From d39cdd2036a63eef17a14efbd969405ca5612886 Mon Sep 17 00:00:00 2001 From: Chunyu Hu Date: Tue, 8 Mar 2016 21:37:01 +0800 Subject: tracing: Make tracer_flags use the right set_flag callback When I was updating the ftrace_stress test of ltp. I encountered a strange phenomemon, excute following steps: echo nop > /sys/kernel/debug/tracing/current_tracer echo 0 > /sys/kernel/debug/tracing/options/funcgraph-cpu bash: echo: write error: Invalid argument check dmesg: [ 1024.903855] nop_test_refuse flag set to 0: we refuse.Now cat trace_options to see the result The reason is that the trace option test will randomly setup trace option under tracing/options no matter what the current_tracer is. but the set_tracer_option is always using the set_flag callback from the current_tracer. This patch adds a pointer to tracer_flags and make it point to the tracer it belongs to. When the option is setup, the set_flag of the right tracer will be used no matter what the the current_tracer is. And the old dummy_tracer_flags is used for all the tracers which doesn't have a tracer_flags, having issue to use it to save the pointer of a tracer. So remove it and use dynamic dummy tracer_flags for tracers needing a dummy tracer_flags, as a result, there are no tracers sharing tracer_flags, so remove the check code. And save the current tracer to trace_option_dentry seems not good as it may waste mem space when mount the debug/trace fs more than one time. Link: http://lkml.kernel.org/r/1457444222-8654-1-git-send-email-chuhu@redhat.com Signed-off-by: Chunyu Hu [ Fixed up function tracer options to work with the change ] Signed-off-by: Steven Rostedt --- kernel/trace/trace.c | 28 ++++++++++++++-------------- kernel/trace/trace.h | 1 + kernel/trace/trace_functions.c | 6 ++++++ 3 files changed, 21 insertions(+), 14 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index d929340..b401a18 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -74,11 +74,6 @@ static struct tracer_opt dummy_tracer_opt[] = { { } }; -static struct tracer_flags dummy_tracer_flags = { - .val = 0, - .opts = dummy_tracer_opt -}; - static int dummy_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set) { @@ -1258,12 +1253,20 @@ int __init register_tracer(struct tracer *type) if (!type->set_flag) type->set_flag = &dummy_set_flag; - if (!type->flags) - type->flags = &dummy_tracer_flags; - else + if (!type->flags) { + /*allocate a dummy tracer_flags*/ + type->flags = kmalloc(sizeof(*type->flags), GFP_KERNEL); + if (!type->flags) + return -ENOMEM; + type->flags->val = 0; + type->flags->opts = dummy_tracer_opt; + } else if (!type->flags->opts) type->flags->opts = dummy_tracer_opt; + /* store the tracer for __set_tracer_option */ + type->flags->trace = type; + ret = run_tracer_selftest(type); if (ret < 0) goto out; @@ -3505,7 +3508,7 @@ static int __set_tracer_option(struct trace_array *tr, struct tracer_flags *tracer_flags, struct tracer_opt *opts, int neg) { - struct tracer *trace = tr->current_trace; + struct tracer *trace = tracer_flags->trace; int ret; ret = trace->set_flag(tr, tracer_flags->val, opts->bit, !neg); @@ -6391,11 +6394,8 @@ create_trace_option_files(struct trace_array *tr, struct tracer *tracer) return; for (i = 0; i < tr->nr_topts; i++) { - /* - * Check if these flags have already been added. - * Some tracers share flags. - */ - if (tr->topts[i].tracer->flags == tracer->flags) + /* Make sure there's no duplicate flags. */ + if (WARN_ON_ONCE(tr->topts[i].tracer->flags == tracer->flags)) return; } diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 8414fa4..b4cae47 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -345,6 +345,7 @@ struct tracer_opt { struct tracer_flags { u32 val; struct tracer_opt *opts; + struct tracer *trace; }; /* Makes more easy to define a tracer opt */ diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c index fcd41a1..5a095c2 100644 --- a/kernel/trace/trace_functions.c +++ b/kernel/trace/trace_functions.c @@ -219,6 +219,8 @@ static void tracing_stop_function_trace(struct trace_array *tr) unregister_ftrace_function(tr->ops); } +static struct tracer function_trace; + static int func_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set) { @@ -228,6 +230,10 @@ func_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set) if (!!set == !!(func_flags.val & TRACE_FUNC_OPT_STACK)) break; + /* We can change this flag when not running. */ + if (tr->current_trace != &function_trace) + break; + unregister_ftrace_function(tr->ops); if (set) { -- cgit v1.1 From 4ef56902fba4d9949918c6266e67ba7d05fba7a4 Mon Sep 17 00:00:00 2001 From: Tom Zanussi Date: Thu, 10 Dec 2015 12:50:43 -0600 Subject: tracing: Make ftrace_event_field checking functions available Make is_string_field() and is_function_field() accessible outside of trace_event_filters.c for other users of ftrace_event_fields. Link: http://lkml.kernel.org/r/2d3f00d3311702e556e82eed7754bae6f017939f.1449767187.git.tom.zanussi@linux.intel.com Signed-off-by: Tom Zanussi Reviewed-by: Masami Hiramatsu Tested-by: Masami Hiramatsu Reviewed-by: Namhyung Kim Signed-off-by: Steven Rostedt --- kernel/trace/trace.h | 12 ++++++++++++ kernel/trace/trace_events_filter.c | 12 ------------ 2 files changed, 12 insertions(+), 12 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index b4cae47..81a8359 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -1112,6 +1112,18 @@ struct filter_pred { unsigned short right; }; +static inline bool is_string_field(struct ftrace_event_field *field) +{ + return field->filter_type == FILTER_DYN_STRING || + field->filter_type == FILTER_STATIC_STRING || + field->filter_type == FILTER_PTR_STRING; +} + +static inline bool is_function_field(struct ftrace_event_field *field) +{ + return field->filter_type == FILTER_TRACE_FN; +} + extern enum regex_type filter_parse_regex(char *buff, int len, char **search, int *not); extern void print_event_filter(struct trace_event_file *file, diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index 6816302..b3f5051 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -961,18 +961,6 @@ int filter_assign_type(const char *type) return FILTER_OTHER; } -static bool is_function_field(struct ftrace_event_field *field) -{ - return field->filter_type == FILTER_TRACE_FN; -} - -static bool is_string_field(struct ftrace_event_field *field) -{ - return field->filter_type == FILTER_DYN_STRING || - field->filter_type == FILTER_STATIC_STRING || - field->filter_type == FILTER_PTR_STRING; -} - static bool is_legal_op(struct ftrace_event_field *field, int op) { if (is_string_field(field) && -- cgit v1.1 From ab4bf008928e8fc73fe1cbaa9249792d36845345 Mon Sep 17 00:00:00 2001 From: Tom Zanussi Date: Thu, 10 Dec 2015 12:50:44 -0600 Subject: tracing: Make event trigger functions available Make various event trigger utility functions available outside of trace_events_trigger.c so that new triggers can be defined outside of that file. Link: http://lkml.kernel.org/r/4a40c1695dd43cac6cd475d72e13ffe30ba84bff.1449767187.git.tom.zanussi@linux.intel.com Signed-off-by: Tom Zanussi Tested-by: Masami Hiramatsu Reviewed-by: Namhyung Kim Signed-off-by: Steven Rostedt --- kernel/trace/trace.h | 14 ++++++++++++++ kernel/trace/trace_events_trigger.c | 28 +++++++++++++--------------- 2 files changed, 27 insertions(+), 15 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 81a8359..b2bc956 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -1175,6 +1175,20 @@ struct event_trigger_data { struct list_head list; }; +extern void trigger_data_free(struct event_trigger_data *data); +extern int event_trigger_init(struct event_trigger_ops *ops, + struct event_trigger_data *data); +extern int trace_event_trigger_enable_disable(struct trace_event_file *file, + int trigger_enable); +extern void update_cond_flag(struct trace_event_file *file); +extern void unregister_trigger(char *glob, struct event_trigger_ops *ops, + struct event_trigger_data *test, + struct trace_event_file *file); +extern int set_trigger_filter(char *filter_str, + struct event_trigger_data *trigger_data, + struct trace_event_file *file); +extern int register_event_command(struct event_command *cmd); + /** * struct event_trigger_ops - callbacks for trace event triggers * diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c index b38f617..f40424f 100644 --- a/kernel/trace/trace_events_trigger.c +++ b/kernel/trace/trace_events_trigger.c @@ -28,8 +28,7 @@ static LIST_HEAD(trigger_commands); static DEFINE_MUTEX(trigger_cmd_mutex); -static void -trigger_data_free(struct event_trigger_data *data) +void trigger_data_free(struct event_trigger_data *data) { if (data->cmd_ops->set_filter) data->cmd_ops->set_filter(NULL, data, NULL); @@ -306,7 +305,7 @@ const struct file_operations event_trigger_fops = { * Currently we only register event commands from __init, so mark this * __init too. */ -static __init int register_event_command(struct event_command *cmd) +__init int register_event_command(struct event_command *cmd) { struct event_command *p; int ret = 0; @@ -395,9 +394,8 @@ event_trigger_print(const char *name, struct seq_file *m, * * Return: 0 on success, errno otherwise */ -static int -event_trigger_init(struct event_trigger_ops *ops, - struct event_trigger_data *data) +int event_trigger_init(struct event_trigger_ops *ops, + struct event_trigger_data *data) { data->ref++; return 0; @@ -425,8 +423,8 @@ event_trigger_free(struct event_trigger_ops *ops, trigger_data_free(data); } -static int trace_event_trigger_enable_disable(struct trace_event_file *file, - int trigger_enable) +int trace_event_trigger_enable_disable(struct trace_event_file *file, + int trigger_enable) { int ret = 0; @@ -483,7 +481,7 @@ clear_event_triggers(struct trace_array *tr) * its TRIGGER_COND bit set, otherwise the TRIGGER_COND bit should be * cleared. */ -static void update_cond_flag(struct trace_event_file *file) +void update_cond_flag(struct trace_event_file *file) { struct event_trigger_data *data; bool set_cond = false; @@ -560,9 +558,9 @@ out: * Usually used directly as the @unreg method in event command * implementations. */ -static void unregister_trigger(char *glob, struct event_trigger_ops *ops, - struct event_trigger_data *test, - struct trace_event_file *file) +void unregister_trigger(char *glob, struct event_trigger_ops *ops, + struct event_trigger_data *test, + struct trace_event_file *file) { struct event_trigger_data *data; bool unregistered = false; @@ -696,9 +694,9 @@ event_trigger_callback(struct event_command *cmd_ops, * * Return: 0 on success, errno otherwise */ -static int set_trigger_filter(char *filter_str, - struct event_trigger_data *trigger_data, - struct trace_event_file *file) +int set_trigger_filter(char *filter_str, + struct event_trigger_data *trigger_data, + struct trace_event_file *file) { struct event_trigger_data *data = trigger_data; struct event_filter *filter = NULL, *tmp; -- cgit v1.1 From c4a5923055c9e0c87dfc0387f7cda5ee2bbac3c1 Mon Sep 17 00:00:00 2001 From: Tom Zanussi Date: Thu, 10 Dec 2015 12:50:45 -0600 Subject: tracing: Add event record param to trigger_ops.func() Some triggers may need access to the trace event, so pass it in. Also fix up the existing trigger funcs and their callers. Link: http://lkml.kernel.org/r/543e31e9fc445ef61077421ab219033401c39846.1449767187.git.tom.zanussi@linux.intel.com Signed-off-by: Tom Zanussi Tested-by: Masami Hiramatsu Reviewed-by: Namhyung Kim Signed-off-by: Steven Rostedt --- kernel/trace/trace.h | 6 ++++-- kernel/trace/trace_events_trigger.c | 36 +++++++++++++++++++----------------- 2 files changed, 23 insertions(+), 19 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index b2bc956..c10456e 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -1201,7 +1201,8 @@ extern int register_event_command(struct event_command *cmd); * @func: The trigger 'probe' function called when the triggering * event occurs. The data passed into this callback is the data * that was supplied to the event_command @reg() function that - * registered the trigger (see struct event_command). + * registered the trigger (see struct event_command) along with + * the trace record, rec. * * @init: An optional initialization function called for the trigger * when the trigger is registered (via the event_command reg() @@ -1226,7 +1227,8 @@ extern int register_event_command(struct event_command *cmd); * (see trace_event_triggers.c). */ struct event_trigger_ops { - void (*func)(struct event_trigger_data *data); + void (*func)(struct event_trigger_data *data, + void *rec); int (*init)(struct event_trigger_ops *ops, struct event_trigger_data *data); void (*free)(struct event_trigger_ops *ops, diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c index f40424f..0a62887 100644 --- a/kernel/trace/trace_events_trigger.c +++ b/kernel/trace/trace_events_trigger.c @@ -73,7 +73,7 @@ event_triggers_call(struct trace_event_file *file, void *rec) list_for_each_entry_rcu(data, &file->triggers, list) { if (!rec) { - data->ops->func(data); + data->ops->func(data, rec); continue; } filter = rcu_dereference_sched(data->filter); @@ -83,7 +83,7 @@ event_triggers_call(struct trace_event_file *file, void *rec) tt |= data->cmd_ops->trigger_type; continue; } - data->ops->func(data); + data->ops->func(data, rec); } return tt; } @@ -93,6 +93,7 @@ EXPORT_SYMBOL_GPL(event_triggers_call); * event_triggers_post_call - Call 'post_triggers' for a trace event * @file: The trace_event_file associated with the event * @tt: enum event_trigger_type containing a set bit for each trigger to invoke + * @rec: The trace entry for the event * * For each trigger associated with an event, invoke the trigger * function registered with the associated trigger command, if the @@ -103,13 +104,14 @@ EXPORT_SYMBOL_GPL(event_triggers_call); */ void event_triggers_post_call(struct trace_event_file *file, - enum event_trigger_type tt) + enum event_trigger_type tt, + void *rec) { struct event_trigger_data *data; list_for_each_entry_rcu(data, &file->triggers, list) { if (data->cmd_ops->trigger_type & tt) - data->ops->func(data); + data->ops->func(data, rec); } } EXPORT_SYMBOL_GPL(event_triggers_post_call); @@ -745,7 +747,7 @@ int set_trigger_filter(char *filter_str, } static void -traceon_trigger(struct event_trigger_data *data) +traceon_trigger(struct event_trigger_data *data, void *rec) { if (tracing_is_on()) return; @@ -754,7 +756,7 @@ traceon_trigger(struct event_trigger_data *data) } static void -traceon_count_trigger(struct event_trigger_data *data) +traceon_count_trigger(struct event_trigger_data *data, void *rec) { if (tracing_is_on()) return; @@ -769,7 +771,7 @@ traceon_count_trigger(struct event_trigger_data *data) } static void -traceoff_trigger(struct event_trigger_data *data) +traceoff_trigger(struct event_trigger_data *data, void *rec) { if (!tracing_is_on()) return; @@ -778,7 +780,7 @@ traceoff_trigger(struct event_trigger_data *data) } static void -traceoff_count_trigger(struct event_trigger_data *data) +traceoff_count_trigger(struct event_trigger_data *data, void *rec) { if (!tracing_is_on()) return; @@ -874,13 +876,13 @@ static struct event_command trigger_traceoff_cmd = { #ifdef CONFIG_TRACER_SNAPSHOT static void -snapshot_trigger(struct event_trigger_data *data) +snapshot_trigger(struct event_trigger_data *data, void *rec) { tracing_snapshot(); } static void -snapshot_count_trigger(struct event_trigger_data *data) +snapshot_count_trigger(struct event_trigger_data *data, void *rec) { if (!data->count) return; @@ -888,7 +890,7 @@ snapshot_count_trigger(struct event_trigger_data *data) if (data->count != -1) (data->count)--; - snapshot_trigger(data); + snapshot_trigger(data, rec); } static int @@ -967,13 +969,13 @@ static __init int register_trigger_snapshot_cmd(void) { return 0; } #define STACK_SKIP 3 static void -stacktrace_trigger(struct event_trigger_data *data) +stacktrace_trigger(struct event_trigger_data *data, void *rec) { trace_dump_stack(STACK_SKIP); } static void -stacktrace_count_trigger(struct event_trigger_data *data) +stacktrace_count_trigger(struct event_trigger_data *data, void *rec) { if (!data->count) return; @@ -981,7 +983,7 @@ stacktrace_count_trigger(struct event_trigger_data *data) if (data->count != -1) (data->count)--; - stacktrace_trigger(data); + stacktrace_trigger(data, rec); } static int @@ -1052,7 +1054,7 @@ struct enable_trigger_data { }; static void -event_enable_trigger(struct event_trigger_data *data) +event_enable_trigger(struct event_trigger_data *data, void *rec) { struct enable_trigger_data *enable_data = data->private_data; @@ -1063,7 +1065,7 @@ event_enable_trigger(struct event_trigger_data *data) } static void -event_enable_count_trigger(struct event_trigger_data *data) +event_enable_count_trigger(struct event_trigger_data *data, void *rec) { struct enable_trigger_data *enable_data = data->private_data; @@ -1077,7 +1079,7 @@ event_enable_count_trigger(struct event_trigger_data *data) if (data->count != -1) (data->count)--; - event_enable_trigger(data); + event_enable_trigger(data, rec); } static int -- cgit v1.1 From dbfeaa7abae4f105afdf8ed4f85b5879cff136ea Mon Sep 17 00:00:00 2001 From: Tom Zanussi Date: Thu, 10 Dec 2015 12:50:46 -0600 Subject: tracing: Add get_syscall_name() Add a utility function to grab the syscall name from the syscall metadata, given a syscall id. Link: http://lkml.kernel.org/r/be26a8dfe3f15e16a837799f1c1e2b4d62742843.1449767187.git.tom.zanussi@linux.intel.com Signed-off-by: Tom Zanussi Tested-by: Masami Hiramatsu Reviewed-by: Namhyung Kim Signed-off-by: Steven Rostedt --- kernel/trace/trace.h | 5 +++++ kernel/trace/trace_syscalls.c | 11 +++++++++++ 2 files changed, 16 insertions(+) (limited to 'kernel') diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index c10456e..0044b91 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -1394,8 +1394,13 @@ int perf_ftrace_event_register(struct trace_event_call *call, #ifdef CONFIG_FTRACE_SYSCALLS void init_ftrace_syscalls(void); +const char *get_syscall_name(int syscall); #else static inline void init_ftrace_syscalls(void) { } +static inline const char *get_syscall_name(int syscall) +{ + return NULL; +} #endif #ifdef CONFIG_EVENT_TRACING diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c index 0655afb..50be560 100644 --- a/kernel/trace/trace_syscalls.c +++ b/kernel/trace/trace_syscalls.c @@ -106,6 +106,17 @@ static struct syscall_metadata *syscall_nr_to_meta(int nr) return syscalls_metadata[nr]; } +const char *get_syscall_name(int syscall) +{ + struct syscall_metadata *entry; + + entry = syscall_nr_to_meta(syscall); + if (!entry) + return NULL; + + return entry->name; +} + static enum print_line_t print_syscall_enter(struct trace_iterator *iter, int flags, struct trace_event *event) -- cgit v1.1 From 104f281044a9c2ac86b851bbebbf74500172b625 Mon Sep 17 00:00:00 2001 From: Tom Zanussi Date: Thu, 10 Dec 2015 12:50:47 -0600 Subject: tracing: Add a per-event-trigger 'paused' field Add a simple per-trigger 'paused' flag, allowing individual triggers to pause. We could leave it to individual triggers that need this functionality to do it themselves, but we also want to allow other events to control pausing, so add it to the trigger data. Link: http://lkml.kernel.org/r/fed37e4879684d7dcc57fe00ce0cbf170032b06d.1449767187.git.tom.zanussi@linux.intel.com Signed-off-by: Tom Zanussi Tested-by: Masami Hiramatsu Reviewed-by: Namhyung Kim Signed-off-by: Steven Rostedt --- kernel/trace/trace.h | 1 + kernel/trace/trace_events_trigger.c | 4 ++++ 2 files changed, 5 insertions(+) (limited to 'kernel') diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 0044b91..f186867 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -1172,6 +1172,7 @@ struct event_trigger_data { struct event_filter __rcu *filter; char *filter_str; void *private_data; + bool paused; struct list_head list; }; diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c index 0a62887..e4d8b37 100644 --- a/kernel/trace/trace_events_trigger.c +++ b/kernel/trace/trace_events_trigger.c @@ -72,6 +72,8 @@ event_triggers_call(struct trace_event_file *file, void *rec) return tt; list_for_each_entry_rcu(data, &file->triggers, list) { + if (data->paused) + continue; if (!rec) { data->ops->func(data, rec); continue; @@ -110,6 +112,8 @@ event_triggers_post_call(struct trace_event_file *file, struct event_trigger_data *data; list_for_each_entry_rcu(data, &file->triggers, list) { + if (data->paused) + continue; if (data->cmd_ops->trigger_type & tt) data->ops->func(data, rec); } -- cgit v1.1 From a5863dae84e2da83a1e5de485a7f150d0c28f08e Mon Sep 17 00:00:00 2001 From: Tom Zanussi Date: Thu, 10 Dec 2015 12:50:48 -0600 Subject: tracing: Add needs_rec flag to event triggers Add a new needs_rec flag for triggers that require unconditional access to trace records in order to function. Normally a trigger requires access to the contents of a trace record only if it has a filter associated with it (since filters need the contents of a record in order to make a filtering decision). Some types of triggers, such as 'hist' triggers, require access to trace record contents independent of the presence of filters, so add a new flag for those triggers. Link: http://lkml.kernel.org/r/7be8fa38f9b90fdb6c47ca0f98d20a07b9fd512b.1449767187.git.tom.zanussi@linux.intel.com Signed-off-by: Tom Zanussi Tested-by: Masami Hiramatsu Reviewed-by: Namhyung Kim Signed-off-by: Steven Rostedt --- kernel/trace/trace.h | 7 +++++++ kernel/trace/trace_events_trigger.c | 3 ++- 2 files changed, 9 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index f186867..8c6aefb 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -1292,6 +1292,12 @@ struct event_trigger_ops { * itself logs to the trace buffer, this flag should be set, * otherwise it can be left unspecified. * + * @needs_rec: A flag that says whether or not this command needs + * access to the trace record in order to perform its function, + * regardless of whether or not it has a filter associated with + * it (filters make a trigger require access to the trace record + * but are not always present). + * * All the methods below, except for @set_filter(), must be * implemented. * @@ -1332,6 +1338,7 @@ struct event_command { char *name; enum event_trigger_type trigger_type; bool post_trigger; + bool needs_rec; int (*func)(struct event_command *cmd_ops, struct trace_event_file *file, char *glob, char *cmd, char *params); diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c index e4d8b37..a11bb47 100644 --- a/kernel/trace/trace_events_trigger.c +++ b/kernel/trace/trace_events_trigger.c @@ -493,7 +493,8 @@ void update_cond_flag(struct trace_event_file *file) bool set_cond = false; list_for_each_entry_rcu(data, &file->triggers, list) { - if (data->filter || data->cmd_ops->post_trigger) { + if (data->filter || data->cmd_ops->post_trigger || + data->cmd_ops->needs_rec) { set_cond = true; break; } -- cgit v1.1 From a88e1cfb1d3081ffb34864d9cf8a5c289630f48e Mon Sep 17 00:00:00 2001 From: Tom Zanussi Date: Thu, 10 Dec 2015 12:50:49 -0600 Subject: tracing: Add an unreg_all() callback to trigger commands Add a new unreg_all() callback that can be used to remove all command-specific triggers from an event and arrange to have it called whenever a trigger file is opened with O_TRUNC set. Commands that don't want truncate semantics, or existing commands that don't implement this function simply do nothing and their triggers remain intact. Link: http://lkml.kernel.org/r/2b7d62854d01f28c19185e1bbb8f826f385edfba.1449767187.git.tom.zanussi@linux.intel.com Signed-off-by: Tom Zanussi Reviewed-by: Namhyung Kim Signed-off-by: Steven Rostedt --- kernel/trace/trace.h | 9 +++++++-- kernel/trace/trace_events_trigger.c | 13 +++++++++++++ 2 files changed, 20 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 8c6aefb..f4dd0ad 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -1298,8 +1298,8 @@ struct event_trigger_ops { * it (filters make a trigger require access to the trace record * but are not always present). * - * All the methods below, except for @set_filter(), must be - * implemented. + * All the methods below, except for @set_filter() and @unreg_all(), + * must be implemented. * * @func: The callback function responsible for parsing and * registering the trigger written to the 'trigger' file by the @@ -1324,6 +1324,10 @@ struct event_trigger_ops { * This is usually implemented by the generic utility function * @unregister_trigger() (see trace_event_triggers.c). * + * @unreg_all: An optional function called to remove all the triggers + * from the list of triggers associated with the event. Called + * when a trigger file is opened in truncate mode. + * * @set_filter: An optional function called to parse and set a filter * for the trigger. If no @set_filter() method is set for the * event command, filters set by the user for the command will be @@ -1350,6 +1354,7 @@ struct event_command { struct event_trigger_ops *ops, struct event_trigger_data *data, struct trace_event_file *file); + void (*unreg_all)(struct trace_event_file *file); int (*set_filter)(char *filter_str, struct event_trigger_data *data, struct trace_event_file *file); diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c index a11bb47..cbb7ee5 100644 --- a/kernel/trace/trace_events_trigger.c +++ b/kernel/trace/trace_events_trigger.c @@ -193,6 +193,19 @@ static int event_trigger_regex_open(struct inode *inode, struct file *file) return -ENODEV; } + if ((file->f_mode & FMODE_WRITE) && + (file->f_flags & O_TRUNC)) { + struct trace_event_file *event_file; + struct event_command *p; + + event_file = event_file_data(file); + + list_for_each_entry(p, &trigger_commands, list) { + if (p->unreg_all) + p->unreg_all(event_file); + } + } + if (file->f_mode & FMODE_READ) { ret = seq_open(file, &event_triggers_seq_ops); if (!ret) { -- cgit v1.1 From 353206f5ca05eb65704b2b3ec9a331b4fdfd3257 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Mon, 22 Feb 2016 15:55:09 -0500 Subject: tracing: Use flags instead of bool in trigger structure gcc isn't known for handling bool in structures. Instead of using bool, use an integer mask and use bit flags instead. Signed-off-by: Steven Rostedt --- kernel/trace/trace.h | 71 +++++++++++++++++++++++-------------- kernel/trace/trace_events_trigger.c | 8 ++--- 2 files changed, 49 insertions(+), 30 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index f4dd0ad..39588c2 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -1273,30 +1273,7 @@ struct event_trigger_ops { * values are defined by adding new values to the trigger_type * enum in include/linux/trace_events.h. * - * @post_trigger: A flag that says whether or not this command needs - * to have its action delayed until after the current event has - * been closed. Some triggers need to avoid being invoked while - * an event is currently in the process of being logged, since - * the trigger may itself log data into the trace buffer. Thus - * we make sure the current event is committed before invoking - * those triggers. To do that, the trigger invocation is split - * in two - the first part checks the filter using the current - * trace record; if a command has the @post_trigger flag set, it - * sets a bit for itself in the return value, otherwise it - * directly invokes the trigger. Once all commands have been - * either invoked or set their return flag, the current record is - * either committed or discarded. At that point, if any commands - * have deferred their triggers, those commands are finally - * invoked following the close of the current event. In other - * words, if the event_trigger_ops @func() probe implementation - * itself logs to the trace buffer, this flag should be set, - * otherwise it can be left unspecified. - * - * @needs_rec: A flag that says whether or not this command needs - * access to the trace record in order to perform its function, - * regardless of whether or not it has a filter associated with - * it (filters make a trigger require access to the trace record - * but are not always present). + * @flags: See the enum event_command_flags below. * * All the methods below, except for @set_filter() and @unreg_all(), * must be implemented. @@ -1341,8 +1318,7 @@ struct event_command { struct list_head list; char *name; enum event_trigger_type trigger_type; - bool post_trigger; - bool needs_rec; + int flags; int (*func)(struct event_command *cmd_ops, struct trace_event_file *file, char *glob, char *cmd, char *params); @@ -1361,6 +1337,49 @@ struct event_command { struct event_trigger_ops *(*get_trigger_ops)(char *cmd, char *param); }; +/** + * enum event_command_flags - flags for struct event_command + * + * @POST_TRIGGER: A flag that says whether or not this command needs + * to have its action delayed until after the current event has + * been closed. Some triggers need to avoid being invoked while + * an event is currently in the process of being logged, since + * the trigger may itself log data into the trace buffer. Thus + * we make sure the current event is committed before invoking + * those triggers. To do that, the trigger invocation is split + * in two - the first part checks the filter using the current + * trace record; if a command has the @post_trigger flag set, it + * sets a bit for itself in the return value, otherwise it + * directly invokes the trigger. Once all commands have been + * either invoked or set their return flag, the current record is + * either committed or discarded. At that point, if any commands + * have deferred their triggers, those commands are finally + * invoked following the close of the current event. In other + * words, if the event_trigger_ops @func() probe implementation + * itself logs to the trace buffer, this flag should be set, + * otherwise it can be left unspecified. + * + * @NEEDS_REC: A flag that says whether or not this command needs + * access to the trace record in order to perform its function, + * regardless of whether or not it has a filter associated with + * it (filters make a trigger require access to the trace record + * but are not always present). + */ +enum event_command_flags { + EVENT_CMD_FL_POST_TRIGGER = 1, + EVENT_CMD_FL_NEEDS_REC = 2, +}; + +static inline bool event_command_post_trigger(struct event_command *cmd_ops) +{ + return cmd_ops->flags & EVENT_CMD_FL_POST_TRIGGER; +} + +static inline bool event_command_needs_rec(struct event_command *cmd_ops) +{ + return cmd_ops->flags & EVENT_CMD_FL_NEEDS_REC; +} + extern int trace_event_enable_disable(struct trace_event_file *file, int enable, int soft_disable); extern int tracing_alloc_snapshot(void); diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c index cbb7ee5..d67992f 100644 --- a/kernel/trace/trace_events_trigger.c +++ b/kernel/trace/trace_events_trigger.c @@ -81,7 +81,7 @@ event_triggers_call(struct trace_event_file *file, void *rec) filter = rcu_dereference_sched(data->filter); if (filter && !filter_match_preds(filter, rec)) continue; - if (data->cmd_ops->post_trigger) { + if (event_command_post_trigger(data->cmd_ops)) { tt |= data->cmd_ops->trigger_type; continue; } @@ -506,8 +506,8 @@ void update_cond_flag(struct trace_event_file *file) bool set_cond = false; list_for_each_entry_rcu(data, &file->triggers, list) { - if (data->filter || data->cmd_ops->post_trigger || - data->cmd_ops->needs_rec) { + if (data->filter || event_command_post_trigger(data->cmd_ops) || + event_command_needs_rec(data->cmd_ops)) { set_cond = true; break; } @@ -1035,7 +1035,7 @@ stacktrace_get_trigger_ops(char *cmd, char *param) static struct event_command trigger_stacktrace_cmd = { .name = "stacktrace", .trigger_type = ETT_STACKTRACE, - .post_trigger = true, + .flags = EVENT_CMD_FL_POST_TRIGGER, .func = event_trigger_callback, .reg = register_trigger, .unreg = unregister_trigger, -- cgit v1.1 From 1cf8067b541884366b7db3a328342073fed2f38f Mon Sep 17 00:00:00 2001 From: Chunyu Hu Date: Tue, 8 Mar 2016 21:37:02 +0800 Subject: tracing: Fix typoes in code comment and printk in trace_nop.c echo nop > /sys/kernel/debug/tracing/options/current_tracer echo 1 > /sys/kernel/debug/tracing/options/test_nop_accept echo 0 > /sys/kernel/debug/tracing/options/test_nop_accept echo 1 > /sys/kernel/debug/tracing/options/test_nop_refuse Before the fix, the dmesg is a bit ugly since a align issue. [ 191.973081] nop_test_accept flag set to 1: we accept. Now cat trace_options to see the result [ 195.156942] nop_test_refuse flag set to 1: we refuse.Now cat trace_options to see the result After the fix, the dmesg will show aligned log for nop_test_refuse and nop_test_accept. [ 2718.032413] nop_test_refuse flag set to 1: we refuse. Now cat trace_options to see the result [ 2734.253360] nop_test_accept flag set to 1: we accept. Now cat trace_options to see the result Link: http://lkml.kernel.org/r/1457444222-8654-2-git-send-email-chuhu@redhat.com Signed-off-by: Chunyu Hu Signed-off-by: Steven Rostedt --- kernel/trace/trace_nop.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace_nop.c b/kernel/trace/trace_nop.c index 8bb2071..49f61fe9 100644 --- a/kernel/trace/trace_nop.c +++ b/kernel/trace/trace_nop.c @@ -56,7 +56,7 @@ static void nop_trace_reset(struct trace_array *tr) } /* It only serves as a signal handler and a callback to - * accept or refuse tthe setting of a flag. + * accept or refuse the setting of a flag. * If you don't implement it, then the flag setting will be * automatically accepted. */ @@ -75,7 +75,7 @@ static int nop_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set) if (bit == TRACE_NOP_OPT_REFUSE) { printk(KERN_DEBUG "nop_test_refuse flag set to %d: we refuse." - "Now cat trace_options to see the result\n", + " Now cat trace_options to see the result\n", set); return -EINVAL; } -- cgit v1.1 From 84b6d3e6149c5280bc18b42e2f12efdaf354e49c Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 16 Mar 2016 15:34:32 +0100 Subject: ftrace: Make ftrace_hash_rec_enable return update bool Change __ftrace_hash_rec_update to return true in case we need to update dynamic ftrace call records. It return false in case no update is needed. Link: http://lkml.kernel.org/r/1458138873-1553-5-git-send-email-jolsa@kernel.org Acked-by: Namhyung Kim Signed-off-by: Jiri Olsa Signed-off-by: Steven Rostedt --- kernel/trace/ftrace.c | 27 +++++++++++++++++---------- 1 file changed, 17 insertions(+), 10 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 57a6eea..11ffcfd3 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1610,7 +1610,7 @@ static bool test_rec_ops_needs_regs(struct dyn_ftrace *rec) return keep_regs; } -static void __ftrace_hash_rec_update(struct ftrace_ops *ops, +static bool __ftrace_hash_rec_update(struct ftrace_ops *ops, int filter_hash, bool inc) { @@ -1618,12 +1618,13 @@ static void __ftrace_hash_rec_update(struct ftrace_ops *ops, struct ftrace_hash *other_hash; struct ftrace_page *pg; struct dyn_ftrace *rec; + bool update = false; int count = 0; int all = 0; /* Only update if the ops has been registered */ if (!(ops->flags & FTRACE_OPS_FL_ENABLED)) - return; + return false; /* * In the filter_hash case: @@ -1650,7 +1651,7 @@ static void __ftrace_hash_rec_update(struct ftrace_ops *ops, * then there's nothing to do. */ if (ftrace_hash_empty(hash)) - return; + return false; } do_for_each_ftrace_rec(pg, rec) { @@ -1694,7 +1695,7 @@ static void __ftrace_hash_rec_update(struct ftrace_ops *ops, if (inc) { rec->flags++; if (FTRACE_WARN_ON(ftrace_rec_count(rec) == FTRACE_REF_MAX)) - return; + return false; /* * If there's only a single callback registered to a @@ -1720,7 +1721,7 @@ static void __ftrace_hash_rec_update(struct ftrace_ops *ops, rec->flags |= FTRACE_FL_REGS; } else { if (FTRACE_WARN_ON(ftrace_rec_count(rec) == 0)) - return; + return false; rec->flags--; /* @@ -1753,22 +1754,28 @@ static void __ftrace_hash_rec_update(struct ftrace_ops *ops, */ } count++; + + /* Must match FTRACE_UPDATE_CALLS in ftrace_modify_all_code() */ + update |= ftrace_test_record(rec, 1) != FTRACE_UPDATE_IGNORE; + /* Shortcut, if we handled all records, we are done. */ if (!all && count == hash->count) - return; + return update; } while_for_each_ftrace_rec(); + + return update; } -static void ftrace_hash_rec_disable(struct ftrace_ops *ops, +static bool ftrace_hash_rec_disable(struct ftrace_ops *ops, int filter_hash) { - __ftrace_hash_rec_update(ops, filter_hash, 0); + return __ftrace_hash_rec_update(ops, filter_hash, 0); } -static void ftrace_hash_rec_enable(struct ftrace_ops *ops, +static bool ftrace_hash_rec_enable(struct ftrace_ops *ops, int filter_hash) { - __ftrace_hash_rec_update(ops, filter_hash, 1); + return __ftrace_hash_rec_update(ops, filter_hash, 1); } static void ftrace_hash_rec_update_modify(struct ftrace_ops *ops, -- cgit v1.1 From 7f50d06bb6b825d34f069c6c7a1aab96ad0b94d9 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 16 Mar 2016 15:34:33 +0100 Subject: ftrace: Update dynamic ftrace calls only if necessary Currently dynamic ftrace calls are updated any time the ftrace_ops is un/registered. If we do this update only when it's needed, we save lot of time for perf system wide ftrace function sampling/counting. The reason is that for system wide sampling/counting, perf creates event for each cpu in the system. Each event then registers separate copy of ftrace_ops, which ends up in FTRACE_UPDATE_CALLS updates. On servers with many cpus that means serious stall (240 cpus server): Counting: # time ./perf stat -e ftrace:function -a sleep 1 Performance counter stats for 'system wide': 370,663 ftrace:function 1.401427505 seconds time elapsed real 3m51.743s user 0m0.023s sys 3m48.569s Sampling: # time ./perf record -e ftrace:function -a sleep 1 [ perf record: Woken up 0 times to write data ] Warning: Processed 141200 events and lost 5 chunks! [ perf record: Captured and wrote 10.703 MB perf.data (135950 samples) ] real 2m31.429s user 0m0.213s sys 2m29.494s There's no reason to do the FTRACE_UPDATE_CALLS update for each event in perf case, because all the ftrace_ops always share the same filter, so the updated calls are always the same. It's required that only first ftrace_ops registration does the FTRACE_UPDATE_CALLS update (also sometimes the second if the first one used the trampoline), but the rest can be only cheaply linked into the ftrace_ops list. Counting: # time ./perf stat -e ftrace:function -a sleep 1 Performance counter stats for 'system wide': 398,571 ftrace:function 1.377503733 seconds time elapsed real 0m2.787s user 0m0.005s sys 0m1.883s Sampling: # time ./perf record -e ftrace:function -a sleep 1 [ perf record: Woken up 0 times to write data ] Warning: Processed 261730 events and lost 9 chunks! [ perf record: Captured and wrote 19.907 MB perf.data (256293 samples) ] real 1m31.948s user 0m0.309s sys 1m32.051s Link: http://lkml.kernel.org/r/1458138873-1553-6-git-send-email-jolsa@kernel.org Acked-by: Namhyung Kim Signed-off-by: Jiri Olsa Signed-off-by: Steven Rostedt --- kernel/trace/ftrace.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 11ffcfd3..d3850cb 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -2651,7 +2651,6 @@ static int ftrace_startup(struct ftrace_ops *ops, int command) return ret; ftrace_start_up++; - command |= FTRACE_UPDATE_CALLS; /* * Note that ftrace probes uses this to start up @@ -2672,7 +2671,8 @@ static int ftrace_startup(struct ftrace_ops *ops, int command) return ret; } - ftrace_hash_rec_enable(ops, 1); + if (ftrace_hash_rec_enable(ops, 1)) + command |= FTRACE_UPDATE_CALLS; ftrace_startup_enable(command); @@ -2702,11 +2702,11 @@ static int ftrace_shutdown(struct ftrace_ops *ops, int command) /* Disabling ipmodify never fails */ ftrace_hash_ipmodify_disable(ops); - ftrace_hash_rec_disable(ops, 1); - ops->flags &= ~FTRACE_OPS_FL_ENABLED; + if (ftrace_hash_rec_disable(ops, 1)) + command |= FTRACE_UPDATE_CALLS; - command |= FTRACE_UPDATE_CALLS; + ops->flags &= ~FTRACE_OPS_FL_ENABLED; if (saved_ftrace_func != ftrace_trace_function) { saved_ftrace_func = ftrace_trace_function; -- cgit v1.1 From 6363c6b599ae67b779d01a48642a7c0d7d721814 Mon Sep 17 00:00:00 2001 From: Geliang Tang Date: Tue, 15 Mar 2016 22:12:34 +0800 Subject: ftrace: Use kasprintf() in ftrace_profile_tracefs() Use kasprintf() instead of kmalloc() and snprintf(). Link: http://lkml.kernel.org/r/135a7bc36e51fd9eaa57124dd2140285b771f738.1458050835.git.geliangtang@163.com Acked-by: Namhyung Kim Signed-off-by: Geliang Tang Signed-off-by: Steven Rostedt --- kernel/trace/ftrace.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index d3850cb..6a93faa 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1030,8 +1030,7 @@ static __init void ftrace_profile_tracefs(struct dentry *d_tracer) for_each_possible_cpu(cpu) { stat = &per_cpu(ftrace_profile_stats, cpu); - /* allocate enough for function name + cpu number */ - name = kmalloc(32, GFP_KERNEL); + name = kasprintf(GFP_KERNEL, "function%d", cpu); if (!name) { /* * The files created are permanent, if something happens @@ -1043,7 +1042,6 @@ static __init void ftrace_profile_tracefs(struct dentry *d_tracer) return; } stat->stat = function_stats; - snprintf(name, 32, "function%d", cpu); stat->stat.name = name; ret = register_stat_tracer(&stat->stat); if (ret) { -- cgit v1.1 From c8ca003b2fde177b83de87f9f20f6a5933fb50bf Mon Sep 17 00:00:00 2001 From: Chunyu Hu Date: Mon, 14 Mar 2016 20:35:41 +0800 Subject: tracing: Fix return while holding a lock in register_tracer() commit d39cdd2036a6 ("tracing: Make tracer_flags use the right set_flag callback") introduces a potential mutex deadlock issue, as it forgets to free the mutex when allocaing the tracer_flags gets fail. The issue was found by Dan Carpenter through Smatch static code check tool. Link: http://lkml.kernel.org/r/1457958941-30265-1-git-send-email-chuhu@redhat.com Fixes: d39cdd2036a6 ("tracing: Make tracer_flags use the right set_flag callback") Reported-by: Dan Carpenter Signed-off-by: Chunyu Hu Signed-off-by: Steven Rostedt --- kernel/trace/trace.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index b401a18..0ae4604 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1256,8 +1256,10 @@ int __init register_tracer(struct tracer *type) if (!type->flags) { /*allocate a dummy tracer_flags*/ type->flags = kmalloc(sizeof(*type->flags), GFP_KERNEL); - if (!type->flags) - return -ENOMEM; + if (!type->flags) { + ret = -ENOMEM; + goto out; + } type->flags->val = 0; type->flags->opts = dummy_tracer_opt; } else -- cgit v1.1 From cb86e05390debcc084cfdb0a71ed4c5dbbec517d Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Fri, 18 Mar 2016 12:27:43 -0400 Subject: tracing: Have preempt(irqs)off trace preempt disabled functions Joel Fernandes reported that the function tracing of preempt disabled sections was not being reported when running either the preemptirqsoff or preemptoff tracers. This was due to the fact that the function tracer callback for those tracers checked if irqs were disabled before tracing. But this fails when we want to trace preempt off locations as well. Joel explained that he wanted to see funcitons where interrupts are enabled but preemption was disabled. The expected output he wanted: <...>-2265 1d.h1 3419us : preempt_count_sub <-irq_exit <...>-2265 1d..1 3419us : __do_softirq <-irq_exit <...>-2265 1d..1 3419us : msecs_to_jiffies <-__do_softirq <...>-2265 1d..1 3420us : irqtime_account_irq <-__do_softirq <...>-2265 1d..1 3420us : __local_bh_disable_ip <-__do_softirq <...>-2265 1..s1 3421us : run_timer_softirq <-__do_softirq <...>-2265 1..s1 3421us : hrtimer_run_pending <-run_timer_softirq <...>-2265 1..s1 3421us : _raw_spin_lock_irq <-run_timer_softirq <...>-2265 1d.s1 3422us : preempt_count_add <-_raw_spin_lock_irq <...>-2265 1d.s2 3422us : _raw_spin_unlock_irq <-run_timer_softirq <...>-2265 1..s2 3422us : preempt_count_sub <-_raw_spin_unlock_irq <...>-2265 1..s1 3423us : rcu_bh_qs <-__do_softirq <...>-2265 1d.s1 3423us : irqtime_account_irq <-__do_softirq <...>-2265 1d.s1 3423us : __local_bh_enable <-__do_softirq There's a comment saying that the irq disabled check is because there's a possible race that tracing_cpu may be set when the function is executed. But I don't remember that race. For now, I added a check for preemption being enabled too to not record the function, as there would be no race if that was the case. I need to re-investigate this, as I'm now thinking that the tracing_cpu will always be correct. But no harm in keeping the check for now, except for the slight performance hit. Link: http://lkml.kernel.org/r/1457770386-88717-1-git-send-email-agnel.joel@gmail.com Fixes: 5e6d2b9cfa3a "tracing: Use one prologue for the preempt irqs off tracer function tracers" Cc: stable@vget.kernel.org # 2.6.37+ Reported-by: Joel Fernandes Signed-off-by: Steven Rostedt --- kernel/trace/trace_irqsoff.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c index e4e5658..be3222b 100644 --- a/kernel/trace/trace_irqsoff.c +++ b/kernel/trace/trace_irqsoff.c @@ -109,8 +109,12 @@ static int func_prolog_dec(struct trace_array *tr, return 0; local_save_flags(*flags); - /* slight chance to get a false positive on tracing_cpu */ - if (!irqs_disabled_flags(*flags)) + /* + * Slight chance to get a false positive on tracing_cpu, + * although I'm starting to think there isn't a chance. + * Leave this for now just to be paranoid. + */ + if (!irqs_disabled_flags(*flags) && !preempt_count()) return 0; *data = per_cpu_ptr(tr->trace_buffer.data, cpu); -- cgit v1.1 From a29054d9478d0435ab01b7544da4f674ab13f533 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Fri, 18 Mar 2016 15:46:48 -0400 Subject: tracing: Fix crash from reading trace_pipe with sendfile If tracing contains data and the trace_pipe file is read with sendfile(), then it can trigger a NULL pointer dereference and various BUG_ON within the VM code. There's a patch to fix this in the splice_to_pipe() code, but it's also a good idea to not let that happen from trace_pipe either. Link: http://lkml.kernel.org/r/1457641146-9068-1-git-send-email-rabin@rab.in Cc: stable@vger.kernel.org # 2.6.30+ Reported-by: Rabin Vincent Signed-off-by: Steven Rostedt --- kernel/trace/trace.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 0ae4604..cb2b708 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -4954,7 +4954,10 @@ static ssize_t tracing_splice_read_pipe(struct file *filp, spd.nr_pages = i; - ret = splice_to_pipe(pipe, &spd); + if (i) + ret = splice_to_pipe(pipe, &spd); + else + ret = 0; out: splice_shrink_spd(&spd); return ret; -- cgit v1.1 From 741f3a69f101250dc6b171b88e14ea51b099b1a9 Mon Sep 17 00:00:00 2001 From: Dmitry Safonov <0x7f454c46@gmail.com> Date: Mon, 19 Oct 2015 21:10:26 +0300 Subject: tracing: Remove redundant reset per-CPU buff in irqsoff tracer There is no reason to do it twice: from commit b6f11df26fdc28 ("trace: Call tracing_reset_online_cpus before tracer->init()") resetting of per-CPU buffers done before tracer->init() call. tracer->init() calls {irqs,preempt,preemptirqs}off_tracer_init() and it calls __irqsoff_tracer_init(), which resets per-CPU ringbuffer second time. It's slowpath, but anyway. Link: http://lkml.kernel.org/r/1445278226-16187-1-git-send-email-0x7f454c46@gmail.com Signed-off-by: Dmitry Safonov <0x7f454c46@gmail.com> Signed-off-by: Steven Rostedt --- kernel/trace/trace_irqsoff.c | 1 - 1 file changed, 1 deletion(-) (limited to 'kernel') diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c index be3222b..03cdff8 100644 --- a/kernel/trace/trace_irqsoff.c +++ b/kernel/trace/trace_irqsoff.c @@ -626,7 +626,6 @@ static int __irqsoff_tracer_init(struct trace_array *tr) irqsoff_trace = tr; /* make sure that the tracer is visible */ smp_wmb(); - tracing_reset_online_cpus(&tr->trace_buffer); ftrace_init_array_ops(tr, irqsoff_tracer_call); -- cgit v1.1 From 3debb0a9ddb16526de8b456491b7db60114f7b5e Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Tue, 22 Mar 2016 17:30:58 -0400 Subject: tracing: Fix trace_printk() to print when not using bprintk() The trace_printk() code will allocate extra buffers if the compile detects that a trace_printk() is used. To do this, the format of the trace_printk() is saved to the __trace_printk_fmt section, and if that section is bigger than zero, the buffers are allocated (along with a message that this has happened). If trace_printk() uses a format that is not a constant, and thus something not guaranteed to be around when the print happens, the compiler optimizes the fmt out, as it is not used, and the __trace_printk_fmt section is not filled. This means the kernel will not allocate the special buffers needed for the trace_printk() and the trace_printk() will not write anything to the tracing buffer. Adding a "__used" to the variable in the __trace_printk_fmt section will keep it around, even though it is set to NULL. This will keep the string from being printed in the debugfs/tracing/printk_formats section as it is not needed. Reported-by: Vlastimil Babka Fixes: 07d777fe8c398 "tracing: Add percpu buffers for trace_printk()" Cc: stable@vger.kernel.org # v3.5+ Signed-off-by: Steven Rostedt --- kernel/trace/trace_printk.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'kernel') diff --git a/kernel/trace/trace_printk.c b/kernel/trace/trace_printk.c index 060df67..f96f038 100644 --- a/kernel/trace/trace_printk.c +++ b/kernel/trace/trace_printk.c @@ -296,6 +296,9 @@ static int t_show(struct seq_file *m, void *v) const char *str = *fmt; int i; + if (!*fmt) + return 0; + seq_printf(m, "0x%lx : \"", *(unsigned long *)fmt); /* -- cgit v1.1 From 7e6867bf831c71fe0e47438831ae3a94d4c7ab3c Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 18 Mar 2016 16:28:04 +0100 Subject: tracing: Record and show NMI state The latency tracer format has a nice column to indicate IRQ state, but this is not able to tell us about NMI state. When tracing perf interrupt handlers (which often run in NMI context) it is very useful to see how the events nest. Link: http://lkml.kernel.org/r/20160318153022.105068893@infradead.org Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Steven Rostedt --- kernel/trace/trace.c | 1 + kernel/trace/trace.h | 1 + kernel/trace/trace_output.c | 10 +++++++--- 3 files changed, 9 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index cb2b708..7bdf8ba 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1664,6 +1664,7 @@ tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags, #else TRACE_FLAG_IRQS_NOSUPPORT | #endif + ((pc & NMI_MASK ) ? TRACE_FLAG_NMI : 0) | ((pc & HARDIRQ_MASK) ? TRACE_FLAG_HARDIRQ : 0) | ((pc & SOFTIRQ_MASK) ? TRACE_FLAG_SOFTIRQ : 0) | (tif_need_resched() ? TRACE_FLAG_NEED_RESCHED : 0) | diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 39588c2..3fff4ad 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -125,6 +125,7 @@ enum trace_flag_type { TRACE_FLAG_HARDIRQ = 0x08, TRACE_FLAG_SOFTIRQ = 0x10, TRACE_FLAG_PREEMPT_RESCHED = 0x20, + TRACE_FLAG_NMI = 0x40, }; #define TRACE_BUF_SIZE 1024 diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index 2829821..0bb9cf2 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -389,7 +389,9 @@ int trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry) char irqs_off; int hardirq; int softirq; + int nmi; + nmi = entry->flags & TRACE_FLAG_NMI; hardirq = entry->flags & TRACE_FLAG_HARDIRQ; softirq = entry->flags & TRACE_FLAG_SOFTIRQ; @@ -415,10 +417,12 @@ int trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry) } hardsoft_irq = + (nmi && hardirq) ? 'Z' : + nmi ? 'z' : (hardirq && softirq) ? 'H' : - hardirq ? 'h' : - softirq ? 's' : - '.'; + hardirq ? 'h' : + softirq ? 's' : + '.' ; trace_seq_printf(s, "%c%c%c", irqs_off, need_resched, hardsoft_irq); -- cgit v1.1