From 172bf02d564bdb6df8410f64720fa2c68e755d1a Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 7 Jan 2019 16:24:27 -0300 Subject: [PATCH 01/16] perf trace: Fix ')' placement in "interrupted" syscall lines MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When we get the sys_enter for a syscall we check if the last one is still waiting for its matching sys_exit, if so we print this: 468.753 ( ): firefox/32382 poll(ufds: 0x7f3988d3dd00, nfds: 7, timeout_msecs: 4294967295) ... 449.575 ( 0.004 ms): Softwar~cThrea/32434 futex(uaddr: 0x7f39a18a9b70, op: WAKE|PRIVATE_FLAG, val: 1) = 0 At some point we'll get that poll sys_exit event and will print a "[continued]" line. While making the sizing of the alignment after the syscall arg list and its result configurable, so that we can mimic strace, which uses a smaller alingment by default, a bug was introduced where the closing parens appeared before the syscall name and its arg list, fix it. Fixes: 4b8a240ed5e0 ("perf trace: Add alignment spaces after the closing parens") Cc: Adrian Hunter Cc: Jiri Olsa Cc: Luis Cláudio Gonçalves Cc: Namhyung Kim Cc: Wang Nan Link: https://lkml.kernel.org/n/tip-oi45i54s59h1w1kmgpzrfuum@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-trace.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index adbf28183560..b8bf5d025563 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -1758,6 +1758,7 @@ static int trace__printf_interrupted_entry(struct trace *trace) { struct thread_trace *ttrace; size_t printed; + int len; if (trace->failure_only || trace->current == NULL) return 0; @@ -1768,9 +1769,14 @@ static int trace__printf_interrupted_entry(struct trace *trace) return 0; printed = trace__fprintf_entry_head(trace, trace->current, 0, false, ttrace->entry_time, trace->output); - printed += fprintf(trace->output, ")%-*s ...\n", trace->args_alignment, ttrace->entry_str); - ttrace->entry_pending = false; + printed += len = fprintf(trace->output, "%s)", ttrace->entry_str); + if (len < trace->args_alignment - 4) + printed += fprintf(trace->output, "%-*s", trace->args_alignment - 4 - len, " "); + + printed += fprintf(trace->output, " ...\n"); + + ttrace->entry_pending = false; ++trace->nr_events_printed; return printed; From ac6e022cbfdce215ad545e91d9827060855da3d7 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 7 Jan 2019 16:54:38 -0300 Subject: [PATCH 02/16] perf trace: Fix alignment for [continued] lines MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit We were not taking into account the "... [continued]" printed characters, fix it. Cc: Adrian Hunter Cc: Jiri Olsa Cc: Luis Cláudio Gonçalves Cc: Namhyung Kim Cc: Wang Nan Link: https://lkml.kernel.org/n/tip-qt20y0acmf8k0bzisce8kw95@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-trace.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index b8bf5d025563..ed4583128b9c 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -2032,9 +2032,10 @@ static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel, if (ttrace->entry_pending) { printed = fprintf(trace->output, "%s", ttrace->entry_str); } else { - fprintf(trace->output, " ... ["); + printed += fprintf(trace->output, " ... ["); color_fprintf(trace->output, PERF_COLOR_YELLOW, "continued"); - fprintf(trace->output, "]: %s()", sc->name); + printed += 9; + printed += fprintf(trace->output, "]: %s()", sc->name); } printed++; /* the closing ')' */ From 011532379b7c2de6757e129037bdfc8d704bce23 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Thu, 20 Dec 2018 19:43:36 -0800 Subject: [PATCH 03/16] perf tools: Make find_vdso_map() more modular In preparation for checking that the vectors page on the ARM architecture, refactor the find_vdso_map() function to accept finding an arbitrary string and create a dedicated helper function for that under util/find-map.c and update the filename to find-map.c and all references to it: perf-read-vdso.c and util/vdso.c. Signed-off-by: Florian Fainelli Acked-by: Jiri Olsa Cc: Alexander Shishkin Cc: Chris Healy Cc: Greg Kroah-Hartman Cc: Kim Phillips Cc: Lucas Stach Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Russell King Cc: Thomas Gleixner Cc: Thomas Richter Link: http://lkml.kernel.org/r/20181221034337.26663-2-f.fainelli@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Makefile.perf | 4 ++-- tools/perf/perf-read-vdso.c | 6 +++--- tools/perf/util/{find-vdso-map.c => find-map.c} | 7 +++---- tools/perf/util/vdso.c | 6 +++--- 4 files changed, 11 insertions(+), 12 deletions(-) rename tools/perf/util/{find-vdso-map.c => find-map.c} (71%) diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 2921f829a0f4..0ee6795d82cc 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -662,12 +662,12 @@ $(OUTPUT)perf-%: %.o $(PERFLIBS) $(QUIET_LINK)$(CC) $(CFLAGS) -o $@ $(LDFLAGS) $(filter %.o,$^) $(LIBS) ifndef NO_PERF_READ_VDSO32 -$(OUTPUT)perf-read-vdso32: perf-read-vdso.c util/find-vdso-map.c +$(OUTPUT)perf-read-vdso32: perf-read-vdso.c util/find-map.c $(QUIET_CC)$(CC) -m32 $(filter -static,$(LDFLAGS)) -Wall -Werror -o $@ perf-read-vdso.c endif ifndef NO_PERF_READ_VDSOX32 -$(OUTPUT)perf-read-vdsox32: perf-read-vdso.c util/find-vdso-map.c +$(OUTPUT)perf-read-vdsox32: perf-read-vdso.c util/find-map.c $(QUIET_CC)$(CC) -mx32 $(filter -static,$(LDFLAGS)) -Wall -Werror -o $@ perf-read-vdso.c endif diff --git a/tools/perf/perf-read-vdso.c b/tools/perf/perf-read-vdso.c index 8c0ca0cc428f..aaa5210ea84a 100644 --- a/tools/perf/perf-read-vdso.c +++ b/tools/perf/perf-read-vdso.c @@ -5,17 +5,17 @@ #define VDSO__MAP_NAME "[vdso]" /* - * Include definition of find_vdso_map() also used in util/vdso.c for + * Include definition of find_map() also used in util/vdso.c for * building perf. */ -#include "util/find-vdso-map.c" +#include "util/find-map.c" int main(void) { void *start, *end; size_t size, written; - if (find_vdso_map(&start, &end)) + if (find_map(&start, &end, VDSO__MAP_NAME)) return 1; size = end - start; diff --git a/tools/perf/util/find-vdso-map.c b/tools/perf/util/find-map.c similarity index 71% rename from tools/perf/util/find-vdso-map.c rename to tools/perf/util/find-map.c index d7823e3508fc..7b2300588ece 100644 --- a/tools/perf/util/find-vdso-map.c +++ b/tools/perf/util/find-map.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -static int find_vdso_map(void **start, void **end) +static int find_map(void **start, void **end, const char *name) { FILE *maps; char line[128]; @@ -7,7 +7,7 @@ static int find_vdso_map(void **start, void **end) maps = fopen("/proc/self/maps", "r"); if (!maps) { - fprintf(stderr, "vdso: cannot open maps\n"); + fprintf(stderr, "cannot open maps\n"); return -1; } @@ -21,8 +21,7 @@ static int find_vdso_map(void **start, void **end) if (m < 0) continue; - if (!strncmp(&line[m], VDSO__MAP_NAME, - sizeof(VDSO__MAP_NAME) - 1)) + if (!strncmp(&line[m], name, strlen(name))) found = 1; } diff --git a/tools/perf/util/vdso.c b/tools/perf/util/vdso.c index 741af209b19d..3702cba11d7d 100644 --- a/tools/perf/util/vdso.c +++ b/tools/perf/util/vdso.c @@ -18,10 +18,10 @@ #include "debug.h" /* - * Include definition of find_vdso_map() also used in perf-read-vdso.c for + * Include definition of find_map() also used in perf-read-vdso.c for * building perf-read-vdso32 and perf-read-vdsox32. */ -#include "find-vdso-map.c" +#include "find-map.c" #define VDSO__TEMP_FILE_NAME "/tmp/perf-vdso.so-XXXXXX" @@ -76,7 +76,7 @@ static char *get_file(struct vdso_file *vdso_file) if (vdso_file->found) return vdso_file->temp_file_name; - if (vdso_file->error || find_vdso_map(&start, &end)) + if (vdso_file->error || find_map(&start, &end, VDSO__MAP_NAME)) return NULL; size = end - start; From 21327c7843e9169d5e2e527713e60e6c9842a56c Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Thu, 20 Dec 2018 19:43:37 -0800 Subject: [PATCH 04/16] perf tests: Add a test for the ARM 32-bit [vectors] page perf on ARM requires CONFIG_KUSER_HELPERS to be turned on to allow some independance with respect to the ARM CPU being used. Add a test which tries to locate the [vectors] page, created when CONFIG_KUSER_HELPERS is turned on to help asses the system's health. Signed-off-by: Florian Fainelli Acked-by: Jiri Olsa Cc: Alexander Shishkin Cc: Chris Healy Cc: Greg Kroah-Hartman Cc: Kim Phillips Cc: Lucas Stach Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Russell King Cc: Thomas Gleixner Cc: Thomas Richter Link: http://lkml.kernel.org/r/20181221034337.26663-3-f.fainelli@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/arch/arm/tests/Build | 1 + tools/perf/arch/arm/tests/arch-tests.c | 4 ++++ tools/perf/arch/arm/tests/vectors-page.c | 24 ++++++++++++++++++++++++ tools/perf/tests/tests.h | 5 +++++ 4 files changed, 34 insertions(+) create mode 100644 tools/perf/arch/arm/tests/vectors-page.c diff --git a/tools/perf/arch/arm/tests/Build b/tools/perf/arch/arm/tests/Build index 883c57ff0c08..d9ae2733f9cc 100644 --- a/tools/perf/arch/arm/tests/Build +++ b/tools/perf/arch/arm/tests/Build @@ -1,4 +1,5 @@ libperf-y += regs_load.o libperf-y += dwarf-unwind.o +libperf-y += vectors-page.o libperf-y += arch-tests.o diff --git a/tools/perf/arch/arm/tests/arch-tests.c b/tools/perf/arch/arm/tests/arch-tests.c index 5b1543c98022..6848101a855f 100644 --- a/tools/perf/arch/arm/tests/arch-tests.c +++ b/tools/perf/arch/arm/tests/arch-tests.c @@ -10,6 +10,10 @@ struct test arch_tests[] = { .func = test__dwarf_unwind, }, #endif + { + .desc = "Vectors page", + .func = test__vectors_page, + }, { .func = NULL, }, diff --git a/tools/perf/arch/arm/tests/vectors-page.c b/tools/perf/arch/arm/tests/vectors-page.c new file mode 100644 index 000000000000..7ffdd79971c8 --- /dev/null +++ b/tools/perf/arch/arm/tests/vectors-page.c @@ -0,0 +1,24 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include +#include + +#include "debug.h" +#include "tests/tests.h" +#include "util/find-map.c" + +#define VECTORS__MAP_NAME "[vectors]" + +int test__vectors_page(struct test *test __maybe_unused, + int subtest __maybe_unused) +{ + void *start, *end; + + if (find_map(&start, &end, VECTORS__MAP_NAME)) { + pr_err("%s not found, is CONFIG_KUSER_HELPERS enabled?\n", + VECTORS__MAP_NAME); + return TEST_FAIL; + } + + return TEST_OK; +} diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h index b82f55fcc294..399f18ca71a3 100644 --- a/tools/perf/tests/tests.h +++ b/tools/perf/tests/tests.h @@ -119,4 +119,9 @@ int test__arch_unwind_sample(struct perf_sample *sample, struct thread *thread); #endif #endif + +#if defined(__arm__) +int test__vectors_page(struct test *test, int subtest); +#endif + #endif /* TESTS_H */ From ca3958b1c0968a6f3105e211355f128ce871e796 Mon Sep 17 00:00:00 2001 From: Tzvetomir Stoyanov Date: Fri, 30 Nov 2018 10:44:11 -0500 Subject: [PATCH 05/16] tools lib traceevent: Introduce new libtracevent API: tep_override_comm() This patch adds a new API of tracevent library: tep_override_comm() It registers a pid / command mapping. If a mapping with the same pid already exists, the entry is updated with the new command. Signed-off-by: Tzvetomir Stoyanov Cc: Andrew Morton Cc: Jiri Olsa Cc: Namhyung Kim Link: http://lkml.kernel.org/r/20181130154648.038915912@goodmis.org Signed-off-by: Steven Rostedt (VMware) Signed-off-by: Arnaldo Carvalho de Melo --- tools/lib/traceevent/event-parse.c | 69 +++++++++++++++++++++++------- tools/lib/traceevent/event-parse.h | 1 + 2 files changed, 55 insertions(+), 15 deletions(-) diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c index 69a96e39f0ab..156e513074b2 100644 --- a/tools/lib/traceevent/event-parse.c +++ b/tools/lib/traceevent/event-parse.c @@ -232,11 +232,13 @@ int tep_pid_is_registered(struct tep_handle *pevent, int pid) * we must add this pid. This is much slower than when cmdlines * are added before the array is initialized. */ -static int add_new_comm(struct tep_handle *pevent, const char *comm, int pid) +static int add_new_comm(struct tep_handle *pevent, + const char *comm, int pid, bool override) { struct cmdline *cmdlines = pevent->cmdlines; - const struct cmdline *cmdline; + struct cmdline *cmdline; struct cmdline key; + char *new_comm; if (!pid) return 0; @@ -247,8 +249,19 @@ static int add_new_comm(struct tep_handle *pevent, const char *comm, int pid) cmdline = bsearch(&key, pevent->cmdlines, pevent->cmdline_count, sizeof(*pevent->cmdlines), cmdline_cmp); if (cmdline) { - errno = EEXIST; - return -1; + if (!override) { + errno = EEXIST; + return -1; + } + new_comm = strdup(comm); + if (!new_comm) { + errno = ENOMEM; + return -1; + } + free(cmdline->comm); + cmdline->comm = new_comm; + + return 0; } cmdlines = realloc(cmdlines, sizeof(*cmdlines) * (pevent->cmdline_count + 1)); @@ -275,21 +288,13 @@ static int add_new_comm(struct tep_handle *pevent, const char *comm, int pid) return 0; } -/** - * tep_register_comm - register a pid / comm mapping - * @pevent: handle for the pevent - * @comm: the command line to register - * @pid: the pid to map the command line to - * - * This adds a mapping to search for command line names with - * a given pid. The comm is duplicated. - */ -int tep_register_comm(struct tep_handle *pevent, const char *comm, int pid) +static int _tep_register_comm(struct tep_handle *pevent, + const char *comm, int pid, bool override) { struct cmdline_list *item; if (pevent->cmdlines) - return add_new_comm(pevent, comm, pid); + return add_new_comm(pevent, comm, pid, override); item = malloc(sizeof(*item)); if (!item) @@ -312,6 +317,40 @@ int tep_register_comm(struct tep_handle *pevent, const char *comm, int pid) return 0; } +/** + * tep_register_comm - register a pid / comm mapping + * @pevent: handle for the pevent + * @comm: the command line to register + * @pid: the pid to map the command line to + * + * This adds a mapping to search for command line names with + * a given pid. The comm is duplicated. If a command with the same pid + * already exist, -1 is returned and errno is set to EEXIST + */ +int tep_register_comm(struct tep_handle *pevent, const char *comm, int pid) +{ + return _tep_register_comm(pevent, comm, pid, false); +} + +/** + * tep_override_comm - register a pid / comm mapping + * @pevent: handle for the pevent + * @comm: the command line to register + * @pid: the pid to map the command line to + * + * This adds a mapping to search for command line names with + * a given pid. The comm is duplicated. If a command with the same pid + * already exist, the command string is udapted with the new one + */ +int tep_override_comm(struct tep_handle *pevent, const char *comm, int pid) +{ + if (!pevent->cmdlines && cmdline_init(pevent)) { + errno = ENOMEM; + return -1; + } + return _tep_register_comm(pevent, comm, pid, true); +} + int tep_register_trace_clock(struct tep_handle *pevent, const char *trace_clock) { pevent->trace_clock = strdup(trace_clock); diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h index 35d37087d3c5..e6f4249910e6 100644 --- a/tools/lib/traceevent/event-parse.h +++ b/tools/lib/traceevent/event-parse.h @@ -432,6 +432,7 @@ int tep_set_function_resolver(struct tep_handle *pevent, tep_func_resolver_t *func, void *priv); void tep_reset_function_resolver(struct tep_handle *pevent); int tep_register_comm(struct tep_handle *pevent, const char *comm, int pid); +int tep_override_comm(struct tep_handle *pevent, const char *comm, int pid); int tep_register_trace_clock(struct tep_handle *pevent, const char *trace_clock); int tep_register_function(struct tep_handle *pevent, char *name, unsigned long long addr, char *mod); From eed14f4b075ec594ac09921b998bf3dd61f5886b Mon Sep 17 00:00:00 2001 From: Tzvetomir Stoyanov Date: Fri, 30 Nov 2018 23:08:08 -0500 Subject: [PATCH 06/16] tools lib traceevent: Initialize host_bigendian at tep_handle allocation This patch initializes the host_bigendian member of the tep_handle structure with the byte order of the current host, when this handler is created - in tep_alloc() API. We need this in order to remove the tep_set_host_bigendian() API. Signed-off-by: Tzvetomir Stoyanov Cc: Andrew Morton Cc: Jiri Olsa Cc: Namhyung Kim Link: http://lkml.kernel.org/r/20181201040852.216292134@goodmis.org Signed-off-by: Steven Rostedt (VMware) Signed-off-by: Arnaldo Carvalho de Melo --- tools/lib/traceevent/event-parse.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c index 156e513074b2..44b80471b024 100644 --- a/tools/lib/traceevent/event-parse.c +++ b/tools/lib/traceevent/event-parse.c @@ -6762,8 +6762,10 @@ struct tep_handle *tep_alloc(void) { struct tep_handle *pevent = calloc(1, sizeof(*pevent)); - if (pevent) + if (pevent) { pevent->ref_count = 1; + pevent->host_bigendian = tep_host_bigendian(); + } return pevent; } From 2e4318a287bdf815140462257ab8697f5289a12f Mon Sep 17 00:00:00 2001 From: Tzvetomir Stoyanov Date: Fri, 30 Nov 2018 23:08:09 -0500 Subject: [PATCH 07/16] tools lib traceevent: Rename struct cmdline to struct tep_cmdline In order to make libtraceevent a proper library, variables, data structures and functions should have a unique prefix to prevent name space conflicts. That prefix will be "tep_". This patch renames 'struct cmdline' to 'struct tep_cmdline'. Signed-off-by: Tzvetomir Stoyanov Cc: Andrew Morton Cc: Jiri Olsa Cc: Namhyung Kim Link: http://lkml.kernel.org/r/20181201040852.358871851@goodmis.org Signed-off-by: Steven Rostedt (VMware) Signed-off-by: Arnaldo Carvalho de Melo --- tools/lib/traceevent/event-parse-local.h | 4 +-- tools/lib/traceevent/event-parse.c | 36 ++++++++++++------------ tools/lib/traceevent/event-parse.h | 8 +++--- 3 files changed, 24 insertions(+), 24 deletions(-) diff --git a/tools/lib/traceevent/event-parse-local.h b/tools/lib/traceevent/event-parse-local.h index 9a092dd4a86d..35833ee32d6c 100644 --- a/tools/lib/traceevent/event-parse-local.h +++ b/tools/lib/traceevent/event-parse-local.h @@ -7,7 +7,7 @@ #ifndef _PARSE_EVENTS_INT_H #define _PARSE_EVENTS_INT_H -struct cmdline; +struct tep_cmdline; struct cmdline_list; struct func_map; struct func_list; @@ -36,7 +36,7 @@ struct tep_handle { int long_size; int page_size; - struct cmdline *cmdlines; + struct tep_cmdline *cmdlines; struct cmdline_list *cmdlist; int cmdline_count; diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c index 44b80471b024..a850342baf86 100644 --- a/tools/lib/traceevent/event-parse.c +++ b/tools/lib/traceevent/event-parse.c @@ -124,15 +124,15 @@ struct tep_print_arg *alloc_arg(void) return calloc(1, sizeof(struct tep_print_arg)); } -struct cmdline { +struct tep_cmdline { char *comm; int pid; }; static int cmdline_cmp(const void *a, const void *b) { - const struct cmdline *ca = a; - const struct cmdline *cb = b; + const struct tep_cmdline *ca = a; + const struct tep_cmdline *cb = b; if (ca->pid < cb->pid) return -1; @@ -152,7 +152,7 @@ static int cmdline_init(struct tep_handle *pevent) { struct cmdline_list *cmdlist = pevent->cmdlist; struct cmdline_list *item; - struct cmdline *cmdlines; + struct tep_cmdline *cmdlines; int i; cmdlines = malloc(sizeof(*cmdlines) * pevent->cmdline_count); @@ -179,8 +179,8 @@ static int cmdline_init(struct tep_handle *pevent) static const char *find_cmdline(struct tep_handle *pevent, int pid) { - const struct cmdline *comm; - struct cmdline key; + const struct tep_cmdline *comm; + struct tep_cmdline key; if (!pid) return ""; @@ -208,8 +208,8 @@ static const char *find_cmdline(struct tep_handle *pevent, int pid) */ int tep_pid_is_registered(struct tep_handle *pevent, int pid) { - const struct cmdline *comm; - struct cmdline key; + const struct tep_cmdline *comm; + struct tep_cmdline key; if (!pid) return 1; @@ -235,9 +235,9 @@ int tep_pid_is_registered(struct tep_handle *pevent, int pid) static int add_new_comm(struct tep_handle *pevent, const char *comm, int pid, bool override) { - struct cmdline *cmdlines = pevent->cmdlines; - struct cmdline *cmdline; - struct cmdline key; + struct tep_cmdline *cmdlines = pevent->cmdlines; + struct tep_cmdline *cmdline; + struct tep_cmdline key; char *new_comm; if (!pid) @@ -5331,8 +5331,8 @@ const char *tep_data_comm_from_pid(struct tep_handle *pevent, int pid) return comm; } -static struct cmdline * -pid_from_cmdlist(struct tep_handle *pevent, const char *comm, struct cmdline *next) +static struct tep_cmdline * +pid_from_cmdlist(struct tep_handle *pevent, const char *comm, struct tep_cmdline *next) { struct cmdline_list *cmdlist = (struct cmdline_list *)next; @@ -5344,7 +5344,7 @@ pid_from_cmdlist(struct tep_handle *pevent, const char *comm, struct cmdline *ne while (cmdlist && strcmp(cmdlist->comm, comm) != 0) cmdlist = cmdlist->next; - return (struct cmdline *)cmdlist; + return (struct tep_cmdline *)cmdlist; } /** @@ -5360,10 +5360,10 @@ pid_from_cmdlist(struct tep_handle *pevent, const char *comm, struct cmdline *ne * next pid. * Also, it does a linear search, so it may be slow. */ -struct cmdline *tep_data_pid_from_comm(struct tep_handle *pevent, const char *comm, - struct cmdline *next) +struct tep_cmdline *tep_data_pid_from_comm(struct tep_handle *pevent, const char *comm, + struct tep_cmdline *next) { - struct cmdline *cmdline; + struct tep_cmdline *cmdline; /* * If the cmdlines have not been converted yet, then use @@ -5402,7 +5402,7 @@ struct cmdline *tep_data_pid_from_comm(struct tep_handle *pevent, const char *co * Returns the pid for a give cmdline. If @cmdline is NULL, then * -1 is returned. */ -int tep_cmdline_pid(struct tep_handle *pevent, struct cmdline *cmdline) +int tep_cmdline_pid(struct tep_handle *pevent, struct tep_cmdline *cmdline) { struct cmdline_list *cmdlist = (struct cmdline_list *)cmdline; diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h index e6f4249910e6..77a4a1dd4b4d 100644 --- a/tools/lib/traceevent/event-parse.h +++ b/tools/lib/traceevent/event-parse.h @@ -526,10 +526,10 @@ int tep_data_pid(struct tep_handle *pevent, struct tep_record *rec); int tep_data_preempt_count(struct tep_handle *pevent, struct tep_record *rec); int tep_data_flags(struct tep_handle *pevent, struct tep_record *rec); const char *tep_data_comm_from_pid(struct tep_handle *pevent, int pid); -struct cmdline; -struct cmdline *tep_data_pid_from_comm(struct tep_handle *pevent, const char *comm, - struct cmdline *next); -int tep_cmdline_pid(struct tep_handle *pevent, struct cmdline *cmdline); +struct tep_cmdline; +struct tep_cmdline *tep_data_pid_from_comm(struct tep_handle *pevent, const char *comm, + struct tep_cmdline *next); +int tep_cmdline_pid(struct tep_handle *pevent, struct tep_cmdline *cmdline); void tep_print_field(struct trace_seq *s, void *data, struct tep_format_field *field); From 6d2d6fd7e3ee0daf0d8308741792b3ec41aafd0c Mon Sep 17 00:00:00 2001 From: Tzvetomir Stoyanov Date: Fri, 30 Nov 2018 23:08:10 -0500 Subject: [PATCH 08/16] tools lib traceevent: Changed return logic of trace_seq_printf() and trace_seq_vprintf() APIs In order to make libtraceevent into a proper library, its API should be straightforward. The trace_seq_printf() and trace_seq_vprintf() APIs have inconsistent returned values with the other trace_seq_* APIs. This path changes the return logic of trace_seq_printf() and trace_seq_vprintf() to return the number of printed characters, as the other trace_seq_* related APIs. Signed-off-by: Tzvetomir Stoyanov Cc: Andrew Morton Cc: Jiri Olsa Cc: Namhyung Kim Link: http://lkml.kernel.org/r/20181201040852.485792891@goodmis.org Signed-off-by: Steven Rostedt (VMware) Signed-off-by: Arnaldo Carvalho de Melo --- tools/lib/traceevent/trace-seq.c | 17 ++++++++++++----- 1 file changed, 12 insertions(+), 5 deletions(-) diff --git a/tools/lib/traceevent/trace-seq.c b/tools/lib/traceevent/trace-seq.c index 8ff1d55954d1..8d5ecd2bf877 100644 --- a/tools/lib/traceevent/trace-seq.c +++ b/tools/lib/traceevent/trace-seq.c @@ -100,7 +100,8 @@ static void expand_buffer(struct trace_seq *s) * @fmt: printf format string * * It returns 0 if the trace oversizes the buffer's free - * space, 1 otherwise. + * space, the number of characters printed, or a negative + * value in case of an error. * * The tracer may use either sequence operations or its own * copy to user routines. To simplify formating of a trace @@ -129,9 +130,10 @@ trace_seq_printf(struct trace_seq *s, const char *fmt, ...) goto try_again; } - s->len += ret; + if (ret > 0) + s->len += ret; - return 1; + return ret; } /** @@ -139,6 +141,10 @@ trace_seq_printf(struct trace_seq *s, const char *fmt, ...) * @s: trace sequence descriptor * @fmt: printf format string * + * It returns 0 if the trace oversizes the buffer's free + * space, the number of characters printed, or a negative + * value in case of an error. + * * * The tracer may use either sequence operations or its own * copy to user routines. To simplify formating of a trace * trace_seq_printf is used to store strings into a special @@ -163,9 +169,10 @@ trace_seq_vprintf(struct trace_seq *s, const char *fmt, va_list args) goto try_again; } - s->len += ret; + if (ret > 0) + s->len += ret; - return len; + return ret; } /** From f87ce7c43f36d4abff91b19edadd23939f99ff98 Mon Sep 17 00:00:00 2001 From: Tzvetomir Stoyanov Date: Fri, 30 Nov 2018 23:08:11 -0500 Subject: [PATCH 09/16] tools lib traceevent: Changed return logic of tep_register_event_handler() API In order to make libtraceevent into a proper library, its API should be straightforward. The tep_register_event_handler() functions returns -1 in case it successfully registers the new event handler. Such return code is used by the other library APIs in case of an error. To unify the return logic of tep_register_event_handler() with the other APIs, this patch introduces enum tep_reg_handler, which is used by this function as return value, to handle all possible successful return cases. Signed-off-by: Tzvetomir Stoyanov Cc: Andrew Morton Cc: Jiri Olsa Cc: Namhyung Kim Link: http://lkml.kernel.org/r/20181201040852.628034497@goodmis.org Signed-off-by: Steven Rostedt (VMware) Signed-off-by: Arnaldo Carvalho de Melo --- tools/lib/traceevent/event-parse.c | 10 ++++++++-- tools/lib/traceevent/event-parse.h | 5 +++++ 2 files changed, 13 insertions(+), 2 deletions(-) diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c index a850342baf86..54d94054eef0 100644 --- a/tools/lib/traceevent/event-parse.c +++ b/tools/lib/traceevent/event-parse.c @@ -6632,6 +6632,12 @@ static struct tep_event *search_event(struct tep_handle *pevent, int id, * * If @id is >= 0, then it is used to find the event. * else @sys_name and @event_name are used. + * + * Returns: + * TEP_REGISTER_SUCCESS_OVERWRITE if an existing handler is overwritten + * TEP_REGISTER_SUCCESS if a new handler is registered successfully + * negative TEP_ERRNO_... in case of an error + * */ int tep_register_event_handler(struct tep_handle *pevent, int id, const char *sys_name, const char *event_name, @@ -6649,7 +6655,7 @@ int tep_register_event_handler(struct tep_handle *pevent, int id, event->handler = func; event->context = context; - return 0; + return TEP_REGISTER_SUCCESS_OVERWRITE; not_found: /* Save for later use. */ @@ -6679,7 +6685,7 @@ int tep_register_event_handler(struct tep_handle *pevent, int id, pevent->handlers = handle; handle->context = context; - return -1; + return TEP_REGISTER_SUCCESS; } static int handle_matches(struct event_handler *handler, int id, diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h index 77a4a1dd4b4d..ac377ae99008 100644 --- a/tools/lib/traceevent/event-parse.h +++ b/tools/lib/traceevent/event-parse.h @@ -485,6 +485,11 @@ int tep_print_func_field(struct trace_seq *s, const char *fmt, struct tep_event *event, const char *name, struct tep_record *record, int err); +enum tep_reg_handler { + TEP_REGISTER_SUCCESS = 0, + TEP_REGISTER_SUCCESS_OVERWRITE, +}; + int tep_register_event_handler(struct tep_handle *pevent, int id, const char *sys_name, const char *event_name, tep_event_handler_func func, void *context); From 4104e604277016b3e6a7d120368054f9d2716953 Mon Sep 17 00:00:00 2001 From: Tzvetomir Stoyanov Date: Fri, 30 Nov 2018 23:08:12 -0500 Subject: [PATCH 10/16] tools lib traceevent: Rename tep_is_file_bigendian() to tep_file_bigendian() In order to make libtraceevent into a proper library, its API should be straightforward. After a discussion with Steven Rostedt, we decided to rename a few APIs, to have more intuitive names. This patch renames tep_is_file_bigendian() to tep_file_bigendian(). Signed-off-by: Tzvetomir Stoyanov Cc: Andrew Morton Cc: Jiri Olsa Cc: Namhyung Kim Link: http://lkml.kernel.org/r/20181201040852.767549746@goodmis.org Signed-off-by: Steven Rostedt (VMware) Signed-off-by: Arnaldo Carvalho de Melo --- tools/lib/traceevent/event-parse-api.c | 4 ++-- tools/lib/traceevent/event-parse.h | 2 +- tools/lib/traceevent/plugin_kvm.c | 2 +- 3 files changed, 4 insertions(+), 4 deletions(-) diff --git a/tools/lib/traceevent/event-parse-api.c b/tools/lib/traceevent/event-parse-api.c index 8b31c0e00ba3..d463761a58f4 100644 --- a/tools/lib/traceevent/event-parse-api.c +++ b/tools/lib/traceevent/event-parse-api.c @@ -194,13 +194,13 @@ void tep_set_page_size(struct tep_handle *pevent, int _page_size) } /** - * tep_is_file_bigendian - get if the file is in big endian order + * tep_file_bigendian - get if the file is in big endian order * @pevent: a handle to the tep_handle * * This returns if the file is in big endian order * If @pevent is NULL, 0 is returned. */ -int tep_is_file_bigendian(struct tep_handle *pevent) +int tep_file_bigendian(struct tep_handle *pevent) { if(pevent) return pevent->file_bigendian; diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h index ac377ae99008..bd1bd9a27839 100644 --- a/tools/lib/traceevent/event-parse.h +++ b/tools/lib/traceevent/event-parse.h @@ -559,7 +559,7 @@ int tep_get_long_size(struct tep_handle *pevent); void tep_set_long_size(struct tep_handle *pevent, int long_size); int tep_get_page_size(struct tep_handle *pevent); void tep_set_page_size(struct tep_handle *pevent, int _page_size); -int tep_is_file_bigendian(struct tep_handle *pevent); +int tep_file_bigendian(struct tep_handle *pevent); void tep_set_file_bigendian(struct tep_handle *pevent, enum tep_endian endian); int tep_is_host_bigendian(struct tep_handle *pevent); void tep_set_host_bigendian(struct tep_handle *pevent, enum tep_endian endian); diff --git a/tools/lib/traceevent/plugin_kvm.c b/tools/lib/traceevent/plugin_kvm.c index 754050eea467..64b9c25a1fd3 100644 --- a/tools/lib/traceevent/plugin_kvm.c +++ b/tools/lib/traceevent/plugin_kvm.c @@ -389,7 +389,7 @@ static int kvm_mmu_print_role(struct trace_seq *s, struct tep_record *record, * We can only use the structure if file is of the same * endianness. */ - if (tep_is_file_bigendian(event->pevent) == + if (tep_file_bigendian(event->pevent) == tep_is_host_bigendian(event->pevent)) { trace_seq_printf(s, "%u q%u%s %s%s %spae %snxe %swp%s%s%s", From 9231967e2f515fce9e19687c0c40dfda416b3512 Mon Sep 17 00:00:00 2001 From: Tzvetomir Stoyanov Date: Fri, 30 Nov 2018 23:08:13 -0500 Subject: [PATCH 11/16] tools lib traceevent: Remove tep_data_event_from_type() API In order to make libtraceevent into a proper library, its API should be straightforward. After discussion with Steven Rostedt, we decided to remove the tep_data_event_from_type() API and to replace it with tep_find_event(), as it does the same. Signed-off-by: Tzvetomir Stoyanov Cc: Andrew Morton Cc: Jiri Olsa Cc: Namhyung Kim Link: http://lkml.kernel.org/r/20181201040852.913841066@goodmis.org Signed-off-by: Steven Rostedt (VMware) Signed-off-by: Arnaldo Carvalho de Melo --- tools/lib/traceevent/event-parse.c | 12 ------------ tools/lib/traceevent/event-parse.h | 1 - 2 files changed, 13 deletions(-) diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c index 54d94054eef0..abd4fa5d3088 100644 --- a/tools/lib/traceevent/event-parse.c +++ b/tools/lib/traceevent/event-parse.c @@ -5265,18 +5265,6 @@ int tep_data_type(struct tep_handle *pevent, struct tep_record *rec) return trace_parse_common_type(pevent, rec->data); } -/** - * tep_data_event_from_type - find the event by a given type - * @pevent: a handle to the pevent - * @type: the type of the event. - * - * This returns the event form a given @type; - */ -struct tep_event *tep_data_event_from_type(struct tep_handle *pevent, int type) -{ - return tep_find_event(pevent, type); -} - /** * tep_data_pid - parse the PID from record * @pevent: a handle to the pevent diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h index bd1bd9a27839..aec48f2aea8a 100644 --- a/tools/lib/traceevent/event-parse.h +++ b/tools/lib/traceevent/event-parse.h @@ -526,7 +526,6 @@ tep_find_event_by_record(struct tep_handle *pevent, struct tep_record *record); void tep_data_lat_fmt(struct tep_handle *pevent, struct trace_seq *s, struct tep_record *record); int tep_data_type(struct tep_handle *pevent, struct tep_record *rec); -struct tep_event *tep_data_event_from_type(struct tep_handle *pevent, int type); int tep_data_pid(struct tep_handle *pevent, struct tep_record *rec); int tep_data_preempt_count(struct tep_handle *pevent, struct tep_record *rec); int tep_data_flags(struct tep_handle *pevent, struct tep_record *rec); From f2e14cd2c93699aa0aeaa8240457ab359f1258ff Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 8 Jan 2019 10:56:59 -0300 Subject: [PATCH 12/16] perf top: Lift restriction on using callchains without "sym" in --sort This restriction is not present in 'perf report' and since 'perf top' uses the same hists browser, remove it from it as well. With this we create per event buckets with callchain trees, so that # perf top --sort dso -g --no-children Bucketizes samples by DSO and below it shows the callchains leading to functions in this DSO. Try also: # perf top -e sched:*switch -g --no-children To see the callchains leading to sched switches, pressing 'E' to expand all one can quickly see the most common scheduler switches and what leads to them, for instance, calls to IO, futexes, etc. Acked-by: Namhyung Kim Cc: Adrian Hunter Cc: Jiri Olsa Link: https://lkml.kernel.org/r/20190107140854.GA28965@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-top.c | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index fe3ecfb2e64b..f64e312db787 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -1028,12 +1028,7 @@ static int perf_top__start_counters(struct perf_top *top) static int callchain_param__setup_sample_type(struct callchain_param *callchain) { - if (!perf_hpp_list.sym) { - if (callchain->enabled) { - ui__error("Selected -g but \"sym\" not present in --sort/-s."); - return -EINVAL; - } - } else if (callchain->mode != CHAIN_NONE) { + if (callchain->mode != CHAIN_NONE) { if (callchain_register_param(callchain) < 0) { ui__error("Can't register callchain params.\n"); return -EINVAL; From 250bfc87ddc427fa001bbc8bc1468ce5fc06645b Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 8 Jan 2019 13:42:37 -0300 Subject: [PATCH 13/16] tools include uapi: Grab a copy of linux/mount.h MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit We were using a copy of uapi/linux/fs.h to create the mount syscall 'flags' string table to use in 'perf trace', to convert from the number obtained via the raw_syscalls:sys_enter into a string, using tools/perf/trace/beauty/mount_flags.sh, but in e262e32d6bde ("vfs: Suppress MS_* flag defs within the kernel unless explicitly enabled") those defines got moved to linux/mount.h, so grab a copy of mount.h too. Keep the uapi/linux/fs.h as we'll use it for the SEEK_ constants. Cc: Adrian Hunter Cc: David Howells Cc: Jiri Olsa Cc: Luis Cláudio Gonçalves Cc: Namhyung Kim Cc: Wang Nan Link: https://lkml.kernel.org/n/tip-i2ricmpwpdrpukfq3298jr1z@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/uapi/linux/mount.h | 58 ++++++++++++++++++++++++++++++++ tools/perf/check-headers.sh | 1 + 2 files changed, 59 insertions(+) create mode 100644 tools/include/uapi/linux/mount.h diff --git a/tools/include/uapi/linux/mount.h b/tools/include/uapi/linux/mount.h new file mode 100644 index 000000000000..3f9ec42510b0 --- /dev/null +++ b/tools/include/uapi/linux/mount.h @@ -0,0 +1,58 @@ +#ifndef _UAPI_LINUX_MOUNT_H +#define _UAPI_LINUX_MOUNT_H + +/* + * These are the fs-independent mount-flags: up to 32 flags are supported + * + * Usage of these is restricted within the kernel to core mount(2) code and + * callers of sys_mount() only. Filesystems should be using the SB_* + * equivalent instead. + */ +#define MS_RDONLY 1 /* Mount read-only */ +#define MS_NOSUID 2 /* Ignore suid and sgid bits */ +#define MS_NODEV 4 /* Disallow access to device special files */ +#define MS_NOEXEC 8 /* Disallow program execution */ +#define MS_SYNCHRONOUS 16 /* Writes are synced at once */ +#define MS_REMOUNT 32 /* Alter flags of a mounted FS */ +#define MS_MANDLOCK 64 /* Allow mandatory locks on an FS */ +#define MS_DIRSYNC 128 /* Directory modifications are synchronous */ +#define MS_NOATIME 1024 /* Do not update access times. */ +#define MS_NODIRATIME 2048 /* Do not update directory access times */ +#define MS_BIND 4096 +#define MS_MOVE 8192 +#define MS_REC 16384 +#define MS_VERBOSE 32768 /* War is peace. Verbosity is silence. + MS_VERBOSE is deprecated. */ +#define MS_SILENT 32768 +#define MS_POSIXACL (1<<16) /* VFS does not apply the umask */ +#define MS_UNBINDABLE (1<<17) /* change to unbindable */ +#define MS_PRIVATE (1<<18) /* change to private */ +#define MS_SLAVE (1<<19) /* change to slave */ +#define MS_SHARED (1<<20) /* change to shared */ +#define MS_RELATIME (1<<21) /* Update atime relative to mtime/ctime. */ +#define MS_KERNMOUNT (1<<22) /* this is a kern_mount call */ +#define MS_I_VERSION (1<<23) /* Update inode I_version field */ +#define MS_STRICTATIME (1<<24) /* Always perform atime updates */ +#define MS_LAZYTIME (1<<25) /* Update the on-disk [acm]times lazily */ + +/* These sb flags are internal to the kernel */ +#define MS_SUBMOUNT (1<<26) +#define MS_NOREMOTELOCK (1<<27) +#define MS_NOSEC (1<<28) +#define MS_BORN (1<<29) +#define MS_ACTIVE (1<<30) +#define MS_NOUSER (1<<31) + +/* + * Superblock flags that can be altered by MS_REMOUNT + */ +#define MS_RMT_MASK (MS_RDONLY|MS_SYNCHRONOUS|MS_MANDLOCK|MS_I_VERSION|\ + MS_LAZYTIME) + +/* + * Old magic mount flag and mask + */ +#define MS_MGC_VAL 0xC0ED0000 +#define MS_MGC_MSK 0xffff0000 + +#endif /* _UAPI_LINUX_MOUNT_H */ diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh index 6cb98f8570a2..b51e952ab35f 100755 --- a/tools/perf/check-headers.sh +++ b/tools/perf/check-headers.sh @@ -10,6 +10,7 @@ include/uapi/linux/fs.h include/uapi/linux/kcmp.h include/uapi/linux/kvm.h include/uapi/linux/in.h +include/uapi/linux/mount.h include/uapi/linux/perf_event.h include/uapi/linux/prctl.h include/uapi/linux/sched.h From 1c23397d2a6a077ab32f01c01406c2fe61b7b3a4 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 8 Jan 2019 13:46:43 -0300 Subject: [PATCH 14/16] perf beauty: Switch from using uapi/linux/fs.h to uapi/linux/mount.h MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit As now we'll update our fs.h copy and what tools/perf/trace/beauty/mount_flags.sh needs just got moved to mount.h, use that instead. Cc: Adrian Hunter Cc: David Howells Cc: Jiri Olsa Cc: Luis Cláudio Gonçalves Cc: Namhyung Kim Cc: Wang Nan Link: https://lkml.kernel.org/n/tip-ls19h376xukeouxrw9dswkcn@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/trace/beauty/mount_flags.sh | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/perf/trace/beauty/mount_flags.sh b/tools/perf/trace/beauty/mount_flags.sh index 45547573a1db..847850b2ef6c 100755 --- a/tools/perf/trace/beauty/mount_flags.sh +++ b/tools/perf/trace/beauty/mount_flags.sh @@ -5,11 +5,11 @@ printf "static const char *mount_flags[] = {\n" regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+MS_([[:alnum:]_]+)[[:space:]]+([[:digit:]]+)[[:space:]]*.*' -egrep $regex ${header_dir}/fs.h | egrep -v '(MSK|VERBOSE|MGC_VAL)\>' | \ +egrep $regex ${header_dir}/mount.h | egrep -v '(MSK|VERBOSE|MGC_VAL)\>' | \ sed -r "s/$regex/\2 \2 \1/g" | sort -n | \ xargs printf "\t[%s ? (ilog2(%s) + 1) : 0] = \"%s\",\n" regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+MS_([[:alnum:]_]+)[[:space:]]+\(1<<([[:digit:]]+)\)[[:space:]]*.*' -egrep $regex ${header_dir}/fs.h | \ +egrep $regex ${header_dir}/mount.h | \ sed -r "s/$regex/\2 \1/g" | \ xargs printf "\t[%s + 1] = \"%s\",\n" printf "};\n" From fdc42ca190c7d8976f4f9240752f0bd008270b72 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 8 Jan 2019 13:48:14 -0300 Subject: [PATCH 15/16] tools include uapi: Sync linux/fs.h copy with the kernel sources MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit To get the changes in: e262e32d6bde ("vfs: Suppress MS_* flag defs within the kernel unless explicitly enabled") That made the mount flags string table generator to switch to using mount.h instead. This silences the following perf build warning: Warning: Kernel ABI header at 'tools/include/uapi/linux/fs.h' differs from latest version at 'include/uapi/linux/fs.h' diff -u tools/include/uapi/linux/fs.h include/uapi/linux/fs.h Cc: Adrian Hunter Cc: David Howells Cc: Jiri Olsa Cc: Luis Cláudio Gonçalves Cc: Namhyung Kim Cc: Wang Nan Link: https://lkml.kernel.org/n/tip-mosz81pa6iwxko4p2owbm3ss@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/uapi/linux/fs.h | 60 +++++------------------------------ 1 file changed, 8 insertions(+), 52 deletions(-) diff --git a/tools/include/uapi/linux/fs.h b/tools/include/uapi/linux/fs.h index a441ea1bfe6d..121e82ce296b 100644 --- a/tools/include/uapi/linux/fs.h +++ b/tools/include/uapi/linux/fs.h @@ -14,6 +14,11 @@ #include #include +/* Use of MS_* flags within the kernel is restricted to core mount(2) code. */ +#if !defined(__KERNEL__) +#include +#endif + /* * It's silly to have NR_OPEN bigger than NR_FILE, but you can change * the file limit at runtime and only root can increase the per-process @@ -101,57 +106,6 @@ struct inodes_stat_t { #define NR_FILE 8192 /* this can well be larger on a larger system */ - -/* - * These are the fs-independent mount-flags: up to 32 flags are supported - */ -#define MS_RDONLY 1 /* Mount read-only */ -#define MS_NOSUID 2 /* Ignore suid and sgid bits */ -#define MS_NODEV 4 /* Disallow access to device special files */ -#define MS_NOEXEC 8 /* Disallow program execution */ -#define MS_SYNCHRONOUS 16 /* Writes are synced at once */ -#define MS_REMOUNT 32 /* Alter flags of a mounted FS */ -#define MS_MANDLOCK 64 /* Allow mandatory locks on an FS */ -#define MS_DIRSYNC 128 /* Directory modifications are synchronous */ -#define MS_NOATIME 1024 /* Do not update access times. */ -#define MS_NODIRATIME 2048 /* Do not update directory access times */ -#define MS_BIND 4096 -#define MS_MOVE 8192 -#define MS_REC 16384 -#define MS_VERBOSE 32768 /* War is peace. Verbosity is silence. - MS_VERBOSE is deprecated. */ -#define MS_SILENT 32768 -#define MS_POSIXACL (1<<16) /* VFS does not apply the umask */ -#define MS_UNBINDABLE (1<<17) /* change to unbindable */ -#define MS_PRIVATE (1<<18) /* change to private */ -#define MS_SLAVE (1<<19) /* change to slave */ -#define MS_SHARED (1<<20) /* change to shared */ -#define MS_RELATIME (1<<21) /* Update atime relative to mtime/ctime. */ -#define MS_KERNMOUNT (1<<22) /* this is a kern_mount call */ -#define MS_I_VERSION (1<<23) /* Update inode I_version field */ -#define MS_STRICTATIME (1<<24) /* Always perform atime updates */ -#define MS_LAZYTIME (1<<25) /* Update the on-disk [acm]times lazily */ - -/* These sb flags are internal to the kernel */ -#define MS_SUBMOUNT (1<<26) -#define MS_NOREMOTELOCK (1<<27) -#define MS_NOSEC (1<<28) -#define MS_BORN (1<<29) -#define MS_ACTIVE (1<<30) -#define MS_NOUSER (1<<31) - -/* - * Superblock flags that can be altered by MS_REMOUNT - */ -#define MS_RMT_MASK (MS_RDONLY|MS_SYNCHRONOUS|MS_MANDLOCK|MS_I_VERSION|\ - MS_LAZYTIME) - -/* - * Old magic mount flag and mask - */ -#define MS_MGC_VAL 0xC0ED0000 -#define MS_MGC_MSK 0xffff0000 - /* * Structure for FS_IOC_FSGETXATTR[A] and FS_IOC_FSSETXATTR. */ @@ -269,7 +223,8 @@ struct fsxattr { #define FS_POLICY_FLAGS_PAD_16 0x02 #define FS_POLICY_FLAGS_PAD_32 0x03 #define FS_POLICY_FLAGS_PAD_MASK 0x03 -#define FS_POLICY_FLAGS_VALID 0x03 +#define FS_POLICY_FLAG_DIRECT_KEY 0x04 /* use master key directly */ +#define FS_POLICY_FLAGS_VALID 0x07 /* Encryption algorithms */ #define FS_ENCRYPTION_MODE_INVALID 0 @@ -281,6 +236,7 @@ struct fsxattr { #define FS_ENCRYPTION_MODE_AES_128_CTS 6 #define FS_ENCRYPTION_MODE_SPECK128_256_XTS 7 /* Removed, do not use. */ #define FS_ENCRYPTION_MODE_SPECK128_256_CTS 8 /* Removed, do not use. */ +#define FS_ENCRYPTION_MODE_ADIANTUM 9 struct fscrypt_policy { __u8 version; From ee412f14693a3fe2645b3528603dfd37dd05118a Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 8 Jan 2019 13:53:23 -0300 Subject: [PATCH 16/16] tools include uapi: Sync linux/vhost.h with the kernel sources MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit To get the changes in: 4b86713236e4 ("vhost: split structs into a separate header file") Silencing this perf build warning: Warning: Kernel ABI header at 'tools/include/uapi/linux/vhost.h' differs from latest version at 'include/uapi/linux/vhost.h' diff -u tools/include/uapi/linux/vhost.h include/uapi/linux/vhost.h Those didn't touch things used in tools, i.e. the following continues working: $ tools/perf/trace/beauty/vhost_virtio_ioctl.sh static const char *vhost_virtio_ioctl_cmds[] = { [0x00] = "SET_FEATURES", [0x01] = "SET_OWNER", [0x02] = "RESET_OWNER", [0x03] = "SET_MEM_TABLE", [0x04] = "SET_LOG_BASE", [0x07] = "SET_LOG_FD", [0x10] = "SET_VRING_NUM", [0x11] = "SET_VRING_ADDR", [0x12] = "SET_VRING_BASE", [0x13] = "SET_VRING_ENDIAN", [0x14] = "GET_VRING_ENDIAN", [0x20] = "SET_VRING_KICK", [0x21] = "SET_VRING_CALL", [0x22] = "SET_VRING_ERR", [0x23] = "SET_VRING_BUSYLOOP_TIMEOUT", [0x24] = "GET_VRING_BUSYLOOP_TIMEOUT", [0x25] = "SET_BACKEND_FEATURES", [0x30] = "NET_SET_BACKEND", [0x40] = "SCSI_SET_ENDPOINT", [0x41] = "SCSI_CLEAR_ENDPOINT", [0x42] = "SCSI_GET_ABI_VERSION", [0x43] = "SCSI_SET_EVENTS_MISSED", [0x44] = "SCSI_GET_EVENTS_MISSED", [0x60] = "VSOCK_SET_GUEST_CID", [0x61] = "VSOCK_SET_RUNNING", }; static const char *vhost_virtio_ioctl_read_cmds[] = { [0x00] = "GET_FEATURES", [0x12] = "GET_VRING_BASE", [0x26] = "GET_BACKEND_FEATURES", }; $ At some point in the eBPFication of perf, using something like: # perf trace -e ioctl(cmd=VHOST_VRING*) Will setup a BPF filter right at the raw_syscalls:sys_enter tracepoint, i.e. filtering at the origin. Cc: Adrian Hunter Cc: Jiri Olsa Cc: Luis Cláudio Gonçalves Cc: Michael S. Tsirkin Cc: Namhyung Kim Cc: Paolo Bonzini Cc: Wang Nan Link: https://lkml.kernel.org/n/tip-g28usrt7l59lwq3wuh8vzbig@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/uapi/linux/vhost.h | 113 +------------------------------ 1 file changed, 2 insertions(+), 111 deletions(-) diff --git a/tools/include/uapi/linux/vhost.h b/tools/include/uapi/linux/vhost.h index 84c3de89696a..40d028eed645 100644 --- a/tools/include/uapi/linux/vhost.h +++ b/tools/include/uapi/linux/vhost.h @@ -11,94 +11,9 @@ * device configuration. */ +#include #include -#include #include -#include -#include - -struct vhost_vring_state { - unsigned int index; - unsigned int num; -}; - -struct vhost_vring_file { - unsigned int index; - int fd; /* Pass -1 to unbind from file. */ - -}; - -struct vhost_vring_addr { - unsigned int index; - /* Option flags. */ - unsigned int flags; - /* Flag values: */ - /* Whether log address is valid. If set enables logging. */ -#define VHOST_VRING_F_LOG 0 - - /* Start of array of descriptors (virtually contiguous) */ - __u64 desc_user_addr; - /* Used structure address. Must be 32 bit aligned */ - __u64 used_user_addr; - /* Available structure address. Must be 16 bit aligned */ - __u64 avail_user_addr; - /* Logging support. */ - /* Log writes to used structure, at offset calculated from specified - * address. Address must be 32 bit aligned. */ - __u64 log_guest_addr; -}; - -/* no alignment requirement */ -struct vhost_iotlb_msg { - __u64 iova; - __u64 size; - __u64 uaddr; -#define VHOST_ACCESS_RO 0x1 -#define VHOST_ACCESS_WO 0x2 -#define VHOST_ACCESS_RW 0x3 - __u8 perm; -#define VHOST_IOTLB_MISS 1 -#define VHOST_IOTLB_UPDATE 2 -#define VHOST_IOTLB_INVALIDATE 3 -#define VHOST_IOTLB_ACCESS_FAIL 4 - __u8 type; -}; - -#define VHOST_IOTLB_MSG 0x1 -#define VHOST_IOTLB_MSG_V2 0x2 - -struct vhost_msg { - int type; - union { - struct vhost_iotlb_msg iotlb; - __u8 padding[64]; - }; -}; - -struct vhost_msg_v2 { - __u32 type; - __u32 reserved; - union { - struct vhost_iotlb_msg iotlb; - __u8 padding[64]; - }; -}; - -struct vhost_memory_region { - __u64 guest_phys_addr; - __u64 memory_size; /* bytes */ - __u64 userspace_addr; - __u64 flags_padding; /* No flags are currently specified. */ -}; - -/* All region addresses and sizes must be 4K aligned. */ -#define VHOST_PAGE_SIZE 0x1000 - -struct vhost_memory { - __u32 nregions; - __u32 padding; - struct vhost_memory_region regions[0]; -}; /* ioctls */ @@ -186,31 +101,7 @@ struct vhost_memory { * device. This can be used to stop the ring (e.g. for migration). */ #define VHOST_NET_SET_BACKEND _IOW(VHOST_VIRTIO, 0x30, struct vhost_vring_file) -/* Feature bits */ -/* Log all write descriptors. Can be changed while device is active. */ -#define VHOST_F_LOG_ALL 26 -/* vhost-net should add virtio_net_hdr for RX, and strip for TX packets. */ -#define VHOST_NET_F_VIRTIO_NET_HDR 27 - -/* VHOST_SCSI specific definitions */ - -/* - * Used by QEMU userspace to ensure a consistent vhost-scsi ABI. - * - * ABI Rev 0: July 2012 version starting point for v3.6-rc merge candidate + - * RFC-v2 vhost-scsi userspace. Add GET_ABI_VERSION ioctl usage - * ABI Rev 1: January 2013. Ignore vhost_tpgt filed in struct vhost_scsi_target. - * All the targets under vhost_wwpn can be seen and used by guset. - */ - -#define VHOST_SCSI_ABI_VERSION 1 - -struct vhost_scsi_target { - int abi_version; - char vhost_wwpn[224]; /* TRANSPORT_IQN_LEN */ - unsigned short vhost_tpgt; - unsigned short reserved; -}; +/* VHOST_SCSI specific defines */ #define VHOST_SCSI_SET_ENDPOINT _IOW(VHOST_VIRTIO, 0x40, struct vhost_scsi_target) #define VHOST_SCSI_CLEAR_ENDPOINT _IOW(VHOST_VIRTIO, 0x41, struct vhost_scsi_target)