summaryrefslogtreecommitdiffstats
path: root/include
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2016-05-16 14:08:43 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2016-05-16 14:08:43 -0700
commit36db171cc733bc7b8c628ef21831467d1919decd (patch)
tree96c6bda274155d7f4e41b2168edc291216f477ba /include
parent3469d261eac65912927dca13ee8f77c744ad7aa2 (diff)
parent3f56e687a138481894a1088d5aa7d41951bdb020 (diff)
downloadlinux-36db171cc733bc7b8c628ef21831467d1919decd.tar.bz2
Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull perf updates from Ingo Molnar: "Bigger kernel side changes: - Add backwards writing capability to the perf ring-buffer code, which is preparation for future advanced features like robust 'overwrite support' and snapshot mode. (Wang Nan) - Add pause and resume ioctls for the perf ringbuffer (Wang Nan) - x86 Intel cstate code cleanups and reorgnization (Thomas Gleixner) - x86 Intel uncore and CPU PMU driver updates (Kan Liang, Peter Zijlstra) - x86 AUX (Intel PT) related enhancements and updates (Alexander Shishkin) - x86 MSR PMU driver enhancements and updates (Huang Rui) - ... and lots of other changes spread out over 40+ commits. Biggest tooling side changes: - 'perf trace' features and enhancements. (Arnaldo Carvalho de Melo) - BPF tooling updates (Wang Nan) - 'perf sched' updates (Jiri Olsa) - 'perf probe' updates (Masami Hiramatsu) - ... plus 200+ other enhancements, fixes and cleanups to tools/ The merge commits, the shortlog and the changelogs contain a lot more details" * 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (249 commits) perf/core: Disable the event on a truncated AUX record perf/x86/intel/pt: Generate PMI in the STOP region as well perf buildid-cache: Use lsdir() for looking up buildid caches perf symbols: Use lsdir() for the search in kcore cache directory perf tools: Use SBUILD_ID_SIZE where applicable perf tools: Fix lsdir to set errno correctly perf trace: Move seccomp args beautifiers to tools/perf/trace/beauty/ perf trace: Move flock op beautifier to tools/perf/trace/beauty/ perf build: Add build-test for debug-frame on arm/arm64 perf build: Add build-test for libunwind cross-platforms support perf script: Fix export of callchains with recursion in db-export perf script: Fix callchain addresses in db-export perf script: Fix symbol insertion behavior in db-export perf symbols: Add dso__insert_symbol function perf scripting python: Use Py_FatalError instead of die() perf tools: Remove xrealloc and ALLOC_GROW perf help: Do not use ALLOC_GROW in add_cmd_list perf pmu: Make pmu_formats_string to check return value of strbuf perf header: Make topology checkers to check return value of strbuf perf tools: Make alias handler to check return value of strbuf ...
Diffstat (limited to 'include')
-rw-r--r--include/linux/perf_event.h139
-rw-r--r--include/uapi/linux/perf_event.h4
2 files changed, 138 insertions, 5 deletions
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index f291275ffd71..9e1c3ada91c4 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -58,7 +58,7 @@ struct perf_guest_info_callbacks {
struct perf_callchain_entry {
__u64 nr;
- __u64 ip[PERF_MAX_STACK_DEPTH];
+ __u64 ip[0]; /* /proc/sys/kernel/perf_event_max_stack */
};
struct perf_raw_record {
@@ -151,6 +151,15 @@ struct hw_perf_event {
*/
struct task_struct *target;
+ /*
+ * PMU would store hardware filter configuration
+ * here.
+ */
+ void *addr_filters;
+
+ /* Last sync'ed generation of filters */
+ unsigned long addr_filters_gen;
+
/*
* hw_perf_event::state flags; used to track the PERF_EF_* state.
*/
@@ -216,6 +225,7 @@ struct perf_event;
#define PERF_PMU_CAP_AUX_SW_DOUBLEBUF 0x08
#define PERF_PMU_CAP_EXCLUSIVE 0x10
#define PERF_PMU_CAP_ITRACE 0x20
+#define PERF_PMU_CAP_HETEROGENEOUS_CPUS 0x40
/**
* struct pmu - generic performance monitoring unit
@@ -240,6 +250,9 @@ struct pmu {
int task_ctx_nr;
int hrtimer_interval_ms;
+ /* number of address filters this PMU can do */
+ unsigned int nr_addr_filters;
+
/*
* Fully disable/enable this PMU, can be used to protect from the PMI
* as well as for lazy/batch writing of the MSRs.
@@ -393,12 +406,71 @@ struct pmu {
void (*free_aux) (void *aux); /* optional */
/*
+ * Validate address range filters: make sure the HW supports the
+ * requested configuration and number of filters; return 0 if the
+ * supplied filters are valid, -errno otherwise.
+ *
+ * Runs in the context of the ioctl()ing process and is not serialized
+ * with the rest of the PMU callbacks.
+ */
+ int (*addr_filters_validate) (struct list_head *filters);
+ /* optional */
+
+ /*
+ * Synchronize address range filter configuration:
+ * translate hw-agnostic filters into hardware configuration in
+ * event::hw::addr_filters.
+ *
+ * Runs as a part of filter sync sequence that is done in ->start()
+ * callback by calling perf_event_addr_filters_sync().
+ *
+ * May (and should) traverse event::addr_filters::list, for which its
+ * caller provides necessary serialization.
+ */
+ void (*addr_filters_sync) (struct perf_event *event);
+ /* optional */
+
+ /*
* Filter events for PMU-specific reasons.
*/
int (*filter_match) (struct perf_event *event); /* optional */
};
/**
+ * struct perf_addr_filter - address range filter definition
+ * @entry: event's filter list linkage
+ * @inode: object file's inode for file-based filters
+ * @offset: filter range offset
+ * @size: filter range size
+ * @range: 1: range, 0: address
+ * @filter: 1: filter/start, 0: stop
+ *
+ * This is a hardware-agnostic filter configuration as specified by the user.
+ */
+struct perf_addr_filter {
+ struct list_head entry;
+ struct inode *inode;
+ unsigned long offset;
+ unsigned long size;
+ unsigned int range : 1,
+ filter : 1;
+};
+
+/**
+ * struct perf_addr_filters_head - container for address range filters
+ * @list: list of filters for this event
+ * @lock: spinlock that serializes accesses to the @list and event's
+ * (and its children's) filter generations.
+ *
+ * A child event will use parent's @list (and therefore @lock), so they are
+ * bundled together; see perf_event_addr_filters().
+ */
+struct perf_addr_filters_head {
+ struct list_head list;
+ raw_spinlock_t lock;
+};
+
+/**
* enum perf_event_active_state - the states of a event
*/
enum perf_event_active_state {
@@ -566,6 +638,12 @@ struct perf_event {
atomic_t event_limit;
+ /* address range filters */
+ struct perf_addr_filters_head addr_filters;
+ /* vma address array for file-based filders */
+ unsigned long *addr_filters_offs;
+ unsigned long addr_filters_gen;
+
void (*destroy)(struct perf_event *);
struct rcu_head rcu_head;
@@ -834,9 +912,25 @@ extern int perf_event_overflow(struct perf_event *event,
struct perf_sample_data *data,
struct pt_regs *regs);
+extern void perf_event_output_forward(struct perf_event *event,
+ struct perf_sample_data *data,
+ struct pt_regs *regs);
+extern void perf_event_output_backward(struct perf_event *event,
+ struct perf_sample_data *data,
+ struct pt_regs *regs);
extern void perf_event_output(struct perf_event *event,
- struct perf_sample_data *data,
- struct pt_regs *regs);
+ struct perf_sample_data *data,
+ struct pt_regs *regs);
+
+static inline bool
+is_default_overflow_handler(struct perf_event *event)
+{
+ if (likely(event->overflow_handler == perf_event_output_forward))
+ return true;
+ if (unlikely(event->overflow_handler == perf_event_output_backward))
+ return true;
+ return false;
+}
extern void
perf_event_header__init_id(struct perf_event_header *header,
@@ -977,9 +1071,11 @@ get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user,
extern int get_callchain_buffers(void);
extern void put_callchain_buffers(void);
+extern int sysctl_perf_event_max_stack;
+
static inline int perf_callchain_store(struct perf_callchain_entry *entry, u64 ip)
{
- if (entry->nr < PERF_MAX_STACK_DEPTH) {
+ if (entry->nr < sysctl_perf_event_max_stack) {
entry->ip[entry->nr++] = ip;
return 0;
} else {
@@ -1001,6 +1097,8 @@ extern int perf_cpu_time_max_percent_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp,
loff_t *ppos);
+int perf_event_max_stack_handler(struct ctl_table *table, int write,
+ void __user *buffer, size_t *lenp, loff_t *ppos);
static inline bool perf_paranoid_tracepoint_raw(void)
{
@@ -1045,8 +1143,41 @@ static inline bool has_aux(struct perf_event *event)
return event->pmu->setup_aux;
}
+static inline bool is_write_backward(struct perf_event *event)
+{
+ return !!event->attr.write_backward;
+}
+
+static inline bool has_addr_filter(struct perf_event *event)
+{
+ return event->pmu->nr_addr_filters;
+}
+
+/*
+ * An inherited event uses parent's filters
+ */
+static inline struct perf_addr_filters_head *
+perf_event_addr_filters(struct perf_event *event)
+{
+ struct perf_addr_filters_head *ifh = &event->addr_filters;
+
+ if (event->parent)
+ ifh = &event->parent->addr_filters;
+
+ return ifh;
+}
+
+extern void perf_event_addr_filters_sync(struct perf_event *event);
+
extern int perf_output_begin(struct perf_output_handle *handle,
struct perf_event *event, unsigned int size);
+extern int perf_output_begin_forward(struct perf_output_handle *handle,
+ struct perf_event *event,
+ unsigned int size);
+extern int perf_output_begin_backward(struct perf_output_handle *handle,
+ struct perf_event *event,
+ unsigned int size);
+
extern void perf_output_end(struct perf_output_handle *handle);
extern unsigned int perf_output_copy(struct perf_output_handle *handle,
const void *buf, unsigned int len);
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 1afe9623c1a7..43fc8d213472 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -340,7 +340,8 @@ struct perf_event_attr {
comm_exec : 1, /* flag comm events that are due to an exec */
use_clockid : 1, /* use @clockid for time fields */
context_switch : 1, /* context switch data */
- __reserved_1 : 37;
+ write_backward : 1, /* Write ring buffer from end to beginning */
+ __reserved_1 : 36;
union {
__u32 wakeup_events; /* wakeup every n events */
@@ -401,6 +402,7 @@ struct perf_event_attr {
#define PERF_EVENT_IOC_SET_FILTER _IOW('$', 6, char *)
#define PERF_EVENT_IOC_ID _IOR('$', 7, __u64 *)
#define PERF_EVENT_IOC_SET_BPF _IOW('$', 8, __u32)
+#define PERF_EVENT_IOC_PAUSE_OUTPUT _IOW('$', 9, __u32)
enum perf_event_ioc_flags {
PERF_IOC_FLAG_GROUP = 1U << 0,