From ceec0b6fc7cd43b38a40c2d40223f9cd0616f0cd Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 15 Feb 2012 15:51:49 +0100 Subject: ftrace, perf: Add open/close tracepoint perf registration actions Adding TRACE_REG_PERF_OPEN and TRACE_REG_PERF_CLOSE to differentiate register/unregister from open/close actions. The register/unregister actions are invoked for the first/last tracepoint user when opening/closing the event. The open/close actions are invoked for each tracepoint user when opening/closing the event. Link: http://lkml.kernel.org/r/1329317514-8131-3-git-send-email-jolsa@redhat.com Acked-by: Frederic Weisbecker Signed-off-by: Jiri Olsa Signed-off-by: Steven Rostedt --- kernel/trace/trace_event_perf.c | 116 ++++++++++++++++++++++++++-------------- 1 file changed, 75 insertions(+), 41 deletions(-) (limited to 'kernel/trace/trace_event_perf.c') diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c index 19a359d5e6d5..0cfcc37f63de 100644 --- a/kernel/trace/trace_event_perf.c +++ b/kernel/trace/trace_event_perf.c @@ -44,23 +44,17 @@ static int perf_trace_event_perm(struct ftrace_event_call *tp_event, return 0; } -static int perf_trace_event_init(struct ftrace_event_call *tp_event, - struct perf_event *p_event) +static int perf_trace_event_reg(struct ftrace_event_call *tp_event, + struct perf_event *p_event) { struct hlist_head __percpu *list; - int ret; + int ret = -ENOMEM; int cpu; - ret = perf_trace_event_perm(tp_event, p_event); - if (ret) - return ret; - p_event->tp_event = tp_event; if (tp_event->perf_refcount++ > 0) return 0; - ret = -ENOMEM; - list = alloc_percpu(struct hlist_head); if (!list) goto fail; @@ -83,7 +77,7 @@ static int perf_trace_event_init(struct ftrace_event_call *tp_event, } } - ret = tp_event->class->reg(tp_event, TRACE_REG_PERF_REGISTER); + ret = tp_event->class->reg(tp_event, TRACE_REG_PERF_REGISTER, NULL); if (ret) goto fail; @@ -108,6 +102,69 @@ fail: return ret; } +static void perf_trace_event_unreg(struct perf_event *p_event) +{ + struct ftrace_event_call *tp_event = p_event->tp_event; + int i; + + if (--tp_event->perf_refcount > 0) + goto out; + + tp_event->class->reg(tp_event, TRACE_REG_PERF_UNREGISTER, NULL); + + /* + * Ensure our callback won't be called anymore. The buffers + * will be freed after that. + */ + tracepoint_synchronize_unregister(); + + free_percpu(tp_event->perf_events); + tp_event->perf_events = NULL; + + if (!--total_ref_count) { + for (i = 0; i < PERF_NR_CONTEXTS; i++) { + free_percpu(perf_trace_buf[i]); + perf_trace_buf[i] = NULL; + } + } +out: + module_put(tp_event->mod); +} + +static int perf_trace_event_open(struct perf_event *p_event) +{ + struct ftrace_event_call *tp_event = p_event->tp_event; + return tp_event->class->reg(tp_event, TRACE_REG_PERF_OPEN, p_event); +} + +static void perf_trace_event_close(struct perf_event *p_event) +{ + struct ftrace_event_call *tp_event = p_event->tp_event; + tp_event->class->reg(tp_event, TRACE_REG_PERF_CLOSE, p_event); +} + +static int perf_trace_event_init(struct ftrace_event_call *tp_event, + struct perf_event *p_event) +{ + int ret; + + ret = perf_trace_event_perm(tp_event, p_event); + if (ret) + return ret; + + ret = perf_trace_event_reg(tp_event, p_event); + if (ret) + return ret; + + ret = perf_trace_event_open(p_event); + if (ret) { + perf_trace_event_unreg(p_event); + return ret; + } + + return 0; +} + int perf_trace_init(struct perf_event *p_event) { struct ftrace_event_call *tp_event; @@ -130,6 +187,14 @@ int perf_trace_init(struct perf_event *p_event) return ret; } +void perf_trace_destroy(struct perf_event *p_event) +{ + mutex_lock(&event_mutex); + perf_trace_event_close(p_event); + perf_trace_event_unreg(p_event); + mutex_unlock(&event_mutex); +} + int perf_trace_add(struct perf_event *p_event, int flags) { struct ftrace_event_call *tp_event = p_event->tp_event; @@ -154,37 +219,6 @@ void perf_trace_del(struct perf_event *p_event, int flags) hlist_del_rcu(&p_event->hlist_entry); } -void perf_trace_destroy(struct perf_event *p_event) -{ - struct ftrace_event_call *tp_event = p_event->tp_event; - int i; - - mutex_lock(&event_mutex); - if (--tp_event->perf_refcount > 0) - goto out; - - tp_event->class->reg(tp_event, TRACE_REG_PERF_UNREGISTER); - - /* - * Ensure our callback won't be called anymore. The buffers - * will be freed after that. - */ - tracepoint_synchronize_unregister(); - - free_percpu(tp_event->perf_events); - tp_event->perf_events = NULL; - - if (!--total_ref_count) { - for (i = 0; i < PERF_NR_CONTEXTS; i++) { - free_percpu(perf_trace_buf[i]); - perf_trace_buf[i] = NULL; - } - } -out: - module_put(tp_event->mod); - mutex_unlock(&event_mutex); -} - __kprobes void *perf_trace_buf_prepare(int size, unsigned short type, struct pt_regs *regs, int *rctxp) { -- cgit v1.2.3 From 489c75c3b333dfda4c8d2b7ad1b00e5da024bfa7 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 15 Feb 2012 15:51:50 +0100 Subject: ftrace, perf: Add add/del tracepoint perf registration actions Adding TRACE_REG_PERF_ADD and TRACE_REG_PERF_DEL to handle perf event schedule in/out actions. The add action is invoked for when the perf event is scheduled in, while the del action is invoked when the event is scheduled out. Link: http://lkml.kernel.org/r/1329317514-8131-4-git-send-email-jolsa@redhat.com Acked-by: Frederic Weisbecker Signed-off-by: Jiri Olsa Signed-off-by: Steven Rostedt --- kernel/trace/trace_event_perf.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'kernel/trace/trace_event_perf.c') diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c index 0cfcc37f63de..d72af0b03822 100644 --- a/kernel/trace/trace_event_perf.c +++ b/kernel/trace/trace_event_perf.c @@ -211,12 +211,14 @@ int perf_trace_add(struct perf_event *p_event, int flags) list = this_cpu_ptr(pcpu_list); hlist_add_head_rcu(&p_event->hlist_entry, list); - return 0; + return tp_event->class->reg(tp_event, TRACE_REG_PERF_ADD, p_event); } void perf_trace_del(struct perf_event *p_event, int flags) { + struct ftrace_event_call *tp_event = p_event->tp_event; hlist_del_rcu(&p_event->hlist_entry); + tp_event->class->reg(tp_event, TRACE_REG_PERF_DEL, p_event); } __kprobes void *perf_trace_buf_prepare(int size, unsigned short type, -- cgit v1.2.3 From ced39002f5ea736b716ae233fb68b26d59783912 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 15 Feb 2012 15:51:52 +0100 Subject: ftrace, perf: Add support to use function tracepoint in perf Adding perf registration support for the ftrace function event, so it is now possible to register it via perf interface. The perf_event struct statically contains ftrace_ops as a handle for function tracer. The function tracer is registered/unregistered in open/close actions. To be efficient, we enable/disable ftrace_ops each time the traced process is scheduled in/out (via TRACE_REG_PERF_(ADD|DELL) handlers). This way tracing is enabled only when the process is running. Intentionally using this way instead of the event's hw state PERF_HES_STOPPED, which would not disable the ftrace_ops. It is now possible to use function trace within perf commands like: perf record -e ftrace:function ls perf stat -e ftrace:function ls Allowed only for root. Link: http://lkml.kernel.org/r/1329317514-8131-6-git-send-email-jolsa@redhat.com Acked-by: Frederic Weisbecker Signed-off-by: Jiri Olsa Signed-off-by: Steven Rostedt --- kernel/trace/trace_event_perf.c | 86 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 86 insertions(+) (limited to 'kernel/trace/trace_event_perf.c') diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c index d72af0b03822..fdeeb5c49627 100644 --- a/kernel/trace/trace_event_perf.c +++ b/kernel/trace/trace_event_perf.c @@ -24,6 +24,11 @@ static int total_ref_count; static int perf_trace_event_perm(struct ftrace_event_call *tp_event, struct perf_event *p_event) { + /* The ftrace function trace is allowed only for root. */ + if (ftrace_event_is_function(tp_event) && + perf_paranoid_kernel() && !capable(CAP_SYS_ADMIN)) + return -EPERM; + /* No tracing, just counting, so no obvious leak */ if (!(p_event->attr.sample_type & PERF_SAMPLE_RAW)) return 0; @@ -250,3 +255,84 @@ __kprobes void *perf_trace_buf_prepare(int size, unsigned short type, return raw_data; } EXPORT_SYMBOL_GPL(perf_trace_buf_prepare); + +#ifdef CONFIG_FUNCTION_TRACER +static void +perf_ftrace_function_call(unsigned long ip, unsigned long parent_ip) +{ + struct ftrace_entry *entry; + struct hlist_head *head; + struct pt_regs regs; + int rctx; + +#define ENTRY_SIZE (ALIGN(sizeof(struct ftrace_entry) + sizeof(u32), \ + sizeof(u64)) - sizeof(u32)) + + BUILD_BUG_ON(ENTRY_SIZE > PERF_MAX_TRACE_SIZE); + + perf_fetch_caller_regs(®s); + + entry = perf_trace_buf_prepare(ENTRY_SIZE, TRACE_FN, NULL, &rctx); + if (!entry) + return; + + entry->ip = ip; + entry->parent_ip = parent_ip; + + head = this_cpu_ptr(event_function.perf_events); + perf_trace_buf_submit(entry, ENTRY_SIZE, rctx, 0, + 1, ®s, head); + +#undef ENTRY_SIZE +} + +static int perf_ftrace_function_register(struct perf_event *event) +{ + struct ftrace_ops *ops = &event->ftrace_ops; + + ops->flags |= FTRACE_OPS_FL_CONTROL; + ops->func = perf_ftrace_function_call; + return register_ftrace_function(ops); +} + +static int perf_ftrace_function_unregister(struct perf_event *event) +{ + struct ftrace_ops *ops = &event->ftrace_ops; + return unregister_ftrace_function(ops); +} + +static void perf_ftrace_function_enable(struct perf_event *event) +{ + ftrace_function_local_enable(&event->ftrace_ops); +} + +static void perf_ftrace_function_disable(struct perf_event *event) +{ + ftrace_function_local_disable(&event->ftrace_ops); +} + +int perf_ftrace_event_register(struct ftrace_event_call *call, + enum trace_reg type, void *data) +{ + switch (type) { + case TRACE_REG_REGISTER: + case TRACE_REG_UNREGISTER: + break; + case TRACE_REG_PERF_REGISTER: + case TRACE_REG_PERF_UNREGISTER: + return 0; + case TRACE_REG_PERF_OPEN: + return perf_ftrace_function_register(data); + case TRACE_REG_PERF_CLOSE: + return perf_ftrace_function_unregister(data); + case TRACE_REG_PERF_ADD: + perf_ftrace_function_enable(data); + return 0; + case TRACE_REG_PERF_DEL: + perf_ftrace_function_disable(data); + return 0; + } + + return -EINVAL; +} +#endif /* CONFIG_FUNCTION_TRACER */ -- cgit v1.2.3 From 5500fa51199aee770ce53718853732600543619e Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 15 Feb 2012 15:51:54 +0100 Subject: ftrace, perf: Add filter support for function trace event Adding support to filter function trace event via perf interface. It is now possible to use filter interface in the perf tool like: perf record -e ftrace:function --filter="(ip == mm_*)" ls The filter syntax is restricted to the the 'ip' field only, and following operators are accepted '==' '!=' '||', ending up with the filter strings like: ip == f1[, ]f2 ... || ip != f3[, ]f4 ... with comma ',' or space ' ' as a function separator. If the space ' ' is used as a separator, the right side of the assignment needs to be enclosed in double quotes '"', e.g.: perf record -e ftrace:function --filter '(ip == do_execve,sys_*,ext*)' ls perf record -e ftrace:function --filter '(ip == "do_execve,sys_*,ext*")' ls perf record -e ftrace:function --filter '(ip == "do_execve sys_* ext*")' ls The '==' operator adds trace filter with same effect as would be added via set_ftrace_filter file. The '!=' operator adds trace filter with same effect as would be added via set_ftrace_notrace file. The right side of the '!=', '==' operators is list of functions or regexp. to be added to filter separated by space. The '||' operator is used for connecting multiple filter definitions together. It is possible to have more than one '==' and '!=' operators within one filter string. Link: http://lkml.kernel.org/r/1329317514-8131-8-git-send-email-jolsa@redhat.com Signed-off-by: Jiri Olsa Signed-off-by: Steven Rostedt --- kernel/trace/trace_event_perf.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'kernel/trace/trace_event_perf.c') diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c index fdeeb5c49627..fee3752ae8f6 100644 --- a/kernel/trace/trace_event_perf.c +++ b/kernel/trace/trace_event_perf.c @@ -298,7 +298,9 @@ static int perf_ftrace_function_register(struct perf_event *event) static int perf_ftrace_function_unregister(struct perf_event *event) { struct ftrace_ops *ops = &event->ftrace_ops; - return unregister_ftrace_function(ops); + int ret = unregister_ftrace_function(ops); + ftrace_free_filter(ops); + return ret; } static void perf_ftrace_function_enable(struct perf_event *event) -- cgit v1.2.3