diff options
Diffstat (limited to 'tools')
| -rw-r--r-- | tools/perf/Documentation/perf-kmem.txt | 8 | ||||
| -rw-r--r-- | tools/perf/builtin-kmem.c | 500 | ||||
| -rw-r--r-- | tools/perf/util/probe-event.c | 60 | ||||
| -rw-r--r-- | tools/perf/util/probe-finder.c | 73 | ||||
| -rw-r--r-- | tools/perf/util/probe-finder.h | 4 | ||||
| -rw-r--r-- | tools/testing/selftests/x86/Makefile | 2 | ||||
| -rw-r--r-- | tools/testing/selftests/x86/run_x86_tests.sh | 2 | ||||
| -rw-r--r-- | tools/testing/selftests/x86/single_step_syscall.c | 181 |
8 files changed, 751 insertions, 79 deletions
diff --git a/tools/perf/Documentation/perf-kmem.txt b/tools/perf/Documentation/perf-kmem.txt index 150253cc3c97..23219c65c16f 100644 --- a/tools/perf/Documentation/perf-kmem.txt +++ b/tools/perf/Documentation/perf-kmem.txt @@ -3,7 +3,7 @@ perf-kmem(1) NAME ---- -perf-kmem - Tool to trace/measure kernel memory(slab) properties +perf-kmem - Tool to trace/measure kernel memory properties SYNOPSIS -------- @@ -46,6 +46,12 @@ OPTIONS --raw-ip:: Print raw ip instead of symbol +--slab:: + Analyze SLAB allocator events. + +--page:: + Analyze page allocator events + SEE ALSO -------- linkperf:perf-record[1] diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c index 4ebf65c79434..63ea01349b6e 100644 --- a/tools/perf/builtin-kmem.c +++ b/tools/perf/builtin-kmem.c @@ -22,6 +22,11 @@ #include <linux/string.h> #include <locale.h> +static int kmem_slab; +static int kmem_page; + +static long kmem_page_size; + struct alloc_stat; typedef int (*sort_fn_t)(struct alloc_stat *, struct alloc_stat *); @@ -226,6 +231,244 @@ static int perf_evsel__process_free_event(struct perf_evsel *evsel, return 0; } +static u64 total_page_alloc_bytes; +static u64 total_page_free_bytes; +static u64 total_page_nomatch_bytes; +static u64 total_page_fail_bytes; +static unsigned long nr_page_allocs; +static unsigned long nr_page_frees; +static unsigned long nr_page_fails; +static unsigned long nr_page_nomatch; + +static bool use_pfn; + +#define MAX_MIGRATE_TYPES 6 +#define MAX_PAGE_ORDER 11 + +static int order_stats[MAX_PAGE_ORDER][MAX_MIGRATE_TYPES]; + +struct page_stat { + struct rb_node node; + u64 page; + int order; + unsigned gfp_flags; + unsigned migrate_type; + u64 alloc_bytes; + u64 free_bytes; + int nr_alloc; + int nr_free; +}; + +static struct rb_root page_tree; +static struct rb_root page_alloc_tree; +static struct rb_root page_alloc_sorted; + +static struct page_stat *search_page(unsigned long page, bool create) +{ + struct rb_node **node = &page_tree.rb_node; + struct rb_node *parent = NULL; + struct page_stat *data; + + while (*node) { + s64 cmp; + + parent = *node; + data = rb_entry(*node, struct page_stat, node); + + cmp = data->page - page; + if (cmp < 0) + node = &parent->rb_left; + else if (cmp > 0) + node = &parent->rb_right; + else + return data; + } + + if (!create) + return NULL; + + data = zalloc(sizeof(*data)); + if (data != NULL) { + data->page = page; + + rb_link_node(&data->node, parent, node); + rb_insert_color(&data->node, &page_tree); + } + + return data; +} + +static int page_stat_cmp(struct page_stat *a, struct page_stat *b) +{ + if (a->page > b->page) + return -1; + if (a->page < b->page) + return 1; + if (a->order > b->order) + return -1; + if (a->order < b->order) + return 1; + if (a->migrate_type > b->migrate_type) + return -1; + if (a->migrate_type < b->migrate_type) + return 1; + if (a->gfp_flags > b->gfp_flags) + return -1; + if (a->gfp_flags < b->gfp_flags) + return 1; + return 0; +} + +static struct page_stat *search_page_alloc_stat(struct page_stat *stat, bool create) +{ + struct rb_node **node = &page_alloc_tree.rb_node; + struct rb_node *parent = NULL; + struct page_stat *data; + + while (*node) { + s64 cmp; + + parent = *node; + data = rb_entry(*node, struct page_stat, node); + + cmp = page_stat_cmp(data, stat); + if (cmp < 0) + node = &parent->rb_left; + else if (cmp > 0) + node = &parent->rb_right; + else + return data; + } + + if (!create) + return NULL; + + data = zalloc(sizeof(*data)); + if (data != NULL) { + data->page = stat->page; + data->order = stat->order; + data->gfp_flags = stat->gfp_flags; + data->migrate_type = stat->migrate_type; + + rb_link_node(&data->node, parent, node); + rb_insert_color(&data->node, &page_alloc_tree); + } + + return data; +} + +static bool valid_page(u64 pfn_or_page) +{ + if (use_pfn && pfn_or_page == -1UL) + return false; + if (!use_pfn && pfn_or_page == 0) + return false; + return true; +} + +static int perf_evsel__process_page_alloc_event(struct perf_evsel *evsel, + struct perf_sample *sample) +{ + u64 page; + unsigned int order = perf_evsel__intval(evsel, sample, "order"); + unsigned int gfp_flags = perf_evsel__intval(evsel, sample, "gfp_flags"); + unsigned int migrate_type = perf_evsel__intval(evsel, sample, + "migratetype"); + u64 bytes = kmem_page_size << order; + struct page_stat *stat; + struct page_stat this = { + .order = order, + .gfp_flags = gfp_flags, + .migrate_type = migrate_type, + }; + + if (use_pfn) + page = perf_evsel__intval(evsel, sample, "pfn"); + else + page = perf_evsel__intval(evsel, sample, "page"); + + nr_page_allocs++; + total_page_alloc_bytes += bytes; + + if (!valid_page(page)) { + nr_page_fails++; + total_page_fail_bytes += bytes; + + return 0; + } + + /* + * This is to find the current page (with correct gfp flags and + * migrate type) at free event. + */ + stat = search_page(page, true); + if (stat == NULL) + return -ENOMEM; + + stat->order = order; + stat->gfp_flags = gfp_flags; + stat->migrate_type = migrate_type; + + this.page = page; + stat = search_page_alloc_stat(&this, true); + if (stat == NULL) + return -ENOMEM; + + stat->nr_alloc++; + stat->alloc_bytes += bytes; + + order_stats[order][migrate_type]++; + + return 0; +} + +static int perf_evsel__process_page_free_event(struct perf_evsel *evsel, + struct perf_sample *sample) +{ + u64 page; + unsigned int order = perf_evsel__intval(evsel, sample, "order"); + u64 bytes = kmem_page_size << order; + struct page_stat *stat; + struct page_stat this = { + .order = order, + }; + + if (use_pfn) + page = perf_evsel__intval(evsel, sample, "pfn"); + else + page = perf_evsel__intval(evsel, sample, "page"); + + nr_page_frees++; + total_page_free_bytes += bytes; + + stat = search_page(page, false); + if (stat == NULL) { + pr_debug2("missing free at page %"PRIx64" (order: %d)\n", + page, order); + + nr_page_nomatch++; + total_page_nomatch_bytes += bytes; + + return 0; + } + + this.page = page; + this.gfp_flags = stat->gfp_flags; + this.migrate_type = stat->migrate_type; + + rb_erase(&stat->node, &page_tree); + free(stat); + + stat = search_page_alloc_stat(&this, false); + if (stat == NULL) + return -ENOENT; + + stat->nr_free++; + stat->free_bytes += bytes; + + return 0; +} + typedef int (*tracepoint_handler)(struct perf_evsel *evsel, struct perf_sample *sample); @@ -270,8 +513,9 @@ static double fragmentation(unsigned long n_req, unsigned long n_alloc) return 100.0 - (100.0 * n_req / n_alloc); } -static void __print_result(struct rb_root *root, struct perf_session *session, - int n_lines, int is_caller) +static void __print_slab_result(struct rb_root *root, + struct perf_session *session, + int n_lines, int is_caller) { struct rb_node *next; struct machine *machine = &session->machines.host; @@ -323,9 +567,56 @@ static void __print_result(struct rb_root *root, struct perf_session *session, printf("%.105s\n", graph_dotted_line); } -static void print_summary(void) +static const char * const migrate_type_str[] = { + "UNMOVABL", + "RECLAIM", + "MOVABLE", + "RESERVED", + "CMA/ISLT", + "UNKNOWN", +}; + +static void __print_page_result(struct rb_root *root, + struct perf_session *session __maybe_unused, + int n_lines) +{ + struct rb_node *next = rb_first(root); + const char *format; + + printf("\n%.80s\n", graph_dotted_line); + printf(" %-16s | Total alloc (KB) | Hits | Order | Mig.type | GFP flags\n", + use_pfn ? "PFN" : "Page"); + printf("%.80s\n", graph_dotted_line); + + if (use_pfn) + format = " %16llu | %'16llu | %'9d | %5d | %8s | %08lx\n"; + else + format = " %016llx | %'16llu | %'9d | %5d | %8s | %08lx\n"; + + while (next && n_lines--) { + struct page_stat *data; + + data = rb_entry(next, struct page_stat, node); + + printf(format, (unsigned long long)data->page, + (unsigned long long)data->alloc_bytes / 1024, + data->nr_alloc, data->order, + migrate_type_str[data->migrate_type], + (unsigned long)data->gfp_flags); + + next = rb_next(next); + } + + if (n_lines == -1) + printf(" ... | ... | ... | ... | ... | ... \n"); + + printf("%.80s\n", graph_dotted_line); +} + +static void print_slab_summary(void) { - printf("\nSUMMARY\n=======\n"); + printf("\nSUMMARY (SLAB allocator)"); + printf("\n========================\n"); printf("Total bytes requested: %'lu\n", total_requested); printf("Total bytes allocated: %'lu\n", total_allocated); printf("Total bytes wasted on internal fragmentation: %'lu\n", @@ -335,13 +626,73 @@ static void print_summary(void) printf("Cross CPU allocations: %'lu/%'lu\n", nr_cross_allocs, nr_allocs); } -static void print_result(struct perf_session *session) +static void print_page_summary(void) +{ + int o, m; + u64 nr_alloc_freed = nr_page_frees - nr_page_nomatch; + u64 total_alloc_freed_bytes = total_page_free_bytes - total_page_nomatch_bytes; + + printf("\nSUMMARY (page allocator)"); + printf("\n========================\n"); + printf("%-30s: %'16lu [ %'16"PRIu64" KB ]\n", "Total allocation requests", + nr_page_allocs, total_page_alloc_bytes / 1024); + printf("%-30s: %'16lu [ %'16"PRIu64" KB ]\n", "Total free requests", + nr_page_frees, total_page_free_bytes / 1024); + printf("\n"); + + printf("%-30s: %'16lu [ %'16"PRIu64" KB ]\n", "Total alloc+freed requests", + nr_alloc_freed, (total_alloc_freed_bytes) / 1024); + printf("%-30s: %'16lu [ %'16"PRIu64" KB ]\n", "Total alloc-only requests", + nr_page_allocs - nr_alloc_freed, + (total_page_alloc_bytes - total_alloc_freed_bytes) / 1024); + printf("%-30s: %'16lu [ %'16"PRIu64" KB ]\n", "Total free-only requests", + nr_page_nomatch, total_page_nomatch_bytes / 1024); + printf("\n"); + + printf("%-30s: %'16lu [ %'16"PRIu64" KB ]\n", "Total allocation failures", + nr_page_fails, total_page_fail_bytes / 1024); + printf("\n"); + + printf("%5s %12s %12s %12s %12s %12s\n", "Order", "Unmovable", + "Reclaimable", "Movable", "Reserved", "CMA/Isolated"); + printf("%.5s %.12s %.12s %.12s %.12s %.12s\n", graph_dotted_line, + graph_dotted_line, graph_dotted_line, graph_dotted_line, + graph_dotted_line, graph_dotted_line); + + for (o = 0; o < MAX_PAGE_ORDER; o++) { + printf("%5d", o); + for (m = 0; m < MAX_MIGRATE_TYPES - 1; m++) { + if (order_stats[o][m]) + printf(" %'12d", order_stats[o][m]); + else + printf(" %12c", '.'); + } + printf("\n"); + } +} + +static void print_slab_result(struct perf_session *session) { if (caller_flag) - __print_result(&root_caller_sorted, session, caller_lines, 1); + __print_slab_result(&root_caller_sorted, session, caller_lines, 1); + if (alloc_flag) + __print_slab_result(&root_alloc_sorted, session, alloc_lines, 0); + print_slab_summary(); +} + +static void print_page_result(struct perf_session *session) +{ if (alloc_flag) - __print_result(&root_alloc_sorted, session, alloc_lines, 0); - print_summary(); + __print_page_result(&page_alloc_sorted, session, alloc_lines); + print_page_summary(); +} + +static void print_result(struct perf_session *session) +{ + if (kmem_slab) + print_slab_result(session); + if (kmem_page) + print_page_result(session); } struct sort_dimension { @@ -353,8 +704,8 @@ struct sort_dimension { static LIST_HEAD(caller_sort); static LIST_HEAD(alloc_sort); -static void sort_insert(struct rb_root *root, struct alloc_stat *data, - struct list_head *sort_list) +static void sort_slab_insert(struct rb_root *root, struct alloc_stat *data, + struct list_head *sort_list) { struct rb_node **new = &(root->rb_node); struct rb_node *parent = NULL; @@ -383,8 +734,8 @@ static void sort_insert(struct rb_root *root, struct alloc_stat *data, rb_insert_color(&data->node, root); } -static void __sort_result(struct rb_root *root, struct rb_root *root_sorted, - struct list_head *sort_list) +static void __sort_slab_result(struct rb_root *root, struct rb_root *root_sorted, + struct list_head *sort_list) { struct rb_node *node; struct alloc_stat *data; @@ -396,26 +747,79 @@ static void __sort_result(struct rb_root *root, struct rb_root *root_sorted, rb_erase(node, root); data = rb_entry(node, struct alloc_stat, node); - sort_insert(root_sorted, data, sort_list); + sort_slab_insert(root_sorted, data, sort_list); + } +} + +static void sort_page_insert(struct rb_root *root, struct page_stat *data) +{ + struct rb_node **new = &root->rb_node; + struct rb_node *parent = NULL; + + while (*new) { + struct page_stat *this; + int cmp = 0; + + this = rb_entry(*new, struct page_stat, node); + parent = *new; + + /* TODO: support more sort key */ + cmp = data->alloc_bytes - this->alloc_bytes; + + if (cmp > 0) + new = &parent->rb_left; + else + new = &parent->rb_right; + } + + rb_link_node(&data->node, parent, new); + rb_insert_color(&data->node, root); +} + +static void __sort_page_result(struct rb_root *root, struct rb_root *root_sorted) +{ + struct rb_node *node; + struct page_stat *data; + + for (;;) { + node = rb_first(root); + if (!node) + break; + + rb_erase(node, root); + data = rb_entry(node, struct page_stat, node); + sort_page_insert(root_sorted, data); } } static void sort_result(void) { - __sort_result(&root_alloc_stat, &root_alloc_sorted, &alloc_sort); - __sort_result(&root_caller_stat, &root_caller_sorted, &caller_sort); + if (kmem_slab) { + __sort_slab_result(&root_alloc_stat, &root_alloc_sorted, + &alloc_sort); + __sort_slab_result(&root_caller_stat, &root_caller_sorted, + &caller_sort); + } + if (kmem_page) { + __sort_page_result(&page_alloc_tree, &page_alloc_sorted); + } } static int __cmd_kmem(struct perf_session *session) { int err = -EINVAL; + struct perf_evsel *evsel; const struct perf_evsel_str_handler kmem_tracepoints[] = { + /* slab allocator */ { "kmem:kmalloc", perf_evsel__process_alloc_event, }, { "kmem:kmem_cache_alloc", perf_evsel__process_alloc_event, }, { "kmem:kmalloc_node", perf_evsel__process_alloc_node_event, }, { "kmem:kmem_cache_alloc_node", perf_evsel__process_alloc_node_event, }, { "kmem:kfree", perf_evsel__process_free_event, }, { "kmem:kmem_cache_free", perf_evsel__process_free_event, }, + /* page allocator */ + { "kmem:mm_page_alloc", perf_evsel__process_page_alloc_event, }, + { "kmem:mm_page_free", perf_evsel__process_page_free_event, }, }; if (!perf_session__has_traces(session, "kmem record")) @@ -426,10 +830,20 @@ static int __cmd_kmem(struct perf_session *session) goto out; } + evlist__for_each(session->evlist, evsel) { + if (!strcmp(perf_evsel__name(evsel), "kmem:mm_page_alloc") && + perf_evsel__field(evsel, "pfn")) { + use_pfn = true; + break; + } + } + setup_pager(); err = perf_session__process_events(session); - if (err != 0) + if (err != 0) { + pr_err("error during process events: %d\n", err); goto out; + } sort_result(); print_result(session); out: @@ -612,6 +1026,22 @@ static int parse_alloc_opt(const struct option *opt __maybe_unused, return 0; } +static int parse_slab_opt(const struct option *opt __maybe_unused, + const char *arg __maybe_unused, + int unset __maybe_unused) +{ + kmem_slab = (kmem_page + 1); + return 0; +} + +static int parse_page_opt(const struct option *opt __maybe_unused, + const char *arg __maybe_unused, + int unset __maybe_unused) +{ + kmem_page = (kmem_slab + 1); + return 0; +} + static int parse_line_opt(const struct option *opt __maybe_unused, const char *arg, int unset __maybe_unused) { @@ -634,6 +1064,8 @@ static int __cmd_record(int argc, const char **argv) { const char * const record_args[] = { "record", "-a", "-R", "-c", "1", + }; + const char * const slab_events[] = { "-e", "kmem:kmalloc", "-e", "kmem:kmalloc_node", "-e", "kmem:kfree", @@ -641,10 +1073,19 @@ static int __cmd_record(int argc, const char **argv) "-e", "kmem:kmem_cache_alloc_node", "-e", "kmem:kmem_cache_free", }; + const char * const page_events[] = { + "-e", "kmem:mm_page_alloc", + "-e", "kmem:mm_page_free", + }; unsigned int rec_argc, i, j; const char **rec_argv; rec_argc = ARRAY_SIZE(record_args) + argc - 1; + if (kmem_slab) + rec_argc += ARRAY_SIZE(slab_events); + if (kmem_page) + rec_argc += ARRAY_SIZE(page_events); + rec_argv = calloc(rec_argc + 1, sizeof(char *)); if (rec_argv == NULL) @@ -653,6 +1094,15 @@ static int __cmd_record(int argc, const char **argv) for (i = 0; i < ARRAY_SIZE(record_args); i++) rec_argv[i] = strdup(record_args[i]); + if (kmem_slab) { + for (j = 0; j < ARRAY_SIZE(slab_events); j++, i++) + rec_argv[i] = strdup(slab_events[j]); + } + if (kmem_page) { + for (j = 0; j < ARRAY_SIZE(page_events); j++, i++) + rec_argv[i] = strdup(page_events[j]); + } + for (j = 1; j < (unsigned int)argc; j++, i++) rec_argv[i] = argv[j]; @@ -679,6 +1129,10 @@ int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused) OPT_CALLBACK('l', "line", NULL, "num", "show n lines", parse_line_opt), OPT_BOOLEAN(0, "raw-ip", &raw_ip, "show raw ip instead of symbol"), OPT_BOOLEAN('f', "force", &file.force, "don't complain, do it"), + OPT_CALLBACK_NOOPT(0, "slab", NULL, NULL, "Analyze slab allocator", + parse_slab_opt), + OPT_CALLBACK_NOOPT(0, "page", NULL, NULL, "Analyze page allocator", + parse_page_opt), OPT_END() }; const char *const kmem_subcommands[] = { "record", "stat", NULL }; @@ -695,6 +1149,9 @@ int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused) if (!argc) usage_with_options(kmem_usage, kmem_options); + if (kmem_slab == 0 && kmem_page == 0) + kmem_slab = 1; /* for backward compatibility */ + if (!strncmp(argv[0], "rec", 3)) { symbol__init(NULL); return __cmd_record(argc, argv); @@ -706,6 +1163,17 @@ int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused) if (session == NULL) return -1; + if (kmem_page) { + struct perf_evsel *evsel = perf_evlist__first(session->evlist); + + if (evsel == NULL || evsel->tp_format == NULL) { + pr_err("invalid event found.. aborting\n"); + return -1; + } + + kmem_page_size = pevent_get_page_size(evsel->tp_format->pevent); + } + symbol__init(&session->header.env); if (!strcmp(argv[0], "stat")) { diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index 30545ce2c712..d8bb616ff57c 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -332,6 +332,7 @@ static int find_alternative_probe_point(struct debuginfo *dinfo, else { result->offset += pp->offset; result->line += pp->line; + result->retprobe = pp->retprobe; ret = 0; } @@ -654,65 +655,6 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev, return ntevs; } -/* - * Find a src file from a DWARF tag path. Prepend optional source path prefix - * and chop off leading directories that do not exist. Result is passed back as - * a newly allocated path on success. - * Return 0 if file was found and readable, -errno otherwise. - */ -static int get_real_path(const char *raw_path, const char *comp_dir, - char **new_path) -{ - const char *prefix = symbol_conf.source_prefix; - - if (!prefix) { - if (raw_path[0] != '/' && comp_dir) - /* If not an absolute path, try to use comp_dir */ - prefix = comp_dir; - else { - if (access(raw_path, R_OK) == 0) { - *new_path = strdup(raw_path); - return *new_path ? 0 : -ENOMEM; - } else - return -errno; - } - } - - *new_path = malloc((strlen(prefix) + strlen(raw_path) + 2)); - if (!*new_path) - return -ENOMEM; - - for (;;) { - sprintf(*new_path, "%s/%s", prefix, raw_path); - - if (access(*new_path, R_OK) == 0) - return 0; - - if (!symbol_conf.source_prefix) { - /* In case of searching comp_dir, don't retry */ - zfree(new_path); - return -errno; - } - - switch (errno) { - case ENAMETOOLONG: - case ENOENT: - case EROFS: - case EFAULT: - raw_path = strchr(++raw_path, '/'); - if (!raw_path) { - zfree(new_path); - return -ENOENT; - } - continue; - - default: - zfree(new_path); - return -errno; - } - } -} - #define LINEBUF_SIZE 256 #define NR_ADDITIONAL_LINES 2 diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c index e3074230f236..b5bf9d5efeaf 100644 --- a/tools/perf/util/probe-finder.c +++ b/tools/perf/util/probe-finder.c @@ -855,11 +855,22 @@ static int probe_point_lazy_walker(const char *fname, int lineno, static int find_probe_point_lazy(Dwarf_Die *sp_die, struct probe_finder *pf) { int ret = 0; + char *fpath; if (intlist__empty(pf->lcache)) { + const char *comp_dir; + + comp_dir = cu_get_comp_dir(&pf->cu_die); + ret = get_real_path(pf->fname, comp_dir, &fpath); + if (ret < 0) { + pr_warning("Failed to find source file path.\n"); + return ret; + } + /* Matching lazy line pattern */ - ret = find_lazy_match_lines(pf->lcache, pf->fname, + ret = find_lazy_match_lines(pf->lcache, fpath, pf->pev->point.lazy_line); + free(fpath); if (ret <= 0) return ret; } @@ -1055,7 +1066,7 @@ static int debuginfo__find_probes(struct debuginfo *dbg, if (pp->function) ret = find_probe_point_by_func(pf); else if (pp->lazy_line) - ret = find_probe_point_lazy(NULL, pf); + ret = find_probe_point_lazy(&pf->cu_die, pf); else { pf->lno = pp->line; ret = find_probe_point_by_line(pf); @@ -1622,3 +1633,61 @@ found: return (ret < 0) ? ret : lf.found; } +/* + * Find a src file from a DWARF tag path. Prepend optional source path prefix + * and chop off leading directories that do not exist. Result is passed back as + * a newly allocated path on success. + * Return 0 if file was found and readable, -errno otherwise. + */ +int get_real_path(const char *raw_path, const char *comp_dir, + char **new_path) +{ + const char *prefix = symbol_conf.source_prefix; + + if (!prefix) { + if (raw_path[0] != '/' && comp_dir) + /* If not an absolute path, try to use comp_dir */ + prefix = comp_dir; + else { + if (access(raw_path, R_OK) == 0) { + *new_path = strdup(raw_path); + return *new_path ? 0 : -ENOMEM; + } else + return -errno; + } + } + + *new_path = malloc((strlen(prefix) + strlen(raw_path) + 2)); + if (!*new_path) + return -ENOMEM; + + for (;;) { + sprintf(*new_path, "%s/%s", prefix, raw_path); + + if (access(*new_path, R_OK) == 0) + return 0; + + if (!symbol_conf.source_prefix) { + /* In case of searching comp_dir, don't retry */ + zfree(new_path); + return -errno; + } + + switch (errno) { + case ENAMETOOLONG: + case ENOENT: + case EROFS: + case EFAULT: + raw_path = strchr(++raw_path, '/'); + if (!raw_path) { + zfree(new_path); + return -ENOENT; + } + continue; + + default: + zfree(new_path); + return -errno; + } + } +} diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h index 92590b2c7e1c..ebf8c8c81453 100644 --- a/tools/perf/util/probe-finder.h +++ b/tools/perf/util/probe-finder.h @@ -55,6 +55,10 @@ extern int debuginfo__find_available_vars_at(struct debuginfo *dbg, struct variable_list **vls, int max_points, bool externs); +/* Find a src file from a DWARF tag path */ +int get_real_path(const char *raw_path, const char *comp_dir, + char **new_path); + struct probe_finder { struct perf_probe_event *pev; /* Target probe event */ diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile index f0a7918178dd..ddf63569df5a 100644 --- a/tools/testing/selftests/x86/Makefile +++ b/tools/testing/selftests/x86/Makefile @@ -1,6 +1,6 @@ .PHONY: all all_32 all_64 check_build32 clean run_tests -TARGETS_C_BOTHBITS := sigreturn +TARGETS_C_BOTHBITS := sigreturn single_step_syscall BINARIES_32 := $(TARGETS_C_BOTHBITS:%=%_32) BINARIES_64 := $(TARGETS_C_BOTHBITS:%=%_64) diff --git a/tools/testing/selftests/x86/run_x86_tests.sh b/tools/testing/selftests/x86/run_x86_tests.sh index 3d3ec65f3e7c..3fc19b376812 100644 --- a/tools/testing/selftests/x86/run_x86_tests.sh +++ b/tools/testing/selftests/x86/run_x86_tests.sh @@ -3,9 +3,11 @@ # This is deliberately minimal. IMO kselftests should provide a standard # script here. ./sigreturn_32 || exit 1 +./single_step_syscall_32 || exit 1 if [[ "$uname -p" -eq "x86_64" ]]; then ./sigreturn_64 || exit 1 + ./single_step_syscall_64 || exit 1 fi exit 0 diff --git a/tools/testing/selftests/x86/single_step_syscall.c b/tools/testing/selftests/x86/single_step_syscall.c new file mode 100644 index 000000000000..50c26358e8b7 --- /dev/null +++ b/tools/testing/selftests/x86/single_step_syscall.c @@ -0,0 +1,181 @@ +/* + * single_step_syscall.c - single-steps various x86 syscalls + * Copyright (c) 2014-2015 Andrew Lutomirski + * + * This program is free software; you can redistribute it and/or modify + * it under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * This is a very simple series of tests that makes system calls with + * the TF flag set. This exercises some nasty kernel code in the + * SYSENTER case: SYSENTER does not clear TF, so SYSENTER with TF set + * immediately issues #DB from CPL 0. This requires special handling in + * the kernel. + */ + +#define _GNU_SOURCE + +#include <sys/time.h> +#include <time.h> +#include <stdlib.h> +#include <sys/syscall.h> +#include <unistd.h> +#include <stdio.h> +#include <string.h> +#include <inttypes.h> +#include <sys/mman.h> +#include <sys/signal.h> +#include <sys/ucontext.h> +#include <asm/ldt.h> +#include <err.h> +#include <setjmp.h> +#include <stddef.h> +#include <stdbool.h> +#include <sys/ptrace.h> +#include <sys/user.h> + +static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *), + int flags) +{ + struct sigaction sa; + memset(&sa, 0, sizeof(sa)); + sa.sa_sigaction = handler; + sa.sa_flags = SA_SIGINFO | flags; + sigemptyset(&sa.sa_mask); + if (sigaction(sig, &sa, 0)) + err(1, "sigaction"); +} + +static volatile sig_atomic_t sig_traps; + +#ifdef __x86_64__ +# define REG_IP REG_RIP +# define WIDTH "q" +#else +# define REG_IP REG_EIP +# define WIDTH "l" +#endif + +static unsigned long get_eflags(void) +{ + unsigned long eflags; + asm volatile ("pushf" WIDTH "\n\tpop" WIDTH " %0" : "=rm" (eflags)); + return eflags; +} + +static void set_eflags(unsigned long eflags) +{ + asm volatile ("push" WIDTH " %0\n\tpopf" WIDTH + : : "rm" (eflags) : "flags"); +} + +#define X86_EFLAGS_TF (1UL << 8) + +static void sigtrap(int sig, siginfo_t *info, void *ctx_void) +{ + ucontext_t *ctx = (ucontext_t*)ctx_void; + + if (get_eflags() & X86_EFLAGS_TF) { + set_eflags(get_eflags() & ~X86_EFLAGS_TF); + printf("[WARN]\tSIGTRAP handler had TF set\n"); + _exit(1); + } + + sig_traps++; + + if (sig_traps == 10000 || sig_traps == 10001) { + printf("[WARN]\tHit %d SIGTRAPs with si_addr 0x%lx, ip 0x%lx\n", + (int)sig_traps, + (unsigned long)info->si_addr, + (unsigned long)ctx->uc_mcontext.gregs[REG_IP]); + } +} + +static void check_result(void) +{ + unsigned long new_eflags = get_eflags(); + set_eflags(new_eflags & ~X86_EFLAGS_TF); + + if (!sig_traps) { + printf("[FAIL]\tNo SIGTRAP\n"); + exit(1); + } + + if (!(new_eflags & X86_EFLAGS_TF)) { + printf("[FAIL]\tTF was cleared\n"); + exit(1); + } + + printf("[OK]\tSurvived with TF set and %d traps\n", (int)sig_traps); + sig_traps = 0; +} + +int main() +{ + int tmp; + + sethandler(SIGTRAP, sigtrap, 0); + + printf("[RUN]\tSet TF and check nop\n"); + set_eflags(get_eflags() | X86_EFLAGS_TF); + asm volatile ("nop"); + check_result(); + +#ifdef __x86_64__ + printf("[RUN]\tSet TF and check syscall-less opportunistic sysret\n"); + set_eflags(get_eflags() | X86_EFLAGS_TF); + extern unsigned char post_nop[]; + asm volatile ("pushf" WIDTH "\n\t" + "pop" WIDTH " %%r11\n\t" + "nop\n\t" + "post_nop:" + : : "c" (post_nop) : "r11"); + check_result(); +#endif + + printf("[RUN]\tSet TF and check int80\n"); + set_eflags(get_eflags() | X86_EFLAGS_TF); + asm volatile ("int $0x80" : "=a" (tmp) : "a" (SYS_getpid)); + check_result(); + + /* + * This test is particularly interesting if fast syscalls use + * SYSENTER: it triggers a nasty design flaw in SYSENTER. + * Specifically, SYSENTER does not clear TF, so either SYSENTER + * or the next instruction traps at CPL0. (Of course, Intel + * mostly forgot to document exactly what happens here.) So we + * get a CPL0 fault with usergs (on 64-bit kernels) and possibly + * no stack. The only sane way the kernel can possibly handle + * it is to clear TF on return from the #DB handler, but this + * happens way too early to set TF in the saved pt_regs, so the + * kernel has to do something clever to avoid losing track of + * the TF bit. + * + * Needless to say, we've had bugs in this area. + */ + syscall(SYS_getpid); /* Force symbol binding without TF set. */ + printf("[RUN]\tSet TF and check a fast syscall\n"); + set_eflags(get_eflags() | X86_EFLAGS_TF); + syscall(SYS_getpid); + check_result(); + + /* Now make sure that another fast syscall doesn't set TF again. */ + printf("[RUN]\tFast syscall with TF cleared\n"); + fflush(stdout); /* Force a syscall */ + if (get_eflags() & X86_EFLAGS_TF) { + printf("[FAIL]\tTF is now set\n"); + exit(1); + } + if (sig_traps) { + printf("[FAIL]\tGot SIGTRAP\n"); + exit(1); + } + printf("[OK]\tNothing unexpected happened\n"); + + return 0; +} |