From 89975bd335f37b96ffd3cc24b9effb1fa25e7788 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 20 Sep 2017 16:41:34 -0300 Subject: perf tools: Get all of tools/{arch,include}/ in the MANIFEST Now that I'm switching the container builds from using a local volume pointing to the kernel repository with the perf sources, instead getting a detached tarball to be able to use a container cluster, some places broke because I forgot to put some of the required files in tools/perf/MANIFEST, namely some bitsperlong.h files. So, to fix it do the same as for tools/build/ and pack the whole tools/arch/ directory. Cc: Adrian Hunter Cc: David Ahern Cc: Jiri Olsa Cc: Namhyung Kim Cc: Wang Nan Link: http://lkml.kernel.org/n/tip-wmenpjfjsobwdnfde30qqncj@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/MANIFEST | 87 ++--------------------------------------------------- 1 file changed, 2 insertions(+), 85 deletions(-) (limited to 'tools/perf') diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST index 62072822dc85..627b7cada144 100644 --- a/tools/perf/MANIFEST +++ b/tools/perf/MANIFEST @@ -1,34 +1,8 @@ tools/perf -tools/arch/alpha/include/asm/barrier.h -tools/arch/arm/include/asm/barrier.h -tools/arch/arm64/include/asm/barrier.h -tools/arch/ia64/include/asm/barrier.h -tools/arch/mips/include/asm/barrier.h -tools/arch/powerpc/include/asm/barrier.h -tools/arch/s390/include/asm/barrier.h -tools/arch/sh/include/asm/barrier.h -tools/arch/sparc/include/asm/barrier.h -tools/arch/sparc/include/asm/barrier_32.h -tools/arch/sparc/include/asm/barrier_64.h -tools/arch/tile/include/asm/barrier.h -tools/arch/x86/include/asm/barrier.h -tools/arch/x86/include/asm/cmpxchg.h -tools/arch/x86/include/asm/cpufeatures.h -tools/arch/x86/include/asm/disabled-features.h -tools/arch/x86/include/asm/required-features.h -tools/arch/x86/include/uapi/asm/svm.h -tools/arch/x86/include/uapi/asm/vmx.h -tools/arch/x86/include/uapi/asm/kvm.h -tools/arch/x86/include/uapi/asm/kvm_perf.h -tools/arch/x86/lib/memcpy_64.S -tools/arch/x86/lib/memset_64.S -tools/arch/s390/include/uapi/asm/kvm_perf.h -tools/arch/s390/include/uapi/asm/sie.h -tools/arch/xtensa/include/asm/barrier.h +tools/arch tools/scripts tools/build -tools/arch/x86/include/asm/atomic.h -tools/arch/x86/include/asm/rmwcc.h +tools/include tools/lib/traceevent tools/lib/api tools/lib/bpf @@ -42,60 +16,3 @@ tools/lib/find_bit.c tools/lib/bitmap.c tools/lib/str_error_r.c tools/lib/vsprintf.c -tools/include/asm/alternative-asm.h -tools/include/asm/atomic.h -tools/include/asm/barrier.h -tools/include/asm/bug.h -tools/include/asm-generic/atomic-gcc.h -tools/include/asm-generic/barrier.h -tools/include/asm-generic/bitops/arch_hweight.h -tools/include/asm-generic/bitops/atomic.h -tools/include/asm-generic/bitops/const_hweight.h -tools/include/asm-generic/bitops/__ffs.h -tools/include/asm-generic/bitops/__ffz.h -tools/include/asm-generic/bitops/__fls.h -tools/include/asm-generic/bitops/find.h -tools/include/asm-generic/bitops/fls64.h -tools/include/asm-generic/bitops/fls.h -tools/include/asm-generic/bitops/hweight.h -tools/include/asm-generic/bitops.h -tools/include/linux/atomic.h -tools/include/linux/bitops.h -tools/include/linux/compiler.h -tools/include/linux/compiler-gcc.h -tools/include/linux/coresight-pmu.h -tools/include/linux/bug.h -tools/include/linux/filter.h -tools/include/linux/hash.h -tools/include/linux/kernel.h -tools/include/linux/list.h -tools/include/linux/log2.h -tools/include/uapi/asm-generic/fcntl.h -tools/include/uapi/asm-generic/ioctls.h -tools/include/uapi/asm-generic/mman-common.h -tools/include/uapi/asm-generic/mman.h -tools/include/uapi/drm/drm.h -tools/include/uapi/drm/i915_drm.h -tools/include/uapi/linux/bpf.h -tools/include/uapi/linux/bpf_common.h -tools/include/uapi/linux/fcntl.h -tools/include/uapi/linux/hw_breakpoint.h -tools/include/uapi/linux/kvm.h -tools/include/uapi/linux/mman.h -tools/include/uapi/linux/perf_event.h -tools/include/uapi/linux/sched.h -tools/include/uapi/linux/stat.h -tools/include/uapi/linux/vhost.h -tools/include/uapi/sound/asound.h -tools/include/linux/poison.h -tools/include/linux/rbtree.h -tools/include/linux/rbtree_augmented.h -tools/include/linux/refcount.h -tools/include/linux/string.h -tools/include/linux/stringify.h -tools/include/linux/types.h -tools/include/linux/err.h -tools/include/linux/bitmap.h -tools/include/linux/time64.h -tools/arch/*/include/uapi/asm/mman.h -tools/arch/*/include/uapi/asm/perf_regs.h -- cgit From f1e52f14a69386ac460a8d700df0647a631cf595 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Fri, 22 Sep 2017 15:41:44 -0300 Subject: perf evsel: Fix attr.exclude_kernel setting for default cycles:p Yet another fix for probing the max attr.precise_ip setting: it is not enough settting attr.exclude_kernel for !root users, as they _can_ profile the kernel if the kernel.perf_event_paranoid sysctl is set to -1, so check that as well. Testing it: As non root: $ sysctl kernel.perf_event_paranoid kernel.perf_event_paranoid = 2 $ perf record sleep 1 $ perf evlist -v cycles:uppp: ..., exclude_kernel: 1, ... precise_ip: 3, ... Now as non-root, but with kernel.perf_event_paranoid set set to the most permissive value, -1: $ sysctl kernel.perf_event_paranoid kernel.perf_event_paranoid = -1 $ perf record sleep 1 $ perf evlist -v cycles:ppp: ..., exclude_kernel: 0, ... precise_ip: 3, ... $ I.e. non-root, default kernel.perf_event_paranoid: :uppp modifier = not allowed to sample the kernel, non-root, most permissible kernel.perf_event_paranoid: :ppp = allowed to sample the kernel. In both cases, use the highest available precision: attr.precise_ip = 3. Reported-and-Tested-by: Ingo Molnar Cc: Adrian Hunter Cc: Andy Lutomirski Cc: David Ahern Cc: Jiri Olsa Cc: Namhyung Kim Cc: Wang Nan Fixes: d37a36979077 ("perf evsel: Fix attr.exclude_kernel setting for default cycles:p") Link: http://lkml.kernel.org/n/tip-nj2qkf75xsd6pw6hhjzfqqdx@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/evsel.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'tools/perf') diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 4bb89373eb52..0dccdb89572c 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -271,12 +271,17 @@ struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx) return evsel; } +static bool perf_event_can_profile_kernel(void) +{ + return geteuid() == 0 || perf_event_paranoid() == -1; +} + struct perf_evsel *perf_evsel__new_cycles(bool precise) { struct perf_event_attr attr = { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CPU_CYCLES, - .exclude_kernel = geteuid() != 0, + .exclude_kernel = !perf_event_can_profile_kernel(), }; struct perf_evsel *evsel; -- cgit From 9789e7e93f2b892098d7684ac8131092aa617814 Mon Sep 17 00:00:00 2001 From: Mengting Zhang Date: Sat, 23 Sep 2017 16:18:14 +0800 Subject: perf report: Fix debug messages with --call-graph option With --call-graph option, perf report can display call chains using type, min percent threshold, optional print limit and order. And the default call-graph parameter is 'graph,0.5,caller,function,percent'. Before this patch, 'perf report --call-graph' shows incorrect debug messages as below: # perf report --call-graph Invalid callchain mode: 0.5 Invalid callchain order: 0.5 Invalid callchain sort key: 0.5 Invalid callchain config key: 0.5 Invalid callchain mode: caller Invalid callchain mode: function Invalid callchain order: function Invalid callchain mode: percent Invalid callchain order: percent Invalid callchain sort key: percent That is because in function __parse_callchain_report_opt(),each field of the call-graph parameter is passed to parse_callchain_{mode,order, sort_key,value} in turn until it meets the matching value. For example, the order field "caller" is passed to parse_callchain_mode() firstly and obviously it doesn't match any mode field. Therefore parse_callchain_mode() will shows the debug message "Invalid callchain mode: caller", which could confuse users. The patch fixes this issue by moving the warning out of the function parse_callchain_{mode,order,sort_key,value}. Signed-off-by: Mengting Zhang Acked-by: Jiri Olsa Tested-by: Arnaldo Carvalho de Melo Cc: Alexander Shishkin Cc: Andi Kleen Cc: Krister Johansen Cc: Li Bin Cc: Milian Wolff Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Wang Nan Cc: Yao Jin Link: http://lkml.kernel.org/r/1506154694-39691-1-git-send-email-zhangmengting@huawei.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/callchain.c | 35 +++++++++++++++++++++-------------- 1 file changed, 21 insertions(+), 14 deletions(-) (limited to 'tools/perf') diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c index 510b513e0f01..be09d77cade0 100644 --- a/tools/perf/util/callchain.c +++ b/tools/perf/util/callchain.c @@ -65,8 +65,6 @@ static int parse_callchain_mode(const char *value) callchain_param.mode = CHAIN_FOLDED; return 0; } - - pr_err("Invalid callchain mode: %s\n", value); return -1; } @@ -82,8 +80,6 @@ static int parse_callchain_order(const char *value) callchain_param.order_set = true; return 0; } - - pr_err("Invalid callchain order: %s\n", value); return -1; } @@ -105,8 +101,6 @@ static int parse_callchain_sort_key(const char *value) callchain_param.branch_callstack = 1; return 0; } - - pr_err("Invalid callchain sort key: %s\n", value); return -1; } @@ -124,8 +118,6 @@ static int parse_callchain_value(const char *value) callchain_param.value = CCVAL_COUNT; return 0; } - - pr_err("Invalid callchain config key: %s\n", value); return -1; } @@ -319,12 +311,27 @@ int perf_callchain_config(const char *var, const char *value) return ret; } - if (!strcmp(var, "print-type")) - return parse_callchain_mode(value); - if (!strcmp(var, "order")) - return parse_callchain_order(value); - if (!strcmp(var, "sort-key")) - return parse_callchain_sort_key(value); + if (!strcmp(var, "print-type")){ + int ret; + ret = parse_callchain_mode(value); + if (ret == -1) + pr_err("Invalid callchain mode: %s\n", value); + return ret; + } + if (!strcmp(var, "order")){ + int ret; + ret = parse_callchain_order(value); + if (ret == -1) + pr_err("Invalid callchain order: %s\n", value); + return ret; + } + if (!strcmp(var, "sort-key")){ + int ret; + ret = parse_callchain_sort_key(value); + if (ret == -1) + pr_err("Invalid callchain sort key: %s\n", value); + return ret; + } if (!strcmp(var, "threshold")) { callchain_param.min_percent = strtod(value, &endptr); if (value == endptr) { -- cgit From 090657c9fb7094e4c1b05c1713d6c2a12ef43dea Mon Sep 17 00:00:00 2001 From: Akemi Yagi Date: Fri, 22 Sep 2017 22:11:53 +0000 Subject: perf tools: Fix syscalltbl build failure The build of kernel v4.14-rc1 for i686 fails on RHEL 6 with the error in tools/perf: util/syscalltbl.c:157: error: expected ';', ',' or ')' before '__maybe_unused' mv: cannot stat `util/.syscalltbl.o.tmp': No such file or directory Fix it by placing/moving: #include outside of #ifdef HAVE_SYSCALL_TABLE block. Signed-off-by: Akemi Yagi Cc: Alan Bartlett Link: http://lkml.kernel.org/r/oq41r8$1v9$1@blaine.gmane.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/syscalltbl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools/perf') diff --git a/tools/perf/util/syscalltbl.c b/tools/perf/util/syscalltbl.c index 19e5db90394c..6eea7cff3d4e 100644 --- a/tools/perf/util/syscalltbl.c +++ b/tools/perf/util/syscalltbl.c @@ -15,9 +15,9 @@ #include "syscalltbl.h" #include +#include #ifdef HAVE_SYSCALL_TABLE -#include #include #include "string2.h" #include "util.h" -- cgit From b28503a3fe6400757817e4460090f96bc1b9d6e7 Mon Sep 17 00:00:00 2001 From: Thomas Richter Date: Fri, 15 Sep 2017 09:14:03 +0200 Subject: perf test: Fix vmlinux failure on s390x On s390x perf test 1 failed. It turned out that commit 4a084ecfc821 ("perf report: Fix module symbol adjustment for s390x") was incorrect. The previous implementation in dso__load_sym() is also suitable for s390x. Therefore this patch undoes commit 4a084ecfc821. Signed-off-by: Thomas-Mich Richter Cc: Hendrik Brueckner Cc: Zvonko Kosic Fixes: 4a084ecfc821 ("perf report: Fix module symbol adjustment for s390x") LPU-Reference: 20170915071404.58398-1-tmricht@linux.vnet.ibm.com Link: http://lkml.kernel.org/n/tip-5ani7ly57zji7s0hmzkx416l@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/arch/s390/util/sym-handling.c | 8 -------- tools/perf/util/symbol-elf.c | 8 +------- tools/perf/util/symbol.h | 3 --- 3 files changed, 1 insertion(+), 18 deletions(-) (limited to 'tools/perf') diff --git a/tools/perf/arch/s390/util/sym-handling.c b/tools/perf/arch/s390/util/sym-handling.c index e103f6e46afe..581d4c5a896b 100644 --- a/tools/perf/arch/s390/util/sym-handling.c +++ b/tools/perf/arch/s390/util/sym-handling.c @@ -18,12 +18,4 @@ bool elf__needs_adjust_symbols(GElf_Ehdr ehdr) return false; return ehdr.e_type == ET_REL || ehdr.e_type == ET_DYN; } - -void arch__adjust_sym_map_offset(GElf_Sym *sym, - GElf_Shdr *shdr __maybe_unused, - struct map *map) -{ - if (map->type == MAP__FUNCTION) - sym->st_value += map->start; -} #endif diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 5c39f420111e..9cf781f0d8a2 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -810,12 +810,6 @@ static u64 ref_reloc(struct kmap *kmap) void __weak arch__sym_update(struct symbol *s __maybe_unused, GElf_Sym *sym __maybe_unused) { } -void __weak arch__adjust_sym_map_offset(GElf_Sym *sym, GElf_Shdr *shdr, - struct map *map __maybe_unused) -{ - sym->st_value -= shdr->sh_addr - shdr->sh_offset; -} - int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss, struct symsrc *runtime_ss, int kmodule) { @@ -996,7 +990,7 @@ int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss, /* Adjust symbol to map to file offset */ if (adjust_kernel_syms) - arch__adjust_sym_map_offset(&sym, &shdr, map); + sym.st_value -= shdr.sh_addr - shdr.sh_offset; if (strcmp(section_name, (curr_dso->short_name + diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index 2bd6a1f01a1c..aad99e7e179b 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -344,9 +344,6 @@ int setup_intlist(struct intlist **list, const char *list_str, #ifdef HAVE_LIBELF_SUPPORT bool elf__needs_adjust_symbols(GElf_Ehdr ehdr); void arch__sym_update(struct symbol *s, GElf_Sym *sym); -void arch__adjust_sym_map_offset(GElf_Sym *sym, - GElf_Shdr *shdr __maybe_unused, - struct map *map __maybe_unused); #endif #define SYMBOL_A 0 -- cgit From 5357413f5c067f60933e4b8d79d483fbe62b2bb5 Mon Sep 17 00:00:00 2001 From: Thomas Richter Date: Fri, 15 Sep 2017 09:14:04 +0200 Subject: perf test: Fix vmlinux failure on s390x part 2 On s390x perf test 1 failed. It turned out that commit cf6383f73cf2 ("perf report: Fix kernel symbol adjustment for s390x") was incorrect. The previous implementation in dso__load_sym() is also suitable for s390x. Therefore this patch undoes commit cf6383f73cf2 Signed-off-by: Thomas-Mich Richter Cc: Zvonko Kosic Cc: Hendrik Brueckner Fixes: cf6383f73cf2 ("perf report: Fix kernel symbol adjustment for s390x") LPU-Reference: 20170915071404.58398-2-tmricht@linux.vnet.ibm.com Link: http://lkml.kernel.org/n/tip-v101o8k25vuja2ogosgf15yy@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/arch/s390/util/Build | 1 - tools/perf/arch/s390/util/sym-handling.c | 21 --------------------- 2 files changed, 22 deletions(-) delete mode 100644 tools/perf/arch/s390/util/sym-handling.c (limited to 'tools/perf') diff --git a/tools/perf/arch/s390/util/Build b/tools/perf/arch/s390/util/Build index bd518b623d7a..5bd7b9260cc0 100644 --- a/tools/perf/arch/s390/util/Build +++ b/tools/perf/arch/s390/util/Build @@ -1,5 +1,4 @@ libperf-y += header.o -libperf-y += sym-handling.o libperf-y += kvm-stat.o libperf-$(CONFIG_DWARF) += dwarf-regs.o diff --git a/tools/perf/arch/s390/util/sym-handling.c b/tools/perf/arch/s390/util/sym-handling.c deleted file mode 100644 index 581d4c5a896b..000000000000 --- a/tools/perf/arch/s390/util/sym-handling.c +++ /dev/null @@ -1,21 +0,0 @@ -/* - * Architecture specific ELF symbol handling and relocation mapping. - * - * Copyright 2017 IBM Corp. - * Author(s): Thomas Richter - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License (version 2 only) - * as published by the Free Software Foundation. - */ - -#include "symbol.h" - -#ifdef HAVE_LIBELF_SUPPORT -bool elf__needs_adjust_symbols(GElf_Ehdr ehdr) -{ - if (ehdr.e_type == ET_EXEC) - return false; - return ehdr.e_type == ET_REL || ehdr.e_type == ET_DYN; -} -#endif -- cgit