mirror/linux
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Merge branch 'perf/hw-branch-sampling' into perf/core

Browse Source 
Merge reason: The 'perf record -b' hardware branch sampling feature is ready for upstream.

Signed-off-by: Ingo Molnar <mingo@elte.hu>
This commit is contained in:
Ingo Molnar
2012-03-12 20:46:35 +01:00
parent f9b4eeb809 24bff2dc0f
commit bea95c152d
33 changed files with 2019 additions and 245 deletions
Download Patch File Download Diff File Expand all files Collapse all files

82
include/linux/perf_event.h
View File

@@ -129,10 +129,39 @@ 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 */
};
/*
@@ -458,6 +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,
@@ -530,12 +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];
@@ -566,7 +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;
@@ -690,6 +748,11 @@ struct pmu {
* 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);
};
/**
@@ -923,7 +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;
};
@@ -988,6 +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;
@@ -1007,12 +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,
@@ -1151,6 +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);