From 6bb536cc4b06df70012cec6168cc1788e200bc9d Mon Sep 17 00:00:00 2001 From: Wang Nan Date: Fri, 29 May 2015 09:45:47 +0000 Subject: [PATCH 1/6] perf probe: Fix segfault when glob matching function without debuginfo Commit 4c859351226c920b227fec040a3b447f0d482af3 ("perf probe: Support glob wildcards for function name") introduces segfault problems when debuginfo is not available: # perf probe 'sys_w*' Added new events: Segmentation fault The first problem resides in find_probe_trace_events_from_map(). In that function, find_probe_functions() is called to match each symbol against glob to find the number of matching functions, but still use map__for_each_symbol_by_name() to find 'struct symbol' for matching functions. Unfortunately, map__for_each_symbol_by_name() does exact matching by searching in an rbtree. It doesn't know glob matching, and not easy for it to support it because it use rbtree based binary search, but we are unable to ensure all names matched by the glob (any glob passed by user) reside in one subtree. This patch drops map__for_each_symbol_by_name(). Since there is no rbtree again, re-matching all symbols costs a lot. This patch avoid it by saving all matching results into an array (syms). The second problem is the lost of tp->realname. In __add_probe_trace_events(), if pev->point.function is glob, the event name should be set to tev->point.realname. This patch ensures its existence by strdup sym->name instead of leaving a NULL pointer there. After this patch: # perf probe 'sys_w*' Added new events: probe:sys_waitid (on sys_w*) probe:sys_wait4 (on sys_w*) probe:sys_waitpid (on sys_w*) probe:sys_write (on sys_w*) probe:sys_writev (on sys_w*) You can now use it in all perf tools, such as: perf record -e probe:sys_writev -aR sleep 1 Signed-off-by: Wang Nan Acked-by: Masami Hiramatsu Cc: Jiri Olsa Cc: Namhyung Kim Cc: Zefan Li Link: http://lkml.kernel.org/r/1432892747-232506-1-git-send-email-wangnan0@huawei.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/probe-event.c | 26 +++++++++++++++++++++----- 1 file changed, 21 insertions(+), 5 deletions(-) diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index d27edef5eb5b..e6f215b7a052 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -2494,7 +2494,8 @@ close_out: return ret; } -static int find_probe_functions(struct map *map, char *name) +static int find_probe_functions(struct map *map, char *name, + struct symbol **syms) { int found = 0; struct symbol *sym; @@ -2504,8 +2505,11 @@ static int find_probe_functions(struct map *map, char *name) return 0; map__for_each_symbol(map, sym, tmp) { - if (strglobmatch(sym->name, name)) + if (strglobmatch(sym->name, name)) { found++; + if (syms && found < probe_conf.max_probes) + syms[found - 1] = sym; + } } return found; @@ -2528,11 +2532,12 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev, struct map *map = NULL; struct ref_reloc_sym *reloc_sym = NULL; struct symbol *sym; + struct symbol **syms = NULL; struct probe_trace_event *tev; struct perf_probe_point *pp = &pev->point; struct probe_trace_point *tp; int num_matched_functions; - int ret, i; + int ret, i, j; map = get_target_map(pev->target, pev->uprobes); if (!map) { @@ -2540,11 +2545,17 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev, goto out; } + syms = malloc(sizeof(struct symbol *) * probe_conf.max_probes); + if (!syms) { + ret = -ENOMEM; + goto out; + } + /* * Load matched symbols: Since the different local symbols may have * same name but different addresses, this lists all the symbols. */ - num_matched_functions = find_probe_functions(map, pp->function); + num_matched_functions = find_probe_functions(map, pp->function, syms); if (num_matched_functions == 0) { pr_err("Failed to find symbol %s in %s\n", pp->function, pev->target ? : "kernel"); @@ -2575,7 +2586,9 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev, ret = 0; - map__for_each_symbol_by_name(map, pp->function, sym) { + for (j = 0; j < num_matched_functions; j++) { + sym = syms[j]; + tev = (*tevs) + ret; tp = &tev->point; if (ret == num_matched_functions) { @@ -2599,6 +2612,8 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev, tp->symbol = strdup_or_goto(sym->name, nomem_out); tp->offset = pp->offset; } + tp->realname = strdup_or_goto(sym->name, nomem_out); + tp->retprobe = pp->retprobe; if (pev->target) tev->point.module = strdup_or_goto(pev->target, @@ -2629,6 +2644,7 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev, out: put_target_map(map, pev->uprobes); + free(syms); return ret; nomem_out: From 9ecae065f3295d7ea5e1c5492170a848ca255a46 Mon Sep 17 00:00:00 2001 From: Madhavan Srinivasan Date: Sun, 31 May 2015 11:36:23 +0530 Subject: [PATCH 2/6] perf tools: Remove newline char when reading event scale and unit The commit intruduced the perf_event_sysfs_show function to display the event_str value of an attr in kernel/event/core.c. But the function returns the value with a newline char. So, if a event also carries a event.unit file, when printing the counter data perf tool formatting goes for a spin. That is, because of the event unit, event name is printed in the newline because of perf_event_sysfs_show returns with a newline char. Now fixing perf core will break API, hencing proposing a fix in the perf tool. Signed-off-by: Madhavan Srinivasan Cc: Jiri Olsa Cc: Michael Ellerman Cc: Peter Zijlstra Cc: Sukadev Bhattiprolu Link: http://lkml.kernel.org/r/1433052383-21802-1-git-send-email-maddy@linux.vnet.ibm.com [ Add spaces around operators ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/pmu.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index 5d3ab7c8ceaf..0fcc624eb767 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -112,7 +112,11 @@ static int perf_pmu__parse_scale(struct perf_pmu_alias *alias, char *dir, char * if (sret < 0) goto error; - scale[sret] = '\0'; + if (scale[sret - 1] == '\n') + scale[sret - 1] = '\0'; + else + scale[sret] = '\0'; + /* * save current locale */ @@ -154,7 +158,10 @@ static int perf_pmu__parse_unit(struct perf_pmu_alias *alias, char *dir, char *n close(fd); - alias->unit[sret] = '\0'; + if (alias->unit[sret - 1] == '\n') + alias->unit[sret - 1] = '\0'; + else + alias->unit[sret] = '\0'; return 0; error: From 0443f36b0de026143a78c858aac773572f7dd5db Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 2 Jun 2015 11:28:13 -0300 Subject: [PATCH 3/6] perf machine: Fix the search for the kernel DSO on the unified list When unifying the user_dsos and kernel_dsos a bug was introduced by inverting the check for dso->kernel, fix it. Fixes: 3d39ac538629 ("perf machine: No need to have two DSOs lists") Cc: Adrian Hunter Cc: David Ahern Cc: Jiri Olsa Cc: Namhyung Kim Link: http://lkml.kernel.org/n/tip-xnrnq0kams3s2z9ek1wjb506@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/machine.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 2ed61f59d415..4e29e80932e5 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -1149,7 +1149,7 @@ static int machine__process_kernel_mmap_event(struct machine *machine, struct dso *dso; list_for_each_entry(dso, &machine->dsos.head, node) { - if (dso->kernel && is_kernel_module(dso->long_name)) + if (!dso->kernel || is_kernel_module(dso->long_name)) continue; kernel = dso; From 37fbe0a4a0a9afe3b0fe843a4775a85ccf430deb Mon Sep 17 00:00:00 2001 From: Wang Nan Date: Mon, 1 Jun 2015 07:37:47 +0000 Subject: [PATCH 4/6] perf tools: Move linux/kernel.h to tools/include This patch moves kernel.h from tools/perf/util/include/linux/kernel.h to tools/include/linux/kernel.h to enable other libraries use macros in it, like libbpf which will be introduced by further patches. MANIFEST is also updated for 'make perf-*-src-pkg'. Signed-off-by: Wang Nan Acked-by: Alexei Starovoitov Cc: Brendan Gregg Cc: Daniel Borkmann Cc: David Ahern Cc: He Kuang Cc: Jiri Olsa Cc: Kaixu Xia Cc: Masami Hiramatsu Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Zefan Li Cc: pi3orama@163.com Link: http://lkml.kernel.org/r/1433144296-74992-2-git-send-email-wangnan0@huawei.com [ Fixed up the ifdef guard to match other entries in tools/include/linux ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/{perf/util => }/include/linux/kernel.h | 4 ++-- tools/perf/MANIFEST | 1 + 2 files changed, 3 insertions(+), 2 deletions(-) rename tools/{perf/util => }/include/linux/kernel.h (97%) diff --git a/tools/perf/util/include/linux/kernel.h b/tools/include/linux/kernel.h similarity index 97% rename from tools/perf/util/include/linux/kernel.h rename to tools/include/linux/kernel.h index 09e8e7aea7c6..76df53539c2a 100644 --- a/tools/perf/util/include/linux/kernel.h +++ b/tools/include/linux/kernel.h @@ -1,5 +1,5 @@ -#ifndef PERF_LINUX_KERNEL_H_ -#define PERF_LINUX_KERNEL_H_ +#ifndef __TOOLS_LINUX_KERNEL_H +#define __TOOLS_LINUX_KERNEL_H #include #include diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST index a83cf75164e1..fce4a47347aa 100644 --- a/tools/perf/MANIFEST +++ b/tools/perf/MANIFEST @@ -40,6 +40,7 @@ tools/include/linux/bitops.h tools/include/linux/compiler.h tools/include/linux/export.h tools/include/linux/hash.h +tools/include/linux/kernel.h tools/include/linux/log2.h tools/include/linux/types.h include/asm-generic/bitops/arch_hweight.h From 4fc62a89dc607cee4f75f6dbb102cd6215fd0d64 Mon Sep 17 00:00:00 2001 From: Wang Nan Date: Mon, 1 Jun 2015 07:37:48 +0000 Subject: [PATCH 5/6] tools: Move tools/perf/util/include/linux/{list.h,poison.h} to tools/include This patch moves list.h from tools/perf/util/include/linux/list.h to tools/include/linux/list.h to enable other libraries use macros in it, like libbpf which will be introduced by further patches. Since list.h depend on poison.h, poison.h is also moved. Both file use relative path, so one '..' is removed for each header to make them suit for new directory. MANIFEST is also updated for 'make perf-*-src-pkg'. Signed-off-by: Wang Nan Cc: Alexei Starovoitov Cc: Brendan Gregg Cc: Daniel Borkmann Cc: David Ahern Cc: He Kuang Cc: Jiri Olsa Cc: Kaixu Xia Cc: Masami Hiramatsu Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Zefan Li Cc: pi3orama@163.com Link: http://lkml.kernel.org/r/1433144296-74992-3-git-send-email-wangnan0@huawei.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/{perf/util => }/include/linux/list.h | 6 +++--- tools/include/linux/poison.h | 1 + tools/perf/MANIFEST | 2 ++ tools/perf/util/include/linux/poison.h | 1 - 4 files changed, 6 insertions(+), 4 deletions(-) rename tools/{perf/util => }/include/linux/list.h (90%) create mode 100644 tools/include/linux/poison.h delete mode 100644 tools/perf/util/include/linux/poison.h diff --git a/tools/perf/util/include/linux/list.h b/tools/include/linux/list.h similarity index 90% rename from tools/perf/util/include/linux/list.h rename to tools/include/linux/list.h index 76ddbc726343..76b014c96893 100644 --- a/tools/perf/util/include/linux/list.h +++ b/tools/include/linux/list.h @@ -1,10 +1,10 @@ #include #include -#include "../../../../include/linux/list.h" +#include "../../../include/linux/list.h" -#ifndef PERF_LIST_H -#define PERF_LIST_H +#ifndef TOOLS_LIST_H +#define TOOLS_LIST_H /** * list_del_range - deletes range of entries from list. * @begin: first element in the range to delete from the list. diff --git a/tools/include/linux/poison.h b/tools/include/linux/poison.h new file mode 100644 index 000000000000..0c27bdf14233 --- /dev/null +++ b/tools/include/linux/poison.h @@ -0,0 +1 @@ +#include "../../../include/linux/poison.h" diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST index fce4a47347aa..a0bdd6124583 100644 --- a/tools/perf/MANIFEST +++ b/tools/perf/MANIFEST @@ -41,7 +41,9 @@ tools/include/linux/compiler.h tools/include/linux/export.h tools/include/linux/hash.h tools/include/linux/kernel.h +tools/include/linux/list.h tools/include/linux/log2.h +tools/include/linux/poison.h tools/include/linux/types.h include/asm-generic/bitops/arch_hweight.h include/asm-generic/bitops/const_hweight.h diff --git a/tools/perf/util/include/linux/poison.h b/tools/perf/util/include/linux/poison.h deleted file mode 100644 index fef6dbc9ce13..000000000000 --- a/tools/perf/util/include/linux/poison.h +++ /dev/null @@ -1 +0,0 @@ -#include "../../../../include/linux/poison.h" From 1f121b03d058dd07199d8924373d3c52a207f63b Mon Sep 17 00:00:00 2001 From: Wang Nan Date: Wed, 3 Jun 2015 08:52:21 +0000 Subject: [PATCH 6/6] perf tools: Deal with kernel module names in '[]' correctly Before patch ba92732e9808 ('perf kmaps: Check kmaps to make code more robust'), 'perf report' and 'perf annotate' will segfault if trace data contains kernel module information like this: # perf report -D -i ./perf.data ... 0 0 0x188 [0x50]: PERF_RECORD_MMAP -1/0: [0xffffffbff1018000(0xf068000) @ 0]: x [test_module] ... # perf report -i ./perf.data --objdump=/path/to/objdump --kallsyms=/path/to/kallsyms perf: Segmentation fault -------- backtrace -------- /path/to/perf[0x503478] /lib64/libc.so.6(+0x3545f)[0x7fb201f3745f] /path/to/perf[0x499b56] /path/to/perf(dso__load_kallsyms+0x13c)[0x49b56c] /path/to/perf(dso__load+0x72e)[0x49c21e] /path/to/perf(map__load+0x6e)[0x4ae9ee] /path/to/perf(thread__find_addr_map+0x24c)[0x47deec] /path/to/perf(perf_event__preprocess_sample+0x88)[0x47e238] /path/to/perf[0x43ad02] /path/to/perf[0x4b55bc] /path/to/perf(ordered_events__flush+0xca)[0x4b57ea] /path/to/perf[0x4b1a01] /path/to/perf(perf_session__process_events+0x3be)[0x4b428e] /path/to/perf(cmd_report+0xf11)[0x43bfc1] /path/to/perf[0x474702] /path/to/perf(main+0x5f5)[0x42de95] /lib64/libc.so.6(__libc_start_main+0xf4)[0x7fb201f23bd4] /path/to/perf[0x42dfc4] This is because __kmod_path__parse treats '[' leading names as kernel name instead of names of kernel module. If perf.data contains build information and the buildid of such modules can be found, the dso->kernel of it will be set to DSO_TYPE_KERNEL by __event_process_build_id(), not kernel module. It will then be passed to dso__load() -> dso__load_kernel_sym() -> dso__load_kcore() if --kallsyms is provided. The refered patch adds NULL pointer checker to avoid segfault. However, such kernel modules are still processed incorrectly. This patch fixes __kmod_path__parse, makes it treat names like '[test_module]' as kernel modules. kmod-path.c is also update to reflect the above changes. Signed-off-by: Wang Nan Acked-by: Jiri Olsa Cc: Namhyung Kim Cc: Zefan Li Link: http://lkml.kernel.org/r/1433321541-170245-1-git-send-email-wangnan0@huawei.com [ Fixed the merged with 0443f36b0de0 ("perf machine: Fix the search for the kernel DSO on the unified list" ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/kmod-path.c | 72 ++++++++++++++++++++++++++++++++++++ tools/perf/util/dso.c | 45 ++++++++++++++++++++-- tools/perf/util/dso.h | 2 +- tools/perf/util/header.c | 8 ++-- tools/perf/util/machine.c | 22 ++++++++++- 5 files changed, 139 insertions(+), 10 deletions(-) diff --git a/tools/perf/tests/kmod-path.c b/tools/perf/tests/kmod-path.c index e8d7cbb9320c..08c433b4bf4f 100644 --- a/tools/perf/tests/kmod-path.c +++ b/tools/perf/tests/kmod-path.c @@ -34,9 +34,21 @@ static int test(const char *path, bool alloc_name, bool alloc_ext, return 0; } +static int test_is_kernel_module(const char *path, int cpumode, bool expect) +{ + TEST_ASSERT_VAL("is_kernel_module", + (!!is_kernel_module(path, cpumode)) == (!!expect)); + pr_debug("%s (cpumode: %d) - is_kernel_module: %s\n", + path, cpumode, expect ? "true" : "false"); + return 0; +} + #define T(path, an, ae, k, c, n, e) \ TEST_ASSERT_VAL("failed", !test(path, an, ae, k, c, n, e)) +#define M(path, c, e) \ + TEST_ASSERT_VAL("failed", !test_is_kernel_module(path, c, e)) + int test__kmod_path__parse(void) { /* path alloc_name alloc_ext kmod comp name ext */ @@ -44,30 +56,90 @@ int test__kmod_path__parse(void) T("/xxxx/xxxx/x-x.ko", false , true , true, false, NULL , NULL); T("/xxxx/xxxx/x-x.ko", true , false , true, false, "[x_x]", NULL); T("/xxxx/xxxx/x-x.ko", false , false , true, false, NULL , NULL); + M("/xxxx/xxxx/x-x.ko", PERF_RECORD_MISC_CPUMODE_UNKNOWN, true); + M("/xxxx/xxxx/x-x.ko", PERF_RECORD_MISC_KERNEL, true); + M("/xxxx/xxxx/x-x.ko", PERF_RECORD_MISC_USER, false); /* path alloc_name alloc_ext kmod comp name ext */ T("/xxxx/xxxx/x.ko.gz", true , true , true, true, "[x]", "gz"); T("/xxxx/xxxx/x.ko.gz", false , true , true, true, NULL , "gz"); T("/xxxx/xxxx/x.ko.gz", true , false , true, true, "[x]", NULL); T("/xxxx/xxxx/x.ko.gz", false , false , true, true, NULL , NULL); + M("/xxxx/xxxx/x.ko.gz", PERF_RECORD_MISC_CPUMODE_UNKNOWN, true); + M("/xxxx/xxxx/x.ko.gz", PERF_RECORD_MISC_KERNEL, true); + M("/xxxx/xxxx/x.ko.gz", PERF_RECORD_MISC_USER, false); /* path alloc_name alloc_ext kmod comp name ext */ T("/xxxx/xxxx/x.gz", true , true , false, true, "x.gz" ,"gz"); T("/xxxx/xxxx/x.gz", false , true , false, true, NULL ,"gz"); T("/xxxx/xxxx/x.gz", true , false , false, true, "x.gz" , NULL); T("/xxxx/xxxx/x.gz", false , false , false, true, NULL , NULL); + M("/xxxx/xxxx/x.gz", PERF_RECORD_MISC_CPUMODE_UNKNOWN, false); + M("/xxxx/xxxx/x.gz", PERF_RECORD_MISC_KERNEL, false); + M("/xxxx/xxxx/x.gz", PERF_RECORD_MISC_USER, false); /* path alloc_name alloc_ext kmod comp name ext */ T("x.gz", true , true , false, true, "x.gz", "gz"); T("x.gz", false , true , false, true, NULL , "gz"); T("x.gz", true , false , false, true, "x.gz", NULL); T("x.gz", false , false , false, true, NULL , NULL); + M("x.gz", PERF_RECORD_MISC_CPUMODE_UNKNOWN, false); + M("x.gz", PERF_RECORD_MISC_KERNEL, false); + M("x.gz", PERF_RECORD_MISC_USER, false); /* path alloc_name alloc_ext kmod comp name ext */ T("x.ko.gz", true , true , true, true, "[x]", "gz"); T("x.ko.gz", false , true , true, true, NULL , "gz"); T("x.ko.gz", true , false , true, true, "[x]", NULL); T("x.ko.gz", false , false , true, true, NULL , NULL); + M("x.ko.gz", PERF_RECORD_MISC_CPUMODE_UNKNOWN, true); + M("x.ko.gz", PERF_RECORD_MISC_KERNEL, true); + M("x.ko.gz", PERF_RECORD_MISC_USER, false); + + /* path alloc_name alloc_ext kmod comp name ext */ + T("[test_module]", true , true , true, false, "[test_module]", NULL); + T("[test_module]", false , true , true, false, NULL , NULL); + T("[test_module]", true , false , true, false, "[test_module]", NULL); + T("[test_module]", false , false , true, false, NULL , NULL); + M("[test_module]", PERF_RECORD_MISC_CPUMODE_UNKNOWN, true); + M("[test_module]", PERF_RECORD_MISC_KERNEL, true); + M("[test_module]", PERF_RECORD_MISC_USER, false); + + /* path alloc_name alloc_ext kmod comp name ext */ + T("[test.module]", true , true , true, false, "[test.module]", NULL); + T("[test.module]", false , true , true, false, NULL , NULL); + T("[test.module]", true , false , true, false, "[test.module]", NULL); + T("[test.module]", false , false , true, false, NULL , NULL); + M("[test.module]", PERF_RECORD_MISC_CPUMODE_UNKNOWN, true); + M("[test.module]", PERF_RECORD_MISC_KERNEL, true); + M("[test.module]", PERF_RECORD_MISC_USER, false); + + /* path alloc_name alloc_ext kmod comp name ext */ + T("[vdso]", true , true , false, false, "[vdso]", NULL); + T("[vdso]", false , true , false, false, NULL , NULL); + T("[vdso]", true , false , false, false, "[vdso]", NULL); + T("[vdso]", false , false , false, false, NULL , NULL); + M("[vdso]", PERF_RECORD_MISC_CPUMODE_UNKNOWN, false); + M("[vdso]", PERF_RECORD_MISC_KERNEL, false); + M("[vdso]", PERF_RECORD_MISC_USER, false); + + /* path alloc_name alloc_ext kmod comp name ext */ + T("[vsyscall]", true , true , false, false, "[vsyscall]", NULL); + T("[vsyscall]", false , true , false, false, NULL , NULL); + T("[vsyscall]", true , false , false, false, "[vsyscall]", NULL); + T("[vsyscall]", false , false , false, false, NULL , NULL); + M("[vsyscall]", PERF_RECORD_MISC_CPUMODE_UNKNOWN, false); + M("[vsyscall]", PERF_RECORD_MISC_KERNEL, false); + M("[vsyscall]", PERF_RECORD_MISC_USER, false); + + /* path alloc_name alloc_ext kmod comp name ext */ + T("[kernel.kallsyms]", true , true , false, false, "[kernel.kallsyms]", NULL); + T("[kernel.kallsyms]", false , true , false, false, NULL , NULL); + T("[kernel.kallsyms]", true , false , false, false, "[kernel.kallsyms]", NULL); + T("[kernel.kallsyms]", false , false , false, false, NULL , NULL); + M("[kernel.kallsyms]", PERF_RECORD_MISC_CPUMODE_UNKNOWN, false); + M("[kernel.kallsyms]", PERF_RECORD_MISC_KERNEL, false); + M("[kernel.kallsyms]", PERF_RECORD_MISC_USER, false); return 0; } diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c index b335db3532a2..5ec9e892c89b 100644 --- a/tools/perf/util/dso.c +++ b/tools/perf/util/dso.c @@ -166,12 +166,28 @@ bool is_supported_compression(const char *ext) return false; } -bool is_kernel_module(const char *pathname) +bool is_kernel_module(const char *pathname, int cpumode) { struct kmod_path m; + int mode = cpumode & PERF_RECORD_MISC_CPUMODE_MASK; - if (kmod_path__parse(&m, pathname)) - return NULL; + WARN_ONCE(mode != cpumode, + "Internal error: passing unmasked cpumode (%x) to is_kernel_module", + cpumode); + + switch (mode) { + case PERF_RECORD_MISC_USER: + case PERF_RECORD_MISC_HYPERVISOR: + case PERF_RECORD_MISC_GUEST_USER: + return false; + /* Treat PERF_RECORD_MISC_CPUMODE_UNKNOWN as kernel */ + default: + if (kmod_path__parse(&m, pathname)) { + pr_err("Failed to check whether %s is a kernel module or not. Assume it is.", + pathname); + return true; + } + } return m.kmod; } @@ -215,12 +231,33 @@ int __kmod_path__parse(struct kmod_path *m, const char *path, { const char *name = strrchr(path, '/'); const char *ext = strrchr(path, '.'); + bool is_simple_name = false; memset(m, 0x0, sizeof(*m)); name = name ? name + 1 : path; + /* + * '.' is also a valid character for module name. For example: + * [aaa.bbb] is a valid module name. '[' should have higher + * priority than '.ko' suffix. + * + * The kernel names are from machine__mmap_name. Such + * name should belong to kernel itself, not kernel module. + */ + if (name[0] == '[') { + is_simple_name = true; + if ((strncmp(name, "[kernel.kallsyms]", 17) == 0) || + (strncmp(name, "[guest.kernel.kallsyms", 22) == 0) || + (strncmp(name, "[vdso]", 6) == 0) || + (strncmp(name, "[vsyscall]", 10) == 0)) { + m->kmod = false; + + } else + m->kmod = true; + } + /* No extension, just return name. */ - if (ext == NULL) { + if ((ext == NULL) || is_simple_name) { if (alloc_name) { m->name = strdup(name); return m->name ? 0 : -ENOMEM; diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h index 24a507a54147..ba2d90ed881f 100644 --- a/tools/perf/util/dso.h +++ b/tools/perf/util/dso.h @@ -220,7 +220,7 @@ char dso__symtab_origin(const struct dso *dso); int dso__read_binary_type_filename(const struct dso *dso, enum dso_binary_type type, char *root_dir, char *filename, size_t size); bool is_supported_compression(const char *ext); -bool is_kernel_module(const char *pathname); +bool is_kernel_module(const char *pathname, int cpumode); bool decompress_to_file(const char *ext, const char *filename, int output_fd); bool dso__needs_decompress(struct dso *dso); diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 851143a7988d..ac5aaaeed7ff 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -1239,7 +1239,7 @@ static int __event_process_build_id(struct build_id_event *bev, { int err = -1; struct machine *machine; - u16 misc; + u16 cpumode; struct dso *dso; enum dso_kernel_type dso_type; @@ -1247,9 +1247,9 @@ static int __event_process_build_id(struct build_id_event *bev, if (!machine) goto out; - misc = bev->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; + cpumode = bev->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; - switch (misc) { + switch (cpumode) { case PERF_RECORD_MISC_KERNEL: dso_type = DSO_TYPE_KERNEL; break; @@ -1270,7 +1270,7 @@ static int __event_process_build_id(struct build_id_event *bev, dso__set_build_id(dso, &bev->build_id); - if (!is_kernel_module(filename)) + if (!is_kernel_module(filename, cpumode)) dso->kernel = dso_type; build_id__sprintf(dso->build_id, sizeof(dso->build_id), diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 4e29e80932e5..9e02c86f39f5 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -1149,9 +1149,29 @@ static int machine__process_kernel_mmap_event(struct machine *machine, struct dso *dso; list_for_each_entry(dso, &machine->dsos.head, node) { - if (!dso->kernel || is_kernel_module(dso->long_name)) + + /* + * The cpumode passed to is_kernel_module is not the + * cpumode of *this* event. If we insist on passing + * correct cpumode to is_kernel_module, we should + * record the cpumode when we adding this dso to the + * linked list. + * + * However we don't really need passing correct + * cpumode. We know the correct cpumode must be kernel + * mode (if not, we should not link it onto kernel_dsos + * list). + * + * Therefore, we pass PERF_RECORD_MISC_CPUMODE_UNKNOWN. + * is_kernel_module() treats it as a kernel cpumode. + */ + + if (!dso->kernel || + is_kernel_module(dso->long_name, + PERF_RECORD_MISC_CPUMODE_UNKNOWN)) continue; + kernel = dso; break; }