From 8f0820183056ad26dabc0202115848a92f1143fc Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Tue, 20 Apr 2010 10:47:33 -0400 Subject: tracing: Create class struct for events This patch creates a ftrace_event_class struct that event structs point to. This class struct will be made to hold information to modify the events. Currently the class struct only holds the events system name. This patch slightly increases the size, but this change lays the ground work of other changes to make the footprint of tracepoints smaller. With 82 standard tracepoints, and 618 system call tracepoints (two tracepoints per syscall: enter and exit): text data bss dec hex filename 4913961 1088356 861512 6863829 68bbd5 vmlinux.orig 4914025 1088868 861512 6864405 68be15 vmlinux.class This patch also cleans up some stale comments in ftrace.h. v2: Fixed missing semi-colon in macro. Acked-by: Frederic Weisbecker Acked-by: Mathieu Desnoyers Acked-by: Masami Hiramatsu Signed-off-by: Steven Rostedt --- kernel/trace/trace_events.c | 20 ++++++++++---------- kernel/trace/trace_events_filter.c | 6 +++--- kernel/trace/trace_export.c | 6 +++++- kernel/trace/trace_kprobe.c | 12 ++++++------ kernel/trace/trace_syscalls.c | 4 ++++ 5 files changed, 28 insertions(+), 20 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index c697c7043349..2f54b48d3632 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -176,10 +176,10 @@ static int __ftrace_set_clr_event(const char *match, const char *sub, if (match && strcmp(match, call->name) != 0 && - strcmp(match, call->system) != 0) + strcmp(match, call->class->system) != 0) continue; - if (sub && strcmp(sub, call->system) != 0) + if (sub && strcmp(sub, call->class->system) != 0) continue; if (event && strcmp(event, call->name) != 0) @@ -355,8 +355,8 @@ static int t_show(struct seq_file *m, void *v) { struct ftrace_event_call *call = v; - if (strcmp(call->system, TRACE_SYSTEM) != 0) - seq_printf(m, "%s:", call->system); + if (strcmp(call->class->system, TRACE_SYSTEM) != 0) + seq_printf(m, "%s:", call->class->system); seq_printf(m, "%s\n", call->name); return 0; @@ -453,7 +453,7 @@ system_enable_read(struct file *filp, char __user *ubuf, size_t cnt, if (!call->name || !call->regfunc) continue; - if (system && strcmp(call->system, system) != 0) + if (system && strcmp(call->class->system, system) != 0) continue; /* @@ -925,8 +925,8 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events, * If the trace point header did not define TRACE_SYSTEM * then the system would be called "TRACE_SYSTEM". */ - if (strcmp(call->system, TRACE_SYSTEM) != 0) - d_events = event_subsystem_dir(call->system, d_events); + if (strcmp(call->class->system, TRACE_SYSTEM) != 0) + d_events = event_subsystem_dir(call->class->system, d_events); call->dir = debugfs_create_dir(call->name, d_events); if (!call->dir) { @@ -1041,7 +1041,7 @@ static void __trace_remove_event_call(struct ftrace_event_call *call) list_del(&call->list); trace_destroy_fields(call); destroy_preds(call); - remove_subsystem_dir(call->system); + remove_subsystem_dir(call->class->system); } /* Remove an event_call */ @@ -1399,8 +1399,8 @@ static __init void event_trace_self_tests(void) * syscalls as we test. */ #ifndef CONFIG_EVENT_TRACE_TEST_SYSCALLS - if (call->system && - strcmp(call->system, "syscalls") == 0) + if (call->class->system && + strcmp(call->class->system, "syscalls") == 0) continue; #endif diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index 88c0b6dbd7fe..ca329603d0bf 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -628,7 +628,7 @@ static int init_subsystem_preds(struct event_subsystem *system) if (!call->define_fields) continue; - if (strcmp(call->system, system->name) != 0) + if (strcmp(call->class->system, system->name) != 0) continue; err = init_preds(call); @@ -647,7 +647,7 @@ static void filter_free_subsystem_preds(struct event_subsystem *system) if (!call->define_fields) continue; - if (strcmp(call->system, system->name) != 0) + if (strcmp(call->class->system, system->name) != 0) continue; filter_disable_preds(call); @@ -1252,7 +1252,7 @@ static int replace_system_preds(struct event_subsystem *system, if (!call->define_fields) continue; - if (strcmp(call->system, system->name) != 0) + if (strcmp(call->class->system, system->name) != 0) continue; /* try to see if the filter can be applied */ diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c index e091f64ba6ce..7f16e2163817 100644 --- a/kernel/trace/trace_export.c +++ b/kernel/trace/trace_export.c @@ -18,6 +18,10 @@ #undef TRACE_SYSTEM #define TRACE_SYSTEM ftrace +struct ftrace_event_class event_class_ftrace = { + .system = __stringify(TRACE_SYSTEM), +}; + /* not needed for this file */ #undef __field_struct #define __field_struct(type, item) @@ -160,7 +164,7 @@ __attribute__((__aligned__(4))) \ __attribute__((section("_ftrace_events"))) event_##call = { \ .name = #call, \ .id = type, \ - .system = __stringify(TRACE_SYSTEM), \ + .class = &event_class_ftrace, \ .raw_init = ftrace_raw_init_event, \ .print_fmt = print, \ .define_fields = ftrace_define_fields_##call, \ diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 1251e367bae9..eda220bf2065 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -332,8 +332,8 @@ static struct trace_probe *alloc_trace_probe(const char *group, goto error; } - tp->call.system = kstrdup(group, GFP_KERNEL); - if (!tp->call.system) + tp->call.class->system = kstrdup(group, GFP_KERNEL); + if (!tp->call.class->system) goto error; INIT_LIST_HEAD(&tp->list); @@ -361,7 +361,7 @@ static void free_trace_probe(struct trace_probe *tp) for (i = 0; i < tp->nr_args; i++) free_probe_arg(&tp->args[i]); - kfree(tp->call.system); + kfree(tp->call.class->system); kfree(tp->call.name); kfree(tp->symbol); kfree(tp); @@ -374,7 +374,7 @@ static struct trace_probe *find_probe_event(const char *event, list_for_each_entry(tp, &probe_list, list) if (strcmp(tp->call.name, event) == 0 && - strcmp(tp->call.system, group) == 0) + strcmp(tp->call.class->system, group) == 0) return tp; return NULL; } @@ -399,7 +399,7 @@ static int register_trace_probe(struct trace_probe *tp) mutex_lock(&probe_lock); /* register as an event */ - old_tp = find_probe_event(tp->call.name, tp->call.system); + old_tp = find_probe_event(tp->call.name, tp->call.class->system); if (old_tp) { /* delete old event */ unregister_trace_probe(old_tp); @@ -798,7 +798,7 @@ static int probes_seq_show(struct seq_file *m, void *v) char buf[MAX_ARGSTR_LEN + 1]; seq_printf(m, "%c", probe_is_return(tp) ? 'r' : 'p'); - seq_printf(m, ":%s/%s", tp->call.system, tp->call.name); + seq_printf(m, ":%s/%s", tp->call.class->system, tp->call.name); if (!tp->symbol) seq_printf(m, " 0x%p", tp->rp.kp.addr); diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c index 4d6d711717f2..d036a74a64f3 100644 --- a/kernel/trace/trace_syscalls.c +++ b/kernel/trace/trace_syscalls.c @@ -15,6 +15,10 @@ static int sys_refcount_exit; static DECLARE_BITMAP(enabled_enter_syscalls, NR_syscalls); static DECLARE_BITMAP(enabled_exit_syscalls, NR_syscalls); +struct ftrace_event_class event_class_syscalls = { + .system = "syscalls" +}; + extern unsigned long __start_syscalls_metadata[]; extern unsigned long __stop_syscalls_metadata[]; -- cgit v1.2.1 From 38516ab59fbc5b3bb278cf5e1fe2867c70cff32e Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Tue, 20 Apr 2010 17:04:50 -0400 Subject: tracing: Let tracepoints have data passed to tracepoint callbacks This patch adds data to be passed to tracepoint callbacks. The created functions from DECLARE_TRACE() now need a mandatory data parameter. For example: DECLARE_TRACE(mytracepoint, int value, value) Will create the register function: int register_trace_mytracepoint((void(*)(void *data, int value))probe, void *data); As the first argument, all callbacks (probes) must take a (void *data) parameter. So a callback for the above tracepoint will look like: void myprobe(void *data, int value) { } The callback may choose to ignore the data parameter. This change allows callbacks to register a private data pointer along with the function probe. void mycallback(void *data, int value); register_trace_mytracepoint(mycallback, mydata); Then the mycallback() will receive the "mydata" as the first parameter before the args. A more detailed example: DECLARE_TRACE(mytracepoint, TP_PROTO(int status), TP_ARGS(status)); /* In the C file */ DEFINE_TRACE(mytracepoint, TP_PROTO(int status), TP_ARGS(status)); [...] trace_mytracepoint(status); /* In a file registering this tracepoint */ int my_callback(void *data, int status) { struct my_struct my_data = data; [...] } [...] my_data = kmalloc(sizeof(*my_data), GFP_KERNEL); init_my_data(my_data); register_trace_mytracepoint(my_callback, my_data); The same callback can also be registered to the same tracepoint as long as the data registered is different. Note, the data must also be used to unregister the callback: unregister_trace_mytracepoint(my_callback, my_data); Because of the data parameter, tracepoints declared this way can not have no args. That is: DECLARE_TRACE(mytracepoint, TP_PROTO(void), TP_ARGS()); will cause an error. If no arguments are needed, a new macro can be used instead: DECLARE_TRACE_NOARGS(mytracepoint); Since there are no arguments, the proto and args fields are left out. This is part of a series to make the tracepoint footprint smaller: text data bss dec hex filename 4913961 1088356 861512 6863829 68bbd5 vmlinux.orig 4914025 1088868 861512 6864405 68be15 vmlinux.class 4918492 1084612 861512 6864616 68bee8 vmlinux.tracepoint Again, this patch also increases the size of the kernel, but lays the ground work for decreasing it. v5: Fixed net/core/drop_monitor.c to handle these updates. v4: Moved the DECLARE_TRACE() DECLARE_TRACE_NOARGS out of the #ifdef CONFIG_TRACE_POINTS, since the two are the same in both cases. The __DECLARE_TRACE() is what changes. Thanks to Frederic Weisbecker for pointing this out. v3: Made all register_* functions require data to be passed and all callbacks to take a void * parameter as its first argument. This makes the calling functions comply with C standards. Also added more comments to the modifications of DECLARE_TRACE(). v2: Made the DECLARE_TRACE() have the ability to pass arguments and added a new DECLARE_TRACE_NOARGS() for tracepoints that do not need any arguments. Acked-by: Mathieu Desnoyers Acked-by: Masami Hiramatsu Acked-by: Frederic Weisbecker Cc: Neil Horman Cc: David S. Miller Signed-off-by: Steven Rostedt --- kernel/trace/blktrace.c | 125 +++++++++++++++++++++----------------- kernel/trace/ftrace.c | 7 ++- kernel/trace/kmemtrace.c | 42 +++++++------ kernel/trace/trace_sched_switch.c | 20 +++--- kernel/trace/trace_sched_wakeup.c | 28 +++++---- kernel/trace/trace_syscalls.c | 24 ++++---- kernel/trace/trace_workqueue.c | 26 ++++---- kernel/tracepoint.c | 91 +++++++++++++++------------ 8 files changed, 201 insertions(+), 162 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index b3bc91a3f510..19d93f83e3c3 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -675,28 +675,33 @@ static void blk_add_trace_rq(struct request_queue *q, struct request *rq, } } -static void blk_add_trace_rq_abort(struct request_queue *q, struct request *rq) +static void blk_add_trace_rq_abort(void *ignore, + struct request_queue *q, struct request *rq) { blk_add_trace_rq(q, rq, BLK_TA_ABORT); } -static void blk_add_trace_rq_insert(struct request_queue *q, struct request *rq) +static void blk_add_trace_rq_insert(void *ignore, + struct request_queue *q, struct request *rq) { blk_add_trace_rq(q, rq, BLK_TA_INSERT); } -static void blk_add_trace_rq_issue(struct request_queue *q, struct request *rq) +static void blk_add_trace_rq_issue(void *ignore, + struct request_queue *q, struct request *rq) { blk_add_trace_rq(q, rq, BLK_TA_ISSUE); } -static void blk_add_trace_rq_requeue(struct request_queue *q, +static void blk_add_trace_rq_requeue(void *ignore, + struct request_queue *q, struct request *rq) { blk_add_trace_rq(q, rq, BLK_TA_REQUEUE); } -static void blk_add_trace_rq_complete(struct request_queue *q, +static void blk_add_trace_rq_complete(void *ignore, + struct request_queue *q, struct request *rq) { blk_add_trace_rq(q, rq, BLK_TA_COMPLETE); @@ -724,34 +729,40 @@ static void blk_add_trace_bio(struct request_queue *q, struct bio *bio, !bio_flagged(bio, BIO_UPTODATE), 0, NULL); } -static void blk_add_trace_bio_bounce(struct request_queue *q, struct bio *bio) +static void blk_add_trace_bio_bounce(void *ignore, + struct request_queue *q, struct bio *bio) { blk_add_trace_bio(q, bio, BLK_TA_BOUNCE); } -static void blk_add_trace_bio_complete(struct request_queue *q, struct bio *bio) +static void blk_add_trace_bio_complete(void *ignore, + struct request_queue *q, struct bio *bio) { blk_add_trace_bio(q, bio, BLK_TA_COMPLETE); } -static void blk_add_trace_bio_backmerge(struct request_queue *q, +static void blk_add_trace_bio_backmerge(void *ignore, + struct request_queue *q, struct bio *bio) { blk_add_trace_bio(q, bio, BLK_TA_BACKMERGE); } -static void blk_add_trace_bio_frontmerge(struct request_queue *q, +static void blk_add_trace_bio_frontmerge(void *ignore, + struct request_queue *q, struct bio *bio) { blk_add_trace_bio(q, bio, BLK_TA_FRONTMERGE); } -static void blk_add_trace_bio_queue(struct request_queue *q, struct bio *bio) +static void blk_add_trace_bio_queue(void *ignore, + struct request_queue *q, struct bio *bio) { blk_add_trace_bio(q, bio, BLK_TA_QUEUE); } -static void blk_add_trace_getrq(struct request_queue *q, +static void blk_add_trace_getrq(void *ignore, + struct request_queue *q, struct bio *bio, int rw) { if (bio) @@ -765,7 +776,8 @@ static void blk_add_trace_getrq(struct request_queue *q, } -static void blk_add_trace_sleeprq(struct request_queue *q, +static void blk_add_trace_sleeprq(void *ignore, + struct request_queue *q, struct bio *bio, int rw) { if (bio) @@ -779,7 +791,7 @@ static void blk_add_trace_sleeprq(struct request_queue *q, } } -static void blk_add_trace_plug(struct request_queue *q) +static void blk_add_trace_plug(void *ignore, struct request_queue *q) { struct blk_trace *bt = q->blk_trace; @@ -787,7 +799,7 @@ static void blk_add_trace_plug(struct request_queue *q) __blk_add_trace(bt, 0, 0, 0, BLK_TA_PLUG, 0, 0, NULL); } -static void blk_add_trace_unplug_io(struct request_queue *q) +static void blk_add_trace_unplug_io(void *ignore, struct request_queue *q) { struct blk_trace *bt = q->blk_trace; @@ -800,7 +812,7 @@ static void blk_add_trace_unplug_io(struct request_queue *q) } } -static void blk_add_trace_unplug_timer(struct request_queue *q) +static void blk_add_trace_unplug_timer(void *ignore, struct request_queue *q) { struct blk_trace *bt = q->blk_trace; @@ -813,7 +825,8 @@ static void blk_add_trace_unplug_timer(struct request_queue *q) } } -static void blk_add_trace_split(struct request_queue *q, struct bio *bio, +static void blk_add_trace_split(void *ignore, + struct request_queue *q, struct bio *bio, unsigned int pdu) { struct blk_trace *bt = q->blk_trace; @@ -839,8 +852,9 @@ static void blk_add_trace_split(struct request_queue *q, struct bio *bio, * it spans a stripe (or similar). Add a trace for that action. * **/ -static void blk_add_trace_remap(struct request_queue *q, struct bio *bio, - dev_t dev, sector_t from) +static void blk_add_trace_remap(void *ignore, + struct request_queue *q, struct bio *bio, + dev_t dev, sector_t from) { struct blk_trace *bt = q->blk_trace; struct blk_io_trace_remap r; @@ -869,7 +883,8 @@ static void blk_add_trace_remap(struct request_queue *q, struct bio *bio, * Add a trace for that action. * **/ -static void blk_add_trace_rq_remap(struct request_queue *q, +static void blk_add_trace_rq_remap(void *ignore, + struct request_queue *q, struct request *rq, dev_t dev, sector_t from) { @@ -921,64 +936,64 @@ static void blk_register_tracepoints(void) { int ret; - ret = register_trace_block_rq_abort(blk_add_trace_rq_abort); + ret = register_trace_block_rq_abort(blk_add_trace_rq_abort, NULL); WARN_ON(ret); - ret = register_trace_block_rq_insert(blk_add_trace_rq_insert); + ret = register_trace_block_rq_insert(blk_add_trace_rq_insert, NULL); WARN_ON(ret); - ret = register_trace_block_rq_issue(blk_add_trace_rq_issue); + ret = register_trace_block_rq_issue(blk_add_trace_rq_issue, NULL); WARN_ON(ret); - ret = register_trace_block_rq_requeue(blk_add_trace_rq_requeue); + ret = register_trace_block_rq_requeue(blk_add_trace_rq_requeue, NULL); WARN_ON(ret); - ret = register_trace_block_rq_complete(blk_add_trace_rq_complete); + ret = register_trace_block_rq_complete(blk_add_trace_rq_complete, NULL); WARN_ON(ret); - ret = register_trace_block_bio_bounce(blk_add_trace_bio_bounce); + ret = register_trace_block_bio_bounce(blk_add_trace_bio_bounce, NULL); WARN_ON(ret); - ret = register_trace_block_bio_complete(blk_add_trace_bio_complete); + ret = register_trace_block_bio_complete(blk_add_trace_bio_complete, NULL); WARN_ON(ret); - ret = register_trace_block_bio_backmerge(blk_add_trace_bio_backmerge); + ret = register_trace_block_bio_backmerge(blk_add_trace_bio_backmerge, NULL); WARN_ON(ret); - ret = register_trace_block_bio_frontmerge(blk_add_trace_bio_frontmerge); + ret = register_trace_block_bio_frontmerge(blk_add_trace_bio_frontmerge, NULL); WARN_ON(ret); - ret = register_trace_block_bio_queue(blk_add_trace_bio_queue); + ret = register_trace_block_bio_queue(blk_add_trace_bio_queue, NULL); WARN_ON(ret); - ret = register_trace_block_getrq(blk_add_trace_getrq); + ret = register_trace_block_getrq(blk_add_trace_getrq, NULL); WARN_ON(ret); - ret = register_trace_block_sleeprq(blk_add_trace_sleeprq); + ret = register_trace_block_sleeprq(blk_add_trace_sleeprq, NULL); WARN_ON(ret); - ret = register_trace_block_plug(blk_add_trace_plug); + ret = register_trace_block_plug(blk_add_trace_plug, NULL); WARN_ON(ret); - ret = register_trace_block_unplug_timer(blk_add_trace_unplug_timer); + ret = register_trace_block_unplug_timer(blk_add_trace_unplug_timer, NULL); WARN_ON(ret); - ret = register_trace_block_unplug_io(blk_add_trace_unplug_io); + ret = register_trace_block_unplug_io(blk_add_trace_unplug_io, NULL); WARN_ON(ret); - ret = register_trace_block_split(blk_add_trace_split); + ret = register_trace_block_split(blk_add_trace_split, NULL); WARN_ON(ret); - ret = register_trace_block_remap(blk_add_trace_remap); + ret = register_trace_block_remap(blk_add_trace_remap, NULL); WARN_ON(ret); - ret = register_trace_block_rq_remap(blk_add_trace_rq_remap); + ret = register_trace_block_rq_remap(blk_add_trace_rq_remap, NULL); WARN_ON(ret); } static void blk_unregister_tracepoints(void) { - unregister_trace_block_rq_remap(blk_add_trace_rq_remap); - unregister_trace_block_remap(blk_add_trace_remap); - unregister_trace_block_split(blk_add_trace_split); - unregister_trace_block_unplug_io(blk_add_trace_unplug_io); - unregister_trace_block_unplug_timer(blk_add_trace_unplug_timer); - unregister_trace_block_plug(blk_add_trace_plug); - unregister_trace_block_sleeprq(blk_add_trace_sleeprq); - unregister_trace_block_getrq(blk_add_trace_getrq); - unregister_trace_block_bio_queue(blk_add_trace_bio_queue); - unregister_trace_block_bio_frontmerge(blk_add_trace_bio_frontmerge); - unregister_trace_block_bio_backmerge(blk_add_trace_bio_backmerge); - unregister_trace_block_bio_complete(blk_add_trace_bio_complete); - unregister_trace_block_bio_bounce(blk_add_trace_bio_bounce); - unregister_trace_block_rq_complete(blk_add_trace_rq_complete); - unregister_trace_block_rq_requeue(blk_add_trace_rq_requeue); - unregister_trace_block_rq_issue(blk_add_trace_rq_issue); - unregister_trace_block_rq_insert(blk_add_trace_rq_insert); - unregister_trace_block_rq_abort(blk_add_trace_rq_abort); + unregister_trace_block_rq_remap(blk_add_trace_rq_remap, NULL); + unregister_trace_block_remap(blk_add_trace_remap, NULL); + unregister_trace_block_split(blk_add_trace_split, NULL); + unregister_trace_block_unplug_io(blk_add_trace_unplug_io, NULL); + unregister_trace_block_unplug_timer(blk_add_trace_unplug_timer, NULL); + unregister_trace_block_plug(blk_add_trace_plug, NULL); + unregister_trace_block_sleeprq(blk_add_trace_sleeprq, NULL); + unregister_trace_block_getrq(blk_add_trace_getrq, NULL); + unregister_trace_block_bio_queue(blk_add_trace_bio_queue, NULL); + unregister_trace_block_bio_frontmerge(blk_add_trace_bio_frontmerge, NULL); + unregister_trace_block_bio_backmerge(blk_add_trace_bio_backmerge, NULL); + unregister_trace_block_bio_complete(blk_add_trace_bio_complete, NULL); + unregister_trace_block_bio_bounce(blk_add_trace_bio_bounce, NULL); + unregister_trace_block_rq_complete(blk_add_trace_rq_complete, NULL); + unregister_trace_block_rq_requeue(blk_add_trace_rq_requeue, NULL); + unregister_trace_block_rq_issue(blk_add_trace_rq_issue, NULL); + unregister_trace_block_rq_insert(blk_add_trace_rq_insert, NULL); + unregister_trace_block_rq_abort(blk_add_trace_rq_abort, NULL); tracepoint_synchronize_unregister(); } diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 32837e19e3bd..6d2cb14f9449 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -3234,7 +3234,8 @@ free: } static void -ftrace_graph_probe_sched_switch(struct task_struct *prev, struct task_struct *next) +ftrace_graph_probe_sched_switch(void *ignore, + struct task_struct *prev, struct task_struct *next) { unsigned long long timestamp; int index; @@ -3288,7 +3289,7 @@ static int start_graph_tracing(void) } while (ret == -EAGAIN); if (!ret) { - ret = register_trace_sched_switch(ftrace_graph_probe_sched_switch); + ret = register_trace_sched_switch(ftrace_graph_probe_sched_switch, NULL); if (ret) pr_info("ftrace_graph: Couldn't activate tracepoint" " probe to kernel_sched_switch\n"); @@ -3364,7 +3365,7 @@ void unregister_ftrace_graph(void) ftrace_graph_entry = ftrace_graph_entry_stub; ftrace_shutdown(FTRACE_STOP_FUNC_RET); unregister_pm_notifier(&ftrace_suspend_notifier); - unregister_trace_sched_switch(ftrace_graph_probe_sched_switch); + unregister_trace_sched_switch(ftrace_graph_probe_sched_switch, NULL); out: mutex_unlock(&ftrace_lock); diff --git a/kernel/trace/kmemtrace.c b/kernel/trace/kmemtrace.c index a91da69f153a..7253d0c1c32f 100644 --- a/kernel/trace/kmemtrace.c +++ b/kernel/trace/kmemtrace.c @@ -95,7 +95,8 @@ static inline void kmemtrace_free(enum kmemtrace_type_id type_id, trace_wake_up(); } -static void kmemtrace_kmalloc(unsigned long call_site, +static void kmemtrace_kmalloc(void *ignore, + unsigned long call_site, const void *ptr, size_t bytes_req, size_t bytes_alloc, @@ -105,7 +106,8 @@ static void kmemtrace_kmalloc(unsigned long call_site, bytes_req, bytes_alloc, gfp_flags, -1); } -static void kmemtrace_kmem_cache_alloc(unsigned long call_site, +static void kmemtrace_kmem_cache_alloc(void *ignore, + unsigned long call_site, const void *ptr, size_t bytes_req, size_t bytes_alloc, @@ -115,7 +117,8 @@ static void kmemtrace_kmem_cache_alloc(unsigned long call_site, bytes_req, bytes_alloc, gfp_flags, -1); } -static void kmemtrace_kmalloc_node(unsigned long call_site, +static void kmemtrace_kmalloc_node(void *ignore, + unsigned long call_site, const void *ptr, size_t bytes_req, size_t bytes_alloc, @@ -126,7 +129,8 @@ static void kmemtrace_kmalloc_node(unsigned long call_site, bytes_req, bytes_alloc, gfp_flags, node); } -static void kmemtrace_kmem_cache_alloc_node(unsigned long call_site, +static void kmemtrace_kmem_cache_alloc_node(void *ignore, + unsigned long call_site, const void *ptr, size_t bytes_req, size_t bytes_alloc, @@ -137,12 +141,14 @@ static void kmemtrace_kmem_cache_alloc_node(unsigned long call_site, bytes_req, bytes_alloc, gfp_flags, node); } -static void kmemtrace_kfree(unsigned long call_site, const void *ptr) +static void +kmemtrace_kfree(void *ignore, unsigned long call_site, const void *ptr) { kmemtrace_free(KMEMTRACE_TYPE_KMALLOC, call_site, ptr); } -static void kmemtrace_kmem_cache_free(unsigned long call_site, const void *ptr) +static void kmemtrace_kmem_cache_free(void *ignore, + unsigned long call_site, const void *ptr) { kmemtrace_free(KMEMTRACE_TYPE_CACHE, call_site, ptr); } @@ -151,34 +157,34 @@ static int kmemtrace_start_probes(void) { int err; - err = register_trace_kmalloc(kmemtrace_kmalloc); + err = register_trace_kmalloc(kmemtrace_kmalloc, NULL); if (err) return err; - err = register_trace_kmem_cache_alloc(kmemtrace_kmem_cache_alloc); + err = register_trace_kmem_cache_alloc(kmemtrace_kmem_cache_alloc, NULL); if (err) return err; - err = register_trace_kmalloc_node(kmemtrace_kmalloc_node); + err = register_trace_kmalloc_node(kmemtrace_kmalloc_node, NULL); if (err) return err; - err = register_trace_kmem_cache_alloc_node(kmemtrace_kmem_cache_alloc_node); + err = register_trace_kmem_cache_alloc_node(kmemtrace_kmem_cache_alloc_node, NULL); if (err) return err; - err = register_trace_kfree(kmemtrace_kfree); + err = register_trace_kfree(kmemtrace_kfree, NULL); if (err) return err; - err = register_trace_kmem_cache_free(kmemtrace_kmem_cache_free); + err = register_trace_kmem_cache_free(kmemtrace_kmem_cache_free, NULL); return err; } static void kmemtrace_stop_probes(void) { - unregister_trace_kmalloc(kmemtrace_kmalloc); - unregister_trace_kmem_cache_alloc(kmemtrace_kmem_cache_alloc); - unregister_trace_kmalloc_node(kmemtrace_kmalloc_node); - unregister_trace_kmem_cache_alloc_node(kmemtrace_kmem_cache_alloc_node); - unregister_trace_kfree(kmemtrace_kfree); - unregister_trace_kmem_cache_free(kmemtrace_kmem_cache_free); + unregister_trace_kmalloc(kmemtrace_kmalloc, NULL); + unregister_trace_kmem_cache_alloc(kmemtrace_kmem_cache_alloc, NULL); + unregister_trace_kmalloc_node(kmemtrace_kmalloc_node, NULL); + unregister_trace_kmem_cache_alloc_node(kmemtrace_kmem_cache_alloc_node, NULL); + unregister_trace_kfree(kmemtrace_kfree, NULL); + unregister_trace_kmem_cache_free(kmemtrace_kmem_cache_free, NULL); } static int kmem_trace_init(struct trace_array *tr) diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c index a55fccfede5d..8f758d070c43 100644 --- a/kernel/trace/trace_sched_switch.c +++ b/kernel/trace/trace_sched_switch.c @@ -50,7 +50,7 @@ tracing_sched_switch_trace(struct trace_array *tr, } static void -probe_sched_switch(struct task_struct *prev, struct task_struct *next) +probe_sched_switch(void *ignore, struct task_struct *prev, struct task_struct *next) { struct trace_array_cpu *data; unsigned long flags; @@ -108,7 +108,7 @@ tracing_sched_wakeup_trace(struct trace_array *tr, } static void -probe_sched_wakeup(struct task_struct *wakee, int success) +probe_sched_wakeup(void *ignore, struct task_struct *wakee, int success) { struct trace_array_cpu *data; unsigned long flags; @@ -138,21 +138,21 @@ static int tracing_sched_register(void) { int ret; - ret = register_trace_sched_wakeup(probe_sched_wakeup); + ret = register_trace_sched_wakeup(probe_sched_wakeup, NULL); if (ret) { pr_info("wakeup trace: Couldn't activate tracepoint" " probe to kernel_sched_wakeup\n"); return ret; } - ret = register_trace_sched_wakeup_new(probe_sched_wakeup); + ret = register_trace_sched_wakeup_new(probe_sched_wakeup, NULL); if (ret) { pr_info("wakeup trace: Couldn't activate tracepoint" " probe to kernel_sched_wakeup_new\n"); goto fail_deprobe; } - ret = register_trace_sched_switch(probe_sched_switch); + ret = register_trace_sched_switch(probe_sched_switch, NULL); if (ret) { pr_info("sched trace: Couldn't activate tracepoint" " probe to kernel_sched_switch\n"); @@ -161,17 +161,17 @@ static int tracing_sched_register(void) return ret; fail_deprobe_wake_new: - unregister_trace_sched_wakeup_new(probe_sched_wakeup); + unregister_trace_sched_wakeup_new(probe_sched_wakeup, NULL); fail_deprobe: - unregister_trace_sched_wakeup(probe_sched_wakeup); + unregister_trace_sched_wakeup(probe_sched_wakeup, NULL); return ret; } static void tracing_sched_unregister(void) { - unregister_trace_sched_switch(probe_sched_switch); - unregister_trace_sched_wakeup_new(probe_sched_wakeup); - unregister_trace_sched_wakeup(probe_sched_wakeup); + unregister_trace_sched_switch(probe_sched_switch, NULL); + unregister_trace_sched_wakeup_new(probe_sched_wakeup, NULL); + unregister_trace_sched_wakeup(probe_sched_wakeup, NULL); } static void tracing_start_sched_switch(void) diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c index 8052446ceeaa..0e73bc2ef8c5 100644 --- a/kernel/trace/trace_sched_wakeup.c +++ b/kernel/trace/trace_sched_wakeup.c @@ -98,7 +98,8 @@ static int report_latency(cycle_t delta) return 1; } -static void probe_wakeup_migrate_task(struct task_struct *task, int cpu) +static void +probe_wakeup_migrate_task(void *ignore, struct task_struct *task, int cpu) { if (task != wakeup_task) return; @@ -107,7 +108,8 @@ static void probe_wakeup_migrate_task(struct task_struct *task, int cpu) } static void notrace -probe_wakeup_sched_switch(struct task_struct *prev, struct task_struct *next) +probe_wakeup_sched_switch(void *ignore, + struct task_struct *prev, struct task_struct *next) { struct trace_array_cpu *data; cycle_t T0, T1, delta; @@ -199,7 +201,7 @@ static void wakeup_reset(struct trace_array *tr) } static void -probe_wakeup(struct task_struct *p, int success) +probe_wakeup(void *ignore, struct task_struct *p, int success) { struct trace_array_cpu *data; int cpu = smp_processor_id(); @@ -263,28 +265,28 @@ static void start_wakeup_tracer(struct trace_array *tr) { int ret; - ret = register_trace_sched_wakeup(probe_wakeup); + ret = register_trace_sched_wakeup(probe_wakeup, NULL); if (ret) { pr_info("wakeup trace: Couldn't activate tracepoint" " probe to kernel_sched_wakeup\n"); return; } - ret = register_trace_sched_wakeup_new(probe_wakeup); + ret = register_trace_sched_wakeup_new(probe_wakeup, NULL); if (ret) { pr_info("wakeup trace: Couldn't activate tracepoint" " probe to kernel_sched_wakeup_new\n"); goto fail_deprobe; } - ret = register_trace_sched_switch(probe_wakeup_sched_switch); + ret = register_trace_sched_switch(probe_wakeup_sched_switch, NULL); if (ret) { pr_info("sched trace: Couldn't activate tracepoint" " probe to kernel_sched_switch\n"); goto fail_deprobe_wake_new; } - ret = register_trace_sched_migrate_task(probe_wakeup_migrate_task); + ret = register_trace_sched_migrate_task(probe_wakeup_migrate_task, NULL); if (ret) { pr_info("wakeup trace: Couldn't activate tracepoint" " probe to kernel_sched_migrate_task\n"); @@ -311,19 +313,19 @@ static void start_wakeup_tracer(struct trace_array *tr) return; fail_deprobe_wake_new: - unregister_trace_sched_wakeup_new(probe_wakeup); + unregister_trace_sched_wakeup_new(probe_wakeup, NULL); fail_deprobe: - unregister_trace_sched_wakeup(probe_wakeup); + unregister_trace_sched_wakeup(probe_wakeup, NULL); } static void stop_wakeup_tracer(struct trace_array *tr) { tracer_enabled = 0; unregister_ftrace_function(&trace_ops); - unregister_trace_sched_switch(probe_wakeup_sched_switch); - unregister_trace_sched_wakeup_new(probe_wakeup); - unregister_trace_sched_wakeup(probe_wakeup); - unregister_trace_sched_migrate_task(probe_wakeup_migrate_task); + unregister_trace_sched_switch(probe_wakeup_sched_switch, NULL); + unregister_trace_sched_wakeup_new(probe_wakeup, NULL); + unregister_trace_sched_wakeup(probe_wakeup, NULL); + unregister_trace_sched_migrate_task(probe_wakeup_migrate_task, NULL); } static int __wakeup_tracer_init(struct trace_array *tr) diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c index d036a74a64f3..b8d30e7ecd05 100644 --- a/kernel/trace/trace_syscalls.c +++ b/kernel/trace/trace_syscalls.c @@ -247,7 +247,7 @@ int syscall_exit_define_fields(struct ftrace_event_call *call) return ret; } -void ftrace_syscall_enter(struct pt_regs *regs, long id) +void ftrace_syscall_enter(void *ignore, struct pt_regs *regs, long id) { struct syscall_trace_enter *entry; struct syscall_metadata *sys_data; @@ -282,7 +282,7 @@ void ftrace_syscall_enter(struct pt_regs *regs, long id) trace_current_buffer_unlock_commit(buffer, event, 0, 0); } -void ftrace_syscall_exit(struct pt_regs *regs, long ret) +void ftrace_syscall_exit(void *ignore, struct pt_regs *regs, long ret) { struct syscall_trace_exit *entry; struct syscall_metadata *sys_data; @@ -324,7 +324,7 @@ int reg_event_syscall_enter(struct ftrace_event_call *call) return -ENOSYS; mutex_lock(&syscall_trace_lock); if (!sys_refcount_enter) - ret = register_trace_sys_enter(ftrace_syscall_enter); + ret = register_trace_sys_enter(ftrace_syscall_enter, NULL); if (!ret) { set_bit(num, enabled_enter_syscalls); sys_refcount_enter++; @@ -344,7 +344,7 @@ void unreg_event_syscall_enter(struct ftrace_event_call *call) sys_refcount_enter--; clear_bit(num, enabled_enter_syscalls); if (!sys_refcount_enter) - unregister_trace_sys_enter(ftrace_syscall_enter); + unregister_trace_sys_enter(ftrace_syscall_enter, NULL); mutex_unlock(&syscall_trace_lock); } @@ -358,7 +358,7 @@ int reg_event_syscall_exit(struct ftrace_event_call *call) return -ENOSYS; mutex_lock(&syscall_trace_lock); if (!sys_refcount_exit) - ret = register_trace_sys_exit(ftrace_syscall_exit); + ret = register_trace_sys_exit(ftrace_syscall_exit, NULL); if (!ret) { set_bit(num, enabled_exit_syscalls); sys_refcount_exit++; @@ -378,7 +378,7 @@ void unreg_event_syscall_exit(struct ftrace_event_call *call) sys_refcount_exit--; clear_bit(num, enabled_exit_syscalls); if (!sys_refcount_exit) - unregister_trace_sys_exit(ftrace_syscall_exit); + unregister_trace_sys_exit(ftrace_syscall_exit, NULL); mutex_unlock(&syscall_trace_lock); } @@ -438,7 +438,7 @@ static DECLARE_BITMAP(enabled_perf_exit_syscalls, NR_syscalls); static int sys_perf_refcount_enter; static int sys_perf_refcount_exit; -static void perf_syscall_enter(struct pt_regs *regs, long id) +static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id) { struct syscall_metadata *sys_data; struct syscall_trace_enter *rec; @@ -484,7 +484,7 @@ int perf_sysenter_enable(struct ftrace_event_call *call) mutex_lock(&syscall_trace_lock); if (!sys_perf_refcount_enter) - ret = register_trace_sys_enter(perf_syscall_enter); + ret = register_trace_sys_enter(perf_syscall_enter, NULL); if (ret) { pr_info("event trace: Could not activate" "syscall entry trace point"); @@ -506,11 +506,11 @@ void perf_sysenter_disable(struct ftrace_event_call *call) sys_perf_refcount_enter--; clear_bit(num, enabled_perf_enter_syscalls); if (!sys_perf_refcount_enter) - unregister_trace_sys_enter(perf_syscall_enter); + unregister_trace_sys_enter(perf_syscall_enter, NULL); mutex_unlock(&syscall_trace_lock); } -static void perf_syscall_exit(struct pt_regs *regs, long ret) +static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret) { struct syscall_metadata *sys_data; struct syscall_trace_exit *rec; @@ -559,7 +559,7 @@ int perf_sysexit_enable(struct ftrace_event_call *call) mutex_lock(&syscall_trace_lock); if (!sys_perf_refcount_exit) - ret = register_trace_sys_exit(perf_syscall_exit); + ret = register_trace_sys_exit(perf_syscall_exit, NULL); if (ret) { pr_info("event trace: Could not activate" "syscall exit trace point"); @@ -581,7 +581,7 @@ void perf_sysexit_disable(struct ftrace_event_call *call) sys_perf_refcount_exit--; clear_bit(num, enabled_perf_exit_syscalls); if (!sys_perf_refcount_exit) - unregister_trace_sys_exit(perf_syscall_exit); + unregister_trace_sys_exit(perf_syscall_exit, NULL); mutex_unlock(&syscall_trace_lock); } diff --git a/kernel/trace/trace_workqueue.c b/kernel/trace/trace_workqueue.c index cc2d2faa7d9e..a7cc3793baf6 100644 --- a/kernel/trace/trace_workqueue.c +++ b/kernel/trace/trace_workqueue.c @@ -49,7 +49,8 @@ static void cpu_workqueue_stat_free(struct kref *kref) /* Insertion of a work */ static void -probe_workqueue_insertion(struct task_struct *wq_thread, +probe_workqueue_insertion(void *ignore, + struct task_struct *wq_thread, struct work_struct *work) { int cpu = cpumask_first(&wq_thread->cpus_allowed); @@ -70,7 +71,8 @@ found: /* Execution of a work */ static void -probe_workqueue_execution(struct task_struct *wq_thread, +probe_workqueue_execution(void *ignore, + struct task_struct *wq_thread, struct work_struct *work) { int cpu = cpumask_first(&wq_thread->cpus_allowed); @@ -90,7 +92,8 @@ found: } /* Creation of a cpu workqueue thread */ -static void probe_workqueue_creation(struct task_struct *wq_thread, int cpu) +static void probe_workqueue_creation(void *ignore, + struct task_struct *wq_thread, int cpu) { struct cpu_workqueue_stats *cws; unsigned long flags; @@ -114,7 +117,8 @@ static void probe_workqueue_creation(struct task_struct *wq_thread, int cpu) } /* Destruction of a cpu workqueue thread */ -static void probe_workqueue_destruction(struct task_struct *wq_thread) +static void +probe_workqueue_destruction(void *ignore, struct task_struct *wq_thread) { /* Workqueue only execute on one cpu */ int cpu = cpumask_first(&wq_thread->cpus_allowed); @@ -259,19 +263,19 @@ int __init trace_workqueue_early_init(void) { int ret, cpu; - ret = register_trace_workqueue_insertion(probe_workqueue_insertion); + ret = register_trace_workqueue_insertion(probe_workqueue_insertion, NULL); if (ret) goto out; - ret = register_trace_workqueue_execution(probe_workqueue_execution); + ret = register_trace_workqueue_execution(probe_workqueue_execution, NULL); if (ret) goto no_insertion; - ret = register_trace_workqueue_creation(probe_workqueue_creation); + ret = register_trace_workqueue_creation(probe_workqueue_creation, NULL); if (ret) goto no_execution; - ret = register_trace_workqueue_destruction(probe_workqueue_destruction); + ret = register_trace_workqueue_destruction(probe_workqueue_destruction, NULL); if (ret) goto no_creation; @@ -283,11 +287,11 @@ int __init trace_workqueue_early_init(void) return 0; no_creation: - unregister_trace_workqueue_creation(probe_workqueue_creation); + unregister_trace_workqueue_creation(probe_workqueue_creation, NULL); no_execution: - unregister_trace_workqueue_execution(probe_workqueue_execution); + unregister_trace_workqueue_execution(probe_workqueue_execution, NULL); no_insertion: - unregister_trace_workqueue_insertion(probe_workqueue_insertion); + unregister_trace_workqueue_insertion(probe_workqueue_insertion, NULL); out: pr_warning("trace_workqueue: unable to trace workqueues\n"); diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c index cc89be5bc0f8..c77f3eceea25 100644 --- a/kernel/tracepoint.c +++ b/kernel/tracepoint.c @@ -54,7 +54,7 @@ static struct hlist_head tracepoint_table[TRACEPOINT_TABLE_SIZE]; */ struct tracepoint_entry { struct hlist_node hlist; - void **funcs; + struct tracepoint_func *funcs; int refcount; /* Number of times armed. 0 if disarmed. */ char name[0]; }; @@ -64,12 +64,12 @@ struct tp_probes { struct rcu_head rcu; struct list_head list; } u; - void *probes[0]; + struct tracepoint_func probes[0]; }; static inline void *allocate_probes(int count) { - struct tp_probes *p = kmalloc(count * sizeof(void *) + struct tp_probes *p = kmalloc(count * sizeof(struct tracepoint_func) + sizeof(struct tp_probes), GFP_KERNEL); return p == NULL ? NULL : p->probes; } @@ -79,7 +79,7 @@ static void rcu_free_old_probes(struct rcu_head *head) kfree(container_of(head, struct tp_probes, u.rcu)); } -static inline void release_probes(void *old) +static inline void release_probes(struct tracepoint_func *old) { if (old) { struct tp_probes *tp_probes = container_of(old, @@ -95,15 +95,16 @@ static void debug_print_probes(struct tracepoint_entry *entry) if (!tracepoint_debug || !entry->funcs) return; - for (i = 0; entry->funcs[i]; i++) - printk(KERN_DEBUG "Probe %d : %p\n", i, entry->funcs[i]); + for (i = 0; entry->funcs[i].func; i++) + printk(KERN_DEBUG "Probe %d : %p\n", i, entry->funcs[i].func); } -static void * -tracepoint_entry_add_probe(struct tracepoint_entry *entry, void *probe) +static struct tracepoint_func * +tracepoint_entry_add_probe(struct tracepoint_entry *entry, + void *probe, void *data) { int nr_probes = 0; - void **old, **new; + struct tracepoint_func *old, *new; WARN_ON(!probe); @@ -111,8 +112,9 @@ tracepoint_entry_add_probe(struct tracepoint_entry *entry, void *probe) old = entry->funcs; if (old) { /* (N -> N+1), (N != 0, 1) probes */ - for (nr_probes = 0; old[nr_probes]; nr_probes++) - if (old[nr_probes] == probe) + for (nr_probes = 0; old[nr_probes].func; nr_probes++) + if (old[nr_probes].func == probe && + old[nr_probes].data == data) return ERR_PTR(-EEXIST); } /* + 2 : one for new probe, one for NULL func */ @@ -120,9 +122,10 @@ tracepoint_entry_add_probe(struct tracepoint_entry *entry, void *probe) if (new == NULL) return ERR_PTR(-ENOMEM); if (old) - memcpy(new, old, nr_probes * sizeof(void *)); - new[nr_probes] = probe; - new[nr_probes + 1] = NULL; + memcpy(new, old, nr_probes * sizeof(struct tracepoint_func)); + new[nr_probes].func = probe; + new[nr_probes].data = data; + new[nr_probes + 1].func = NULL; entry->refcount = nr_probes + 1; entry->funcs = new; debug_print_probes(entry); @@ -130,10 +133,11 @@ tracepoint_entry_add_probe(struct tracepoint_entry *entry, void *probe) } static void * -tracepoint_entry_remove_probe(struct tracepoint_entry *entry, void *probe) +tracepoint_entry_remove_probe(struct tracepoint_entry *entry, + void *probe, void *data) { int nr_probes = 0, nr_del = 0, i; - void **old, **new; + struct tracepoint_func *old, *new; old = entry->funcs; @@ -142,8 +146,10 @@ tracepoint_entry_remove_probe(struct tracepoint_entry *entry, void *probe) debug_print_probes(entry); /* (N -> M), (N > 1, M >= 0) probes */ - for (nr_probes = 0; old[nr_probes]; nr_probes++) { - if ((!probe || old[nr_probes] == probe)) + for (nr_probes = 0; old[nr_probes].func; nr_probes++) { + if (!probe || + (old[nr_probes].func == probe && + old[nr_probes].data == data)) nr_del++; } @@ -160,10 +166,11 @@ tracepoint_entry_remove_probe(struct tracepoint_entry *entry, void *probe) new = allocate_probes(nr_probes - nr_del + 1); if (new == NULL) return ERR_PTR(-ENOMEM); - for (i = 0; old[i]; i++) - if ((probe && old[i] != probe)) + for (i = 0; old[i].func; i++) + if (probe && + (old[i].func != probe || old[i].data != data)) new[j++] = old[i]; - new[nr_probes - nr_del] = NULL; + new[nr_probes - nr_del].func = NULL; entry->refcount = nr_probes - nr_del; entry->funcs = new; } @@ -315,18 +322,19 @@ static void tracepoint_update_probes(void) module_update_tracepoints(); } -static void *tracepoint_add_probe(const char *name, void *probe) +static struct tracepoint_func * +tracepoint_add_probe(const char *name, void *probe, void *data) { struct tracepoint_entry *entry; - void *old; + struct tracepoint_func *old; entry = get_tracepoint(name); if (!entry) { entry = add_tracepoint(name); if (IS_ERR(entry)) - return entry; + return (struct tracepoint_func *)entry; } - old = tracepoint_entry_add_probe(entry, probe); + old = tracepoint_entry_add_probe(entry, probe, data); if (IS_ERR(old) && !entry->refcount) remove_tracepoint(entry); return old; @@ -340,12 +348,12 @@ static void *tracepoint_add_probe(const char *name, void *probe) * Returns 0 if ok, error value on error. * The probe address must at least be aligned on the architecture pointer size. */ -int tracepoint_probe_register(const char *name, void *probe) +int tracepoint_probe_register(const char *name, void *probe, void *data) { - void *old; + struct tracepoint_func *old; mutex_lock(&tracepoints_mutex); - old = tracepoint_add_probe(name, probe); + old = tracepoint_add_probe(name, probe, data); mutex_unlock(&tracepoints_mutex); if (IS_ERR(old)) return PTR_ERR(old); @@ -356,15 +364,16 @@ int tracepoint_probe_register(const char *name, void *probe) } EXPORT_SYMBOL_GPL(tracepoint_probe_register); -static void *tracepoint_remove_probe(const char *name, void *probe) +static struct tracepoint_func * +tracepoint_remove_probe(const char *name, void *probe, void *data) { struct tracepoint_entry *entry; - void *old; + struct tracepoint_func *old; entry = get_tracepoint(name); if (!entry) return ERR_PTR(-ENOENT); - old = tracepoint_entry_remove_probe(entry, probe); + old = tracepoint_entry_remove_probe(entry, probe, data); if (IS_ERR(old)) return old; if (!entry->refcount) @@ -382,12 +391,12 @@ static void *tracepoint_remove_probe(const char *name, void *probe) * itself uses stop_machine(), which insures that every preempt disabled section * have finished. */ -int tracepoint_probe_unregister(const char *name, void *probe) +int tracepoint_probe_unregister(const char *name, void *probe, void *data) { - void *old; + struct tracepoint_func *old; mutex_lock(&tracepoints_mutex); - old = tracepoint_remove_probe(name, probe); + old = tracepoint_remove_probe(name, probe, data); mutex_unlock(&tracepoints_mutex); if (IS_ERR(old)) return PTR_ERR(old); @@ -418,12 +427,13 @@ static void tracepoint_add_old_probes(void *old) * * caller must call tracepoint_probe_update_all() */ -int tracepoint_probe_register_noupdate(const char *name, void *probe) +int tracepoint_probe_register_noupdate(const char *name, void *probe, + void *data) { - void *old; + struct tracepoint_func *old; mutex_lock(&tracepoints_mutex); - old = tracepoint_add_probe(name, probe); + old = tracepoint_add_probe(name, probe, data); if (IS_ERR(old)) { mutex_unlock(&tracepoints_mutex); return PTR_ERR(old); @@ -441,12 +451,13 @@ EXPORT_SYMBOL_GPL(tracepoint_probe_register_noupdate); * * caller must call tracepoint_probe_update_all() */ -int tracepoint_probe_unregister_noupdate(const char *name, void *probe) +int tracepoint_probe_unregister_noupdate(const char *name, void *probe, + void *data) { - void *old; + struct tracepoint_func *old; mutex_lock(&tracepoints_mutex); - old = tracepoint_remove_probe(name, probe); + old = tracepoint_remove_probe(name, probe, data); if (IS_ERR(old)) { mutex_unlock(&tracepoints_mutex); return PTR_ERR(old); -- cgit v1.2.1 From 2239291aeb0379fe47980b0e560e0eb9fd7e82ec Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Wed, 21 Apr 2010 12:27:06 -0400 Subject: tracing: Remove per event trace registering This patch removes the register functions of TRACE_EVENT() to enable and disable tracepoints. The registering of a event is now down directly in the trace_events.c file. The tracepoint_probe_register() is now called directly. The prototypes are no longer type checked, but this should not be an issue since the tracepoints are created automatically by the macros. If a prototype is incorrect in the TRACE_EVENT() macro, then other macros will catch it. The trace_event_class structure now holds the probes to be called by the callbacks. This removes needing to have each event have a separate pointer for the probe. To handle kprobes and syscalls, since they register probes in a different manner, a "reg" field is added to the ftrace_event_class structure. If the "reg" field is assigned, then it will be called for enabling and disabling of the probe for either ftrace or perf. To let the reg function know what is happening, a new enum (trace_reg) is created that has the type of control that is needed. With this new rework, the 82 kernel events and 618 syscall events has their footprint dramatically lowered: text data bss dec hex filename 4913961 1088356 861512 6863829 68bbd5 vmlinux.orig 4914025 1088868 861512 6864405 68be15 vmlinux.class 4918492 1084612 861512 6864616 68bee8 vmlinux.tracepoint 4900252 1057412 861512 6819176 680d68 vmlinux.regs The size went from 6863829 to 6819176, that's a total of 44K in savings. With tracepoints being continuously added, this is critical that the footprint becomes minimal. v5: Added #ifdef CONFIG_PERF_EVENTS around a reference to perf specific structure in trace_events.c. v4: Fixed trace self tests to check probe because regfunc no longer exists. v3: Updated to handle void *data in beginning of probe parameters. Also added the tracepoint: check_trace_callback_type_##call(). v2: Changed the callback probes to pass void * and typecast the value within the function. Acked-by: Mathieu Desnoyers Acked-by: Masami Hiramatsu Acked-by: Frederic Weisbecker Signed-off-by: Steven Rostedt --- kernel/trace/trace_event_perf.c | 15 ++++++++--- kernel/trace/trace_events.c | 32 ++++++++++++++++------- kernel/trace/trace_kprobe.c | 34 ++++++++++++++++++------- kernel/trace/trace_syscalls.c | 56 +++++++++++++++++++++++++++++++++++++++-- 4 files changed, 114 insertions(+), 23 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c index 0565bb42566f..196fe9d26773 100644 --- a/kernel/trace/trace_event_perf.c +++ b/kernel/trace/trace_event_perf.c @@ -49,7 +49,12 @@ static int perf_trace_event_enable(struct ftrace_event_call *event) rcu_assign_pointer(perf_trace_buf_nmi, buf); } - ret = event->perf_event_enable(event); + if (event->class->reg) + ret = event->class->reg(event, TRACE_REG_PERF_REGISTER); + else + ret = tracepoint_probe_register(event->name, + event->class->perf_probe, + event); if (!ret) { total_ref_count++; return 0; @@ -75,7 +80,8 @@ int perf_trace_enable(int event_id) mutex_lock(&event_mutex); list_for_each_entry(event, &ftrace_events, list) { - if (event->id == event_id && event->perf_event_enable && + if (event->id == event_id && + event->class && event->class->perf_probe && try_module_get(event->mod)) { ret = perf_trace_event_enable(event); break; @@ -93,7 +99,10 @@ static void perf_trace_event_disable(struct ftrace_event_call *event) if (--event->perf_refcount > 0) return; - event->perf_event_disable(event); + if (event->class->reg) + event->class->reg(event, TRACE_REG_PERF_UNREGISTER); + else + tracepoint_probe_unregister(event->name, event->class->perf_probe, event); if (!--total_ref_count) { buf = perf_trace_buf; diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 2f54b48d3632..19d1eb0a7188 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -127,13 +127,23 @@ static int ftrace_event_enable_disable(struct ftrace_event_call *call, if (call->enabled) { call->enabled = 0; tracing_stop_cmdline_record(); - call->unregfunc(call); + if (call->class->reg) + call->class->reg(call, TRACE_REG_UNREGISTER); + else + tracepoint_probe_unregister(call->name, + call->class->probe, + call); } break; case 1: if (!call->enabled) { tracing_start_cmdline_record(); - ret = call->regfunc(call); + if (call->class->reg) + ret = call->class->reg(call, TRACE_REG_REGISTER); + else + ret = tracepoint_probe_register(call->name, + call->class->probe, + call); if (ret) { tracing_stop_cmdline_record(); pr_info("event trace: Could not enable event " @@ -171,7 +181,8 @@ static int __ftrace_set_clr_event(const char *match, const char *sub, mutex_lock(&event_mutex); list_for_each_entry(call, &ftrace_events, list) { - if (!call->name || !call->regfunc) + if (!call->name || !call->class || + (!call->class->probe && !call->class->reg)) continue; if (match && @@ -297,7 +308,7 @@ t_next(struct seq_file *m, void *v, loff_t *pos) * The ftrace subsystem is for showing formats only. * They can not be enabled or disabled via the event files. */ - if (call->regfunc) + if (call->class && (call->class->probe || call->class->reg)) return call; } @@ -450,7 +461,8 @@ system_enable_read(struct file *filp, char __user *ubuf, size_t cnt, mutex_lock(&event_mutex); list_for_each_entry(call, &ftrace_events, list) { - if (!call->name || !call->regfunc) + if (!call->name || !call->class || + (!call->class->probe && !call->class->reg)) continue; if (system && strcmp(call->class->system, system) != 0) @@ -935,13 +947,15 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events, return -1; } - if (call->regfunc) + if (call->class->probe || call->class->reg) trace_create_file("enable", 0644, call->dir, call, enable); - if (call->id && call->perf_event_enable) +#ifdef CONFIG_PERF_EVENTS + if (call->id && (call->class->perf_probe || call->class->reg)) trace_create_file("id", 0444, call->dir, call, id); +#endif if (call->define_fields) { ret = trace_define_common_fields(call); @@ -1388,8 +1402,8 @@ static __init void event_trace_self_tests(void) list_for_each_entry(call, &ftrace_events, list) { - /* Only test those that have a regfunc */ - if (!call->regfunc) + /* Only test those that have a probe */ + if (!call->class || !call->class->probe) continue; /* diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index eda220bf2065..f8af21a53f0c 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -202,6 +202,7 @@ struct trace_probe { unsigned long nhit; unsigned int flags; /* For TP_FLAG_* */ const char *symbol; /* symbol name */ + struct ftrace_event_class class; struct ftrace_event_call call; struct trace_event event; unsigned int nr_args; @@ -323,6 +324,7 @@ static struct trace_probe *alloc_trace_probe(const char *group, goto error; } + tp->call.class = &tp->class; tp->call.name = kstrdup(event, GFP_KERNEL); if (!tp->call.name) goto error; @@ -332,8 +334,8 @@ static struct trace_probe *alloc_trace_probe(const char *group, goto error; } - tp->call.class->system = kstrdup(group, GFP_KERNEL); - if (!tp->call.class->system) + tp->class.system = kstrdup(group, GFP_KERNEL); + if (!tp->class.system) goto error; INIT_LIST_HEAD(&tp->list); @@ -1302,6 +1304,26 @@ static void probe_perf_disable(struct ftrace_event_call *call) } #endif /* CONFIG_PERF_EVENTS */ +static __kprobes +int kprobe_register(struct ftrace_event_call *event, enum trace_reg type) +{ + switch (type) { + case TRACE_REG_REGISTER: + return probe_event_enable(event); + case TRACE_REG_UNREGISTER: + probe_event_disable(event); + return 0; + +#ifdef CONFIG_PERF_EVENTS + case TRACE_REG_PERF_REGISTER: + return probe_perf_enable(event); + case TRACE_REG_PERF_UNREGISTER: + probe_perf_disable(event); + return 0; +#endif + } + return 0; +} static __kprobes int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs) @@ -1355,13 +1377,7 @@ static int register_probe_event(struct trace_probe *tp) return -ENODEV; } call->enabled = 0; - call->regfunc = probe_event_enable; - call->unregfunc = probe_event_disable; - -#ifdef CONFIG_PERF_EVENTS - call->perf_event_enable = probe_perf_enable; - call->perf_event_disable = probe_perf_disable; -#endif + call->class->reg = kprobe_register; call->data = tp; ret = trace_add_event_call(call); if (ret) { diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c index b8d30e7ecd05..a21d366cae46 100644 --- a/kernel/trace/trace_syscalls.c +++ b/kernel/trace/trace_syscalls.c @@ -15,8 +15,19 @@ static int sys_refcount_exit; static DECLARE_BITMAP(enabled_enter_syscalls, NR_syscalls); static DECLARE_BITMAP(enabled_exit_syscalls, NR_syscalls); -struct ftrace_event_class event_class_syscalls = { - .system = "syscalls" +static int syscall_enter_register(struct ftrace_event_call *event, + enum trace_reg type); +static int syscall_exit_register(struct ftrace_event_call *event, + enum trace_reg type); + +struct ftrace_event_class event_class_syscall_enter = { + .system = "syscalls", + .reg = syscall_enter_register +}; + +struct ftrace_event_class event_class_syscall_exit = { + .system = "syscalls", + .reg = syscall_exit_register }; extern unsigned long __start_syscalls_metadata[]; @@ -587,3 +598,44 @@ void perf_sysexit_disable(struct ftrace_event_call *call) #endif /* CONFIG_PERF_EVENTS */ +static int syscall_enter_register(struct ftrace_event_call *event, + enum trace_reg type) +{ + switch (type) { + case TRACE_REG_REGISTER: + return reg_event_syscall_enter(event); + case TRACE_REG_UNREGISTER: + unreg_event_syscall_enter(event); + return 0; + +#ifdef CONFIG_PERF_EVENTS + case TRACE_REG_PERF_REGISTER: + return perf_sysenter_enable(event); + case TRACE_REG_PERF_UNREGISTER: + perf_sysenter_disable(event); + return 0; +#endif + } + return 0; +} + +static int syscall_exit_register(struct ftrace_event_call *event, + enum trace_reg type) +{ + switch (type) { + case TRACE_REG_REGISTER: + return reg_event_syscall_exit(event); + case TRACE_REG_UNREGISTER: + unreg_event_syscall_exit(event); + return 0; + +#ifdef CONFIG_PERF_EVENTS + case TRACE_REG_PERF_REGISTER: + return perf_sysexit_enable(event); + case TRACE_REG_PERF_UNREGISTER: + perf_sysexit_disable(event); + return 0; +#endif + } + return 0; +} -- cgit v1.2.1 From 2e33af029556cb8bd22bf4f86f42d540249177ea Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 22 Apr 2010 10:35:55 -0400 Subject: tracing: Move fields from event to class structure Move the defined fields from the event to the class structure. Since the fields of the event are defined by the class they belong to, it makes sense to have the class hold the information instead of the individual events. The events of the same class would just hold duplicate information. After this change the size of the kernel dropped another 3K: text data bss dec hex filename 4913961 1088356 861512 6863829 68bbd5 vmlinux.orig 4900252 1057412 861512 6819176 680d68 vmlinux.regs 4900375 1053380 861512 6815267 67fe23 vmlinux.fields Although the text increased, this was mainly due to the C files having to adapt to the change. This is a constant increase, where new tracepoints will not increase the Text. But the big drop is in the data size (as well as needed allocations to hold the fields). This will give even more savings as more tracepoints are created. Note, if just TRACE_EVENT()s are used and not DECLARE_EVENT_CLASS() with several DEFINE_EVENT()s, then the savings will be lost. But we are pushing developers to consolidate events with DEFINE_EVENT() so this should not be an issue. The kprobes define a unique class to every new event, but are dynamic so it should not be a issue. The syscalls however have a single class but the fields for the individual events are different. The syscalls use a metadata to define the fields. I moved the fields list from the event to the metadata and added a "get_fields()" function to the class. This function is used to find the fields. For normal events and kprobes, get_fields() just returns a pointer to the fields list_head in the class. For syscall events, it returns the fields list_head in the metadata for the event. v2: Fixed the syscall fields. The syscall metadata needs a list of fields for both enter and exit. Acked-by: Frederic Weisbecker Acked-by: Mathieu Desnoyers Acked-by: Masami Hiramatsu Cc: Tom Zanussi Cc: Peter Zijlstra Signed-off-by: Steven Rostedt --- kernel/trace/trace.h | 3 +++ kernel/trace/trace_events.c | 48 ++++++++++++++++++++++++++++---------- kernel/trace/trace_events_filter.c | 10 ++++---- kernel/trace/trace_export.c | 14 +++++------ kernel/trace/trace_kprobe.c | 8 +++---- kernel/trace/trace_syscalls.c | 31 ++++++++++++++++++++---- 6 files changed, 83 insertions(+), 31 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 911e9864e94a..c88c563a59a5 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -794,6 +794,9 @@ extern void print_subsystem_event_filter(struct event_subsystem *system, struct trace_seq *s); extern int filter_assign_type(const char *type); +struct list_head * +trace_get_fields(struct ftrace_event_call *event_call); + static inline int filter_check_discard(struct ftrace_event_call *call, void *rec, struct ring_buffer *buffer, diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 19d1eb0a7188..acc0f55742c3 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -29,11 +29,23 @@ DEFINE_MUTEX(event_mutex); LIST_HEAD(ftrace_events); +struct list_head * +trace_get_fields(struct ftrace_event_call *event_call) +{ + if (!event_call->class->get_fields) + return &event_call->class->fields; + return event_call->class->get_fields(event_call); +} + int trace_define_field(struct ftrace_event_call *call, const char *type, const char *name, int offset, int size, int is_signed, int filter_type) { struct ftrace_event_field *field; + struct list_head *head; + + if (WARN_ON(!call->class)) + return 0; field = kzalloc(sizeof(*field), GFP_KERNEL); if (!field) @@ -56,7 +68,8 @@ int trace_define_field(struct ftrace_event_call *call, const char *type, field->size = size; field->is_signed = is_signed; - list_add(&field->link, &call->fields); + head = trace_get_fields(call); + list_add(&field->link, head); return 0; @@ -94,8 +107,10 @@ static int trace_define_common_fields(struct ftrace_event_call *call) void trace_destroy_fields(struct ftrace_event_call *call) { struct ftrace_event_field *field, *next; + struct list_head *head; - list_for_each_entry_safe(field, next, &call->fields, link) { + head = trace_get_fields(call); + list_for_each_entry_safe(field, next, head, link) { list_del(&field->link); kfree(field->type); kfree(field->name); @@ -111,7 +126,6 @@ int trace_event_raw_init(struct ftrace_event_call *call) if (!id) return -ENODEV; call->id = id; - INIT_LIST_HEAD(&call->fields); return 0; } @@ -537,6 +551,7 @@ event_format_read(struct file *filp, char __user *ubuf, size_t cnt, { struct ftrace_event_call *call = filp->private_data; struct ftrace_event_field *field; + struct list_head *head; struct trace_seq *s; int common_field_count = 5; char *buf; @@ -555,7 +570,8 @@ event_format_read(struct file *filp, char __user *ubuf, size_t cnt, trace_seq_printf(s, "ID: %d\n", call->id); trace_seq_printf(s, "format:\n"); - list_for_each_entry_reverse(field, &call->fields, link) { + head = trace_get_fields(call); + list_for_each_entry_reverse(field, head, link) { /* * Smartly shows the array type(except dynamic array). * Normal: @@ -931,6 +947,7 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events, const struct file_operations *filter, const struct file_operations *format) { + struct list_head *head; int ret; /* @@ -957,14 +974,21 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events, id); #endif - if (call->define_fields) { - ret = trace_define_common_fields(call); - if (!ret) - ret = call->define_fields(call); - if (ret < 0) { - pr_warning("Could not initialize trace point" - " events/%s\n", call->name); - return ret; + if (call->class->define_fields) { + /* + * Other events may have the same class. Only update + * the fields if they are not already defined. + */ + head = trace_get_fields(call); + if (list_empty(head)) { + ret = trace_define_common_fields(call); + if (!ret) + ret = call->class->define_fields(call); + if (ret < 0) { + pr_warning("Could not initialize trace point" + " events/%s\n", call->name); + return ret; + } } trace_create_file("filter", 0644, call->dir, call, filter); diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index ca329603d0bf..961f99b74bdd 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -500,8 +500,10 @@ static struct ftrace_event_field * find_event_field(struct ftrace_event_call *call, char *name) { struct ftrace_event_field *field; + struct list_head *head; - list_for_each_entry(field, &call->fields, link) { + head = trace_get_fields(call); + list_for_each_entry(field, head, link) { if (!strcmp(field->name, name)) return field; } @@ -625,7 +627,7 @@ static int init_subsystem_preds(struct event_subsystem *system) int err; list_for_each_entry(call, &ftrace_events, list) { - if (!call->define_fields) + if (!call->class || !call->class->define_fields) continue; if (strcmp(call->class->system, system->name) != 0) @@ -644,7 +646,7 @@ static void filter_free_subsystem_preds(struct event_subsystem *system) struct ftrace_event_call *call; list_for_each_entry(call, &ftrace_events, list) { - if (!call->define_fields) + if (!call->class || !call->class->define_fields) continue; if (strcmp(call->class->system, system->name) != 0) @@ -1249,7 +1251,7 @@ static int replace_system_preds(struct event_subsystem *system, list_for_each_entry(call, &ftrace_events, list) { struct event_filter *filter = call->filter; - if (!call->define_fields) + if (!call->class || !call->class->define_fields) continue; if (strcmp(call->class->system, system->name) != 0) diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c index 7f16e2163817..e700a0c1803f 100644 --- a/kernel/trace/trace_export.c +++ b/kernel/trace/trace_export.c @@ -18,10 +18,6 @@ #undef TRACE_SYSTEM #define TRACE_SYSTEM ftrace -struct ftrace_event_class event_class_ftrace = { - .system = __stringify(TRACE_SYSTEM), -}; - /* not needed for this file */ #undef __field_struct #define __field_struct(type, item) @@ -131,7 +127,7 @@ ftrace_define_fields_##name(struct ftrace_event_call *event_call) \ static int ftrace_raw_init_event(struct ftrace_event_call *call) { - INIT_LIST_HEAD(&call->fields); + INIT_LIST_HEAD(&call->class->fields); return 0; } @@ -159,15 +155,19 @@ static int ftrace_raw_init_event(struct ftrace_event_call *call) #undef FTRACE_ENTRY #define FTRACE_ENTRY(call, struct_name, type, tstruct, print) \ \ +struct ftrace_event_class event_class_ftrace_##call = { \ + .system = __stringify(TRACE_SYSTEM), \ + .define_fields = ftrace_define_fields_##call, \ +}; \ + \ struct ftrace_event_call __used \ __attribute__((__aligned__(4))) \ __attribute__((section("_ftrace_events"))) event_##call = { \ .name = #call, \ .id = type, \ - .class = &event_class_ftrace, \ + .class = &event_class_ftrace_##call, \ .raw_init = ftrace_raw_init_event, \ .print_fmt = print, \ - .define_fields = ftrace_define_fields_##call, \ }; \ #include "trace_entries.h" diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index f8af21a53f0c..b14bf745356f 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -1112,8 +1112,6 @@ static void probe_event_disable(struct ftrace_event_call *call) static int probe_event_raw_init(struct ftrace_event_call *event_call) { - INIT_LIST_HEAD(&event_call->fields); - return 0; } @@ -1362,11 +1360,13 @@ static int register_probe_event(struct trace_probe *tp) if (probe_is_return(tp)) { tp->event.trace = print_kretprobe_event; call->raw_init = probe_event_raw_init; - call->define_fields = kretprobe_event_define_fields; + INIT_LIST_HEAD(&call->class->fields); + call->class->define_fields = kretprobe_event_define_fields; } else { tp->event.trace = print_kprobe_event; call->raw_init = probe_event_raw_init; - call->define_fields = kprobe_event_define_fields; + INIT_LIST_HEAD(&call->class->fields); + call->class->define_fields = kprobe_event_define_fields; } if (set_print_fmt(tp) < 0) return -ENOMEM; diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c index a21d366cae46..cceccf0d2e91 100644 --- a/kernel/trace/trace_syscalls.c +++ b/kernel/trace/trace_syscalls.c @@ -20,14 +20,37 @@ static int syscall_enter_register(struct ftrace_event_call *event, static int syscall_exit_register(struct ftrace_event_call *event, enum trace_reg type); +static int syscall_enter_define_fields(struct ftrace_event_call *call); +static int syscall_exit_define_fields(struct ftrace_event_call *call); + +static struct list_head * +syscall_get_enter_fields(struct ftrace_event_call *call) +{ + struct syscall_metadata *entry = call->data; + + return &entry->enter_fields; +} + +static struct list_head * +syscall_get_exit_fields(struct ftrace_event_call *call) +{ + struct syscall_metadata *entry = call->data; + + return &entry->exit_fields; +} + struct ftrace_event_class event_class_syscall_enter = { .system = "syscalls", - .reg = syscall_enter_register + .reg = syscall_enter_register, + .define_fields = syscall_enter_define_fields, + .get_fields = syscall_get_enter_fields, }; struct ftrace_event_class event_class_syscall_exit = { .system = "syscalls", - .reg = syscall_exit_register + .reg = syscall_exit_register, + .define_fields = syscall_exit_define_fields, + .get_fields = syscall_get_exit_fields, }; extern unsigned long __start_syscalls_metadata[]; @@ -220,7 +243,7 @@ static void free_syscall_print_fmt(struct ftrace_event_call *call) kfree(call->print_fmt); } -int syscall_enter_define_fields(struct ftrace_event_call *call) +static int syscall_enter_define_fields(struct ftrace_event_call *call) { struct syscall_trace_enter trace; struct syscall_metadata *meta = call->data; @@ -243,7 +266,7 @@ int syscall_enter_define_fields(struct ftrace_event_call *call) return ret; } -int syscall_exit_define_fields(struct ftrace_event_call *call) +static int syscall_exit_define_fields(struct ftrace_event_call *call) { struct syscall_trace_exit trace; int ret; -- cgit v1.2.1 From 0405ab80aa94afb13bf9ac4a6fc9f2923d4b9114 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 22 Apr 2010 11:46:44 -0400 Subject: tracing: Move raw_init from events to class The raw_init function pointer in the event is used to initialize various kinds of events. The type of initialization needed is usually classed to the kind of event it is. Two events with the same class will always have the same initialization function, so it makes sense to move this to the class structure. Perhaps even making a special system structure would work since the initialization is the same for all events within a system. But since there's no system structure (yet), this will just move it to the class. text data bss dec hex filename 4913961 1088356 861512 6863829 68bbd5 vmlinux.orig 4900375 1053380 861512 6815267 67fe23 vmlinux.fields 4900382 1048964 861512 6810858 67ecea vmlinux.init The text grew very slightly, but this is a constant growth that happened with the changing of the C files that call the init code. The bigger savings is the data which will be saved the more events share a class. Acked-by: Mathieu Desnoyers Acked-by: Masami Hiramatsu Acked-by: Frederic Weisbecker Signed-off-by: Steven Rostedt --- kernel/trace/trace_events.c | 12 ++++++------ kernel/trace/trace_export.c | 2 +- kernel/trace/trace_kprobe.c | 6 +++--- kernel/trace/trace_syscalls.c | 2 ++ 4 files changed, 12 insertions(+), 10 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index acc0f55742c3..8e94255a45e7 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -1008,8 +1008,8 @@ static int __trace_add_event_call(struct ftrace_event_call *call) if (!call->name) return -EINVAL; - if (call->raw_init) { - ret = call->raw_init(call); + if (call->class->raw_init) { + ret = call->class->raw_init(call); if (ret < 0) { if (ret != -ENOSYS) pr_warning("Could not initialize trace " @@ -1170,8 +1170,8 @@ static void trace_module_add_events(struct module *mod) /* The linker may leave blanks */ if (!call->name) continue; - if (call->raw_init) { - ret = call->raw_init(call); + if (call->class->raw_init) { + ret = call->class->raw_init(call); if (ret < 0) { if (ret != -ENOSYS) pr_warning("Could not initialize trace " @@ -1324,8 +1324,8 @@ static __init int event_trace_init(void) /* The linker may leave blanks */ if (!call->name) continue; - if (call->raw_init) { - ret = call->raw_init(call); + if (call->class->raw_init) { + ret = call->class->raw_init(call); if (ret < 0) { if (ret != -ENOSYS) pr_warning("Could not initialize trace " diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c index e700a0c1803f..e878d06c0ac0 100644 --- a/kernel/trace/trace_export.c +++ b/kernel/trace/trace_export.c @@ -158,6 +158,7 @@ static int ftrace_raw_init_event(struct ftrace_event_call *call) struct ftrace_event_class event_class_ftrace_##call = { \ .system = __stringify(TRACE_SYSTEM), \ .define_fields = ftrace_define_fields_##call, \ + .raw_init = ftrace_raw_init_event, \ }; \ \ struct ftrace_event_call __used \ @@ -166,7 +167,6 @@ __attribute__((section("_ftrace_events"))) event_##call = { \ .name = #call, \ .id = type, \ .class = &event_class_ftrace_##call, \ - .raw_init = ftrace_raw_init_event, \ .print_fmt = print, \ }; \ diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index b14bf745356f..428f4a52de69 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -1359,13 +1359,13 @@ static int register_probe_event(struct trace_probe *tp) /* Initialize ftrace_event_call */ if (probe_is_return(tp)) { tp->event.trace = print_kretprobe_event; - call->raw_init = probe_event_raw_init; INIT_LIST_HEAD(&call->class->fields); + call->class->raw_init = probe_event_raw_init; call->class->define_fields = kretprobe_event_define_fields; } else { - tp->event.trace = print_kprobe_event; - call->raw_init = probe_event_raw_init; INIT_LIST_HEAD(&call->class->fields); + tp->event.trace = print_kprobe_event; + call->class->raw_init = probe_event_raw_init; call->class->define_fields = kprobe_event_define_fields; } if (set_print_fmt(tp) < 0) diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c index cceccf0d2e91..1c1b9bf3ccc6 100644 --- a/kernel/trace/trace_syscalls.c +++ b/kernel/trace/trace_syscalls.c @@ -44,6 +44,7 @@ struct ftrace_event_class event_class_syscall_enter = { .reg = syscall_enter_register, .define_fields = syscall_enter_define_fields, .get_fields = syscall_get_enter_fields, + .raw_init = init_syscall_trace, }; struct ftrace_event_class event_class_syscall_exit = { @@ -51,6 +52,7 @@ struct ftrace_event_class event_class_syscall_exit = { .reg = syscall_exit_register, .define_fields = syscall_exit_define_fields, .get_fields = syscall_get_exit_fields, + .raw_init = init_syscall_trace, }; extern unsigned long __start_syscalls_metadata[]; -- cgit v1.2.1 From a9a5776380208a3e48a92d0c763ee1a3b486fb73 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 22 Apr 2010 18:46:14 -0400 Subject: tracing: Allow events to share their print functions Multiple events may use the same method to print their data. Instead of having all events have a pointer to their print funtions, the trace_event structure now points to a trace_event_functions structure that will hold the way to print ouf the event. The event itself is now passed to the print function to let the print function know what kind of event it should print. This opens the door to consolidating the way several events print their output. text data bss dec hex filename 4913961 1088356 861512 6863829 68bbd5 vmlinux.orig 4900382 1048964 861512 6810858 67ecea vmlinux.init 4900446 1049028 861512 6810986 67ed6a vmlinux.preprint This change slightly increases the size but is needed for the next change. v3: Fix the branch tracer events to handle this change. v2: Fix the new function graph tracer event calls to handle this change. Acked-by: Mathieu Desnoyers Acked-by: Masami Hiramatsu Acked-by: Frederic Weisbecker Signed-off-by: Steven Rostedt --- kernel/trace/blktrace.c | 13 +++- kernel/trace/kmemtrace.c | 28 +++++-- kernel/trace/trace.c | 9 ++- kernel/trace/trace_branch.c | 8 +- kernel/trace/trace_functions_graph.c | 13 +++- kernel/trace/trace_kprobe.c | 22 ++++-- kernel/trace/trace_output.c | 137 +++++++++++++++++++++++------------ kernel/trace/trace_output.h | 2 +- kernel/trace/trace_syscalls.c | 6 +- 9 files changed, 160 insertions(+), 78 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 19d93f83e3c3..36ea2b65dcdc 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -1336,7 +1336,7 @@ out: } static enum print_line_t blk_trace_event_print(struct trace_iterator *iter, - int flags) + int flags, struct trace_event *event) { return print_one_line(iter, false); } @@ -1358,7 +1358,8 @@ static int blk_trace_synthesize_old_trace(struct trace_iterator *iter) } static enum print_line_t -blk_trace_event_print_binary(struct trace_iterator *iter, int flags) +blk_trace_event_print_binary(struct trace_iterator *iter, int flags, + struct trace_event *event) { return blk_trace_synthesize_old_trace(iter) ? TRACE_TYPE_HANDLED : TRACE_TYPE_PARTIAL_LINE; @@ -1396,12 +1397,16 @@ static struct tracer blk_tracer __read_mostly = { .set_flag = blk_tracer_set_flag, }; -static struct trace_event trace_blk_event = { - .type = TRACE_BLK, +static struct trace_event_functions trace_blk_event_funcs = { .trace = blk_trace_event_print, .binary = blk_trace_event_print_binary, }; +static struct trace_event trace_blk_event = { + .type = TRACE_BLK, + .funcs = &trace_blk_event_funcs, +}; + static int __init init_blk_tracer(void) { if (!register_ftrace_event(&trace_blk_event)) { diff --git a/kernel/trace/kmemtrace.c b/kernel/trace/kmemtrace.c index 7253d0c1c32f..bbfc1bb1660b 100644 --- a/kernel/trace/kmemtrace.c +++ b/kernel/trace/kmemtrace.c @@ -243,7 +243,8 @@ struct kmemtrace_user_event_alloc { }; static enum print_line_t -kmemtrace_print_alloc(struct trace_iterator *iter, int flags) +kmemtrace_print_alloc(struct trace_iterator *iter, int flags, + struct trace_event *event) { struct trace_seq *s = &iter->seq; struct kmemtrace_alloc_entry *entry; @@ -263,7 +264,8 @@ kmemtrace_print_alloc(struct trace_iterator *iter, int flags) } static enum print_line_t -kmemtrace_print_free(struct trace_iterator *iter, int flags) +kmemtrace_print_free(struct trace_iterator *iter, int flags, + struct trace_event *event) { struct trace_seq *s = &iter->seq; struct kmemtrace_free_entry *entry; @@ -281,7 +283,8 @@ kmemtrace_print_free(struct trace_iterator *iter, int flags) } static enum print_line_t -kmemtrace_print_alloc_user(struct trace_iterator *iter, int flags) +kmemtrace_print_alloc_user(struct trace_iterator *iter, int flags, + struct trace_event *event) { struct trace_seq *s = &iter->seq; struct kmemtrace_alloc_entry *entry; @@ -315,7 +318,8 @@ kmemtrace_print_alloc_user(struct trace_iterator *iter, int flags) } static enum print_line_t -kmemtrace_print_free_user(struct trace_iterator *iter, int flags) +kmemtrace_print_free_user(struct trace_iterator *iter, int flags, + struct trace_event *event) { struct trace_seq *s = &iter->seq; struct kmemtrace_free_entry *entry; @@ -469,18 +473,26 @@ static enum print_line_t kmemtrace_print_line(struct trace_iterator *iter) } } -static struct trace_event kmem_trace_alloc = { - .type = TRACE_KMEM_ALLOC, +static struct trace_event_functions kmem_trace_alloc_funcs = { .trace = kmemtrace_print_alloc, .binary = kmemtrace_print_alloc_user, }; -static struct trace_event kmem_trace_free = { - .type = TRACE_KMEM_FREE, +static struct trace_event kmem_trace_alloc = { + .type = TRACE_KMEM_ALLOC, + .funcs = &kmem_trace_alloc_funcs, +}; + +static struct trace_event_functions kmem_trace_free_funcs = { .trace = kmemtrace_print_free, .binary = kmemtrace_print_free_user, }; +static struct trace_event kmem_trace_free = { + .type = TRACE_KMEM_FREE, + .funcs = &kmem_trace_free_funcs, +}; + static struct tracer kmem_tracer __read_mostly = { .name = "kmemtrace", .init = kmem_trace_init, diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 756d7283318b..ba0ec81158b2 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1936,7 +1936,7 @@ static enum print_line_t print_trace_fmt(struct trace_iterator *iter) } if (event) - return event->trace(iter, sym_flags); + return event->funcs->trace(iter, sym_flags, event); if (!trace_seq_printf(s, "Unknown type %d\n", entry->type)) goto partial; @@ -1962,7 +1962,7 @@ static enum print_line_t print_raw_fmt(struct trace_iterator *iter) event = ftrace_find_event(entry->type); if (event) - return event->raw(iter, 0); + return event->funcs->raw(iter, 0, event); if (!trace_seq_printf(s, "%d ?\n", entry->type)) goto partial; @@ -1989,7 +1989,7 @@ static enum print_line_t print_hex_fmt(struct trace_iterator *iter) event = ftrace_find_event(entry->type); if (event) { - enum print_line_t ret = event->hex(iter, 0); + enum print_line_t ret = event->funcs->hex(iter, 0, event); if (ret != TRACE_TYPE_HANDLED) return ret; } @@ -2014,7 +2014,8 @@ static enum print_line_t print_bin_fmt(struct trace_iterator *iter) } event = ftrace_find_event(entry->type); - return event ? event->binary(iter, 0) : TRACE_TYPE_HANDLED; + return event ? event->funcs->binary(iter, 0, event) : + TRACE_TYPE_HANDLED; } int trace_empty(struct trace_iterator *iter) diff --git a/kernel/trace/trace_branch.c b/kernel/trace/trace_branch.c index b9bc4d470177..8d3538b4ea5f 100644 --- a/kernel/trace/trace_branch.c +++ b/kernel/trace/trace_branch.c @@ -143,7 +143,7 @@ static void branch_trace_reset(struct trace_array *tr) } static enum print_line_t trace_branch_print(struct trace_iterator *iter, - int flags) + int flags, struct trace_event *event) { struct trace_branch *field; @@ -167,9 +167,13 @@ static void branch_print_header(struct seq_file *s) " |\n"); } +static struct trace_event_functions trace_branch_funcs = { + .trace = trace_branch_print, +}; + static struct trace_event trace_branch_event = { .type = TRACE_BRANCH, - .trace = trace_branch_print, + .funcs = &trace_branch_funcs, }; static struct tracer branch_trace __read_mostly = diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index dd11c830eb84..79f4bac99a94 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -1025,7 +1025,7 @@ print_graph_comment(struct trace_seq *s, struct trace_entry *ent, if (!event) return TRACE_TYPE_UNHANDLED; - ret = event->trace(iter, sym_flags); + ret = event->funcs->trace(iter, sym_flags, event); if (ret != TRACE_TYPE_HANDLED) return ret; } @@ -1112,7 +1112,8 @@ print_graph_function(struct trace_iterator *iter) } static enum print_line_t -print_graph_function_event(struct trace_iterator *iter, int flags) +print_graph_function_event(struct trace_iterator *iter, int flags, + struct trace_event *event) { return print_graph_function(iter); } @@ -1225,14 +1226,18 @@ void graph_trace_close(struct trace_iterator *iter) } } +static struct trace_event_functions graph_functions = { + .trace = print_graph_function_event, +}; + static struct trace_event graph_trace_entry_event = { .type = TRACE_GRAPH_ENT, - .trace = print_graph_function_event, + .funcs = &graph_functions, }; static struct trace_event graph_trace_ret_event = { .type = TRACE_GRAPH_RET, - .trace = print_graph_function_event, + .funcs = &graph_functions }; static struct tracer graph_trace __read_mostly = { diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 428f4a52de69..b989ae229a20 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -1011,16 +1011,15 @@ static __kprobes void kretprobe_trace_func(struct kretprobe_instance *ri, /* Event entry printers */ enum print_line_t -print_kprobe_event(struct trace_iterator *iter, int flags) +print_kprobe_event(struct trace_iterator *iter, int flags, + struct trace_event *event) { struct kprobe_trace_entry *field; struct trace_seq *s = &iter->seq; - struct trace_event *event; struct trace_probe *tp; int i; field = (struct kprobe_trace_entry *)iter->ent; - event = ftrace_find_event(field->ent.type); tp = container_of(event, struct trace_probe, event); if (!trace_seq_printf(s, "%s: (", tp->call.name)) @@ -1046,16 +1045,15 @@ partial: } enum print_line_t -print_kretprobe_event(struct trace_iterator *iter, int flags) +print_kretprobe_event(struct trace_iterator *iter, int flags, + struct trace_event *event) { struct kretprobe_trace_entry *field; struct trace_seq *s = &iter->seq; - struct trace_event *event; struct trace_probe *tp; int i; field = (struct kretprobe_trace_entry *)iter->ent; - event = ftrace_find_event(field->ent.type); tp = container_of(event, struct trace_probe, event); if (!trace_seq_printf(s, "%s: (", tp->call.name)) @@ -1351,6 +1349,14 @@ int kretprobe_dispatcher(struct kretprobe_instance *ri, struct pt_regs *regs) return 0; /* We don't tweek kernel, so just return 0 */ } +static struct trace_event_functions kretprobe_funcs = { + .trace = print_kretprobe_event +}; + +static struct trace_event_functions kprobe_funcs = { + .trace = print_kprobe_event +}; + static int register_probe_event(struct trace_probe *tp) { struct ftrace_event_call *call = &tp->call; @@ -1358,13 +1364,13 @@ static int register_probe_event(struct trace_probe *tp) /* Initialize ftrace_event_call */ if (probe_is_return(tp)) { - tp->event.trace = print_kretprobe_event; + tp->event.funcs = &kretprobe_funcs; INIT_LIST_HEAD(&call->class->fields); call->class->raw_init = probe_event_raw_init; call->class->define_fields = kretprobe_event_define_fields; } else { INIT_LIST_HEAD(&call->class->fields); - tp->event.trace = print_kprobe_event; + tp->event.funcs = &kprobe_funcs; call->class->raw_init = probe_event_raw_init; call->class->define_fields = kprobe_event_define_fields; } diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index 2404c129a8c9..fc9d4dbb089e 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -726,6 +726,9 @@ int register_ftrace_event(struct trace_event *event) if (WARN_ON(!event)) goto out; + if (WARN_ON(!event->funcs)) + goto out; + INIT_LIST_HEAD(&event->list); if (!event->type) { @@ -758,14 +761,14 @@ int register_ftrace_event(struct trace_event *event) goto out; } - if (event->trace == NULL) - event->trace = trace_nop_print; - if (event->raw == NULL) - event->raw = trace_nop_print; - if (event->hex == NULL) - event->hex = trace_nop_print; - if (event->binary == NULL) - event->binary = trace_nop_print; + if (event->funcs->trace == NULL) + event->funcs->trace = trace_nop_print; + if (event->funcs->raw == NULL) + event->funcs->raw = trace_nop_print; + if (event->funcs->hex == NULL) + event->funcs->hex = trace_nop_print; + if (event->funcs->binary == NULL) + event->funcs->binary = trace_nop_print; key = event->type & (EVENT_HASHSIZE - 1); @@ -807,13 +810,15 @@ EXPORT_SYMBOL_GPL(unregister_ftrace_event); * Standard events */ -enum print_line_t trace_nop_print(struct trace_iterator *iter, int flags) +enum print_line_t trace_nop_print(struct trace_iterator *iter, int flags, + struct trace_event *event) { return TRACE_TYPE_HANDLED; } /* TRACE_FN */ -static enum print_line_t trace_fn_trace(struct trace_iterator *iter, int flags) +static enum print_line_t trace_fn_trace(struct trace_iterator *iter, int flags, + struct trace_event *event) { struct ftrace_entry *field; struct trace_seq *s = &iter->seq; @@ -840,7 +845,8 @@ static enum print_line_t trace_fn_trace(struct trace_iterator *iter, int flags) return TRACE_TYPE_PARTIAL_LINE; } -static enum print_line_t trace_fn_raw(struct trace_iterator *iter, int flags) +static enum print_line_t trace_fn_raw(struct trace_iterator *iter, int flags, + struct trace_event *event) { struct ftrace_entry *field; @@ -854,7 +860,8 @@ static enum print_line_t trace_fn_raw(struct trace_iterator *iter, int flags) return TRACE_TYPE_HANDLED; } -static enum print_line_t trace_fn_hex(struct trace_iterator *iter, int flags) +static enum print_line_t trace_fn_hex(struct trace_iterator *iter, int flags, + struct trace_event *event) { struct ftrace_entry *field; struct trace_seq *s = &iter->seq; @@ -867,7 +874,8 @@ static enum print_line_t trace_fn_hex(struct trace_iterator *iter, int flags) return TRACE_TYPE_HANDLED; } -static enum print_line_t trace_fn_bin(struct trace_iterator *iter, int flags) +static enum print_line_t trace_fn_bin(struct trace_iterator *iter, int flags, + struct trace_event *event) { struct ftrace_entry *field; struct trace_seq *s = &iter->seq; @@ -880,14 +888,18 @@ static enum print_line_t trace_fn_bin(struct trace_iterator *iter, int flags) return TRACE_TYPE_HANDLED; } -static struct trace_event trace_fn_event = { - .type = TRACE_FN, +static struct trace_event_functions trace_fn_funcs = { .trace = trace_fn_trace, .raw = trace_fn_raw, .hex = trace_fn_hex, .binary = trace_fn_bin, }; +static struct trace_event trace_fn_event = { + .type = TRACE_FN, + .funcs = &trace_fn_funcs, +}; + /* TRACE_CTX an TRACE_WAKE */ static enum print_line_t trace_ctxwake_print(struct trace_iterator *iter, char *delim) @@ -916,13 +928,14 @@ static enum print_line_t trace_ctxwake_print(struct trace_iterator *iter, return TRACE_TYPE_HANDLED; } -static enum print_line_t trace_ctx_print(struct trace_iterator *iter, int flags) +static enum print_line_t trace_ctx_print(struct trace_iterator *iter, int flags, + struct trace_event *event) { return trace_ctxwake_print(iter, "==>"); } static enum print_line_t trace_wake_print(struct trace_iterator *iter, - int flags) + int flags, struct trace_event *event) { return trace_ctxwake_print(iter, " +"); } @@ -950,12 +963,14 @@ static int trace_ctxwake_raw(struct trace_iterator *iter, char S) return TRACE_TYPE_HANDLED; } -static enum print_line_t trace_ctx_raw(struct trace_iterator *iter, int flags) +static enum print_line_t trace_ctx_raw(struct trace_iterator *iter, int flags, + struct trace_event *event) { return trace_ctxwake_raw(iter, 0); } -static enum print_line_t trace_wake_raw(struct trace_iterator *iter, int flags) +static enum print_line_t trace_wake_raw(struct trace_iterator *iter, int flags, + struct trace_event *event) { return trace_ctxwake_raw(iter, '+'); } @@ -984,18 +999,20 @@ static int trace_ctxwake_hex(struct trace_iterator *iter, char S) return TRACE_TYPE_HANDLED; } -static enum print_line_t trace_ctx_hex(struct trace_iterator *iter, int flags) +static enum print_line_t trace_ctx_hex(struct trace_iterator *iter, int flags, + struct trace_event *event) { return trace_ctxwake_hex(iter, 0); } -static enum print_line_t trace_wake_hex(struct trace_iterator *iter, int flags) +static enum print_line_t trace_wake_hex(struct trace_iterator *iter, int flags, + struct trace_event *event) { return trace_ctxwake_hex(iter, '+'); } static enum print_line_t trace_ctxwake_bin(struct trace_iterator *iter, - int flags) + int flags, struct trace_event *event) { struct ctx_switch_entry *field; struct trace_seq *s = &iter->seq; @@ -1012,25 +1029,33 @@ static enum print_line_t trace_ctxwake_bin(struct trace_iterator *iter, return TRACE_TYPE_HANDLED; } -static struct trace_event trace_ctx_event = { - .type = TRACE_CTX, +static struct trace_event_functions trace_ctx_funcs = { .trace = trace_ctx_print, .raw = trace_ctx_raw, .hex = trace_ctx_hex, .binary = trace_ctxwake_bin, }; -static struct trace_event trace_wake_event = { - .type = TRACE_WAKE, +static struct trace_event trace_ctx_event = { + .type = TRACE_CTX, + .funcs = &trace_ctx_funcs, +}; + +static struct trace_event_functions trace_wake_funcs = { .trace = trace_wake_print, .raw = trace_wake_raw, .hex = trace_wake_hex, .binary = trace_ctxwake_bin, }; +static struct trace_event trace_wake_event = { + .type = TRACE_WAKE, + .funcs = &trace_wake_funcs, +}; + /* TRACE_SPECIAL */ static enum print_line_t trace_special_print(struct trace_iterator *iter, - int flags) + int flags, struct trace_event *event) { struct special_entry *field; @@ -1046,7 +1071,7 @@ static enum print_line_t trace_special_print(struct trace_iterator *iter, } static enum print_line_t trace_special_hex(struct trace_iterator *iter, - int flags) + int flags, struct trace_event *event) { struct special_entry *field; struct trace_seq *s = &iter->seq; @@ -1061,7 +1086,7 @@ static enum print_line_t trace_special_hex(struct trace_iterator *iter, } static enum print_line_t trace_special_bin(struct trace_iterator *iter, - int flags) + int flags, struct trace_event *event) { struct special_entry *field; struct trace_seq *s = &iter->seq; @@ -1075,18 +1100,22 @@ static enum print_line_t trace_special_bin(struct trace_iterator *iter, return TRACE_TYPE_HANDLED; } -static struct trace_event trace_special_event = { - .type = TRACE_SPECIAL, +static struct trace_event_functions trace_special_funcs = { .trace = trace_special_print, .raw = trace_special_print, .hex = trace_special_hex, .binary = trace_special_bin, }; +static struct trace_event trace_special_event = { + .type = TRACE_SPECIAL, + .funcs = &trace_special_funcs, +}; + /* TRACE_STACK */ static enum print_line_t trace_stack_print(struct trace_iterator *iter, - int flags) + int flags, struct trace_event *event) { struct stack_entry *field; struct trace_seq *s = &iter->seq; @@ -1114,17 +1143,21 @@ static enum print_line_t trace_stack_print(struct trace_iterator *iter, return TRACE_TYPE_PARTIAL_LINE; } -static struct trace_event trace_stack_event = { - .type = TRACE_STACK, +static struct trace_event_functions trace_stack_funcs = { .trace = trace_stack_print, .raw = trace_special_print, .hex = trace_special_hex, .binary = trace_special_bin, }; +static struct trace_event trace_stack_event = { + .type = TRACE_STACK, + .funcs = &trace_stack_funcs, +}; + /* TRACE_USER_STACK */ static enum print_line_t trace_user_stack_print(struct trace_iterator *iter, - int flags) + int flags, struct trace_event *event) { struct userstack_entry *field; struct trace_seq *s = &iter->seq; @@ -1143,17 +1176,22 @@ static enum print_line_t trace_user_stack_print(struct trace_iterator *iter, return TRACE_TYPE_PARTIAL_LINE; } -static struct trace_event trace_user_stack_event = { - .type = TRACE_USER_STACK, +static struct trace_event_functions trace_user_stack_funcs = { .trace = trace_user_stack_print, .raw = trace_special_print, .hex = trace_special_hex, .binary = trace_special_bin, }; +static struct trace_event trace_user_stack_event = { + .type = TRACE_USER_STACK, + .funcs = &trace_user_stack_funcs, +}; + /* TRACE_BPRINT */ static enum print_line_t -trace_bprint_print(struct trace_iterator *iter, int flags) +trace_bprint_print(struct trace_iterator *iter, int flags, + struct trace_event *event) { struct trace_entry *entry = iter->ent; struct trace_seq *s = &iter->seq; @@ -1178,7 +1216,8 @@ trace_bprint_print(struct trace_iterator *iter, int flags) static enum print_line_t -trace_bprint_raw(struct trace_iterator *iter, int flags) +trace_bprint_raw(struct trace_iterator *iter, int flags, + struct trace_event *event) { struct bprint_entry *field; struct trace_seq *s = &iter->seq; @@ -1197,16 +1236,19 @@ trace_bprint_raw(struct trace_iterator *iter, int flags) return TRACE_TYPE_PARTIAL_LINE; } +static struct trace_event_functions trace_bprint_funcs = { + .trace = trace_bprint_print, + .raw = trace_bprint_raw, +}; static struct trace_event trace_bprint_event = { .type = TRACE_BPRINT, - .trace = trace_bprint_print, - .raw = trace_bprint_raw, + .funcs = &trace_bprint_funcs, }; /* TRACE_PRINT */ static enum print_line_t trace_print_print(struct trace_iterator *iter, - int flags) + int flags, struct trace_event *event) { struct print_entry *field; struct trace_seq *s = &iter->seq; @@ -1225,7 +1267,8 @@ static enum print_line_t trace_print_print(struct trace_iterator *iter, return TRACE_TYPE_PARTIAL_LINE; } -static enum print_line_t trace_print_raw(struct trace_iterator *iter, int flags) +static enum print_line_t trace_print_raw(struct trace_iterator *iter, int flags, + struct trace_event *event) { struct print_entry *field; @@ -1240,12 +1283,16 @@ static enum print_line_t trace_print_raw(struct trace_iterator *iter, int flags) return TRACE_TYPE_PARTIAL_LINE; } -static struct trace_event trace_print_event = { - .type = TRACE_PRINT, +static struct trace_event_functions trace_print_funcs = { .trace = trace_print_print, .raw = trace_print_raw, }; +static struct trace_event trace_print_event = { + .type = TRACE_PRINT, + .funcs = &trace_print_funcs, +}; + static struct trace_event *events[] __initdata = { &trace_fn_event, diff --git a/kernel/trace/trace_output.h b/kernel/trace/trace_output.h index 9d91c72ba38b..c038eba0492b 100644 --- a/kernel/trace/trace_output.h +++ b/kernel/trace/trace_output.h @@ -25,7 +25,7 @@ extern void trace_event_read_unlock(void); extern struct trace_event *ftrace_find_event(int type); extern enum print_line_t trace_nop_print(struct trace_iterator *iter, - int flags); + int flags, struct trace_event *event); extern int trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry); diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c index 1c1b9bf3ccc6..3751c81998cb 100644 --- a/kernel/trace/trace_syscalls.c +++ b/kernel/trace/trace_syscalls.c @@ -93,7 +93,8 @@ static struct syscall_metadata *syscall_nr_to_meta(int nr) } enum print_line_t -print_syscall_enter(struct trace_iterator *iter, int flags) +print_syscall_enter(struct trace_iterator *iter, int flags, + struct trace_event *event) { struct trace_seq *s = &iter->seq; struct trace_entry *ent = iter->ent; @@ -145,7 +146,8 @@ end: } enum print_line_t -print_syscall_exit(struct trace_iterator *iter, int flags) +print_syscall_exit(struct trace_iterator *iter, int flags, + struct trace_event *event) { struct trace_seq *s = &iter->seq; struct trace_entry *ent = iter->ent; -- cgit v1.2.1 From 80decc70afc57c87eee9d6b836aec2ecacba3457 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 23 Apr 2010 10:00:22 -0400 Subject: tracing: Move print functions into event class Currently, every event has its own trace_event structure. This is fine since the structure is needed anyway. But the print function structure (trace_event_functions) is now separate. Since the output of the trace event is done by the class (with the exception of events defined by DEFINE_EVENT_PRINT), it makes sense to have the class define the print functions that all events in the class can use. This makes a bigger deal with the syscall events since all syscall events use the same class. The savings here is another 30K. text data bss dec hex filename 4913961 1088356 861512 6863829 68bbd5 vmlinux.orig 4900382 1048964 861512 6810858 67ecea vmlinux.init 4900446 1049028 861512 6810986 67ed6a vmlinux.preprint 4895024 1023812 861512 6780348 6775bc vmlinux.print To accomplish this, and to let the class know what event is being printed, the event structure is embedded in the ftrace_event_call structure. This should not be an issues since the event structure was created for each event anyway. Acked-by: Mathieu Desnoyers Acked-by: Masami Hiramatsu Acked-by: Frederic Weisbecker Signed-off-by: Steven Rostedt --- kernel/trace/trace_events.c | 6 +++--- kernel/trace/trace_kprobe.c | 14 ++++++-------- kernel/trace/trace_syscalls.c | 8 ++++++++ 3 files changed, 17 insertions(+), 11 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 8e94255a45e7..aafe5bff8f59 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -122,7 +122,7 @@ int trace_event_raw_init(struct ftrace_event_call *call) { int id; - id = register_ftrace_event(call->event); + id = register_ftrace_event(&call->event); if (!id) return -ENODEV; call->id = id; @@ -1073,8 +1073,8 @@ static void remove_subsystem_dir(const char *name) static void __trace_remove_event_call(struct ftrace_event_call *call) { ftrace_event_enable_disable(call, 0); - if (call->event) - __unregister_ftrace_event(call->event); + if (call->event.funcs) + __unregister_ftrace_event(&call->event); debugfs_remove_recursive(call->dir); list_del(&call->list); trace_destroy_fields(call); diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index b989ae229a20..d8061c3e02c9 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -204,7 +204,6 @@ struct trace_probe { const char *symbol; /* symbol name */ struct ftrace_event_class class; struct ftrace_event_call call; - struct trace_event event; unsigned int nr_args; struct probe_arg args[]; }; @@ -1020,7 +1019,7 @@ print_kprobe_event(struct trace_iterator *iter, int flags, int i; field = (struct kprobe_trace_entry *)iter->ent; - tp = container_of(event, struct trace_probe, event); + tp = container_of(event, struct trace_probe, call.event); if (!trace_seq_printf(s, "%s: (", tp->call.name)) goto partial; @@ -1054,7 +1053,7 @@ print_kretprobe_event(struct trace_iterator *iter, int flags, int i; field = (struct kretprobe_trace_entry *)iter->ent; - tp = container_of(event, struct trace_probe, event); + tp = container_of(event, struct trace_probe, call.event); if (!trace_seq_printf(s, "%s: (", tp->call.name)) goto partial; @@ -1364,20 +1363,19 @@ static int register_probe_event(struct trace_probe *tp) /* Initialize ftrace_event_call */ if (probe_is_return(tp)) { - tp->event.funcs = &kretprobe_funcs; INIT_LIST_HEAD(&call->class->fields); + call->event.funcs = &kretprobe_funcs; call->class->raw_init = probe_event_raw_init; call->class->define_fields = kretprobe_event_define_fields; } else { INIT_LIST_HEAD(&call->class->fields); - tp->event.funcs = &kprobe_funcs; + call->event.funcs = &kprobe_funcs; call->class->raw_init = probe_event_raw_init; call->class->define_fields = kprobe_event_define_fields; } if (set_print_fmt(tp) < 0) return -ENOMEM; - call->event = &tp->event; - call->id = register_ftrace_event(&tp->event); + call->id = register_ftrace_event(&call->event); if (!call->id) { kfree(call->print_fmt); return -ENODEV; @@ -1389,7 +1387,7 @@ static int register_probe_event(struct trace_probe *tp) if (ret) { pr_info("Failed to register kprobe event: %s\n", call->name); kfree(call->print_fmt); - unregister_ftrace_event(&tp->event); + unregister_ftrace_event(&call->event); } return ret; } diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c index 3751c81998cb..7c7cfe95a853 100644 --- a/kernel/trace/trace_syscalls.c +++ b/kernel/trace/trace_syscalls.c @@ -39,6 +39,14 @@ syscall_get_exit_fields(struct ftrace_event_call *call) return &entry->exit_fields; } +struct trace_event_functions enter_syscall_print_funcs = { + .trace = print_syscall_enter, +}; + +struct trace_event_functions exit_syscall_print_funcs = { + .trace = print_syscall_exit, +}; + struct ftrace_event_class event_class_syscall_enter = { .system = "syscalls", .reg = syscall_enter_register, -- cgit v1.2.1 From 32c0edaeaad74a7883e736ae0f3798784cfc2a80 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 23 Apr 2010 10:38:03 -0400 Subject: tracing: Remove duplicate id information in event structure Now that the trace_event structure is embedded in the ftrace_event_call structure, there is no need for the ftrace_event_call id field. The id field is the same as the trace_event type field. Removing the id and re-arranging the structure brings down the tracepoint footprint by another 5K. text data bss dec hex filename 4913961 1088356 861512 6863829 68bbd5 vmlinux.orig 4895024 1023812 861512 6780348 6775bc vmlinux.print 4894944 1018052 861512 6774508 675eec vmlinux.id Acked-by: Mathieu Desnoyers Acked-by: Masami Hiramatsu Acked-by: Frederic Weisbecker Signed-off-by: Steven Rostedt --- kernel/trace/trace_event_perf.c | 4 ++-- kernel/trace/trace_events.c | 7 +++---- kernel/trace/trace_events_filter.c | 2 +- kernel/trace/trace_export.c | 4 ++-- kernel/trace/trace_kprobe.c | 18 ++++++++++-------- kernel/trace/trace_syscalls.c | 14 ++++++++------ 6 files changed, 26 insertions(+), 23 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c index 196fe9d26773..0a47e8d6b491 100644 --- a/kernel/trace/trace_event_perf.c +++ b/kernel/trace/trace_event_perf.c @@ -80,7 +80,7 @@ int perf_trace_enable(int event_id) mutex_lock(&event_mutex); list_for_each_entry(event, &ftrace_events, list) { - if (event->id == event_id && + if (event->event.type == event_id && event->class && event->class->perf_probe && try_module_get(event->mod)) { ret = perf_trace_event_enable(event); @@ -128,7 +128,7 @@ void perf_trace_disable(int event_id) mutex_lock(&event_mutex); list_for_each_entry(event, &ftrace_events, list) { - if (event->id == event_id) { + if (event->event.type == event_id) { perf_trace_event_disable(event); module_put(event->mod); break; diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index aafe5bff8f59..8daaca5475b5 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -125,7 +125,6 @@ int trace_event_raw_init(struct ftrace_event_call *call) id = register_ftrace_event(&call->event); if (!id) return -ENODEV; - call->id = id; return 0; } @@ -567,7 +566,7 @@ event_format_read(struct file *filp, char __user *ubuf, size_t cnt, trace_seq_init(s); trace_seq_printf(s, "name: %s\n", call->name); - trace_seq_printf(s, "ID: %d\n", call->id); + trace_seq_printf(s, "ID: %d\n", call->event.type); trace_seq_printf(s, "format:\n"); head = trace_get_fields(call); @@ -641,7 +640,7 @@ event_id_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) return -ENOMEM; trace_seq_init(s); - trace_seq_printf(s, "%d\n", call->id); + trace_seq_printf(s, "%d\n", call->event.type); r = simple_read_from_buffer(ubuf, cnt, ppos, s->buffer, s->len); @@ -969,7 +968,7 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events, enable); #ifdef CONFIG_PERF_EVENTS - if (call->id && (call->class->perf_probe || call->class->reg)) + if (call->event.type && (call->class->perf_probe || call->class->reg)) trace_create_file("id", 0444, call->dir, call, id); #endif diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index 961f99b74bdd..2702d6bbf1ab 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -1395,7 +1395,7 @@ int ftrace_profile_set_filter(struct perf_event *event, int event_id, mutex_lock(&event_mutex); list_for_each_entry(call, &ftrace_events, list) { - if (call->id == event_id) + if (call->event.type == event_id) break; } diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c index e878d06c0ac0..8536e2a65969 100644 --- a/kernel/trace/trace_export.c +++ b/kernel/trace/trace_export.c @@ -153,7 +153,7 @@ static int ftrace_raw_init_event(struct ftrace_event_call *call) #define F_printk(fmt, args...) #fmt ", " __stringify(args) #undef FTRACE_ENTRY -#define FTRACE_ENTRY(call, struct_name, type, tstruct, print) \ +#define FTRACE_ENTRY(call, struct_name, etype, tstruct, print) \ \ struct ftrace_event_class event_class_ftrace_##call = { \ .system = __stringify(TRACE_SYSTEM), \ @@ -165,7 +165,7 @@ struct ftrace_event_call __used \ __attribute__((__aligned__(4))) \ __attribute__((section("_ftrace_events"))) event_##call = { \ .name = #call, \ - .id = type, \ + .event.type = etype, \ .class = &event_class_ftrace_##call, \ .print_fmt = print, \ }; \ diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index d8061c3e02c9..934078bca3f9 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -960,8 +960,8 @@ static __kprobes void kprobe_trace_func(struct kprobe *kp, struct pt_regs *regs) size = SIZEOF_KPROBE_TRACE_ENTRY(tp->nr_args); - event = trace_current_buffer_lock_reserve(&buffer, call->id, size, - irq_flags, pc); + event = trace_current_buffer_lock_reserve(&buffer, call->event.type, + size, irq_flags, pc); if (!event) return; @@ -992,8 +992,8 @@ static __kprobes void kretprobe_trace_func(struct kretprobe_instance *ri, size = SIZEOF_KRETPROBE_TRACE_ENTRY(tp->nr_args); - event = trace_current_buffer_lock_reserve(&buffer, call->id, size, - irq_flags, pc); + event = trace_current_buffer_lock_reserve(&buffer, call->event.type, + size, irq_flags, pc); if (!event) return; @@ -1228,7 +1228,8 @@ static __kprobes void kprobe_perf_func(struct kprobe *kp, "profile buffer not large enough")) return; - entry = perf_trace_buf_prepare(size, call->id, &rctx, &irq_flags); + entry = perf_trace_buf_prepare(size, call->event.type, + &rctx, &irq_flags); if (!entry) return; @@ -1258,7 +1259,8 @@ static __kprobes void kretprobe_perf_func(struct kretprobe_instance *ri, "profile buffer not large enough")) return; - entry = perf_trace_buf_prepare(size, call->id, &rctx, &irq_flags); + entry = perf_trace_buf_prepare(size, call->event.type, + &rctx, &irq_flags); if (!entry) return; @@ -1375,8 +1377,8 @@ static int register_probe_event(struct trace_probe *tp) } if (set_print_fmt(tp) < 0) return -ENOMEM; - call->id = register_ftrace_event(&call->event); - if (!call->id) { + ret = register_ftrace_event(&call->event); + if (!ret) { kfree(call->print_fmt); return -ENODEV; } diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c index 7c7cfe95a853..9d358301ae3e 100644 --- a/kernel/trace/trace_syscalls.c +++ b/kernel/trace/trace_syscalls.c @@ -117,7 +117,7 @@ print_syscall_enter(struct trace_iterator *iter, int flags, if (!entry) goto end; - if (entry->enter_event->id != ent->type) { + if (entry->enter_event->event.type != ent->type) { WARN_ON_ONCE(1); goto end; } @@ -173,7 +173,7 @@ print_syscall_exit(struct trace_iterator *iter, int flags, return TRACE_TYPE_HANDLED; } - if (entry->exit_event->id != ent->type) { + if (entry->exit_event->event.type != ent->type) { WARN_ON_ONCE(1); return TRACE_TYPE_UNHANDLED; } @@ -315,7 +315,7 @@ void ftrace_syscall_enter(void *ignore, struct pt_regs *regs, long id) size = sizeof(*entry) + sizeof(unsigned long) * sys_data->nb_args; event = trace_current_buffer_lock_reserve(&buffer, - sys_data->enter_event->id, size, 0, 0); + sys_data->enter_event->event.type, size, 0, 0); if (!event) return; @@ -347,7 +347,7 @@ void ftrace_syscall_exit(void *ignore, struct pt_regs *regs, long ret) return; event = trace_current_buffer_lock_reserve(&buffer, - sys_data->exit_event->id, sizeof(*entry), 0, 0); + sys_data->exit_event->event.type, sizeof(*entry), 0, 0); if (!event) return; @@ -511,7 +511,8 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id) return; rec = (struct syscall_trace_enter *)perf_trace_buf_prepare(size, - sys_data->enter_event->id, &rctx, &flags); + sys_data->enter_event->event.type, + &rctx, &flags); if (!rec) return; @@ -586,7 +587,8 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret) return; rec = (struct syscall_trace_exit *)perf_trace_buf_prepare(size, - sys_data->exit_event->id, &rctx, &flags); + sys_data->exit_event->event.type, + &rctx, &flags); if (!rec) return; -- cgit v1.2.1 From 553552ce1796c32cf4e3d4f45cd5b537de91dd1d Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 23 Apr 2010 11:12:36 -0400 Subject: tracing: Combine event filter_active and enable into single flags field The filter_active and enable both use an int (4 bytes each) to set a single flag. We can save 4 bytes per event by combining the two into a single integer. text data bss dec hex filename 4913961 1088356 861512 6863829 68bbd5 vmlinux.orig 4894944 1018052 861512 6774508 675eec vmlinux.id 4894871 1012292 861512 6768675 674823 vmlinux.flags This gives us another 5K in savings. The modification of both the enable and filter fields are done under the event_mutex, so it is still safe to combine the two. Note: Although Mathieu gave his Acked-by, he would like it documented that the reads of flags are not protected by the mutex. The way the code works, these reads will not break anything, but will have a residual effect. Since this behavior is the same even before this patch, describing this situation is left to another patch, as this patch does not change the behavior, but just brought it to Mathieu's attention. v2: Updated the event trace self test to for this change. Acked-by: Mathieu Desnoyers Acked-by: Masami Hiramatsu Acked-by: Frederic Weisbecker Cc: Tom Zanussi Signed-off-by: Steven Rostedt --- kernel/trace/trace.h | 2 +- kernel/trace/trace_events.c | 16 ++++++++-------- kernel/trace/trace_events_filter.c | 10 +++++----- kernel/trace/trace_kprobe.c | 2 +- 4 files changed, 15 insertions(+), 15 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index c88c563a59a5..63562595f2b2 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -802,7 +802,7 @@ filter_check_discard(struct ftrace_event_call *call, void *rec, struct ring_buffer *buffer, struct ring_buffer_event *event) { - if (unlikely(call->filter_active) && + if (unlikely(call->flags & TRACE_EVENT_FL_FILTERED) && !filter_match_preds(call->filter, rec)) { ring_buffer_discard_commit(buffer, event); return 1; diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 8daaca5475b5..53cffc0b0801 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -137,8 +137,8 @@ static int ftrace_event_enable_disable(struct ftrace_event_call *call, switch (enable) { case 0: - if (call->enabled) { - call->enabled = 0; + if (call->flags & TRACE_EVENT_FL_ENABLED) { + call->flags &= ~TRACE_EVENT_FL_ENABLED; tracing_stop_cmdline_record(); if (call->class->reg) call->class->reg(call, TRACE_REG_UNREGISTER); @@ -149,7 +149,7 @@ static int ftrace_event_enable_disable(struct ftrace_event_call *call, } break; case 1: - if (!call->enabled) { + if (!(call->flags & TRACE_EVENT_FL_ENABLED)) { tracing_start_cmdline_record(); if (call->class->reg) ret = call->class->reg(call, TRACE_REG_REGISTER); @@ -163,7 +163,7 @@ static int ftrace_event_enable_disable(struct ftrace_event_call *call, "%s\n", call->name); break; } - call->enabled = 1; + call->flags |= TRACE_EVENT_FL_ENABLED; } break; } @@ -352,7 +352,7 @@ s_next(struct seq_file *m, void *v, loff_t *pos) (*pos)++; list_for_each_entry_continue(call, &ftrace_events, list) { - if (call->enabled) + if (call->flags & TRACE_EVENT_FL_ENABLED) return call; } @@ -411,7 +411,7 @@ event_enable_read(struct file *filp, char __user *ubuf, size_t cnt, struct ftrace_event_call *call = filp->private_data; char *buf; - if (call->enabled) + if (call->flags & TRACE_EVENT_FL_ENABLED) buf = "1\n"; else buf = "0\n"; @@ -486,7 +486,7 @@ system_enable_read(struct file *filp, char __user *ubuf, size_t cnt, * or if all events or cleared, or if we have * a mixture. */ - set |= (1 << !!call->enabled); + set |= (1 << !!(call->flags & TRACE_EVENT_FL_ENABLED)); /* * If we have a mixture, no need to look further. @@ -1447,7 +1447,7 @@ static __init void event_trace_self_tests(void) * If an event is already enabled, someone is using * it and the self test should not be on. */ - if (call->enabled) { + if (call->flags & TRACE_EVENT_FL_ENABLED) { pr_warning("Enabled event during self test!\n"); WARN_ON_ONCE(1); continue; diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index 2702d6bbf1ab..239ea5d77d68 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -547,7 +547,7 @@ static void filter_disable_preds(struct ftrace_event_call *call) struct event_filter *filter = call->filter; int i; - call->filter_active = 0; + call->flags &= ~TRACE_EVENT_FL_FILTERED; filter->n_preds = 0; for (i = 0; i < MAX_FILTER_PRED; i++) @@ -574,7 +574,7 @@ void destroy_preds(struct ftrace_event_call *call) { __free_preds(call->filter); call->filter = NULL; - call->filter_active = 0; + call->flags &= ~TRACE_EVENT_FL_FILTERED; } static struct event_filter *__alloc_preds(void) @@ -613,7 +613,7 @@ static int init_preds(struct ftrace_event_call *call) if (call->filter) return 0; - call->filter_active = 0; + call->flags &= ~TRACE_EVENT_FL_FILTERED; call->filter = __alloc_preds(); if (IS_ERR(call->filter)) return PTR_ERR(call->filter); @@ -1268,7 +1268,7 @@ static int replace_system_preds(struct event_subsystem *system, if (err) filter_disable_preds(call); else { - call->filter_active = 1; + call->flags |= TRACE_EVENT_FL_FILTERED; replace_filter_string(filter, filter_string); } fail = false; @@ -1317,7 +1317,7 @@ int apply_event_filter(struct ftrace_event_call *call, char *filter_string) if (err) append_filter_err(ps, call->filter); else - call->filter_active = 1; + call->flags |= TRACE_EVENT_FL_FILTERED; out: filter_opstack_clear(ps); postfix_clear(ps); diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 934078bca3f9..0e3ded64cdb7 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -1382,7 +1382,7 @@ static int register_probe_event(struct trace_probe *tp) kfree(call->print_fmt); return -ENODEV; } - call->enabled = 0; + call->flags = 0; call->class->reg = kprobe_register; call->data = tp; ret = trace_add_event_call(call); -- cgit v1.2.1 From e1f7992e015ae1373d66c8068d0a45e4111a0aed Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Mon, 10 May 2010 11:23:00 +0800 Subject: tracing: Fix function declarations if !CONFIG_STACKTRACE ftrace_trace_stack() and frace_trace_userstacke() take a struct ring_buffer argument, not struct trace_array. Commit e77405ad("tracing: pass around ring buffer instead of tracer") made this change. Signed-off-by: Li Zefan LKML-Reference: <4BE77C14.5010806@cn.fujitsu.com> Signed-off-by: Steven Rostedt --- kernel/trace/trace.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 63562595f2b2..40cd1718fb1b 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -419,12 +419,12 @@ void ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, void __trace_stack(struct trace_array *tr, unsigned long flags, int skip, int pc); #else -static inline void ftrace_trace_stack(struct trace_array *tr, +static inline void ftrace_trace_stack(struct ring_buffer *buffer, unsigned long flags, int skip, int pc) { } -static inline void ftrace_trace_userstack(struct trace_array *tr, +static inline void ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc) { } -- cgit v1.2.1 From 4f41c013f553957765902fb01475972f0af3e8e7 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 18 May 2010 18:08:32 +0200 Subject: perf/ftrace: Optimize perf/tracepoint interaction for single events When we've got but a single event per tracepoint there is no reason to try and multiplex it so don't. Signed-off-by: Peter Zijlstra Tested-by: Ingo Molnar Cc: Steven Rostedt Cc: Frederic Weisbecker Cc: Mike Galbraith Cc: Paul Mackerras Cc: Arnaldo Carvalho de Melo LKML-Reference: Signed-off-by: Ingo Molnar --- kernel/perf_event.c | 15 ++++++++++----- kernel/trace/trace_event_perf.c | 11 +++++++---- kernel/trace/trace_kprobe.c | 4 ++-- kernel/trace/trace_syscalls.c | 6 ++++-- 4 files changed, 23 insertions(+), 13 deletions(-) (limited to 'kernel') diff --git a/kernel/perf_event.c b/kernel/perf_event.c index a4fa381db3c2..17ac47f4bce6 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -4468,8 +4468,9 @@ static int swevent_hlist_get(struct perf_event *event) #ifdef CONFIG_EVENT_TRACING void perf_tp_event(int event_id, u64 addr, u64 count, void *record, - int entry_size, struct pt_regs *regs) + int entry_size, struct pt_regs *regs, void *event) { + const int type = PERF_TYPE_TRACEPOINT; struct perf_sample_data data; struct perf_raw_record raw = { .size = entry_size, @@ -4479,9 +4480,13 @@ void perf_tp_event(int event_id, u64 addr, u64 count, void *record, perf_sample_data_init(&data, addr); data.raw = &raw; - /* Trace events already protected against recursion */ - do_perf_sw_event(PERF_TYPE_TRACEPOINT, event_id, count, 1, - &data, regs); + if (!event) { + do_perf_sw_event(type, event_id, count, 1, &data, regs); + return; + } + + if (perf_swevent_match(event, type, event_id, &data, regs)) + perf_swevent_add(event, count, 1, &data, regs); } EXPORT_SYMBOL_GPL(perf_tp_event); @@ -4514,7 +4519,7 @@ static const struct pmu *tp_perf_event_init(struct perf_event *event) !capable(CAP_SYS_ADMIN)) return ERR_PTR(-EPERM); - if (perf_trace_enable(event->attr.config)) + if (perf_trace_enable(event->attr.config, event)) return NULL; event->destroy = tp_perf_event_destroy; diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c index 0565bb42566f..89b780a7c522 100644 --- a/kernel/trace/trace_event_perf.c +++ b/kernel/trace/trace_event_perf.c @@ -27,13 +27,15 @@ typedef typeof(unsigned long [PERF_MAX_TRACE_SIZE / sizeof(unsigned long)]) /* Count the events in use (per event id, not per instance) */ static int total_ref_count; -static int perf_trace_event_enable(struct ftrace_event_call *event) +static int perf_trace_event_enable(struct ftrace_event_call *event, void *data) { char *buf; int ret = -ENOMEM; - if (event->perf_refcount++ > 0) + if (event->perf_refcount++ > 0) { + event->perf_data = NULL; return 0; + } if (!total_ref_count) { buf = (char *)alloc_percpu(perf_trace_t); @@ -51,6 +53,7 @@ static int perf_trace_event_enable(struct ftrace_event_call *event) ret = event->perf_event_enable(event); if (!ret) { + event->perf_data = data; total_ref_count++; return 0; } @@ -68,7 +71,7 @@ fail_buf: return ret; } -int perf_trace_enable(int event_id) +int perf_trace_enable(int event_id, void *data) { struct ftrace_event_call *event; int ret = -EINVAL; @@ -77,7 +80,7 @@ int perf_trace_enable(int event_id) list_for_each_entry(event, &ftrace_events, list) { if (event->id == event_id && event->perf_event_enable && try_module_get(event->mod)) { - ret = perf_trace_event_enable(event); + ret = perf_trace_event_enable(event, data); break; } } diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index a7514326052b..2d7bf4146be8 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -1362,7 +1362,7 @@ static __kprobes void kprobe_perf_func(struct kprobe *kp, for (i = 0; i < tp->nr_args; i++) call_fetch(&tp->args[i].fetch, regs, data + tp->args[i].offset); - perf_trace_buf_submit(entry, size, rctx, entry->ip, 1, irq_flags, regs); + perf_trace_buf_submit(entry, size, rctx, entry->ip, 1, irq_flags, regs, call->perf_data); } /* Kretprobe profile handler */ @@ -1395,7 +1395,7 @@ static __kprobes void kretprobe_perf_func(struct kretprobe_instance *ri, call_fetch(&tp->args[i].fetch, regs, data + tp->args[i].offset); perf_trace_buf_submit(entry, size, rctx, entry->ret_ip, 1, - irq_flags, regs); + irq_flags, regs, call->perf_data); } static int probe_perf_enable(struct ftrace_event_call *call) diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c index 4d6d711717f2..9eff1a4b49b9 100644 --- a/kernel/trace/trace_syscalls.c +++ b/kernel/trace/trace_syscalls.c @@ -468,7 +468,8 @@ static void perf_syscall_enter(struct pt_regs *regs, long id) rec->nr = syscall_nr; syscall_get_arguments(current, regs, 0, sys_data->nb_args, (unsigned long *)&rec->args); - perf_trace_buf_submit(rec, size, rctx, 0, 1, flags, regs); + perf_trace_buf_submit(rec, size, rctx, 0, 1, flags, regs, + sys_data->enter_event->perf_data); } int perf_sysenter_enable(struct ftrace_event_call *call) @@ -543,7 +544,8 @@ static void perf_syscall_exit(struct pt_regs *regs, long ret) rec->nr = syscall_nr; rec->ret = syscall_get_return_value(current, regs); - perf_trace_buf_submit(rec, size, rctx, 0, 1, flags, regs); + perf_trace_buf_submit(rec, size, rctx, 0, 1, flags, regs, + sys_data->exit_event->perf_data); } int perf_sysexit_enable(struct ftrace_event_call *call) -- cgit v1.2.1 From 00d1d0b095ba4e5c0958cb228b2a9c445d4a339d Mon Sep 17 00:00:00 2001 From: Stephane Eranian Date: Mon, 17 May 2010 12:46:01 +0200 Subject: perf: Fix errors path in perf_output_begin() In case the sampling buffer has no "payload" pages, nr_pages is 0. The problem is that the error path in perf_output_begin() skips to a label which assumes perf_output_lock() has been issued which is not the case. That triggers a WARN_ON() in perf_output_unlock(). This patch fixes the problem by skipping perf_output_unlock() in case data->nr_pages is 0. Signed-off-by: Stephane Eranian Signed-off-by: Peter Zijlstra Cc: Mike Galbraith Cc: Paul Mackerras Cc: Arnaldo Carvalho de Melo Cc: Frederic Weisbecker LKML-Reference: <4bf13674.014fd80a.6c82.ffffb20c@mx.google.com> Signed-off-by: Ingo Molnar --- kernel/perf_event.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/perf_event.c b/kernel/perf_event.c index 17ac47f4bce6..8d61d292f719 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -3036,7 +3036,7 @@ int perf_output_begin(struct perf_output_handle *handle, handle->sample = sample; if (!data->nr_pages) - goto fail; + goto out; have_lost = atomic_read(&data->lost); if (have_lost) -- cgit v1.2.1 From a19d35c11fd559dd7dfd5a2078df7c9af74a5d88 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 17 May 2010 18:48:00 +0200 Subject: perf: Optimize buffer placement by allocating buffers NUMA aware Ensure cpu bound buffers live on the right NUMA node. Suggested-by: Stephane Eranian Signed-off-by: Peter Zijlstra Cc: Mike Galbraith Cc: Paul Mackerras Cc: Arnaldo Carvalho de Melo Cc: Frederic Weisbecker LKML-Reference: <1274114880.5605.5236.camel@twins> Signed-off-by: Ingo Molnar --- kernel/perf_event.c | 17 +++++++++++++++-- 1 file changed, 15 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/perf_event.c b/kernel/perf_event.c index 8d61d292f719..6ae62186dd0c 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -2320,6 +2320,19 @@ perf_mmap_to_page(struct perf_mmap_data *data, unsigned long pgoff) return virt_to_page(data->data_pages[pgoff - 1]); } +static void *perf_mmap_alloc_page(int cpu) +{ + struct page *page; + int node; + + node = (cpu == -1) ? cpu : cpu_to_node(cpu); + page = alloc_pages_node(node, GFP_KERNEL | __GFP_ZERO, 0); + if (!page) + return NULL; + + return page_address(page); +} + static struct perf_mmap_data * perf_mmap_data_alloc(struct perf_event *event, int nr_pages) { @@ -2336,12 +2349,12 @@ perf_mmap_data_alloc(struct perf_event *event, int nr_pages) if (!data) goto fail; - data->user_page = (void *)get_zeroed_page(GFP_KERNEL); + data->user_page = perf_mmap_alloc_page(event->cpu); if (!data->user_page) goto fail_user_page; for (i = 0; i < nr_pages; i++) { - data->data_pages[i] = (void *)get_zeroed_page(GFP_KERNEL); + data->data_pages[i] = perf_mmap_alloc_page(event->cpu); if (!data->data_pages[i]) goto fail_data_pages; } -- cgit v1.2.1 From c7920614cebbf269a7c8397ff959a8dcf727465c Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 18 May 2010 10:33:24 +0200 Subject: perf: Disallow mmap() on per-task inherited events Since we now have working per-task-per-cpu events for a while, disallow mmap() on per-task inherited events. Those things were a performance problem anyway, and doing away with it allows us to optimize the buffer somewhat by assuming there is only a single writer. Signed-off-by: Peter Zijlstra Cc: Mike Galbraith Cc: Paul Mackerras Cc: Arnaldo Carvalho de Melo Cc: Frederic Weisbecker LKML-Reference: Signed-off-by: Ingo Molnar --- kernel/perf_event.c | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'kernel') diff --git a/kernel/perf_event.c b/kernel/perf_event.c index 6ae62186dd0c..ff5d430d45a7 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -2593,6 +2593,14 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma) long user_extra, extra; int ret = 0; + /* + * Don't allow mmap() of inherited per-task counters. This would + * create a performance issue due to all children writing to the + * same buffer. + */ + if (event->cpu == -1 && event->attr.inherit) + return -EINVAL; + if (!(vma->vm_flags & VM_SHARED)) return -EINVAL; -- cgit v1.2.1 From ef60777c9abd999db5eb4e338aae3eb593ae8e10 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 18 May 2010 10:50:41 +0200 Subject: perf: Optimize the perf_output() path by removing IRQ-disables Since we can now assume there is only a single writer to each buffer, we can remove per-cpu lock thingy and use a simply nest-count to the same effect. This removes the need to disable IRQs. Signed-off-by: Peter Zijlstra Cc: Mike Galbraith Cc: Paul Mackerras Cc: Arnaldo Carvalho de Melo Cc: Frederic Weisbecker LKML-Reference: Signed-off-by: Ingo Molnar --- kernel/perf_event.c | 94 ++++++++++++++++------------------------------------- 1 file changed, 28 insertions(+), 66 deletions(-) (limited to 'kernel') diff --git a/kernel/perf_event.c b/kernel/perf_event.c index ff5d430d45a7..8cf737da3ec4 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -2519,8 +2519,6 @@ perf_mmap_data_init(struct perf_event *event, struct perf_mmap_data *data) { long max_size = perf_data_size(data); - atomic_set(&data->lock, -1); - if (event->attr.watermark) { data->watermark = min_t(long, max_size, event->attr.wakeup_watermark); @@ -2906,82 +2904,56 @@ static void perf_output_wakeup(struct perf_output_handle *handle) } /* - * Curious locking construct. - * * We need to ensure a later event_id doesn't publish a head when a former - * event_id isn't done writing. However since we need to deal with NMIs we + * event isn't done writing. However since we need to deal with NMIs we * cannot fully serialize things. * - * What we do is serialize between CPUs so we only have to deal with NMI - * nesting on a single CPU. - * * We only publish the head (and generate a wakeup) when the outer-most - * event_id completes. + * event completes. */ -static void perf_output_lock(struct perf_output_handle *handle) +static void perf_output_get_handle(struct perf_output_handle *handle) { struct perf_mmap_data *data = handle->data; - int cur, cpu = get_cpu(); - handle->locked = 0; - - for (;;) { - cur = atomic_cmpxchg(&data->lock, -1, cpu); - if (cur == -1) { - handle->locked = 1; - break; - } - if (cur == cpu) - break; - - cpu_relax(); - } + preempt_disable(); + atomic_inc(&data->nest); } -static void perf_output_unlock(struct perf_output_handle *handle) +static void perf_output_put_handle(struct perf_output_handle *handle) { struct perf_mmap_data *data = handle->data; unsigned long head; - int cpu; - - data->done_head = data->head; - - if (!handle->locked) - goto out; again: - /* - * The xchg implies a full barrier that ensures all writes are done - * before we publish the new head, matched by a rmb() in userspace when - * reading this position. - */ - while ((head = atomic_long_xchg(&data->done_head, 0))) - data->user_page->data_head = head; + head = atomic_long_read(&data->head); /* - * NMI can happen here, which means we can miss a done_head update. + * IRQ/NMI can happen here, which means we can miss a head update. */ - cpu = atomic_xchg(&data->lock, -1); - WARN_ON_ONCE(cpu != smp_processor_id()); + if (!atomic_dec_and_test(&data->nest)) + return; /* - * Therefore we have to validate we did not indeed do so. + * Publish the known good head. Rely on the full barrier implied + * by atomic_dec_and_test() order the data->head read and this + * write. */ - if (unlikely(atomic_long_read(&data->done_head))) { - /* - * Since we had it locked, we can lock it again. - */ - while (atomic_cmpxchg(&data->lock, -1, cpu) != -1) - cpu_relax(); + data->user_page->data_head = head; + /* + * Now check if we missed an update, rely on the (compiler) + * barrier in atomic_dec_and_test() to re-read data->head. + */ + if (unlikely(head != atomic_long_read(&data->head))) { + atomic_inc(&data->nest); goto again; } if (atomic_xchg(&data->wakeup, 0)) perf_output_wakeup(handle); -out: - put_cpu(); + + preempt_enable(); } void perf_output_copy(struct perf_output_handle *handle, @@ -3063,7 +3035,7 @@ int perf_output_begin(struct perf_output_handle *handle, if (have_lost) size += sizeof(lost_event); - perf_output_lock(handle); + perf_output_get_handle(handle); do { /* @@ -3083,7 +3055,7 @@ int perf_output_begin(struct perf_output_handle *handle, handle->head = head; if (head - tail > data->watermark) - atomic_set(&data->wakeup, 1); + atomic_inc(&data->wakeup); if (have_lost) { lost_event.header.type = PERF_RECORD_LOST; @@ -3099,7 +3071,7 @@ int perf_output_begin(struct perf_output_handle *handle, fail: atomic_inc(&data->lost); - perf_output_unlock(handle); + perf_output_put_handle(handle); out: rcu_read_unlock(); @@ -3117,11 +3089,11 @@ void perf_output_end(struct perf_output_handle *handle) int events = atomic_inc_return(&data->events); if (events >= wakeup_events) { atomic_sub(wakeup_events, &data->events); - atomic_set(&data->wakeup, 1); + atomic_inc(&data->wakeup); } } - perf_output_unlock(handle); + perf_output_put_handle(handle); rcu_read_unlock(); } @@ -3457,22 +3429,13 @@ static void perf_event_task_output(struct perf_event *event, { struct perf_output_handle handle; struct task_struct *task = task_event->task; - unsigned long flags; int size, ret; - /* - * If this CPU attempts to acquire an rq lock held by a CPU spinning - * in perf_output_lock() from interrupt context, it's game over. - */ - local_irq_save(flags); - size = task_event->event_id.header.size; ret = perf_output_begin(&handle, event, size, 0, 0); - if (ret) { - local_irq_restore(flags); + if (ret) return; - } task_event->event_id.pid = perf_event_pid(event, task); task_event->event_id.ppid = perf_event_pid(event, current); @@ -3483,7 +3446,6 @@ static void perf_event_task_output(struct perf_event *event, perf_output_put(&handle, task_event->event_id); perf_output_end(&handle); - local_irq_restore(flags); } static int perf_event_task_match(struct perf_event *event) -- cgit v1.2.1 From fa5881514ef9c9bcb29319aad85cf2d8889d91f1 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 18 May 2010 10:54:20 +0200 Subject: perf: Optimize the hotpath by converting the perf output buffer to local_t Since there is now only a single writer, we can use local_t instead and avoid all these pesky LOCK insn. Signed-off-by: Peter Zijlstra LKML-Reference: Signed-off-by: Ingo Molnar --- kernel/perf_event.c | 30 +++++++++++++++--------------- 1 file changed, 15 insertions(+), 15 deletions(-) (limited to 'kernel') diff --git a/kernel/perf_event.c b/kernel/perf_event.c index 8cf737da3ec4..1f98c78c3343 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -2916,7 +2916,7 @@ static void perf_output_get_handle(struct perf_output_handle *handle) struct perf_mmap_data *data = handle->data; preempt_disable(); - atomic_inc(&data->nest); + local_inc(&data->nest); } static void perf_output_put_handle(struct perf_output_handle *handle) @@ -2925,13 +2925,13 @@ static void perf_output_put_handle(struct perf_output_handle *handle) unsigned long head; again: - head = atomic_long_read(&data->head); + head = local_read(&data->head); /* * IRQ/NMI can happen here, which means we can miss a head update. */ - if (!atomic_dec_and_test(&data->nest)) + if (!local_dec_and_test(&data->nest)) return; /* @@ -2945,12 +2945,12 @@ again: * Now check if we missed an update, rely on the (compiler) * barrier in atomic_dec_and_test() to re-read data->head. */ - if (unlikely(head != atomic_long_read(&data->head))) { - atomic_inc(&data->nest); + if (unlikely(head != local_read(&data->head))) { + local_inc(&data->nest); goto again; } - if (atomic_xchg(&data->wakeup, 0)) + if (local_xchg(&data->wakeup, 0)) perf_output_wakeup(handle); preempt_enable(); @@ -3031,7 +3031,7 @@ int perf_output_begin(struct perf_output_handle *handle, if (!data->nr_pages) goto out; - have_lost = atomic_read(&data->lost); + have_lost = local_read(&data->lost); if (have_lost) size += sizeof(lost_event); @@ -3045,24 +3045,24 @@ int perf_output_begin(struct perf_output_handle *handle, */ tail = ACCESS_ONCE(data->user_page->data_tail); smp_rmb(); - offset = head = atomic_long_read(&data->head); + offset = head = local_read(&data->head); head += size; if (unlikely(!perf_output_space(data, tail, offset, head))) goto fail; - } while (atomic_long_cmpxchg(&data->head, offset, head) != offset); + } while (local_cmpxchg(&data->head, offset, head) != offset); handle->offset = offset; handle->head = head; if (head - tail > data->watermark) - atomic_inc(&data->wakeup); + local_inc(&data->wakeup); if (have_lost) { lost_event.header.type = PERF_RECORD_LOST; lost_event.header.misc = 0; lost_event.header.size = sizeof(lost_event); lost_event.id = event->id; - lost_event.lost = atomic_xchg(&data->lost, 0); + lost_event.lost = local_xchg(&data->lost, 0); perf_output_put(handle, lost_event); } @@ -3070,7 +3070,7 @@ int perf_output_begin(struct perf_output_handle *handle, return 0; fail: - atomic_inc(&data->lost); + local_inc(&data->lost); perf_output_put_handle(handle); out: rcu_read_unlock(); @@ -3086,10 +3086,10 @@ void perf_output_end(struct perf_output_handle *handle) int wakeup_events = event->attr.wakeup_events; if (handle->sample && wakeup_events) { - int events = atomic_inc_return(&data->events); + int events = local_inc_return(&data->events); if (events >= wakeup_events) { - atomic_sub(wakeup_events, &data->events); - atomic_inc(&data->wakeup); + local_sub(wakeup_events, &data->events); + local_inc(&data->wakeup); } } -- cgit v1.2.1 From 6d1acfd5c6bfd5231c13a8f2858d7f2afbaa1b62 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 18 May 2010 11:12:48 +0200 Subject: perf: Optimize perf_output_*() by avoiding local_xchg() Since the x86 XCHG ins implies LOCK, avoid the use by using a sequence count instead. Signed-off-by: Peter Zijlstra LKML-Reference: Signed-off-by: Ingo Molnar --- kernel/perf_event.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/perf_event.c b/kernel/perf_event.c index 1f98c78c3343..7e3bcf1a29f0 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -2917,6 +2917,7 @@ static void perf_output_get_handle(struct perf_output_handle *handle) preempt_disable(); local_inc(&data->nest); + handle->wakeup = local_read(&data->wakeup); } static void perf_output_put_handle(struct perf_output_handle *handle) @@ -2950,7 +2951,7 @@ again: goto again; } - if (local_xchg(&data->wakeup, 0)) + if (handle->wakeup != local_read(&data->wakeup)) perf_output_wakeup(handle); preempt_enable(); -- cgit v1.2.1 From 49f135ed02828a58b2401f149926c2e3c9cb0116 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Thu, 20 May 2010 10:17:46 +0200 Subject: perf: Comply with new rcu checks API The software events hlist doesn't fully comply with the new rcu checks api. We need to consider three different sides that access the hlist: - the hlist allocation/release side. This side happens when an events is created or released, accesses to the hlist are serialized under the cpuctx mutex. - the events insertion/removal in the hlist. This side is always serialized against the above one. The hlist is always present during such operations. This side happens when a software event is scheduled in/out. The serialization that ensures the software event is really attached to the context is made under the ctx->lock. - events triggering. This is the read side, it can happen concurrently with any update side. This patch deals with them one by one and anticipates with the separate rcu mem space patches in preparation. This patch fixes various annoying rcu warnings. Reported-by: Paul E. McKenney Signed-off-by: Frederic Weisbecker Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Arnaldo Carvalho de Melo Cc: Paul Mackerras --- kernel/perf_event.c | 58 ++++++++++++++++++++++++++++++++++++++++++----------- 1 file changed, 46 insertions(+), 12 deletions(-) (limited to 'kernel') diff --git a/kernel/perf_event.c b/kernel/perf_event.c index a4fa381db3c2..511677bc1c6a 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -4066,19 +4066,46 @@ static inline u64 swevent_hash(u64 type, u32 event_id) return hash_64(val, SWEVENT_HLIST_BITS); } -static struct hlist_head * -find_swevent_head(struct perf_cpu_context *ctx, u64 type, u32 event_id) +static inline struct hlist_head * +__find_swevent_head(struct swevent_hlist *hlist, u64 type, u32 event_id) { - u64 hash; - struct swevent_hlist *hlist; + u64 hash = swevent_hash(type, event_id); + + return &hlist->heads[hash]; +} - hash = swevent_hash(type, event_id); +/* For the read side: events when they trigger */ +static inline struct hlist_head * +find_swevent_head_rcu(struct perf_cpu_context *ctx, u64 type, u32 event_id) +{ + struct swevent_hlist *hlist; hlist = rcu_dereference(ctx->swevent_hlist); if (!hlist) return NULL; - return &hlist->heads[hash]; + return __find_swevent_head(hlist, type, event_id); +} + +/* For the event head insertion and removal in the hlist */ +static inline struct hlist_head * +find_swevent_head(struct perf_cpu_context *ctx, struct perf_event *event) +{ + struct swevent_hlist *hlist; + u32 event_id = event->attr.config; + u64 type = event->attr.type; + + /* + * Event scheduling is always serialized against hlist allocation + * and release. Which makes the protected version suitable here. + * The context lock guarantees that. + */ + hlist = rcu_dereference_protected(ctx->swevent_hlist, + lockdep_is_held(&event->ctx->lock)); + if (!hlist) + return NULL; + + return __find_swevent_head(hlist, type, event_id); } static void do_perf_sw_event(enum perf_type_id type, u32 event_id, @@ -4095,7 +4122,7 @@ static void do_perf_sw_event(enum perf_type_id type, u32 event_id, rcu_read_lock(); - head = find_swevent_head(cpuctx, type, event_id); + head = find_swevent_head_rcu(cpuctx, type, event_id); if (!head) goto end; @@ -4178,7 +4205,7 @@ static int perf_swevent_enable(struct perf_event *event) perf_swevent_set_period(event); } - head = find_swevent_head(cpuctx, event->attr.type, event->attr.config); + head = find_swevent_head(cpuctx, event); if (WARN_ON_ONCE(!head)) return -EINVAL; @@ -4366,6 +4393,14 @@ static const struct pmu perf_ops_task_clock = { .read = task_clock_perf_event_read, }; +/* Deref the hlist from the update side */ +static inline struct swevent_hlist * +swevent_hlist_deref(struct perf_cpu_context *cpuctx) +{ + return rcu_dereference_protected(cpuctx->swevent_hlist, + lockdep_is_held(&cpuctx->hlist_mutex)); +} + static void swevent_hlist_release_rcu(struct rcu_head *rcu_head) { struct swevent_hlist *hlist; @@ -4376,12 +4411,11 @@ static void swevent_hlist_release_rcu(struct rcu_head *rcu_head) static void swevent_hlist_release(struct perf_cpu_context *cpuctx) { - struct swevent_hlist *hlist; + struct swevent_hlist *hlist = swevent_hlist_deref(cpuctx); - if (!cpuctx->swevent_hlist) + if (!hlist) return; - hlist = cpuctx->swevent_hlist; rcu_assign_pointer(cpuctx->swevent_hlist, NULL); call_rcu(&hlist->rcu_head, swevent_hlist_release_rcu); } @@ -4418,7 +4452,7 @@ static int swevent_hlist_get_cpu(struct perf_event *event, int cpu) mutex_lock(&cpuctx->hlist_mutex); - if (!cpuctx->swevent_hlist && cpu_online(cpu)) { + if (!swevent_hlist_deref(cpuctx) && cpu_online(cpu)) { struct swevent_hlist *hlist; hlist = kzalloc(sizeof(*hlist), GFP_KERNEL); -- cgit v1.2.1 From acd35a463cb2a8d2b28e094d718cf6e653ad7191 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Thu, 20 May 2010 21:28:34 +0200 Subject: perf: Fix forgotten preempt_enable by nested writers A writer that gets a reference to the buffer handle disables preemption. When we put that reference, we check if we are the outer most writer and if not, we simply return and defer the head update to the outer most writer. The problem here is that preemption is only reenabled by the outer most, that produces preemption count imbalance for every nested writer that exit. So just don't forget to always re-enable preemption when we put the buffer reference, whoever we are. Fixes lots of sleeping in atomic warnings, visible with lock events recording. Signed-off-by: Frederic Weisbecker Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Arnaldo Carvalho de Melo Cc: Paul Mackerras Cc: Stephane Eranian Cc: Robert Richter --- kernel/perf_event.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/perf_event.c b/kernel/perf_event.c index 2a060be3b07f..45b7aec55458 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -2933,7 +2933,7 @@ again: */ if (!local_dec_and_test(&data->nest)) - return; + goto out; /* * Publish the known good head. Rely on the full barrier implied @@ -2954,6 +2954,7 @@ again: if (handle->wakeup != local_read(&data->wakeup)) perf_output_wakeup(handle); + out: preempt_enable(); } -- cgit v1.2.1 From b7e2ecef92d2e7785e6d76b41e5ba8bcbc45259d Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 19 May 2010 10:52:27 +0200 Subject: perf, trace: Optimize tracepoints by removing IRQ-disable from perf/tracepoint interaction Improves performance. Acked-by: Frederic Weisbecker Signed-off-by: Peter Zijlstra Cc: Arnaldo Carvalho de Melo Cc: Frederic Weisbecker Cc: Paul Mackerras Cc: Mike Galbraith Cc: Steven Rostedt LKML-Reference: <1274259525.5605.10352.camel@twins> Signed-off-by: Ingo Molnar --- kernel/trace/trace_event_perf.c | 73 ++++++++++++++++------------------------- kernel/trace/trace_kprobe.c | 10 +++--- kernel/trace/trace_syscalls.c | 10 +++--- 3 files changed, 37 insertions(+), 56 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c index 89b780a7c522..a1304f8c4440 100644 --- a/kernel/trace/trace_event_perf.c +++ b/kernel/trace/trace_event_perf.c @@ -9,13 +9,9 @@ #include #include "trace.h" -DEFINE_PER_CPU(struct pt_regs, perf_trace_regs); -EXPORT_PER_CPU_SYMBOL_GPL(perf_trace_regs); - EXPORT_SYMBOL_GPL(perf_arch_fetch_caller_regs); -static char *perf_trace_buf; -static char *perf_trace_buf_nmi; +static char *perf_trace_buf[4]; /* * Force it to be aligned to unsigned long to avoid misaligned accesses @@ -29,7 +25,6 @@ static int total_ref_count; static int perf_trace_event_enable(struct ftrace_event_call *event, void *data) { - char *buf; int ret = -ENOMEM; if (event->perf_refcount++ > 0) { @@ -38,17 +33,16 @@ static int perf_trace_event_enable(struct ftrace_event_call *event, void *data) } if (!total_ref_count) { - buf = (char *)alloc_percpu(perf_trace_t); - if (!buf) - goto fail_buf; - - rcu_assign_pointer(perf_trace_buf, buf); + char *buf; + int i; - buf = (char *)alloc_percpu(perf_trace_t); - if (!buf) - goto fail_buf_nmi; + for (i = 0; i < 4; i++) { + buf = (char *)alloc_percpu(perf_trace_t); + if (!buf) + goto fail_buf; - rcu_assign_pointer(perf_trace_buf_nmi, buf); + rcu_assign_pointer(perf_trace_buf[i], buf); + } } ret = event->perf_event_enable(event); @@ -58,14 +52,15 @@ static int perf_trace_event_enable(struct ftrace_event_call *event, void *data) return 0; } -fail_buf_nmi: +fail_buf: if (!total_ref_count) { - free_percpu(perf_trace_buf_nmi); - free_percpu(perf_trace_buf); - perf_trace_buf_nmi = NULL; - perf_trace_buf = NULL; + int i; + + for (i = 0; i < 4; i++) { + free_percpu(perf_trace_buf[i]); + perf_trace_buf[i] = NULL; + } } -fail_buf: event->perf_refcount--; return ret; @@ -91,19 +86,19 @@ int perf_trace_enable(int event_id, void *data) static void perf_trace_event_disable(struct ftrace_event_call *event) { - char *buf, *nmi_buf; - if (--event->perf_refcount > 0) return; event->perf_event_disable(event); if (!--total_ref_count) { - buf = perf_trace_buf; - rcu_assign_pointer(perf_trace_buf, NULL); + char *buf[4]; + int i; - nmi_buf = perf_trace_buf_nmi; - rcu_assign_pointer(perf_trace_buf_nmi, NULL); + for (i = 0; i < 4; i++) { + buf[i] = perf_trace_buf[i]; + rcu_assign_pointer(perf_trace_buf[i], NULL); + } /* * Ensure every events in profiling have finished before @@ -111,8 +106,8 @@ static void perf_trace_event_disable(struct ftrace_event_call *event) */ synchronize_sched(); - free_percpu(buf); - free_percpu(nmi_buf); + for (i = 0; i < 4; i++) + free_percpu(buf[i]); } } @@ -132,47 +127,37 @@ void perf_trace_disable(int event_id) } __kprobes void *perf_trace_buf_prepare(int size, unsigned short type, - int *rctxp, unsigned long *irq_flags) + struct pt_regs *regs, int *rctxp) { struct trace_entry *entry; char *trace_buf, *raw_data; - int pc, cpu; + int pc; BUILD_BUG_ON(PERF_MAX_TRACE_SIZE % sizeof(unsigned long)); pc = preempt_count(); - /* Protect the per cpu buffer, begin the rcu read side */ - local_irq_save(*irq_flags); - *rctxp = perf_swevent_get_recursion_context(); if (*rctxp < 0) goto err_recursion; - cpu = smp_processor_id(); - - if (in_nmi()) - trace_buf = rcu_dereference_sched(perf_trace_buf_nmi); - else - trace_buf = rcu_dereference_sched(perf_trace_buf); - + trace_buf = rcu_dereference_sched(perf_trace_buf[*rctxp]); if (!trace_buf) goto err; - raw_data = per_cpu_ptr(trace_buf, cpu); + raw_data = per_cpu_ptr(trace_buf, smp_processor_id()); /* zero the dead bytes from align to not leak stack to user */ memset(&raw_data[size - sizeof(u64)], 0, sizeof(u64)); entry = (struct trace_entry *)raw_data; - tracing_generic_entry_update(entry, *irq_flags, pc); + tracing_generic_entry_update(entry, regs->flags, pc); entry->type = type; return raw_data; err: perf_swevent_put_recursion_context(*rctxp); err_recursion: - local_irq_restore(*irq_flags); return NULL; } EXPORT_SYMBOL_GPL(perf_trace_buf_prepare); diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 2d7bf4146be8..20c96de0aea0 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -1343,7 +1343,6 @@ static __kprobes void kprobe_perf_func(struct kprobe *kp, struct kprobe_trace_entry_head *entry; u8 *data; int size, __size, i; - unsigned long irq_flags; int rctx; __size = sizeof(*entry) + tp->size; @@ -1353,7 +1352,7 @@ static __kprobes void kprobe_perf_func(struct kprobe *kp, "profile buffer not large enough")) return; - entry = perf_trace_buf_prepare(size, call->id, &rctx, &irq_flags); + entry = perf_trace_buf_prepare(size, call->id, regs, &rctx); if (!entry) return; @@ -1362,7 +1361,7 @@ static __kprobes void kprobe_perf_func(struct kprobe *kp, for (i = 0; i < tp->nr_args; i++) call_fetch(&tp->args[i].fetch, regs, data + tp->args[i].offset); - perf_trace_buf_submit(entry, size, rctx, entry->ip, 1, irq_flags, regs, call->perf_data); + perf_trace_buf_submit(entry, size, rctx, entry->ip, 1, regs, call->perf_data); } /* Kretprobe profile handler */ @@ -1374,7 +1373,6 @@ static __kprobes void kretprobe_perf_func(struct kretprobe_instance *ri, struct kretprobe_trace_entry_head *entry; u8 *data; int size, __size, i; - unsigned long irq_flags; int rctx; __size = sizeof(*entry) + tp->size; @@ -1384,7 +1382,7 @@ static __kprobes void kretprobe_perf_func(struct kretprobe_instance *ri, "profile buffer not large enough")) return; - entry = perf_trace_buf_prepare(size, call->id, &rctx, &irq_flags); + entry = perf_trace_buf_prepare(size, call->id, regs, &rctx); if (!entry) return; @@ -1395,7 +1393,7 @@ static __kprobes void kretprobe_perf_func(struct kretprobe_instance *ri, call_fetch(&tp->args[i].fetch, regs, data + tp->args[i].offset); perf_trace_buf_submit(entry, size, rctx, entry->ret_ip, 1, - irq_flags, regs, call->perf_data); + regs, call->perf_data); } static int probe_perf_enable(struct ftrace_event_call *call) diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c index 9eff1a4b49b9..a657cefbb137 100644 --- a/kernel/trace/trace_syscalls.c +++ b/kernel/trace/trace_syscalls.c @@ -438,7 +438,6 @@ static void perf_syscall_enter(struct pt_regs *regs, long id) { struct syscall_metadata *sys_data; struct syscall_trace_enter *rec; - unsigned long flags; int syscall_nr; int rctx; int size; @@ -461,14 +460,14 @@ static void perf_syscall_enter(struct pt_regs *regs, long id) return; rec = (struct syscall_trace_enter *)perf_trace_buf_prepare(size, - sys_data->enter_event->id, &rctx, &flags); + sys_data->enter_event->id, regs, &rctx); if (!rec) return; rec->nr = syscall_nr; syscall_get_arguments(current, regs, 0, sys_data->nb_args, (unsigned long *)&rec->args); - perf_trace_buf_submit(rec, size, rctx, 0, 1, flags, regs, + perf_trace_buf_submit(rec, size, rctx, 0, 1, regs, sys_data->enter_event->perf_data); } @@ -511,7 +510,6 @@ static void perf_syscall_exit(struct pt_regs *regs, long ret) { struct syscall_metadata *sys_data; struct syscall_trace_exit *rec; - unsigned long flags; int syscall_nr; int rctx; int size; @@ -537,14 +535,14 @@ static void perf_syscall_exit(struct pt_regs *regs, long ret) return; rec = (struct syscall_trace_exit *)perf_trace_buf_prepare(size, - sys_data->exit_event->id, &rctx, &flags); + sys_data->exit_event->id, regs, &rctx); if (!rec) return; rec->nr = syscall_nr; rec->ret = syscall_get_return_value(current, regs); - perf_trace_buf_submit(rec, size, rctx, 0, 1, flags, regs, + perf_trace_buf_submit(rec, size, rctx, 0, 1, regs, sys_data->exit_event->perf_data); } -- cgit v1.2.1 From 1c024eca51fdc965290acf342ae16a476c2189d0 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 19 May 2010 14:02:22 +0200 Subject: perf, trace: Optimize tracepoints by using per-tracepoint-per-cpu hlist to track events Avoid the swevent hash-table by using per-tracepoint hlists. Also, avoid conditionals on the fast path by ordering with probe unregister so that we should never get on the callback path without the data being there. Signed-off-by: Peter Zijlstra Cc: Arnaldo Carvalho de Melo Cc: Frederic Weisbecker Cc: Paul Mackerras Cc: Mike Galbraith Cc: Steven Rostedt LKML-Reference: <20100521090710.473188012@chello.nl> Signed-off-by: Ingo Molnar --- kernel/perf_event.c | 94 ++++++++++++++--------------- kernel/trace/trace_event_perf.c | 127 +++++++++++++++++++++------------------- kernel/trace/trace_kprobe.c | 9 ++- kernel/trace/trace_syscalls.c | 11 ++-- 4 files changed, 128 insertions(+), 113 deletions(-) (limited to 'kernel') diff --git a/kernel/perf_event.c b/kernel/perf_event.c index 45b7aec55458..3f2cc313ee25 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -4005,9 +4005,6 @@ static void perf_swevent_add(struct perf_event *event, u64 nr, perf_swevent_overflow(event, 0, nmi, data, regs); } -static int perf_tp_event_match(struct perf_event *event, - struct perf_sample_data *data); - static int perf_exclude_event(struct perf_event *event, struct pt_regs *regs) { @@ -4037,10 +4034,6 @@ static int perf_swevent_match(struct perf_event *event, if (perf_exclude_event(event, regs)) return 0; - if (event->attr.type == PERF_TYPE_TRACEPOINT && - !perf_tp_event_match(event, data)) - return 0; - return 1; } @@ -4122,7 +4115,7 @@ end: int perf_swevent_get_recursion_context(void) { - struct perf_cpu_context *cpuctx = &get_cpu_var(perf_cpu_context); + struct perf_cpu_context *cpuctx = &__get_cpu_var(perf_cpu_context); int rctx; if (in_nmi()) @@ -4134,10 +4127,8 @@ int perf_swevent_get_recursion_context(void) else rctx = 0; - if (cpuctx->recursion[rctx]) { - put_cpu_var(perf_cpu_context); + if (cpuctx->recursion[rctx]) return -1; - } cpuctx->recursion[rctx]++; barrier(); @@ -4151,7 +4142,6 @@ void perf_swevent_put_recursion_context(int rctx) struct perf_cpu_context *cpuctx = &__get_cpu_var(perf_cpu_context); barrier(); cpuctx->recursion[rctx]--; - put_cpu_var(perf_cpu_context); } EXPORT_SYMBOL_GPL(perf_swevent_put_recursion_context); @@ -4162,6 +4152,7 @@ void __perf_sw_event(u32 event_id, u64 nr, int nmi, struct perf_sample_data data; int rctx; + preempt_disable_notrace(); rctx = perf_swevent_get_recursion_context(); if (rctx < 0) return; @@ -4171,6 +4162,7 @@ void __perf_sw_event(u32 event_id, u64 nr, int nmi, do_perf_sw_event(PERF_TYPE_SOFTWARE, event_id, nr, nmi, &data, regs); perf_swevent_put_recursion_context(rctx); + preempt_enable_notrace(); } static void perf_swevent_read(struct perf_event *event) @@ -4486,11 +4478,43 @@ static int swevent_hlist_get(struct perf_event *event) #ifdef CONFIG_EVENT_TRACING -void perf_tp_event(int event_id, u64 addr, u64 count, void *record, - int entry_size, struct pt_regs *regs, void *event) +static const struct pmu perf_ops_tracepoint = { + .enable = perf_trace_enable, + .disable = perf_trace_disable, + .read = perf_swevent_read, + .unthrottle = perf_swevent_unthrottle, +}; + +static int perf_tp_filter_match(struct perf_event *event, + struct perf_sample_data *data) +{ + void *record = data->raw->data; + + if (likely(!event->filter) || filter_match_preds(event->filter, record)) + return 1; + return 0; +} + +static int perf_tp_event_match(struct perf_event *event, + struct perf_sample_data *data, + struct pt_regs *regs) +{ + if (perf_exclude_event(event, regs)) + return 0; + + if (!perf_tp_filter_match(event, data)) + return 0; + + return 1; +} + +void perf_tp_event(u64 addr, u64 count, void *record, int entry_size, + struct pt_regs *regs, struct hlist_head *head) { - const int type = PERF_TYPE_TRACEPOINT; struct perf_sample_data data; + struct perf_event *event; + struct hlist_node *node; + struct perf_raw_record raw = { .size = entry_size, .data = record, @@ -4499,30 +4523,18 @@ void perf_tp_event(int event_id, u64 addr, u64 count, void *record, perf_sample_data_init(&data, addr); data.raw = &raw; - if (!event) { - do_perf_sw_event(type, event_id, count, 1, &data, regs); - return; + rcu_read_lock(); + hlist_for_each_entry_rcu(event, node, head, hlist_entry) { + if (perf_tp_event_match(event, &data, regs)) + perf_swevent_add(event, count, 1, &data, regs); } - - if (perf_swevent_match(event, type, event_id, &data, regs)) - perf_swevent_add(event, count, 1, &data, regs); + rcu_read_unlock(); } EXPORT_SYMBOL_GPL(perf_tp_event); -static int perf_tp_event_match(struct perf_event *event, - struct perf_sample_data *data) -{ - void *record = data->raw->data; - - if (likely(!event->filter) || filter_match_preds(event->filter, record)) - return 1; - return 0; -} - static void tp_perf_event_destroy(struct perf_event *event) { - perf_trace_disable(event->attr.config); - swevent_hlist_put(event); + perf_trace_destroy(event); } static const struct pmu *tp_perf_event_init(struct perf_event *event) @@ -4538,17 +4550,13 @@ static const struct pmu *tp_perf_event_init(struct perf_event *event) !capable(CAP_SYS_ADMIN)) return ERR_PTR(-EPERM); - if (perf_trace_enable(event->attr.config, event)) + err = perf_trace_init(event); + if (err) return NULL; event->destroy = tp_perf_event_destroy; - err = swevent_hlist_get(event); - if (err) { - perf_trace_disable(event->attr.config); - return ERR_PTR(err); - } - return &perf_ops_generic; + return &perf_ops_tracepoint; } static int perf_event_set_filter(struct perf_event *event, void __user *arg) @@ -4576,12 +4584,6 @@ static void perf_event_free_filter(struct perf_event *event) #else -static int perf_tp_event_match(struct perf_event *event, - struct perf_sample_data *data) -{ - return 1; -} - static const struct pmu *tp_perf_event_init(struct perf_event *event) { return NULL; diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c index a1304f8c4440..39d5ea7b0653 100644 --- a/kernel/trace/trace_event_perf.c +++ b/kernel/trace/trace_event_perf.c @@ -23,14 +23,25 @@ typedef typeof(unsigned long [PERF_MAX_TRACE_SIZE / sizeof(unsigned long)]) /* Count the events in use (per event id, not per instance) */ static int total_ref_count; -static int perf_trace_event_enable(struct ftrace_event_call *event, void *data) +static int perf_trace_event_init(struct ftrace_event_call *tp_event, + struct perf_event *p_event) { + struct hlist_head *list; int ret = -ENOMEM; + int cpu; - if (event->perf_refcount++ > 0) { - event->perf_data = NULL; + p_event->tp_event = tp_event; + if (tp_event->perf_refcount++ > 0) return 0; - } + + list = alloc_percpu(struct hlist_head); + if (!list) + goto fail; + + for_each_possible_cpu(cpu) + INIT_HLIST_HEAD(per_cpu_ptr(list, cpu)); + + tp_event->perf_events = list; if (!total_ref_count) { char *buf; @@ -39,20 +50,20 @@ static int perf_trace_event_enable(struct ftrace_event_call *event, void *data) for (i = 0; i < 4; i++) { buf = (char *)alloc_percpu(perf_trace_t); if (!buf) - goto fail_buf; + goto fail; - rcu_assign_pointer(perf_trace_buf[i], buf); + perf_trace_buf[i] = buf; } } - ret = event->perf_event_enable(event); - if (!ret) { - event->perf_data = data; - total_ref_count++; - return 0; - } + ret = tp_event->perf_event_enable(tp_event); + if (ret) + goto fail; -fail_buf: + total_ref_count++; + return 0; + +fail: if (!total_ref_count) { int i; @@ -61,21 +72,26 @@ fail_buf: perf_trace_buf[i] = NULL; } } - event->perf_refcount--; + + if (!--tp_event->perf_refcount) { + free_percpu(tp_event->perf_events); + tp_event->perf_events = NULL; + } return ret; } -int perf_trace_enable(int event_id, void *data) +int perf_trace_init(struct perf_event *p_event) { - struct ftrace_event_call *event; + struct ftrace_event_call *tp_event; + int event_id = p_event->attr.config; int ret = -EINVAL; mutex_lock(&event_mutex); - list_for_each_entry(event, &ftrace_events, list) { - if (event->id == event_id && event->perf_event_enable && - try_module_get(event->mod)) { - ret = perf_trace_event_enable(event, data); + list_for_each_entry(tp_event, &ftrace_events, list) { + if (tp_event->id == event_id && tp_event->perf_event_enable && + try_module_get(tp_event->mod)) { + ret = perf_trace_event_init(tp_event, p_event); break; } } @@ -84,53 +100,52 @@ int perf_trace_enable(int event_id, void *data) return ret; } -static void perf_trace_event_disable(struct ftrace_event_call *event) +int perf_trace_enable(struct perf_event *p_event) { - if (--event->perf_refcount > 0) - return; + struct ftrace_event_call *tp_event = p_event->tp_event; + struct hlist_head *list; - event->perf_event_disable(event); + list = tp_event->perf_events; + if (WARN_ON_ONCE(!list)) + return -EINVAL; - if (!--total_ref_count) { - char *buf[4]; - int i; - - for (i = 0; i < 4; i++) { - buf[i] = perf_trace_buf[i]; - rcu_assign_pointer(perf_trace_buf[i], NULL); - } + list = per_cpu_ptr(list, smp_processor_id()); + hlist_add_head_rcu(&p_event->hlist_entry, list); - /* - * Ensure every events in profiling have finished before - * releasing the buffers - */ - synchronize_sched(); + return 0; +} - for (i = 0; i < 4; i++) - free_percpu(buf[i]); - } +void perf_trace_disable(struct perf_event *p_event) +{ + hlist_del_rcu(&p_event->hlist_entry); } -void perf_trace_disable(int event_id) +void perf_trace_destroy(struct perf_event *p_event) { - struct ftrace_event_call *event; + struct ftrace_event_call *tp_event = p_event->tp_event; + int i; - mutex_lock(&event_mutex); - list_for_each_entry(event, &ftrace_events, list) { - if (event->id == event_id) { - perf_trace_event_disable(event); - module_put(event->mod); - break; + if (--tp_event->perf_refcount > 0) + return; + + tp_event->perf_event_disable(tp_event); + + free_percpu(tp_event->perf_events); + tp_event->perf_events = NULL; + + if (!--total_ref_count) { + for (i = 0; i < 4; i++) { + free_percpu(perf_trace_buf[i]); + perf_trace_buf[i] = NULL; } } - mutex_unlock(&event_mutex); } __kprobes void *perf_trace_buf_prepare(int size, unsigned short type, struct pt_regs *regs, int *rctxp) { struct trace_entry *entry; - char *trace_buf, *raw_data; + char *raw_data; int pc; BUILD_BUG_ON(PERF_MAX_TRACE_SIZE % sizeof(unsigned long)); @@ -139,13 +154,9 @@ __kprobes void *perf_trace_buf_prepare(int size, unsigned short type, *rctxp = perf_swevent_get_recursion_context(); if (*rctxp < 0) - goto err_recursion; - - trace_buf = rcu_dereference_sched(perf_trace_buf[*rctxp]); - if (!trace_buf) - goto err; + return NULL; - raw_data = per_cpu_ptr(trace_buf, smp_processor_id()); + raw_data = per_cpu_ptr(perf_trace_buf[*rctxp], smp_processor_id()); /* zero the dead bytes from align to not leak stack to user */ memset(&raw_data[size - sizeof(u64)], 0, sizeof(u64)); @@ -155,9 +166,5 @@ __kprobes void *perf_trace_buf_prepare(int size, unsigned short type, entry->type = type; return raw_data; -err: - perf_swevent_put_recursion_context(*rctxp); -err_recursion: - return NULL; } EXPORT_SYMBOL_GPL(perf_trace_buf_prepare); diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 20c96de0aea0..4681f60dac00 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -1341,6 +1341,7 @@ static __kprobes void kprobe_perf_func(struct kprobe *kp, struct trace_probe *tp = container_of(kp, struct trace_probe, rp.kp); struct ftrace_event_call *call = &tp->call; struct kprobe_trace_entry_head *entry; + struct hlist_head *head; u8 *data; int size, __size, i; int rctx; @@ -1361,7 +1362,8 @@ static __kprobes void kprobe_perf_func(struct kprobe *kp, for (i = 0; i < tp->nr_args; i++) call_fetch(&tp->args[i].fetch, regs, data + tp->args[i].offset); - perf_trace_buf_submit(entry, size, rctx, entry->ip, 1, regs, call->perf_data); + head = per_cpu_ptr(call->perf_events, smp_processor_id()); + perf_trace_buf_submit(entry, size, rctx, entry->ip, 1, regs, head); } /* Kretprobe profile handler */ @@ -1371,6 +1373,7 @@ static __kprobes void kretprobe_perf_func(struct kretprobe_instance *ri, struct trace_probe *tp = container_of(ri->rp, struct trace_probe, rp); struct ftrace_event_call *call = &tp->call; struct kretprobe_trace_entry_head *entry; + struct hlist_head *head; u8 *data; int size, __size, i; int rctx; @@ -1392,8 +1395,8 @@ static __kprobes void kretprobe_perf_func(struct kretprobe_instance *ri, for (i = 0; i < tp->nr_args; i++) call_fetch(&tp->args[i].fetch, regs, data + tp->args[i].offset); - perf_trace_buf_submit(entry, size, rctx, entry->ret_ip, 1, - regs, call->perf_data); + head = per_cpu_ptr(call->perf_events, smp_processor_id()); + perf_trace_buf_submit(entry, size, rctx, entry->ret_ip, 1, regs, head); } static int probe_perf_enable(struct ftrace_event_call *call) diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c index a657cefbb137..eb769f270291 100644 --- a/kernel/trace/trace_syscalls.c +++ b/kernel/trace/trace_syscalls.c @@ -438,6 +438,7 @@ static void perf_syscall_enter(struct pt_regs *regs, long id) { struct syscall_metadata *sys_data; struct syscall_trace_enter *rec; + struct hlist_head *head; int syscall_nr; int rctx; int size; @@ -467,8 +468,9 @@ static void perf_syscall_enter(struct pt_regs *regs, long id) rec->nr = syscall_nr; syscall_get_arguments(current, regs, 0, sys_data->nb_args, (unsigned long *)&rec->args); - perf_trace_buf_submit(rec, size, rctx, 0, 1, regs, - sys_data->enter_event->perf_data); + + head = per_cpu_ptr(sys_data->enter_event->perf_events, smp_processor_id()); + perf_trace_buf_submit(rec, size, rctx, 0, 1, regs, head); } int perf_sysenter_enable(struct ftrace_event_call *call) @@ -510,6 +512,7 @@ static void perf_syscall_exit(struct pt_regs *regs, long ret) { struct syscall_metadata *sys_data; struct syscall_trace_exit *rec; + struct hlist_head *head; int syscall_nr; int rctx; int size; @@ -542,8 +545,8 @@ static void perf_syscall_exit(struct pt_regs *regs, long ret) rec->nr = syscall_nr; rec->ret = syscall_get_return_value(current, regs); - perf_trace_buf_submit(rec, size, rctx, 0, 1, regs, - sys_data->exit_event->perf_data); + head = per_cpu_ptr(sys_data->exit_event->perf_events, smp_processor_id()); + perf_trace_buf_submit(rec, size, rctx, 0, 1, regs, head); } int perf_sysexit_enable(struct ftrace_event_call *call) -- cgit v1.2.1 From 0f139300c9057c16b5833a4636b715b104fe0baa Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 20 May 2010 14:35:15 +0200 Subject: perf: Ensure that IOC_OUTPUT isn't used to create multi-writer buffers Since we want to ensure buffers only have a single writer, we must avoid creating one with multiple. Signed-off-by: Peter Zijlstra Cc: Arnaldo Carvalho de Melo Cc: Frederic Weisbecker Cc: Paul Mackerras Cc: Mike Galbraith Cc: Steven Rostedt LKML-Reference: <20100521090710.528215873@chello.nl> Signed-off-by: Ingo Molnar --- kernel/perf_event.c | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'kernel') diff --git a/kernel/perf_event.c b/kernel/perf_event.c index 3f2cc313ee25..7a932526946f 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -4920,6 +4920,13 @@ static int perf_event_set_output(struct perf_event *event, int output_fd) int fput_needed = 0; int ret = -EINVAL; + /* + * Don't allow output of inherited per-task events. This would + * create performance issues due to cross cpu access. + */ + if (event->cpu == -1 && event->attr.inherit) + return -EINVAL; + if (!output_fd) goto set; @@ -4940,6 +4947,18 @@ static int perf_event_set_output(struct perf_event *event, int output_fd) if (event->data) goto out; + /* + * Don't allow cross-cpu buffers + */ + if (output_event->cpu != event->cpu) + goto out; + + /* + * If its not a per-cpu buffer, it must be the same task. + */ + if (output_event->cpu == -1 && output_event->ctx != event->ctx) + goto out; + atomic_long_inc(&output_file->f_count); set: -- cgit v1.2.1 From adb8e118f288dc4c569ac9a89010b81a4745fbf0 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 20 May 2010 16:21:55 +0200 Subject: perf: Fix wakeup storm for RO mmap()s RO mmap()s don't update the tail pointer, so comparing against it for determining the written data size doesn't really do any good. Keep track of when we last did a wakeup, and compare against that. Signed-off-by: Peter Zijlstra Cc: Arnaldo Carvalho de Melo Cc: Frederic Weisbecker Cc: Paul Mackerras Cc: Mike Galbraith Cc: Steven Rostedt LKML-Reference: <20100521090710.684479310@chello.nl> Signed-off-by: Ingo Molnar --- kernel/perf_event.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/perf_event.c b/kernel/perf_event.c index 7a932526946f..1531e0b409a5 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -3056,8 +3056,8 @@ int perf_output_begin(struct perf_output_handle *handle, handle->offset = offset; handle->head = head; - if (head - tail > data->watermark) - local_inc(&data->wakeup); + if (head - local_read(&data->wakeup) > data->watermark) + local_add(data->watermark, &data->wakeup); if (have_lost) { lost_event.header.type = PERF_RECORD_LOST; -- cgit v1.2.1 From 5d967a8be636a4f301a8daad642bd1007299d9ec Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 20 May 2010 16:46:39 +0200 Subject: perf: Optimize perf_output_copy() Reduce the clutter in perf_output_copy() by keeping an interator in perf_output_handle. Signed-off-by: Peter Zijlstra Cc: Arnaldo Carvalho de Melo Cc: Frederic Weisbecker Cc: Paul Mackerras Cc: Mike Galbraith Cc: Steven Rostedt LKML-Reference: <20100521090710.742809176@chello.nl> Signed-off-by: Ingo Molnar --- kernel/perf_event.c | 54 ++++++++++++++++++++++++++--------------------------- 1 file changed, 26 insertions(+), 28 deletions(-) (limited to 'kernel') diff --git a/kernel/perf_event.c b/kernel/perf_event.c index 1531e0b409a5..b67549a08626 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -2961,39 +2961,30 @@ again: void perf_output_copy(struct perf_output_handle *handle, const void *buf, unsigned int len) { - unsigned int pages_mask; - unsigned long offset; - unsigned int size; - void **pages; - - offset = handle->offset; - pages_mask = handle->data->nr_pages - 1; - pages = handle->data->data_pages; - - do { - unsigned long page_offset; - unsigned long page_size; - int nr; - - nr = (offset >> PAGE_SHIFT) & pages_mask; - page_size = 1UL << (handle->data->data_order + PAGE_SHIFT); - page_offset = offset & (page_size - 1); - size = min_t(unsigned int, page_size - page_offset, len); - - memcpy(pages[nr] + page_offset, buf, size); - - len -= size; - buf += size; - offset += size; - } while (len); - - handle->offset = offset; + handle->offset += len; /* * Check we didn't copy past our reservation window, taking the * possible unsigned int wrap into account. */ - WARN_ON_ONCE(((long)(handle->head - handle->offset)) < 0); + if (WARN_ON_ONCE(((long)(handle->head - handle->offset)) < 0)) + return; + + do { + unsigned long size = min(handle->size, len); + + memcpy(handle->addr, buf, size); + + len -= size; + handle->addr += size; + handle->size -= size; + if (!handle->size) { + handle->page++; + handle->page &= handle->data->nr_pages - 1; + handle->addr = handle->data->data_pages[handle->page]; + handle->size = PAGE_SIZE << handle->data->data_order; + } + } while (len); } int perf_output_begin(struct perf_output_handle *handle, @@ -3059,6 +3050,13 @@ int perf_output_begin(struct perf_output_handle *handle, if (head - local_read(&data->wakeup) > data->watermark) local_add(data->watermark, &data->wakeup); + handle->page = handle->offset >> (PAGE_SHIFT + data->data_order); + handle->page &= data->nr_pages - 1; + handle->size = handle->offset & ((PAGE_SIZE << data->data_order) - 1); + handle->addr = data->data_pages[handle->page]; + handle->addr += handle->size; + handle->size = (PAGE_SIZE << data->data_order) - handle->size; + if (have_lost) { lost_event.header.type = PERF_RECORD_LOST; lost_event.header.misc = 0; -- cgit v1.2.1 From 3cafa9fbb5c1d564b7b8e7224f493effbf04ffee Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 20 May 2010 19:07:56 +0200 Subject: perf: Optimize the !vmalloc backed buffer Reduce code and data by using the knowledge that for !PERF_USE_VMALLOC data_order is always 0. Signed-off-by: Peter Zijlstra Cc: Arnaldo Carvalho de Melo Cc: Frederic Weisbecker Cc: Paul Mackerras Cc: Mike Galbraith Cc: Steven Rostedt LKML-Reference: <20100521090710.795019386@chello.nl> Signed-off-by: Ingo Molnar --- kernel/perf_event.c | 41 ++++++++++++++++++++++++++--------------- 1 file changed, 26 insertions(+), 15 deletions(-) (limited to 'kernel') diff --git a/kernel/perf_event.c b/kernel/perf_event.c index b67549a08626..953ce46d7b2f 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -2297,11 +2297,6 @@ unlock: rcu_read_unlock(); } -static unsigned long perf_data_size(struct perf_mmap_data *data) -{ - return data->nr_pages << (PAGE_SHIFT + data->data_order); -} - #ifndef CONFIG_PERF_USE_VMALLOC /* @@ -2359,7 +2354,6 @@ perf_mmap_data_alloc(struct perf_event *event, int nr_pages) goto fail_data_pages; } - data->data_order = 0; data->nr_pages = nr_pages; return data; @@ -2395,6 +2389,11 @@ static void perf_mmap_data_free(struct perf_mmap_data *data) kfree(data); } +static inline int page_order(struct perf_mmap_data *data) +{ + return 0; +} + #else /* @@ -2403,10 +2402,15 @@ static void perf_mmap_data_free(struct perf_mmap_data *data) * Required for architectures that have d-cache aliasing issues. */ +static inline int page_order(struct perf_mmap_data *data) +{ + return data->page_order; +} + static struct page * perf_mmap_to_page(struct perf_mmap_data *data, unsigned long pgoff) { - if (pgoff > (1UL << data->data_order)) + if (pgoff > (1UL << page_order(data))) return NULL; return vmalloc_to_page((void *)data->user_page + pgoff * PAGE_SIZE); @@ -2426,7 +2430,7 @@ static void perf_mmap_data_free_work(struct work_struct *work) int i, nr; data = container_of(work, struct perf_mmap_data, work); - nr = 1 << data->data_order; + nr = 1 << page_order(data); base = data->user_page; for (i = 0; i < nr + 1; i++) @@ -2465,7 +2469,7 @@ perf_mmap_data_alloc(struct perf_event *event, int nr_pages) data->user_page = all_buf; data->data_pages[0] = all_buf + PAGE_SIZE; - data->data_order = ilog2(nr_pages); + data->page_order = ilog2(nr_pages); data->nr_pages = 1; return data; @@ -2479,6 +2483,11 @@ fail: #endif +static unsigned long perf_data_size(struct perf_mmap_data *data) +{ + return data->nr_pages << (PAGE_SHIFT + page_order(data)); +} + static int perf_mmap_fault(struct vm_area_struct *vma, struct vm_fault *vmf) { struct perf_event *event = vma->vm_file->private_data; @@ -2979,10 +2988,12 @@ void perf_output_copy(struct perf_output_handle *handle, handle->addr += size; handle->size -= size; if (!handle->size) { + struct perf_mmap_data *data = handle->data; + handle->page++; - handle->page &= handle->data->nr_pages - 1; - handle->addr = handle->data->data_pages[handle->page]; - handle->size = PAGE_SIZE << handle->data->data_order; + handle->page &= data->nr_pages - 1; + handle->addr = data->data_pages[handle->page]; + handle->size = PAGE_SIZE << page_order(data); } } while (len); } @@ -3050,12 +3061,12 @@ int perf_output_begin(struct perf_output_handle *handle, if (head - local_read(&data->wakeup) > data->watermark) local_add(data->watermark, &data->wakeup); - handle->page = handle->offset >> (PAGE_SHIFT + data->data_order); + handle->page = handle->offset >> (PAGE_SHIFT + page_order(data)); handle->page &= data->nr_pages - 1; - handle->size = handle->offset & ((PAGE_SIZE << data->data_order) - 1); + handle->size = handle->offset & ((PAGE_SIZE << page_order(data)) - 1); handle->addr = data->data_pages[handle->page]; handle->addr += handle->size; - handle->size = (PAGE_SIZE << data->data_order) - handle->size; + handle->size = (PAGE_SIZE << page_order(data)) - handle->size; if (have_lost) { lost_event.header.type = PERF_RECORD_LOST; -- cgit v1.2.1 From a94ffaaf55552769af328eaca9260fe6291c66c7 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 20 May 2010 19:50:07 +0200 Subject: perf: Remove more code from the fastpath Sanity checks cost instructions. Signed-off-by: Peter Zijlstra Cc: Arnaldo Carvalho de Melo Cc: Frederic Weisbecker Cc: Paul Mackerras Cc: Mike Galbraith Cc: Steven Rostedt LKML-Reference: <20100521090710.852926930@chello.nl> Signed-off-by: Ingo Molnar --- kernel/perf_event.c | 20 ++++---------------- 1 file changed, 4 insertions(+), 16 deletions(-) (limited to 'kernel') diff --git a/kernel/perf_event.c b/kernel/perf_event.c index 953ce46d7b2f..d25c864cadbf 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -2967,20 +2967,11 @@ again: preempt_enable(); } -void perf_output_copy(struct perf_output_handle *handle, +__always_inline void perf_output_copy(struct perf_output_handle *handle, const void *buf, unsigned int len) { - handle->offset += len; - - /* - * Check we didn't copy past our reservation window, taking the - * possible unsigned int wrap into account. - */ - if (WARN_ON_ONCE(((long)(handle->head - handle->offset)) < 0)) - return; - do { - unsigned long size = min(handle->size, len); + unsigned long size = min_t(unsigned long, handle->size, len); memcpy(handle->addr, buf, size); @@ -3055,15 +3046,12 @@ int perf_output_begin(struct perf_output_handle *handle, goto fail; } while (local_cmpxchg(&data->head, offset, head) != offset); - handle->offset = offset; - handle->head = head; - if (head - local_read(&data->wakeup) > data->watermark) local_add(data->watermark, &data->wakeup); - handle->page = handle->offset >> (PAGE_SHIFT + page_order(data)); + handle->page = offset >> (PAGE_SHIFT + page_order(data)); handle->page &= data->nr_pages - 1; - handle->size = handle->offset & ((PAGE_SIZE << page_order(data)) - 1); + handle->size = offset & ((PAGE_SIZE << page_order(data)) - 1); handle->addr = data->data_pages[handle->page]; handle->addr += handle->size; handle->size = (PAGE_SIZE << page_order(data)) - handle->size; -- cgit v1.2.1 From 580d607cd666dfabfc1c7b0fb08c8ac690c7c87f Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 20 May 2010 20:54:31 +0200 Subject: perf: Optimize perf_tp_event_match() Since we know tracepoints come from kernel context, avoid conditionals that try and establish that very fact. Signed-off-by: Peter Zijlstra Cc: Arnaldo Carvalho de Melo Cc: Frederic Weisbecker Cc: Paul Mackerras Cc: Mike Galbraith Cc: Steven Rostedt LKML-Reference: <20100521090710.904944001@chello.nl> Signed-off-by: Ingo Molnar --- kernel/perf_event.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/perf_event.c b/kernel/perf_event.c index d25c864cadbf..e099650cd249 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -4496,7 +4496,10 @@ static int perf_tp_event_match(struct perf_event *event, struct perf_sample_data *data, struct pt_regs *regs) { - if (perf_exclude_event(event, regs)) + /* + * All tracepoints are from kernel-space. + */ + if (event->attr.exclude_kernel) return 0; if (!perf_tp_filter_match(event, data)) -- cgit v1.2.1 From 87f44bbc246c5244c76a701f8eefba7788bce64a Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 25 May 2010 11:02:55 +0200 Subject: perf, trace: Fix !x86 build bug Patch b7e2ecef92 (perf, trace: Optimize tracepoints by removing IRQ-disable from perf/tracepoint interaction) made the unfortunate mistake of assuming the world is x86 only, correct this. The problem was that perf_fetch_caller_regs() did local_save_flags() into regs->flags, and I re-used that to remove another local_save_flags(), forgetting !x86 doesn't have regs->flags. Do the reverse, remove the local_save_flags() from perf_fetch_caller_regs() and let the ftrace site do the local_save_flags() instead. Signed-off-by: Peter Zijlstra Acked-by: Paul Mackerras Cc: acme@redhat.com Cc: efault@gmx.de Cc: fweisbec@gmail.com Cc: rostedt@goodmis.org LKML-Reference: <1274778175.5882.623.camel@twins> Signed-off-by: Ingo Molnar --- kernel/trace/trace_event_perf.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c index 26b8607a0abc..cb6f365016e4 100644 --- a/kernel/trace/trace_event_perf.c +++ b/kernel/trace/trace_event_perf.c @@ -157,6 +157,7 @@ __kprobes void *perf_trace_buf_prepare(int size, unsigned short type, struct pt_regs *regs, int *rctxp) { struct trace_entry *entry; + unsigned long flags; char *raw_data; int pc; @@ -174,7 +175,8 @@ __kprobes void *perf_trace_buf_prepare(int size, unsigned short type, memset(&raw_data[size - sizeof(u64)], 0, sizeof(u64)); entry = (struct trace_entry *)raw_data; - tracing_generic_entry_update(entry, regs->flags, pc); + local_save_flags(flags); + tracing_generic_entry_update(entry, flags, pc); entry->type = type; return raw_data; -- cgit v1.2.1