linux/tools/perf/util/callchain.h
Kan Liang ff165628d7 perf callchain: Stitch LBR call stack
In LBR call stack mode, the depth of reconstructed LBR call stack limits
to the number of LBR registers.

  For example, on skylake, the depth of reconstructed LBR call stack is
  always <= 32.

  # To display the perf.data header info, please use
  # --header/--header-only options.
  #
  #
  # Total Lost Samples: 0
  #
  # Samples: 6K of event 'cycles'
  # Event count (approx.): 6487119731
  #
  # Children      Self  Command          Shared Object       Symbol
  # ........  ........  ...............  ..................
  # ................................

    99.97%    99.97%  tchain_edit      tchain_edit        [.] f43
            |
             --99.64%--f11
                       f12
                       f13
                       f14
                       f15
                       f16
                       f17
                       f18
                       f19
                       f20
                       f21
                       f22
                       f23
                       f24
                       f25
                       f26
                       f27
                       f28
                       f29
                       f30
                       f31
                       f32
                       f33
                       f34
                       f35
                       f36
                       f37
                       f38
                       f39
                       f40
                       f41
                       f42
                       f43

For a call stack which is deeper than LBR limit, HW will overwrite the
LBR register with oldest branch. Only partial call stacks can be
reconstructed.

However, the overwritten LBRs may still be retrieved from previous
sample. At that moment, HW hasn't overwritten the LBR registers yet.
Perf tools can stitch those overwritten LBRs on current call stacks to
get a more complete call stack.

To determine if LBRs can be stitched, perf tools need to compare current
sample with previous sample.

- They should have identical LBR records (Same from, to and flags
  values, and the same physical index of LBR registers).

- The searching starts from the base-of-stack of current sample.

Once perf determines to stitch the previous LBRs, the corresponding LBR
cursor nodes will be copied to 'lists'.  The 'lists' is to track the LBR
cursor nodes which are going to be stitched.

When the stitching is over, the nodes will not be freed immediately.
They will be moved to 'free_lists'. Next stitching may reuse the space.
Both 'lists' and 'free_lists' will be freed when all samples are
processed.

Committer notes:

Fix the intel-pt.c initialization of the union with 'struct
branch_flags', that breaks the build with its unnamed union on older gcc
versions.

Uninline thread__free_stitch_list(), as it grew big and started dragging
includes to thread.h, so move it to thread.c where what it needs in
terms of headers are already there.

This fixes the build in several systems such as debian:experimental when
cross building to the MIPS32 architecture, i.e. in the other cases what
was needed was being included by sheer luck.

  In file included from builtin-sched.c:11:
  util/thread.h: In function 'thread__free_stitch_list':
  util/thread.h:169:3: error: implicit declaration of function 'free' [-Werror=implicit-function-declaration]
    169 |   free(pos);
        |   ^~~~
  util/thread.h:169:3: error: incompatible implicit declaration of built-in function 'free' [-Werror]
  util/thread.h:19:1: note: include '<stdlib.h>' or provide a declaration of 'free'
     18 | #include "callchain.h"
    +++ |+#include <stdlib.h>
     19 |
  util/thread.h:174:3: error: incompatible implicit declaration of built-in function 'free' [-Werror]
    174 |   free(pos);
        |   ^~~~
  util/thread.h:174:3: note: include '<stdlib.h>' or provide a declaration of 'free'

Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Reviewed-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexey Budankov <alexey.budankov@linux.intel.com>
Cc: Mathieu Poirier <mathieu.poirier@linaro.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Pavel Gerasimov <pavel.gerasimov@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Vitaly Slobodskoy <vitaly.slobodskoy@intel.com>
Link: http://lore.kernel.org/lkml/20200319202517.23423-13-kan.liang@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-04-18 09:05:01 -03:00

301 lines
7.9 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef __PERF_CALLCHAIN_H
#define __PERF_CALLCHAIN_H
#include <linux/list.h>
#include <linux/rbtree.h>
#include "map_symbol.h"
#include "branch.h"
struct addr_location;
struct evsel;
struct ip_callchain;
struct map;
struct perf_sample;
struct thread;
#define HELP_PAD "\t\t\t\t"
#define CALLCHAIN_HELP "setup and enables call-graph (stack chain/backtrace):\n\n"
# define RECORD_MODE_HELP HELP_PAD "record_mode:\tcall graph recording mode (fp|dwarf|lbr)\n"
#define RECORD_SIZE_HELP \
HELP_PAD "record_size:\tif record_mode is 'dwarf', max size of stack recording (<bytes>)\n" \
HELP_PAD "\t\tdefault: 8192 (bytes)\n"
#define CALLCHAIN_RECORD_HELP CALLCHAIN_HELP RECORD_MODE_HELP RECORD_SIZE_HELP
#define CALLCHAIN_REPORT_HELP \
HELP_PAD "print_type:\tcall graph printing style (graph|flat|fractal|folded|none)\n" \
HELP_PAD "threshold:\tminimum call graph inclusion threshold (<percent>)\n" \
HELP_PAD "print_limit:\tmaximum number of call graph entry (<number>)\n" \
HELP_PAD "order:\t\tcall graph order (caller|callee)\n" \
HELP_PAD "sort_key:\tcall graph sort key (function|address)\n" \
HELP_PAD "branch:\t\tinclude last branch info to call graph (branch)\n" \
HELP_PAD "value:\t\tcall graph value (percent|period|count)\n"
enum perf_call_graph_mode {
CALLCHAIN_NONE,
CALLCHAIN_FP,
CALLCHAIN_DWARF,
CALLCHAIN_LBR,
CALLCHAIN_MAX
};
enum chain_mode {
CHAIN_NONE,
CHAIN_FLAT,
CHAIN_GRAPH_ABS,
CHAIN_GRAPH_REL,
CHAIN_FOLDED,
};
enum chain_order {
ORDER_CALLER,
ORDER_CALLEE
};
struct callchain_node {
struct callchain_node *parent;
struct list_head val;
struct list_head parent_val;
struct rb_node rb_node_in; /* to insert nodes in an rbtree */
struct rb_node rb_node; /* to sort nodes in an output tree */
struct rb_root rb_root_in; /* input tree of children */
struct rb_root rb_root; /* sorted output tree of children */
unsigned int val_nr;
unsigned int count;
unsigned int children_count;
u64 hit;
u64 children_hit;
};
struct callchain_root {
u64 max_depth;
struct callchain_node node;
};
struct callchain_param;
typedef void (*sort_chain_func_t)(struct rb_root *, struct callchain_root *,
u64, struct callchain_param *);
enum chain_key {
CCKEY_FUNCTION,
CCKEY_ADDRESS,
CCKEY_SRCLINE
};
enum chain_value {
CCVAL_PERCENT,
CCVAL_PERIOD,
CCVAL_COUNT,
};
extern bool dwarf_callchain_users;
struct callchain_param {
bool enabled;
enum perf_call_graph_mode record_mode;
u32 dump_size;
enum chain_mode mode;
u16 max_stack;
u32 print_limit;
double min_percent;
sort_chain_func_t sort;
enum chain_order order;
bool order_set;
enum chain_key key;
bool branch_callstack;
enum chain_value value;
};
extern struct callchain_param callchain_param;
extern struct callchain_param callchain_param_default;
struct callchain_list {
u64 ip;
struct map_symbol ms;
struct /* for TUI */ {
bool unfolded;
bool has_children;
};
u64 branch_count;
u64 from_count;
u64 predicted_count;
u64 abort_count;
u64 cycles_count;
u64 iter_count;
u64 iter_cycles;
struct branch_type_stat brtype_stat;
const char *srcline;
struct list_head list;
};
/*
* A callchain cursor is a single linked list that
* let one feed a callchain progressively.
* It keeps persistent allocated entries to minimize
* allocations.
*/
struct callchain_cursor_node {
u64 ip;
struct map_symbol ms;
const char *srcline;
/* Indicate valid cursor node for LBR stitch */
bool valid;
bool branch;
struct branch_flags branch_flags;
u64 branch_from;
int nr_loop_iter;
u64 iter_cycles;
struct callchain_cursor_node *next;
};
struct stitch_list {
struct list_head node;
struct callchain_cursor_node cursor;
};
struct callchain_cursor {
u64 nr;
struct callchain_cursor_node *first;
struct callchain_cursor_node **last;
u64 pos;
struct callchain_cursor_node *curr;
};
extern __thread struct callchain_cursor callchain_cursor;
static inline void callchain_init(struct callchain_root *root)
{
INIT_LIST_HEAD(&root->node.val);
INIT_LIST_HEAD(&root->node.parent_val);
root->node.parent = NULL;
root->node.hit = 0;
root->node.children_hit = 0;
root->node.rb_root_in = RB_ROOT;
root->max_depth = 0;
}
static inline u64 callchain_cumul_hits(struct callchain_node *node)
{
return node->hit + node->children_hit;
}
static inline unsigned callchain_cumul_counts(struct callchain_node *node)
{
return node->count + node->children_count;
}
int callchain_register_param(struct callchain_param *param);
int callchain_append(struct callchain_root *root,
struct callchain_cursor *cursor,
u64 period);
int callchain_merge(struct callchain_cursor *cursor,
struct callchain_root *dst, struct callchain_root *src);
void callchain_cursor_reset(struct callchain_cursor *cursor);
int callchain_cursor_append(struct callchain_cursor *cursor, u64 ip,
struct map_symbol *ms,
bool branch, struct branch_flags *flags,
int nr_loop_iter, u64 iter_cycles, u64 branch_from,
const char *srcline);
/* Close a cursor writing session. Initialize for the reader */
static inline void callchain_cursor_commit(struct callchain_cursor *cursor)
{
cursor->curr = cursor->first;
cursor->pos = 0;
}
/* Cursor reading iteration helpers */
static inline struct callchain_cursor_node *
callchain_cursor_current(struct callchain_cursor *cursor)
{
if (cursor->pos == cursor->nr)
return NULL;
return cursor->curr;
}
static inline void callchain_cursor_advance(struct callchain_cursor *cursor)
{
cursor->curr = cursor->curr->next;
cursor->pos++;
}
int callchain_cursor__copy(struct callchain_cursor *dst,
struct callchain_cursor *src);
struct option;
struct hist_entry;
int record_parse_callchain_opt(const struct option *opt, const char *arg, int unset);
int record_callchain_opt(const struct option *opt, const char *arg, int unset);
struct record_opts;
int record_opts__parse_callchain(struct record_opts *record,
struct callchain_param *callchain,
const char *arg, bool unset);
int sample__resolve_callchain(struct perf_sample *sample,
struct callchain_cursor *cursor, struct symbol **parent,
struct evsel *evsel, struct addr_location *al,
int max_stack);
int hist_entry__append_callchain(struct hist_entry *he, struct perf_sample *sample);
int fill_callchain_info(struct addr_location *al, struct callchain_cursor_node *node,
bool hide_unresolved);
extern const char record_callchain_help[];
int parse_callchain_record(const char *arg, struct callchain_param *param);
int parse_callchain_record_opt(const char *arg, struct callchain_param *param);
int parse_callchain_report_opt(const char *arg);
int parse_callchain_top_opt(const char *arg);
int perf_callchain_config(const char *var, const char *value);
static inline void callchain_cursor_snapshot(struct callchain_cursor *dest,
struct callchain_cursor *src)
{
*dest = *src;
dest->first = src->curr;
dest->nr -= src->pos;
}
#ifdef HAVE_SKIP_CALLCHAIN_IDX
int arch_skip_callchain_idx(struct thread *thread, struct ip_callchain *chain);
#else
static inline int arch_skip_callchain_idx(struct thread *thread __maybe_unused,
struct ip_callchain *chain __maybe_unused)
{
return -1;
}
#endif
char *callchain_list__sym_name(struct callchain_list *cl,
char *bf, size_t bfsize, bool show_dso);
char *callchain_node__scnprintf_value(struct callchain_node *node,
char *bf, size_t bfsize, u64 total);
int callchain_node__fprintf_value(struct callchain_node *node,
FILE *fp, u64 total);
int callchain_list_counts__printf_value(struct callchain_list *clist,
FILE *fp, char *bf, int bfsize);
void free_callchain(struct callchain_root *root);
void decay_callchain(struct callchain_root *root);
int callchain_node__make_parent_list(struct callchain_node *node);
int callchain_branch_counts(struct callchain_root *root,
u64 *branch_count, u64 *predicted_count,
u64 *abort_count, u64 *cycles_count);
#endif /* __PERF_CALLCHAIN_H */