summaryrefslogtreecommitdiffstats
path: root/include/linux/perf_event.h
diff options
context:
space:
mode:
Diffstat (limited to 'include/linux/perf_event.h')
-rw-r--r--include/linux/perf_event.h108
1 files changed, 96 insertions, 12 deletions
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index abb2776be1ba..bd9f55a5958d 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -129,11 +129,40 @@ enum perf_event_sample_format {
PERF_SAMPLE_PERIOD = 1U << 8,
PERF_SAMPLE_STREAM_ID = 1U << 9,
PERF_SAMPLE_RAW = 1U << 10,
+ PERF_SAMPLE_BRANCH_STACK = 1U << 11,
- PERF_SAMPLE_MAX = 1U << 11, /* non-ABI */
+ PERF_SAMPLE_MAX = 1U << 12, /* non-ABI */
};
/*
+ * values to program into branch_sample_type when PERF_SAMPLE_BRANCH is set
+ *
+ * If the user does not pass priv level information via branch_sample_type,
+ * the kernel uses the event's priv level. Branch and event priv levels do
+ * not have to match. Branch priv level is checked for permissions.
+ *
+ * The branch types can be combined, however BRANCH_ANY covers all types
+ * of branches and therefore it supersedes all the other types.
+ */
+enum perf_branch_sample_type {
+ PERF_SAMPLE_BRANCH_USER = 1U << 0, /* user branches */
+ PERF_SAMPLE_BRANCH_KERNEL = 1U << 1, /* kernel branches */
+ PERF_SAMPLE_BRANCH_HV = 1U << 2, /* hypervisor branches */
+
+ PERF_SAMPLE_BRANCH_ANY = 1U << 3, /* any branch types */
+ PERF_SAMPLE_BRANCH_ANY_CALL = 1U << 4, /* any call branch */
+ PERF_SAMPLE_BRANCH_ANY_RETURN = 1U << 5, /* any return branch */
+ PERF_SAMPLE_BRANCH_IND_CALL = 1U << 6, /* indirect calls */
+
+ PERF_SAMPLE_BRANCH_MAX = 1U << 7, /* non-ABI */
+};
+
+#define PERF_SAMPLE_BRANCH_PLM_ALL \
+ (PERF_SAMPLE_BRANCH_USER|\
+ PERF_SAMPLE_BRANCH_KERNEL|\
+ PERF_SAMPLE_BRANCH_HV)
+
+/*
* The format of the data returned by read() on a perf event fd,
* as specified by attr.read_format:
*
@@ -163,6 +192,8 @@ enum perf_event_read_format {
};
#define PERF_ATTR_SIZE_VER0 64 /* sizeof first published struct */
+#define PERF_ATTR_SIZE_VER1 72 /* add: config2 */
+#define PERF_ATTR_SIZE_VER2 80 /* add: branch_sample_type */
/*
* Hardware event_id to monitor via a performance monitoring event:
@@ -240,6 +271,7 @@ struct perf_event_attr {
__u64 bp_len;
__u64 config2; /* extension of config1 */
};
+ __u64 branch_sample_type; /* enum branch_sample_type */
};
/*
@@ -291,12 +323,14 @@ struct perf_event_mmap_page {
__s64 offset; /* add to hardware event value */
__u64 time_enabled; /* time event active */
__u64 time_running; /* time event on cpu */
+ __u32 time_mult, time_shift;
+ __u64 time_offset;
/*
* Hole for extension of the self monitor capabilities
*/
- __u64 __reserved[123]; /* align to 1k */
+ __u64 __reserved[121]; /* align to 1k */
/*
* Control data for the mmap() data buffer.
@@ -456,6 +490,8 @@ enum perf_event_type {
*
* { u32 size;
* char data[size];}&& PERF_SAMPLE_RAW
+ *
+ * { u64 from, to, flags } lbr[nr];} && PERF_SAMPLE_BRANCH_STACK
* };
*/
PERF_RECORD_SAMPLE = 9,
@@ -512,7 +548,7 @@ struct perf_guest_info_callbacks {
#include <linux/ftrace.h>
#include <linux/cpu.h>
#include <linux/irq_work.h>
-#include <linux/jump_label.h>
+#include <linux/static_key.h>
#include <linux/atomic.h>
#include <asm/local.h>
@@ -528,12 +564,34 @@ struct perf_raw_record {
void *data;
};
+/*
+ * single taken branch record layout:
+ *
+ * from: source instruction (may not always be a branch insn)
+ * to: branch target
+ * mispred: branch target was mispredicted
+ * predicted: branch target was predicted
+ *
+ * support for mispred, predicted is optional. In case it
+ * is not supported mispred = predicted = 0.
+ */
struct perf_branch_entry {
- __u64 from;
- __u64 to;
- __u64 flags;
+ __u64 from;
+ __u64 to;
+ __u64 mispred:1, /* target mispredicted */
+ predicted:1,/* target predicted */
+ reserved:62;
};
+/*
+ * branch stack layout:
+ * nr: number of taken branches stored in entries[]
+ *
+ * Note that nr can vary from sample to sample
+ * branches (to, from) are stored from most recent
+ * to least recent, i.e., entries[0] contains the most
+ * recent branch.
+ */
struct perf_branch_stack {
__u64 nr;
struct perf_branch_entry entries[0];
@@ -564,7 +622,9 @@ struct hw_perf_event {
unsigned long event_base;
int idx;
int last_cpu;
+
struct hw_perf_event_extra extra_reg;
+ struct hw_perf_event_extra branch_reg;
};
struct { /* software */
struct hrtimer hrtimer;
@@ -616,6 +676,7 @@ struct pmu {
struct list_head entry;
struct device *dev;
+ const struct attribute_group **attr_groups;
char *name;
int type;
@@ -681,6 +742,17 @@ struct pmu {
* for each successful ->add() during the transaction.
*/
void (*cancel_txn) (struct pmu *pmu); /* optional */
+
+ /*
+ * Will return the value for perf_event_mmap_page::index for this event,
+ * if no implementation is provided it will default to: event->hw.idx + 1.
+ */
+ int (*event_idx) (struct perf_event *event); /*optional */
+
+ /*
+ * flush branch stack on context-switches (needed in cpu-wide mode)
+ */
+ void (*flush_branch_stack) (void);
};
/**
@@ -850,6 +922,9 @@ struct perf_event {
#ifdef CONFIG_EVENT_TRACING
struct ftrace_event_call *tp_event;
struct event_filter *filter;
+#ifdef CONFIG_FUNCTION_TRACER
+ struct ftrace_ops ftrace_ops;
+#endif
#endif
#ifdef CONFIG_CGROUP_PERF
@@ -911,7 +986,8 @@ struct perf_event_context {
u64 parent_gen;
u64 generation;
int pin_count;
- int nr_cgroups; /* cgroup events present */
+ int nr_cgroups; /* cgroup evts */
+ int nr_branch_stack; /* branch_stack evt */
struct rcu_head rcu_head;
};
@@ -976,6 +1052,7 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr,
extern u64 perf_event_read_value(struct perf_event *event,
u64 *enabled, u64 *running);
+
struct perf_sample_data {
u64 type;
@@ -995,12 +1072,14 @@ struct perf_sample_data {
u64 period;
struct perf_callchain_entry *callchain;
struct perf_raw_record *raw;
+ struct perf_branch_stack *br_stack;
};
static inline void perf_sample_data_init(struct perf_sample_data *data, u64 addr)
{
data->addr = addr;
data->raw = NULL;
+ data->br_stack = NULL;
}
extern void perf_output_sample(struct perf_output_handle *handle,
@@ -1029,7 +1108,7 @@ static inline int is_software_event(struct perf_event *event)
return event->pmu->task_ctx_nr == perf_sw_context;
}
-extern struct jump_label_key perf_swevent_enabled[PERF_COUNT_SW_MAX];
+extern struct static_key perf_swevent_enabled[PERF_COUNT_SW_MAX];
extern void __perf_sw_event(u32, u64, struct pt_regs *, u64);
@@ -1057,7 +1136,7 @@ perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr)
{
struct pt_regs hot_regs;
- if (static_branch(&perf_swevent_enabled[event_id])) {
+ if (static_key_false(&perf_swevent_enabled[event_id])) {
if (!regs) {
perf_fetch_caller_regs(&hot_regs);
regs = &hot_regs;
@@ -1066,12 +1145,12 @@ perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr)
}
}
-extern struct jump_label_key_deferred perf_sched_events;
+extern struct static_key_deferred perf_sched_events;
static inline void perf_event_task_sched_in(struct task_struct *prev,
struct task_struct *task)
{
- if (static_branch(&perf_sched_events.key))
+ if (static_key_false(&perf_sched_events.key))
__perf_event_task_sched_in(prev, task);
}
@@ -1080,7 +1159,7 @@ static inline void perf_event_task_sched_out(struct task_struct *prev,
{
perf_sw_event(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, NULL, 0);
- if (static_branch(&perf_sched_events.key))
+ if (static_key_false(&perf_sched_events.key))
__perf_event_task_sched_out(prev, next);
}
@@ -1139,6 +1218,11 @@ extern void perf_bp_event(struct perf_event *event, void *data);
# define perf_instruction_pointer(regs) instruction_pointer(regs)
#endif
+static inline bool has_branch_stack(struct perf_event *event)
+{
+ return event->attr.sample_type & PERF_SAMPLE_BRANCH_STACK;
+}
+
extern int perf_output_begin(struct perf_output_handle *handle,
struct perf_event *event, unsigned int size);
extern void perf_output_end(struct perf_output_handle *handle);