the test inlined in the fast paths and only does the function call if stack tracing is enabled. Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Andrew Morton Link: https://patch.msgid.link/20260208032449.974218132@kernel.org Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace.c | 45 ++++----------------------------------------- kernel/trace/trace.h | 31 +++++++++++++++++++++++++++++++ 2 files changed, 35 insertions(+), 41 deletions(-) (limited to 'kernel/trace/trace.h') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 55cd0c774886..a515b5241391 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1032,32 +1032,6 @@ static inline void trace_access_lock_init(void) #endif -#ifdef CONFIG_STACKTRACE -static void __ftrace_trace_stack(struct trace_array *tr, - struct trace_buffer *buffer, - unsigned int trace_ctx, - int skip, struct pt_regs *regs); -static inline void ftrace_trace_stack(struct trace_array *tr, - struct trace_buffer *buffer, - unsigned int trace_ctx, - int skip, struct pt_regs *regs); - -#else -static inline void __ftrace_trace_stack(struct trace_array *tr, - struct trace_buffer *buffer, - unsigned int trace_ctx, - int skip, struct pt_regs *regs) -{ -} -static inline void ftrace_trace_stack(struct trace_array *tr, - struct trace_buffer *buffer, - unsigned long trace_ctx, - int skip, struct pt_regs *regs) -{ -} - -#endif - void tracer_tracing_on(struct trace_array *tr) { if (tr->array_buffer.buffer) @@ -2964,10 +2938,10 @@ struct ftrace_stacks { static DEFINE_PER_CPU(struct ftrace_stacks, ftrace_stacks); static DEFINE_PER_CPU(int, ftrace_stack_reserve); -static void __ftrace_trace_stack(struct trace_array *tr, - struct trace_buffer *buffer, - unsigned int trace_ctx, - int skip, struct pt_regs *regs) +void __ftrace_trace_stack(struct trace_array *tr, + struct trace_buffer *buffer, + unsigned int trace_ctx, + int skip, struct pt_regs *regs) { struct ring_buffer_event *event; unsigned int size, nr_entries; @@ -3050,17 +3024,6 @@ static void __ftrace_trace_stack(struct trace_array *tr, trace_clear_recursion(bit); } -static inline void ftrace_trace_stack(struct trace_array *tr, - struct trace_buffer *buffer, - unsigned int trace_ctx, - int skip, struct pt_regs *regs) -{ - if (!(tr->trace_flags & TRACE_ITER(STACKTRACE))) - return; - - __ftrace_trace_stack(tr, buffer, trace_ctx, skip, regs); -} - void __trace_stack(struct trace_array *tr, unsigned int trace_ctx, int skip) { diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index c2beabe96952..605ee23f3262 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -2279,6 +2279,37 @@ static inline void sanitize_event_name(char *name) *name = '_'; } +#ifdef CONFIG_STACKTRACE +void __ftrace_trace_stack(struct trace_array *tr, + struct trace_buffer *buffer, + unsigned int trace_ctx, + int skip, struct pt_regs *regs); + +static __always_inline void ftrace_trace_stack(struct trace_array *tr, + struct trace_buffer *buffer, + unsigned int trace_ctx, + int skip, struct pt_regs *regs) +{ + if (!(tr->trace_flags & TRACE_ITER(STACKTRACE))) + return; + + __ftrace_trace_stack(tr, buffer, trace_ctx, skip, regs); +} +#else +static inline void __ftrace_trace_stack(struct trace_array *tr, + struct trace_buffer *buffer, + unsigned int trace_ctx, + int skip, struct pt_regs *regs) +{ +} +static inline void ftrace_trace_stack(struct trace_array *tr, + struct trace_buffer *buffer, + unsigned long trace_ctx, + int skip, struct pt_regs *regs) +{ +} +#endif + /* * This is a generic way to read and write a u64 value from a file in tracefs. * -- cgit v1.2.3 From 1c53d781d42541adc5ba76b4f843a3ff382e01fb Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Sat, 7 Feb 2026 22:24:22 -0500 Subject: tracing: Make printk_trace global for tracing system The printk_trace is used to determine which trace_array trace_printk() writes to. By making it a global variable among the tracing subsystem it will allow the trace_printk functions to be moved out of trace.c and still have direct access to that variable. Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Andrew Morton Link: https://patch.msgid.link/20260208032450.144525891@kernel.org Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace.c | 2 +- kernel/trace/trace.h | 2 ++ 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'kernel/trace/trace.h') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index a515b5241391..4a73822e2603 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -534,7 +534,7 @@ static struct trace_array global_trace = { .trace_flags = TRACE_DEFAULT_FLAGS, }; -static struct trace_array *printk_trace = &global_trace; +struct trace_array *printk_trace = &global_trace; /* List of trace_arrays interested in the top level trace_marker */ static LIST_HEAD(marker_copies); diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 605ee23f3262..921e4daa2825 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -482,6 +482,8 @@ extern bool trace_clock_in_ns(struct trace_array *tr); extern unsigned long trace_adjust_address(struct trace_array *tr, unsigned long addr); +extern struct trace_array *printk_trace; + /* * The global tracer (top) should be the first trace array added, * but we check the flag anyway. -- cgit v1.2.3 From 27931ee8f45415db3a10586f9d5b6f77ef7d7d84 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Sat, 7 Feb 2026 22:24:26 -0500 Subject: tracing: Move trace_printk functions out of trace.c and into trace_printk.c The file trace.c has become a catchall for most things tracing. Start making it smaller by breaking out various aspects into their own files. Move the functions associated to the trace_printk operations out of trace.c and into trace_printk.c. Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Andrew Morton Link: https://patch.msgid.link/20260208032450.828744197@kernel.org Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace.c | 431 -------------------------------------------- kernel/trace/trace.h | 1 + kernel/trace/trace_printk.c | 431 ++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 432 insertions(+), 431 deletions(-) (limited to 'kernel/trace/trace.h') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 4066c33674e7..5812b830c1fa 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -539,17 +539,6 @@ struct trace_array *printk_trace = &global_trace; /* List of trace_arrays interested in the top level trace_marker */ static LIST_HEAD(marker_copies); -static __always_inline bool printk_binsafe(struct trace_array *tr) -{ - /* - * The binary format of traceprintk can cause a crash if used - * by a buffer from another boot. Force the use of the - * non binary version of trace_printk if the trace_printk - * buffer is a boot mapped ring buffer. - */ - return !(tr->flags & TRACE_ARRAY_FL_BOOT); -} - static void update_printk_trace(struct trace_array *tr) { if (printk_trace == tr) @@ -1059,108 +1048,6 @@ void tracing_on(void) } EXPORT_SYMBOL_GPL(tracing_on); -int __trace_array_puts(struct trace_array *tr, unsigned long ip, - const char *str, int size) -{ - struct ring_buffer_event *event; - struct trace_buffer *buffer; - struct print_entry *entry; - unsigned int trace_ctx; - int alloc; - - if (!(tr->trace_flags & TRACE_ITER(PRINTK))) - return 0; - - if (unlikely(tracing_selftest_running && - (tr->flags & TRACE_ARRAY_FL_GLOBAL))) - return 0; - - if (unlikely(tracing_disabled)) - return 0; - - alloc = sizeof(*entry) + size + 2; /* possible \n added */ - - trace_ctx = tracing_gen_ctx(); - buffer = tr->array_buffer.buffer; - guard(ring_buffer_nest)(buffer); - event = __trace_buffer_lock_reserve(buffer, TRACE_PRINT, alloc, - trace_ctx); - if (!event) - return 0; - - entry = ring_buffer_event_data(event); - entry->ip = ip; - - memcpy(&entry->buf, str, size); - - /* Add a newline if necessary */ - if (entry->buf[size - 1] != '\n') { - entry->buf[size] = '\n'; - entry->buf[size + 1] = '\0'; - } else - entry->buf[size] = '\0'; - - __buffer_unlock_commit(buffer, event); - ftrace_trace_stack(tr, buffer, trace_ctx, 4, NULL); - return size; -} -EXPORT_SYMBOL_GPL(__trace_array_puts); - -/** - * __trace_puts - write a constant string into the trace buffer. - * @ip: The address of the caller - * @str: The constant string to write - * @size: The size of the string. - */ -int __trace_puts(unsigned long ip, const char *str, int size) -{ - return __trace_array_puts(printk_trace, ip, str, size); -} -EXPORT_SYMBOL_GPL(__trace_puts); - -/** - * __trace_bputs - write the pointer to a constant string into trace buffer - * @ip: The address of the caller - * @str: The constant string to write to the buffer to - */ -int __trace_bputs(unsigned long ip, const char *str) -{ - struct trace_array *tr = READ_ONCE(printk_trace); - struct ring_buffer_event *event; - struct trace_buffer *buffer; - struct bputs_entry *entry; - unsigned int trace_ctx; - int size = sizeof(struct bputs_entry); - - if (!printk_binsafe(tr)) - return __trace_puts(ip, str, strlen(str)); - - if (!(tr->trace_flags & TRACE_ITER(PRINTK))) - return 0; - - if (unlikely(tracing_selftest_running || tracing_disabled)) - return 0; - - trace_ctx = tracing_gen_ctx(); - buffer = tr->array_buffer.buffer; - - guard(ring_buffer_nest)(buffer); - event = __trace_buffer_lock_reserve(buffer, TRACE_BPUTS, size, - trace_ctx); - if (!event) - return 0; - - entry = ring_buffer_event_data(event); - entry->ip = ip; - entry->str = str; - - __buffer_unlock_commit(buffer, event); - ftrace_trace_stack(tr, buffer, trace_ctx, 4, NULL); - - return 1; -} -EXPORT_SYMBOL_GPL(__trace_bputs); - #ifdef CONFIG_TRACER_SNAPSHOT static void tracing_snapshot_instance_cond(struct trace_array *tr, void *cond_data) @@ -3159,324 +3046,6 @@ void trace_last_func_repeats(struct trace_array *tr, __buffer_unlock_commit(buffer, event); } -/* created for use with alloc_percpu */ -struct trace_buffer_struct { - int nesting; - char buffer[4][TRACE_BUF_SIZE]; -}; - -static struct trace_buffer_struct __percpu *trace_percpu_buffer; - -/* - * This allows for lockless recording. If we're nested too deeply, then - * this returns NULL. - */ -static char *get_trace_buf(void) -{ - struct trace_buffer_struct *buffer = this_cpu_ptr(trace_percpu_buffer); - - if (!trace_percpu_buffer || buffer->nesting >= 4) - return NULL; - - buffer->nesting++; - - /* Interrupts must see nesting incremented before we use the buffer */ - barrier(); - return &buffer->buffer[buffer->nesting - 1][0]; -} - -static void put_trace_buf(void) -{ - /* Don't let the decrement of nesting leak before this */ - barrier(); - this_cpu_dec(trace_percpu_buffer->nesting); -} - -static int alloc_percpu_trace_buffer(void) -{ - struct trace_buffer_struct __percpu *buffers; - - if (trace_percpu_buffer) - return 0; - - buffers = alloc_percpu(struct trace_buffer_struct); - if (MEM_FAIL(!buffers, "Could not allocate percpu trace_printk buffer")) - return -ENOMEM; - - trace_percpu_buffer = buffers; - return 0; -} - -static int buffers_allocated; - -void trace_printk_init_buffers(void) -{ - if (buffers_allocated) - return; - - if (alloc_percpu_trace_buffer()) - return; - - /* trace_printk() is for debug use only. Don't use it in production. */ - - pr_warn("\n"); - pr_warn("**********************************************************\n"); - pr_warn("** NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE **\n"); - pr_warn("** **\n"); - pr_warn("** trace_printk() being used. Allocating extra memory. **\n"); - pr_warn("** **\n"); - pr_warn("** This means that this is a DEBUG kernel and it is **\n"); - pr_warn("** unsafe for production use. **\n"); - pr_warn("** **\n"); - pr_warn("** If you see this message and you are not debugging **\n"); - pr_warn("** the kernel, report this immediately to your vendor! **\n"); - pr_warn("** **\n"); - pr_warn("** NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE **\n"); - pr_warn("**********************************************************\n"); - - /* Expand the buffers to set size */ - if (tracing_update_buffers(NULL) < 0) - pr_err("Failed to expand tracing buffers for trace_printk() calls\n"); - else - buffers_allocated = 1; - - /* - * trace_printk_init_buffers() can be called by modules. - * If that happens, then we need to start cmdline recording - * directly here. - */ - if (system_state == SYSTEM_RUNNING) - tracing_start_cmdline_record(); -} -EXPORT_SYMBOL_GPL(trace_printk_init_buffers); - -void trace_printk_start_comm(void) -{ - /* Start tracing comms if trace printk is set */ - if (!buffers_allocated) - return; - tracing_start_cmdline_record(); -} - -static void trace_printk_start_stop_comm(int enabled) -{ - if (!buffers_allocated) - return; - - if (enabled) - tracing_start_cmdline_record(); - else - tracing_stop_cmdline_record(); -} - -/** - * trace_vbprintk - write binary msg to tracing buffer - * @ip: The address of the caller - * @fmt: The string format to write to the buffer - * @args: Arguments for @fmt - */ -int trace_vbprintk(unsigned long ip, const char *fmt, va_list args) -{ - struct ring_buffer_event *event; - struct trace_buffer *buffer; - struct trace_array *tr = READ_ONCE(printk_trace); - struct bprint_entry *entry; - unsigned int trace_ctx; - char *tbuffer; - int len = 0, size; - - if (!printk_binsafe(tr)) - return trace_vprintk(ip, fmt, args); - - if (unlikely(tracing_selftest_running || tracing_disabled)) - return 0; - - /* Don't pollute graph traces with trace_vprintk internals */ - pause_graph_tracing(); - - trace_ctx = tracing_gen_ctx(); - guard(preempt_notrace)(); - - tbuffer = get_trace_buf(); - if (!tbuffer) { - len = 0; - goto out_nobuffer; - } - - len = vbin_printf((u32 *)tbuffer, TRACE_BUF_SIZE/sizeof(int), fmt, args); - - if (len > TRACE_BUF_SIZE/sizeof(int) || len < 0) - goto out_put; - - size = sizeof(*entry) + sizeof(u32) * len; - buffer = tr->array_buffer.buffer; - scoped_guard(ring_buffer_nest, buffer) { - event = __trace_buffer_lock_reserve(buffer, TRACE_BPRINT, size, - trace_ctx); - if (!event) - goto out_put; - entry = ring_buffer_event_data(event); - entry->ip = ip; - entry->fmt = fmt; - - memcpy(entry->buf, tbuffer, sizeof(u32) * len); - __buffer_unlock_commit(buffer, event); - ftrace_trace_stack(tr, buffer, trace_ctx, 6, NULL); - } -out_put: - put_trace_buf(); - -out_nobuffer: - unpause_graph_tracing(); - - return len; -} -EXPORT_SYMBOL_GPL(trace_vbprintk); - -static __printf(3, 0) -int __trace_array_vprintk(struct trace_buffer *buffer, - unsigned long ip, const char *fmt, va_list args) -{ - struct ring_buffer_event *event; - int len = 0, size; - struct print_entry *entry; - unsigned int trace_ctx; - char *tbuffer; - - if (unlikely(tracing_disabled)) - return 0; - - /* Don't pollute graph traces with trace_vprintk internals */ - pause_graph_tracing(); - - trace_ctx = tracing_gen_ctx(); - guard(preempt_notrace)(); - - - tbuffer = get_trace_buf(); - if (!tbuffer) { - len = 0; - goto out_nobuffer; - } - - len = vscnprintf(tbuffer, TRACE_BUF_SIZE, fmt, args); - - size = sizeof(*entry) + len + 1; - scoped_guard(ring_buffer_nest, buffer) { - event = __trace_buffer_lock_reserve(buffer, TRACE_PRINT, size, - trace_ctx); - if (!event) - goto out; - entry = ring_buffer_event_data(event); - entry->ip = ip; - - memcpy(&entry->buf, tbuffer, len + 1); - __buffer_unlock_commit(buffer, event); - ftrace_trace_stack(printk_trace, buffer, trace_ctx, 6, NULL); - } -out: - put_trace_buf(); - -out_nobuffer: - unpause_graph_tracing(); - - return len; -} - -int trace_array_vprintk(struct trace_array *tr, - unsigned long ip, const char *fmt, va_list args) -{ - if (tracing_selftest_running && (tr->flags & TRACE_ARRAY_FL_GLOBAL)) - return 0; - - return __trace_array_vprintk(tr->array_buffer.buffer, ip, fmt, args); -} - -/** - * trace_array_printk - Print a message to a specific instance - * @tr: The instance trace_array descriptor - * @ip: The instruction pointer that this is called from. - * @fmt: The format to print (printf format) - * - * If a subsystem sets up its own instance, they have the right to - * printk strings into their tracing instance buffer using this - * function. Note, this function will not write into the top level - * buffer (use trace_printk() for that), as writing into the top level - * buffer should only have events that can be individually disabled. - * trace_printk() is only used for debugging a kernel, and should not - * be ever incorporated in normal use. - * - * trace_array_printk() can be used, as it will not add noise to the - * top level tracing buffer. - * - * Note, trace_array_init_printk() must be called on @tr before this - * can be used. - */ -int trace_array_printk(struct trace_array *tr, - unsigned long ip, const char *fmt, ...) -{ - int ret; - va_list ap; - - if (!tr) - return -ENOENT; - - /* This is only allowed for created instances */ - if (tr->flags & TRACE_ARRAY_FL_GLOBAL) - return 0; - - if (!(tr->trace_flags & TRACE_ITER(PRINTK))) - return 0; - - va_start(ap, fmt); - ret = trace_array_vprintk(tr, ip, fmt, ap); - va_end(ap); - return ret; -} -EXPORT_SYMBOL_GPL(trace_array_printk); - -/** - * trace_array_init_printk - Initialize buffers for trace_array_printk() - * @tr: The trace array to initialize the buffers for - * - * As trace_array_printk() only writes into instances, they are OK to - * have in the kernel (unlike trace_printk()). This needs to be called - * before trace_array_printk() can be used on a trace_array. - */ -int trace_array_init_printk(struct trace_array *tr) -{ - if (!tr) - return -ENOENT; - - /* This is only allowed for created instances */ - if (tr->flags & TRACE_ARRAY_FL_GLOBAL) - return -EINVAL; - - return alloc_percpu_trace_buffer(); -} -EXPORT_SYMBOL_GPL(trace_array_init_printk); - -int trace_array_printk_buf(struct trace_buffer *buffer, - unsigned long ip, const char *fmt, ...) -{ - int ret; - va_list ap; - - if (!(printk_trace->trace_flags & TRACE_ITER(PRINTK))) - return 0; - - va_start(ap, fmt); - ret = __trace_array_vprintk(buffer, ip, fmt, ap); - va_end(ap); - return ret; -} - -int trace_vprintk(unsigned long ip, const char *fmt, va_list args) -{ - return trace_array_vprintk(printk_trace, ip, fmt, args); -} -EXPORT_SYMBOL_GPL(trace_vprintk); - static void trace_iterator_increment(struct trace_iterator *iter) { struct ring_buffer_iter *buf_iter = trace_buffer_iter(iter, iter->cpu); diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 921e4daa2825..6b0fedf2f532 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -2131,6 +2131,7 @@ extern const char *__stop___tracepoint_str[]; void trace_printk_control(bool enabled); void trace_printk_start_comm(void); +void trace_printk_start_stop_comm(int enabled); int trace_keep_overwrite(struct tracer *tracer, u64 mask, int set); int set_tracer_flag(struct trace_array *tr, u64 mask, int enabled); diff --git a/kernel/trace/trace_printk.c b/kernel/trace/trace_printk.c index 29f6e95439b6..c9cb74a33b3c 100644 --- a/kernel/trace/trace_printk.c +++ b/kernel/trace/trace_printk.c @@ -376,6 +376,437 @@ static const struct file_operations ftrace_formats_fops = { .release = seq_release, }; +static __always_inline bool printk_binsafe(struct trace_array *tr) +{ + /* + * The binary format of traceprintk can cause a crash if used + * by a buffer from another boot. Force the use of the + * non binary version of trace_printk if the trace_printk + * buffer is a boot mapped ring buffer. + */ + return !(tr->flags & TRACE_ARRAY_FL_BOOT); +} + +int __trace_array_puts(struct trace_array *tr, unsigned long ip, + const char *str, int size) +{ + struct ring_buffer_event *event; + struct trace_buffer *buffer; + struct print_entry *entry; + unsigned int trace_ctx; + int alloc; + + if (!(tr->trace_flags & TRACE_ITER(PRINTK))) + return 0; + + if (unlikely(tracing_selftest_running && + (tr->flags & TRACE_ARRAY_FL_GLOBAL))) + return 0; + + if (unlikely(tracing_disabled)) + return 0; + + alloc = sizeof(*entry) + size + 2; /* possible \n added */ + + trace_ctx = tracing_gen_ctx(); + buffer = tr->array_buffer.buffer; + guard(ring_buffer_nest)(buffer); + event = __trace_buffer_lock_reserve(buffer, TRACE_PRINT, alloc, + trace_ctx); + if (!event) + return 0; + + entry = ring_buffer_event_data(event); + entry->ip = ip; + + memcpy(&entry->buf, str, size); + + /* Add a newline if necessary */ + if (entry->buf[size - 1] != '\n') { + entry->buf[size] = '\n'; + entry->buf[size + 1] = '\0'; + } else + entry->buf[size] = '\0'; + + __buffer_unlock_commit(buffer, event); + ftrace_trace_stack(tr, buffer, trace_ctx, 4, NULL); + return size; +} +EXPORT_SYMBOL_GPL(__trace_array_puts); + +/** + * __trace_puts - write a constant string into the trace buffer. + * @ip: The address of the caller + * @str: The constant string to write + * @size: The size of the string. + */ +int __trace_puts(unsigned long ip, const char *str, int size) +{ + return __trace_array_puts(printk_trace, ip, str, size); +} +EXPORT_SYMBOL_GPL(__trace_puts); + +/** + * __trace_bputs - write the pointer to a constant string into trace buffer + * @ip: The address of the caller + * @str: The constant string to write to the buffer to + */ +int __trace_bputs(unsigned long ip, const char *str) +{ + struct trace_array *tr = READ_ONCE(printk_trace); + struct ring_buffer_event *event; + struct trace_buffer *buffer; + struct bputs_entry *entry; + unsigned int trace_ctx; + int size = sizeof(struct bputs_entry); + + if (!printk_binsafe(tr)) + return __trace_puts(ip, str, strlen(str)); + + if (!(tr->trace_flags & TRACE_ITER(PRINTK))) + return 0; + + if (unlikely(tracing_selftest_running || tracing_disabled)) + return 0; + + trace_ctx = tracing_gen_ctx(); + buffer = tr->array_buffer.buffer; + + guard(ring_buffer_nest)(buffer); + event = __trace_buffer_lock_reserve(buffer, TRACE_BPUTS, size, + trace_ctx); + if (!event) + return 0; + + entry = ring_buffer_event_data(event); + entry->ip = ip; + entry->str = str; + + __buffer_unlock_commit(buffer, event); + ftrace_trace_stack(tr, buffer, trace_ctx, 4, NULL); + + return 1; +} +EXPORT_SYMBOL_GPL(__trace_bputs); + +/* created for use with alloc_percpu */ +struct trace_buffer_struct { + int nesting; + char buffer[4][TRACE_BUF_SIZE]; +}; + +static struct trace_buffer_struct __percpu *trace_percpu_buffer; + +/* + * This allows for lockless recording. If we're nested too deeply, then + * this returns NULL. + */ +static char *get_trace_buf(void) +{ + struct trace_buffer_struct *buffer = this_cpu_ptr(trace_percpu_buffer); + + if (!trace_percpu_buffer || buffer->nesting >= 4) + return NULL; + + buffer->nesting++; + + /* Interrupts must see nesting incremented before we use the buffer */ + barrier(); + return &buffer->buffer[buffer->nesting - 1][0]; +} + +static void put_trace_buf(void) +{ + /* Don't let the decrement of nesting leak before this */ + barrier(); + this_cpu_dec(trace_percpu_buffer->nesting); +} + +static int alloc_percpu_trace_buffer(void) +{ + struct trace_buffer_struct __percpu *buffers; + + if (trace_percpu_buffer) + return 0; + + buffers = alloc_percpu(struct trace_buffer_struct); + if (MEM_FAIL(!buffers, "Could not allocate percpu trace_printk buffer")) + return -ENOMEM; + + trace_percpu_buffer = buffers; + return 0; +} + +static int buffers_allocated; + +void trace_printk_init_buffers(void) +{ + if (buffers_allocated) + return; + + if (alloc_percpu_trace_buffer()) + return; + + /* trace_printk() is for debug use only. Don't use it in production. */ + + pr_warn("\n"); + pr_warn("**********************************************************\n"); + pr_warn("** NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE **\n"); + pr_warn("** **\n"); + pr_warn("** trace_printk() being used. Allocating extra memory. **\n"); + pr_warn("** **\n"); + pr_warn("** This means that this is a DEBUG kernel and it is **\n"); + pr_warn("** unsafe for production use. **\n"); + pr_warn("** **\n"); + pr_warn("** If you see this message and you are not debugging **\n"); + pr_warn("** the kernel, report this immediately to your vendor! **\n"); + pr_warn("** **\n"); + pr_warn("** NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE **\n"); + pr_warn("**********************************************************\n"); + + /* Expand the buffers to set size */ + if (tracing_update_buffers(NULL) < 0) + pr_err("Failed to expand tracing buffers for trace_printk() calls\n"); + else + buffers_allocated = 1; + + /* + * trace_printk_init_buffers() can be called by modules. + * If that happens, then we need to start cmdline recording + * directly here. + */ + if (system_state == SYSTEM_RUNNING) + tracing_start_cmdline_record(); +} +EXPORT_SYMBOL_GPL(trace_printk_init_buffers); + +void trace_printk_start_comm(void) +{ + /* Start tracing comms if trace printk is set */ + if (!buffers_allocated) + return; + tracing_start_cmdline_record(); +} + +void trace_printk_start_stop_comm(int enabled) +{ + if (!buffers_allocated) + return; + + if (enabled) + tracing_start_cmdline_record(); + else + tracing_stop_cmdline_record(); +} + +/** + * trace_vbprintk - write binary msg to tracing buffer + * @ip: The address of the caller + * @fmt: The string format to write to the buffer + * @args: Arguments for @fmt + */ +int trace_vbprintk(unsigned long ip, const char *fmt, va_list args) +{ + struct ring_buffer_event *event; + struct trace_buffer *buffer; + struct trace_array *tr = READ_ONCE(printk_trace); + struct bprint_entry *entry; + unsigned int trace_ctx; + char *tbuffer; + int len = 0, size; + + if (!printk_binsafe(tr)) + return trace_vprintk(ip, fmt, args); + + if (unlikely(tracing_selftest_running || tracing_disabled)) + return 0; + + /* Don't pollute graph traces with trace_vprintk internals */ + pause_graph_tracing(); + + trace_ctx = tracing_gen_ctx(); + guard(preempt_notrace)(); + + tbuffer = get_trace_buf(); + if (!tbuffer) { + len = 0; + goto out_nobuffer; + } + + len = vbin_printf((u32 *)tbuffer, TRACE_BUF_SIZE/sizeof(int), fmt, args); + + if (len > TRACE_BUF_SIZE/sizeof(int) || len < 0) + goto out_put; + + size = sizeof(*entry) + sizeof(u32) * len; + buffer = tr->array_buffer.buffer; + scoped_guard(ring_buffer_nest, buffer) { + event = __trace_buffer_lock_reserve(buffer, TRACE_BPRINT, size, + trace_ctx); + if (!event) + goto out_put; + entry = ring_buffer_event_data(event); + entry->ip = ip; + entry->fmt = fmt; + + memcpy(entry->buf, tbuffer, sizeof(u32) * len); + __buffer_unlock_commit(buffer, event); + ftrace_trace_stack(tr, buffer, trace_ctx, 6, NULL); + } +out_put: + put_trace_buf(); + +out_nobuffer: + unpause_graph_tracing(); + + return len; +} +EXPORT_SYMBOL_GPL(trace_vbprintk); + +static __printf(3, 0) +int __trace_array_vprintk(struct trace_buffer *buffer, + unsigned long ip, const char *fmt, va_list args) +{ + struct ring_buffer_event *event; + int len = 0, size; + struct print_entry *entry; + unsigned int trace_ctx; + char *tbuffer; + + if (unlikely(tracing_disabled)) + return 0; + + /* Don't pollute graph traces with trace_vprintk internals */ + pause_graph_tracing(); + + trace_ctx = tracing_gen_ctx(); + guard(preempt_notrace)(); + + + tbuffer = get_trace_buf(); + if (!tbuffer) { + len = 0; + goto out_nobuffer; + } + + len = vscnprintf(tbuffer, TRACE_BUF_SIZE, fmt, args); + + size = sizeof(*entry) + len + 1; + scoped_guard(ring_buffer_nest, buffer) { + event = __trace_buffer_lock_reserve(buffer, TRACE_PRINT, size, + trace_ctx); + if (!event) + goto out; + entry = ring_buffer_event_data(event); + entry->ip = ip; + + memcpy(&entry->buf, tbuffer, len + 1); + __buffer_unlock_commit(buffer, event); + ftrace_trace_stack(printk_trace, buffer, trace_ctx, 6, NULL); + } +out: + put_trace_buf(); + +out_nobuffer: + unpause_graph_tracing(); + + return len; +} + +int trace_array_vprintk(struct trace_array *tr, + unsigned long ip, const char *fmt, va_list args) +{ + if (tracing_selftest_running && (tr->flags & TRACE_ARRAY_FL_GLOBAL)) + return 0; + + return __trace_array_vprintk(tr->array_buffer.buffer, ip, fmt, args); +} + +/** + * trace_array_printk - Print a message to a specific instance + * @tr: The instance trace_array descriptor + * @ip: The instruction pointer that this is called from. + * @fmt: The format to print (printf format) + * + * If a subsystem sets up its own instance, they have the right to + * printk strings into their tracing instance buffer using this + * function. Note, this function will not write into the top level + * buffer (use trace_printk() for that), as writing into the top level + * buffer should only have events that can be individually disabled. + * trace_printk() is only used for debugging a kernel, and should not + * be ever incorporated in normal use. + * + * trace_array_printk() can be used, as it will not add noise to the + * top level tracing buffer. + * + * Note, trace_array_init_printk() must be called on @tr before this + * can be used. + */ +int trace_array_printk(struct trace_array *tr, + unsigned long ip, const char *fmt, ...) +{ + int ret; + va_list ap; + + if (!tr) + return -ENOENT; + + /* This is only allowed for created instances */ + if (tr->flags & TRACE_ARRAY_FL_GLOBAL) + return 0; + + if (!(tr->trace_flags & TRACE_ITER(PRINTK))) + return 0; + + va_start(ap, fmt); + ret = trace_array_vprintk(tr, ip, fmt, ap); + va_end(ap); + return ret; +} +EXPORT_SYMBOL_GPL(trace_array_printk); + +/** + * trace_array_init_printk - Initialize buffers for trace_array_printk() + * @tr: The trace array to initialize the buffers for + * + * As trace_array_printk() only writes into instances, they are OK to + * have in the kernel (unlike trace_printk()). This needs to be called + * before trace_array_printk() can be used on a trace_array. + */ +int trace_array_init_printk(struct trace_array *tr) +{ + if (!tr) + return -ENOENT; + + /* This is only allowed for created instances */ + if (tr->flags & TRACE_ARRAY_FL_GLOBAL) + return -EINVAL; + + return alloc_percpu_trace_buffer(); +} +EXPORT_SYMBOL_GPL(trace_array_init_printk); + +int trace_array_printk_buf(struct trace_buffer *buffer, + unsigned long ip, const char *fmt, ...) +{ + int ret; + va_list ap; + + if (!(printk_trace->trace_flags & TRACE_ITER(PRINTK))) + return 0; + + va_start(ap, fmt); + ret = __trace_array_vprintk(buffer, ip, fmt, ap); + va_end(ap); + return ret; +} + +int trace_vprintk(unsigned long ip, const char *fmt, va_list args) +{ + return trace_array_vprintk(printk_trace, ip, fmt, args); +} +EXPORT_SYMBOL_GPL(trace_vprintk); + static __init int init_trace_printk_function_export(void) { int ret; -- cgit v1.2.3 From 694b3f6fe0b6c86ff75e94302708f5a718027297 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Sun, 8 Feb 2026 13:38:33 -0500 Subject: tracing: Rename trace_array field max_buffer to snapshot_buffer When tracing was first added, there were latency tracers that would take a snapshot of the current trace when a new max latency was hit. This snapshot buffer was called "max_buffer". Since then, a snapshot feature was added that allowed user space or event triggers to trigger a snapshot of the current buffer using the same max_buffer of the trace_array. As this snapshot buffer now has a more generic use case, calling it "max_buffer" is confusing. Rename it to snapshot_buffer. Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Andrew Morton Link: https://patch.msgid.link/20260208183856.428446729@kernel.org Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace.c | 72 +++++++++++++++++++++---------------------- kernel/trace/trace.h | 13 ++++---- kernel/trace/trace_selftest.c | 10 +++--- 3 files changed, 48 insertions(+), 47 deletions(-) (limited to 'kernel/trace/trace.h') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 551a452befa0..98524d0656bf 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -934,12 +934,12 @@ int tracing_alloc_snapshot_instance(struct trace_array *tr) /* Make the snapshot buffer have the same order as main buffer */ order = ring_buffer_subbuf_order_get(tr->array_buffer.buffer); - ret = ring_buffer_subbuf_order_set(tr->max_buffer.buffer, order); + ret = ring_buffer_subbuf_order_set(tr->snapshot_buffer.buffer, order); if (ret < 0) return ret; /* allocate spare buffer */ - ret = resize_buffer_duplicate_size(&tr->max_buffer, + ret = resize_buffer_duplicate_size(&tr->snapshot_buffer, &tr->array_buffer, RING_BUFFER_ALL_CPUS); if (ret < 0) return ret; @@ -957,10 +957,10 @@ static void free_snapshot(struct trace_array *tr) * The max_tr ring buffer has some state (e.g. ring->clock) and * we want preserve it. */ - ring_buffer_subbuf_order_set(tr->max_buffer.buffer, 0); - ring_buffer_resize(tr->max_buffer.buffer, 1, RING_BUFFER_ALL_CPUS); - set_buffer_entries(&tr->max_buffer, 1); - tracing_reset_online_cpus(&tr->max_buffer); + ring_buffer_subbuf_order_set(tr->snapshot_buffer.buffer, 0); + ring_buffer_resize(tr->snapshot_buffer.buffer, 1, RING_BUFFER_ALL_CPUS); + set_buffer_entries(&tr->snapshot_buffer, 1); + tracing_reset_online_cpus(&tr->snapshot_buffer); tr->allocated_snapshot = false; } @@ -1556,7 +1556,7 @@ static void __update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu) { struct array_buffer *trace_buf = &tr->array_buffer; - struct array_buffer *max_buf = &tr->max_buffer; + struct array_buffer *max_buf = &tr->snapshot_buffer; struct trace_array_cpu *data = per_cpu_ptr(trace_buf->data, cpu); struct trace_array_cpu *max_data = per_cpu_ptr(max_buf->data, cpu); @@ -1616,9 +1616,9 @@ update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu, /* Inherit the recordable setting from array_buffer */ if (ring_buffer_record_is_set_on(tr->array_buffer.buffer)) - ring_buffer_record_on(tr->max_buffer.buffer); + ring_buffer_record_on(tr->snapshot_buffer.buffer); else - ring_buffer_record_off(tr->max_buffer.buffer); + ring_buffer_record_off(tr->snapshot_buffer.buffer); #ifdef CONFIG_TRACER_SNAPSHOT if (tr->cond_snapshot && !tr->cond_snapshot->update(tr, cond_data)) { @@ -1626,7 +1626,7 @@ update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu, return; } #endif - swap(tr->array_buffer.buffer, tr->max_buffer.buffer); + swap(tr->array_buffer.buffer, tr->snapshot_buffer.buffer); __update_max_tr(tr, tsk, cpu); @@ -1661,7 +1661,7 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu) arch_spin_lock(&tr->max_lock); - ret = ring_buffer_swap_cpu(tr->max_buffer.buffer, tr->array_buffer.buffer, cpu); + ret = ring_buffer_swap_cpu(tr->snapshot_buffer.buffer, tr->array_buffer.buffer, cpu); if (ret == -EBUSY) { /* @@ -1671,7 +1671,7 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu) * and flag that it failed. * Another reason is resize is in progress. */ - trace_array_printk_buf(tr->max_buffer.buffer, _THIS_IP_, + trace_array_printk_buf(tr->snapshot_buffer.buffer, _THIS_IP_, "Failed to swap buffers due to commit or resize in progress\n"); } @@ -1722,7 +1722,7 @@ static int wait_on_pipe(struct trace_iterator *iter, int full) * to happen, this would now be the main buffer. */ if (iter->snapshot) - iter->array_buffer = &iter->tr->max_buffer; + iter->array_buffer = &iter->tr->snapshot_buffer; #endif return ret; } @@ -1790,7 +1790,7 @@ static int run_tracer_selftest(struct tracer *type) if (type->use_max_tr) { /* If we expanded the buffers, make sure the max is expanded too */ if (tr->ring_buffer_expanded) - ring_buffer_resize(tr->max_buffer.buffer, trace_buf_size, + ring_buffer_resize(tr->snapshot_buffer.buffer, trace_buf_size, RING_BUFFER_ALL_CPUS); tr->allocated_snapshot = true; } @@ -1817,7 +1817,7 @@ static int run_tracer_selftest(struct tracer *type) /* Shrink the max buffer again */ if (tr->ring_buffer_expanded) - ring_buffer_resize(tr->max_buffer.buffer, 1, + ring_buffer_resize(tr->snapshot_buffer.buffer, 1, RING_BUFFER_ALL_CPUS); } #endif @@ -2060,7 +2060,7 @@ void tracing_reset_all_online_cpus_unlocked(void) tr->clear_trace = false; tracing_reset_online_cpus(&tr->array_buffer); #ifdef CONFIG_TRACER_MAX_TRACE - tracing_reset_online_cpus(&tr->max_buffer); + tracing_reset_online_cpus(&tr->snapshot_buffer); #endif } } @@ -2100,7 +2100,7 @@ static void tracing_start_tr(struct trace_array *tr) ring_buffer_record_enable(buffer); #ifdef CONFIG_TRACER_MAX_TRACE - buffer = tr->max_buffer.buffer; + buffer = tr->snapshot_buffer.buffer; if (buffer) ring_buffer_record_enable(buffer); #endif @@ -2136,7 +2136,7 @@ static void tracing_stop_tr(struct trace_array *tr) ring_buffer_record_disable(buffer); #ifdef CONFIG_TRACER_MAX_TRACE - buffer = tr->max_buffer.buffer; + buffer = tr->snapshot_buffer.buffer; if (buffer) ring_buffer_record_disable(buffer); #endif @@ -3943,7 +3943,7 @@ __tracing_open(struct inode *inode, struct file *file, bool snapshot) #ifdef CONFIG_TRACER_MAX_TRACE /* Currently only the top directory has a snapshot */ if (tr->current_trace->print_max || snapshot) - iter->array_buffer = &tr->max_buffer; + iter->array_buffer = &tr->snapshot_buffer; else #endif iter->array_buffer = &tr->array_buffer; @@ -4146,7 +4146,7 @@ static int tracing_open(struct inode *inode, struct file *file) #ifdef CONFIG_TRACER_MAX_TRACE if (tr->current_trace->print_max) - trace_buf = &tr->max_buffer; + trace_buf = &tr->snapshot_buffer; #endif if (cpu == RING_BUFFER_ALL_CPUS) @@ -4359,14 +4359,14 @@ int tracing_set_cpumask(struct trace_array *tr, !cpumask_test_cpu(cpu, tracing_cpumask_new)) { ring_buffer_record_disable_cpu(tr->array_buffer.buffer, cpu); #ifdef CONFIG_TRACER_MAX_TRACE - ring_buffer_record_disable_cpu(tr->max_buffer.buffer, cpu); + ring_buffer_record_disable_cpu(tr->snapshot_buffer.buffer, cpu); #endif } if (!cpumask_test_cpu(cpu, tr->tracing_cpumask) && cpumask_test_cpu(cpu, tracing_cpumask_new)) { ring_buffer_record_enable_cpu(tr->array_buffer.buffer, cpu); #ifdef CONFIG_TRACER_MAX_TRACE - ring_buffer_record_enable_cpu(tr->max_buffer.buffer, cpu); + ring_buffer_record_enable_cpu(tr->snapshot_buffer.buffer, cpu); #endif } } @@ -4576,7 +4576,7 @@ int set_tracer_flag(struct trace_array *tr, u64 mask, int enabled) case TRACE_ITER(OVERWRITE): ring_buffer_change_overwrite(tr->array_buffer.buffer, enabled); #ifdef CONFIG_TRACER_MAX_TRACE - ring_buffer_change_overwrite(tr->max_buffer.buffer, enabled); + ring_buffer_change_overwrite(tr->snapshot_buffer.buffer, enabled); #endif break; @@ -5294,7 +5294,7 @@ static int __tracing_resize_ring_buffer(struct trace_array *tr, if (!tr->allocated_snapshot) goto out; - ret = ring_buffer_resize(tr->max_buffer.buffer, size, cpu); + ret = ring_buffer_resize(tr->snapshot_buffer.buffer, size, cpu); if (ret < 0) { int r = resize_buffer_duplicate_size(&tr->array_buffer, &tr->array_buffer, cpu); @@ -5319,7 +5319,7 @@ static int __tracing_resize_ring_buffer(struct trace_array *tr, goto out_start; } - update_buffer_entries(&tr->max_buffer, cpu); + update_buffer_entries(&tr->snapshot_buffer, cpu); out: #endif /* CONFIG_TRACER_MAX_TRACE */ @@ -7036,9 +7036,9 @@ int tracing_set_clock(struct trace_array *tr, const char *clockstr) tracing_reset_online_cpus(&tr->array_buffer); #ifdef CONFIG_TRACER_MAX_TRACE - if (tr->max_buffer.buffer) - ring_buffer_set_clock(tr->max_buffer.buffer, trace_clocks[i].func); - tracing_reset_online_cpus(&tr->max_buffer); + if (tr->snapshot_buffer.buffer) + ring_buffer_set_clock(tr->snapshot_buffer.buffer, trace_clocks[i].func); + tracing_reset_online_cpus(&tr->snapshot_buffer); #endif if (tr->scratch && !(tr->flags & TRACE_ARRAY_FL_LAST_BOOT)) { @@ -7170,7 +7170,7 @@ static int tracing_snapshot_open(struct inode *inode, struct file *file) ret = 0; iter->tr = tr; - iter->array_buffer = &tr->max_buffer; + iter->array_buffer = &tr->snapshot_buffer; iter->cpu_file = tracing_get_cpu(inode); m->private = iter; file->private_data = m; @@ -7233,7 +7233,7 @@ tracing_snapshot_write(struct file *filp, const char __user *ubuf, size_t cnt, return -EINVAL; #endif if (tr->allocated_snapshot) - ret = resize_buffer_duplicate_size(&tr->max_buffer, + ret = resize_buffer_duplicate_size(&tr->snapshot_buffer, &tr->array_buffer, iter->cpu_file); ret = tracing_arm_snapshot_locked(tr); @@ -7254,9 +7254,9 @@ tracing_snapshot_write(struct file *filp, const char __user *ubuf, size_t cnt, default: if (tr->allocated_snapshot) { if (iter->cpu_file == RING_BUFFER_ALL_CPUS) - tracing_reset_online_cpus(&tr->max_buffer); + tracing_reset_online_cpus(&tr->snapshot_buffer); else - tracing_reset_cpu(&tr->max_buffer, iter->cpu_file); + tracing_reset_cpu(&tr->snapshot_buffer, iter->cpu_file); } break; } @@ -7312,7 +7312,7 @@ static int snapshot_raw_open(struct inode *inode, struct file *filp) } info->iter.snapshot = true; - info->iter.array_buffer = &info->iter.tr->max_buffer; + info->iter.array_buffer = &info->iter.tr->snapshot_buffer; return ret; } @@ -9195,7 +9195,7 @@ buffer_subbuf_size_write(struct file *filp, const char __user *ubuf, if (!tr->allocated_snapshot) goto out_max; - ret = ring_buffer_subbuf_order_set(tr->max_buffer.buffer, order); + ret = ring_buffer_subbuf_order_set(tr->snapshot_buffer.buffer, order); if (ret) { /* Put back the old order */ cnt = ring_buffer_subbuf_order_set(tr->array_buffer.buffer, old_order); @@ -9416,7 +9416,7 @@ static int allocate_trace_buffers(struct trace_array *tr, int size) if (tr->range_addr_start) return 0; - ret = allocate_trace_buffer(tr, &tr->max_buffer, + ret = allocate_trace_buffer(tr, &tr->snapshot_buffer, allocate_snapshot ? size : 1); if (MEM_FAIL(ret, "Failed to allocate trace buffer\n")) { free_trace_buffer(&tr->array_buffer); @@ -9439,7 +9439,7 @@ static void free_trace_buffers(struct trace_array *tr) kfree(tr->module_delta); #ifdef CONFIG_TRACER_MAX_TRACE - free_trace_buffer(&tr->max_buffer); + free_trace_buffer(&tr->snapshot_buffer); #endif } diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 6b0fedf2f532..b50383aa8e50 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -331,17 +331,18 @@ struct trace_array { struct array_buffer array_buffer; #ifdef CONFIG_TRACER_MAX_TRACE /* - * The max_buffer is used to snapshot the trace when a maximum + * The snapshot_buffer is used to snapshot the trace when a maximum * latency is reached, or when the user initiates a snapshot. * Some tracers will use this to store a maximum trace while * it continues examining live traces. * - * The buffers for the max_buffer are set up the same as the array_buffer - * When a snapshot is taken, the buffer of the max_buffer is swapped - * with the buffer of the array_buffer and the buffers are reset for - * the array_buffer so the tracing can continue. + * The buffers for the snapshot_buffer are set up the same as the + * array_buffer. When a snapshot is taken, the buffer of the + * snapshot_buffer is swapped with the buffer of the array_buffer + * and the buffers are reset for the array_buffer so the tracing can + * continue. */ - struct array_buffer max_buffer; + struct array_buffer snapshot_buffer; bool allocated_snapshot; spinlock_t snapshot_trigger_lock; unsigned int snapshot; diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c index d88c44f1dfa5..be53fe6fee6a 100644 --- a/kernel/trace/trace_selftest.c +++ b/kernel/trace/trace_selftest.c @@ -1225,7 +1225,7 @@ trace_selftest_startup_irqsoff(struct tracer *trace, struct trace_array *tr) /* check both trace buffers */ ret = trace_test_buffer(&tr->array_buffer, NULL); if (!ret) - ret = trace_test_buffer(&tr->max_buffer, &count); + ret = trace_test_buffer(&tr->snapshot_buffer, &count); trace->reset(tr); tracing_start(); @@ -1287,7 +1287,7 @@ trace_selftest_startup_preemptoff(struct tracer *trace, struct trace_array *tr) /* check both trace buffers */ ret = trace_test_buffer(&tr->array_buffer, NULL); if (!ret) - ret = trace_test_buffer(&tr->max_buffer, &count); + ret = trace_test_buffer(&tr->snapshot_buffer, &count); trace->reset(tr); tracing_start(); @@ -1355,7 +1355,7 @@ trace_selftest_startup_preemptirqsoff(struct tracer *trace, struct trace_array * if (ret) goto out; - ret = trace_test_buffer(&tr->max_buffer, &count); + ret = trace_test_buffer(&tr->snapshot_buffer, &count); if (ret) goto out; @@ -1385,7 +1385,7 @@ trace_selftest_startup_preemptirqsoff(struct tracer *trace, struct trace_array * if (ret) goto out; - ret = trace_test_buffer(&tr->max_buffer, &count); + ret = trace_test_buffer(&tr->snapshot_buffer, &count); if (!ret && !count) { printk(KERN_CONT ".. no entries found .."); @@ -1513,7 +1513,7 @@ trace_selftest_startup_wakeup(struct tracer *trace, struct trace_array *tr) /* check both trace buffers */ ret = trace_test_buffer(&tr->array_buffer, NULL); if (!ret) - ret = trace_test_buffer(&tr->max_buffer, &count); + ret = trace_test_buffer(&tr->snapshot_buffer, &count); trace->reset(tr); -- cgit v1.2.3 From e4c1a09afbe2f02fc66b5ccbc96aa3a7109f9b79 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Sun, 8 Feb 2026 13:38:34 -0500 Subject: tracing: Add tracer_uses_snapshot() helper to remove #ifdefs Instead of having #ifdef CONFIG_TRACER_MAX_TRACE around every access to the struct tracer's use_max_tr field, add a helper function for that access and if CONFIG_TRACER_MAX_TRACE is not configured it just returns false. Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Andrew Morton Link: https://patch.msgid.link/20260208183856.599390238@kernel.org Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace.c | 51 ++++++++++++++++----------------------------------- kernel/trace/trace.h | 12 ++++++++++++ 2 files changed, 28 insertions(+), 35 deletions(-) (limited to 'kernel/trace/trace.h') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 98524d0656bf..405212166677 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -810,7 +810,6 @@ EXPORT_SYMBOL_GPL(tracing_on); static void tracing_snapshot_instance_cond(struct trace_array *tr, void *cond_data) { - struct tracer *tracer = tr->current_trace; unsigned long flags; if (in_nmi()) { @@ -827,7 +826,7 @@ static void tracing_snapshot_instance_cond(struct trace_array *tr, } /* Note, snapshot can not be used when the tracer uses it */ - if (tracer->use_max_tr) { + if (tracer_uses_snapshot(tr->current_trace)) { trace_array_puts(tr, "*** LATENCY TRACER ACTIVE ***\n"); trace_array_puts(tr, "*** Can not use snapshot (sorry) ***\n"); return; @@ -1076,7 +1075,7 @@ int tracing_snapshot_cond_enable(struct trace_array *tr, void *cond_data, guard(mutex)(&trace_types_lock); - if (tr->current_trace->use_max_tr) + if (tracer_uses_snapshot(tr->current_trace)) return -EBUSY; /* @@ -1787,7 +1786,7 @@ static int run_tracer_selftest(struct tracer *type) tr->current_trace_flags = type->flags ? : type->default_flags; #ifdef CONFIG_TRACER_MAX_TRACE - if (type->use_max_tr) { + if (tracer_uses_snapshot(type)) { /* If we expanded the buffers, make sure the max is expanded too */ if (tr->ring_buffer_expanded) ring_buffer_resize(tr->snapshot_buffer.buffer, trace_buf_size, @@ -1812,7 +1811,7 @@ static int run_tracer_selftest(struct tracer *type) tracing_reset_online_cpus(&tr->array_buffer); #ifdef CONFIG_TRACER_MAX_TRACE - if (type->use_max_tr) { + if (tracer_uses_snapshot(type)) { tr->allocated_snapshot = false; /* Shrink the max buffer again */ @@ -3240,10 +3239,8 @@ static void *s_start(struct seq_file *m, loff_t *pos) } mutex_unlock(&trace_types_lock); -#ifdef CONFIG_TRACER_MAX_TRACE - if (iter->snapshot && iter->trace->use_max_tr) + if (iter->snapshot && tracer_uses_snapshot(iter->trace)) return ERR_PTR(-EBUSY); -#endif if (*pos != iter->pos) { iter->ent = NULL; @@ -3282,10 +3279,8 @@ static void s_stop(struct seq_file *m, void *p) { struct trace_iterator *iter = m->private; -#ifdef CONFIG_TRACER_MAX_TRACE - if (iter->snapshot && iter->trace->use_max_tr) + if (iter->snapshot && tracer_uses_snapshot(iter->trace)) return; -#endif trace_access_unlock(iter->cpu_file); trace_event_read_unlock(); @@ -4177,11 +4172,9 @@ static int tracing_open(struct inode *inode, struct file *file) static bool trace_ok_for_array(struct tracer *t, struct trace_array *tr) { -#ifdef CONFIG_TRACER_SNAPSHOT /* arrays with mapped buffer range do not have snapshots */ - if (tr->range_addr_start && t->use_max_tr) + if (tr->range_addr_start && tracer_uses_snapshot(t)) return false; -#endif return (tr->flags & TRACE_ARRAY_FL_GLOBAL) || t->allow_instances; } @@ -5550,9 +5543,7 @@ int tracing_set_tracer(struct trace_array *tr, const char *buf) { struct tracer *trace = NULL; struct tracers *t; -#ifdef CONFIG_TRACER_MAX_TRACE bool had_max_tr; -#endif int ret; guard(mutex)(&trace_types_lock); @@ -5580,7 +5571,7 @@ int tracing_set_tracer(struct trace_array *tr, const char *buf) return 0; #ifdef CONFIG_TRACER_SNAPSHOT - if (trace->use_max_tr) { + if (tracer_uses_snapshot(trace)) { local_irq_disable(); arch_spin_lock(&tr->max_lock); ret = tr->cond_snapshot ? -EBUSY : 0; @@ -5612,14 +5603,13 @@ int tracing_set_tracer(struct trace_array *tr, const char *buf) if (tr->current_trace->reset) tr->current_trace->reset(tr); -#ifdef CONFIG_TRACER_MAX_TRACE - had_max_tr = tr->current_trace->use_max_tr; + had_max_tr = tracer_uses_snapshot(tr->current_trace); /* Current trace needs to be nop_trace before synchronize_rcu */ tr->current_trace = &nop_trace; tr->current_trace_flags = nop_trace.flags; - if (had_max_tr && !trace->use_max_tr) { + if (had_max_tr && !tracer_uses_snapshot(trace)) { /* * We need to make sure that the update_max_tr sees that * current_trace changed to nop_trace to keep it from @@ -5632,24 +5622,19 @@ int tracing_set_tracer(struct trace_array *tr, const char *buf) tracing_disarm_snapshot(tr); } - if (!had_max_tr && trace->use_max_tr) { + if (!had_max_tr && tracer_uses_snapshot(trace)) { ret = tracing_arm_snapshot_locked(tr); if (ret) return ret; } -#else - tr->current_trace = &nop_trace; -#endif tr->current_trace_flags = t->flags ? : t->tracer->flags; if (trace->init) { ret = tracer_init(trace, tr); if (ret) { -#ifdef CONFIG_TRACER_MAX_TRACE - if (trace->use_max_tr) + if (tracer_uses_snapshot(trace)) tracing_disarm_snapshot(tr); -#endif tr->current_trace_flags = nop_trace.flags; return ret; } @@ -7207,7 +7192,7 @@ tracing_snapshot_write(struct file *filp, const char __user *ubuf, size_t cnt, guard(mutex)(&trace_types_lock); - if (tr->current_trace->use_max_tr) + if (tracer_uses_snapshot(tr->current_trace)) return -EBUSY; local_irq_disable(); @@ -7306,7 +7291,7 @@ static int snapshot_raw_open(struct inode *inode, struct file *filp) info = filp->private_data; - if (info->iter.trace->use_max_tr) { + if (tracer_uses_snapshot(info->iter.trace)) { tracing_buffers_release(inode, filp); return -EBUSY; } @@ -7862,10 +7847,8 @@ tracing_buffers_read(struct file *filp, char __user *ubuf, if (!count) return 0; -#ifdef CONFIG_TRACER_MAX_TRACE - if (iter->snapshot && iter->tr->current_trace->use_max_tr) + if (iter->snapshot && tracer_uses_snapshot(iter->tr->current_trace)) return -EBUSY; -#endif page_size = ring_buffer_subbuf_size_get(iter->array_buffer->buffer); @@ -8049,10 +8032,8 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, int entries, i; ssize_t ret = 0; -#ifdef CONFIG_TRACER_MAX_TRACE - if (iter->snapshot && iter->tr->current_trace->use_max_tr) + if (iter->snapshot && tracer_uses_snapshot(iter->tr->current_trace)) return -EBUSY; -#endif page_size = ring_buffer_subbuf_size_get(iter->array_buffer->buffer); if (*ppos & (page_size - 1)) diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index b50383aa8e50..ebb47abc0ee7 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -817,6 +817,18 @@ static inline void __trace_stack(struct trace_array *tr, unsigned int trace_ctx, } #endif /* CONFIG_STACKTRACE */ +#ifdef CONFIG_TRACER_MAX_TRACE +static inline bool tracer_uses_snapshot(struct tracer *tracer) +{ + return tracer->use_max_tr; +} +#else +static inline bool tracer_uses_snapshot(struct tracer *tracer) +{ + return false; +} +#endif + void trace_last_func_repeats(struct trace_array *tr, struct trace_func_repeats *last_info, unsigned int trace_ctx); -- cgit v1.2.3 From c4f1fe47b106e9200cbb1b8951bd75f036d53bd3 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Sun, 8 Feb 2026 13:38:35 -0500 Subject: tracing: Better separate SNAPSHOT and MAX_TRACE options The latency tracers (scheduler, irqsoff, etc) were created when tracing was first added. These tracers required a "snapshot" buffer that was the same size as the ring buffer being written to. When a new max latency was hit, the main ring buffer would swap with the snapshot buffer so that the trace leading up to the latency would be saved in the snapshot buffer (The snapshot buffer is never written to directly and the data within it can be viewed without fear of being overwritten). Later, a new feature was added to allow snapshots to be taken by user space or even event triggers. This created a "snapshot" file that allowed users to trigger a snapshot from user space to save the current trace. The config for this new feature (CONFIG_TRACER_SNAPSHOT) would select the latency tracer config (CONFIG_TRACER_MAX_LATENCY) as it would need all the functionality from it as it already existed. But this was incorrect. As the snapshot feature is really what the latency tracers need and not the other way around. Have CONFIG_TRACER_MAX_TRACE select CONFIG_TRACER_SNAPSHOT where the tracers that needs the max latency buffer selects the TRACE_MAX_TRACE which will then select TRACER_SNAPSHOT. Also, go through trace.c and trace.h and make the code that only needs the TRACER_MAX_TRACE protected by that and the code that always requires the snapshot to be protected by TRACER_SNAPSHOT. Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Andrew Morton Link: https://patch.msgid.link/20260208183856.767870992@kernel.org Signed-off-by: Steven Rostedt (Google) --- kernel/trace/Kconfig | 8 +++--- kernel/trace/trace.c | 73 +++++++++++++++++++++++++++------------------------- kernel/trace/trace.h | 19 ++++++++------ 3 files changed, 53 insertions(+), 47 deletions(-) (limited to 'kernel/trace/trace.h') diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index bfa2ec46e075..bedb2f982823 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -133,6 +133,7 @@ config BUILDTIME_MCOUNT_SORT config TRACER_MAX_TRACE bool + select TRACER_SNAPSHOT config TRACE_CLOCK bool @@ -422,7 +423,6 @@ config IRQSOFF_TRACER select GENERIC_TRACER select TRACER_MAX_TRACE select RING_BUFFER_ALLOW_SWAP - select TRACER_SNAPSHOT select TRACER_SNAPSHOT_PER_CPU_SWAP help This option measures the time spent in irqs-off critical @@ -445,7 +445,6 @@ config PREEMPT_TRACER select GENERIC_TRACER select TRACER_MAX_TRACE select RING_BUFFER_ALLOW_SWAP - select TRACER_SNAPSHOT select TRACER_SNAPSHOT_PER_CPU_SWAP select TRACE_PREEMPT_TOGGLE help @@ -467,7 +466,6 @@ config SCHED_TRACER select GENERIC_TRACER select CONTEXT_SWITCH_TRACER select TRACER_MAX_TRACE - select TRACER_SNAPSHOT help This tracer tracks the latency of the highest priority task to be scheduled in, starting from the point it has woken up. @@ -617,7 +615,6 @@ config TRACE_SYSCALL_BUF_SIZE_DEFAULT config TRACER_SNAPSHOT bool "Create a snapshot trace buffer" - select TRACER_MAX_TRACE help Allow tracing users to take snapshot of the current buffer using the ftrace interface, e.g.: @@ -625,6 +622,9 @@ config TRACER_SNAPSHOT echo 1 > /sys/kernel/tracing/snapshot cat snapshot + Note, the latency tracers select this option. To disable it, + all the latency tracers need to be disabled. + config TRACER_SNAPSHOT_PER_CPU_SWAP bool "Allow snapshot to swap per CPU" depends on TRACER_SNAPSHOT diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 405212166677..845b8a165daf 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -825,15 +825,15 @@ static void tracing_snapshot_instance_cond(struct trace_array *tr, return; } - /* Note, snapshot can not be used when the tracer uses it */ - if (tracer_uses_snapshot(tr->current_trace)) { - trace_array_puts(tr, "*** LATENCY TRACER ACTIVE ***\n"); + if (tr->mapped) { + trace_array_puts(tr, "*** BUFFER MEMORY MAPPED ***\n"); trace_array_puts(tr, "*** Can not use snapshot (sorry) ***\n"); return; } - if (tr->mapped) { - trace_array_puts(tr, "*** BUFFER MEMORY MAPPED ***\n"); + /* Note, snapshot can not be used when the tracer uses it */ + if (tracer_uses_snapshot(tr->current_trace)) { + trace_array_puts(tr, "*** LATENCY TRACER ACTIVE ***\n"); trace_array_puts(tr, "*** Can not use snapshot (sorry) ***\n"); return; } @@ -1555,8 +1555,8 @@ static void __update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu) { struct array_buffer *trace_buf = &tr->array_buffer; - struct array_buffer *max_buf = &tr->snapshot_buffer; struct trace_array_cpu *data = per_cpu_ptr(trace_buf->data, cpu); + struct array_buffer *max_buf = &tr->snapshot_buffer; struct trace_array_cpu *max_data = per_cpu_ptr(max_buf->data, cpu); max_buf->cpu = cpu; @@ -1585,7 +1585,14 @@ __update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu) tracing_record_cmdline(tsk); latency_fsnotify(tr); } +#else +static inline void trace_create_maxlat_file(struct trace_array *tr, + struct dentry *d_tracer) { } +static inline void __update_max_tr(struct trace_array *tr, + struct task_struct *tsk, int cpu) { } +#endif /* CONFIG_TRACER_MAX_TRACE */ +#ifdef CONFIG_TRACER_SNAPSHOT /** * update_max_tr - snapshot all trace buffers from global_trace to max_tr * @tr: tracer @@ -1619,12 +1626,11 @@ update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu, else ring_buffer_record_off(tr->snapshot_buffer.buffer); -#ifdef CONFIG_TRACER_SNAPSHOT if (tr->cond_snapshot && !tr->cond_snapshot->update(tr, cond_data)) { arch_spin_unlock(&tr->max_lock); return; } -#endif + swap(tr->array_buffer.buffer, tr->snapshot_buffer.buffer); __update_max_tr(tr, tsk, cpu); @@ -1679,10 +1685,7 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu) __update_max_tr(tr, tsk, cpu); arch_spin_unlock(&tr->max_lock); } -#else /* !CONFIG_TRACER_MAX_TRACE */ -static inline void trace_create_maxlat_file(struct trace_array *tr, - struct dentry *d_tracer) { } -#endif /* CONFIG_TRACER_MAX_TRACE */ +#endif /* CONFIG_TRACER_SNAPSHOT */ struct pipe_wait { struct trace_iterator *iter; @@ -1715,7 +1718,7 @@ static int wait_on_pipe(struct trace_iterator *iter, int full) ret = ring_buffer_wait(iter->array_buffer->buffer, iter->cpu_file, full, wait_pipe_cond, &pwait); -#ifdef CONFIG_TRACER_MAX_TRACE +#ifdef CONFIG_TRACER_SNAPSHOT /* * Make sure this is still the snapshot buffer, as if a snapshot were * to happen, this would now be the main buffer. @@ -2058,7 +2061,7 @@ void tracing_reset_all_online_cpus_unlocked(void) continue; tr->clear_trace = false; tracing_reset_online_cpus(&tr->array_buffer); -#ifdef CONFIG_TRACER_MAX_TRACE +#ifdef CONFIG_TRACER_SNAPSHOT tracing_reset_online_cpus(&tr->snapshot_buffer); #endif } @@ -2098,7 +2101,7 @@ static void tracing_start_tr(struct trace_array *tr) if (buffer) ring_buffer_record_enable(buffer); -#ifdef CONFIG_TRACER_MAX_TRACE +#ifdef CONFIG_TRACER_SNAPSHOT buffer = tr->snapshot_buffer.buffer; if (buffer) ring_buffer_record_enable(buffer); @@ -2134,7 +2137,7 @@ static void tracing_stop_tr(struct trace_array *tr) if (buffer) ring_buffer_record_disable(buffer); -#ifdef CONFIG_TRACER_MAX_TRACE +#ifdef CONFIG_TRACER_SNAPSHOT buffer = tr->snapshot_buffer.buffer; if (buffer) ring_buffer_record_disable(buffer); @@ -3757,7 +3760,7 @@ static void test_ftrace_alive(struct seq_file *m) "# MAY BE MISSING FUNCTION EVENTS\n"); } -#ifdef CONFIG_TRACER_MAX_TRACE +#ifdef CONFIG_TRACER_SNAPSHOT static void show_snapshot_main_help(struct seq_file *m) { seq_puts(m, "# echo 0 > snapshot : Clears and frees snapshot buffer\n" @@ -3935,7 +3938,7 @@ __tracing_open(struct inode *inode, struct file *file, bool snapshot) iter->tr = tr; -#ifdef CONFIG_TRACER_MAX_TRACE +#ifdef CONFIG_TRACER_SNAPSHOT /* Currently only the top directory has a snapshot */ if (tr->current_trace->print_max || snapshot) iter->array_buffer = &tr->snapshot_buffer; @@ -4351,14 +4354,14 @@ int tracing_set_cpumask(struct trace_array *tr, if (cpumask_test_cpu(cpu, tr->tracing_cpumask) && !cpumask_test_cpu(cpu, tracing_cpumask_new)) { ring_buffer_record_disable_cpu(tr->array_buffer.buffer, cpu); -#ifdef CONFIG_TRACER_MAX_TRACE +#ifdef CONFIG_TRACER_SNAPSHOT ring_buffer_record_disable_cpu(tr->snapshot_buffer.buffer, cpu); #endif } if (!cpumask_test_cpu(cpu, tr->tracing_cpumask) && cpumask_test_cpu(cpu, tracing_cpumask_new)) { ring_buffer_record_enable_cpu(tr->array_buffer.buffer, cpu); -#ifdef CONFIG_TRACER_MAX_TRACE +#ifdef CONFIG_TRACER_SNAPSHOT ring_buffer_record_enable_cpu(tr->snapshot_buffer.buffer, cpu); #endif } @@ -4568,7 +4571,7 @@ int set_tracer_flag(struct trace_array *tr, u64 mask, int enabled) case TRACE_ITER(OVERWRITE): ring_buffer_change_overwrite(tr->array_buffer.buffer, enabled); -#ifdef CONFIG_TRACER_MAX_TRACE +#ifdef CONFIG_TRACER_SNAPSHOT ring_buffer_change_overwrite(tr->snapshot_buffer.buffer, enabled); #endif break; @@ -5232,7 +5235,7 @@ static void update_buffer_entries(struct array_buffer *buf, int cpu) } } -#ifdef CONFIG_TRACER_MAX_TRACE +#ifdef CONFIG_TRACER_SNAPSHOT /* resize @tr's buffer to the size of @size_tr's entries */ static int resize_buffer_duplicate_size(struct array_buffer *trace_buf, struct array_buffer *size_buf, int cpu_id) @@ -5258,7 +5261,7 @@ static int resize_buffer_duplicate_size(struct array_buffer *trace_buf, return ret; } -#endif /* CONFIG_TRACER_MAX_TRACE */ +#endif /* CONFIG_TRACER_SNAPSHOT */ static int __tracing_resize_ring_buffer(struct trace_array *tr, unsigned long size, int cpu) @@ -5283,7 +5286,7 @@ static int __tracing_resize_ring_buffer(struct trace_array *tr, if (ret < 0) goto out_start; -#ifdef CONFIG_TRACER_MAX_TRACE +#ifdef CONFIG_TRACER_SNAPSHOT if (!tr->allocated_snapshot) goto out; @@ -5315,7 +5318,7 @@ static int __tracing_resize_ring_buffer(struct trace_array *tr, update_buffer_entries(&tr->snapshot_buffer, cpu); out: -#endif /* CONFIG_TRACER_MAX_TRACE */ +#endif /* CONFIG_TRACER_SNAPSHOT */ update_buffer_entries(&tr->array_buffer, cpu); out_start: @@ -7020,7 +7023,7 @@ int tracing_set_clock(struct trace_array *tr, const char *clockstr) */ tracing_reset_online_cpus(&tr->array_buffer); -#ifdef CONFIG_TRACER_MAX_TRACE +#ifdef CONFIG_TRACER_SNAPSHOT if (tr->snapshot_buffer.buffer) ring_buffer_set_clock(tr->snapshot_buffer.buffer, trace_clocks[i].func); tracing_reset_online_cpus(&tr->snapshot_buffer); @@ -8167,7 +8170,7 @@ static long tracing_buffers_ioctl(struct file *file, unsigned int cmd, unsigned return 0; } -#ifdef CONFIG_TRACER_MAX_TRACE +#ifdef CONFIG_TRACER_SNAPSHOT static int get_snapshot_map(struct trace_array *tr) { int err = 0; @@ -9171,7 +9174,7 @@ buffer_subbuf_size_write(struct file *filp, const char __user *ubuf, if (ret) goto out; -#ifdef CONFIG_TRACER_MAX_TRACE +#ifdef CONFIG_TRACER_SNAPSHOT if (!tr->allocated_snapshot) goto out_max; @@ -9392,7 +9395,7 @@ static int allocate_trace_buffers(struct trace_array *tr, int size) if (ret) return ret; -#ifdef CONFIG_TRACER_MAX_TRACE +#ifdef CONFIG_TRACER_SNAPSHOT /* Fix mapped buffer trace arrays do not have snapshot buffers */ if (tr->range_addr_start) return 0; @@ -9419,7 +9422,7 @@ static void free_trace_buffers(struct trace_array *tr) free_trace_buffer(&tr->array_buffer); kfree(tr->module_delta); -#ifdef CONFIG_TRACER_MAX_TRACE +#ifdef CONFIG_TRACER_SNAPSHOT free_trace_buffer(&tr->snapshot_buffer); #endif } @@ -9561,7 +9564,7 @@ trace_array_create_systems(const char *name, const char *systems, tr->syscall_buf_sz = global_trace.syscall_buf_sz; tr->max_lock = (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED; -#ifdef CONFIG_TRACER_MAX_TRACE +#ifdef CONFIG_TRACER_SNAPSHOT spin_lock_init(&tr->snapshot_trigger_lock); #endif tr->current_trace = &nop_trace; @@ -10515,7 +10518,7 @@ ssize_t trace_parse_run_command(struct file *file, const char __user *buffer, return done; } -#ifdef CONFIG_TRACER_MAX_TRACE +#ifdef CONFIG_TRACER_SNAPSHOT __init static bool tr_needs_alloc_snapshot(const char *name) { char *test; @@ -10705,7 +10708,7 @@ __init static void enable_instances(void) } } else { /* Only non mapped buffers have snapshot buffers */ - if (IS_ENABLED(CONFIG_TRACER_MAX_TRACE)) + if (IS_ENABLED(CONFIG_TRACER_SNAPSHOT)) do_allocate_snapshot(name); } @@ -10832,7 +10835,7 @@ __init static int tracer_alloc_buffers(void) global_trace.current_trace_flags = nop_trace.flags; global_trace.max_lock = (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED; -#ifdef CONFIG_TRACER_MAX_TRACE +#ifdef CONFIG_TRACER_SNAPSHOT spin_lock_init(&global_trace.snapshot_trigger_lock); #endif ftrace_init_global_array_ops(&global_trace); @@ -10900,7 +10903,7 @@ struct trace_array *trace_get_global_array(void) void __init ftrace_boot_snapshot(void) { -#ifdef CONFIG_TRACER_MAX_TRACE +#ifdef CONFIG_TRACER_SNAPSHOT struct trace_array *tr; if (!snapshot_at_boot) diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index ebb47abc0ee7..649fdd20fc91 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -329,7 +329,7 @@ struct trace_array { struct list_head list; char *name; struct array_buffer array_buffer; -#ifdef CONFIG_TRACER_MAX_TRACE +#ifdef CONFIG_TRACER_SNAPSHOT /* * The snapshot_buffer is used to snapshot the trace when a maximum * latency is reached, or when the user initiates a snapshot. @@ -346,13 +346,16 @@ struct trace_array { bool allocated_snapshot; spinlock_t snapshot_trigger_lock; unsigned int snapshot; +#ifdef CONFIG_TRACER_MAX_TRACE unsigned long max_latency; #ifdef CONFIG_FSNOTIFY struct dentry *d_max_latency; struct work_struct fsnotify_work; struct irq_work fsnotify_irqwork; -#endif -#endif +#endif /* CONFIG_FSNOTIFY */ +#endif /* CONFIG_TRACER_MAX_TRACE */ +#endif /* CONFIG_TRACER_SNAPSHOT */ + /* The below is for memory mapped ring buffer */ unsigned int mapped; unsigned long range_addr_start; @@ -378,7 +381,7 @@ struct trace_array { * * It is also used in other places outside the update_max_tr * so it needs to be defined outside of the - * CONFIG_TRACER_MAX_TRACE. + * CONFIG_TRACER_SNAPSHOT. */ arch_spinlock_t max_lock; #ifdef CONFIG_FTRACE_SYSCALLS @@ -791,22 +794,22 @@ int trace_pid_write(struct trace_pid_list *filtered_pids, struct trace_pid_list **new_pid_list, const char __user *ubuf, size_t cnt); -#ifdef CONFIG_TRACER_MAX_TRACE +#ifdef CONFIG_TRACER_SNAPSHOT void update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu, void *cond_data); void update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu); -#ifdef CONFIG_FSNOTIFY -#define LATENCY_FS_NOTIFY +#if defined(CONFIG_TRACER_MAX_TRACE) && defined(CONFIG_FSNOTIFY) +# define LATENCY_FS_NOTIFY #endif -#endif /* CONFIG_TRACER_MAX_TRACE */ #ifdef LATENCY_FS_NOTIFY void latency_fsnotify(struct trace_array *tr); #else static inline void latency_fsnotify(struct trace_array *tr) { } #endif +#endif /* CONFIG_TRACER_SNAPSHOT */ #ifdef CONFIG_STACKTRACE void __trace_stack(struct trace_array *tr, unsigned int trace_ctx, int skip); -- cgit v1.2.3 From b4bade506b18eb2e5e34ac84f915d7ee6156d4e2 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Mon, 9 Feb 2026 19:46:31 -0500 Subject: tracing: Move d_max_latency out of CONFIG_FSNOTIFY protection The tracing_max_latency shouldn't be limited if CONFIG_FSNOTIFY is defined or not and it was moved out of that protection to be always available with CONFIG_TRACER_MAX_TRACE. All was moved out except the dentry descriptor for it (d_max_latency) and it failed to build on some configs. Move that out of the CONFIG_FSNOTIFY protection too. Cc: Masami Hiramatsu Cc: Mathieu Desnoyers Link: https://patch.msgid.link/20260209194631.788bfc85@fedora Fixes: ba73713da50e ("tracing: Clean up use of trace_create_maxlat_file()") Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202602092133.fTdojd95-lkp@intel.com/ Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/trace/trace.h') diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 649fdd20fc91..7894bf55743c 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -348,8 +348,8 @@ struct trace_array { unsigned int snapshot; #ifdef CONFIG_TRACER_MAX_TRACE unsigned long max_latency; -#ifdef CONFIG_FSNOTIFY struct dentry *d_max_latency; +#ifdef CONFIG_FSNOTIFY struct work_struct fsnotify_work; struct irq_work fsnotify_irqwork; #endif /* CONFIG_FSNOTIFY */ -- cgit v1.2.3