From 7949ba1fa249caa7e611abb8d92f40b0a46c8617 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Sat, 10 Jan 2015 19:33:48 +0900 Subject: [PATCH 01/10] perf probe: Propagate error code when write(2) failed When it failed to write probe commands to the probe_event file in debugfs, it needs to propagate the error code properly. Current code blindly uses the return value of the write(2) so it always uses -1 (-EPERM) and it might confuse users. Signed-off-by: Namhyung Kim Acked-by: Masami Hiramatsu Cc: David Ahern Cc: Ingo Molnar Cc: Jiri Olsa Cc: Masami Hiramatsu Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1420886028-15135-4-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/probe-event.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index 7f9b8632e433..94a717bf007d 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -2052,9 +2052,11 @@ static int write_probe_trace_event(int fd, struct probe_trace_event *tev) pr_debug("Writing event: %s\n", buf); if (!probe_event_dry_run) { ret = write(fd, buf, strlen(buf)); - if (ret <= 0) + if (ret <= 0) { + ret = -errno; pr_warning("Failed to write event: %s\n", strerror_r(errno, sbuf, sizeof(sbuf))); + } } free(buf); return ret; From c6e5e9fbc3ea1c1a5648a3498d085fc3978df2d4 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Mon, 12 Jan 2015 10:20:55 +0800 Subject: [PATCH 02/10] perf tools: Fix building error in x86_64 when dwarf unwind is on When build with 'make ARCH=x86' and dwarf unwind is on, there is a compiling error: CC /home/wn/perf/arch/x86/util/unwind-libdw.o CC /home/wn/perf/arch/x86/tests/regs_load.o arch/x86/tests/regs_load.S: Assembler messages: arch/x86/tests/regs_load.S:65: Error: operand type mismatch for `push' arch/x86/tests/regs_load.S:72: Error: operand type mismatch for `pop' make[1]: *** [/home/wn/perf/arch/x86/tests/regs_load.o] Error 1 make[1]: INTERNAL: Exiting with 25 jobserver tokens available; should be 24! make: *** [all] Error 2 ... Which is caused by incorrectly undefine macro HAVE_ARCH_X86_64_SUPPORT. 'config/Makefile.arch' tests __x86_64__ only when 'ARCH=x86_64'. However, when building x86_64 kernel, ARCH=x86 is valid and commonly used. Build systems, such as yocto, uses x86_64 compiler with 'ARCH=x86' to build x86_64 perf, which causes mismatching. As __LP64__ is defined for x86_64 as well, we can consolidate the __x86_64__ check to the __LP64__ check and get rid of the IS_X86_64 IMHO. (This patch is made by Namhyung Kim when replying my v1 patch: https://lkml.org/lkml/2015/1/7/17 I modified the code to remove dependency on RAW_ARCH: https://lkml.org/lkml/2015/1/7/865 Namhyung Kim didn't provide his SOB in his original email. I add mine only for my modification.) Signed-off-by: Namhyung Kim Signed-off-by: Wang Nan Acked-by: Jiri Olsa Cc: Jiri Olsa Cc: Li Zefan Cc: Ingo Molnar Cc: Namhyung Kim Link: http://lkml.kernel.org/r/1421029255-23039-1-git-send-email-wangnan0@huawei.com [ Namhyung provided his S-o-B on a followup to this patch thread on lkml ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Makefile.perf | 4 +++- tools/perf/config/Makefile | 2 +- tools/perf/config/Makefile.arch | 26 +++++++++++++------------- 3 files changed, 17 insertions(+), 15 deletions(-) diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 67a03a825b3c..1f71a32aea78 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -462,10 +462,12 @@ BUILTIN_OBJS += $(OUTPUT)builtin-bench.o # Benchmark modules BUILTIN_OBJS += $(OUTPUT)bench/sched-messaging.o BUILTIN_OBJS += $(OUTPUT)bench/sched-pipe.o -ifeq ($(RAW_ARCH),x86_64) +ifeq ($(ARCH), x86) +ifeq ($(IS_64_BIT), 1) BUILTIN_OBJS += $(OUTPUT)bench/mem-memcpy-x86-64-asm.o BUILTIN_OBJS += $(OUTPUT)bench/mem-memset-x86-64-asm.o endif +endif BUILTIN_OBJS += $(OUTPUT)bench/mem-memcpy.o BUILTIN_OBJS += $(OUTPUT)bench/futex-hash.o BUILTIN_OBJS += $(OUTPUT)bench/futex-wake.o diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile index 5d4b039fe1ed..648e31ff4021 100644 --- a/tools/perf/config/Makefile +++ b/tools/perf/config/Makefile @@ -20,7 +20,7 @@ NO_PERF_REGS := 1 # Additional ARCH settings for x86 ifeq ($(ARCH),x86) - ifeq (${IS_X86_64}, 1) + ifeq (${IS_64_BIT}, 1) CFLAGS += -DHAVE_ARCH_X86_64_SUPPORT ARCH_INCLUDE = ../../arch/x86/lib/memcpy_64.S ../../arch/x86/lib/memset_64.S LIBUNWIND_LIBS = -lunwind -lunwind-x86_64 diff --git a/tools/perf/config/Makefile.arch b/tools/perf/config/Makefile.arch index 851cd0172a76..ff95a68741d1 100644 --- a/tools/perf/config/Makefile.arch +++ b/tools/perf/config/Makefile.arch @@ -1,7 +1,7 @@ uname_M := $(shell uname -m 2>/dev/null || echo not) -ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/i386/ -e s/sun4u/sparc64/ \ +RAW_ARCH := $(shell echo $(uname_M) | sed -e s/i.86/i386/ -e s/sun4u/sparc64/ \ -e s/arm.*/arm/ -e s/sa110/arm/ \ -e s/s390x/s390/ -e s/parisc64/parisc/ \ -e s/ppc.*/powerpc/ -e s/mips.*/mips/ \ @@ -9,23 +9,23 @@ ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/i386/ -e s/sun4u/sparc64/ \ -e s/tile.*/tile/ ) # Additional ARCH settings for x86 -ifeq ($(ARCH),i386) - override ARCH := x86 +ifeq ($(RAW_ARCH),i386) + ARCH ?= x86 endif -ifeq ($(ARCH),x86_64) - override ARCH := x86 - IS_X86_64 := 0 - ifeq (, $(findstring m32,$(CFLAGS))) - IS_X86_64 := $(shell echo __x86_64__ | ${CC} -E -x c - | tail -n 1) - RAW_ARCH := x86_64 +ifeq ($(RAW_ARCH),x86_64) + ARCH ?= x86 + + ifneq (, $(findstring m32,$(CFLAGS))) + RAW_ARCH := x86_32 endif endif -ifeq (${IS_X86_64}, 1) +ARCH ?= $(RAW_ARCH) + +LP64 := $(shell echo __LP64__ | ${CC} ${CFLAGS} -E -x c - | tail -n 1) +ifeq ($(LP64), 1) IS_64_BIT := 1 -else ifeq ($(ARCH),x86) - IS_64_BIT := 0 else - IS_64_BIT := $(shell echo __LP64__ | ${CC} ${CFLAGS} -E -x c - | tail -n 1) + IS_64_BIT := 0 endif From 260d819e3abdbdaa2b88fb983d1314f1b263f9e2 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Fri, 9 Jan 2015 09:38:12 +0900 Subject: [PATCH 03/10] perf machine: Fix __machine__findnew_thread() error path When thread__init_map_groups() fails, a new thread should be removed from the rbtree since it's gonna be freed. Also update last match cache only if the function succeeded. Reported-by: David Ahern Signed-off-by: Namhyung Kim Acked-by: Jiri Olsa Cc: David Ahern Cc: Ingo Molnar Cc: Jiri Olsa Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1420763892-15535-1-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/machine.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 94de3e48b490..1bca3a9f2b16 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -389,7 +389,6 @@ static struct thread *__machine__findnew_thread(struct machine *machine, if (th != NULL) { rb_link_node(&th->rb_node, parent, p); rb_insert_color(&th->rb_node, &machine->threads); - machine->last_match = th; /* * We have to initialize map_groups separately @@ -400,9 +399,12 @@ static struct thread *__machine__findnew_thread(struct machine *machine, * leader and that would screwed the rb tree. */ if (thread__init_map_groups(th, machine)) { + rb_erase(&th->rb_node, &machine->threads); thread__delete(th); return NULL; } + + machine->last_match = th; } return th; From 25cd480e447eba47b8bdad1c9f95cadc074abc75 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 13 Jan 2015 10:19:12 -0300 Subject: [PATCH 04/10] tools: Remove bitops/hweight usage of bits in tools/perf We need to use lib/hweight.c for that, just like we do for lib/rbtree.c, so tools need to link hweight.o. For now do it directly, but we need to have a tools/lib/lk.a or .so that collects these goodies... Reported-by: Jan Beulich Cc: Adrian Hunter Cc: Borislav Petkov Cc: David Ahern Cc: Don Zickus Cc: Frederic Weisbecker Cc: Jiri Olsa Cc: Mike Galbraith Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/n/tip-a1e91dx3apzqw5kbdt7ut21s@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/asm-generic/bitops.h | 2 ++ .../include/asm-generic/bitops/arch_hweight.h | 1 + .../asm-generic/bitops/const_hweight.h | 1 + tools/include/asm-generic/bitops/hweight.h | 7 +++++ tools/include/linux/bitops.h | 7 ++++- tools/perf/MANIFEST | 6 ++++ tools/perf/Makefile.perf | 7 ++++- tools/perf/util/hweight.c | 31 ------------------- tools/perf/util/include/asm/hweight.h | 8 ----- tools/perf/util/python-ext-sources | 2 +- 10 files changed, 30 insertions(+), 42 deletions(-) create mode 100644 tools/include/asm-generic/bitops/arch_hweight.h create mode 100644 tools/include/asm-generic/bitops/const_hweight.h create mode 100644 tools/include/asm-generic/bitops/hweight.h delete mode 100644 tools/perf/util/hweight.c delete mode 100644 tools/perf/util/include/asm/hweight.h diff --git a/tools/include/asm-generic/bitops.h b/tools/include/asm-generic/bitops.h index 6eedba1f7732..653d1bad77de 100644 --- a/tools/include/asm-generic/bitops.h +++ b/tools/include/asm-generic/bitops.h @@ -22,6 +22,8 @@ #error only can be included directly #endif +#include + #include #endif /* __TOOLS_ASM_GENERIC_BITOPS_H */ diff --git a/tools/include/asm-generic/bitops/arch_hweight.h b/tools/include/asm-generic/bitops/arch_hweight.h new file mode 100644 index 000000000000..318bb2b202b0 --- /dev/null +++ b/tools/include/asm-generic/bitops/arch_hweight.h @@ -0,0 +1 @@ +#include "../../../../include/asm-generic/bitops/arch_hweight.h" diff --git a/tools/include/asm-generic/bitops/const_hweight.h b/tools/include/asm-generic/bitops/const_hweight.h new file mode 100644 index 000000000000..0afd644aff83 --- /dev/null +++ b/tools/include/asm-generic/bitops/const_hweight.h @@ -0,0 +1 @@ +#include "../../../../include/asm-generic/bitops/const_hweight.h" diff --git a/tools/include/asm-generic/bitops/hweight.h b/tools/include/asm-generic/bitops/hweight.h new file mode 100644 index 000000000000..290120c01a8e --- /dev/null +++ b/tools/include/asm-generic/bitops/hweight.h @@ -0,0 +1,7 @@ +#ifndef _TOOLS_LINUX_ASM_GENERIC_BITOPS_HWEIGHT_H_ +#define _TOOLS_LINUX_ASM_GENERIC_BITOPS_HWEIGHT_H_ + +#include +#include + +#endif /* _TOOLS_LINUX_ASM_GENERIC_BITOPS_HWEIGHT_H_ */ diff --git a/tools/include/linux/bitops.h b/tools/include/linux/bitops.h index 26005a15e7e2..5ad9ee1dd7f6 100644 --- a/tools/include/linux/bitops.h +++ b/tools/include/linux/bitops.h @@ -1,9 +1,9 @@ #ifndef _TOOLS_LINUX_BITOPS_H_ #define _TOOLS_LINUX_BITOPS_H_ +#include #include #include -#include #ifndef __WORDSIZE #define __WORDSIZE (__SIZEOF_LONG__ * 8) @@ -19,6 +19,11 @@ #define BITS_TO_U32(nr) DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(u32)) #define BITS_TO_BYTES(nr) DIV_ROUND_UP(nr, BITS_PER_BYTE) +extern unsigned int __sw_hweight8(unsigned int w); +extern unsigned int __sw_hweight16(unsigned int w); +extern unsigned int __sw_hweight32(unsigned int w); +extern unsigned long __sw_hweight64(__u64 w); + /* * Include this here because some architectures need generic_ffs/fls in * scope diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST index 83e2887f91a3..fbbfdc39271d 100644 --- a/tools/perf/MANIFEST +++ b/tools/perf/MANIFEST @@ -6,12 +6,15 @@ tools/lib/symbol/kallsyms.c tools/lib/symbol/kallsyms.h tools/lib/util/find_next_bit.c tools/include/asm/bug.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/__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/bitops.h tools/include/linux/compiler.h @@ -19,6 +22,8 @@ tools/include/linux/export.h tools/include/linux/hash.h tools/include/linux/log2.h tools/include/linux/types.h +include/asm-generic/bitops/arch_hweight.h +include/asm-generic/bitops/const_hweight.h include/asm-generic/bitops/fls64.h include/asm-generic/bitops/__fls.h include/asm-generic/bitops/fls.h @@ -29,6 +34,7 @@ include/linux/list.h include/linux/hash.h include/linux/stringify.h lib/find_next_bit.c +lib/hweight.c lib/rbtree.c include/linux/swab.h arch/*/include/asm/unistd*.h diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 1f71a32aea78..aa6a50447c32 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -232,12 +232,15 @@ LIB_H += ../include/linux/hash.h LIB_H += ../../include/linux/stringify.h LIB_H += util/include/linux/bitmap.h LIB_H += ../include/linux/bitops.h +LIB_H += ../include/asm-generic/bitops/arch_hweight.h LIB_H += ../include/asm-generic/bitops/atomic.h +LIB_H += ../include/asm-generic/bitops/const_hweight.h LIB_H += ../include/asm-generic/bitops/find.h LIB_H += ../include/asm-generic/bitops/fls64.h LIB_H += ../include/asm-generic/bitops/fls.h LIB_H += ../include/asm-generic/bitops/__ffs.h LIB_H += ../include/asm-generic/bitops/__fls.h +LIB_H += ../include/asm-generic/bitops/hweight.h LIB_H += ../include/asm-generic/bitops.h LIB_H += ../include/linux/compiler.h LIB_H += ../include/linux/log2.h @@ -255,7 +258,6 @@ LIB_H += util/include/linux/linkage.h LIB_H += util/include/asm/asm-offsets.h LIB_H += ../include/asm/bug.h LIB_H += util/include/asm/byteorder.h -LIB_H += util/include/asm/hweight.h LIB_H += util/include/asm/swab.h LIB_H += util/include/asm/system.h LIB_H += util/include/asm/uaccess.h @@ -745,6 +747,9 @@ $(OUTPUT)util/kallsyms.o: ../lib/symbol/kallsyms.c $(OUTPUT)PERF-CFLAGS $(OUTPUT)util/rbtree.o: ../../lib/rbtree.c $(OUTPUT)PERF-CFLAGS $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -Wno-unused-parameter -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $< +$(OUTPUT)util/hweight.o: ../../lib/hweight.c $(OUTPUT)PERF-CFLAGS + $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -Wno-unused-parameter -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $< + $(OUTPUT)util/find_next_bit.o: ../lib/util/find_next_bit.c $(OUTPUT)PERF-CFLAGS $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -Wno-unused-parameter -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $< diff --git a/tools/perf/util/hweight.c b/tools/perf/util/hweight.c deleted file mode 100644 index 5c1d0d099f0d..000000000000 --- a/tools/perf/util/hweight.c +++ /dev/null @@ -1,31 +0,0 @@ -#include - -/** - * hweightN - returns the hamming weight of a N-bit word - * @x: the word to weigh - * - * The Hamming Weight of a number is the total number of bits set in it. - */ - -unsigned int hweight32(unsigned int w) -{ - unsigned int res = w - ((w >> 1) & 0x55555555); - res = (res & 0x33333333) + ((res >> 2) & 0x33333333); - res = (res + (res >> 4)) & 0x0F0F0F0F; - res = res + (res >> 8); - return (res + (res >> 16)) & 0x000000FF; -} - -unsigned long hweight64(__u64 w) -{ -#if BITS_PER_LONG == 32 - return hweight32((unsigned int)(w >> 32)) + hweight32((unsigned int)w); -#elif BITS_PER_LONG == 64 - __u64 res = w - ((w >> 1) & 0x5555555555555555ul); - res = (res & 0x3333333333333333ul) + ((res >> 2) & 0x3333333333333333ul); - res = (res + (res >> 4)) & 0x0F0F0F0F0F0F0F0Ful; - res = res + (res >> 8); - res = res + (res >> 16); - return (res + (res >> 32)) & 0x00000000000000FFul; -#endif -} diff --git a/tools/perf/util/include/asm/hweight.h b/tools/perf/util/include/asm/hweight.h deleted file mode 100644 index 36cf26d434a5..000000000000 --- a/tools/perf/util/include/asm/hweight.h +++ /dev/null @@ -1,8 +0,0 @@ -#ifndef PERF_HWEIGHT_H -#define PERF_HWEIGHT_H - -#include -unsigned int hweight32(unsigned int w); -unsigned long hweight64(__u64 w); - -#endif /* PERF_HWEIGHT_H */ diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources index 16a475a7d492..6c6a6953fa93 100644 --- a/tools/perf/util/python-ext-sources +++ b/tools/perf/util/python-ext-sources @@ -10,7 +10,7 @@ util/ctype.c util/evlist.c util/evsel.c util/cpumap.c -util/hweight.c +../../lib/hweight.c util/thread_map.c util/util.c util/xyarray.c From db1806edcfef007d9594435a331dcf7e7f1b8fac Mon Sep 17 00:00:00 2001 From: Alexey Brodkin Date: Sat, 10 Jan 2015 16:40:50 +0530 Subject: [PATCH 05/10] perf tools: Fix statfs.f_type data type mismatch build error with uclibc ARC Linux uses the no legacy syscalls abi and corresponding uClibc headers statfs defines f_type to be U32 which causes perf build breakage http://git.uclibc.org/uClibc/tree/libc/sysdeps/linux/common-generic/bits/statfs.h ----------->8--------------- CC fs/fs.o fs/fs.c: In function 'fs__valid_mount': fs/fs.c:82:24: error: comparison between signed and unsigned integer expressions [-Werror=sign-compare] else if (st_fs.f_type != magic) ^ cc1: all warnings being treated as errors ----------->8--------------- Signed-off-by: Alexey Brodkin Acked-by: Jiri Olsa Cc: Borislav Petkov Cc: Cody P Schafer Cc: Ingo Molnar Cc: Jiri Olsa Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Vineet Gupta Link: http://lkml.kernel.org/r/1420888254-17504-2-git-send-email-vgupta@synopsys.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/lib/api/fs/debugfs.c | 2 +- tools/lib/api/fs/fs.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/lib/api/fs/debugfs.c b/tools/lib/api/fs/debugfs.c index a74fba6d7743..86ea2d7b8845 100644 --- a/tools/lib/api/fs/debugfs.c +++ b/tools/lib/api/fs/debugfs.c @@ -67,7 +67,7 @@ int debugfs_valid_mountpoint(const char *debugfs) if (statfs(debugfs, &st_fs) < 0) return -ENOENT; - else if (st_fs.f_type != (long) DEBUGFS_MAGIC) + else if ((long)st_fs.f_type != (long)DEBUGFS_MAGIC) return -ENOENT; return 0; diff --git a/tools/lib/api/fs/fs.c b/tools/lib/api/fs/fs.c index 65d9be3f9887..128ef6332a6b 100644 --- a/tools/lib/api/fs/fs.c +++ b/tools/lib/api/fs/fs.c @@ -79,7 +79,7 @@ static int fs__valid_mount(const char *fs, long magic) if (statfs(fs, &st_fs) < 0) return -ENOENT; - else if (st_fs.f_type != magic) + else if ((long)st_fs.f_type != magic) return -ENOENT; return 0; From a83d869f300bf91df07443b5272db7a5a8eb18b7 Mon Sep 17 00:00:00 2001 From: Vineet Gupta Date: Tue, 13 Jan 2015 19:13:21 +0530 Subject: [PATCH 06/10] perf tools: Elide strlcpy warning with uclibc ----------------->8------------------ CC bench/sched-pipe.o In file included from builtin-annotate.c:13:0: util/cache.h:76:15: warning: redundant redeclaration of 'strlcpy' [-Wredundant-decls] extern size_t strlcpy(char *dest, const char *src, size_t size); ^ In file included from util/util.h:55:0, from builtin.h:4, from builtin-annotate.c:8: ~/vineetg/arc/gnu/INSTALL_1412-arc-2014.12-rc1/arc-snps-linux-uclibc/sysroot/usr/include/string.h:396:15: note: previous declaration of 'strlcpy' was here extern size_t strlcpy(char *__restrict dst, const char *__restrict src, ----------------->8------------------ Signed-off-by: Vineet Gupta Cc: Alexey Brodkin Cc: Ingo Molnar Cc: Jiri Olsa Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1421156604-30603-3-git-send-email-vgupta@synopsys.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/cache.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tools/perf/util/cache.h b/tools/perf/util/cache.h index 5cf9e1b5989d..d04d770d90f6 100644 --- a/tools/perf/util/cache.h +++ b/tools/perf/util/cache.h @@ -71,7 +71,9 @@ extern char *perf_path(const char *fmt, ...) __attribute__((format (printf, 1, 2 extern char *perf_pathdup(const char *fmt, ...) __attribute__((format (printf, 1, 2))); +#ifndef __UCLIBC__ /* Matches the libc/libbsd function attribute so we declare this unconditionally: */ extern size_t strlcpy(char *dest, const char *src, size_t size); +#endif #endif /* __PERF_CACHE_H */ From ea1fe3a88763d4dfef7e2529ba606f96e8e6b271 Mon Sep 17 00:00:00 2001 From: Vineet Gupta Date: Tue, 13 Jan 2015 19:13:22 +0530 Subject: [PATCH 07/10] perf tools: Avoid build splat for syscall numbers with uclibc This is due to duplicated unistd inclusion (via uClibc headers + kernel headers) Also seen on ARM uClibc based tools ------- ARC build ---------->8------------- CC util/evlist.o In file included from ~/arc/k.org/arch/arc/include/uapi/asm/unistd.h:25:0, from util/../perf-sys.h:10, from util/../perf.h:15, from util/event.h:7, from util/event.c:3: ~/arc/k.org/include/uapi/asm-generic/unistd.h:906:0: warning: "__NR_fcntl64" redefined [enabled by default] #define __NR_fcntl64 __NR3264_fcntl ^ In file included from ~/arc/gnu/INSTALL_1412-arc-2014.12-rc1/arc-snps-linux-uclibc/sysroot/usr/include/sys/syscall.h:24:0, from util/../perf-sys.h:6, ----------------->8------------------- ------- ARM build ---------->8------------- CC FPIC plugin_scsi.o In file included from util/../perf-sys.h:9:0, from util/../perf.h:15, from util/cache.h:7, from perf.c:12: ~/arc/k.org/arch/arm/include/uapi/asm/unistd.h:28:0: warning: "__NR_restart_syscall" redefined [enabled by default] In file included from ~/buildroot/host/usr/arm-buildroot-linux-uclibcgnueabi/sysroot/usr/include/sys/syscall.h:25:0, from util/../perf-sys.h:6, from util/../perf.h:15, from util/cache.h:7, from perf.c:12: ~/buildroot/host/usr/arm-buildroot-linux-uclibcgnueabi/sysroot/usr/include/bits/sysnum.h:17:0: note: this is the location of the previous definition ----------------->8------------------- Signed-off-by: Vineet Gupta Cc: Alexey Brodkin Cc: Ingo Molnar Cc: Jiri Olsa Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1421156604-30603-4-git-send-email-vgupta@synopsys.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/bench/sched-pipe.c | 2 +- tools/perf/builtin-top.c | 1 - tools/perf/perf-sys.h | 1 - 3 files changed, 1 insertion(+), 3 deletions(-) diff --git a/tools/perf/bench/sched-pipe.c b/tools/perf/bench/sched-pipe.c index 07a8d7646a15..005cc283790c 100644 --- a/tools/perf/bench/sched-pipe.c +++ b/tools/perf/bench/sched-pipe.c @@ -19,12 +19,12 @@ #include #include #include -#include #include #include #include #include #include +#include #include diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 961cea183a83..616f0fcb4701 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -66,7 +66,6 @@ #include #include -#include #include static volatile int done; diff --git a/tools/perf/perf-sys.h b/tools/perf/perf-sys.h index a3b13d7dc1d4..6ef68165c9db 100644 --- a/tools/perf/perf-sys.h +++ b/tools/perf/perf-sys.h @@ -6,7 +6,6 @@ #include #include #include -#include #if defined(__i386__) #define mb() asm volatile("lock; addl $0,0(%%esp)" ::: "memory") From b93b0967826a4a00297dde1cbbda8df673c1689e Mon Sep 17 00:00:00 2001 From: Wang Nan Date: Wed, 14 Jan 2015 10:36:47 +0800 Subject: [PATCH 08/10] perf test: Fix dwarf unwind using libunwind. Perf tool fails to unwind user stack if the event raises in a shared object. This patch improves tests/dwarf-unwind.c to demonstrate the problem by utilizing commonly used glibc function "bsearch". If perf is not statically linked, the testcase will try to unwind a mixed call trace. By debugging libunwind I found that there is a bug in unwind-libunwind: it always passes 0 as segbase to libunwind, cause libunwind unable to locate debug_frame entry fir first level ip address (I add some more debugging output into libunwind to make things clear): >_Uarm_dwarf_find_debug_frame: start_ip = 10be98, end_ip = 10c2a4 >_Uarm_dwarf_find_debug_frame: found debug_frame table `/lib/libc-2.18.so': segbase=0x0, len=7, gp=0x0, table_data=0x449388 >_Uarm_dwarf_search_unwind_table: call lookup:ip = b6cd3bcc, segbase = 0, rel_ip = b6cd3bcc >lookup: e->start_ip_offset = bcf18 (rel_ip = b6cd3bcc) >lookup: e->start_ip_offset = 6d314 (rel_ip = b6cd3bcc) >lookup: e->start_ip_offset = 33d0c (rel_ip = b6cd3bcc) ... >lookup: e->start_ip_offset = 15d0c (rel_ip = b6cd3bcc) >lookup: e->start_ip_offset = 15c40 (rel_ip = b6cd3bcc) >_Uarm_dwarf_search_unwind_table: IP b6cd3bcc inside range b6c12000-b6d4c000, but no explicit unwind info found >put_rs_cache: unmasking signals/interrupts and releasing lock >_Uarm_dwarf_step: returning -10 >_Uarm_step: dwarf_step()=-10 This patch passes map->start as segbase to dwarf_find_debug_frame(), so di will be initialized correctly. In addition, dso and executable are different when setting segbase. This patch first check whether the elf is executable, and pass segbase only for shared object. Signed-off-by: Wang Nan Acked-by: Jiri Olsa Cc: Ingo Molnar Cc: Jiri Olsa Cc: Li Zefan Cc: Masami Hiramatsu Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1421203007-75799-1-git-send-email-wangnan0@huawei.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/dwarf-unwind.c | 36 ++++++++++++++++++++++++++++-- tools/perf/util/unwind-libunwind.c | 28 ++++++++++++++++++++++- 2 files changed, 61 insertions(+), 3 deletions(-) diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c index ab28cca2cb97..0bf06bec68c7 100644 --- a/tools/perf/tests/dwarf-unwind.c +++ b/tools/perf/tests/dwarf-unwind.c @@ -11,6 +11,9 @@ #include "thread.h" #include "callchain.h" +/* For bsearch. We try to unwind functions in shared object. */ +#include + static int mmap_handler(struct perf_tool *tool __maybe_unused, union perf_event *event, struct perf_sample *sample __maybe_unused, @@ -28,7 +31,7 @@ static int init_live_machine(struct machine *machine) mmap_handler, machine, true); } -#define MAX_STACK 6 +#define MAX_STACK 8 static int unwind_entry(struct unwind_entry *entry, void *arg) { @@ -37,6 +40,8 @@ static int unwind_entry(struct unwind_entry *entry, void *arg) static const char *funcs[MAX_STACK] = { "test__arch_unwind_sample", "unwind_thread", + "compare", + "bsearch", "krava_3", "krava_2", "krava_1", @@ -88,10 +93,37 @@ static int unwind_thread(struct thread *thread) return err; } +static int global_unwind_retval = -INT_MAX; + +__attribute__ ((noinline)) +static int compare(void *p1, void *p2) +{ + /* Any possible value should be 'thread' */ + struct thread *thread = *(struct thread **)p1; + + if (global_unwind_retval == -INT_MAX) + global_unwind_retval = unwind_thread(thread); + + return p1 - p2; +} + __attribute__ ((noinline)) static int krava_3(struct thread *thread) { - return unwind_thread(thread); + struct thread *array[2] = {thread, thread}; + void *fp = &bsearch; + /* + * make _bsearch a volatile function pointer to + * prevent potential optimization, which may expand + * bsearch and call compare directly from this function, + * instead of libc shared object. + */ + void *(*volatile _bsearch)(void *, void *, size_t, + size_t, int (*)(void *, void *)); + + _bsearch = fp; + _bsearch(array, &thread, 2, sizeof(struct thread **), compare); + return global_unwind_retval; } __attribute__ ((noinline)) diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c index 371219a6daf1..6edf535f65c2 100644 --- a/tools/perf/util/unwind-libunwind.c +++ b/tools/perf/util/unwind-libunwind.c @@ -185,6 +185,28 @@ static u64 elf_section_offset(int fd, const char *name) return offset; } +#ifndef NO_LIBUNWIND_DEBUG_FRAME +static int elf_is_exec(int fd, const char *name) +{ + Elf *elf; + GElf_Ehdr ehdr; + int retval = 0; + + elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL); + if (elf == NULL) + return 0; + if (gelf_getehdr(elf, &ehdr) == NULL) + goto out; + + retval = (ehdr.e_type == ET_EXEC); + +out: + elf_end(elf); + pr_debug("unwind: elf_is_exec(%s): %d\n", name, retval); + return retval; +} +#endif + struct table_entry { u32 start_ip_offset; u32 fde_offset; @@ -322,8 +344,12 @@ find_proc_info(unw_addr_space_t as, unw_word_t ip, unw_proc_info_t *pi, #ifndef NO_LIBUNWIND_DEBUG_FRAME /* Check the .debug_frame section for unwinding info */ if (!read_unwind_spec_debug_frame(map->dso, ui->machine, &segbase)) { + int fd = dso__data_fd(map->dso, ui->machine); + int is_exec = elf_is_exec(fd, map->dso->name); + unw_word_t base = is_exec ? 0 : map->start; + memset(&di, 0, sizeof(di)); - if (dwarf_find_debug_frame(0, &di, ip, 0, map->dso->name, + if (dwarf_find_debug_frame(0, &di, ip, base, map->dso->name, map->start, map->end)) return dwarf_search_unwind_table(as, ip, &di, pi, need_unwind_info, arg); From 813ccd15452ed34e97aa526ffc70d6d8e6c466c5 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Wed, 14 Jan 2015 20:18:05 +0900 Subject: [PATCH 09/10] perf tools: Fix segfault for symbol annotation on TUI Currently the symbol structure is allocated with symbol_conf.priv_size to carry sideband information like annotation, map browser on TUI and sort-by-name tree node. So retrieving these information from symbol needs to care about the details of such placement. However the annotation code just assumes that the symbol is placed after the struct annotation. But actually there's other info between them. So accessing those struct will lead to an undefined behavior (usually a crash) after they write their info to the same location. To reproduce the problem, please follow the steps below: 1. run perf report (TUI of course) with -v option 2. open map browser (by pressing right arrow key for any entry) 3. search any function (by pressing '/' key and input whatever..) 4. return to the hist browser (by pressing 'q' or left arrow key) 5. open annotation window for the same entry (by pressing 'a' key) Signed-off-by: Namhyung Kim Cc: David Ahern Cc: Ingo Molnar Cc: Jiri Olsa Cc: Masami Hiramatsu Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1421234288-22758-1-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/annotate.h | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h index 0784a9420528..cadbdc90a5cb 100644 --- a/tools/perf/util/annotate.h +++ b/tools/perf/util/annotate.h @@ -116,11 +116,6 @@ struct annotation { struct annotated_source *src; }; -struct sannotation { - struct annotation annotation; - struct symbol symbol; -}; - static inline struct sym_hist *annotation__histogram(struct annotation *notes, int idx) { return (((void *)¬es->src->histograms) + @@ -129,8 +124,7 @@ static inline struct sym_hist *annotation__histogram(struct annotation *notes, i static inline struct annotation *symbol__annotation(struct symbol *sym) { - struct sannotation *a = container_of(sym, struct sannotation, symbol); - return &a->annotation; + return (void *)sym - symbol_conf.priv_size; } int addr_map_symbol__inc_samples(struct addr_map_symbol *ams, int evidx); From 6bcf9c1ff3ec22fd81eba336737d9865476509b1 Mon Sep 17 00:00:00 2001 From: Sukadev Bhattiprolu Date: Fri, 21 Nov 2014 20:33:53 -0500 Subject: [PATCH 10/10] perf tools powerpc: Use dwfl_report_elf() instead of offline. dwfl_report_offline() works only when libraries are prelinked. Replace dwfl_report_offline() with dwfl_report_elf() so we correctly extract debug info even from libraries that are not prelinked. Reported-by: Jiri Olsa Signed-off-by: Sukadev Bhattiprolu Tested-by: Jiri Olsa Cc: Jiri Olsa Cc: Michael Ellerman Link: http://lkml.kernel.org/r/20150114221045.GA17703@us.ibm.com Signed-off-by: Arnaldo Carvalho de Melo --- .../arch/powerpc/util/skip-callchain-idx.c | 19 +++++++++++-------- 1 file changed, 11 insertions(+), 8 deletions(-) diff --git a/tools/perf/arch/powerpc/util/skip-callchain-idx.c b/tools/perf/arch/powerpc/util/skip-callchain-idx.c index 3bb50eac5542..0c370f81e002 100644 --- a/tools/perf/arch/powerpc/util/skip-callchain-idx.c +++ b/tools/perf/arch/powerpc/util/skip-callchain-idx.c @@ -103,7 +103,7 @@ static Dwarf_Frame *get_eh_frame(Dwfl_Module *mod, Dwarf_Addr pc) return NULL; } - result = dwarf_cfi_addrframe(cfi, pc, &frame); + result = dwarf_cfi_addrframe(cfi, pc-bias, &frame); if (result) { pr_debug("%s(): %s\n", __func__, dwfl_errmsg(-1)); return NULL; @@ -128,7 +128,7 @@ static Dwarf_Frame *get_dwarf_frame(Dwfl_Module *mod, Dwarf_Addr pc) return NULL; } - result = dwarf_cfi_addrframe(cfi, pc, &frame); + result = dwarf_cfi_addrframe(cfi, pc-bias, &frame); if (result) { pr_debug("%s(): %s\n", __func__, dwfl_errmsg(-1)); return NULL; @@ -145,7 +145,7 @@ static Dwarf_Frame *get_dwarf_frame(Dwfl_Module *mod, Dwarf_Addr pc) * yet used) * -1 in case of errors */ -static int check_return_addr(struct dso *dso, Dwarf_Addr pc) +static int check_return_addr(struct dso *dso, u64 map_start, Dwarf_Addr pc) { int rc = -1; Dwfl *dwfl; @@ -155,6 +155,7 @@ static int check_return_addr(struct dso *dso, Dwarf_Addr pc) Dwarf_Addr start = pc; Dwarf_Addr end = pc; bool signalp; + const char *exec_file = dso->long_name; dwfl = dso->dwfl; @@ -165,8 +166,10 @@ static int check_return_addr(struct dso *dso, Dwarf_Addr pc) return -1; } - if (dwfl_report_offline(dwfl, "", dso->long_name, -1) == NULL) { - pr_debug("dwfl_report_offline() failed %s\n", + mod = dwfl_report_elf(dwfl, exec_file, exec_file, -1, + map_start, false); + if (!mod) { + pr_debug("dwfl_report_elf() failed %s\n", dwarf_errmsg(-1)); /* * We normally cache the DWARF debug info and never @@ -256,10 +259,10 @@ int arch_skip_callchain_idx(struct thread *thread, struct ip_callchain *chain) return skip_slot; } - rc = check_return_addr(dso, ip); + rc = check_return_addr(dso, al.map->start, ip); - pr_debug("DSO %s, nr %" PRIx64 ", ip 0x%" PRIx64 "rc %d\n", - dso->long_name, chain->nr, ip, rc); + pr_debug("[DSO %s, sym %s, ip 0x%" PRIx64 "] rc %d\n", + dso->long_name, al.sym->name, ip, rc); if (rc == 0) { /*