linux/tools/perf/util/symbol.c

2099 lines
47 KiB
C
Raw Normal View History

#include <dirent.h>
#include <errno.h>
#include <stdlib.h>
#include <stdio.h>
#include <string.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <sys/param.h>
#include <fcntl.h>
#include <unistd.h>
#include <inttypes.h>
#include "annotate.h"
perf annotate: Use build-ids to find the right DSO We were still using the pathname found on the MMAP event, that could not be the one we used when recording, so use the build-id cache for that, only falling back to use the pathname in the MMAP event if no build-ids are available. With this we now also are able to do secure, seamless offline annotation. Example: [root@doppio linux-2.6-tip]# perf report -g none -v 2> /dev/null | head -10 8.12% Xorg /usr/lib64/libpixman-1.so.0.14.0 0x0000000000026d02 B [.] pixman_rasterize_edges 4.68% firefox /usr/lib64/xulrunner-1.9.1/libxul.so 0x00000000005dbdba B [.] 0x000000005dbdba 3.70% swapper /lib/modules/2.6.34-rc6/build/vmlinux 0xffffffff81022cea ! [k] read_hpet 2.96% init /lib/modules/2.6.34-rc6/build/vmlinux 0xffffffff81022cea ! [k] read_hpet 2.73% swapper /lib/modules/2.6.34-rc6/build/vmlinux 0xffffffff8100a738 ! [k] mwait_idle_with_hints [root@doppio linux-2.6-tip]# perf annotate -v pixman_rasterize_edges 2>&1 | grep Executing Executing: objdump --start-address=0x000000371ce26670 --stop-address=0x000000371ce2709f -dS /root/.debug/.build-id/bd/6ac5199137aaeb279f864717d8d061477466c1|grep -v /root/.debug/.build-id/bd/6ac5199137aaeb279f864717d8d061477466c1|expand [root@doppio linux-2.6-tip]# perf buildid-list | grep libpixman-1.so.0.14.0 bd6ac5199137aaeb279f864717d8d061477466c1 /usr/lib64/libpixman-1.so.0.14.0 [root@doppio linux-2.6-tip]# Reported-by: Stephane Eranian <eranian@google.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Stephane Eranian <eranian@google.com> Cc: Tom Zanussi <tzanussi@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-05-20 15:15:33 +00:00
#include "build-id.h"
#include "util.h"
#include "debug.h"
#include "machine.h"
#include "symbol.h"
#include "strlist.h"
#include "intlist.h"
perf tools: Check recorded kernel version when finding vmlinux Currently vmlinux_path__init() only tries to find vmlinux file from current directory, /boot and some canonical directories with version number of the running kernel. This can be a problem when reporting old data recorded on a kernel version not running currently. We can use --symfs option for this but it's annoying for user to do it always. As we already have the info in the perf.data file, it can be changed to use it for the search automatically. Before: $ perf report ... # Samples: 4K of event 'cpu-clock' # Event count (approx.): 1067250000 # # Overhead Command Shared Object Symbol # ........ .......... ................. .............................. 71.87% swapper [kernel.kallsyms] [k] recover_probed_instruction After: # Overhead Command Shared Object Symbol # ........ .......... ................. .................... 71.87% swapper [kernel.kallsyms] [k] native_safe_halt This requires to change signature of symbol__init() to receive struct perf_session_env *. Reported-by: Minchan Kim <minchan@kernel.org> 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: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Minchan Kim <minchan@kernel.org> 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/1407825645-24586-14-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2014-08-12 06:40:45 +00:00
#include "header.h"
#include <elf.h>
#include <limits.h>
#include <symbol/kallsyms.h>
perf tools: Rewrite and improve support for kernel modules Representing modules as struct map entries, backed by a DSO, etc, using /proc/modules to find where the module is loaded. DSOs now can have a short and long name, so that in verbose mode we can show exactly which .ko or vmlinux image was used. As kernel modules now are a DSO separate from the kernel, we can ask for just the hits for a particular set of kernel modules, just like we can do with shared libraries: [root@doppio linux-2.6-tip]# perf report -n --vmlinux /home/acme/git/build/tip-recvmmsg/vmlinux --modules --dsos \[drm\] | head -15 84.58% 13266 Xorg [k] drm_clflush_pages 4.02% 630 Xorg [k] trace_kmalloc.clone.0 3.95% 619 Xorg [k] drm_ioctl 2.07% 324 Xorg [k] drm_addbufs 1.68% 263 Xorg [k] drm_gem_close_ioctl 0.77% 120 Xorg [k] drm_setmaster_ioctl 0.70% 110 Xorg [k] drm_lastclose 0.68% 106 Xorg [k] drm_open 0.54% 85 Xorg [k] drm_mm_search_free [root@doppio linux-2.6-tip]# Specifying --dsos /lib/modules/2.6.31-tip/kernel/drivers/gpu/drm/drm.ko would have the same effect. Allowing specifying just 'drm.ko' is left for another patch. Processing kallsyms so that per kernel module struct map are instantiated was also left for another patch. That will allow removing the module name from each of its symbols. struct symbol was reduced by removing the ->module backpointer and moving it (well now the map) to struct symbol_entry in perf top, that is its only user right now. The total linecount went down by ~500 lines. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Avi Kivity <avi@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-02 06:29:58 +00:00
#include <sys/utsname.h>
static int dso__load_kernel_sym(struct dso *dso, struct map *map);
static int dso__load_guest_kernel_sym(struct dso *dso, struct map *map);
static bool symbol__is_idle(const char *name);
int vmlinux_path__nr_entries;
char **vmlinux_path;
perf tools: Rewrite and improve support for kernel modules Representing modules as struct map entries, backed by a DSO, etc, using /proc/modules to find where the module is loaded. DSOs now can have a short and long name, so that in verbose mode we can show exactly which .ko or vmlinux image was used. As kernel modules now are a DSO separate from the kernel, we can ask for just the hits for a particular set of kernel modules, just like we can do with shared libraries: [root@doppio linux-2.6-tip]# perf report -n --vmlinux /home/acme/git/build/tip-recvmmsg/vmlinux --modules --dsos \[drm\] | head -15 84.58% 13266 Xorg [k] drm_clflush_pages 4.02% 630 Xorg [k] trace_kmalloc.clone.0 3.95% 619 Xorg [k] drm_ioctl 2.07% 324 Xorg [k] drm_addbufs 1.68% 263 Xorg [k] drm_gem_close_ioctl 0.77% 120 Xorg [k] drm_setmaster_ioctl 0.70% 110 Xorg [k] drm_lastclose 0.68% 106 Xorg [k] drm_open 0.54% 85 Xorg [k] drm_mm_search_free [root@doppio linux-2.6-tip]# Specifying --dsos /lib/modules/2.6.31-tip/kernel/drivers/gpu/drm/drm.ko would have the same effect. Allowing specifying just 'drm.ko' is left for another patch. Processing kallsyms so that per kernel module struct map are instantiated was also left for another patch. That will allow removing the module name from each of its symbols. struct symbol was reduced by removing the ->module backpointer and moving it (well now the map) to struct symbol_entry in perf top, that is its only user right now. The total linecount went down by ~500 lines. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Avi Kivity <avi@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-02 06:29:58 +00:00
struct symbol_conf symbol_conf = {
.use_modules = true,
.try_vmlinux_path = true,
.annotate_src = true,
.demangle = true,
.demangle_kernel = false,
.cumulate_callchain = true,
.show_hist_headers = true,
.symfs = "",
.event_group = true,
};
static enum dso_binary_type binary_type_symtab[] = {
DSO_BINARY_TYPE__KALLSYMS,
DSO_BINARY_TYPE__GUEST_KALLSYMS,
DSO_BINARY_TYPE__JAVA_JIT,
DSO_BINARY_TYPE__DEBUGLINK,
DSO_BINARY_TYPE__BUILD_ID_CACHE,
DSO_BINARY_TYPE__FEDORA_DEBUGINFO,
DSO_BINARY_TYPE__UBUNTU_DEBUGINFO,
DSO_BINARY_TYPE__BUILDID_DEBUGINFO,
DSO_BINARY_TYPE__SYSTEM_PATH_DSO,
DSO_BINARY_TYPE__GUEST_KMODULE,
DSO_BINARY_TYPE__GUEST_KMODULE_COMP,
DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE,
DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP,
DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO,
DSO_BINARY_TYPE__NOT_FOUND,
};
#define DSO_BINARY_TYPE__SYMTAB_CNT ARRAY_SIZE(binary_type_symtab)
bool symbol_type__is_a(char symbol_type, enum map_type map_type)
{
symbol_type = toupper(symbol_type);
switch (map_type) {
case MAP__FUNCTION:
return symbol_type == 'T' || symbol_type == 'W';
perf symbols: Add support for 'variable' symtabs Example: { u64 addr = strtoull(sym_filter, NULL, 16); struct map *map = map_groups__find(kmaps, MAP__VARIABLE, addr); if (map == NULL) pr_err("couldn't find map!\n"); else { struct symbol *sym = map__find_symbol(map, addr, NULL); if (sym == NULL) pr_err("couldn't find addr!\n"); else pr_info("addr %#Lx is in %s global var\n", addr, sym->name); } exit(0); } Added just after symbol__init() call in 'perf top', then: { u64 addr = strtoull(sym_filter, NULL, 16); struct map *map = map_groups__find(kmaps, MAP__VARIABLE, addr); if (map == NULL) pr_err("couldn't find map!\n"); else { struct symbol *sym = map__find_symbol(map, addr, NULL); if (sym == NULL) pr_err("couldn't find addr!\n"); else pr_info("addr %#Lx is in %s global var\n", addr, sym->name); } exit(0); } [root@doppio linux-2.6-tip]# grep ' [dD] ' /proc/kallsyms | grep ' sched' ffffffff817827d8 d sched_nr_latency ffffffff81782ce0 d sched_domains_mutex ffffffff8178c070 d schedstr.22423 ffffffff817909a0 d sched_register_mutex ffffffff81823490 d sched_feat_names ffffffff81823558 d scheduler_running ffffffff818235b8 d sched_clock_running ffffffff818235bc D sched_clock_stable ffffffff81824f00 d sched_switch_trace [root@doppio linux-2.6-tip]# perf top -s 0xffffffff817827d9 addr 0xffffffff817827d9 is in sched_nr_latency global var [root@doppio linux-2.6-tip]# perf top -s ffffffff81782ce0 addr 0xffffffff81782ce0 is in sched_domains_mutex global var [root@doppio linux-2.6-tip]# [root@doppio linux-2.6-tip]# perf top -s ffffffff81782ce0 --vmlinux OFF The file OFF cannot be used, trying to use /proc/kallsyms...addr 0xffffffff81782ce0 is in sched_domains_mutex global var [root@doppio linux-2.6-tip]# perf top -s ffffffff818235bc --vmlinux OFF The file OFF cannot be used, trying to use /proc/kallsyms...addr 0xffffffff818235bc is in sched_clock_stable global var [root@doppio linux-2.6-tip]# So it works with both /proc/kallsyms and with ELF symtabs, either the one on the vmlinux explicitely passed via --vmlinux or in one in the vmlinux_path that matches the buildid for the running kernel or the one found in the buildid header section in a perf.data file. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> LKML-Reference: <1260550239-5372-4-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-11 16:50:39 +00:00
case MAP__VARIABLE:
return symbol_type == 'D';
default:
return false;
}
}
static int prefix_underscores_count(const char *str)
{
const char *tail = str;
while (*tail == '_')
tail++;
return tail - str;
}
int __weak arch__choose_best_symbol(struct symbol *syma,
struct symbol *symb __maybe_unused)
{
/* Avoid "SyS" kernel syscall aliases */
if (strlen(syma->name) >= 3 && !strncmp(syma->name, "SyS", 3))
return SYMBOL_B;
if (strlen(syma->name) >= 10 && !strncmp(syma->name, "compat_SyS", 10))
return SYMBOL_B;
return SYMBOL_A;
}
static int choose_best_symbol(struct symbol *syma, struct symbol *symb)
{
s64 a;
s64 b;
size_t na, nb;
/* Prefer a symbol with non zero length */
a = syma->end - syma->start;
b = symb->end - symb->start;
if ((b == 0) && (a > 0))
return SYMBOL_A;
else if ((a == 0) && (b > 0))
return SYMBOL_B;
/* Prefer a non weak symbol over a weak one */
a = syma->binding == STB_WEAK;
b = symb->binding == STB_WEAK;
if (b && !a)
return SYMBOL_A;
if (a && !b)
return SYMBOL_B;
/* Prefer a global symbol over a non global one */
a = syma->binding == STB_GLOBAL;
b = symb->binding == STB_GLOBAL;
if (a && !b)
return SYMBOL_A;
if (b && !a)
return SYMBOL_B;
/* Prefer a symbol with less underscores */
a = prefix_underscores_count(syma->name);
b = prefix_underscores_count(symb->name);
if (b > a)
return SYMBOL_A;
else if (a > b)
return SYMBOL_B;
/* Choose the symbol with the longest name */
na = strlen(syma->name);
nb = strlen(symb->name);
if (na > nb)
return SYMBOL_A;
else if (na < nb)
return SYMBOL_B;
return arch__choose_best_symbol(syma, symb);
}
void symbols__fixup_duplicate(struct rb_root *symbols)
{
struct rb_node *nd;
struct symbol *curr, *next;
if (symbol_conf.allow_aliases)
return;
nd = rb_first(symbols);
while (nd) {
curr = rb_entry(nd, struct symbol, rb_node);
again:
nd = rb_next(&curr->rb_node);
next = rb_entry(nd, struct symbol, rb_node);
if (!nd)
break;
if (curr->start != next->start)
continue;
if (choose_best_symbol(curr, next) == SYMBOL_A) {
rb_erase(&next->rb_node, symbols);
symbol__delete(next);
goto again;
} else {
nd = rb_next(&curr->rb_node);
rb_erase(&curr->rb_node, symbols);
symbol__delete(curr);
}
}
}
void symbols__fixup_end(struct rb_root *symbols)
{
struct rb_node *nd, *prevnd = rb_first(symbols);
perf tools: Improve kernel/modules symbol lookup This removes the ovelapping of vmlinux addresses with modules, using the ELF section name when using --vmlinux and creating a unique DSO name when using /proc/kallsyms ([kernel].N). This is done by creating multiple 'struct map' instances for address ranges backed by DSOs that have just the symbols for that range and a name that is derived from the ELF section name.o Now it is possible to ask for just the symbols in some particular kernel section: $ perf report -m --vmlinux ../build/tip-recvmmsg/vmlinux \ --dsos [kernel].vsyscall_fn | head -15 52.73% Xorg [.] vread_hpet 18.61% firefox [.] vread_hpet 14.50% npviewer.bin [.] vread_hpet 6.83% compiz [.] vread_hpet 5.73% glxgears [.] vread_hpet 0.63% java [.] vread_hpet 0.30% gnome-terminal [.] vread_hpet 0.23% perf [.] vread_hpet 0.18% xchat [.] vread_hpet $ Now we don't have to first lookup the list of modules and then, if it fails, vmlinux symbols, its just a simple lookup for the map then the symbols, just like for threads. Reports generated using /proc/kallsyms and --vmlinux should provide the same results, modulo the DSO name for sections other than ".text". But they don't right now because things like: ffffffff81011c20-ffffffff81012068 system_call ffffffff81011c30-ffffffff81011c9b system_call_after_swapgs ffffffff81011c9c-ffffffff81011cb6 system_call_fastpath ffffffff81011cb7-ffffffff81011cbb ret_from_sys_call I.e. overlapping symbols, again some ASM special case that we have to fixup. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <1254934136-8503-1-git-send-email-acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-07 16:48:56 +00:00
struct symbol *curr, *prev;
if (prevnd == NULL)
return;
perf tools: Improve kernel/modules symbol lookup This removes the ovelapping of vmlinux addresses with modules, using the ELF section name when using --vmlinux and creating a unique DSO name when using /proc/kallsyms ([kernel].N). This is done by creating multiple 'struct map' instances for address ranges backed by DSOs that have just the symbols for that range and a name that is derived from the ELF section name.o Now it is possible to ask for just the symbols in some particular kernel section: $ perf report -m --vmlinux ../build/tip-recvmmsg/vmlinux \ --dsos [kernel].vsyscall_fn | head -15 52.73% Xorg [.] vread_hpet 18.61% firefox [.] vread_hpet 14.50% npviewer.bin [.] vread_hpet 6.83% compiz [.] vread_hpet 5.73% glxgears [.] vread_hpet 0.63% java [.] vread_hpet 0.30% gnome-terminal [.] vread_hpet 0.23% perf [.] vread_hpet 0.18% xchat [.] vread_hpet $ Now we don't have to first lookup the list of modules and then, if it fails, vmlinux symbols, its just a simple lookup for the map then the symbols, just like for threads. Reports generated using /proc/kallsyms and --vmlinux should provide the same results, modulo the DSO name for sections other than ".text". But they don't right now because things like: ffffffff81011c20-ffffffff81012068 system_call ffffffff81011c30-ffffffff81011c9b system_call_after_swapgs ffffffff81011c9c-ffffffff81011cb6 system_call_fastpath ffffffff81011cb7-ffffffff81011cbb ret_from_sys_call I.e. overlapping symbols, again some ASM special case that we have to fixup. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <1254934136-8503-1-git-send-email-acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-07 16:48:56 +00:00
curr = rb_entry(prevnd, struct symbol, rb_node);
for (nd = rb_next(prevnd); nd; nd = rb_next(nd)) {
perf tools: Improve kernel/modules symbol lookup This removes the ovelapping of vmlinux addresses with modules, using the ELF section name when using --vmlinux and creating a unique DSO name when using /proc/kallsyms ([kernel].N). This is done by creating multiple 'struct map' instances for address ranges backed by DSOs that have just the symbols for that range and a name that is derived from the ELF section name.o Now it is possible to ask for just the symbols in some particular kernel section: $ perf report -m --vmlinux ../build/tip-recvmmsg/vmlinux \ --dsos [kernel].vsyscall_fn | head -15 52.73% Xorg [.] vread_hpet 18.61% firefox [.] vread_hpet 14.50% npviewer.bin [.] vread_hpet 6.83% compiz [.] vread_hpet 5.73% glxgears [.] vread_hpet 0.63% java [.] vread_hpet 0.30% gnome-terminal [.] vread_hpet 0.23% perf [.] vread_hpet 0.18% xchat [.] vread_hpet $ Now we don't have to first lookup the list of modules and then, if it fails, vmlinux symbols, its just a simple lookup for the map then the symbols, just like for threads. Reports generated using /proc/kallsyms and --vmlinux should provide the same results, modulo the DSO name for sections other than ".text". But they don't right now because things like: ffffffff81011c20-ffffffff81012068 system_call ffffffff81011c30-ffffffff81011c9b system_call_after_swapgs ffffffff81011c9c-ffffffff81011cb6 system_call_fastpath ffffffff81011cb7-ffffffff81011cbb ret_from_sys_call I.e. overlapping symbols, again some ASM special case that we have to fixup. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <1254934136-8503-1-git-send-email-acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-07 16:48:56 +00:00
prev = curr;
curr = rb_entry(nd, struct symbol, rb_node);
if (prev->end == prev->start && prev->end != curr->start)
prev->end = curr->start;
}
perf tools: Improve kernel/modules symbol lookup This removes the ovelapping of vmlinux addresses with modules, using the ELF section name when using --vmlinux and creating a unique DSO name when using /proc/kallsyms ([kernel].N). This is done by creating multiple 'struct map' instances for address ranges backed by DSOs that have just the symbols for that range and a name that is derived from the ELF section name.o Now it is possible to ask for just the symbols in some particular kernel section: $ perf report -m --vmlinux ../build/tip-recvmmsg/vmlinux \ --dsos [kernel].vsyscall_fn | head -15 52.73% Xorg [.] vread_hpet 18.61% firefox [.] vread_hpet 14.50% npviewer.bin [.] vread_hpet 6.83% compiz [.] vread_hpet 5.73% glxgears [.] vread_hpet 0.63% java [.] vread_hpet 0.30% gnome-terminal [.] vread_hpet 0.23% perf [.] vread_hpet 0.18% xchat [.] vread_hpet $ Now we don't have to first lookup the list of modules and then, if it fails, vmlinux symbols, its just a simple lookup for the map then the symbols, just like for threads. Reports generated using /proc/kallsyms and --vmlinux should provide the same results, modulo the DSO name for sections other than ".text". But they don't right now because things like: ffffffff81011c20-ffffffff81012068 system_call ffffffff81011c30-ffffffff81011c9b system_call_after_swapgs ffffffff81011c9c-ffffffff81011cb6 system_call_fastpath ffffffff81011cb7-ffffffff81011cbb ret_from_sys_call I.e. overlapping symbols, again some ASM special case that we have to fixup. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <1254934136-8503-1-git-send-email-acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-07 16:48:56 +00:00
/* Last entry */
if (curr->end == curr->start)
curr->end = roundup(curr->start, 4096);
}
void __map_groups__fixup_end(struct map_groups *mg, enum map_type type)
{
struct maps *maps = &mg->maps[type];
struct map *next, *curr;
pthread_rwlock_wrlock(&maps->lock);
curr = maps__first(maps);
if (curr == NULL)
goto out_unlock;
for (next = map__next(curr); next; next = map__next(curr)) {
curr->end = next->start;
curr = next;
perf tools: Improve kernel/modules symbol lookup This removes the ovelapping of vmlinux addresses with modules, using the ELF section name when using --vmlinux and creating a unique DSO name when using /proc/kallsyms ([kernel].N). This is done by creating multiple 'struct map' instances for address ranges backed by DSOs that have just the symbols for that range and a name that is derived from the ELF section name.o Now it is possible to ask for just the symbols in some particular kernel section: $ perf report -m --vmlinux ../build/tip-recvmmsg/vmlinux \ --dsos [kernel].vsyscall_fn | head -15 52.73% Xorg [.] vread_hpet 18.61% firefox [.] vread_hpet 14.50% npviewer.bin [.] vread_hpet 6.83% compiz [.] vread_hpet 5.73% glxgears [.] vread_hpet 0.63% java [.] vread_hpet 0.30% gnome-terminal [.] vread_hpet 0.23% perf [.] vread_hpet 0.18% xchat [.] vread_hpet $ Now we don't have to first lookup the list of modules and then, if it fails, vmlinux symbols, its just a simple lookup for the map then the symbols, just like for threads. Reports generated using /proc/kallsyms and --vmlinux should provide the same results, modulo the DSO name for sections other than ".text". But they don't right now because things like: ffffffff81011c20-ffffffff81012068 system_call ffffffff81011c30-ffffffff81011c9b system_call_after_swapgs ffffffff81011c9c-ffffffff81011cb6 system_call_fastpath ffffffff81011cb7-ffffffff81011cbb ret_from_sys_call I.e. overlapping symbols, again some ASM special case that we have to fixup. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <1254934136-8503-1-git-send-email-acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-07 16:48:56 +00:00
}
/*
* We still haven't the actual symbols, so guess the
* last map final address.
*/
curr->end = ~0ULL;
out_unlock:
pthread_rwlock_unlock(&maps->lock);
}
struct symbol *symbol__new(u64 start, u64 len, u8 binding, const char *name)
{
size_t namelen = strlen(name) + 1;
struct symbol *sym = calloc(1, (symbol_conf.priv_size +
sizeof(*sym) + namelen));
if (sym == NULL)
perf_counter tools: Add 'perf annotate' feature Add new perf sub-command to display annotated source code: $ perf annotate decode_tree_entry ------------------------------------------------ Percent | Source code & Disassembly of /home/mingo/git/git ------------------------------------------------ : : /home/mingo/git/git: file format elf64-x86-64 : : : Disassembly of section .text: : : 00000000004a0da0 <decode_tree_entry>: : *modep = mode; : return str; : } : : static void decode_tree_entry(struct tree_desc *desc, const char *buf, unsigned long size) : { 3.82 : 4a0da0: 41 54 push %r12 : const char *path; : unsigned int mode, len; : : if (size < 24 || buf[size - 21]) 0.17 : 4a0da2: 48 83 fa 17 cmp $0x17,%rdx : *modep = mode; : return str; : } : : static void decode_tree_entry(struct tree_desc *desc, const char *buf, unsigned long size) : { 0.00 : 4a0da6: 49 89 fc mov %rdi,%r12 0.00 : 4a0da9: 55 push %rbp 3.37 : 4a0daa: 53 push %rbx : const char *path; : unsigned int mode, len; : : if (size < 24 || buf[size - 21]) 0.08 : 4a0dab: 76 73 jbe 4a0e20 <decode_tree_entry+0x80> 0.00 : 4a0dad: 80 7c 16 eb 00 cmpb $0x0,-0x15(%rsi,%rdx,1) 3.48 : 4a0db2: 75 6c jne 4a0e20 <decode_tree_entry+0x80> : static const char *get_mode(const char *str, unsigned int *modep) : { : unsigned char c; : unsigned int mode = 0; : : if (*str == ' ') 1.94 : 4a0db4: 0f b6 06 movzbl (%rsi),%eax 0.39 : 4a0db7: 3c 20 cmp $0x20,%al 0.00 : 4a0db9: 74 65 je 4a0e20 <decode_tree_entry+0x80> : return NULL; : : while ((c = *str++) != ' ') { 0.06 : 4a0dbb: 89 c2 mov %eax,%edx : if (c < '0' || c > '7') 1.99 : 4a0dbd: 31 ed xor %ebp,%ebp : unsigned int mode = 0; : : if (*str == ' ') : return NULL; : : while ((c = *str++) != ' ') { 1.74 : 4a0dbf: 48 8d 5e 01 lea 0x1(%rsi),%rbx : if (c < '0' || c > '7') 0.00 : 4a0dc3: 8d 42 d0 lea -0x30(%rdx),%eax 0.17 : 4a0dc6: 3c 07 cmp $0x7,%al 0.00 : 4a0dc8: 76 0d jbe 4a0dd7 <decode_tree_entry+0x37> 0.00 : 4a0dca: eb 54 jmp 4a0e20 <decode_tree_entry+0x80> 0.00 : 4a0dcc: 0f 1f 40 00 nopl 0x0(%rax) 16.57 : 4a0dd0: 8d 42 d0 lea -0x30(%rdx),%eax 0.14 : 4a0dd3: 3c 07 cmp $0x7,%al 0.00 : 4a0dd5: 77 49 ja 4a0e20 <decode_tree_entry+0x80> : return NULL; : mode = (mode << 3) + (c - '0'); 3.12 : 4a0dd7: 0f b6 c2 movzbl %dl,%eax : unsigned int mode = 0; : : if (*str == ' ') : return NULL; : : while ((c = *str++) != ' ') { 0.00 : 4a0dda: 0f b6 13 movzbl (%rbx),%edx 16.74 : 4a0ddd: 48 83 c3 01 add $0x1,%rbx : if (c < '0' || c > '7') : return NULL; : mode = (mode << 3) + (c - '0'); The first column is the percentage of samples that arrived on that particular line - relative to the total cost of the function. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-06 13:48:52 +00:00
return NULL;
if (symbol_conf.priv_size) {
if (symbol_conf.init_annotation) {
struct annotation *notes = (void *)sym;
pthread_mutex_init(&notes->lock, NULL);
}
sym = ((void *)sym) + symbol_conf.priv_size;
}
sym->start = start;
sym->end = len ? start + len : start;
sym->binding = binding;
sym->namelen = namelen - 1;
pr_debug4("%s: %s %#" PRIx64 "-%#" PRIx64 "\n",
__func__, name, start, sym->end);
memcpy(sym->name, name, namelen);
return sym;
}
void symbol__delete(struct symbol *sym)
{
free(((void *)sym) - symbol_conf.priv_size);
}
void symbols__delete(struct rb_root *symbols)
{
struct symbol *pos;
struct rb_node *next = rb_first(symbols);
while (next) {
pos = rb_entry(next, struct symbol, rb_node);
next = rb_next(&pos->rb_node);
rb_erase(&pos->rb_node, symbols);
symbol__delete(pos);
}
}
void __symbols__insert(struct rb_root *symbols, struct symbol *sym, bool kernel)
{
struct rb_node **p = &symbols->rb_node;
struct rb_node *parent = NULL;
const u64 ip = sym->start;
struct symbol *s;
if (kernel) {
const char *name = sym->name;
/*
* ppc64 uses function descriptors and appends a '.' to the
* start of every instruction address. Remove it.
*/
if (name[0] == '.')
name++;
sym->idle = symbol__is_idle(name);
}
while (*p != NULL) {
parent = *p;
s = rb_entry(parent, struct symbol, rb_node);
if (ip < s->start)
p = &(*p)->rb_left;
else
p = &(*p)->rb_right;
}
rb_link_node(&sym->rb_node, parent, p);
rb_insert_color(&sym->rb_node, symbols);
}
void symbols__insert(struct rb_root *symbols, struct symbol *sym)
{
__symbols__insert(symbols, sym, false);
}
static struct symbol *symbols__find(struct rb_root *symbols, u64 ip)
{
struct rb_node *n;
if (symbols == NULL)
return NULL;
n = symbols->rb_node;
while (n) {
struct symbol *s = rb_entry(n, struct symbol, rb_node);
if (ip < s->start)
n = n->rb_left;
perf symbols: Fix handling of zero-length symbols. This change introduces a fix to symbols__find, so that it is able to find symbols of length zero (where start == end). The current code has the following problem: - The current implementation of symbols__find is unable to find any symbols of length zero. - The db-export framework explicitly creates zero length symbols at locations where no symbol currently exists. The combination of the two above behaviors results in behavior similar to the example below. 1. addr_location is created for a sample, but symbol is unable to be resolved. 2. db export creates an "unknown" symbol of length zero at that address and inserts it into the dso. 3. A new sample comes in at the same address, but symbol__find is unable to find the zero length symbol, so it is still unresolved. 4. db export sees the symbol is unresolved, and allocated a duplicate symbol, even though it already did this in step 2. This behavior continues every time an address without symbol information is seen, which causes a very large number of these symbols to be allocated. The effect of this fix can be observed by looking at the contents of an exported database before/after the fix (generated with scripts/python/export-to-postgresql.py) Ex. BEFORE THE CHANGE: example_db=# select count(*) from symbols; count -------- 900213 (1 row) example_db=# select count(*) from symbols where symbols.name='unknown'; count -------- 897355 (1 row) example_db=# select count(*) from symbols where symbols.name!='unknown'; count ------- 2858 (1 row) AFTER THE CHANGE: example_db=# select count(*) from symbols; count ------- 25217 (1 row) example_db=# select count(*) from symbols where name='unknown'; count ------- 22359 (1 row) example_db=# select count(*) from symbols where name!='unknown'; count ------- 2858 (1 row) Signed-off-by: Chris Phlipot <cphlipot0@gmail.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1462612620-25008-1-git-send-email-cphlipot0@gmail.com [ Moved the test to later in the rb_tree tests, as this not the likely case ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-05-07 09:16:59 +00:00
else if (ip > s->end || (ip == s->end && ip != s->start))
n = n->rb_right;
else
return s;
}
return NULL;
}
static struct symbol *symbols__first(struct rb_root *symbols)
{
struct rb_node *n = rb_first(symbols);
if (n)
return rb_entry(n, struct symbol, rb_node);
return NULL;
}
static struct symbol *symbols__last(struct rb_root *symbols)
{
struct rb_node *n = rb_last(symbols);
if (n)
return rb_entry(n, struct symbol, rb_node);
return NULL;
}
static struct symbol *symbols__next(struct symbol *sym)
{
struct rb_node *n = rb_next(&sym->rb_node);
if (n)
return rb_entry(n, struct symbol, rb_node);
return NULL;
}
static void symbols__insert_by_name(struct rb_root *symbols, struct symbol *sym)
{
struct rb_node **p = &symbols->rb_node;
struct rb_node *parent = NULL;
struct symbol_name_rb_node *symn, *s;
symn = container_of(sym, struct symbol_name_rb_node, sym);
while (*p != NULL) {
parent = *p;
s = rb_entry(parent, struct symbol_name_rb_node, rb_node);
if (strcmp(sym->name, s->sym.name) < 0)
p = &(*p)->rb_left;
else
p = &(*p)->rb_right;
}
rb_link_node(&symn->rb_node, parent, p);
rb_insert_color(&symn->rb_node, symbols);
}
static void symbols__sort_by_name(struct rb_root *symbols,
struct rb_root *source)
{
struct rb_node *nd;
for (nd = rb_first(source); nd; nd = rb_next(nd)) {
struct symbol *pos = rb_entry(nd, struct symbol, rb_node);
symbols__insert_by_name(symbols, pos);
}
}
static struct symbol *symbols__find_by_name(struct rb_root *symbols,
const char *name)
{
struct rb_node *n;
struct symbol_name_rb_node *s = NULL;
if (symbols == NULL)
return NULL;
n = symbols->rb_node;
while (n) {
int cmp;
s = rb_entry(n, struct symbol_name_rb_node, rb_node);
cmp = arch__compare_symbol_names(name, s->sym.name);
if (cmp < 0)
n = n->rb_left;
else if (cmp > 0)
n = n->rb_right;
else
break;
}
if (n == NULL)
return NULL;
/* return first symbol that has same name (if any) */
for (n = rb_prev(n); n; n = rb_prev(n)) {
struct symbol_name_rb_node *tmp;
tmp = rb_entry(n, struct symbol_name_rb_node, rb_node);
if (arch__compare_symbol_names(tmp->sym.name, s->sym.name))
break;
s = tmp;
}
return &s->sym;
}
void dso__reset_find_symbol_cache(struct dso *dso)
{
enum map_type type;
for (type = MAP__FUNCTION; type <= MAP__VARIABLE; ++type) {
dso->last_find_result[type].addr = 0;
dso->last_find_result[type].symbol = NULL;
}
}
void dso__insert_symbol(struct dso *dso, enum map_type type, struct symbol *sym)
{
__symbols__insert(&dso->symbols[type], sym, dso->kernel);
/* update the symbol cache if necessary */
if (dso->last_find_result[type].addr >= sym->start &&
(dso->last_find_result[type].addr < sym->end ||
sym->start == sym->end)) {
dso->last_find_result[type].symbol = sym;
}
}
struct symbol *dso__find_symbol(struct dso *dso,
enum map_type type, u64 addr)
{
if (dso->last_find_result[type].addr != addr) {
dso->last_find_result[type].addr = addr;
dso->last_find_result[type].symbol = symbols__find(&dso->symbols[type], addr);
}
return dso->last_find_result[type].symbol;
}
struct symbol *dso__first_symbol(struct dso *dso, enum map_type type)
{
return symbols__first(&dso->symbols[type]);
}
struct symbol *dso__last_symbol(struct dso *dso, enum map_type type)
{
return symbols__last(&dso->symbols[type]);
}
struct symbol *dso__next_symbol(struct symbol *sym)
{
return symbols__next(sym);
}
struct symbol *symbol__next_by_name(struct symbol *sym)
{
struct symbol_name_rb_node *s = container_of(sym, struct symbol_name_rb_node, sym);
struct rb_node *n = rb_next(&s->rb_node);
return n ? &rb_entry(n, struct symbol_name_rb_node, rb_node)->sym : NULL;
}
/*
* Teturns first symbol that matched with @name.
*/
struct symbol *dso__find_symbol_by_name(struct dso *dso, enum map_type type,
const char *name)
{
return symbols__find_by_name(&dso->symbol_names[type], name);
}
void dso__sort_by_name(struct dso *dso, enum map_type type)
{
dso__set_sorted_by_name(dso, type);
return symbols__sort_by_name(&dso->symbol_names[type],
&dso->symbols[type]);
}
int modules__parse(const char *filename, void *arg,
int (*process_module)(void *arg, const char *name,
u64 start))
{
char *line = NULL;
size_t n;
FILE *file;
int err = 0;
file = fopen(filename, "r");
if (file == NULL)
return -1;
while (1) {
char name[PATH_MAX];
u64 start;
char *sep;
ssize_t line_len;
line_len = getline(&line, &n, file);
if (line_len < 0) {
if (feof(file))
break;
err = -1;
goto out;
}
if (!line) {
err = -1;
goto out;
}
line[--line_len] = '\0'; /* \n */
sep = strrchr(line, 'x');
if (sep == NULL)
continue;
hex2u64(sep + 1, &start);
sep = strchr(line, ' ');
if (sep == NULL)
continue;
*sep = '\0';
scnprintf(name, sizeof(name), "[%s]", line);
err = process_module(arg, name, start);
if (err)
break;
}
out:
free(line);
fclose(file);
return err;
}
struct process_kallsyms_args {
struct map *map;
struct dso *dso;
};
/*
* These are symbols in the kernel image, so make sure that
* sym is from a kernel DSO.
*/
static bool symbol__is_idle(const char *name)
{
const char * const idle_symbols[] = {
"cpu_idle",
"cpu_startup_entry",
"intel_idle",
"default_idle",
"native_safe_halt",
"enter_idle",
"exit_idle",
"mwait_idle",
"mwait_idle_with_hints",
"poll_idle",
"ppc64_runlatch_off",
"pseries_dedicated_idle_sleep",
NULL
};
int i;
for (i = 0; idle_symbols[i]; i++) {
if (!strcmp(idle_symbols[i], name))
return true;
}
return false;
}
static int map__process_kallsym_symbol(void *arg, const char *name,
char type, u64 start)
{
struct symbol *sym;
struct process_kallsyms_args *a = arg;
struct rb_root *root = &a->dso->symbols[a->map->type];
if (!symbol_type__is_a(type, a->map->type))
return 0;
/*
* module symbols are not sorted so we add all
* symbols, setting length to 0, and rely on
* symbols__fixup_end() to fix it up.
*/
sym = symbol__new(start, 0, kallsyms2elf_binding(type), name);
if (sym == NULL)
return -ENOMEM;
/*
* We will pass the symbols to the filter later, in
* map__split_kallsyms, when we have split the maps per module
*/
__symbols__insert(root, sym, !strchr(name, '['));
return 0;
}
/*
* Loads the function entries in /proc/kallsyms into kernel_map->dso,
* so that we can in the next step set the symbol ->end address and then
* call kernel_maps__split_kallsyms.
*/
static int dso__load_all_kallsyms(struct dso *dso, const char *filename,
struct map *map)
{
struct process_kallsyms_args args = { .map = map, .dso = dso, };
return kallsyms__parse(filename, &args, map__process_kallsym_symbol);
}
static int dso__split_kallsyms_for_kcore(struct dso *dso, struct map *map)
{
struct map_groups *kmaps = map__kmaps(map);
struct map *curr_map;
struct symbol *pos;
int count = 0;
struct rb_root old_root = dso->symbols[map->type];
struct rb_root *root = &dso->symbols[map->type];
struct rb_node *next = rb_first(root);
if (!kmaps)
return -1;
*root = RB_ROOT;
while (next) {
char *module;
pos = rb_entry(next, struct symbol, rb_node);
next = rb_next(&pos->rb_node);
rb_erase_init(&pos->rb_node, &old_root);
module = strchr(pos->name, '\t');
if (module)
*module = '\0';
curr_map = map_groups__find(kmaps, map->type, pos->start);
if (!curr_map) {
symbol__delete(pos);
continue;
}
pos->start -= curr_map->start - curr_map->pgoff;
if (pos->end)
pos->end -= curr_map->start - curr_map->pgoff;
symbols__insert(&curr_map->dso->symbols[curr_map->type], pos);
++count;
}
/* Symbols have been adjusted */
dso->adjust_symbols = 1;
return count;
}
perf tools: Improve kernel/modules symbol lookup This removes the ovelapping of vmlinux addresses with modules, using the ELF section name when using --vmlinux and creating a unique DSO name when using /proc/kallsyms ([kernel].N). This is done by creating multiple 'struct map' instances for address ranges backed by DSOs that have just the symbols for that range and a name that is derived from the ELF section name.o Now it is possible to ask for just the symbols in some particular kernel section: $ perf report -m --vmlinux ../build/tip-recvmmsg/vmlinux \ --dsos [kernel].vsyscall_fn | head -15 52.73% Xorg [.] vread_hpet 18.61% firefox [.] vread_hpet 14.50% npviewer.bin [.] vread_hpet 6.83% compiz [.] vread_hpet 5.73% glxgears [.] vread_hpet 0.63% java [.] vread_hpet 0.30% gnome-terminal [.] vread_hpet 0.23% perf [.] vread_hpet 0.18% xchat [.] vread_hpet $ Now we don't have to first lookup the list of modules and then, if it fails, vmlinux symbols, its just a simple lookup for the map then the symbols, just like for threads. Reports generated using /proc/kallsyms and --vmlinux should provide the same results, modulo the DSO name for sections other than ".text". But they don't right now because things like: ffffffff81011c20-ffffffff81012068 system_call ffffffff81011c30-ffffffff81011c9b system_call_after_swapgs ffffffff81011c9c-ffffffff81011cb6 system_call_fastpath ffffffff81011cb7-ffffffff81011cbb ret_from_sys_call I.e. overlapping symbols, again some ASM special case that we have to fixup. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <1254934136-8503-1-git-send-email-acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-07 16:48:56 +00:00
/*
* Split the symbols into maps, making sure there are no overlaps, i.e. the
* kernel range is broken in several maps, named [kernel].N, as we don't have
* the original ELF section names vmlinux have.
*/
static int dso__split_kallsyms(struct dso *dso, struct map *map, u64 delta)
perf tools: Improve kernel/modules symbol lookup This removes the ovelapping of vmlinux addresses with modules, using the ELF section name when using --vmlinux and creating a unique DSO name when using /proc/kallsyms ([kernel].N). This is done by creating multiple 'struct map' instances for address ranges backed by DSOs that have just the symbols for that range and a name that is derived from the ELF section name.o Now it is possible to ask for just the symbols in some particular kernel section: $ perf report -m --vmlinux ../build/tip-recvmmsg/vmlinux \ --dsos [kernel].vsyscall_fn | head -15 52.73% Xorg [.] vread_hpet 18.61% firefox [.] vread_hpet 14.50% npviewer.bin [.] vread_hpet 6.83% compiz [.] vread_hpet 5.73% glxgears [.] vread_hpet 0.63% java [.] vread_hpet 0.30% gnome-terminal [.] vread_hpet 0.23% perf [.] vread_hpet 0.18% xchat [.] vread_hpet $ Now we don't have to first lookup the list of modules and then, if it fails, vmlinux symbols, its just a simple lookup for the map then the symbols, just like for threads. Reports generated using /proc/kallsyms and --vmlinux should provide the same results, modulo the DSO name for sections other than ".text". But they don't right now because things like: ffffffff81011c20-ffffffff81012068 system_call ffffffff81011c30-ffffffff81011c9b system_call_after_swapgs ffffffff81011c9c-ffffffff81011cb6 system_call_fastpath ffffffff81011cb7-ffffffff81011cbb ret_from_sys_call I.e. overlapping symbols, again some ASM special case that we have to fixup. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <1254934136-8503-1-git-send-email-acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-07 16:48:56 +00:00
{
struct map_groups *kmaps = map__kmaps(map);
struct machine *machine;
struct map *curr_map = map;
perf tools: Improve kernel/modules symbol lookup This removes the ovelapping of vmlinux addresses with modules, using the ELF section name when using --vmlinux and creating a unique DSO name when using /proc/kallsyms ([kernel].N). This is done by creating multiple 'struct map' instances for address ranges backed by DSOs that have just the symbols for that range and a name that is derived from the ELF section name.o Now it is possible to ask for just the symbols in some particular kernel section: $ perf report -m --vmlinux ../build/tip-recvmmsg/vmlinux \ --dsos [kernel].vsyscall_fn | head -15 52.73% Xorg [.] vread_hpet 18.61% firefox [.] vread_hpet 14.50% npviewer.bin [.] vread_hpet 6.83% compiz [.] vread_hpet 5.73% glxgears [.] vread_hpet 0.63% java [.] vread_hpet 0.30% gnome-terminal [.] vread_hpet 0.23% perf [.] vread_hpet 0.18% xchat [.] vread_hpet $ Now we don't have to first lookup the list of modules and then, if it fails, vmlinux symbols, its just a simple lookup for the map then the symbols, just like for threads. Reports generated using /proc/kallsyms and --vmlinux should provide the same results, modulo the DSO name for sections other than ".text". But they don't right now because things like: ffffffff81011c20-ffffffff81012068 system_call ffffffff81011c30-ffffffff81011c9b system_call_after_swapgs ffffffff81011c9c-ffffffff81011cb6 system_call_fastpath ffffffff81011cb7-ffffffff81011cbb ret_from_sys_call I.e. overlapping symbols, again some ASM special case that we have to fixup. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <1254934136-8503-1-git-send-email-acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-07 16:48:56 +00:00
struct symbol *pos;
int count = 0, moved = 0;
struct rb_root *root = &dso->symbols[map->type];
struct rb_node *next = rb_first(root);
perf tools: Improve kernel/modules symbol lookup This removes the ovelapping of vmlinux addresses with modules, using the ELF section name when using --vmlinux and creating a unique DSO name when using /proc/kallsyms ([kernel].N). This is done by creating multiple 'struct map' instances for address ranges backed by DSOs that have just the symbols for that range and a name that is derived from the ELF section name.o Now it is possible to ask for just the symbols in some particular kernel section: $ perf report -m --vmlinux ../build/tip-recvmmsg/vmlinux \ --dsos [kernel].vsyscall_fn | head -15 52.73% Xorg [.] vread_hpet 18.61% firefox [.] vread_hpet 14.50% npviewer.bin [.] vread_hpet 6.83% compiz [.] vread_hpet 5.73% glxgears [.] vread_hpet 0.63% java [.] vread_hpet 0.30% gnome-terminal [.] vread_hpet 0.23% perf [.] vread_hpet 0.18% xchat [.] vread_hpet $ Now we don't have to first lookup the list of modules and then, if it fails, vmlinux symbols, its just a simple lookup for the map then the symbols, just like for threads. Reports generated using /proc/kallsyms and --vmlinux should provide the same results, modulo the DSO name for sections other than ".text". But they don't right now because things like: ffffffff81011c20-ffffffff81012068 system_call ffffffff81011c30-ffffffff81011c9b system_call_after_swapgs ffffffff81011c9c-ffffffff81011cb6 system_call_fastpath ffffffff81011cb7-ffffffff81011cbb ret_from_sys_call I.e. overlapping symbols, again some ASM special case that we have to fixup. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <1254934136-8503-1-git-send-email-acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-07 16:48:56 +00:00
int kernel_range = 0;
if (!kmaps)
return -1;
machine = kmaps->machine;
perf tools: Improve kernel/modules symbol lookup This removes the ovelapping of vmlinux addresses with modules, using the ELF section name when using --vmlinux and creating a unique DSO name when using /proc/kallsyms ([kernel].N). This is done by creating multiple 'struct map' instances for address ranges backed by DSOs that have just the symbols for that range and a name that is derived from the ELF section name.o Now it is possible to ask for just the symbols in some particular kernel section: $ perf report -m --vmlinux ../build/tip-recvmmsg/vmlinux \ --dsos [kernel].vsyscall_fn | head -15 52.73% Xorg [.] vread_hpet 18.61% firefox [.] vread_hpet 14.50% npviewer.bin [.] vread_hpet 6.83% compiz [.] vread_hpet 5.73% glxgears [.] vread_hpet 0.63% java [.] vread_hpet 0.30% gnome-terminal [.] vread_hpet 0.23% perf [.] vread_hpet 0.18% xchat [.] vread_hpet $ Now we don't have to first lookup the list of modules and then, if it fails, vmlinux symbols, its just a simple lookup for the map then the symbols, just like for threads. Reports generated using /proc/kallsyms and --vmlinux should provide the same results, modulo the DSO name for sections other than ".text". But they don't right now because things like: ffffffff81011c20-ffffffff81012068 system_call ffffffff81011c30-ffffffff81011c9b system_call_after_swapgs ffffffff81011c9c-ffffffff81011cb6 system_call_fastpath ffffffff81011cb7-ffffffff81011cbb ret_from_sys_call I.e. overlapping symbols, again some ASM special case that we have to fixup. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <1254934136-8503-1-git-send-email-acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-07 16:48:56 +00:00
while (next) {
char *module;
pos = rb_entry(next, struct symbol, rb_node);
next = rb_next(&pos->rb_node);
module = strchr(pos->name, '\t');
if (module) {
if (!symbol_conf.use_modules)
goto discard_symbol;
perf tools: Improve kernel/modules symbol lookup This removes the ovelapping of vmlinux addresses with modules, using the ELF section name when using --vmlinux and creating a unique DSO name when using /proc/kallsyms ([kernel].N). This is done by creating multiple 'struct map' instances for address ranges backed by DSOs that have just the symbols for that range and a name that is derived from the ELF section name.o Now it is possible to ask for just the symbols in some particular kernel section: $ perf report -m --vmlinux ../build/tip-recvmmsg/vmlinux \ --dsos [kernel].vsyscall_fn | head -15 52.73% Xorg [.] vread_hpet 18.61% firefox [.] vread_hpet 14.50% npviewer.bin [.] vread_hpet 6.83% compiz [.] vread_hpet 5.73% glxgears [.] vread_hpet 0.63% java [.] vread_hpet 0.30% gnome-terminal [.] vread_hpet 0.23% perf [.] vread_hpet 0.18% xchat [.] vread_hpet $ Now we don't have to first lookup the list of modules and then, if it fails, vmlinux symbols, its just a simple lookup for the map then the symbols, just like for threads. Reports generated using /proc/kallsyms and --vmlinux should provide the same results, modulo the DSO name for sections other than ".text". But they don't right now because things like: ffffffff81011c20-ffffffff81012068 system_call ffffffff81011c30-ffffffff81011c9b system_call_after_swapgs ffffffff81011c9c-ffffffff81011cb6 system_call_fastpath ffffffff81011cb7-ffffffff81011cbb ret_from_sys_call I.e. overlapping symbols, again some ASM special case that we have to fixup. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <1254934136-8503-1-git-send-email-acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-07 16:48:56 +00:00
*module++ = '\0';
if (strcmp(curr_map->dso->short_name, module)) {
if (curr_map != map &&
dso->kernel == DSO_TYPE_GUEST_KERNEL &&
machine__is_default_guest(machine)) {
/*
* We assume all symbols of a module are
* continuous in * kallsyms, so curr_map
* points to a module and all its
* symbols are in its kmap. Mark it as
* loaded.
*/
dso__set_loaded(curr_map->dso,
curr_map->type);
}
curr_map = map_groups__find_by_name(kmaps,
map->type, module);
if (curr_map == NULL) {
pr_debug("%s/proc/{kallsyms,modules} "
"inconsistency while looking "
"for \"%s\" module!\n",
machine->root_dir, module);
curr_map = map;
goto discard_symbol;
}
if (curr_map->dso->loaded &&
!machine__is_default_guest(machine))
goto discard_symbol;
}
perf tools: Improve kernel/modules symbol lookup This removes the ovelapping of vmlinux addresses with modules, using the ELF section name when using --vmlinux and creating a unique DSO name when using /proc/kallsyms ([kernel].N). This is done by creating multiple 'struct map' instances for address ranges backed by DSOs that have just the symbols for that range and a name that is derived from the ELF section name.o Now it is possible to ask for just the symbols in some particular kernel section: $ perf report -m --vmlinux ../build/tip-recvmmsg/vmlinux \ --dsos [kernel].vsyscall_fn | head -15 52.73% Xorg [.] vread_hpet 18.61% firefox [.] vread_hpet 14.50% npviewer.bin [.] vread_hpet 6.83% compiz [.] vread_hpet 5.73% glxgears [.] vread_hpet 0.63% java [.] vread_hpet 0.30% gnome-terminal [.] vread_hpet 0.23% perf [.] vread_hpet 0.18% xchat [.] vread_hpet $ Now we don't have to first lookup the list of modules and then, if it fails, vmlinux symbols, its just a simple lookup for the map then the symbols, just like for threads. Reports generated using /proc/kallsyms and --vmlinux should provide the same results, modulo the DSO name for sections other than ".text". But they don't right now because things like: ffffffff81011c20-ffffffff81012068 system_call ffffffff81011c30-ffffffff81011c9b system_call_after_swapgs ffffffff81011c9c-ffffffff81011cb6 system_call_fastpath ffffffff81011cb7-ffffffff81011cbb ret_from_sys_call I.e. overlapping symbols, again some ASM special case that we have to fixup. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <1254934136-8503-1-git-send-email-acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-07 16:48:56 +00:00
/*
* So that we look just like we get from .ko files,
* i.e. not prelinked, relative to map->start.
*/
pos->start = curr_map->map_ip(curr_map, pos->start);
pos->end = curr_map->map_ip(curr_map, pos->end);
} else if (curr_map != map) {
perf tools: Improve kernel/modules symbol lookup This removes the ovelapping of vmlinux addresses with modules, using the ELF section name when using --vmlinux and creating a unique DSO name when using /proc/kallsyms ([kernel].N). This is done by creating multiple 'struct map' instances for address ranges backed by DSOs that have just the symbols for that range and a name that is derived from the ELF section name.o Now it is possible to ask for just the symbols in some particular kernel section: $ perf report -m --vmlinux ../build/tip-recvmmsg/vmlinux \ --dsos [kernel].vsyscall_fn | head -15 52.73% Xorg [.] vread_hpet 18.61% firefox [.] vread_hpet 14.50% npviewer.bin [.] vread_hpet 6.83% compiz [.] vread_hpet 5.73% glxgears [.] vread_hpet 0.63% java [.] vread_hpet 0.30% gnome-terminal [.] vread_hpet 0.23% perf [.] vread_hpet 0.18% xchat [.] vread_hpet $ Now we don't have to first lookup the list of modules and then, if it fails, vmlinux symbols, its just a simple lookup for the map then the symbols, just like for threads. Reports generated using /proc/kallsyms and --vmlinux should provide the same results, modulo the DSO name for sections other than ".text". But they don't right now because things like: ffffffff81011c20-ffffffff81012068 system_call ffffffff81011c30-ffffffff81011c9b system_call_after_swapgs ffffffff81011c9c-ffffffff81011cb6 system_call_fastpath ffffffff81011cb7-ffffffff81011cbb ret_from_sys_call I.e. overlapping symbols, again some ASM special case that we have to fixup. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <1254934136-8503-1-git-send-email-acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-07 16:48:56 +00:00
char dso_name[PATH_MAX];
struct dso *ndso;
perf tools: Improve kernel/modules symbol lookup This removes the ovelapping of vmlinux addresses with modules, using the ELF section name when using --vmlinux and creating a unique DSO name when using /proc/kallsyms ([kernel].N). This is done by creating multiple 'struct map' instances for address ranges backed by DSOs that have just the symbols for that range and a name that is derived from the ELF section name.o Now it is possible to ask for just the symbols in some particular kernel section: $ perf report -m --vmlinux ../build/tip-recvmmsg/vmlinux \ --dsos [kernel].vsyscall_fn | head -15 52.73% Xorg [.] vread_hpet 18.61% firefox [.] vread_hpet 14.50% npviewer.bin [.] vread_hpet 6.83% compiz [.] vread_hpet 5.73% glxgears [.] vread_hpet 0.63% java [.] vread_hpet 0.30% gnome-terminal [.] vread_hpet 0.23% perf [.] vread_hpet 0.18% xchat [.] vread_hpet $ Now we don't have to first lookup the list of modules and then, if it fails, vmlinux symbols, its just a simple lookup for the map then the symbols, just like for threads. Reports generated using /proc/kallsyms and --vmlinux should provide the same results, modulo the DSO name for sections other than ".text". But they don't right now because things like: ffffffff81011c20-ffffffff81012068 system_call ffffffff81011c30-ffffffff81011c9b system_call_after_swapgs ffffffff81011c9c-ffffffff81011cb6 system_call_fastpath ffffffff81011cb7-ffffffff81011cbb ret_from_sys_call I.e. overlapping symbols, again some ASM special case that we have to fixup. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <1254934136-8503-1-git-send-email-acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-07 16:48:56 +00:00
if (delta) {
/* Kernel was relocated at boot time */
pos->start -= delta;
pos->end -= delta;
}
if (count == 0) {
curr_map = map;
goto add_symbol;
}
if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
snprintf(dso_name, sizeof(dso_name),
"[guest.kernel].%d",
kernel_range++);
else
snprintf(dso_name, sizeof(dso_name),
"[kernel].%d",
kernel_range++);
perf tools: Improve kernel/modules symbol lookup This removes the ovelapping of vmlinux addresses with modules, using the ELF section name when using --vmlinux and creating a unique DSO name when using /proc/kallsyms ([kernel].N). This is done by creating multiple 'struct map' instances for address ranges backed by DSOs that have just the symbols for that range and a name that is derived from the ELF section name.o Now it is possible to ask for just the symbols in some particular kernel section: $ perf report -m --vmlinux ../build/tip-recvmmsg/vmlinux \ --dsos [kernel].vsyscall_fn | head -15 52.73% Xorg [.] vread_hpet 18.61% firefox [.] vread_hpet 14.50% npviewer.bin [.] vread_hpet 6.83% compiz [.] vread_hpet 5.73% glxgears [.] vread_hpet 0.63% java [.] vread_hpet 0.30% gnome-terminal [.] vread_hpet 0.23% perf [.] vread_hpet 0.18% xchat [.] vread_hpet $ Now we don't have to first lookup the list of modules and then, if it fails, vmlinux symbols, its just a simple lookup for the map then the symbols, just like for threads. Reports generated using /proc/kallsyms and --vmlinux should provide the same results, modulo the DSO name for sections other than ".text". But they don't right now because things like: ffffffff81011c20-ffffffff81012068 system_call ffffffff81011c30-ffffffff81011c9b system_call_after_swapgs ffffffff81011c9c-ffffffff81011cb6 system_call_fastpath ffffffff81011cb7-ffffffff81011cbb ret_from_sys_call I.e. overlapping symbols, again some ASM special case that we have to fixup. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <1254934136-8503-1-git-send-email-acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-07 16:48:56 +00:00
ndso = dso__new(dso_name);
if (ndso == NULL)
perf tools: Improve kernel/modules symbol lookup This removes the ovelapping of vmlinux addresses with modules, using the ELF section name when using --vmlinux and creating a unique DSO name when using /proc/kallsyms ([kernel].N). This is done by creating multiple 'struct map' instances for address ranges backed by DSOs that have just the symbols for that range and a name that is derived from the ELF section name.o Now it is possible to ask for just the symbols in some particular kernel section: $ perf report -m --vmlinux ../build/tip-recvmmsg/vmlinux \ --dsos [kernel].vsyscall_fn | head -15 52.73% Xorg [.] vread_hpet 18.61% firefox [.] vread_hpet 14.50% npviewer.bin [.] vread_hpet 6.83% compiz [.] vread_hpet 5.73% glxgears [.] vread_hpet 0.63% java [.] vread_hpet 0.30% gnome-terminal [.] vread_hpet 0.23% perf [.] vread_hpet 0.18% xchat [.] vread_hpet $ Now we don't have to first lookup the list of modules and then, if it fails, vmlinux symbols, its just a simple lookup for the map then the symbols, just like for threads. Reports generated using /proc/kallsyms and --vmlinux should provide the same results, modulo the DSO name for sections other than ".text". But they don't right now because things like: ffffffff81011c20-ffffffff81012068 system_call ffffffff81011c30-ffffffff81011c9b system_call_after_swapgs ffffffff81011c9c-ffffffff81011cb6 system_call_fastpath ffffffff81011cb7-ffffffff81011cbb ret_from_sys_call I.e. overlapping symbols, again some ASM special case that we have to fixup. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <1254934136-8503-1-git-send-email-acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-07 16:48:56 +00:00
return -1;
ndso->kernel = dso->kernel;
curr_map = map__new2(pos->start, ndso, map->type);
if (curr_map == NULL) {
dso__put(ndso);
perf tools: Improve kernel/modules symbol lookup This removes the ovelapping of vmlinux addresses with modules, using the ELF section name when using --vmlinux and creating a unique DSO name when using /proc/kallsyms ([kernel].N). This is done by creating multiple 'struct map' instances for address ranges backed by DSOs that have just the symbols for that range and a name that is derived from the ELF section name.o Now it is possible to ask for just the symbols in some particular kernel section: $ perf report -m --vmlinux ../build/tip-recvmmsg/vmlinux \ --dsos [kernel].vsyscall_fn | head -15 52.73% Xorg [.] vread_hpet 18.61% firefox [.] vread_hpet 14.50% npviewer.bin [.] vread_hpet 6.83% compiz [.] vread_hpet 5.73% glxgears [.] vread_hpet 0.63% java [.] vread_hpet 0.30% gnome-terminal [.] vread_hpet 0.23% perf [.] vread_hpet 0.18% xchat [.] vread_hpet $ Now we don't have to first lookup the list of modules and then, if it fails, vmlinux symbols, its just a simple lookup for the map then the symbols, just like for threads. Reports generated using /proc/kallsyms and --vmlinux should provide the same results, modulo the DSO name for sections other than ".text". But they don't right now because things like: ffffffff81011c20-ffffffff81012068 system_call ffffffff81011c30-ffffffff81011c9b system_call_after_swapgs ffffffff81011c9c-ffffffff81011cb6 system_call_fastpath ffffffff81011cb7-ffffffff81011cbb ret_from_sys_call I.e. overlapping symbols, again some ASM special case that we have to fixup. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <1254934136-8503-1-git-send-email-acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-07 16:48:56 +00:00
return -1;
}
curr_map->map_ip = curr_map->unmap_ip = identity__map_ip;
map_groups__insert(kmaps, curr_map);
perf tools: Improve kernel/modules symbol lookup This removes the ovelapping of vmlinux addresses with modules, using the ELF section name when using --vmlinux and creating a unique DSO name when using /proc/kallsyms ([kernel].N). This is done by creating multiple 'struct map' instances for address ranges backed by DSOs that have just the symbols for that range and a name that is derived from the ELF section name.o Now it is possible to ask for just the symbols in some particular kernel section: $ perf report -m --vmlinux ../build/tip-recvmmsg/vmlinux \ --dsos [kernel].vsyscall_fn | head -15 52.73% Xorg [.] vread_hpet 18.61% firefox [.] vread_hpet 14.50% npviewer.bin [.] vread_hpet 6.83% compiz [.] vread_hpet 5.73% glxgears [.] vread_hpet 0.63% java [.] vread_hpet 0.30% gnome-terminal [.] vread_hpet 0.23% perf [.] vread_hpet 0.18% xchat [.] vread_hpet $ Now we don't have to first lookup the list of modules and then, if it fails, vmlinux symbols, its just a simple lookup for the map then the symbols, just like for threads. Reports generated using /proc/kallsyms and --vmlinux should provide the same results, modulo the DSO name for sections other than ".text". But they don't right now because things like: ffffffff81011c20-ffffffff81012068 system_call ffffffff81011c30-ffffffff81011c9b system_call_after_swapgs ffffffff81011c9c-ffffffff81011cb6 system_call_fastpath ffffffff81011cb7-ffffffff81011cbb ret_from_sys_call I.e. overlapping symbols, again some ASM special case that we have to fixup. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <1254934136-8503-1-git-send-email-acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-07 16:48:56 +00:00
++kernel_range;
} else if (delta) {
/* Kernel was relocated at boot time */
pos->start -= delta;
pos->end -= delta;
perf tools: Improve kernel/modules symbol lookup This removes the ovelapping of vmlinux addresses with modules, using the ELF section name when using --vmlinux and creating a unique DSO name when using /proc/kallsyms ([kernel].N). This is done by creating multiple 'struct map' instances for address ranges backed by DSOs that have just the symbols for that range and a name that is derived from the ELF section name.o Now it is possible to ask for just the symbols in some particular kernel section: $ perf report -m --vmlinux ../build/tip-recvmmsg/vmlinux \ --dsos [kernel].vsyscall_fn | head -15 52.73% Xorg [.] vread_hpet 18.61% firefox [.] vread_hpet 14.50% npviewer.bin [.] vread_hpet 6.83% compiz [.] vread_hpet 5.73% glxgears [.] vread_hpet 0.63% java [.] vread_hpet 0.30% gnome-terminal [.] vread_hpet 0.23% perf [.] vread_hpet 0.18% xchat [.] vread_hpet $ Now we don't have to first lookup the list of modules and then, if it fails, vmlinux symbols, its just a simple lookup for the map then the symbols, just like for threads. Reports generated using /proc/kallsyms and --vmlinux should provide the same results, modulo the DSO name for sections other than ".text". But they don't right now because things like: ffffffff81011c20-ffffffff81012068 system_call ffffffff81011c30-ffffffff81011c9b system_call_after_swapgs ffffffff81011c9c-ffffffff81011cb6 system_call_fastpath ffffffff81011cb7-ffffffff81011cbb ret_from_sys_call I.e. overlapping symbols, again some ASM special case that we have to fixup. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <1254934136-8503-1-git-send-email-acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-07 16:48:56 +00:00
}
add_symbol:
if (curr_map != map) {
rb_erase(&pos->rb_node, root);
symbols__insert(&curr_map->dso->symbols[curr_map->type], pos);
++moved;
} else
++count;
continue;
discard_symbol:
rb_erase(&pos->rb_node, root);
symbol__delete(pos);
}
if (curr_map != map &&
dso->kernel == DSO_TYPE_GUEST_KERNEL &&
machine__is_default_guest(kmaps->machine)) {
dso__set_loaded(curr_map->dso, curr_map->type);
}
return count + moved;
perf tools: Improve kernel/modules symbol lookup This removes the ovelapping of vmlinux addresses with modules, using the ELF section name when using --vmlinux and creating a unique DSO name when using /proc/kallsyms ([kernel].N). This is done by creating multiple 'struct map' instances for address ranges backed by DSOs that have just the symbols for that range and a name that is derived from the ELF section name.o Now it is possible to ask for just the symbols in some particular kernel section: $ perf report -m --vmlinux ../build/tip-recvmmsg/vmlinux \ --dsos [kernel].vsyscall_fn | head -15 52.73% Xorg [.] vread_hpet 18.61% firefox [.] vread_hpet 14.50% npviewer.bin [.] vread_hpet 6.83% compiz [.] vread_hpet 5.73% glxgears [.] vread_hpet 0.63% java [.] vread_hpet 0.30% gnome-terminal [.] vread_hpet 0.23% perf [.] vread_hpet 0.18% xchat [.] vread_hpet $ Now we don't have to first lookup the list of modules and then, if it fails, vmlinux symbols, its just a simple lookup for the map then the symbols, just like for threads. Reports generated using /proc/kallsyms and --vmlinux should provide the same results, modulo the DSO name for sections other than ".text". But they don't right now because things like: ffffffff81011c20-ffffffff81012068 system_call ffffffff81011c30-ffffffff81011c9b system_call_after_swapgs ffffffff81011c9c-ffffffff81011cb6 system_call_fastpath ffffffff81011cb7-ffffffff81011cbb ret_from_sys_call I.e. overlapping symbols, again some ASM special case that we have to fixup. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <1254934136-8503-1-git-send-email-acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-07 16:48:56 +00:00
}
bool symbol__restricted_filename(const char *filename,
const char *restricted_filename)
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
{
bool restricted = false;
if (symbol_conf.kptr_restrict) {
char *r = realpath(filename, NULL);
if (r != NULL) {
restricted = strcmp(r, restricted_filename) == 0;
free(r);
return restricted;
}
}
return restricted;
}
struct module_info {
struct rb_node rb_node;
char *name;
u64 start;
};
static void add_module(struct module_info *mi, struct rb_root *modules)
{
struct rb_node **p = &modules->rb_node;
struct rb_node *parent = NULL;
struct module_info *m;
while (*p != NULL) {
parent = *p;
m = rb_entry(parent, struct module_info, rb_node);
if (strcmp(mi->name, m->name) < 0)
p = &(*p)->rb_left;
else
p = &(*p)->rb_right;
}
rb_link_node(&mi->rb_node, parent, p);
rb_insert_color(&mi->rb_node, modules);
}
static void delete_modules(struct rb_root *modules)
{
struct module_info *mi;
struct rb_node *next = rb_first(modules);
while (next) {
mi = rb_entry(next, struct module_info, rb_node);
next = rb_next(&mi->rb_node);
rb_erase(&mi->rb_node, modules);
zfree(&mi->name);
free(mi);
}
}
static struct module_info *find_module(const char *name,
struct rb_root *modules)
{
struct rb_node *n = modules->rb_node;
while (n) {
struct module_info *m;
int cmp;
m = rb_entry(n, struct module_info, rb_node);
cmp = strcmp(name, m->name);
if (cmp < 0)
n = n->rb_left;
else if (cmp > 0)
n = n->rb_right;
else
return m;
}
return NULL;
}
static int __read_proc_modules(void *arg, const char *name, u64 start)
{
struct rb_root *modules = arg;
struct module_info *mi;
mi = zalloc(sizeof(struct module_info));
if (!mi)
return -ENOMEM;
mi->name = strdup(name);
mi->start = start;
if (!mi->name) {
free(mi);
return -ENOMEM;
}
add_module(mi, modules);
return 0;
}
static int read_proc_modules(const char *filename, struct rb_root *modules)
{
if (symbol__restricted_filename(filename, "/proc/modules"))
return -1;
if (modules__parse(filename, modules, __read_proc_modules)) {
delete_modules(modules);
return -1;
}
return 0;
}
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 compare_proc_modules(const char *from, const char *to)
{
struct rb_root from_modules = RB_ROOT;
struct rb_root to_modules = RB_ROOT;
struct rb_node *from_node, *to_node;
struct module_info *from_m, *to_m;
int ret = -1;
if (read_proc_modules(from, &from_modules))
return -1;
if (read_proc_modules(to, &to_modules))
goto out_delete_from;
from_node = rb_first(&from_modules);
to_node = rb_first(&to_modules);
while (from_node) {
if (!to_node)
break;
from_m = rb_entry(from_node, struct module_info, rb_node);
to_m = rb_entry(to_node, struct module_info, rb_node);
if (from_m->start != to_m->start ||
strcmp(from_m->name, to_m->name))
break;
from_node = rb_next(from_node);
to_node = rb_next(to_node);
}
if (!from_node && !to_node)
ret = 0;
delete_modules(&to_modules);
out_delete_from:
delete_modules(&from_modules);
return ret;
}
static int do_validate_kcore_modules(const char *filename, struct map *map,
struct map_groups *kmaps)
{
struct rb_root modules = RB_ROOT;
struct map *old_map;
int err;
err = read_proc_modules(filename, &modules);
if (err)
return err;
old_map = map_groups__first(kmaps, map->type);
while (old_map) {
struct map *next = map_groups__next(old_map);
struct module_info *mi;
if (old_map == map || old_map->start == map->start) {
/* The kernel map */
old_map = next;
continue;
}
/* Module must be in memory at the same address */
mi = find_module(old_map->dso->short_name, &modules);
if (!mi || mi->start != old_map->start) {
err = -EINVAL;
goto out;
}
old_map = next;
}
out:
delete_modules(&modules);
return err;
}
/*
* If kallsyms is referenced by name then we look for filename in the same
* directory.
*/
static bool filename_from_kallsyms_filename(char *filename,
const char *base_name,
const char *kallsyms_filename)
{
char *name;
strcpy(filename, kallsyms_filename);
name = strrchr(filename, '/');
if (!name)
return false;
name += 1;
if (!strcmp(name, "kallsyms")) {
strcpy(name, base_name);
return true;
}
return false;
}
static int validate_kcore_modules(const char *kallsyms_filename,
struct map *map)
{
struct map_groups *kmaps = map__kmaps(map);
char modules_filename[PATH_MAX];
if (!kmaps)
return -EINVAL;
if (!filename_from_kallsyms_filename(modules_filename, "modules",
kallsyms_filename))
return -EINVAL;
if (do_validate_kcore_modules(modules_filename, map, kmaps))
return -EINVAL;
return 0;
}
static int validate_kcore_addresses(const char *kallsyms_filename,
struct map *map)
{
struct kmap *kmap = map__kmap(map);
if (!kmap)
return -EINVAL;
if (kmap->ref_reloc_sym && kmap->ref_reloc_sym->name) {
u64 start;
start = kallsyms__get_function_start(kallsyms_filename,
kmap->ref_reloc_sym->name);
if (start != kmap->ref_reloc_sym->addr)
return -EINVAL;
}
return validate_kcore_modules(kallsyms_filename, map);
}
struct kcore_mapfn_data {
struct dso *dso;
enum map_type type;
struct list_head maps;
};
static int kcore_mapfn(u64 start, u64 len, u64 pgoff, void *data)
{
struct kcore_mapfn_data *md = data;
struct map *map;
map = map__new2(start, md->dso, md->type);
if (map == NULL)
return -ENOMEM;
map->end = map->start + len;
map->pgoff = pgoff;
list_add(&map->node, &md->maps);
return 0;
}
static int dso__load_kcore(struct dso *dso, struct map *map,
const char *kallsyms_filename)
{
struct map_groups *kmaps = map__kmaps(map);
struct machine *machine;
struct kcore_mapfn_data md;
struct map *old_map, *new_map, *replacement_map = NULL;
bool is_64_bit;
int err, fd;
char kcore_filename[PATH_MAX];
struct symbol *sym;
if (!kmaps)
return -EINVAL;
machine = kmaps->machine;
/* This function requires that the map is the kernel map */
if (map != machine->vmlinux_maps[map->type])
return -EINVAL;
if (!filename_from_kallsyms_filename(kcore_filename, "kcore",
kallsyms_filename))
return -EINVAL;
/* Modules and kernel must be present at their original addresses */
if (validate_kcore_addresses(kallsyms_filename, map))
return -EINVAL;
md.dso = dso;
md.type = map->type;
INIT_LIST_HEAD(&md.maps);
fd = open(kcore_filename, O_RDONLY);
if (fd < 0) {
pr_debug("Failed to open %s. Note /proc/kcore requires CAP_SYS_RAWIO capability to access.\n",
kcore_filename);
return -EINVAL;
}
/* Read new maps into temporary lists */
err = file__read_maps(fd, md.type == MAP__FUNCTION, kcore_mapfn, &md,
&is_64_bit);
if (err)
goto out_err;
dso->is_64_bit = is_64_bit;
if (list_empty(&md.maps)) {
err = -EINVAL;
goto out_err;
}
/* Remove old maps */
old_map = map_groups__first(kmaps, map->type);
while (old_map) {
struct map *next = map_groups__next(old_map);
if (old_map != map)
map_groups__remove(kmaps, old_map);
old_map = next;
}
/* Find the kernel map using the first symbol */
sym = dso__first_symbol(dso, map->type);
list_for_each_entry(new_map, &md.maps, node) {
if (sym && sym->start >= new_map->start &&
sym->start < new_map->end) {
replacement_map = new_map;
break;
}
}
if (!replacement_map)
replacement_map = list_entry(md.maps.next, struct map, node);
/* Add new maps */
while (!list_empty(&md.maps)) {
new_map = list_entry(md.maps.next, struct map, node);
list_del_init(&new_map->node);
if (new_map == replacement_map) {
map->start = new_map->start;
map->end = new_map->end;
map->pgoff = new_map->pgoff;
map->map_ip = new_map->map_ip;
map->unmap_ip = new_map->unmap_ip;
/* Ensure maps are correctly ordered */
map__get(map);
map_groups__remove(kmaps, map);
map_groups__insert(kmaps, map);
map__put(map);
} else {
map_groups__insert(kmaps, new_map);
}
map__put(new_map);
}
/*
* Set the data type and long name so that kcore can be read via
* dso__data_read_addr().
*/
if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
dso->binary_type = DSO_BINARY_TYPE__GUEST_KCORE;
else
dso->binary_type = DSO_BINARY_TYPE__KCORE;
dso__set_long_name(dso, strdup(kcore_filename), true);
close(fd);
if (map->type == MAP__FUNCTION)
pr_debug("Using %s for kernel object code\n", kcore_filename);
else
pr_debug("Using %s for kernel data\n", kcore_filename);
return 0;
out_err:
while (!list_empty(&md.maps)) {
map = list_entry(md.maps.next, struct map, node);
list_del_init(&map->node);
map__put(map);
}
close(fd);
return -EINVAL;
}
/*
* If the kernel is relocated at boot time, kallsyms won't match. Compute the
* delta based on the relocation reference symbol.
*/
static int kallsyms__delta(struct map *map, const char *filename, u64 *delta)
{
struct kmap *kmap = map__kmap(map);
u64 addr;
if (!kmap)
return -1;
if (!kmap->ref_reloc_sym || !kmap->ref_reloc_sym->name)
return 0;
addr = kallsyms__get_function_start(filename,
kmap->ref_reloc_sym->name);
if (!addr)
return -1;
*delta = addr - kmap->ref_reloc_sym->addr;
return 0;
}
int __dso__load_kallsyms(struct dso *dso, const char *filename,
struct map *map, bool no_kcore)
perf tools: Improve kernel/modules symbol lookup This removes the ovelapping of vmlinux addresses with modules, using the ELF section name when using --vmlinux and creating a unique DSO name when using /proc/kallsyms ([kernel].N). This is done by creating multiple 'struct map' instances for address ranges backed by DSOs that have just the symbols for that range and a name that is derived from the ELF section name.o Now it is possible to ask for just the symbols in some particular kernel section: $ perf report -m --vmlinux ../build/tip-recvmmsg/vmlinux \ --dsos [kernel].vsyscall_fn | head -15 52.73% Xorg [.] vread_hpet 18.61% firefox [.] vread_hpet 14.50% npviewer.bin [.] vread_hpet 6.83% compiz [.] vread_hpet 5.73% glxgears [.] vread_hpet 0.63% java [.] vread_hpet 0.30% gnome-terminal [.] vread_hpet 0.23% perf [.] vread_hpet 0.18% xchat [.] vread_hpet $ Now we don't have to first lookup the list of modules and then, if it fails, vmlinux symbols, its just a simple lookup for the map then the symbols, just like for threads. Reports generated using /proc/kallsyms and --vmlinux should provide the same results, modulo the DSO name for sections other than ".text". But they don't right now because things like: ffffffff81011c20-ffffffff81012068 system_call ffffffff81011c30-ffffffff81011c9b system_call_after_swapgs ffffffff81011c9c-ffffffff81011cb6 system_call_fastpath ffffffff81011cb7-ffffffff81011cbb ret_from_sys_call I.e. overlapping symbols, again some ASM special case that we have to fixup. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <1254934136-8503-1-git-send-email-acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-07 16:48:56 +00:00
{
u64 delta = 0;
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
if (symbol__restricted_filename(filename, "/proc/kallsyms"))
return -1;
if (dso__load_all_kallsyms(dso, filename, map) < 0)
perf tools: Improve kernel/modules symbol lookup This removes the ovelapping of vmlinux addresses with modules, using the ELF section name when using --vmlinux and creating a unique DSO name when using /proc/kallsyms ([kernel].N). This is done by creating multiple 'struct map' instances for address ranges backed by DSOs that have just the symbols for that range and a name that is derived from the ELF section name.o Now it is possible to ask for just the symbols in some particular kernel section: $ perf report -m --vmlinux ../build/tip-recvmmsg/vmlinux \ --dsos [kernel].vsyscall_fn | head -15 52.73% Xorg [.] vread_hpet 18.61% firefox [.] vread_hpet 14.50% npviewer.bin [.] vread_hpet 6.83% compiz [.] vread_hpet 5.73% glxgears [.] vread_hpet 0.63% java [.] vread_hpet 0.30% gnome-terminal [.] vread_hpet 0.23% perf [.] vread_hpet 0.18% xchat [.] vread_hpet $ Now we don't have to first lookup the list of modules and then, if it fails, vmlinux symbols, its just a simple lookup for the map then the symbols, just like for threads. Reports generated using /proc/kallsyms and --vmlinux should provide the same results, modulo the DSO name for sections other than ".text". But they don't right now because things like: ffffffff81011c20-ffffffff81012068 system_call ffffffff81011c30-ffffffff81011c9b system_call_after_swapgs ffffffff81011c9c-ffffffff81011cb6 system_call_fastpath ffffffff81011cb7-ffffffff81011cbb ret_from_sys_call I.e. overlapping symbols, again some ASM special case that we have to fixup. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <1254934136-8503-1-git-send-email-acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-07 16:48:56 +00:00
return -1;
if (kallsyms__delta(map, filename, &delta))
return -1;
symbols__fixup_end(&dso->symbols[map->type]);
symbols__fixup_duplicate(&dso->symbols[map->type]);
if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
dso->symtab_type = DSO_BINARY_TYPE__GUEST_KALLSYMS;
else
dso->symtab_type = DSO_BINARY_TYPE__KALLSYMS;
perf tools: Improve kernel/modules symbol lookup This removes the ovelapping of vmlinux addresses with modules, using the ELF section name when using --vmlinux and creating a unique DSO name when using /proc/kallsyms ([kernel].N). This is done by creating multiple 'struct map' instances for address ranges backed by DSOs that have just the symbols for that range and a name that is derived from the ELF section name.o Now it is possible to ask for just the symbols in some particular kernel section: $ perf report -m --vmlinux ../build/tip-recvmmsg/vmlinux \ --dsos [kernel].vsyscall_fn | head -15 52.73% Xorg [.] vread_hpet 18.61% firefox [.] vread_hpet 14.50% npviewer.bin [.] vread_hpet 6.83% compiz [.] vread_hpet 5.73% glxgears [.] vread_hpet 0.63% java [.] vread_hpet 0.30% gnome-terminal [.] vread_hpet 0.23% perf [.] vread_hpet 0.18% xchat [.] vread_hpet $ Now we don't have to first lookup the list of modules and then, if it fails, vmlinux symbols, its just a simple lookup for the map then the symbols, just like for threads. Reports generated using /proc/kallsyms and --vmlinux should provide the same results, modulo the DSO name for sections other than ".text". But they don't right now because things like: ffffffff81011c20-ffffffff81012068 system_call ffffffff81011c30-ffffffff81011c9b system_call_after_swapgs ffffffff81011c9c-ffffffff81011cb6 system_call_fastpath ffffffff81011cb7-ffffffff81011cbb ret_from_sys_call I.e. overlapping symbols, again some ASM special case that we have to fixup. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <1254934136-8503-1-git-send-email-acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-07 16:48:56 +00:00
if (!no_kcore && !dso__load_kcore(dso, map, filename))
return dso__split_kallsyms_for_kcore(dso, map);
else
return dso__split_kallsyms(dso, map, delta);
}
int dso__load_kallsyms(struct dso *dso, const char *filename,
struct map *map)
{
return __dso__load_kallsyms(dso, filename, map, false);
}
static int dso__load_perf_map(struct dso *dso, struct map *map)
{
char *line = NULL;
size_t n;
FILE *file;
int nr_syms = 0;
file = fopen(dso->long_name, "r");
if (file == NULL)
goto out_failure;
while (!feof(file)) {
u64 start, size;
struct symbol *sym;
int line_len, len;
line_len = getline(&line, &n, file);
if (line_len < 0)
break;
if (!line)
goto out_failure;
line[--line_len] = '\0'; /* \n */
len = hex2u64(line, &start);
len++;
if (len + 2 >= line_len)
continue;
len += hex2u64(line + len, &size);
len++;
if (len + 2 >= line_len)
continue;
sym = symbol__new(start, size, STB_GLOBAL, line + len);
if (sym == NULL)
goto out_delete_line;
symbols__insert(&dso->symbols[map->type], sym);
nr_syms++;
}
free(line);
fclose(file);
return nr_syms;
out_delete_line:
free(line);
out_failure:
return -1;
}
static bool dso__is_compatible_symtab_type(struct dso *dso, bool kmod,
enum dso_binary_type type)
{
switch (type) {
case DSO_BINARY_TYPE__JAVA_JIT:
case DSO_BINARY_TYPE__DEBUGLINK:
case DSO_BINARY_TYPE__SYSTEM_PATH_DSO:
case DSO_BINARY_TYPE__FEDORA_DEBUGINFO:
case DSO_BINARY_TYPE__UBUNTU_DEBUGINFO:
case DSO_BINARY_TYPE__BUILDID_DEBUGINFO:
case DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO:
return !kmod && dso->kernel == DSO_TYPE_USER;
case DSO_BINARY_TYPE__KALLSYMS:
case DSO_BINARY_TYPE__VMLINUX:
case DSO_BINARY_TYPE__KCORE:
return dso->kernel == DSO_TYPE_KERNEL;
case DSO_BINARY_TYPE__GUEST_KALLSYMS:
case DSO_BINARY_TYPE__GUEST_VMLINUX:
case DSO_BINARY_TYPE__GUEST_KCORE:
return dso->kernel == DSO_TYPE_GUEST_KERNEL;
case DSO_BINARY_TYPE__GUEST_KMODULE:
case DSO_BINARY_TYPE__GUEST_KMODULE_COMP:
case DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE:
case DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP:
/*
* kernel modules know their symtab type - it's set when
* creating a module dso in machine__findnew_module_map().
*/
return kmod && dso->symtab_type == type;
case DSO_BINARY_TYPE__BUILD_ID_CACHE:
return true;
case DSO_BINARY_TYPE__NOT_FOUND:
default:
return false;
}
}
int dso__load(struct dso *dso, struct map *map)
{
char *name;
int ret = -1;
u_int i;
struct machine *machine;
char *root_dir = (char *) "";
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
int ss_pos = 0;
struct symsrc ss_[2];
struct symsrc *syms_ss = NULL, *runtime_ss = NULL;
bool kmod;
unsigned char build_id[BUILD_ID_SIZE];
pthread_mutex_lock(&dso->lock);
/* check again under the dso->lock */
if (dso__loaded(dso, map->type)) {
ret = 1;
goto out;
}
if (dso->kernel) {
if (dso->kernel == DSO_TYPE_KERNEL)
ret = dso__load_kernel_sym(dso, map);
else if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
ret = dso__load_guest_kernel_sym(dso, map);
goto out;
}
if (map->groups && map->groups->machine)
machine = map->groups->machine;
else
machine = NULL;
dso->adjust_symbols = 0;
if (strncmp(dso->name, "/tmp/perf-", 10) == 0) {
struct stat st;
if (lstat(dso->name, &st) < 0)
goto out;
if (!symbol_conf.force && st.st_uid && (st.st_uid != geteuid())) {
pr_warning("File %s not owned by current user or root, "
"ignoring it (use -f to override).\n", dso->name);
goto out;
}
ret = dso__load_perf_map(dso, map);
dso->symtab_type = ret > 0 ? DSO_BINARY_TYPE__JAVA_JIT :
DSO_BINARY_TYPE__NOT_FOUND;
goto out;
}
if (machine)
root_dir = machine->root_dir;
name = malloc(PATH_MAX);
if (!name)
goto out;
kmod = dso->symtab_type == DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE ||
dso->symtab_type == DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP ||
dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE ||
dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE_COMP;
/*
* Read the build id if possible. This is required for
* DSO_BINARY_TYPE__BUILDID_DEBUGINFO to work
*/
perf symbols: Use proper dso name for is_regular_file Marc reported use of uninitialized memory: > In commit "403567217d3f perf symbols: Do not read symbols/data from > device files" a check to uninitialzied memory was added. This leads to > the following valgrind output: > > ==24515== Syscall param stat(file_name) points to uninitialised byte(s) > ==24515== at 0x75B26D5: _xstat (in /lib/x86_64-linux-gnu/libc-2.22.so) > ==24515== by 0x4E548D: stat (stat.h:454) > ==24515== by 0x4E548D: is_regular_file (util.c:687) > ==24515== by 0x4A5BEE: dso__load (symbol.c:1435) > ==24515== by 0x4BB1AE: map__load (map.c:289) > ==24515== by 0x4BB1AE: map__find_symbol (map.c:333) > ==24515== by 0x4835B3: thread__find_addr_location (event.c:1300) > ==24515== by 0x4B5342: add_callchain_ip (machine.c:1652) > ==24515== by 0x4B5342: thread__resolve_callchain_sample (machine.c:1906) > ==24515== by 0x4B9E7D: thread__resolve_callchain (machine.c:1958) > ==24515== by 0x441B3E: process_event (builtin-script.c:795) > ==24515== by 0x441B3E: process_sample_event (builtin-script.c:920) > ==24515== by 0x4BEE29: perf_evlist__deliver_sample (session.c:1192) > ==24515== by 0x4BEE29: machines__deliver_event (session.c:1229) > ==24515== by 0x4BF770: perf_session__deliver_event (session.c:1286) > ==24515== by 0x4BF770: ordered_events__deliver_event (session.c:114) > ==24515== by 0x4C1D17: __ordered_events__flush (ordered-events.c:207) > ==24515== by 0x4C1D17: ordered_events__flush.part.3 (ordered-events.c:274) > ==24515== by 0x4BF44C: perf_session__process_user_event (session.c:1325) > ==24515== by 0x4BF44C: perf_session__process_event (session.c:1451) > ==24515== Address 0x807c6a0 is 0 bytes inside a block of size 4,096 alloc'd > ==24515== at 0x4C29C0F: malloc (in /usr/lib/valgrind/vgpreload_memcheck-amd64-linux.so) > ==24515== by 0x4A5BCB: dso__load (symbol.c:1421) > ==24515== by 0x4BB1AE: map__load (map.c:289) > ==24515== by 0x4BB1AE: map__find_symbol (map.c:333) > ==24515== by 0x4835B3: thread__find_addr_location (event.c:1300) > ==24515== by 0x4B5342: add_callchain_ip (machine.c:1652) > ==24515== by 0x4B5342: thread__resolve_callchain_sample (machine.c:1906) > ==24515== by 0x4B9E7D: thread__resolve_callchain (machine.c:1958) > ==24515== by 0x441B3E: process_event (builtin-script.c:795) > ==24515== by 0x441B3E: process_sample_event (builtin-script.c:920) > ==24515== by 0x4BEE29: perf_evlist__deliver_sample (session.c:1192) > ==24515== by 0x4BEE29: machines__deliver_event (session.c:1229) > ==24515== by 0x4BF770: perf_session__deliver_event (session.c:1286) > ==24515== by 0x4BF770: ordered_events__deliver_event (session.c:114) > ==24515== by 0x4C1D17: __ordered_events__flush (ordered-events.c:207) > ==24515== by 0x4C1D17: ordered_events__flush.part.3 (ordered-events.c:274) > ==24515== by 0x4BF44C: perf_session__process_user_event (session.c:1325) > ==24515== by 0x4BF44C: perf_session__process_event (session.c:1451) > ==24515== by 0x4C0EAC: __perf_session__process_events (session.c:1804) > ==24515== by 0x4C0EAC: perf_session__process_events (session.c:1858) The reason was a typo that passed global 'name' variable as the is_regular_file argument instead dso->long_name. Reported-by: Marc Kleine-Budde <mkl@pengutronix.de> Signed-off-by: Jiri Olsa <jolsa@kernel.org> Acked-by: Marc Kleine-Budde <mkl@pengutronix.de> Cc: David Ahern <dsahern@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Wang Nan <wangnan0@huawei.com> Fixes: 403567217d3f ("perf symbols: Do not read symbols/data from device files") Link: http://lkml.kernel.org/r/1466772025-17471-2-git-send-email-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-06-24 12:40:25 +00:00
if (is_regular_file(dso->long_name) &&
filename__read_build_id(dso->long_name, build_id, BUILD_ID_SIZE) > 0)
dso__set_build_id(dso, build_id);
/*
* Iterate over candidate debug images.
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
* Keep track of "interesting" ones (those which have a symtab, dynsym,
* and/or opd section) for processing.
*/
for (i = 0; i < DSO_BINARY_TYPE__SYMTAB_CNT; i++) {
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
struct symsrc *ss = &ss_[ss_pos];
bool next_slot = false;
enum dso_binary_type symtab_type = binary_type_symtab[i];
if (!dso__is_compatible_symtab_type(dso, kmod, symtab_type))
continue;
if (dso__read_binary_type_filename(dso, symtab_type,
root_dir, name, PATH_MAX))
continue;
if (!is_regular_file(name))
continue;
/* Name is now the name of the next image to try */
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
if (symsrc__init(ss, dso, name, symtab_type) < 0)
continue;
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
if (!syms_ss && symsrc__has_symtab(ss)) {
syms_ss = ss;
next_slot = true;
if (!dso->symsrc_filename)
dso->symsrc_filename = strdup(name);
}
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
if (!runtime_ss && symsrc__possibly_runtime(ss)) {
runtime_ss = ss;
next_slot = true;
}
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
if (next_slot) {
ss_pos++;
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
if (syms_ss && runtime_ss)
break;
} else {
symsrc__destroy(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
}
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
if (!runtime_ss && !syms_ss)
goto out_free;
if (runtime_ss && !syms_ss) {
syms_ss = runtime_ss;
}
/* We'll have to hope for the best */
if (!runtime_ss && syms_ss)
runtime_ss = syms_ss;
perf symbols: Fix symbols searching for module in buildid-cache Before this patch, if a sample is triggered inside a module not in /lib/modules/`uname -r`/, even if the module is in buildid-cache, 'perf report' will still be unable to find the correct symbol. For example: # rm -rf ~/.debug/ # perf buildid-cache -a ./mymodule.ko # perf probe -m ./mymodule.ko -a get_mymodule_val Added new event: probe:get_mymodule_val (on get_mymodule_val in mymodule) You can now use it in all perf tools, such as: perf record -e probe:get_mymodule_val -aR sleep 1 # perf record -e probe:get_mymodule_val cat /proc/mymodule mymodule:3 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.011 MB perf.data (1 samples) ] # perf report --stdio [SNIP] # # Overhead Command Shared Object Symbol # ........ ....... ................ ...................... # 100.00% cat [mymodule] [k] 0x0000000000000001 # perf report -vvvv --stdio dso__load_sym: adjusting symbol: st_value: 0 sh_addr: 0 sh_offset: 0x70 symbol__new: get_mymodule_val 0x70-0x8a [SNIP] This is caused by dso__load() -> dso__load_sym(). In dso__load(), kmod is true only when its file is found in some well know directories. All files loaded from buildid-cache are treated as user programs. Following dso__load_sym() set map->pgoff incorrectly. This patch gives kernel modules in buildid-cache a chance to adjust value of kmod. After dso__load() get the type of symbols, if it is buildid, check the last 3 chars of original filename against '.ko', and adjust the value of kmod if the file is a kernel module. Signed-off-by: Wang Nan <wangnan0@huawei.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Brendan Gregg <brendan.d.gregg@gmail.com> Cc: Cody P Schafer <dev@codyps.com> Cc: He Kuang <hekuang@huawei.com> Cc: Jeremie Galarneau <jeremie.galarneau@efficios.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kirill Smelkov <kirr@nexedi.com> Cc: Li Zefan <lizefan@huawei.com> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: pi3orama@163.com Link: http://lkml.kernel.org/r/1454680939-24963-3-git-send-email-wangnan0@huawei.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-02-05 14:01:27 +00:00
if (syms_ss && syms_ss->type == DSO_BINARY_TYPE__BUILD_ID_CACHE)
if (dso__build_id_is_kmod(dso, name, PATH_MAX))
kmod = true;
if (syms_ss)
ret = dso__load_sym(dso, map, syms_ss, runtime_ss, kmod);
else
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
ret = -1;
perf symbols: Fix builds with NO_LIBELF set Build currently fails: $ make -C tools/perf O=/tmp/pbuild NO_LIBELF=1 util/symbol.c: In function ‘dso__load’: util/symbol.c:1128:27: error: ‘struct symsrc’ has no member named ‘dynsym’ CC /tmp/pbuild/util/pager.o make: *** [/tmp/pbuild/util/symbol.o] Error 1 make: *** Waiting for unfinished jobs.... Moving the dynsym reference to symbol-elf.c reveals that NO_LIBELF requires NO_LIBUNWIND: $ make -C tools/perf O=/tmp/pbuild NO_LIBELF=1 LINK /tmp/pbuild/perf /tmp/pbuild/libperf.a(unwind.o): In function `elf_section_offset': /opt/sw/ahern/perf.git/tools/perf/util/unwind.c:176: undefined reference to `elf_begin' /opt/sw/ahern/perf.git/tools/perf/util/unwind.c:181: undefined reference to `gelf_getehdr' /tmp/pbuild/libperf.a(unwind.o): In function `elf_section_by_name': /opt/sw/ahern/perf.git/tools/perf/util/unwind.c:157: undefined reference to `elf_nextscn' /opt/sw/ahern/perf.git/tools/perf/util/unwind.c:160: undefined reference to `gelf_getshdr' /opt/sw/ahern/perf.git/tools/perf/util/unwind.c:161: undefined reference to `elf_strptr' /tmp/pbuild/libperf.a(unwind.o): In function `elf_section_offset': /opt/sw/ahern/perf.git/tools/perf/util/unwind.c:190: undefined reference to `elf_end' /tmp/pbuild/libperf.a(unwind.o): In function `read_unwind_spec': /opt/sw/ahern/perf.git/tools/perf/util/unwind.c:190: undefined reference to `elf_end' collect2: ld returned 1 exit status make: *** [/tmp/pbuild/perf] Error 1 make: Leaving directory `/opt/sw/ahern/perf.git/tools/perf' This patch fixes both. Reviewed-by: Namhyung Kim <namhyung@kernel.org> Signed-off-by: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Link: http://lkml.kernel.org/r/1345391234-71906-1-git-send-email-dsahern@gmail.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-08-19 15:47:14 +00:00
if (ret > 0) {
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
int nr_plt;
nr_plt = dso__synthesize_plt_symbols(dso, runtime_ss, map);
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
if (nr_plt > 0)
ret += nr_plt;
}
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
for (; ss_pos > 0; ss_pos--)
symsrc__destroy(&ss_[ss_pos - 1]);
out_free:
free(name);
if (ret < 0 && strstr(dso->name, " (deleted)") != NULL)
ret = 0;
out:
dso__set_loaded(dso, map->type);
pthread_mutex_unlock(&dso->lock);
return ret;
}
struct map *map_groups__find_by_name(struct map_groups *mg,
enum map_type type, const char *name)
perf tools: Rewrite and improve support for kernel modules Representing modules as struct map entries, backed by a DSO, etc, using /proc/modules to find where the module is loaded. DSOs now can have a short and long name, so that in verbose mode we can show exactly which .ko or vmlinux image was used. As kernel modules now are a DSO separate from the kernel, we can ask for just the hits for a particular set of kernel modules, just like we can do with shared libraries: [root@doppio linux-2.6-tip]# perf report -n --vmlinux /home/acme/git/build/tip-recvmmsg/vmlinux --modules --dsos \[drm\] | head -15 84.58% 13266 Xorg [k] drm_clflush_pages 4.02% 630 Xorg [k] trace_kmalloc.clone.0 3.95% 619 Xorg [k] drm_ioctl 2.07% 324 Xorg [k] drm_addbufs 1.68% 263 Xorg [k] drm_gem_close_ioctl 0.77% 120 Xorg [k] drm_setmaster_ioctl 0.70% 110 Xorg [k] drm_lastclose 0.68% 106 Xorg [k] drm_open 0.54% 85 Xorg [k] drm_mm_search_free [root@doppio linux-2.6-tip]# Specifying --dsos /lib/modules/2.6.31-tip/kernel/drivers/gpu/drm/drm.ko would have the same effect. Allowing specifying just 'drm.ko' is left for another patch. Processing kallsyms so that per kernel module struct map are instantiated was also left for another patch. That will allow removing the module name from each of its symbols. struct symbol was reduced by removing the ->module backpointer and moving it (well now the map) to struct symbol_entry in perf top, that is its only user right now. The total linecount went down by ~500 lines. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Avi Kivity <avi@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-02 06:29:58 +00:00
{
struct maps *maps = &mg->maps[type];
struct map *map;
perf tools: Rewrite and improve support for kernel modules Representing modules as struct map entries, backed by a DSO, etc, using /proc/modules to find where the module is loaded. DSOs now can have a short and long name, so that in verbose mode we can show exactly which .ko or vmlinux image was used. As kernel modules now are a DSO separate from the kernel, we can ask for just the hits for a particular set of kernel modules, just like we can do with shared libraries: [root@doppio linux-2.6-tip]# perf report -n --vmlinux /home/acme/git/build/tip-recvmmsg/vmlinux --modules --dsos \[drm\] | head -15 84.58% 13266 Xorg [k] drm_clflush_pages 4.02% 630 Xorg [k] trace_kmalloc.clone.0 3.95% 619 Xorg [k] drm_ioctl 2.07% 324 Xorg [k] drm_addbufs 1.68% 263 Xorg [k] drm_gem_close_ioctl 0.77% 120 Xorg [k] drm_setmaster_ioctl 0.70% 110 Xorg [k] drm_lastclose 0.68% 106 Xorg [k] drm_open 0.54% 85 Xorg [k] drm_mm_search_free [root@doppio linux-2.6-tip]# Specifying --dsos /lib/modules/2.6.31-tip/kernel/drivers/gpu/drm/drm.ko would have the same effect. Allowing specifying just 'drm.ko' is left for another patch. Processing kallsyms so that per kernel module struct map are instantiated was also left for another patch. That will allow removing the module name from each of its symbols. struct symbol was reduced by removing the ->module backpointer and moving it (well now the map) to struct symbol_entry in perf top, that is its only user right now. The total linecount went down by ~500 lines. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Avi Kivity <avi@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-02 06:29:58 +00:00
pthread_rwlock_rdlock(&maps->lock);
for (map = maps__first(maps); map; map = map__next(map)) {
if (map->dso && strcmp(map->dso->short_name, name) == 0)
goto out_unlock;
perf tools: Rewrite and improve support for kernel modules Representing modules as struct map entries, backed by a DSO, etc, using /proc/modules to find where the module is loaded. DSOs now can have a short and long name, so that in verbose mode we can show exactly which .ko or vmlinux image was used. As kernel modules now are a DSO separate from the kernel, we can ask for just the hits for a particular set of kernel modules, just like we can do with shared libraries: [root@doppio linux-2.6-tip]# perf report -n --vmlinux /home/acme/git/build/tip-recvmmsg/vmlinux --modules --dsos \[drm\] | head -15 84.58% 13266 Xorg [k] drm_clflush_pages 4.02% 630 Xorg [k] trace_kmalloc.clone.0 3.95% 619 Xorg [k] drm_ioctl 2.07% 324 Xorg [k] drm_addbufs 1.68% 263 Xorg [k] drm_gem_close_ioctl 0.77% 120 Xorg [k] drm_setmaster_ioctl 0.70% 110 Xorg [k] drm_lastclose 0.68% 106 Xorg [k] drm_open 0.54% 85 Xorg [k] drm_mm_search_free [root@doppio linux-2.6-tip]# Specifying --dsos /lib/modules/2.6.31-tip/kernel/drivers/gpu/drm/drm.ko would have the same effect. Allowing specifying just 'drm.ko' is left for another patch. Processing kallsyms so that per kernel module struct map are instantiated was also left for another patch. That will allow removing the module name from each of its symbols. struct symbol was reduced by removing the ->module backpointer and moving it (well now the map) to struct symbol_entry in perf top, that is its only user right now. The total linecount went down by ~500 lines. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Avi Kivity <avi@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-02 06:29:58 +00:00
}
map = NULL;
out_unlock:
pthread_rwlock_unlock(&maps->lock);
return map;
perf tools: Rewrite and improve support for kernel modules Representing modules as struct map entries, backed by a DSO, etc, using /proc/modules to find where the module is loaded. DSOs now can have a short and long name, so that in verbose mode we can show exactly which .ko or vmlinux image was used. As kernel modules now are a DSO separate from the kernel, we can ask for just the hits for a particular set of kernel modules, just like we can do with shared libraries: [root@doppio linux-2.6-tip]# perf report -n --vmlinux /home/acme/git/build/tip-recvmmsg/vmlinux --modules --dsos \[drm\] | head -15 84.58% 13266 Xorg [k] drm_clflush_pages 4.02% 630 Xorg [k] trace_kmalloc.clone.0 3.95% 619 Xorg [k] drm_ioctl 2.07% 324 Xorg [k] drm_addbufs 1.68% 263 Xorg [k] drm_gem_close_ioctl 0.77% 120 Xorg [k] drm_setmaster_ioctl 0.70% 110 Xorg [k] drm_lastclose 0.68% 106 Xorg [k] drm_open 0.54% 85 Xorg [k] drm_mm_search_free [root@doppio linux-2.6-tip]# Specifying --dsos /lib/modules/2.6.31-tip/kernel/drivers/gpu/drm/drm.ko would have the same effect. Allowing specifying just 'drm.ko' is left for another patch. Processing kallsyms so that per kernel module struct map are instantiated was also left for another patch. That will allow removing the module name from each of its symbols. struct symbol was reduced by removing the ->module backpointer and moving it (well now the map) to struct symbol_entry in perf top, that is its only user right now. The total linecount went down by ~500 lines. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Avi Kivity <avi@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-02 06:29:58 +00:00
}
int dso__load_vmlinux(struct dso *dso, struct map *map,
const char *vmlinux, bool vmlinux_allocated)
{
int err = -1;
struct symsrc ss;
char symfs_vmlinux[PATH_MAX];
enum dso_binary_type symtab_type;
if (vmlinux[0] == '/')
snprintf(symfs_vmlinux, sizeof(symfs_vmlinux), "%s", vmlinux);
else
symbol__join_symfs(symfs_vmlinux, vmlinux);
if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
symtab_type = DSO_BINARY_TYPE__GUEST_VMLINUX;
else
symtab_type = DSO_BINARY_TYPE__VMLINUX;
if (symsrc__init(&ss, dso, symfs_vmlinux, symtab_type))
return -1;
err = dso__load_sym(dso, map, &ss, &ss, 0);
symsrc__destroy(&ss);
if (err > 0) {
if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
dso->binary_type = DSO_BINARY_TYPE__GUEST_VMLINUX;
else
dso->binary_type = DSO_BINARY_TYPE__VMLINUX;
dso__set_long_name(dso, vmlinux, vmlinux_allocated);
dso__set_loaded(dso, map->type);
pr_debug("Using %s for symbols\n", symfs_vmlinux);
}
return err;
}
int dso__load_vmlinux_path(struct dso *dso, struct map *map)
{
int i, err = 0;
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
char *filename = NULL;
perf symbols: Try the .debug/ DSO cache as a last resort Not as the first attempt at finding a vmlinux for the running kernel, this way we get a more informative filename to present in tools, it will check that the build-id is the same as the one previously loaded in the DSO in dso->build_id, reading from /sys/kernel/notes, for instance. E.g. in the annotation TUI, going from 'perf top', for the scsi_sg_alloc kernel function, in the first line: Before: scsi_sg_alloc /root/.debug/.build-id/28/2777c262e6b3c0451375163c9a81c893218ab1 After: scsi_sg_alloc /lib/modules/4.3.0-rc1+/build/vmlinux And: # ls -la /root/.debug/.build-id/28/2777c262e6b3c0451375163c9a81c893218ab1 lrwxrwxrwx. 1 root root 81 Sep 22 16:11 /root/.debug/.build-id/28/2777c262e6b3c0451375163c9a81c893218ab1 -> ../../home/git/build/v4.3.0-rc1+/vmlinux/282777c262e6b3c0451375163c9a81c893218ab1 # file ~/.debug/home/git/build/v4.3.0-rc1+/vmlinux/282777c262e6b3c0451375163c9a81c893218ab1 /root/.debug/home/git/build/v4.3.0-rc1+/vmlinux/282777c262e6b3c0451375163c9a81c893218ab1: ELF 64-bit LSB executable, x86-64, version 1 (SYSV), statically linked, BuildID[sha1]=282777c262e6b3c0451375163c9a81c893218ab1, not stripped # The same as: # file /lib/modules/4.3.0-rc1+/build/vmlinux /lib/modules/4.3.0-rc1+/build/vmlinux: ELF 64-bit LSB executable, x86-64, version 1 (SYSV), statically linked, BuildID[sha1]=282777c262e6b3c0451375163c9a81c893218ab1, not stripped Furthermore: # sha256sum /lib/modules/4.3.0-rc1+/build/vmlinux e7a789bbdc61029ec09140c228e1dd651271f38ef0b8416c0b7d5ff727b98be2 /lib/modules/4.3.0-rc1+/build/vmlinux # sha256sum ~/.debug/home/git/build/v4.3.0-rc1+/vmlinux/282777c262e6b3c0451375163c9a81c893218ab1 e7a789bbdc61029ec09140c228e1dd651271f38ef0b8416c0b7d5ff727b98be2 /root/.debug/home/git/build/v4.3.0-rc1+/vmlinux/282777c262e6b3c0451375163c9a81c893218ab1 [root@zoo new]# Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Borislav Petkov <bp@suse.de> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Stephane Eranian <eranian@google.com> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/n/tip-9y42ikzq3jisiddoi6f07n8z@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-10-11 20:17:24 +00:00
pr_debug("Looking at the vmlinux_path (%d entries long)\n",
vmlinux_path__nr_entries + 1);
for (i = 0; i < vmlinux_path__nr_entries; ++i) {
err = dso__load_vmlinux(dso, map, vmlinux_path[i], false);
perf symbols: Try the .debug/ DSO cache as a last resort Not as the first attempt at finding a vmlinux for the running kernel, this way we get a more informative filename to present in tools, it will check that the build-id is the same as the one previously loaded in the DSO in dso->build_id, reading from /sys/kernel/notes, for instance. E.g. in the annotation TUI, going from 'perf top', for the scsi_sg_alloc kernel function, in the first line: Before: scsi_sg_alloc /root/.debug/.build-id/28/2777c262e6b3c0451375163c9a81c893218ab1 After: scsi_sg_alloc /lib/modules/4.3.0-rc1+/build/vmlinux And: # ls -la /root/.debug/.build-id/28/2777c262e6b3c0451375163c9a81c893218ab1 lrwxrwxrwx. 1 root root 81 Sep 22 16:11 /root/.debug/.build-id/28/2777c262e6b3c0451375163c9a81c893218ab1 -> ../../home/git/build/v4.3.0-rc1+/vmlinux/282777c262e6b3c0451375163c9a81c893218ab1 # file ~/.debug/home/git/build/v4.3.0-rc1+/vmlinux/282777c262e6b3c0451375163c9a81c893218ab1 /root/.debug/home/git/build/v4.3.0-rc1+/vmlinux/282777c262e6b3c0451375163c9a81c893218ab1: ELF 64-bit LSB executable, x86-64, version 1 (SYSV), statically linked, BuildID[sha1]=282777c262e6b3c0451375163c9a81c893218ab1, not stripped # The same as: # file /lib/modules/4.3.0-rc1+/build/vmlinux /lib/modules/4.3.0-rc1+/build/vmlinux: ELF 64-bit LSB executable, x86-64, version 1 (SYSV), statically linked, BuildID[sha1]=282777c262e6b3c0451375163c9a81c893218ab1, not stripped Furthermore: # sha256sum /lib/modules/4.3.0-rc1+/build/vmlinux e7a789bbdc61029ec09140c228e1dd651271f38ef0b8416c0b7d5ff727b98be2 /lib/modules/4.3.0-rc1+/build/vmlinux # sha256sum ~/.debug/home/git/build/v4.3.0-rc1+/vmlinux/282777c262e6b3c0451375163c9a81c893218ab1 e7a789bbdc61029ec09140c228e1dd651271f38ef0b8416c0b7d5ff727b98be2 /root/.debug/home/git/build/v4.3.0-rc1+/vmlinux/282777c262e6b3c0451375163c9a81c893218ab1 [root@zoo new]# Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Borislav Petkov <bp@suse.de> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Stephane Eranian <eranian@google.com> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/n/tip-9y42ikzq3jisiddoi6f07n8z@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-10-11 20:17:24 +00:00
if (err > 0)
goto out;
}
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
if (!symbol_conf.ignore_vmlinux_buildid)
filename = dso__build_id_filename(dso, NULL, 0);
if (filename != NULL) {
err = dso__load_vmlinux(dso, map, filename, true);
if (err > 0)
goto out;
free(filename);
}
out:
return err;
}
static bool visible_dir_filter(const char *name, struct dirent *d)
{
if (d->d_type != DT_DIR)
return false;
return lsdir_no_dot_filter(name, d);
}
static int find_matching_kcore(struct map *map, char *dir, size_t dir_sz)
{
char kallsyms_filename[PATH_MAX];
int ret = -1;
struct strlist *dirs;
struct str_node *nd;
dirs = lsdir(dir, visible_dir_filter);
if (!dirs)
return -1;
strlist__for_each_entry(nd, dirs) {
scnprintf(kallsyms_filename, sizeof(kallsyms_filename),
"%s/%s/kallsyms", dir, nd->s);
if (!validate_kcore_addresses(kallsyms_filename, map)) {
strlcpy(dir, kallsyms_filename, dir_sz);
ret = 0;
break;
}
}
strlist__delete(dirs);
return ret;
}
/*
* Use open(O_RDONLY) to check readability directly instead of access(R_OK)
* since access(R_OK) only checks with real UID/GID but open() use effective
* UID/GID and actual capabilities (e.g. /proc/kcore requires CAP_SYS_RAWIO).
*/
static bool filename__readable(const char *file)
{
int fd = open(file, O_RDONLY);
if (fd < 0)
return false;
close(fd);
return true;
}
static char *dso__find_kallsyms(struct dso *dso, struct map *map)
{
u8 host_build_id[BUILD_ID_SIZE];
char sbuild_id[SBUILD_ID_SIZE];
bool is_host = false;
char path[PATH_MAX];
if (!dso->has_build_id) {
/*
* Last resort, if we don't have a build-id and couldn't find
* any vmlinux file, try the running kernel kallsyms table.
*/
goto proc_kallsyms;
}
if (sysfs__read_build_id("/sys/kernel/notes", host_build_id,
sizeof(host_build_id)) == 0)
is_host = dso__build_id_equal(dso, host_build_id);
/* Try a fast path for /proc/kallsyms if possible */
if (is_host) {
/*
* Do not check the build-id cache, unless we know we cannot use
* /proc/kcore or module maps don't match to /proc/kallsyms.
* To check readability of /proc/kcore, do not use access(R_OK)
* since /proc/kcore requires CAP_SYS_RAWIO to read and access
* can't check it.
*/
if (filename__readable("/proc/kcore") &&
!validate_kcore_addresses("/proc/kallsyms", map))
goto proc_kallsyms;
}
build_id__sprintf(dso->build_id, sizeof(dso->build_id), sbuild_id);
/* Find kallsyms in build-id cache with kcore */
scnprintf(path, sizeof(path), "%s/%s/%s",
buildid_dir, DSO__NAME_KCORE, sbuild_id);
if (!find_matching_kcore(map, path, sizeof(path)))
return strdup(path);
/* Use current /proc/kallsyms if possible */
if (is_host) {
proc_kallsyms:
return strdup("/proc/kallsyms");
}
/* Finally, find a cache of kallsyms */
if (!build_id_cache__kallsyms_path(sbuild_id, path, sizeof(path))) {
pr_err("No kallsyms or vmlinux with build-id %s was found\n",
sbuild_id);
return NULL;
}
return strdup(path);
}
static int dso__load_kernel_sym(struct dso *dso, struct map *map)
{
int err;
const char *kallsyms_filename = NULL;
char *kallsyms_allocated_filename = NULL;
/*
* Step 1: if the user specified a kallsyms or vmlinux filename, use
* it and only it, reporting errors to the user if it cannot be used.
*
* For instance, try to analyse an ARM perf.data file _without_ a
* build-id, or if the user specifies the wrong path to the right
* vmlinux file, obviously we can't fallback to another vmlinux (a
* x86_86 one, on the machine where analysis is being performed, say),
* or worse, /proc/kallsyms.
*
* If the specified file _has_ a build-id and there is a build-id
* section in the perf.data file, we will still do the expected
* validation in dso__load_vmlinux and will bail out if they don't
* match.
*/
if (symbol_conf.kallsyms_name != NULL) {
kallsyms_filename = symbol_conf.kallsyms_name;
goto do_kallsyms;
}
if (!symbol_conf.ignore_vmlinux && symbol_conf.vmlinux_name != NULL) {
return dso__load_vmlinux(dso, map, symbol_conf.vmlinux_name, false);
}
if (!symbol_conf.ignore_vmlinux && vmlinux_path != NULL) {
err = dso__load_vmlinux_path(dso, map);
if (err > 0)
return err;
}
/* do not try local files if a symfs was given */
if (symbol_conf.symfs[0] != 0)
return -1;
kallsyms_allocated_filename = dso__find_kallsyms(dso, map);
if (!kallsyms_allocated_filename)
return -1;
kallsyms_filename = kallsyms_allocated_filename;
perf tools: Rewrite and improve support for kernel modules Representing modules as struct map entries, backed by a DSO, etc, using /proc/modules to find where the module is loaded. DSOs now can have a short and long name, so that in verbose mode we can show exactly which .ko or vmlinux image was used. As kernel modules now are a DSO separate from the kernel, we can ask for just the hits for a particular set of kernel modules, just like we can do with shared libraries: [root@doppio linux-2.6-tip]# perf report -n --vmlinux /home/acme/git/build/tip-recvmmsg/vmlinux --modules --dsos \[drm\] | head -15 84.58% 13266 Xorg [k] drm_clflush_pages 4.02% 630 Xorg [k] trace_kmalloc.clone.0 3.95% 619 Xorg [k] drm_ioctl 2.07% 324 Xorg [k] drm_addbufs 1.68% 263 Xorg [k] drm_gem_close_ioctl 0.77% 120 Xorg [k] drm_setmaster_ioctl 0.70% 110 Xorg [k] drm_lastclose 0.68% 106 Xorg [k] drm_open 0.54% 85 Xorg [k] drm_mm_search_free [root@doppio linux-2.6-tip]# Specifying --dsos /lib/modules/2.6.31-tip/kernel/drivers/gpu/drm/drm.ko would have the same effect. Allowing specifying just 'drm.ko' is left for another patch. Processing kallsyms so that per kernel module struct map are instantiated was also left for another patch. That will allow removing the module name from each of its symbols. struct symbol was reduced by removing the ->module backpointer and moving it (well now the map) to struct symbol_entry in perf top, that is its only user right now. The total linecount went down by ~500 lines. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Avi Kivity <avi@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-02 06:29:58 +00:00
do_kallsyms:
err = dso__load_kallsyms(dso, kallsyms_filename, map);
if (err > 0)
pr_debug("Using %s for symbols\n", kallsyms_filename);
free(kallsyms_allocated_filename);
perf tools: Rewrite and improve support for kernel modules Representing modules as struct map entries, backed by a DSO, etc, using /proc/modules to find where the module is loaded. DSOs now can have a short and long name, so that in verbose mode we can show exactly which .ko or vmlinux image was used. As kernel modules now are a DSO separate from the kernel, we can ask for just the hits for a particular set of kernel modules, just like we can do with shared libraries: [root@doppio linux-2.6-tip]# perf report -n --vmlinux /home/acme/git/build/tip-recvmmsg/vmlinux --modules --dsos \[drm\] | head -15 84.58% 13266 Xorg [k] drm_clflush_pages 4.02% 630 Xorg [k] trace_kmalloc.clone.0 3.95% 619 Xorg [k] drm_ioctl 2.07% 324 Xorg [k] drm_addbufs 1.68% 263 Xorg [k] drm_gem_close_ioctl 0.77% 120 Xorg [k] drm_setmaster_ioctl 0.70% 110 Xorg [k] drm_lastclose 0.68% 106 Xorg [k] drm_open 0.54% 85 Xorg [k] drm_mm_search_free [root@doppio linux-2.6-tip]# Specifying --dsos /lib/modules/2.6.31-tip/kernel/drivers/gpu/drm/drm.ko would have the same effect. Allowing specifying just 'drm.ko' is left for another patch. Processing kallsyms so that per kernel module struct map are instantiated was also left for another patch. That will allow removing the module name from each of its symbols. struct symbol was reduced by removing the ->module backpointer and moving it (well now the map) to struct symbol_entry in perf top, that is its only user right now. The total linecount went down by ~500 lines. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Avi Kivity <avi@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-02 06:29:58 +00:00
if (err > 0 && !dso__is_kcore(dso)) {
dso->binary_type = DSO_BINARY_TYPE__KALLSYMS;
dso__set_long_name(dso, DSO__NAME_KALLSYMS, false);
map__fixup_start(map);
map__fixup_end(map);
perf tools: Rewrite and improve support for kernel modules Representing modules as struct map entries, backed by a DSO, etc, using /proc/modules to find where the module is loaded. DSOs now can have a short and long name, so that in verbose mode we can show exactly which .ko or vmlinux image was used. As kernel modules now are a DSO separate from the kernel, we can ask for just the hits for a particular set of kernel modules, just like we can do with shared libraries: [root@doppio linux-2.6-tip]# perf report -n --vmlinux /home/acme/git/build/tip-recvmmsg/vmlinux --modules --dsos \[drm\] | head -15 84.58% 13266 Xorg [k] drm_clflush_pages 4.02% 630 Xorg [k] trace_kmalloc.clone.0 3.95% 619 Xorg [k] drm_ioctl 2.07% 324 Xorg [k] drm_addbufs 1.68% 263 Xorg [k] drm_gem_close_ioctl 0.77% 120 Xorg [k] drm_setmaster_ioctl 0.70% 110 Xorg [k] drm_lastclose 0.68% 106 Xorg [k] drm_open 0.54% 85 Xorg [k] drm_mm_search_free [root@doppio linux-2.6-tip]# Specifying --dsos /lib/modules/2.6.31-tip/kernel/drivers/gpu/drm/drm.ko would have the same effect. Allowing specifying just 'drm.ko' is left for another patch. Processing kallsyms so that per kernel module struct map are instantiated was also left for another patch. That will allow removing the module name from each of its symbols. struct symbol was reduced by removing the ->module backpointer and moving it (well now the map) to struct symbol_entry in perf top, that is its only user right now. The total linecount went down by ~500 lines. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Avi Kivity <avi@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-02 06:29:58 +00:00
}
return err;
}
static int dso__load_guest_kernel_sym(struct dso *dso, struct map *map)
{
int err;
const char *kallsyms_filename = NULL;
struct machine *machine;
char path[PATH_MAX];
if (!map->groups) {
pr_debug("Guest kernel map hasn't the point to groups\n");
return -1;
}
machine = map->groups->machine;
if (machine__is_default_guest(machine)) {
/*
* if the user specified a vmlinux filename, use it and only
* it, reporting errors to the user if it cannot be used.
* Or use file guest_kallsyms inputted by user on commandline
*/
if (symbol_conf.default_guest_vmlinux_name != NULL) {
err = dso__load_vmlinux(dso, map,
symbol_conf.default_guest_vmlinux_name,
false);
return err;
}
kallsyms_filename = symbol_conf.default_guest_kallsyms;
if (!kallsyms_filename)
return -1;
} else {
sprintf(path, "%s/proc/kallsyms", machine->root_dir);
kallsyms_filename = path;
}
err = dso__load_kallsyms(dso, kallsyms_filename, map);
if (err > 0)
pr_debug("Using %s for symbols\n", kallsyms_filename);
if (err > 0 && !dso__is_kcore(dso)) {
dso->binary_type = DSO_BINARY_TYPE__GUEST_KALLSYMS;
machine__mmap_name(machine, path, sizeof(path));
dso__set_long_name(dso, strdup(path), true);
map__fixup_start(map);
map__fixup_end(map);
}
return err;
}
static void vmlinux_path__exit(void)
{
while (--vmlinux_path__nr_entries >= 0)
zfree(&vmlinux_path[vmlinux_path__nr_entries]);
vmlinux_path__nr_entries = 0;
zfree(&vmlinux_path);
}
static const char * const vmlinux_paths[] = {
"vmlinux",
"/boot/vmlinux"
};
static const char * const vmlinux_paths_upd[] = {
"/boot/vmlinux-%s",
"/usr/lib/debug/boot/vmlinux-%s",
"/lib/modules/%s/build/vmlinux",
"/usr/lib/debug/lib/modules/%s/vmlinux",
"/usr/lib/debug/boot/vmlinux-%s.debug"
};
static int vmlinux_path__add(const char *new_entry)
{
vmlinux_path[vmlinux_path__nr_entries] = strdup(new_entry);
if (vmlinux_path[vmlinux_path__nr_entries] == NULL)
return -1;
++vmlinux_path__nr_entries;
return 0;
}
static int vmlinux_path__init(struct perf_env *env)
{
struct utsname uts;
char bf[PATH_MAX];
perf tools: Check recorded kernel version when finding vmlinux Currently vmlinux_path__init() only tries to find vmlinux file from current directory, /boot and some canonical directories with version number of the running kernel. This can be a problem when reporting old data recorded on a kernel version not running currently. We can use --symfs option for this but it's annoying for user to do it always. As we already have the info in the perf.data file, it can be changed to use it for the search automatically. Before: $ perf report ... # Samples: 4K of event 'cpu-clock' # Event count (approx.): 1067250000 # # Overhead Command Shared Object Symbol # ........ .......... ................. .............................. 71.87% swapper [kernel.kallsyms] [k] recover_probed_instruction After: # Overhead Command Shared Object Symbol # ........ .......... ................. .................... 71.87% swapper [kernel.kallsyms] [k] native_safe_halt This requires to change signature of symbol__init() to receive struct perf_session_env *. Reported-by: Minchan Kim <minchan@kernel.org> 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: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Minchan Kim <minchan@kernel.org> 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/1407825645-24586-14-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2014-08-12 06:40:45 +00:00
char *kernel_version;
unsigned int i;
vmlinux_path = malloc(sizeof(char *) * (ARRAY_SIZE(vmlinux_paths) +
ARRAY_SIZE(vmlinux_paths_upd)));
if (vmlinux_path == NULL)
return -1;
for (i = 0; i < ARRAY_SIZE(vmlinux_paths); i++)
if (vmlinux_path__add(vmlinux_paths[i]) < 0)
goto out_fail;
perf tools: Check recorded kernel version when finding vmlinux Currently vmlinux_path__init() only tries to find vmlinux file from current directory, /boot and some canonical directories with version number of the running kernel. This can be a problem when reporting old data recorded on a kernel version not running currently. We can use --symfs option for this but it's annoying for user to do it always. As we already have the info in the perf.data file, it can be changed to use it for the search automatically. Before: $ perf report ... # Samples: 4K of event 'cpu-clock' # Event count (approx.): 1067250000 # # Overhead Command Shared Object Symbol # ........ .......... ................. .............................. 71.87% swapper [kernel.kallsyms] [k] recover_probed_instruction After: # Overhead Command Shared Object Symbol # ........ .......... ................. .................... 71.87% swapper [kernel.kallsyms] [k] native_safe_halt This requires to change signature of symbol__init() to receive struct perf_session_env *. Reported-by: Minchan Kim <minchan@kernel.org> 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: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Minchan Kim <minchan@kernel.org> 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/1407825645-24586-14-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2014-08-12 06:40:45 +00:00
/* only try kernel version if no symfs was given */
if (symbol_conf.symfs[0] != 0)
return 0;
perf tools: Check recorded kernel version when finding vmlinux Currently vmlinux_path__init() only tries to find vmlinux file from current directory, /boot and some canonical directories with version number of the running kernel. This can be a problem when reporting old data recorded on a kernel version not running currently. We can use --symfs option for this but it's annoying for user to do it always. As we already have the info in the perf.data file, it can be changed to use it for the search automatically. Before: $ perf report ... # Samples: 4K of event 'cpu-clock' # Event count (approx.): 1067250000 # # Overhead Command Shared Object Symbol # ........ .......... ................. .............................. 71.87% swapper [kernel.kallsyms] [k] recover_probed_instruction After: # Overhead Command Shared Object Symbol # ........ .......... ................. .................... 71.87% swapper [kernel.kallsyms] [k] native_safe_halt This requires to change signature of symbol__init() to receive struct perf_session_env *. Reported-by: Minchan Kim <minchan@kernel.org> 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: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Minchan Kim <minchan@kernel.org> 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/1407825645-24586-14-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2014-08-12 06:40:45 +00:00
if (env) {
kernel_version = env->os_release;
} else {
if (uname(&uts) < 0)
goto out_fail;
kernel_version = uts.release;
}
for (i = 0; i < ARRAY_SIZE(vmlinux_paths_upd); i++) {
snprintf(bf, sizeof(bf), vmlinux_paths_upd[i], kernel_version);
if (vmlinux_path__add(bf) < 0)
goto out_fail;
}
return 0;
out_fail:
vmlinux_path__exit();
return -1;
}
int setup_list(struct strlist **list, const char *list_str,
const char *list_name)
{
if (list_str == NULL)
return 0;
*list = strlist__new(list_str, NULL);
if (!*list) {
pr_err("problems parsing %s list\n", list_name);
return -1;
}
symbol_conf.has_filter = true;
return 0;
}
int setup_intlist(struct intlist **list, const char *list_str,
const char *list_name)
{
if (list_str == NULL)
return 0;
*list = intlist__new(list_str);
if (!*list) {
pr_err("problems parsing %s list\n", list_name);
return -1;
}
return 0;
}
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
static bool symbol__read_kptr_restrict(void)
{
bool value = false;
FILE *fp = fopen("/proc/sys/kernel/kptr_restrict", "r");
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
if (fp != NULL) {
char line[8];
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
if (fgets(line, sizeof(line), fp) != NULL)
value = (geteuid() != 0) ?
(atoi(line) != 0) :
(atoi(line) == 2);
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
fclose(fp);
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
}
return value;
}
int symbol__annotation_init(void)
{
if (symbol_conf.initialized) {
pr_err("Annotation needs to be init before symbol__init()\n");
return -1;
}
if (symbol_conf.init_annotation) {
pr_warning("Annotation being initialized multiple times\n");
return 0;
}
symbol_conf.priv_size += sizeof(struct annotation);
symbol_conf.init_annotation = true;
return 0;
}
int symbol__init(struct perf_env *env)
{
const char *symfs;
if (symbol_conf.initialized)
return 0;
perf tools: fix ALIGN redefinition in system headers On some systems (e.g. Android), ALIGN is defined in system headers as ALIGN(p). The definition of ALIGN used in perf takes 2 parameters: ALIGN(x,a). This leads to redefinition conflicts. Redefinition error on Android: In file included from util/include/linux/list.h:1:0, from util/callchain.h:5, from util/hist.h:6, from util/session.h:4, from util/build-id.h:4, from util/annotate.c:11: util/include/linux/kernel.h:11:0: error: "ALIGN" redefined [-Werror] bionic/libc/include/sys/param.h:38:0: note: this is the location of the previous definition Conflics with system defined ALIGN in Android: util/event.c: In function 'perf_event__synthesize_comm': util/event.c:115:32: error: macro "ALIGN" passed 2 arguments, but takes just 1 util/event.c:115:9: error: 'ALIGN' undeclared (first use in this function) util/event.c:115:9: note: each undeclared identifier is reported only once for each function it appears in In order to avoid this redefinition, ALIGN is renamed to PERF_ALIGN. Signed-off-by: Irina Tirdea <irina.tirdea@intel.com> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Irina Tirdea <irina.tirdea@intel.com> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/r/1347315303-29906-5-git-send-email-irina.tirdea@intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-10 22:15:01 +00:00
symbol_conf.priv_size = PERF_ALIGN(symbol_conf.priv_size, sizeof(u64));
symbol__elf_init();
if (symbol_conf.sort_by_name)
symbol_conf.priv_size += (sizeof(struct symbol_name_rb_node) -
sizeof(struct symbol));
perf tools: Check recorded kernel version when finding vmlinux Currently vmlinux_path__init() only tries to find vmlinux file from current directory, /boot and some canonical directories with version number of the running kernel. This can be a problem when reporting old data recorded on a kernel version not running currently. We can use --symfs option for this but it's annoying for user to do it always. As we already have the info in the perf.data file, it can be changed to use it for the search automatically. Before: $ perf report ... # Samples: 4K of event 'cpu-clock' # Event count (approx.): 1067250000 # # Overhead Command Shared Object Symbol # ........ .......... ................. .............................. 71.87% swapper [kernel.kallsyms] [k] recover_probed_instruction After: # Overhead Command Shared Object Symbol # ........ .......... ................. .................... 71.87% swapper [kernel.kallsyms] [k] native_safe_halt This requires to change signature of symbol__init() to receive struct perf_session_env *. Reported-by: Minchan Kim <minchan@kernel.org> 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: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Minchan Kim <minchan@kernel.org> 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/1407825645-24586-14-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2014-08-12 06:40:45 +00:00
if (symbol_conf.try_vmlinux_path && vmlinux_path__init(env) < 0)
return -1;
if (symbol_conf.field_sep && *symbol_conf.field_sep == '.') {
pr_err("'.' is the only non valid --field-separator argument\n");
return -1;
}
if (setup_list(&symbol_conf.dso_list,
symbol_conf.dso_list_str, "dso") < 0)
return -1;
if (setup_list(&symbol_conf.comm_list,
symbol_conf.comm_list_str, "comm") < 0)
goto out_free_dso_list;
if (setup_intlist(&symbol_conf.pid_list,
symbol_conf.pid_list_str, "pid") < 0)
goto out_free_comm_list;
if (setup_intlist(&symbol_conf.tid_list,
symbol_conf.tid_list_str, "tid") < 0)
goto out_free_pid_list;
if (setup_list(&symbol_conf.sym_list,
symbol_conf.sym_list_str, "symbol") < 0)
goto out_free_tid_list;
/*
* A path to symbols of "/" is identical to ""
* reset here for simplicity.
*/
symfs = realpath(symbol_conf.symfs, NULL);
if (symfs == NULL)
symfs = symbol_conf.symfs;
if (strcmp(symfs, "/") == 0)
symbol_conf.symfs = "";
if (symfs != symbol_conf.symfs)
free((void *)symfs);
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
symbol_conf.kptr_restrict = symbol__read_kptr_restrict();
symbol_conf.initialized = true;
return 0;
out_free_tid_list:
intlist__delete(symbol_conf.tid_list);
out_free_pid_list:
intlist__delete(symbol_conf.pid_list);
out_free_comm_list:
strlist__delete(symbol_conf.comm_list);
out_free_dso_list:
strlist__delete(symbol_conf.dso_list);
return -1;
}
void symbol__exit(void)
{
if (!symbol_conf.initialized)
return;
strlist__delete(symbol_conf.sym_list);
strlist__delete(symbol_conf.dso_list);
strlist__delete(symbol_conf.comm_list);
intlist__delete(symbol_conf.tid_list);
intlist__delete(symbol_conf.pid_list);
vmlinux_path__exit();
symbol_conf.sym_list = symbol_conf.dso_list = symbol_conf.comm_list = NULL;
symbol_conf.initialized = false;
}
int symbol__config_symfs(const struct option *opt __maybe_unused,
const char *dir, int unset __maybe_unused)
{
char *bf = NULL;
int ret;
symbol_conf.symfs = strdup(dir);
if (symbol_conf.symfs == NULL)
return -ENOMEM;
/* skip the locally configured cache if a symfs is given, and
* config buildid dir to symfs/.debug
*/
ret = asprintf(&bf, "%s/%s", dir, ".debug");
if (ret < 0)
return -ENOMEM;
set_buildid_dir(bf);
free(bf);
return 0;
}