From bac52139f0b7ab31330e98fd87fc5a2664951050 Mon Sep 17 00:00:00 2001 From: Anshuman Khandual Date: Thu, 22 May 2014 12:50:07 +0530 Subject: perf: Add new conditional branch filter 'PERF_SAMPLE_BRANCH_COND' This patch introduces new branch filter PERF_SAMPLE_BRANCH_COND which will extend the existing perf ABI. This will filter branches which are conditional. Various architectures can provide this functionality either with HW filtering support (if present) or with SW filtering of captured branch instructions. Signed-off-by: Anshuman Khandual Reviewed-by: Stephane Eranian Reviewed-by: Andi Kleen Signed-off-by: Peter Zijlstra Cc: mpe@ellerman.id.au Cc: benh@kernel.crashing.org Cc: Arnaldo Carvalho de Melo Cc: Linus Torvalds Link: http://lkml.kernel.org/r/1400743210-32289-1-git-send-email-khandual@linux.vnet.ibm.com Signed-off-by: Ingo Molnar --- include/uapi/linux/perf_event.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index e3fc8f09d110..d9cd853818ad 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -163,8 +163,9 @@ enum perf_branch_sample_type { PERF_SAMPLE_BRANCH_ABORT_TX = 1U << 7, /* transaction aborts */ PERF_SAMPLE_BRANCH_IN_TX = 1U << 8, /* in transaction */ PERF_SAMPLE_BRANCH_NO_TX = 1U << 9, /* not in transaction */ + PERF_SAMPLE_BRANCH_COND = 1U << 10, /* conditional branches */ - PERF_SAMPLE_BRANCH_MAX = 1U << 10, /* non-ABI */ + PERF_SAMPLE_BRANCH_MAX = 1U << 11, /* non-ABI */ }; #define PERF_SAMPLE_BRANCH_PLM_ALL \ -- cgit v1.2.3 From 82b897782d10fcc4930c9d4a15b175348fdd2871 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Wed, 28 May 2014 11:45:04 +0300 Subject: perf: Differentiate exec() and non-exec() comm events perf tools like 'perf report' can aggregate samples by comm strings, which generally works. However, there are other potential use-cases. For example, to pair up 'calls' with 'returns' accurately (from branch events like Intel BTS) it is necessary to identify whether the process has exec'd. Although a comm event is generated when an 'exec' happens it is also generated whenever the comm string is changed on a whim (e.g. by prctl PR_SET_NAME). This patch adds a flag to the comm event to differentiate one case from the other. In order to determine whether the kernel supports the new flag, a selection bit named 'exec' is added to struct perf_event_attr. The bit does nothing but will cause perf_event_open() to fail if the bit is set on kernels that do not have it defined. Signed-off-by: Adrian Hunter Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/537D9EBE.7030806@intel.com Cc: Paul Mackerras Cc: Dave Jones Cc: Arnaldo Carvalho de Melo Cc: David Ahern Cc: Jiri Olsa Cc: Alexander Viro Cc: Linus Torvalds Cc: linux-fsdevel@vger.kernel.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- fs/exec.c | 6 +++--- include/linux/perf_event.h | 4 ++-- include/linux/sched.h | 6 +++++- include/uapi/linux/perf_event.h | 9 +++++++-- kernel/events/core.c | 4 ++-- 5 files changed, 19 insertions(+), 10 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/exec.c b/fs/exec.c index a038a41a3677..a3d33fe592d6 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1046,13 +1046,13 @@ EXPORT_SYMBOL_GPL(get_task_comm); * so that a new one can be started */ -void set_task_comm(struct task_struct *tsk, const char *buf) +void __set_task_comm(struct task_struct *tsk, const char *buf, bool exec) { task_lock(tsk); trace_task_rename(tsk, buf); strlcpy(tsk->comm, buf, sizeof(tsk->comm)); task_unlock(tsk); - perf_event_comm(tsk); + perf_event_comm(tsk, exec); } int flush_old_exec(struct linux_binprm * bprm) @@ -1111,7 +1111,7 @@ void setup_new_exec(struct linux_binprm * bprm) set_dumpable(current->mm, suid_dumpable); perf_event_exec(); - set_task_comm(current, kbasename(bprm->filename)); + __set_task_comm(current, kbasename(bprm->filename), true); /* Set the new mm task size. We have to do that late because it may * depend on TIF_32BIT which is only updated in flush_thread() on diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index b4c1d4685bf0..707617a8c0f6 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -707,7 +707,7 @@ extern int perf_register_guest_info_callbacks(struct perf_guest_info_callbacks * extern int perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks *callbacks); extern void perf_event_exec(void); -extern void perf_event_comm(struct task_struct *tsk); +extern void perf_event_comm(struct task_struct *tsk, bool exec); extern void perf_event_fork(struct task_struct *tsk); /* Callchains */ @@ -815,7 +815,7 @@ static inline int perf_unregister_guest_info_callbacks static inline void perf_event_mmap(struct vm_area_struct *vma) { } static inline void perf_event_exec(void) { } -static inline void perf_event_comm(struct task_struct *tsk) { } +static inline void perf_event_comm(struct task_struct *tsk, bool exec) { } static inline void perf_event_fork(struct task_struct *tsk) { } static inline void perf_event_init(void) { } static inline int perf_swevent_get_recursion_context(void) { return -1; } diff --git a/include/linux/sched.h b/include/linux/sched.h index 221b2bde3723..ad86e1d7dbc2 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2379,7 +2379,11 @@ extern long do_fork(unsigned long, unsigned long, unsigned long, int __user *, i struct task_struct *fork_idle(int); extern pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags); -extern void set_task_comm(struct task_struct *tsk, const char *from); +extern void __set_task_comm(struct task_struct *tsk, const char *from, bool exec); +static inline void set_task_comm(struct task_struct *tsk, const char *from) +{ + __set_task_comm(tsk, from, false); +} extern char *get_task_comm(char *to, struct task_struct *tsk); #ifdef CONFIG_SMP diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index d9cd853818ad..5312fae47218 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -302,8 +302,8 @@ struct perf_event_attr { exclude_callchain_kernel : 1, /* exclude kernel callchains */ exclude_callchain_user : 1, /* exclude user callchains */ mmap2 : 1, /* include mmap with inode data */ - - __reserved_1 : 40; + comm_exec : 1, /* flag comm events that are due to an exec */ + __reserved_1 : 39; union { __u32 wakeup_events; /* wakeup every n events */ @@ -502,7 +502,12 @@ struct perf_event_mmap_page { #define PERF_RECORD_MISC_GUEST_KERNEL (4 << 0) #define PERF_RECORD_MISC_GUEST_USER (5 << 0) +/* + * PERF_RECORD_MISC_MMAP_DATA and PERF_RECORD_MISC_COMM_EXEC are used on + * different events so can reuse the same bit position. + */ #define PERF_RECORD_MISC_MMAP_DATA (1 << 13) +#define PERF_RECORD_MISC_COMM_EXEC (1 << 13) /* * Indicates that the content of PERF_SAMPLE_IP points to * the actual instruction that triggered the event. See also diff --git a/kernel/events/core.c b/kernel/events/core.c index 8fac2056d51e..7da5e561e89a 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -5090,7 +5090,7 @@ static void perf_event_comm_event(struct perf_comm_event *comm_event) NULL); } -void perf_event_comm(struct task_struct *task) +void perf_event_comm(struct task_struct *task, bool exec) { struct perf_comm_event comm_event; @@ -5104,7 +5104,7 @@ void perf_event_comm(struct task_struct *task) .event_id = { .header = { .type = PERF_RECORD_COMM, - .misc = 0, + .misc = exec ? PERF_RECORD_MISC_COMM_EXEC : 0, /* .size */ }, /* .pid */ -- cgit v1.2.3