From 38b14061947fa546491656e3f5e388d4fedf8dba Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 20 Feb 2025 15:20:10 -0500 Subject: ftrace: Fix accounting of adding subops to a manager ops Function graph uses a subops and manager ops mechanism to attach to ftrace. The manager ops connects to ftrace and the functions it connects to is defined by a list of subops that it manages. The function hash that defines what the above ops attaches to limits the functions to attach if the hash has any content. If the hash is empty, it means to trace all functions. The creation of the manager ops hash is done by iterating over all the subops hashes. If any of the subops hashes is empty, it means that the manager ops hash must trace all functions as well. The issue is in the creation of the manager ops. When a second subops is attached, a new hash is created by starting it as NULL and adding the subops one at a time. But the NULL ops is mistaken as an empty hash, and once an empty hash is found, it stops the loop of subops and just enables all functions. # echo "f:myevent1 kernel_clone" >> /sys/kernel/tracing/dynamic_events # cat /sys/kernel/tracing/enabled_functions kernel_clone (1) tramp: 0xffffffffc0309000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60 # echo "f:myevent2 schedule_timeout" >> /sys/kernel/tracing/dynamic_events # cat /sys/kernel/tracing/enabled_functions trace_initcall_start_cb (1) tramp: 0xffffffffc0309000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60 run_init_process (1) tramp: 0xffffffffc0309000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60 try_to_run_init_process (1) tramp: 0xffffffffc0309000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60 x86_pmu_show_pmu_cap (1) tramp: 0xffffffffc0309000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60 cleanup_rapl_pmus (1) tramp: 0xffffffffc0309000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60 uncore_free_pcibus_map (1) tramp: 0xffffffffc0309000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60 uncore_types_exit (1) tramp: 0xffffffffc0309000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60 uncore_pci_exit.part.0 (1) tramp: 0xffffffffc0309000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60 kvm_shutdown (1) tramp: 0xffffffffc0309000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60 vmx_dump_msrs (1) tramp: 0xffffffffc0309000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60 vmx_cleanup_l1d_flush (1) tramp: 0xffffffffc0309000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60 [..] Fix this by initializing the new hash to NULL and if the hash is NULL do not treat it as an empty hash but instead allocate by copying the content of the first sub ops. Then on subsequent iterations, the new hash will not be NULL, but the content of the previous subops. If that first subops attached to all functions, then new hash may assume that the manager ops also needs to attach to all functions. Cc: stable@vger.kernel.org Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Andrew Morton Cc: Heiko Carstens Cc: Sven Schnelle Cc: Vasily Gorbik Cc: Alexander Gordeev Link: https://lore.kernel.org/20250220202055.060300046@goodmis.org Fixes: 5fccc7552ccbc ("ftrace: Add subops logic to allow one ops to manage many") Reviewed-by: Masami Hiramatsu (Google) Signed-off-by: Steven Rostedt (Google) --- kernel/trace/ftrace.c | 33 ++++++++++++++++++++++----------- 1 file changed, 22 insertions(+), 11 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 728ecda6e8d4..bec54dc27204 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -3220,15 +3220,22 @@ static struct ftrace_hash *copy_hash(struct ftrace_hash *src) * The filter_hash updates uses just the append_hash() function * and the notrace_hash does not. */ -static int append_hash(struct ftrace_hash **hash, struct ftrace_hash *new_hash) +static int append_hash(struct ftrace_hash **hash, struct ftrace_hash *new_hash, + int size_bits) { struct ftrace_func_entry *entry; int size; int i; - /* An empty hash does everything */ - if (ftrace_hash_empty(*hash)) - return 0; + if (*hash) { + /* An empty hash does everything */ + if (ftrace_hash_empty(*hash)) + return 0; + } else { + *hash = alloc_ftrace_hash(size_bits); + if (!*hash) + return -ENOMEM; + } /* If new_hash has everything make hash have everything */ if (ftrace_hash_empty(new_hash)) { @@ -3292,16 +3299,18 @@ static int intersect_hash(struct ftrace_hash **hash, struct ftrace_hash *new_has /* Return a new hash that has a union of all @ops->filter_hash entries */ static struct ftrace_hash *append_hashes(struct ftrace_ops *ops) { - struct ftrace_hash *new_hash; + struct ftrace_hash *new_hash = NULL; struct ftrace_ops *subops; + int size_bits; int ret; - new_hash = alloc_ftrace_hash(ops->func_hash->filter_hash->size_bits); - if (!new_hash) - return NULL; + if (ops->func_hash->filter_hash) + size_bits = ops->func_hash->filter_hash->size_bits; + else + size_bits = FTRACE_HASH_DEFAULT_BITS; list_for_each_entry(subops, &ops->subop_list, list) { - ret = append_hash(&new_hash, subops->func_hash->filter_hash); + ret = append_hash(&new_hash, subops->func_hash->filter_hash, size_bits); if (ret < 0) { free_ftrace_hash(new_hash); return NULL; @@ -3310,7 +3319,8 @@ static struct ftrace_hash *append_hashes(struct ftrace_ops *ops) if (ftrace_hash_empty(new_hash)) break; } - return new_hash; + /* Can't return NULL as that means this failed */ + return new_hash ? : EMPTY_HASH; } /* Make @ops trace evenything except what all its subops do not trace */ @@ -3505,7 +3515,8 @@ int ftrace_startup_subops(struct ftrace_ops *ops, struct ftrace_ops *subops, int filter_hash = alloc_and_copy_ftrace_hash(size_bits, ops->func_hash->filter_hash); if (!filter_hash) return -ENOMEM; - ret = append_hash(&filter_hash, subops->func_hash->filter_hash); + ret = append_hash(&filter_hash, subops->func_hash->filter_hash, + size_bits); if (ret < 0) { free_ftrace_hash(filter_hash); return ret; -- cgit v1.2.3 From 8eb4b09e0bbd30981305643229fe7640ad41b667 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 20 Feb 2025 15:20:11 -0500 Subject: ftrace: Do not add duplicate entries in subops manager ops Check if a function is already in the manager ops of a subops. A manager ops contains multiple subops, and if two or more subops are tracing the same function, the manager ops only needs a single entry in its hash. Cc: stable@vger.kernel.org Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Andrew Morton Cc: Sven Schnelle Cc: Vasily Gorbik Cc: Alexander Gordeev Link: https://lore.kernel.org/20250220202055.226762894@goodmis.org Fixes: 4f554e955614f ("ftrace: Add ftrace_set_filter_ips function") Tested-by: Heiko Carstens Reviewed-by: Masami Hiramatsu (Google) Signed-off-by: Steven Rostedt (Google) --- kernel/trace/ftrace.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'kernel/trace') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index bec54dc27204..6b0c25761ccb 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -5718,6 +5718,9 @@ __ftrace_match_addr(struct ftrace_hash *hash, unsigned long ip, int remove) return -ENOENT; free_hash_entry(hash, entry); return 0; + } else if (__ftrace_lookup_ip(hash, ip) != NULL) { + /* Already exists */ + return 0; } entry = add_hash_entry(hash, ip); -- cgit v1.2.3 From ded9140622358a154efb3a777025fa7f7ae2c2d9 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 20 Feb 2025 15:20:12 -0500 Subject: fprobe: Always unregister fgraph function from ops When the last fprobe is removed, it calls unregister_ftrace_graph() to remove the graph_ops from function graph. The issue is when it does so, it calls return before removing the function from its graph ops via ftrace_set_filter_ips(). This leaves the last function lingering in the fprobe's fgraph ops and if a probe is added it also enables that last function (even though the callback will just drop it, it does add unneeded overhead to make that call). # echo "f:myevent1 kernel_clone" >> /sys/kernel/tracing/dynamic_events # cat /sys/kernel/tracing/enabled_functions kernel_clone (1) tramp: 0xffffffffc02f3000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60 # echo "f:myevent2 schedule_timeout" >> /sys/kernel/tracing/dynamic_events # cat /sys/kernel/tracing/enabled_functions kernel_clone (1) tramp: 0xffffffffc02f3000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60 schedule_timeout (1) tramp: 0xffffffffc02f3000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60 # > /sys/kernel/tracing/dynamic_events # cat /sys/kernel/tracing/enabled_functions # echo "f:myevent3 kmem_cache_free" >> /sys/kernel/tracing/dynamic_events # cat /sys/kernel/tracing/enabled_functions kmem_cache_free (1) tramp: 0xffffffffc0219000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60 schedule_timeout (1) tramp: 0xffffffffc0219000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60 The above enabled a fprobe on kernel_clone, and then on schedule_timeout. The content of the enabled_functions shows the functions that have a callback attached to them. The fprobe attached to those functions properly. Then the fprobes were cleared, and enabled_functions was empty after that. But after adding a fprobe on kmem_cache_free, the enabled_functions shows that the schedule_timeout was attached again. This is because it was still left in the fprobe ops that is used to tell function graph what functions it wants callbacks from. Cc: stable@vger.kernel.org Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Andrew Morton Cc: Sven Schnelle Cc: Vasily Gorbik Cc: Alexander Gordeev Link: https://lore.kernel.org/20250220202055.393254452@goodmis.org Fixes: 4346ba1604093 ("fprobe: Rewrite fprobe on function-graph tracer") Tested-by: Heiko Carstens Acked-by: Masami Hiramatsu (Google) Signed-off-by: Steven Rostedt (Google) --- kernel/trace/fprobe.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c index 2560b312ad57..62e8f7d56602 100644 --- a/kernel/trace/fprobe.c +++ b/kernel/trace/fprobe.c @@ -403,11 +403,9 @@ static void fprobe_graph_remove_ips(unsigned long *addrs, int num) lockdep_assert_held(&fprobe_mutex); fprobe_graph_active--; - if (!fprobe_graph_active) { - /* Q: should we unregister it ? */ + /* Q: should we unregister it ? */ + if (!fprobe_graph_active) unregister_ftrace_graph(&fprobe_graph_ops); - return; - } ftrace_set_filter_ips(&fprobe_graph_ops.ops, addrs, num, 1, 0); } -- cgit v1.2.3 From ca26554a1498bc905c4a39fb42d55d93f3ae8df2 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 20 Feb 2025 15:20:13 -0500 Subject: fprobe: Fix accounting of when to unregister from function graph When adding a new fprobe, it will update the function hash to the functions the fprobe is attached to and register with function graph to have it call the registered functions. The fprobe_graph_active variable keeps track of the number of fprobes that are using function graph. If two fprobes attach to the same function, it increments the fprobe_graph_active for each of them. But when they are removed, the first fprobe to be removed will see that the function it is attached to is also used by another fprobe and it will not remove that function from function_graph. The logic will skip decrementing the fprobe_graph_active variable. This causes the fprobe_graph_active variable to not go to zero when all fprobes are removed, and in doing so it does not unregister from function graph. As the fgraph ops hash will now be empty, and an empty filter hash means all functions are enabled, this triggers function graph to add a callback to the fprobe infrastructure for every function! # echo "f:myevent1 kernel_clone" >> /sys/kernel/tracing/dynamic_events # echo "f:myevent2 kernel_clone%return" >> /sys/kernel/tracing/dynamic_events # cat /sys/kernel/tracing/enabled_functions kernel_clone (1) tramp: 0xffffffffc0024000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60 # > /sys/kernel/tracing/dynamic_events # cat /sys/kernel/tracing/enabled_functions trace_initcall_start_cb (1) tramp: 0xffffffffc0026000 (function_trace_call+0x0/0x170) ->function_trace_call+0x0/0x170 run_init_process (1) tramp: 0xffffffffc0026000 (function_trace_call+0x0/0x170) ->function_trace_call+0x0/0x170 try_to_run_init_process (1) tramp: 0xffffffffc0026000 (function_trace_call+0x0/0x170) ->function_trace_call+0x0/0x170 x86_pmu_show_pmu_cap (1) tramp: 0xffffffffc0026000 (function_trace_call+0x0/0x170) ->function_trace_call+0x0/0x170 cleanup_rapl_pmus (1) tramp: 0xffffffffc0026000 (function_trace_call+0x0/0x170) ->function_trace_call+0x0/0x170 uncore_free_pcibus_map (1) tramp: 0xffffffffc0026000 (function_trace_call+0x0/0x170) ->function_trace_call+0x0/0x170 uncore_types_exit (1) tramp: 0xffffffffc0026000 (function_trace_call+0x0/0x170) ->function_trace_call+0x0/0x170 uncore_pci_exit.part.0 (1) tramp: 0xffffffffc0026000 (function_trace_call+0x0/0x170) ->function_trace_call+0x0/0x170 kvm_shutdown (1) tramp: 0xffffffffc0026000 (function_trace_call+0x0/0x170) ->function_trace_call+0x0/0x170 vmx_dump_msrs (1) tramp: 0xffffffffc0026000 (function_trace_call+0x0/0x170) ->function_trace_call+0x0/0x170 [..] # cat /sys/kernel/tracing/enabled_functions | wc -l 54702 If a fprobe is being removed and all its functions are also traced by other fprobes, still decrement the fprobe_graph_active counter. Cc: stable@vger.kernel.org Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Andrew Morton Cc: Sven Schnelle Cc: Vasily Gorbik Cc: Alexander Gordeev Link: https://lore.kernel.org/20250220202055.565129766@goodmis.org Fixes: 4346ba1604093 ("fprobe: Rewrite fprobe on function-graph tracer") Closes: https://lore.kernel.org/all/20250217114918.10397-A-hca@linux.ibm.com/ Reported-by: Heiko Carstens Tested-by: Heiko Carstens Acked-by: Masami Hiramatsu (Google) Signed-off-by: Steven Rostedt (Google) --- kernel/trace/fprobe.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c index 62e8f7d56602..33082c4e8154 100644 --- a/kernel/trace/fprobe.c +++ b/kernel/trace/fprobe.c @@ -407,7 +407,8 @@ static void fprobe_graph_remove_ips(unsigned long *addrs, int num) if (!fprobe_graph_active) unregister_ftrace_graph(&fprobe_graph_ops); - ftrace_set_filter_ips(&fprobe_graph_ops.ops, addrs, num, 1, 0); + if (num) + ftrace_set_filter_ips(&fprobe_graph_ops.ops, addrs, num, 1, 0); } static int symbols_cmp(const void *a, const void *b) @@ -677,8 +678,7 @@ int unregister_fprobe(struct fprobe *fp) } del_fprobe_hash(fp); - if (count) - fprobe_graph_remove_ips(addrs, count); + fprobe_graph_remove_ips(addrs, count); kfree_rcu(hlist_array, rcu); fp->hlist_array = NULL; -- cgit v1.2.3 From 57b76bedc5c52c66968183b5ef57234894c25ce7 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Thu, 20 Feb 2025 15:07:49 +0100 Subject: ftrace: Correct preemption accounting for function tracing. The function tracer should record the preemption level at the point when the function is invoked. If the tracing subsystem decrement the preemption counter it needs to correct this before feeding the data into the trace buffer. This was broken in the commit cited below while shifting the preempt-disabled section. Use tracing_gen_ctx_dec() which properly subtracts one from the preemption counter on a preemptible kernel. Cc: stable@vger.kernel.org Cc: Wander Lairson Costa Cc: Masami Hiramatsu Cc: Mathieu Desnoyers Cc: Thomas Gleixner Link: https://lore.kernel.org/20250220140749.pfw8qoNZ@linutronix.de Fixes: ce5e48036c9e7 ("ftrace: disable preemption when recursion locked") Signed-off-by: Sebastian Andrzej Siewior Tested-by: Wander Lairson Costa Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace_functions.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c index d358c9935164..df56f9b76010 100644 --- a/kernel/trace/trace_functions.c +++ b/kernel/trace/trace_functions.c @@ -216,7 +216,7 @@ function_trace_call(unsigned long ip, unsigned long parent_ip, parent_ip = function_get_true_parent_ip(parent_ip, fregs); - trace_ctx = tracing_gen_ctx(); + trace_ctx = tracing_gen_ctx_dec(); data = this_cpu_ptr(tr->array_buffer.data); if (!atomic_read(&data->disabled)) @@ -321,7 +321,6 @@ function_no_repeats_trace_call(unsigned long ip, unsigned long parent_ip, struct trace_array *tr = op->private; struct trace_array_cpu *data; unsigned int trace_ctx; - unsigned long flags; int bit; if (unlikely(!tr->function_enabled)) @@ -347,8 +346,7 @@ function_no_repeats_trace_call(unsigned long ip, unsigned long parent_ip, if (is_repeat_check(tr, last_info, ip, parent_ip)) goto out; - local_save_flags(flags); - trace_ctx = tracing_gen_ctx_flags(flags); + trace_ctx = tracing_gen_ctx_dec(); process_repeats(tr, ip, parent_ip, last_info, trace_ctx); trace_function(tr, ip, parent_ip, trace_ctx); -- cgit v1.2.3 From 2fa6a01345b538faa7b0fae8f723bb6977312428 Mon Sep 17 00:00:00 2001 From: Adrian Huang Date: Thu, 20 Feb 2025 11:15:28 +0800 Subject: tracing: Fix memory leak when reading set_event file kmemleak reports the following memory leak after reading set_event file: # cat /sys/kernel/tracing/set_event # cat /sys/kernel/debug/kmemleak unreferenced object 0xff110001234449e0 (size 16): comm "cat", pid 13645, jiffies 4294981880 hex dump (first 16 bytes): 01 00 00 00 00 00 00 00 a8 71 e7 84 ff ff ff ff .........q...... backtrace (crc c43abbc): __kmalloc_cache_noprof+0x3ca/0x4b0 s_start+0x72/0x2d0 seq_read_iter+0x265/0x1080 seq_read+0x2c9/0x420 vfs_read+0x166/0xc30 ksys_read+0xf4/0x1d0 do_syscall_64+0x79/0x150 entry_SYSCALL_64_after_hwframe+0x76/0x7e The issue can be reproduced regardless of whether set_event is empty or not. Here is an example about the valid content of set_event. # cat /sys/kernel/tracing/set_event sched:sched_process_fork sched:sched_switch sched:sched_wakeup *:*:mod:trace_events_sample The root cause is that s_next() returns NULL when nothing is found. This results in s_stop() attempting to free a NULL pointer because its parameter is NULL. Fix the issue by freeing the memory appropriately when s_next() fails to find anything. Cc: Mathieu Desnoyers Link: https://lore.kernel.org/20250220031528.7373-1-ahuang12@lenovo.com Fixes: b355247df104 ("tracing: Cache ":mod:" events for modules not loaded yet") Signed-off-by: Adrian Huang Acked-by: Masami Hiramatsu (Google) Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace_events.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 4cb275316e51..513de9ceb80e 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -1591,6 +1591,13 @@ s_next(struct seq_file *m, void *v, loff_t *pos) return iter; #endif + /* + * The iter is allocated in s_start() and passed via the 'v' + * parameter. To stop the iterator, NULL must be returned. But + * the return value is what the 'v' parameter in s_stop() receives + * and frees. Free iter here as it will no longer be used. + */ + kfree(iter); return NULL; } @@ -1667,9 +1674,9 @@ static int s_show(struct seq_file *m, void *v) } #endif -static void s_stop(struct seq_file *m, void *p) +static void s_stop(struct seq_file *m, void *v) { - kfree(p); + kfree(v); t_stop(m, NULL); } -- cgit v1.2.3 From 6f86bdeab633a56d5c6dccf1a2c5989b6a5e323e Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 27 Feb 2025 16:39:44 -0500 Subject: tracing: Fix bad hist from corrupting named_triggers list The following commands causes a crash: ~# cd /sys/kernel/tracing/events/rcu/rcu_callback ~# echo 'hist:name=bad:keys=common_pid:onmax(bogus).save(common_pid)' > trigger bash: echo: write error: Invalid argument ~# echo 'hist:name=bad:keys=common_pid' > trigger Because the following occurs: event_trigger_write() { trigger_process_regex() { event_hist_trigger_parse() { data = event_trigger_alloc(..); event_trigger_register(.., data) { cmd_ops->reg(.., data, ..) [hist_register_trigger()] { data->ops->init() [event_hist_trigger_init()] { save_named_trigger(name, data) { list_add(&data->named_list, &named_triggers); } } } } ret = create_actions(); (return -EINVAL) if (ret) goto out_unreg; [..] ret = hist_trigger_enable(data, ...) { list_add_tail_rcu(&data->list, &file->triggers); <<<---- SKIPPED!!! (this is important!) [..] out_unreg: event_hist_unregister(.., data) { cmd_ops->unreg(.., data, ..) [hist_unregister_trigger()] { list_for_each_entry(iter, &file->triggers, list) { if (!hist_trigger_match(data, iter, named_data, false)) <- never matches continue; [..] test = iter; } if (test && test->ops->free) <<<-- test is NULL test->ops->free(test) [event_hist_trigger_free()] { [..] if (data->name) del_named_trigger(data) { list_del(&data->named_list); <<<<-- NEVER gets removed! } } } } [..] kfree(data); <<<-- frees item but it is still on list The next time a hist with name is registered, it causes an u-a-f bug and the kernel can crash. Move the code around such that if event_trigger_register() succeeds, the next thing called is hist_trigger_enable() which adds it to the list. A bunch of actions is called if get_named_trigger_data() returns false. But that doesn't need to be called after event_trigger_register(), so it can be moved up, allowing event_trigger_register() to be called just before hist_trigger_enable() keeping them together and allowing the file->triggers to be properly populated. Cc: stable@vger.kernel.org Cc: Masami Hiramatsu Cc: Mathieu Desnoyers Link: https://lore.kernel.org/20250227163944.1c37f85f@gandalf.local.home Fixes: 067fe038e70f6 ("tracing: Add variable reference handling to hist triggers") Reported-by: Tomas Glozar Tested-by: Tomas Glozar Reviewed-by: Tom Zanussi Closes: https://lore.kernel.org/all/CAP4=nvTsxjckSBTz=Oe_UYh8keD9_sZC4i++4h72mJLic4_W4A@mail.gmail.com/ Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace_events_hist.c | 30 +++++++++++++++--------------- 1 file changed, 15 insertions(+), 15 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 261163b00137..ad7419e24055 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -6724,27 +6724,27 @@ static int event_hist_trigger_parse(struct event_command *cmd_ops, if (existing_hist_update_only(glob, trigger_data, file)) goto out_free; - ret = event_trigger_register(cmd_ops, file, glob, trigger_data); - if (ret < 0) - goto out_free; + if (!get_named_trigger_data(trigger_data)) { - if (get_named_trigger_data(trigger_data)) - goto enable; + ret = create_actions(hist_data); + if (ret) + goto out_free; - ret = create_actions(hist_data); - if (ret) - goto out_unreg; + if (has_hist_vars(hist_data) || hist_data->n_var_refs) { + ret = save_hist_vars(hist_data); + if (ret) + goto out_free; + } - if (has_hist_vars(hist_data) || hist_data->n_var_refs) { - ret = save_hist_vars(hist_data); + ret = tracing_map_init(hist_data->map); if (ret) - goto out_unreg; + goto out_free; } - ret = tracing_map_init(hist_data->map); - if (ret) - goto out_unreg; -enable: + ret = event_trigger_register(cmd_ops, file, glob, trigger_data); + if (ret < 0) + goto out_free; + ret = hist_trigger_enable(trigger_data, file); if (ret) goto out_unreg; -- cgit v1.2.3 From a1a7eb89ca0b89dc1c326eeee2596f263291aca3 Mon Sep 17 00:00:00 2001 From: Nikolay Kuratov Date: Thu, 6 Feb 2025 12:01:56 +0300 Subject: ftrace: Avoid potential division by zero in function_stat_show() Check whether denominator expression x * (x - 1) * 1000 mod {2^32, 2^64} produce zero and skip stddev computation in that case. For now don't care about rec->counter * rec->counter overflow because rec->time * rec->time overflow will likely happen earlier. Cc: stable@vger.kernel.org Cc: Wen Yang Cc: Mark Rutland Cc: Mathieu Desnoyers Link: https://lore.kernel.org/20250206090156.1561783-1-kniv@yandex-team.ru Fixes: e31f7939c1c27 ("ftrace: Avoid potential division by zero in function profiler") Signed-off-by: Nikolay Kuratov Signed-off-by: Steven Rostedt (Google) --- kernel/trace/ftrace.c | 27 ++++++++++++--------------- 1 file changed, 12 insertions(+), 15 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 6b0c25761ccb..fc88e0688daf 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -540,6 +540,7 @@ static int function_stat_show(struct seq_file *m, void *v) static struct trace_seq s; unsigned long long avg; unsigned long long stddev; + unsigned long long stddev_denom; #endif guard(mutex)(&ftrace_profile_lock); @@ -559,23 +560,19 @@ static int function_stat_show(struct seq_file *m, void *v) #ifdef CONFIG_FUNCTION_GRAPH_TRACER seq_puts(m, " "); - /* Sample standard deviation (s^2) */ - if (rec->counter <= 1) - stddev = 0; - else { - /* - * Apply Welford's method: - * s^2 = 1 / (n * (n-1)) * (n * \Sum (x_i)^2 - (\Sum x_i)^2) - */ + /* + * Variance formula: + * s^2 = 1 / (n * (n-1)) * (n * \Sum (x_i)^2 - (\Sum x_i)^2) + * Maybe Welford's method is better here? + * Divide only by 1000 for ns^2 -> us^2 conversion. + * trace_print_graph_duration will divide by 1000 again. + */ + stddev = 0; + stddev_denom = rec->counter * (rec->counter - 1) * 1000; + if (stddev_denom) { stddev = rec->counter * rec->time_squared - rec->time * rec->time; - - /* - * Divide only 1000 for ns^2 -> us^2 conversion. - * trace_print_graph_duration will divide 1000 again. - */ - stddev = div64_ul(stddev, - rec->counter * (rec->counter - 1) * 1000); + stddev = div64_ul(stddev, stddev_denom); } trace_seq_init(&s); -- cgit v1.2.3