linux/tools/perf/util/kwork.h
Yang Jihong daf07d2207 perf kwork: Implement BPF trace
'perf record' generates perf.data, which generates extra interrupts
for hard disk, amount of data to be collected increases with time.

Using eBPF trace can process the data in kernel, which solves the
preceding two problems.

Add -b/--use-bpf option for latency and report to support
tracing kwork events using eBPF:

1. Create bpf prog and attach to tracepoints,
2. Start tracing after command is entered,
3. After user hit "ctrl+c", stop tracing and report,
4. Support CPU and name filtering.

This commit implements the framework code and
does not add specific event support.

Test cases:

  # perf kwork rep -h

   Usage: perf kwork report [<options>]

      -b, --use-bpf         Use BPF to measure kwork runtime
      -C, --cpu <cpu>       list of cpus to profile
      -i, --input <file>    input file name
      -n, --name <name>     event name to profile
      -s, --sort <key[,key2...]>
                            sort by key(s): runtime, max, count
      -S, --with-summary    Show summary with statistics
          --time <str>      Time span for analysis (start,stop)

  # perf kwork lat -h

   Usage: perf kwork latency [<options>]

      -b, --use-bpf         Use BPF to measure kwork latency
      -C, --cpu <cpu>       list of cpus to profile
      -i, --input <file>    input file name
      -n, --name <name>     event name to profile
      -s, --sort <key[,key2...]>
                            sort by key(s): avg, max, count
          --time <str>      Time span for analysis (start,stop)

  # perf kwork lat -b
  Unsupported bpf trace class irq

  # perf kwork rep -b
  Unsupported bpf trace class irq

Signed-off-by: Yang Jihong <yangjihong1@huawei.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Clarke <pc@us.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20220709015033.38326-15-yangjihong1@huawei.com
[ Simplify work_findnew() ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-07-26 16:31:54 -03:00

258 lines
7.5 KiB
C

#ifndef PERF_UTIL_KWORK_H
#define PERF_UTIL_KWORK_H
#include "perf.h"
#include "util/tool.h"
#include "util/event.h"
#include "util/evlist.h"
#include "util/session.h"
#include "util/time-utils.h"
#include <linux/list.h>
#include <linux/bitmap.h>
enum kwork_class_type {
KWORK_CLASS_IRQ,
KWORK_CLASS_SOFTIRQ,
KWORK_CLASS_WORKQUEUE,
KWORK_CLASS_MAX,
};
enum kwork_report_type {
KWORK_REPORT_RUNTIME,
KWORK_REPORT_LATENCY,
KWORK_REPORT_TIMEHIST,
};
enum kwork_trace_type {
KWORK_TRACE_RAISE,
KWORK_TRACE_ENTRY,
KWORK_TRACE_EXIT,
KWORK_TRACE_MAX,
};
/*
* data structure:
*
* +==================+ +============+ +======================+
* | class | | work | | atom |
* +==================+ +============+ +======================+
* +------------+ | +-----+ | | +------+ | | +-------+ +-----+ |
* | perf_kwork | +-> | irq | --------|+-> | eth0 | --+-> | raise | - | ... | --+ +-----------+
* +-----+------+ || +-----+ ||| +------+ ||| +-------+ +-----+ | | | |
* | || ||| ||| | +-> | atom_page |
* | || ||| ||| +-------+ +-----+ | | |
* | class_list ||| |+-> | entry | - | ... | ----> | |
* | || ||| ||| +-------+ +-----+ | | |
* | || ||| ||| | +-> | |
* | || ||| ||| +-------+ +-----+ | | | |
* | || ||| |+-> | exit | - | ... | --+ +-----+-----+
* | || ||| | | +-------+ +-----+ | |
* | || ||| | | | |
* | || ||| +-----+ | | | |
* | || |+-> | ... | | | | |
* | || | | +-----+ | | | |
* | || | | | | | |
* | || +---------+ | | +-----+ | | +-------+ +-----+ | |
* | +-> | softirq | -------> | RCU | ---+-> | raise | - | ... | --+ +-----+-----+
* | || +---------+ | | +-----+ ||| +-------+ +-----+ | | | |
* | || | | ||| | +-> | atom_page |
* | || | | ||| +-------+ +-----+ | | |
* | || | | |+-> | entry | - | ... | ----> | |
* | || | | ||| +-------+ +-----+ | | |
* | || | | ||| | +-> | |
* | || | | ||| +-------+ +-----+ | | | |
* | || | | |+-> | exit | - | ... | --+ +-----+-----+
* | || | | | | +-------+ +-----+ | |
* | || | | | | | |
* | || +-----------+ | | +-----+ | | | |
* | +-> | workqueue | -----> | ... | | | | |
* | | +-----------+ | | +-----+ | | | |
* | +==================+ +============+ +======================+ |
* | |
* +----> atom_page_list ---------------------------------------------------------+
*
*/
struct kwork_atom {
struct list_head list;
u64 time;
struct kwork_atom *prev;
void *page_addr;
unsigned long bit_inpage;
};
#define NR_ATOM_PER_PAGE 128
struct kwork_atom_page {
struct list_head list;
struct kwork_atom atoms[NR_ATOM_PER_PAGE];
DECLARE_BITMAP(bitmap, NR_ATOM_PER_PAGE);
};
struct kwork_class;
struct kwork_work {
/*
* class field
*/
struct rb_node node;
struct kwork_class *class;
/*
* work field
*/
u64 id;
int cpu;
char *name;
/*
* atom field
*/
u64 nr_atoms;
struct list_head atom_list[KWORK_TRACE_MAX];
/*
* runtime report
*/
u64 max_runtime;
u64 max_runtime_start;
u64 max_runtime_end;
u64 total_runtime;
/*
* latency report
*/
u64 max_latency;
u64 max_latency_start;
u64 max_latency_end;
u64 total_latency;
};
struct kwork_class {
struct list_head list;
const char *name;
enum kwork_class_type type;
unsigned int nr_tracepoints;
const struct evsel_str_handler *tp_handlers;
struct rb_root_cached work_root;
int (*class_init)(struct kwork_class *class,
struct perf_session *session);
void (*work_init)(struct kwork_class *class,
struct kwork_work *work,
struct evsel *evsel,
struct perf_sample *sample,
struct machine *machine);
void (*work_name)(struct kwork_work *work,
char *buf, int len);
};
struct perf_kwork;
struct trace_kwork_handler {
int (*raise_event)(struct perf_kwork *kwork,
struct kwork_class *class, struct evsel *evsel,
struct perf_sample *sample, struct machine *machine);
int (*entry_event)(struct perf_kwork *kwork,
struct kwork_class *class, struct evsel *evsel,
struct perf_sample *sample, struct machine *machine);
int (*exit_event)(struct perf_kwork *kwork,
struct kwork_class *class, struct evsel *evsel,
struct perf_sample *sample, struct machine *machine);
};
struct perf_kwork {
/*
* metadata
*/
struct perf_tool tool;
struct list_head class_list;
struct list_head atom_page_list;
struct list_head sort_list, cmp_id;
struct rb_root_cached sorted_work_root;
const struct trace_kwork_handler *tp_handler;
/*
* profile filters
*/
const char *profile_name;
const char *cpu_list;
DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
const char *time_str;
struct perf_time_interval ptime;
/*
* options for command
*/
bool force;
const char *event_list_str;
enum kwork_report_type report;
/*
* options for subcommand
*/
bool summary;
const char *sort_order;
bool show_callchain;
unsigned int max_stack;
bool use_bpf;
/*
* statistics
*/
u64 timestart;
u64 timeend;
unsigned long nr_events;
unsigned long nr_lost_chunks;
unsigned long nr_lost_events;
u64 all_runtime;
u64 all_count;
u64 nr_skipped_events[KWORK_TRACE_MAX + 1];
};
struct kwork_work *perf_kwork_add_work(struct perf_kwork *kwork,
struct kwork_class *class,
struct kwork_work *key);
#ifdef HAVE_BPF_SKEL
int perf_kwork__trace_prepare_bpf(struct perf_kwork *kwork);
int perf_kwork__report_read_bpf(struct perf_kwork *kwork);
void perf_kwork__report_cleanup_bpf(void);
void perf_kwork__trace_start(void);
void perf_kwork__trace_finish(void);
#else /* !HAVE_BPF_SKEL */
static inline int
perf_kwork__trace_prepare_bpf(struct perf_kwork *kwork __maybe_unused)
{
return -1;
}
static inline int
perf_kwork__report_read_bpf(struct perf_kwork *kwork __maybe_unused)
{
return -1;
}
static inline void perf_kwork__report_cleanup_bpf(void) {}
static inline void perf_kwork__trace_start(void) {}
static inline void perf_kwork__trace_finish(void) {}
#endif /* HAVE_BPF_SKEL */
#endif /* PERF_UTIL_KWORK_H */