linux/tools/perf/util/symbol.h

371 lines
9.5 KiB
C
Raw Normal View History

#ifndef __PERF_SYMBOL
#define __PERF_SYMBOL 1
#include <linux/types.h>
#include <stdbool.h>
#include <stdint.h>
#include "map.h"
#include "../perf.h"
#include <linux/list.h>
#include <linux/rbtree.h>
#include <stdio.h>
perf symbols: Handle different endians properly during symbol load Currently we dont care about the file object's endianness. It's possible we read buildid file object from different architecture than we are currentlly running on. So we need to care about properly reading such object's data - handle different endianness properly. Adding: needs_swap DSO field dso__swap_init function to initialize DSO's needs_swap DSO__SWAP to read the data with proper swaps Together with other endianity patches, this change fixies perf report discrepancies on origin and target systems as described in test 1 below, e.g. following perf report diff: ... 0.12% ps [kernel.kallsyms] [k] clear_page - 0.12% awk bash [.] alloc_word_desc + 0.12% awk bash [.] yyparse 0.11% beah-rhts-task libpython2.6.so.1.0 [.] 0x5560e 0.10% perf libc-2.12.so [.] __ctype_toupper_loc - 0.09% rhts-test-runne bash [.] maybe_make_export_env + 0.09% rhts-test-runne bash [.] 0x385a0 0.09% ps [kernel.kallsyms] [k] page_fault ... Note, running following to test perf endianity handling: test 1) - origin system: # perf record -a -- sleep 10 (any perf record will do) # perf report > report.origin # perf archive perf.data - copy the perf.data, report.origin and perf.data.tar.bz2 to a target system and run: # tar xjvf perf.data.tar.bz2 -C ~/.debug # perf report > report.target # diff -u report.origin report.target - the diff should produce no output (besides some white space stuff and possibly different date/TZ output) test 1) - origin system: # perf record -ag -fo /tmp/perf.data -- sleep 1 - mount origin system root to the target system on /mnt/origin - target system: # perf script --symfs /mnt/origin -I -i /mnt/origin/tmp/perf.data \ --kallsyms /mnt/origin/proc/kallsyms - complete perf.data header is displayed Signed-off-by: Jiri Olsa <jolsa@redhat.com> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1338380624-7443-2-git-send-email-jolsa@redhat.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-05-30 12:23:42 +00:00
#include <byteswap.h>
#include <libgen.h>
#include "build-id.h"
#include "event.h"
#include "util.h"
#ifdef HAVE_LIBELF_SUPPORT
#include <libelf.h>
#include <gelf.h>
#endif
#include <elf.h>
#include "dso.h"
/*
* libelf 0.8.x and earlier do not support ELF_C_READ_MMAP;
* for newer versions we can use mmap to reduce memory usage:
*/
#ifdef HAVE_LIBELF_MMAP_SUPPORT
# define PERF_ELF_C_READ_MMAP ELF_C_READ_MMAP
#else
# define PERF_ELF_C_READ_MMAP ELF_C_READ
#endif
#ifdef HAVE_LIBELF_SUPPORT
Elf_Scn *elf_section_by_name(Elf *elf, GElf_Ehdr *ep,
GElf_Shdr *shp, const char *name, size_t *idx);
#endif
#ifndef DMGL_PARAMS
#define DMGL_NO_OPTS 0 /* For readability... */
#define DMGL_PARAMS (1 << 0) /* Include function args */
#define DMGL_ANSI (1 << 1) /* Include const, volatile, etc */
#endif
#define DSO__NAME_KALLSYMS "[kernel.kallsyms]"
#define DSO__NAME_KCORE "[kernel.kcore]"
/** struct symbol - symtab entry
*
* @ignore - resolvable but tools ignore it (e.g. idle routines)
*/
struct symbol {
struct rb_node rb_node;
u64 start;
u64 end;
u16 namelen;
u8 binding;
bool ignore;
u8 arch_sym;
char name[0];
};
void symbol__delete(struct symbol *sym);
void symbols__delete(struct rb_root *symbols);
perf probe: Allow to add events on the local functions Allow to add events on the local functions without debuginfo. (With the debuginfo, we can add events even on inlined functions) Currently, probing on local functions requires debuginfo to locate actual address. It is also possible without debuginfo since we have symbol maps. Without this change; ---- # ./perf probe -a t_show Added new event: probe:t_show (on t_show) You can now use it in all perf tools, such as: perf record -e probe:t_show -aR sleep 1 # ./perf probe -x perf -a identity__map_ip no symbols found in /kbuild/ksrc/linux-3/tools/perf/perf, maybe install a debug package? Failed to load map. Error: Failed to add events. (-22) ---- As the above results, perf probe just put one event on the first found symbol for kprobe event. Moreover, for uprobe event, perf probe failed to find local functions. With this change; ---- # ./perf probe -a t_show Added new events: probe:t_show (on t_show) probe:t_show_1 (on t_show) probe:t_show_2 (on t_show) probe:t_show_3 (on t_show) You can now use it in all perf tools, such as: perf record -e probe:t_show_3 -aR sleep 1 # ./perf probe -x perf -a identity__map_ip Added new events: probe_perf:identity__map_ip (on identity__map_ip in /kbuild/ksrc/linux-3/tools/perf/perf) probe_perf:identity__map_ip_1 (on identity__map_ip in /kbuild/ksrc/linux-3/tools/perf/perf) probe_perf:identity__map_ip_2 (on identity__map_ip in /kbuild/ksrc/linux-3/tools/perf/perf) probe_perf:identity__map_ip_3 (on identity__map_ip in /kbuild/ksrc/linux-3/tools/perf/perf) You can now use it in all perf tools, such as: perf record -e probe_perf:identity__map_ip_3 -aR sleep 1 ---- Now we succeed to put events on every given local functions for both kprobes and uprobes. :) Note that this also introduces some symbol rbtree iteration macros; symbols__for_each, dso__for_each_symbol, and map__for_each_symbol. These are for walking through the symbol list in a map. Changes from v2: - Fix add_exec_to_probe_trace_events() not to convert address to tp->symbol any more. - Fix to set kernel probes based on ref_reloc_sym. Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: David Ahern <dsahern@gmail.com> Cc: "David A. Long" <dave.long@linaro.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: yrl.pp-manager.tt@hitachi.com Link: http://lkml.kernel.org/r/20140206053225.29635.15026.stgit@kbuild-fedora.yrl.intra.hitachi.co.jp Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2014-02-06 05:32:25 +00:00
/* symbols__for_each_entry - iterate over symbols (rb_root)
*
* @symbols: the rb_root of symbols
* @pos: the 'struct symbol *' to use as a loop cursor
* @nd: the 'struct rb_node *' to use as a temporary storage
*/
#define symbols__for_each_entry(symbols, pos, nd) \
for (nd = rb_first(symbols); \
nd && (pos = rb_entry(nd, struct symbol, rb_node)); \
nd = rb_next(nd))
static inline size_t symbol__size(const struct symbol *sym)
{
return sym->end - sym->start;
}
struct strlist;
struct intlist;
struct symbol_conf {
unsigned short priv_size;
unsigned short nr_events;
bool try_vmlinux_path,
init_annotation,
force,
ignore_vmlinux,
perf record: Do not save pathname in ./debug/.build-id directory for vmlinux When perf record finishes a session, it pre-processes samples in order to write build-id info from DSOs that had samples. During this process it'll call map__load() for the kernel map, and it ends up calling dso__load_vmlinux_path() which replaces dso->long_name. But this function checks kernel's build-id before searching vmlinux path so it'll end up with a cryptic name, the pathname for the entry in the ~/.debug cache, which can be confusing to users. This patch adds a flag to skip the build-id check during record, so that it'll have the original vmlinux path for the kernel dso->long_name, not the entry in the ~/.debug cache. Before: # perf record -va sleep 3 mmap size 528384B [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.196 MB perf.data (~8545 samples) ] Looking at the vmlinux_path (7 entries long) Using /home/namhyung/.debug/.build-id/f0/6e17aa50adf4d00b88925e03775de107611551 for symbols After: # perf record -va sleep 3 mmap size 528384B [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.193 MB perf.data (~8432 samples) ] Looking at the vmlinux_path (7 entries long) Using /lib/modules/3.16.4-1-ARCH/build/vmlinux for symbols Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/r/1415063674-17206-7-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2014-11-04 01:14:32 +00:00
ignore_vmlinux_buildid,
show_kernel_path,
use_modules,
allow_aliases,
sort_by_name,
show_nr_samples,
show_total_period,
use_callchain,
cumulate_callchain,
exclude_other,
show_cpu_utilization,
perf symbols: Handle /proc/sys/kernel/kptr_restrict Perf uses /proc/modules to figure out where kernel modules are loaded. With the advent of kptr_restrict, non root users get zeroes for all module start addresses. So check if kptr_restrict is non zero and don't generate the syntethic PERF_RECORD_MMAP events for them. Warn the user about it in perf record and in perf report. In perf report the reference relocation symbol being zero means that kptr_restrict was set, thus /proc/kallsyms has only zeroed addresses, so don't use it to fixup symbol addresses when using a valid kallsyms (in the buildid cache) or vmlinux (in the vmlinux path) build-id located automatically or specified by the user. Provide an explanation about it in 'perf report' if kernel samples were taken, checking if a suitable vmlinux or kallsyms was found/specified. Restricted /proc/kallsyms don't go to the buildid cache anymore. Example: [acme@emilia ~]$ perf record -F 100000 sleep 1 WARNING: Kernel address maps (/proc/{kallsyms,modules}) are restricted, check /proc/sys/kernel/kptr_restrict. Samples in kernel functions may not be resolved if a suitable vmlinux file is not found in the buildid cache or in the vmlinux path. Samples in kernel modules won't be resolved at all. If some relocation was applied (e.g. kexec) symbols may be misresolved even with a suitable vmlinux or kallsyms file. [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.005 MB perf.data (~231 samples) ] [acme@emilia ~]$ [acme@emilia ~]$ perf report --stdio Kernel address maps (/proc/{kallsyms,modules}) were restricted, check /proc/sys/kernel/kptr_restrict before running 'perf record'. If some relocation was applied (e.g. kexec) symbols may be misresolved. Samples in kernel modules can't be resolved as well. # Events: 13 cycles # # Overhead Command Shared Object Symbol # ........ ....... ................. ..................... # 20.24% sleep [kernel.kallsyms] [k] page_fault 20.04% sleep [kernel.kallsyms] [k] filemap_fault 19.78% sleep [kernel.kallsyms] [k] __lru_cache_add 19.69% sleep ld-2.12.so [.] memcpy 14.71% sleep [kernel.kallsyms] [k] dput 4.70% sleep [kernel.kallsyms] [k] flush_signal_handlers 0.73% sleep [kernel.kallsyms] [k] perf_event_comm 0.11% sleep [kernel.kallsyms] [k] native_write_msr_safe # # (For a higher level overview, try: perf report --sort comm,dso) # [acme@emilia ~]$ This is because it found a suitable vmlinux (build-id checked) in /lib/modules/2.6.39-rc7+/build/vmlinux (use -v in perf report to see the long file name). If we remove that file from the vmlinux path: [root@emilia ~]# mv /lib/modules/2.6.39-rc7+/build/vmlinux \ /lib/modules/2.6.39-rc7+/build/vmlinux.OFF [acme@emilia ~]$ perf report --stdio [kernel.kallsyms] with build id 57298cdbe0131f6871667ec0eaab4804dcf6f562 not found, continuing without symbols Kernel address maps (/proc/{kallsyms,modules}) were restricted, check /proc/sys/kernel/kptr_restrict before running 'perf record'. As no suitable kallsyms nor vmlinux was found, kernel samples can't be resolved. Samples in kernel modules can't be resolved as well. # Events: 13 cycles # # Overhead Command Shared Object Symbol # ........ ....... ................. ...... # 80.31% sleep [kernel.kallsyms] [k] 0xffffffff8103425a 19.69% sleep ld-2.12.so [.] memcpy # # (For a higher level overview, try: perf report --sort comm,dso) # [acme@emilia ~]$ Reported-by: Stephane Eranian <eranian@google.com> Suggested-by: David Miller <davem@davemloft.net> Cc: Dave Jones <davej@redhat.com> Cc: David Miller <davem@davemloft.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Kees Cook <kees.cook@canonical.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Pekka Enberg <penberg@cs.helsinki.fi> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Cc: Tom Zanussi <tzanussi@gmail.com> Link: http://lkml.kernel.org/n/tip-mt512joaxxbhhp1odop04yit@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-05-26 12:53:51 +00:00
initialized,
kptr_restrict,
annotate_asm_raw,
annotate_src,
event_group,
demangle,
demangle_kernel,
filter_relative,
perf callchain: Support handling complete branch stacks as histograms Currently branch stacks can be only shown as edge histograms for individual branches. I never found this display particularly useful. This implements an alternative mode that creates histograms over complete branch traces, instead of individual branches, similar to how normal callgraphs are handled. This is done by putting it in front of the normal callgraph and then using the normal callgraph histogram infrastructure to unify them. This way in complex functions we can understand the control flow that lead to a particular sample, and may even see some control flow in the caller for short functions. Example (simplified, of course for such simple code this is usually not needed), please run this after the whole patchkit is in, as at this point in the patch order there is no --branch-history, that will be added in a patch after this one: tcall.c: volatile a = 10000, b = 100000, c; __attribute__((noinline)) f2() { c = a / b; } __attribute__((noinline)) f1() { f2(); f2(); } main() { int i; for (i = 0; i < 1000000; i++) f1(); } % perf record -b -g ./tsrc/tcall [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.044 MB perf.data (~1923 samples) ] % perf report --no-children --branch-history ... 54.91% tcall.c:6 [.] f2 tcall | |--65.53%-- f2 tcall.c:5 | | | |--70.83%-- f1 tcall.c:11 | | f1 tcall.c:10 | | main tcall.c:18 | | main tcall.c:18 | | main tcall.c:17 | | main tcall.c:17 | | f1 tcall.c:13 | | f1 tcall.c:13 | | f2 tcall.c:7 | | f2 tcall.c:5 | | f1 tcall.c:12 | | f1 tcall.c:12 | | f2 tcall.c:7 | | f2 tcall.c:5 | | f1 tcall.c:11 | | | --29.17%-- f1 tcall.c:12 | f1 tcall.c:12 | f2 tcall.c:7 | f2 tcall.c:5 | f1 tcall.c:11 | f1 tcall.c:10 | main tcall.c:18 | main tcall.c:18 | main tcall.c:17 | main tcall.c:17 | f1 tcall.c:13 | f1 tcall.c:13 | f2 tcall.c:7 | f2 tcall.c:5 | f1 tcall.c:12 The default output is unchanged. This is only implemented in perf report, no change to record or anywhere else. This adds the basic code to report: - add a new "branch" option to the -g option parser to enable this mode - when the flag is set include the LBR into the callstack in machine.c. The rest of the history code is unchanged and doesn't know the difference between LBR entry and normal call entry. - detect overlaps with the callchain - remove small loop duplicates in the LBR Current limitations: - The LBR flags (mispredict etc.) are not shown in the history and LBR entries have no special marker. - It would be nice if annotate marked the LBR entries somehow (e.g. with arrows) v2: Various fixes. v3: Merge further patches into this one. Fix white space. v4: Improve manpage. Address review feedback. v5: Rename functions. Better error message without -g. Fix crash without -b. v6: Rebase v7: Rebase. Use NO_ENTRY in memset. v8: Port to latest tip. Move add_callchain_ip to separate patch. Skip initial entries in callchain. Minor cleanups. Signed-off-by: Andi Kleen <ak@linux.intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Link: http://lkml.kernel.org/r/1415844328-4884-3-git-send-email-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2014-11-13 02:05:20 +00:00
show_hist_headers,
branch_callstack,
has_filter,
show_ref_callgraph,
hide_unresolved,
raw_trace,
report_hierarchy;
const char *vmlinux_name,
*kallsyms_name,
*source_prefix,
*field_sep;
const char *default_guest_vmlinux_name,
*default_guest_kallsyms,
*default_guest_modules;
const char *guestmount;
const char *dso_list_str,
*comm_list_str,
*pid_list_str,
*tid_list_str,
*sym_list_str,
*col_width_list_str;
struct strlist *dso_list,
*comm_list,
*sym_list,
*dso_from_list,
*dso_to_list,
*sym_from_list,
*sym_to_list;
struct intlist *pid_list,
*tid_list;
const char *symfs;
};
extern struct symbol_conf symbol_conf;
struct symbol_name_rb_node {
struct rb_node rb_node;
struct symbol sym;
};
static inline int __symbol__join_symfs(char *bf, size_t size, const char *path)
{
return path__join(bf, size, symbol_conf.symfs, path);
}
#define symbol__join_symfs(bf, path) __symbol__join_symfs(bf, sizeof(bf), path)
extern int vmlinux_path__nr_entries;
extern char **vmlinux_path;
static inline void *symbol__priv(struct symbol *sym)
{
return ((void *)sym) - symbol_conf.priv_size;
}
struct ref_reloc_sym {
const char *name;
u64 addr;
u64 unrelocated_addr;
};
struct map_symbol {
struct map *map;
struct symbol *sym;
};
struct addr_map_symbol {
struct map *map;
struct symbol *sym;
u64 addr;
u64 al_addr;
};
struct branch_info {
struct addr_map_symbol from;
struct addr_map_symbol to;
struct branch_flags flags;
perf report: Add srcline_from/to branch sort keys Add "srcline_from" and "srcline_to" branch sort keys that allow to show the source lines of a branch. That makes it much easier to track down where particular branches happen in the program, for example to examine branch mispredictions, or to associate it with cycle counts: % perf record -b -e cycles:p ./tcall % perf report --sort srcline_from,srcline_to,mispredict ... 15.10% tcall.c:18 tcall.c:10 N 14.83% tcall.c:11 tcall.c:5 N 14.12% tcall.c:7 tcall.c:12 N 14.04% tcall.c:12 tcall.c:5 N 12.42% tcall.c:17 tcall.c:18 N 12.39% tcall.c:7 tcall.c:13 N 12.27% tcall.c:13 tcall.c:17 N ... % perf report --sort srcline_from,srcline_to,cycles ... 17.12% tcall.c:18 tcall.c:11 1 17.01% tcall.c:12 tcall.c:6 1 16.98% tcall.c:11 tcall.c:6 1 15.91% tcall.c:17 tcall.c:18 1 6.38% tcall.c:7 tcall.c:17 7 4.80% tcall.c:7 tcall.c:12 8 4.21% tcall.c:7 tcall.c:17 8 2.67% tcall.c:7 tcall.c:12 7 2.62% tcall.c:7 tcall.c:12 10 2.10% tcall.c:7 tcall.c:17 9 1.58% tcall.c:7 tcall.c:12 6 1.44% tcall.c:7 tcall.c:12 5 1.38% tcall.c:7 tcall.c:12 9 1.06% tcall.c:7 tcall.c:17 13 1.05% tcall.c:7 tcall.c:12 4 1.01% tcall.c:7 tcall.c:17 6 Open issues: - Some kernel symbols get misresolved. Signed-off-by: Andi Kleen <ak@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Link: http://lkml.kernel.org/r/1463775308-32748-1-git-send-email-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-05-20 20:15:08 +00:00
char *srcline_from;
char *srcline_to;
};
struct mem_info {
struct addr_map_symbol iaddr;
struct addr_map_symbol daddr;
union perf_mem_data_src data_src;
};
perf tools: Consolidate symbol resolving across all tools Now we have a very high level routine for simple tools to process IP sample events: int event__preprocess_sample(const event_t *self, struct addr_location *al, symbol_filter_t filter) It receives the event itself and will insert new threads in the global threads list and resolve the map and symbol, filling all this info into the new addr_location struct, so that tools like annotate and report can further process the event by creating hist_entries in their specific way (with or without callgraphs, etc). It in turn uses the new next layer function: void thread__find_addr_location(struct thread *self, u8 cpumode, enum map_type type, u64 addr, struct addr_location *al, symbol_filter_t filter) This one will, given a thread (userspace or the kernel kthread one), will find the given type (MAP__FUNCTION now, MAP__VARIABLE too in the near future) at the given cpumode, taking vdsos into account (userspace hit, but kernel symbol) and will fill all these details in the addr_location given. Tools that need a more compact API for plain function resolution, like 'kmem', can use this other one: struct symbol *thread__find_function(struct thread *self, u64 addr, symbol_filter_t filter) So, to resolve a kernel symbol, that is all the 'kmem' tool needs, its just a matter of calling: sym = thread__find_function(kthread, addr, NULL); The 'filter' parameter is needed because we do lazy parsing/loading of ELF symtabs or /proc/kallsyms. With this we remove more code duplication all around, which is always good, huh? :-) Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: John Kacur <jkacur@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> LKML-Reference: <1259346563-12568-12-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-27 18:29:23 +00:00
struct addr_location {
struct machine *machine;
perf tools: Consolidate symbol resolving across all tools Now we have a very high level routine for simple tools to process IP sample events: int event__preprocess_sample(const event_t *self, struct addr_location *al, symbol_filter_t filter) It receives the event itself and will insert new threads in the global threads list and resolve the map and symbol, filling all this info into the new addr_location struct, so that tools like annotate and report can further process the event by creating hist_entries in their specific way (with or without callgraphs, etc). It in turn uses the new next layer function: void thread__find_addr_location(struct thread *self, u8 cpumode, enum map_type type, u64 addr, struct addr_location *al, symbol_filter_t filter) This one will, given a thread (userspace or the kernel kthread one), will find the given type (MAP__FUNCTION now, MAP__VARIABLE too in the near future) at the given cpumode, taking vdsos into account (userspace hit, but kernel symbol) and will fill all these details in the addr_location given. Tools that need a more compact API for plain function resolution, like 'kmem', can use this other one: struct symbol *thread__find_function(struct thread *self, u64 addr, symbol_filter_t filter) So, to resolve a kernel symbol, that is all the 'kmem' tool needs, its just a matter of calling: sym = thread__find_function(kthread, addr, NULL); The 'filter' parameter is needed because we do lazy parsing/loading of ELF symtabs or /proc/kallsyms. With this we remove more code duplication all around, which is always good, huh? :-) Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: John Kacur <jkacur@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> LKML-Reference: <1259346563-12568-12-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-27 18:29:23 +00:00
struct thread *thread;
struct map *map;
struct symbol *sym;
u64 addr;
char level;
u8 filtered;
u8 cpumode;
s32 cpu;
s32 socket;
};
struct symsrc {
char *name;
int fd;
enum dso_binary_type type;
#ifdef HAVE_LIBELF_SUPPORT
Elf *elf;
GElf_Ehdr ehdr;
Elf_Scn *opdsec;
size_t opdidx;
GElf_Shdr opdshdr;
Elf_Scn *symtab;
GElf_Shdr symshdr;
Elf_Scn *dynsym;
size_t dynsym_idx;
GElf_Shdr dynshdr;
bool adjust_symbols;
bool is_64_bit;
#endif
};
void symsrc__destroy(struct symsrc *ss);
int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name,
enum dso_binary_type type);
bool symsrc__has_symtab(struct symsrc *ss);
perf symbols: Use both runtime and debug images We keep both a 'runtime' elf image as well as a 'debug' elf image around and generate symbols by looking at both of these. This eliminates the need for the want_symtab/goto restart mechanism combined with iterating over and reopening the elf images a second time. Also give dso__synthsize_plt_symbols() the runtime image (which has dynsyms) instead of the symbol image (which may only have a symtab and no dynsyms). Previously if a debug image was found all runtime images were ignored. This fixes 2 issues: - Symbol resolution to failure on PowerPC systems with debug symbols installed, as the debug images lack a '.opd' section which contains function descriptors. - On all archs, plt synthesis failed when a debug image was loaded and that debug image lacks a dynsym section while a runtime image has a dynsym section. Assumptions: - If a .opd section exists, it is contained in the highest priority image with a dynsym section. - This generally implies that the debug image lacks a dynsym section (ie: it is marked as NO_BITS). Signed-off-by: Cody P Schafer <cody@linux.vnet.ibm.com> Cc: David Hansen <dave@linux.vnet.ibm.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Matt Hellsley <matthltc@us.ibm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com> Link: http://lkml.kernel.org/r/1344637382-22789-17-git-send-email-cody@linux.vnet.ibm.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-08-10 22:23:02 +00:00
bool symsrc__possibly_runtime(struct symsrc *ss);
int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter);
int dso__load_vmlinux(struct dso *dso, struct map *map,
const char *vmlinux, bool vmlinux_allocated,
symbol_filter_t filter);
int dso__load_vmlinux_path(struct dso *dso, struct map *map,
symbol_filter_t filter);
int __dso__load_kallsyms(struct dso *dso, const char *filename, struct map *map,
bool no_kcore, symbol_filter_t filter);
int dso__load_kallsyms(struct dso *dso, const char *filename, struct map *map,
symbol_filter_t filter);
void dso__insert_symbol(struct dso *dso, enum map_type type,
struct symbol *sym);
struct symbol *dso__find_symbol(struct dso *dso, enum map_type type,
u64 addr);
struct symbol *dso__find_symbol_by_name(struct dso *dso, enum map_type type,
const char *name);
struct symbol *symbol__next_by_name(struct symbol *sym);
struct symbol *dso__first_symbol(struct dso *dso, enum map_type type);
struct symbol *dso__next_symbol(struct symbol *sym);
enum dso_type dso__type_fd(int fd);
int filename__read_build_id(const char *filename, void *bf, size_t size);
int sysfs__read_build_id(const char *filename, void *bf, size_t size);
int modules__parse(const char *filename, void *arg,
int (*process_module)(void *arg, const char *name,
u64 start));
int filename__read_debuglink(const char *filename, char *debuglink,
size_t size);
struct perf_env;
int symbol__init(struct perf_env *env);
void symbol__exit(void);
void symbol__elf_init(void);
int symbol__annotation_init(void);
struct symbol *symbol__new(u64 start, u64 len, u8 binding, const char *name);
size_t __symbol__fprintf_symname_offs(const struct symbol *sym,
const struct addr_location *al,
bool unknown_as_addr, FILE *fp);
size_t symbol__fprintf_symname_offs(const struct symbol *sym,
const struct addr_location *al, FILE *fp);
size_t __symbol__fprintf_symname(const struct symbol *sym,
const struct addr_location *al,
bool unknown_as_addr, FILE *fp);
size_t symbol__fprintf_symname(const struct symbol *sym, FILE *fp);
size_t symbol__fprintf(struct symbol *sym, FILE *fp);
bool symbol_type__is_a(char symbol_type, enum map_type map_type);
bool symbol__restricted_filename(const char *filename,
const char *restricted_filename);
bool symbol__is_idle(struct symbol *sym);
int symbol__config_symfs(const struct option *opt __maybe_unused,
const char *dir, int unset __maybe_unused);
int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss,
struct symsrc *runtime_ss, symbol_filter_t filter,
int kmodule);
int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss,
struct map *map, symbol_filter_t filter);
void symbols__insert(struct rb_root *symbols, struct symbol *sym);
void symbols__fixup_duplicate(struct rb_root *symbols);
void symbols__fixup_end(struct rb_root *symbols);
void __map_groups__fixup_end(struct map_groups *mg, enum map_type type);
typedef int (*mapfn_t)(u64 start, u64 len, u64 pgoff, void *data);
int file__read_maps(int fd, bool exe, mapfn_t mapfn, void *data,
bool *is_64_bit);
#define PERF_KCORE_EXTRACT "/tmp/perf-kcore-XXXXXX"
struct kcore_extract {
char *kcore_filename;
u64 addr;
u64 offs;
u64 len;
char extract_filename[sizeof(PERF_KCORE_EXTRACT)];
int fd;
};
int kcore_extract__create(struct kcore_extract *kce);
void kcore_extract__delete(struct kcore_extract *kce);
perf buildid-cache: Add ability to add kcore to the cache kcore can be used to view the running kernel object code. However, kcore changes as modules are loaded and unloaded, and when the kernel decides to modify its own code. Consequently it is useful to create a copy of kcore at a particular time. Unlike vmlinux, kcore is not unique for a given build-id. And in addition, the kallsyms and modules files are also needed. The tool therefore creates a directory: ~/.debug/[kernel.kcore]/<build-id>/<YYYYmmddHHMMSShh> which contains: kcore, kallsyms and modules. Note that the copied kcore contains only code sections. See the kcore_copy() function for how that is determined. The tool will not make additional copies of kcore if there is already one with the same modules at the same addresses. Currently, perf tools will not look for kcore in the cache. That is addressed in another patch. Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/r/525BF849.5030405@intel.com [ renamed 'index' to 'idx' to avoid shadowing string.h symbol in f12, use at least one member initializer when initializing a struct to zeros, also to fix the build on f12 ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-10-14 13:57:29 +00:00
int kcore_copy(const char *from_dir, const char *to_dir);
int compare_proc_modules(const char *from, const char *to);
int setup_list(struct strlist **list, const char *list_str,
const char *list_name);
int setup_intlist(struct intlist **list, const char *list_str,
const char *list_name);
#ifdef HAVE_LIBELF_SUPPORT
bool elf__needs_adjust_symbols(GElf_Ehdr ehdr);
void arch__sym_update(struct symbol *s, GElf_Sym *sym);
#endif
#define SYMBOL_A 0
#define SYMBOL_B 1
int arch__choose_best_symbol(struct symbol *syma, struct symbol *symb);
perf sdt: ELF support for SDT This patch serves the initial support to identify and list SDT events in binaries. When programs containing SDT markers are compiled, gcc with the help of assembler directives identifies them and places them in the section ".note.stapsdt". To find these markers from the binaries, one needs to traverse through this section and parse the relevant details like the name, type and location of the marker. Also, the original location could be skewed due to the effect of prelinking. If that is the case, the locations need to be adjusted. The functions in this patch open a given ELF, find out the SDT section, parse the relevant details, adjust the location (if necessary) and populate them in a list. A typical note entry in ".note.stapsdt" section is as follows : |--nhdr.n_namesz--| ------------------------------------ | nhdr | "stapsdt" | ----- |----------------------------------| | | <location> <base_address> | | | <semaphore> | nhdr.n_descsize | "provider_name" "note_name" | | | <args> | ----- |----------------------------------| | nhdr | "stapsdt" | |... The above shows an excerpt from the section ".note.stapsdt". 'nhdr' is a structure which has the note name size (n_namesz), note description size (n_desc_sz) and note type (n_type). So, in order to parse the note note info, we need nhdr to tell us where to start from. As can be seen from <sys/sdt.h>, the name of the SDT notes given is "stapsdt". But this is not the identifier of the note. After that, we go to description of the note to find out its location, the address of the ".stapsdt.base" section and the semaphore address. Then, we find the provider name and the SDT marker name and then follow the arguments. Signed-off-by: Hemant Kumar <hemant@linux.vnet.ibm.com> Reviewed-by: Masami Hiramatsu <mhiramat@kernel.org> Acked-by: Namhyung Kim <namhyung@kernel.org> Cc: Ananth N Mavinakayanahalli <ananth@linux.vnet.ibm.com> Cc: Brendan Gregg <brendan.d.gregg@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/146736022628.27797.1201368329092908163.stgit@devbox Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-07-01 08:03:46 +00:00
/* structure containing an SDT note's info */
struct sdt_note {
char *name; /* name of the note*/
char *provider; /* provider name */
bool bit32; /* whether the location is 32 bits? */
union { /* location, base and semaphore addrs */
Elf64_Addr a64[3];
Elf32_Addr a32[3];
} addr;
struct list_head note_list; /* SDT notes' list */
};
int get_sdt_note_list(struct list_head *head, const char *target);
int cleanup_sdt_note_list(struct list_head *sdt_notes);
int sdt_notes__get_count(struct list_head *start);
#define SDT_BASE_SCN ".stapsdt.base"
#define SDT_NOTE_SCN ".note.stapsdt"
#define SDT_NOTE_TYPE 3
#define SDT_NOTE_NAME "stapsdt"
#define NR_ADDR 3
#endif /* __PERF_SYMBOL */