mirror of
git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
synced 2025-09-04 20:19:47 +08:00
eb8a55e01d
If it failed to find a variable for the location directly, it might be due to a missing variable in the source code. For example, accessing pointer variables in a chain can result in the case like below: struct foo *foo = ...; int i = foo->bar->baz; The DWARF debug information is created for each variable so it'd have one for 'foo'. But there's no variable for 'foo->bar' and then it cannot know the type of 'bar' and 'baz'. The above source code can be compiled to the follow x86 instructions: mov 0x8(%rax), %rcx mov 0x4(%rcx), %rdx <=== PMU sample mov %rdx, -4(%rbp) Let's say 'foo' is located in the %rax and it has a pointer to struct foo. But perf sample is captured in the second instruction and there is no variable or type info for the %rcx. It'd be great if compiler could generate debug info for %rcx, but we should handle it on our side. So this patch implements the logic to iterate instructions and update the type table for each location. As it already collected a list of scopes including the target instruction, we can use it to construct the type table smartly. +---------------- scope[0] subprogram | | +-------------- scope[1] lexical_block | | | | +------------ scope[2] inlined_subroutine | | | | | | +---------- scope[3] inlined_subroutine | | | | | | | | +-------- scope[4] lexical_block | | | | | | | | | | *** target instruction ... Image the target instruction has 5 scopes, each scope will have its own variables and parameters. Then it can start with the innermost scope (4). So it'd search the shortest path from the start of scope[4] to the target address and build a list of basic blocks. Then it iterates the basic blocks with the variables in the scope and update the table. If it finds a type at the target instruction, then returns it. Otherwise, it moves to the upper scope[3]. Now it'd search the shortest path from the start of scope[3] to the start of scope[4]. Then connect it to the existing basic block list. Then it'd iterate the blocks with variables for both scopes. It can repeat this until it finds a type at the target instruction or reaches to the top scope[0]. As the basic blocks contain the shortest path, it won't worry about branches and can update the table simply. The final check will be done by find_matching_type() in the next patch. Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: https://lore.kernel.org/r/20240319055115.4063940-15-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
180 lines
4.5 KiB
C
180 lines
4.5 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#ifndef _PERF_ANNOTATE_DATA_H
|
|
#define _PERF_ANNOTATE_DATA_H
|
|
|
|
#include <errno.h>
|
|
#include <linux/compiler.h>
|
|
#include <linux/rbtree.h>
|
|
#include <linux/types.h>
|
|
|
|
struct annotated_op_loc;
|
|
struct debuginfo;
|
|
struct evsel;
|
|
struct map_symbol;
|
|
struct thread;
|
|
|
|
/**
|
|
* struct annotated_member - Type of member field
|
|
* @node: List entry in the parent list
|
|
* @children: List head for child nodes
|
|
* @type_name: Name of the member type
|
|
* @var_name: Name of the member variable
|
|
* @offset: Offset from the outer data type
|
|
* @size: Size of the member field
|
|
*
|
|
* This represents a member type in a data type.
|
|
*/
|
|
struct annotated_member {
|
|
struct list_head node;
|
|
struct list_head children;
|
|
char *type_name;
|
|
char *var_name;
|
|
int offset;
|
|
int size;
|
|
};
|
|
|
|
/**
|
|
* struct type_hist_entry - Histogram entry per offset
|
|
* @nr_samples: Number of samples
|
|
* @period: Count of event
|
|
*/
|
|
struct type_hist_entry {
|
|
int nr_samples;
|
|
u64 period;
|
|
};
|
|
|
|
/**
|
|
* struct type_hist - Type histogram for each event
|
|
* @nr_samples: Total number of samples in this data type
|
|
* @period: Total count of the event in this data type
|
|
* @offset: Array of histogram entry
|
|
*/
|
|
struct type_hist {
|
|
u64 nr_samples;
|
|
u64 period;
|
|
struct type_hist_entry addr[];
|
|
};
|
|
|
|
/**
|
|
* struct annotated_data_type - Data type to profile
|
|
* @node: RB-tree node for dso->type_tree
|
|
* @self: Actual type information
|
|
* @nr_histogram: Number of histogram entries
|
|
* @histograms: An array of pointers to histograms
|
|
*
|
|
* This represents a data type accessed by samples in the profile data.
|
|
*/
|
|
struct annotated_data_type {
|
|
struct rb_node node;
|
|
struct annotated_member self;
|
|
int nr_histograms;
|
|
struct type_hist **histograms;
|
|
};
|
|
|
|
extern struct annotated_data_type unknown_type;
|
|
extern struct annotated_data_type stackop_type;
|
|
|
|
/**
|
|
* struct data_loc_info - Data location information
|
|
* @arch: CPU architecture info
|
|
* @thread: Thread info
|
|
* @ms: Map and Symbol info
|
|
* @ip: Instruction address
|
|
* @var_addr: Data address (for global variables)
|
|
* @cpumode: CPU execution mode
|
|
* @op: Instruction operand location (regs and offset)
|
|
* @di: Debug info
|
|
* @fbreg: Frame base register
|
|
* @fb_cfa: Whether the frame needs to check CFA
|
|
* @type_offset: Final offset in the type
|
|
*/
|
|
struct data_loc_info {
|
|
/* These are input field, should be filled by caller */
|
|
struct arch *arch;
|
|
struct thread *thread;
|
|
struct map_symbol *ms;
|
|
u64 ip;
|
|
u64 var_addr;
|
|
u8 cpumode;
|
|
struct annotated_op_loc *op;
|
|
|
|
/* These are used internally */
|
|
struct debuginfo *di;
|
|
int fbreg;
|
|
bool fb_cfa;
|
|
|
|
/* This is for the result */
|
|
int type_offset;
|
|
};
|
|
|
|
/**
|
|
* struct annotated_data_stat - Debug statistics
|
|
* @total: Total number of entry
|
|
* @no_sym: No symbol or map found
|
|
* @no_insn: Failed to get disasm line
|
|
* @no_insn_ops: The instruction has no operands
|
|
* @no_mem_ops: The instruction has no memory operands
|
|
* @no_reg: Failed to extract a register from the operand
|
|
* @no_dbginfo: The binary has no debug information
|
|
* @no_cuinfo: Failed to find a compile_unit
|
|
* @no_var: Failed to find a matching variable
|
|
* @no_typeinfo: Failed to get a type info for the variable
|
|
* @invalid_size: Failed to get a size info of the type
|
|
* @bad_offset: The access offset is out of the type
|
|
*/
|
|
struct annotated_data_stat {
|
|
int total;
|
|
int no_sym;
|
|
int no_insn;
|
|
int no_insn_ops;
|
|
int no_mem_ops;
|
|
int no_reg;
|
|
int no_dbginfo;
|
|
int no_cuinfo;
|
|
int no_var;
|
|
int no_typeinfo;
|
|
int invalid_size;
|
|
int bad_offset;
|
|
int insn_track;
|
|
};
|
|
extern struct annotated_data_stat ann_data_stat;
|
|
|
|
#ifdef HAVE_DWARF_SUPPORT
|
|
|
|
/* Returns data type at the location (ip, reg, offset) */
|
|
struct annotated_data_type *find_data_type(struct data_loc_info *dloc);
|
|
|
|
/* Update type access histogram at the given offset */
|
|
int annotated_data_type__update_samples(struct annotated_data_type *adt,
|
|
struct evsel *evsel, int offset,
|
|
int nr_samples, u64 period);
|
|
|
|
/* Release all data type information in the tree */
|
|
void annotated_data_type__tree_delete(struct rb_root *root);
|
|
|
|
#else /* HAVE_DWARF_SUPPORT */
|
|
|
|
static inline struct annotated_data_type *
|
|
find_data_type(struct data_loc_info *dloc __maybe_unused)
|
|
{
|
|
return NULL;
|
|
}
|
|
|
|
static inline int
|
|
annotated_data_type__update_samples(struct annotated_data_type *adt __maybe_unused,
|
|
struct evsel *evsel __maybe_unused,
|
|
int offset __maybe_unused,
|
|
int nr_samples __maybe_unused,
|
|
u64 period __maybe_unused)
|
|
{
|
|
return -1;
|
|
}
|
|
|
|
static inline void annotated_data_type__tree_delete(struct rb_root *root __maybe_unused)
|
|
{
|
|
}
|
|
|
|
#endif /* HAVE_DWARF_SUPPORT */
|
|
|
|
#endif /* _PERF_ANNOTATE_DATA_H */
|