From 7d4df089d77306914426a604c890175f91a9a459 Mon Sep 17 00:00:00 2001 From: Milian Wolff Date: Wed, 24 May 2017 15:21:23 +0900 Subject: perf report: Don't crash on invalid maps in `-g srcline` mode I just hit a segfault when doing `perf report -g srcline`. Valgrind pointed me at this code as the culprit: ==8359== Invalid read of size 8 ==8359== at 0x3096D9: map__rip_2objdump (map.c:430) ==8359== by 0x2FC1A3: match_chain_srcline (callchain.c:645) ==8359== by 0x2FC1A3: match_chain (callchain.c:700) ==8359== by 0x2FC1A3: append_chain (callchain.c:895) ==8359== by 0x2FC1A3: append_chain_children (callchain.c:846) ==8359== by 0x2FF719: callchain_append (callchain.c:944) ==8359== by 0x2FF719: hist_entry__append_callchain (callchain.c:1058) ==8359== by 0x32FA06: iter_add_single_cumulative_entry (hist.c:908) ==8359== by 0x33195C: hist_entry_iter__add (hist.c:1050) ==8359== by 0x258F65: process_sample_event (builtin-report.c:204) ==8359== by 0x30D60C: perf_session__deliver_event (session.c:1310) ==8359== by 0x30D60C: ordered_events__deliver_event (session.c:119) ==8359== by 0x310D12: __ordered_events__flush (ordered-events.c:210) ==8359== by 0x310D12: ordered_events__flush.part.3 (ordered-events.c:277) ==8359== by 0x30DD3C: perf_session__process_user_event (session.c:1349) ==8359== by 0x30DD3C: perf_session__process_event (session.c:1475) ==8359== by 0x30FC3C: __perf_session__process_events (session.c:1867) ==8359== by 0x30FC3C: perf_session__process_events (session.c:1921) ==8359== by 0x25A985: __cmd_report (builtin-report.c:575) ==8359== by 0x25A985: cmd_report (builtin-report.c:1054) ==8359== by 0x2B9A80: run_builtin (perf.c:296) ==8359== Address 0x70 is not stack'd, malloc'd or (recently) free'd This patch fixes the issue. Signed-off-by: Milian Wolff [ Remove dependency from another change ] Signed-off-by: Namhyung Kim Cc: Arnaldo Carvalho de Melo Cc: Arnaldo Carvalho de Melo Cc: David Ahern Cc: Jiri Olsa Cc: Jiri Olsa Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Yao Jin Cc: kernel-team@lge.com Link: http://lkml.kernel.org/r/20170524062129.32529-2-namhyung@kernel.org Signed-off-by: Ingo Molnar --- tools/perf/util/callchain.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) (limited to 'tools') diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c index 81fc29ac798f..b4204b43ed58 100644 --- a/tools/perf/util/callchain.c +++ b/tools/perf/util/callchain.c @@ -621,14 +621,19 @@ enum match_result { static enum match_result match_chain_srcline(struct callchain_cursor_node *node, struct callchain_list *cnode) { - char *left = get_srcline(cnode->ms.map->dso, + char *left = NULL; + char *right = NULL; + enum match_result ret = MATCH_EQ; + int cmp; + + if (cnode->ms.map) + left = get_srcline(cnode->ms.map->dso, map__rip_2objdump(cnode->ms.map, cnode->ip), cnode->ms.sym, true, false); - char *right = get_srcline(node->map->dso, + if (node->map) + right = get_srcline(node->map->dso, map__rip_2objdump(node->map, node->ip), node->sym, true, false); - enum match_result ret = MATCH_EQ; - int cmp; if (left && right) cmp = strcmp(left, right); -- cgit From b21cc97810932a551f7aac46f0b89c469c828b3f Mon Sep 17 00:00:00 2001 From: Milian Wolff Date: Wed, 24 May 2017 15:21:24 +0900 Subject: perf report: Fix memory leak in addr2line when called by addr2inlines When a filename was found in addr2line it was duplicated via strdup() but never freed. Now we pass NULL and handle this gracefully in addr2line. Detected by Valgrind: ==16331== 1,680 bytes in 21 blocks are definitely lost in loss record 148 of 220 ==16331== at 0x4C2AF1F: malloc (in /usr/lib/valgrind/vgpreload_memcheck-amd64-linux.so) ==16331== by 0x672FA69: strdup (in /usr/lib/libc-2.25.so) ==16331== by 0x52769F: addr2line (srcline.c:256) ==16331== by 0x52769F: addr2inlines (srcline.c:294) ==16331== by 0x52769F: dso__parse_addr_inlines (srcline.c:502) ==16331== by 0x574D7A: inline__fprintf (hist.c:41) ==16331== by 0x574D7A: ipchain__fprintf_graph (hist.c:147) ==16331== by 0x57518A: __callchain__fprintf_graph (hist.c:212) ==16331== by 0x5753CF: callchain__fprintf_graph.constprop.6 (hist.c:337) ==16331== by 0x57738E: hist_entry__fprintf (hist.c:628) ==16331== by 0x57738E: hists__fprintf (hist.c:882) ==16331== by 0x44A20F: perf_evlist__tty_browse_hists (builtin-report.c:399) ==16331== by 0x44A20F: report__browse_hists (builtin-report.c:491) ==16331== by 0x44A20F: __cmd_report (builtin-report.c:624) ==16331== by 0x44A20F: cmd_report (builtin-report.c:1054) ==16331== by 0x4A49CE: run_builtin (perf.c:296) ==16331== by 0x4A4CC0: handle_internal_command (perf.c:348) ==16331== by 0x434371: run_argv (perf.c:392) ==16331== by 0x434371: main (perf.c:530) Signed-off-by: Milian Wolff Signed-off-by: Namhyung Kim Cc: Arnaldo Carvalho de Melo Cc: Arnaldo Carvalho de Melo Cc: David Ahern Cc: Jiri Olsa Cc: Jiri Olsa Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Yao Jin Cc: kernel-team@lge.com Link: http://lkml.kernel.org/r/20170524062129.32529-3-namhyung@kernel.org Signed-off-by: Ingo Molnar --- tools/perf/util/srcline.c | 23 +++++++++++++---------- 1 file changed, 13 insertions(+), 10 deletions(-) (limited to 'tools') diff --git a/tools/perf/util/srcline.c b/tools/perf/util/srcline.c index df051a52393c..5e376d64d59e 100644 --- a/tools/perf/util/srcline.c +++ b/tools/perf/util/srcline.c @@ -230,7 +230,10 @@ static int addr2line(const char *dso_name, u64 addr, bfd_map_over_sections(a2l->abfd, find_address_in_section, a2l); - if (a2l->found && unwind_inlines) { + if (!a2l->found) + return 0; + + if (unwind_inlines) { int cnt = 0; while (bfd_find_inliner_info(a2l->abfd, &a2l->filename, @@ -243,6 +246,8 @@ static int addr2line(const char *dso_name, u64 addr, a2l->line, node, dso) != 0) return 0; + // found at least one inline frame + ret = 1; } } @@ -252,14 +257,14 @@ static int addr2line(const char *dso_name, u64 addr, } } - if (a2l->found && a2l->filename) { - *file = strdup(a2l->filename); - *line = a2l->line; - - if (*file) - ret = 1; + if (file) { + *file = a2l->filename ? strdup(a2l->filename) : NULL; + ret = *file ? 1 : 0; } + if (line) + *line = a2l->line; + return ret; } @@ -278,8 +283,6 @@ void dso__free_a2l(struct dso *dso) static struct inline_node *addr2inlines(const char *dso_name, u64 addr, struct dso *dso) { - char *file = NULL; - unsigned int line = 0; struct inline_node *node; node = zalloc(sizeof(*node)); @@ -291,7 +294,7 @@ static struct inline_node *addr2inlines(const char *dso_name, u64 addr, INIT_LIST_HEAD(&node->val); node->addr = addr; - if (!addr2line(dso_name, addr, &file, &line, dso, TRUE, node)) + if (!addr2line(dso_name, addr, NULL, NULL, dso, TRUE, node)) goto out_free_inline_node; if (list_empty(&node->val)) -- cgit From 1982ad48fc82c284a5cc55697a012d3357e84d01 Mon Sep 17 00:00:00 2001 From: Milian Wolff Date: Wed, 24 May 2017 15:21:25 +0900 Subject: perf report: Fix off-by-one for non-activation frames As the documentation for dwfl_frame_pc says, frames that are no activation frames need to have their program counter decremented by one to properly find the function of the caller. This fixes many cases where perf report currently attributes the cost to the next line. I.e. I have code like this: ~~~~~~~~~~~~~~~ #include #include using namespace std; int main() { this_thread::sleep_for(chrono::milliseconds(1000)); this_thread::sleep_for(chrono::milliseconds(100)); this_thread::sleep_for(chrono::milliseconds(10)); return 0; } ~~~~~~~~~~~~~~~ Now compile and record it: ~~~~~~~~~~~~~~~ g++ -std=c++11 -g -O2 test.cpp echo 1 | sudo tee /proc/sys/kernel/sched_schedstats perf record \ --event sched:sched_stat_sleep \ --event sched:sched_process_exit \ --event sched:sched_switch --call-graph=dwarf \ --output perf.data.raw \ ./a.out echo 0 | sudo tee /proc/sys/kernel/sched_schedstats perf inject --sched-stat --input perf.data.raw --output perf.data ~~~~~~~~~~~~~~~ Before this patch, the report clearly shows the off-by-one issue. Most notably, the last sleep invocation is incorrectly attributed to the "return 0;" line: ~~~~~~~~~~~~~~~ Overhead Source:Line ........ ........... 100.00% core.c:0 | ---__schedule core.c:0 schedule do_nanosleep hrtimer.c:0 hrtimer_nanosleep sys_nanosleep entry_SYSCALL_64_fastpath .tmp_entry_64.o:0 __nanosleep_nocancel .:0 std::this_thread::sleep_for > thread:323 | |--90.08%--main test.cpp:9 | __libc_start_main | _start | |--9.01%--main test.cpp:10 | __libc_start_main | _start | --0.91%--main test.cpp:13 __libc_start_main _start ~~~~~~~~~~~~~~~ With this patch here applied, the issue is fixed. The report becomes much more usable: ~~~~~~~~~~~~~~~ Overhead Source:Line ........ ........... 100.00% core.c:0 | ---__schedule core.c:0 schedule do_nanosleep hrtimer.c:0 hrtimer_nanosleep sys_nanosleep entry_SYSCALL_64_fastpath .tmp_entry_64.o:0 __nanosleep_nocancel .:0 std::this_thread::sleep_for > thread:323 | |--90.08%--main test.cpp:8 | __libc_start_main | _start | |--9.01%--main test.cpp:9 | __libc_start_main | _start | --0.91%--main test.cpp:10 __libc_start_main _start ~~~~~~~~~~~~~~~ Similarly it works for signal frames: ~~~~~~~~~~~~~~~ __noinline void bar(void) { volatile long cnt = 0; for (cnt = 0; cnt < 100000000; cnt++); } __noinline void foo(void) { bar(); } void sig_handler(int sig) { foo(); } int main(void) { signal(SIGUSR1, sig_handler); raise(SIGUSR1); foo(); return 0; } ~~~~~~~~~~~~~~~~ Before, the report wrongly points to `signal.c:29` after raise(): ~~~~~~~~~~~~~~~~ $ perf report --stdio --no-children -g srcline -s srcline ... 100.00% signal.c:11 | ---bar signal.c:11 | |--50.49%--main signal.c:29 | __libc_start_main | _start | --49.51%--0x33a8f raise .:0 main signal.c:29 __libc_start_main _start ~~~~~~~~~~~~~~~~ With this patch in, the issue is fixed and we instead get: ~~~~~~~~~~~~~~~~ 100.00% signal signal [.] bar | ---bar signal.c:11 | |--50.49%--main signal.c:29 | __libc_start_main | _start | --49.51%--0x33a8f raise .:0 main signal.c:27 __libc_start_main _start ~~~~~~~~~~~~~~~~ Note how this patch fixes this issue for both unwinding methods, i.e. both dwfl and libunwind. The former case is straight-forward thanks to dwfl_frame_pc(). For libunwind, we replace the functionality via unw_is_signal_frame() for any but the very first frame. Signed-off-by: Milian Wolff Signed-off-by: Namhyung Kim Cc: Arnaldo Carvalho de Melo Cc: Arnaldo Carvalho de Melo Cc: David Ahern Cc: Jiri Olsa Cc: Jiri Olsa Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Yao Jin Cc: kernel-team@lge.com Link: http://lkml.kernel.org/r/20170524062129.32529-4-namhyung@kernel.org Signed-off-by: Ingo Molnar --- tools/perf/util/unwind-libdw.c | 6 +++++- tools/perf/util/unwind-libunwind-local.c | 11 +++++++++++ 2 files changed, 16 insertions(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c index f90e11a555b2..943a06291587 100644 --- a/tools/perf/util/unwind-libdw.c +++ b/tools/perf/util/unwind-libdw.c @@ -168,12 +168,16 @@ frame_callback(Dwfl_Frame *state, void *arg) { struct unwind_info *ui = arg; Dwarf_Addr pc; + bool isactivation; - if (!dwfl_frame_pc(state, &pc, NULL)) { + if (!dwfl_frame_pc(state, &pc, &isactivation)) { pr_err("%s", dwfl_errmsg(-1)); return DWARF_CB_ABORT; } + if (!isactivation) + --pc; + return entry(pc, ui) || !(--ui->max_stack) ? DWARF_CB_ABORT : DWARF_CB_OK; } diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c index f8455bed6e65..672c2ada9357 100644 --- a/tools/perf/util/unwind-libunwind-local.c +++ b/tools/perf/util/unwind-libunwind-local.c @@ -692,6 +692,17 @@ static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb, while (!ret && (unw_step(&c) > 0) && i < max_stack) { unw_get_reg(&c, UNW_REG_IP, &ips[i]); + + /* + * Decrement the IP for any non-activation frames. + * this is required to properly find the srcline + * for caller frames. + * See also the documentation for dwfl_frame_pc(), + * which this code tries to replicate. + */ + if (unw_is_signal_frame(&c) <= 0) + --ips[i]; + ++i; } -- cgit From 325fbff51f961491adff4037d0e0a94d6132bd9b Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Wed, 24 May 2017 15:21:26 +0900 Subject: perf script: Add --inline option for debugging The --inline option is to show inlined functions in callchains. For example: $ perf script a.out 5644 11611.467597: 309961 cycles:u: 790 main (/home/namhyung/tmp/perf/a.out) 20511 __libc_start_main (/usr/lib/libc-2.25.so) 8ba _start (/home/namhyung/tmp/perf/a.out) ... $ perf script --inline a.out 5644 11611.467597: 309961 cycles:u: 790 main (/home/namhyung/tmp/perf/a.out) std::__detail::_Adaptor, double>::operator() std::uniform_real_distribution::operator() > std::uniform_real_distribution::operator() > main 20511 __libc_start_main (/usr/lib/libc-2.25.so) 8ba _start (/home/namhyung/tmp/perf/a.out) ... Reviewed-and-tested-by: Milian Wolff Signed-off-by: Namhyung Kim Cc: Arnaldo Carvalho de Melo Cc: Arnaldo Carvalho de Melo Cc: Jin Yao Cc: Jiri Olsa Cc: Jiri Olsa Cc: Linus Torvalds Cc: Milian Wolff Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: kernel-team@lge.com Link: http://lkml.kernel.org/r/20170524062129.32529-5-namhyung@kernel.org Signed-off-by: Ingo Molnar --- tools/perf/Documentation/perf-script.txt | 4 ++++ tools/perf/builtin-script.c | 2 ++ tools/perf/util/evsel_fprintf.c | 33 ++++++++++++++++++++++++++++++++ 3 files changed, 39 insertions(+) (limited to 'tools') diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt index cb0eda3925e6..3517e204a2b3 100644 --- a/tools/perf/Documentation/perf-script.txt +++ b/tools/perf/Documentation/perf-script.txt @@ -311,6 +311,10 @@ include::itrace.txt[] Set the maximum number of program blocks to print with brstackasm for each sample. +--inline:: + If a callgraph address belongs to an inlined function, the inline stack + will be printed. Each entry has function name and file/line. + SEE ALSO -------- linkperf:perf-record[1], linkperf:perf-script-perl[1], diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index d05aec491cff..4761b0d7fcb5 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -2494,6 +2494,8 @@ int cmd_script(int argc, const char **argv) "Enable kernel symbol demangling"), OPT_STRING(0, "time", &script.time_str, "str", "Time span of interest (start,stop)"), + OPT_BOOLEAN(0, "inline", &symbol_conf.inline_name, + "Show inline function"), OPT_END() }; const char * const script_subcommands[] = { "record", "report", NULL }; diff --git a/tools/perf/util/evsel_fprintf.c b/tools/perf/util/evsel_fprintf.c index e415aee6a245..583f3a602506 100644 --- a/tools/perf/util/evsel_fprintf.c +++ b/tools/perf/util/evsel_fprintf.c @@ -7,6 +7,7 @@ #include "map.h" #include "strlist.h" #include "symbol.h" +#include "srcline.h" static int comma_fprintf(FILE *fp, bool *first, const char *fmt, ...) { @@ -168,6 +169,38 @@ int sample__fprintf_callchain(struct perf_sample *sample, int left_alignment, if (!print_oneline) printed += fprintf(fp, "\n"); + if (symbol_conf.inline_name && node->map) { + struct inline_node *inode; + + addr = map__rip_2objdump(node->map, node->ip), + inode = dso__parse_addr_inlines(node->map->dso, addr); + + if (inode) { + struct inline_list *ilist; + + list_for_each_entry(ilist, &inode->val, list) { + if (print_arrow) + printed += fprintf(fp, " <-"); + + /* IP is same, just skip it */ + if (print_ip) + printed += fprintf(fp, "%c%16s", + s, ""); + if (print_sym) + printed += fprintf(fp, " %s", + ilist->funcname); + if (print_srcline) + printed += fprintf(fp, "\n %s:%d", + ilist->filename, + ilist->line_nr); + if (!print_oneline) + printed += fprintf(fp, "\n"); + } + + inline_node__delete(inode); + } + } + if (symbol_conf.bt_stop_list && node->sym && strlist__has_entry(symbol_conf.bt_stop_list, -- cgit From 28071f51839e393f697d0d1df0b223a4bc373606 Mon Sep 17 00:00:00 2001 From: Milian Wolff Date: Wed, 24 May 2017 15:21:27 +0900 Subject: perf report: Always honor callchain order for inlined nodes So far, the inlined nodes where only reversed when we built perf against libbfd. If that was not available, the addr2line fallback code path was missing the inline_list__reverse call. Now we always add the nodes in the correct order within inline_list__append. This removes the need to reverse the list and also ensures that all callers construct the list in the right order. Signed-off-by: Milian Wolff Signed-off-by: Namhyung Kim Cc: Arnaldo Carvalho de Melo Cc: Arnaldo Carvalho de Melo Cc: David Ahern Cc: Jiri Olsa Cc: Jiri Olsa Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Yao Jin Cc: kernel-team@lge.com Link: http://lkml.kernel.org/r/20170524062129.32529-6-namhyung@kernel.org Signed-off-by: Ingo Molnar --- tools/perf/util/srcline.c | 18 ++++-------------- 1 file changed, 4 insertions(+), 14 deletions(-) (limited to 'tools') diff --git a/tools/perf/util/srcline.c b/tools/perf/util/srcline.c index 5e376d64d59e..6af0364cad06 100644 --- a/tools/perf/util/srcline.c +++ b/tools/perf/util/srcline.c @@ -56,7 +56,10 @@ static int inline_list__append(char *filename, char *funcname, int line_nr, } } - list_add_tail(&ilist->list, &node->val); + if (callchain_param.order == ORDER_CALLEE) + list_add_tail(&ilist->list, &node->val); + else + list_add(&ilist->list, &node->val); return 0; } @@ -200,14 +203,6 @@ static void addr2line_cleanup(struct a2l_data *a2l) #define MAX_INLINE_NEST 1024 -static void inline_list__reverse(struct inline_node *node) -{ - struct inline_list *ilist, *n; - - list_for_each_entry_safe_reverse(ilist, n, &node->val, list) - list_move_tail(&ilist->list, &node->val); -} - static int addr2line(const char *dso_name, u64 addr, char **file, unsigned int *line, struct dso *dso, bool unwind_inlines, struct inline_node *node) @@ -250,11 +245,6 @@ static int addr2line(const char *dso_name, u64 addr, ret = 1; } } - - if ((node != NULL) && - (callchain_param.order != ORDER_CALLEE)) { - inline_list__reverse(node); - } } if (file) { -- cgit From 4d53b9d546f9f4505e6e3d58c8eed894d6f684e7 Mon Sep 17 00:00:00 2001 From: Milian Wolff Date: Wed, 24 May 2017 15:21:28 +0900 Subject: perf report: Do not drop last inlined frame The very last inlined frame, i.e. the one furthest away from the non-inlined frame, was silently dropped. This is apparent when comparing the output of `perf script` and `addr2line`: ~~~~~~ $ perf script --inline ... a.out 26722 80836.309329: 72425 cycles: 21561 __hypot_finite (/usr/lib/libm-2.25.so) ace3 hypot (/usr/lib/libm-2.25.so) a4a main (a.out) std::abs std::_Norm_helper::_S_do_it std::norm main 20510 __libc_start_main (/usr/lib/libc-2.25.so) bd9 _start (a.out) $ addr2line -a -f -i -e /tmp/a.out a4a | c++filt 0x0000000000000a4a std::__complex_abs(doublecomplex ) /usr/include/c++/6.3.1/complex:589 double std::abs(std::complex const&) /usr/include/c++/6.3.1/complex:597 double std::_Norm_helper::_S_do_it(std::complex const&) /usr/include/c++/6.3.1/complex:654 double std::norm(std::complex const&) /usr/include/c++/6.3.1/complex:664 main /tmp/inlining.cpp:14 ~~~~~ Note how `std::__complex_abs` is missing from the `perf script` output. This is similarly showing up in `perf report`. The patch here fixes this issue, and the output becomes: ~~~~~ a.out 26722 80836.309329: 72425 cycles: 21561 __hypot_finite (/usr/lib/libm-2.25.so) ace3 hypot (/usr/lib/libm-2.25.so) a4a main (a.out) std::__complex_abs std::abs std::_Norm_helper::_S_do_it std::norm main 20510 __libc_start_main (/usr/lib/libc-2.25.so) bd9 _start (a.out) ~~~~~ Signed-off-by: Milian Wolff Signed-off-by: Namhyung Kim Cc: Arnaldo Carvalho de Melo Cc: Arnaldo Carvalho de Melo Cc: David Ahern Cc: Jiri Olsa Cc: Jiri Olsa Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Yao Jin Cc: kernel-team@lge.com Link: http://lkml.kernel.org/r/20170524062129.32529-7-namhyung@kernel.org Signed-off-by: Ingo Molnar --- tools/perf/util/srcline.c | 18 ++++++++++++++---- 1 file changed, 14 insertions(+), 4 deletions(-) (limited to 'tools') diff --git a/tools/perf/util/srcline.c b/tools/perf/util/srcline.c index 6af0364cad06..ebc88a74e67b 100644 --- a/tools/perf/util/srcline.c +++ b/tools/perf/util/srcline.c @@ -203,6 +203,16 @@ static void addr2line_cleanup(struct a2l_data *a2l) #define MAX_INLINE_NEST 1024 +static int inline_list__append_dso_a2l(struct dso *dso, + struct inline_node *node) +{ + struct a2l_data *a2l = dso->a2l; + char *funcname = a2l->funcname ? strdup(a2l->funcname) : NULL; + char *filename = a2l->filename ? strdup(a2l->filename) : NULL; + + return inline_list__append(filename, funcname, a2l->line, node, dso); +} + static int addr2line(const char *dso_name, u64 addr, char **file, unsigned int *line, struct dso *dso, bool unwind_inlines, struct inline_node *node) @@ -231,15 +241,15 @@ static int addr2line(const char *dso_name, u64 addr, if (unwind_inlines) { int cnt = 0; + if (node && inline_list__append_dso_a2l(dso, node)) + return 0; + while (bfd_find_inliner_info(a2l->abfd, &a2l->filename, &a2l->funcname, &a2l->line) && cnt++ < MAX_INLINE_NEST) { if (node != NULL) { - if (inline_list__append(strdup(a2l->filename), - strdup(a2l->funcname), - a2l->line, node, - dso) != 0) + if (inline_list__append_dso_a2l(dso, node)) return 0; // found at least one inline frame ret = 1; -- cgit From 7111ffff60a68f55d864200cd6c7677319e5c242 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Wed, 24 May 2017 15:21:29 +0900 Subject: perf tools: Put caller above callee in --children mode The __hpp__sort_acc() sorts entries using callchain depth in order to put callers above in children mode. But it assumed the callchain order was callee-first. Now default (for children) is caller-first so the order of entries is reverted. For example, consider following case: $ perf report --no-children ..l # Overhead Command Shared Object Symbol # ........ ....... ................... .......................... # 99.44% a.out a.out [.] main | ---main __libc_start_main _start Then children mode should show 'start' above '__libc_start_main' since it's the caller (parent) of the __libc_start_main. But it's reversed: # Children Self Command Shared Object Symbol # ........ ........ ....... ............... ..................... # 99.61% 0.00% a.out libc-2.25.so [.] __libc_start_main 99.61% 0.00% a.out a.out [.] _start 99.54% 99.44% a.out a.out [.] main This patch fixes it. # Children Self Command Shared Object Symbol # ........ ........ ....... ............... ..................... # 99.61% 0.00% a.out a.out [.] _start 99.61% 0.00% a.out libc-2.25.so [.] __libc_start_main 99.54% 99.44% a.out a.out [.] main Signed-off-by: Namhyung Kim Acked-by: Jiri Olsa Cc: Arnaldo Carvalho de Melo Cc: Arnaldo Carvalho de Melo Cc: Frederic Weisbecker Cc: Jiri Olsa Cc: Linus Torvalds Cc: Milian Wolff Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Yao Jin Cc: kernel-team@lge.com Link: http://lkml.kernel.org/r/20170524062129.32529-8-namhyung@kernel.org Signed-off-by: Ingo Molnar --- tools/perf/ui/hist.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'tools') diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c index 59addd52d9cd..ddb2c6fbdf91 100644 --- a/tools/perf/ui/hist.c +++ b/tools/perf/ui/hist.c @@ -210,6 +210,8 @@ static int __hpp__sort_acc(struct hist_entry *a, struct hist_entry *b, return 0; ret = b->callchain->max_depth - a->callchain->max_depth; + if (callchain_param.order == ORDER_CALLER) + ret = -ret; } return ret; } -- cgit From 6e30437bd42c4d4e9cfc4c40efda00eb83a11cde Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Wed, 24 May 2017 08:57:21 +0200 Subject: tools/include: Sync kernel ABI headers with tooling headers Sync (copy) the following v4.12 kernel headers to the tooling headers: arch/x86/include/asm/disabled-features.h: arch/x86/include/uapi/asm/kvm.h: arch/powerpc/include/uapi/asm/kvm.h: arch/s390/include/uapi/asm/kvm.h: arch/arm/include/uapi/asm/kvm.h: arch/arm64/include/uapi/asm/kvm.h: - 'struct kvm_sync_regs' got changed in an ABI-incompatible way, fortunately none of the (in-kernel) tooling relied on it - new KVM_DEV calls added arch/x86/include/asm/required-features.h: - 5-level paging hardware ABI detail added arch/x86/include/asm/cpufeatures.h: - new CPU feature added arch/x86/include/uapi/asm/vmx.h: - new VMX exit conditions None of the changes requires fixes in the tooling source code. This addresses the following warnings: Warning: include/uapi/linux/stat.h differs from kernel Warning: arch/x86/include/asm/disabled-features.h differs from kernel Warning: arch/x86/include/asm/required-features.h differs from kernel Warning: arch/x86/include/asm/cpufeatures.h differs from kernel Warning: arch/x86/include/uapi/asm/kvm.h differs from kernel Warning: arch/x86/include/uapi/asm/vmx.h differs from kernel Warning: arch/powerpc/include/uapi/asm/kvm.h differs from kernel Warning: arch/s390/include/uapi/asm/kvm.h differs from kernel Warning: arch/arm/include/uapi/asm/kvm.h differs from kernel Warning: arch/arm64/include/uapi/asm/kvm.h differs from kernel Cc: Arnaldo Carvalho de Melo Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Jiri Olsa Cc: Linus Torvalds Cc: Milian Wolff Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Yao Jin Cc: kernel-team@lge.com Link: http://lkml.kernel.org/r/20170524065721.j2mlch6bgk5klgbc@gmail.com Signed-off-by: Ingo Molnar --- tools/arch/arm/include/uapi/asm/kvm.h | 10 +++++++++- tools/arch/arm64/include/uapi/asm/kvm.h | 10 +++++++++- tools/arch/powerpc/include/uapi/asm/kvm.h | 3 +++ tools/arch/s390/include/uapi/asm/kvm.h | 26 ++++++++++++++++++++++++-- tools/arch/x86/include/asm/cpufeatures.h | 2 ++ tools/arch/x86/include/asm/disabled-features.h | 8 +++++++- tools/arch/x86/include/asm/required-features.h | 8 +++++++- tools/arch/x86/include/uapi/asm/kvm.h | 3 +++ tools/arch/x86/include/uapi/asm/vmx.h | 25 ++++++++++++++++++------- tools/include/uapi/linux/stat.h | 8 ++------ 10 files changed, 84 insertions(+), 19 deletions(-) (limited to 'tools') diff --git a/tools/arch/arm/include/uapi/asm/kvm.h b/tools/arch/arm/include/uapi/asm/kvm.h index 6ebd3e6a1fd1..5e3c673fa3f4 100644 --- a/tools/arch/arm/include/uapi/asm/kvm.h +++ b/tools/arch/arm/include/uapi/asm/kvm.h @@ -27,6 +27,8 @@ #define __KVM_HAVE_IRQ_LINE #define __KVM_HAVE_READONLY_MEM +#define KVM_COALESCED_MMIO_PAGE_OFFSET 1 + #define KVM_REG_SIZE(id) \ (1U << (((id) & KVM_REG_SIZE_MASK) >> KVM_REG_SIZE_SHIFT)) @@ -114,6 +116,8 @@ struct kvm_debug_exit_arch { }; struct kvm_sync_regs { + /* Used with KVM_CAP_ARM_USER_IRQ */ + __u64 device_irq_level; }; struct kvm_arch_memory_slot { @@ -192,13 +196,17 @@ struct kvm_arch_memory_slot { #define KVM_DEV_ARM_VGIC_GRP_REDIST_REGS 5 #define KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS 6 #define KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO 7 +#define KVM_DEV_ARM_VGIC_GRP_ITS_REGS 8 #define KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_SHIFT 10 #define KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_MASK \ (0x3fffffULL << KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_SHIFT) #define KVM_DEV_ARM_VGIC_LINE_LEVEL_INTID_MASK 0x3ff #define VGIC_LEVEL_INFO_LINE_LEVEL 0 -#define KVM_DEV_ARM_VGIC_CTRL_INIT 0 +#define KVM_DEV_ARM_VGIC_CTRL_INIT 0 +#define KVM_DEV_ARM_ITS_SAVE_TABLES 1 +#define KVM_DEV_ARM_ITS_RESTORE_TABLES 2 +#define KVM_DEV_ARM_VGIC_SAVE_PENDING_TABLES 3 /* KVM_IRQ_LINE irq field index values */ #define KVM_ARM_IRQ_TYPE_SHIFT 24 diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h index c2860358ae3e..70eea2ecc663 100644 --- a/tools/arch/arm64/include/uapi/asm/kvm.h +++ b/tools/arch/arm64/include/uapi/asm/kvm.h @@ -39,6 +39,8 @@ #define __KVM_HAVE_IRQ_LINE #define __KVM_HAVE_READONLY_MEM +#define KVM_COALESCED_MMIO_PAGE_OFFSET 1 + #define KVM_REG_SIZE(id) \ (1U << (((id) & KVM_REG_SIZE_MASK) >> KVM_REG_SIZE_SHIFT)) @@ -143,6 +145,8 @@ struct kvm_debug_exit_arch { #define KVM_GUESTDBG_USE_HW (1 << 17) struct kvm_sync_regs { + /* Used with KVM_CAP_ARM_USER_IRQ */ + __u64 device_irq_level; }; struct kvm_arch_memory_slot { @@ -212,13 +216,17 @@ struct kvm_arch_memory_slot { #define KVM_DEV_ARM_VGIC_GRP_REDIST_REGS 5 #define KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS 6 #define KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO 7 +#define KVM_DEV_ARM_VGIC_GRP_ITS_REGS 8 #define KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_SHIFT 10 #define KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_MASK \ (0x3fffffULL << KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_SHIFT) #define KVM_DEV_ARM_VGIC_LINE_LEVEL_INTID_MASK 0x3ff #define VGIC_LEVEL_INFO_LINE_LEVEL 0 -#define KVM_DEV_ARM_VGIC_CTRL_INIT 0 +#define KVM_DEV_ARM_VGIC_CTRL_INIT 0 +#define KVM_DEV_ARM_ITS_SAVE_TABLES 1 +#define KVM_DEV_ARM_ITS_RESTORE_TABLES 2 +#define KVM_DEV_ARM_VGIC_SAVE_PENDING_TABLES 3 /* Device Control API on vcpu fd */ #define KVM_ARM_VCPU_PMU_V3_CTRL 0 diff --git a/tools/arch/powerpc/include/uapi/asm/kvm.h b/tools/arch/powerpc/include/uapi/asm/kvm.h index 4edbe4bb0e8b..07fbeb927834 100644 --- a/tools/arch/powerpc/include/uapi/asm/kvm.h +++ b/tools/arch/powerpc/include/uapi/asm/kvm.h @@ -29,6 +29,9 @@ #define __KVM_HAVE_IRQ_LINE #define __KVM_HAVE_GUEST_DEBUG +/* Not always available, but if it is, this is the correct offset. */ +#define KVM_COALESCED_MMIO_PAGE_OFFSET 1 + struct kvm_regs { __u64 pc; __u64 cr; diff --git a/tools/arch/s390/include/uapi/asm/kvm.h b/tools/arch/s390/include/uapi/asm/kvm.h index 7f4fd65e9208..3dd2a1d308dd 100644 --- a/tools/arch/s390/include/uapi/asm/kvm.h +++ b/tools/arch/s390/include/uapi/asm/kvm.h @@ -26,6 +26,8 @@ #define KVM_DEV_FLIC_ADAPTER_REGISTER 6 #define KVM_DEV_FLIC_ADAPTER_MODIFY 7 #define KVM_DEV_FLIC_CLEAR_IO_IRQ 8 +#define KVM_DEV_FLIC_AISM 9 +#define KVM_DEV_FLIC_AIRQ_INJECT 10 /* * We can have up to 4*64k pending subchannels + 8 adapter interrupts, * as well as up to ASYNC_PF_PER_VCPU*KVM_MAX_VCPUS pfault done interrupts. @@ -41,7 +43,14 @@ struct kvm_s390_io_adapter { __u8 isc; __u8 maskable; __u8 swap; - __u8 pad; + __u8 flags; +}; + +#define KVM_S390_ADAPTER_SUPPRESSIBLE 0x01 + +struct kvm_s390_ais_req { + __u8 isc; + __u16 mode; }; #define KVM_S390_IO_ADAPTER_MASK 1 @@ -110,6 +119,7 @@ struct kvm_s390_vm_cpu_machine { #define KVM_S390_VM_CPU_FEAT_CMMA 10 #define KVM_S390_VM_CPU_FEAT_PFMFI 11 #define KVM_S390_VM_CPU_FEAT_SIGPIF 12 +#define KVM_S390_VM_CPU_FEAT_KSS 13 struct kvm_s390_vm_cpu_feat { __u64 feat[16]; }; @@ -198,6 +208,10 @@ struct kvm_guest_debug_arch { #define KVM_SYNC_VRS (1UL << 6) #define KVM_SYNC_RICCB (1UL << 7) #define KVM_SYNC_FPRS (1UL << 8) +#define KVM_SYNC_GSCB (1UL << 9) +/* length and alignment of the sdnx as a power of two */ +#define SDNXC 8 +#define SDNXL (1UL << SDNXC) /* definition of registers in kvm_run */ struct kvm_sync_regs { __u64 prefix; /* prefix register */ @@ -218,8 +232,16 @@ struct kvm_sync_regs { }; __u8 reserved[512]; /* for future vector expansion */ __u32 fpc; /* valid on KVM_SYNC_VRS or KVM_SYNC_FPRS */ - __u8 padding[52]; /* riccb needs to be 64byte aligned */ + __u8 padding1[52]; /* riccb needs to be 64byte aligned */ __u8 riccb[64]; /* runtime instrumentation controls block */ + __u8 padding2[192]; /* sdnx needs to be 256byte aligned */ + union { + __u8 sdnx[SDNXL]; /* state description annex */ + struct { + __u64 reserved1[2]; + __u64 gscb[4]; + }; + }; }; #define KVM_REG_S390_TODPR (KVM_REG_S390 | KVM_REG_SIZE_U32 | 0x1) diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index 0fe00446f9ca..2701e5f8145b 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -202,6 +202,8 @@ #define X86_FEATURE_AVX512_4VNNIW (7*32+16) /* AVX-512 Neural Network Instructions */ #define X86_FEATURE_AVX512_4FMAPS (7*32+17) /* AVX-512 Multiply Accumulation Single precision */ +#define X86_FEATURE_MBA ( 7*32+18) /* Memory Bandwidth Allocation */ + /* Virtualization flags: Linux defined, word 8 */ #define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */ #define X86_FEATURE_VNMI ( 8*32+ 1) /* Intel Virtual NMI */ diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h index 85599ad4d024..5dff775af7cd 100644 --- a/tools/arch/x86/include/asm/disabled-features.h +++ b/tools/arch/x86/include/asm/disabled-features.h @@ -36,6 +36,12 @@ # define DISABLE_OSPKE (1<<(X86_FEATURE_OSPKE & 31)) #endif /* CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS */ +#ifdef CONFIG_X86_5LEVEL +# define DISABLE_LA57 0 +#else +# define DISABLE_LA57 (1<<(X86_FEATURE_LA57 & 31)) +#endif + /* * Make sure to add features to the correct mask */ @@ -55,7 +61,7 @@ #define DISABLED_MASK13 0 #define DISABLED_MASK14 0 #define DISABLED_MASK15 0 -#define DISABLED_MASK16 (DISABLE_PKU|DISABLE_OSPKE) +#define DISABLED_MASK16 (DISABLE_PKU|DISABLE_OSPKE|DISABLE_LA57) #define DISABLED_MASK17 0 #define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 18) diff --git a/tools/arch/x86/include/asm/required-features.h b/tools/arch/x86/include/asm/required-features.h index fac9a5c0abe9..d91ba04dd007 100644 --- a/tools/arch/x86/include/asm/required-features.h +++ b/tools/arch/x86/include/asm/required-features.h @@ -53,6 +53,12 @@ # define NEED_MOVBE 0 #endif +#ifdef CONFIG_X86_5LEVEL +# define NEED_LA57 (1<<(X86_FEATURE_LA57 & 31)) +#else +# define NEED_LA57 0 +#endif + #ifdef CONFIG_X86_64 #ifdef CONFIG_PARAVIRT /* Paravirtualized systems may not have PSE or PGE available */ @@ -98,7 +104,7 @@ #define REQUIRED_MASK13 0 #define REQUIRED_MASK14 0 #define REQUIRED_MASK15 0 -#define REQUIRED_MASK16 0 +#define REQUIRED_MASK16 (NEED_LA57) #define REQUIRED_MASK17 0 #define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 18) diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h index 739c0c594022..c2824d02ba37 100644 --- a/tools/arch/x86/include/uapi/asm/kvm.h +++ b/tools/arch/x86/include/uapi/asm/kvm.h @@ -9,6 +9,9 @@ #include #include +#define KVM_PIO_PAGE_OFFSET 1 +#define KVM_COALESCED_MMIO_PAGE_OFFSET 2 + #define DE_VECTOR 0 #define DB_VECTOR 1 #define BP_VECTOR 3 diff --git a/tools/arch/x86/include/uapi/asm/vmx.h b/tools/arch/x86/include/uapi/asm/vmx.h index 14458658e988..690a2dcf4078 100644 --- a/tools/arch/x86/include/uapi/asm/vmx.h +++ b/tools/arch/x86/include/uapi/asm/vmx.h @@ -76,7 +76,11 @@ #define EXIT_REASON_WBINVD 54 #define EXIT_REASON_XSETBV 55 #define EXIT_REASON_APIC_WRITE 56 +#define EXIT_REASON_RDRAND 57 #define EXIT_REASON_INVPCID 58 +#define EXIT_REASON_VMFUNC 59 +#define EXIT_REASON_ENCLS 60 +#define EXIT_REASON_RDSEED 61 #define EXIT_REASON_PML_FULL 62 #define EXIT_REASON_XSAVES 63 #define EXIT_REASON_XRSTORS 64 @@ -90,6 +94,7 @@ { EXIT_REASON_TASK_SWITCH, "TASK_SWITCH" }, \ { EXIT_REASON_CPUID, "CPUID" }, \ { EXIT_REASON_HLT, "HLT" }, \ + { EXIT_REASON_INVD, "INVD" }, \ { EXIT_REASON_INVLPG, "INVLPG" }, \ { EXIT_REASON_RDPMC, "RDPMC" }, \ { EXIT_REASON_RDTSC, "RDTSC" }, \ @@ -108,6 +113,8 @@ { EXIT_REASON_IO_INSTRUCTION, "IO_INSTRUCTION" }, \ { EXIT_REASON_MSR_READ, "MSR_READ" }, \ { EXIT_REASON_MSR_WRITE, "MSR_WRITE" }, \ + { EXIT_REASON_INVALID_STATE, "INVALID_STATE" }, \ + { EXIT_REASON_MSR_LOAD_FAIL, "MSR_LOAD_FAIL" }, \ { EXIT_REASON_MWAIT_INSTRUCTION, "MWAIT_INSTRUCTION" }, \ { EXIT_REASON_MONITOR_TRAP_FLAG, "MONITOR_TRAP_FLAG" }, \ { EXIT_REASON_MONITOR_INSTRUCTION, "MONITOR_INSTRUCTION" }, \ @@ -115,20 +122,24 @@ { EXIT_REASON_MCE_DURING_VMENTRY, "MCE_DURING_VMENTRY" }, \ { EXIT_REASON_TPR_BELOW_THRESHOLD, "TPR_BELOW_THRESHOLD" }, \ { EXIT_REASON_APIC_ACCESS, "APIC_ACCESS" }, \ - { EXIT_REASON_GDTR_IDTR, "GDTR_IDTR" }, \ - { EXIT_REASON_LDTR_TR, "LDTR_TR" }, \ + { EXIT_REASON_EOI_INDUCED, "EOI_INDUCED" }, \ + { EXIT_REASON_GDTR_IDTR, "GDTR_IDTR" }, \ + { EXIT_REASON_LDTR_TR, "LDTR_TR" }, \ { EXIT_REASON_EPT_VIOLATION, "EPT_VIOLATION" }, \ { EXIT_REASON_EPT_MISCONFIG, "EPT_MISCONFIG" }, \ { EXIT_REASON_INVEPT, "INVEPT" }, \ + { EXIT_REASON_RDTSCP, "RDTSCP" }, \ { EXIT_REASON_PREEMPTION_TIMER, "PREEMPTION_TIMER" }, \ + { EXIT_REASON_INVVPID, "INVVPID" }, \ { EXIT_REASON_WBINVD, "WBINVD" }, \ + { EXIT_REASON_XSETBV, "XSETBV" }, \ { EXIT_REASON_APIC_WRITE, "APIC_WRITE" }, \ - { EXIT_REASON_EOI_INDUCED, "EOI_INDUCED" }, \ - { EXIT_REASON_INVALID_STATE, "INVALID_STATE" }, \ - { EXIT_REASON_MSR_LOAD_FAIL, "MSR_LOAD_FAIL" }, \ - { EXIT_REASON_INVD, "INVD" }, \ - { EXIT_REASON_INVVPID, "INVVPID" }, \ + { EXIT_REASON_RDRAND, "RDRAND" }, \ { EXIT_REASON_INVPCID, "INVPCID" }, \ + { EXIT_REASON_VMFUNC, "VMFUNC" }, \ + { EXIT_REASON_ENCLS, "ENCLS" }, \ + { EXIT_REASON_RDSEED, "RDSEED" }, \ + { EXIT_REASON_PML_FULL, "PML_FULL" }, \ { EXIT_REASON_XSAVES, "XSAVES" }, \ { EXIT_REASON_XRSTORS, "XRSTORS" } diff --git a/tools/include/uapi/linux/stat.h b/tools/include/uapi/linux/stat.h index d538897b8e08..17b10304c393 100644 --- a/tools/include/uapi/linux/stat.h +++ b/tools/include/uapi/linux/stat.h @@ -48,17 +48,13 @@ * tv_sec holds the number of seconds before (negative) or after (positive) * 00:00:00 1st January 1970 UTC. * - * tv_nsec holds a number of nanoseconds before (0..-999,999,999 if tv_sec is - * negative) or after (0..999,999,999 if tv_sec is positive) the tv_sec time. - * - * Note that if both tv_sec and tv_nsec are non-zero, then the two values must - * either be both positive or both negative. + * tv_nsec holds a number of nanoseconds (0..999,999,999) after the tv_sec time. * * __reserved is held in case we need a yet finer resolution. */ struct statx_timestamp { __s64 tv_sec; - __s32 tv_nsec; + __u32 tv_nsec; __s32 __reserved; }; -- cgit