From f51304d3fe4fee475991ee424a4b7f85eec65a7b Mon Sep 17 00:00:00 2001 From: David Ahern Date: Fri, 20 Jul 2012 17:25:46 -0600 Subject: perf symbols: Add machine id to modules debug message Current debug message is: Problems creating module maps, continuing anyway... When running multiple VMs it would be nice to know which machine the message is referring to: $ perf kvm --guest --guestmount=/tmp/guest-mount record -av -- sleep 10 Problems creating module maps for guest 6613, continuing anyway... Signed-off-by: David Ahern Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Jiri Olsa Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1342826756-64663-2-git-send-email-dsahern@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/symbol.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'tools') diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 50958bbeb26a..66c132e52875 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -2564,8 +2564,15 @@ int machine__create_kernel_maps(struct machine *machine) __machine__create_kernel_maps(machine, kernel) < 0) return -1; - if (symbol_conf.use_modules && machine__create_modules(machine) < 0) - pr_debug("Problems creating module maps, continuing anyway...\n"); + if (symbol_conf.use_modules && machine__create_modules(machine) < 0) { + if (machine__is_host(machine)) + pr_debug("Problems creating module maps, " + "continuing anyway...\n"); + else + pr_debug("Problems creating module maps for guest %d, " + "continuing anyway...\n", machine->pid); + } + /* * Now that we have all the maps created, just set the ->end of them: */ -- cgit From 5cd95c2db479aa7a66f6fa572dfa410c6314c78e Mon Sep 17 00:00:00 2001 From: David Ahern Date: Fri, 20 Jul 2012 17:25:47 -0600 Subject: perf kvm: Set name for VM process in guest machine COMM events are not generated in the context of a guest machine, so the thread name is never set for the VMM process. For example, the qemu-kvm name applies to the process in the host machine, not the guest machine. So, samples for guest machines are currently displayed as: 99.67% :5671 [unknown] [g] 0xffffffff81366b41 where 5671 is the pid of the VMM. With this patch the samples in the guest machine are shown as: 18.43% [guest/5671] [unknown] [g] 0xffffffff810d68b7 Tested-by: Jiri Olsa Signed-off-by: David Ahern Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Jiri Olsa Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1342826756-64663-3-git-send-email-dsahern@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/map.c | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index a1f4e3669142..8668569d4b2a 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -7,6 +7,7 @@ #include #include #include "map.h" +#include "thread.h" const char *map_type__name[MAP__NR_TYPES] = { [MAP__FUNCTION] = "Functions", @@ -585,7 +586,21 @@ int machine__init(struct machine *self, const char *root_dir, pid_t pid) self->kmaps.machine = self; self->pid = pid; self->root_dir = strdup(root_dir); - return self->root_dir == NULL ? -ENOMEM : 0; + if (self->root_dir == NULL) + return -ENOMEM; + + if (pid != HOST_KERNEL_ID) { + struct thread *thread = machine__findnew_thread(self, pid); + char comm[64]; + + if (thread == NULL) + return -ENOMEM; + + snprintf(comm, sizeof(comm), "[guest/%d]", pid); + thread__set_comm(thread, comm); + } + + return 0; } static void dsos__delete(struct list_head *self) -- cgit From 7c0f4a4113ba5de7898c246eeaeee4c23d94b887 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Fri, 20 Jul 2012 17:25:48 -0600 Subject: perf kvm: Guest userspace samples should not be lumped with host uspace e.g., perf kvm --host --guest report -i perf.data --stdio -D shows: 1 599127912065356 0x143b8 [0x48]: PERF_RECORD_SAMPLE(IP, 5): 5671/5676: 0x7fdf95a061c0 period: 1 addr: 0 ... chain: nr:2 ..... 0: ffffffffffffff80 ..... 1: fffffffffffffe00 ... thread: qemu-kvm:5671 ...... dso: (IP, 5) means sample in guest userspace. Those samples should not be lumped into the VMM's host thread. i.e, the report output: 56.86% qemu-kvm [unknown] [u] 0x00007fdf95a061c0 With this patch the output emphasizes it is a guest userspace hit: 56.86% [guest/5671] [unknown] [u] 0x00007fdf95a061c0 Looking at 3 VMs (2 64-bit, 1 32-bit) with each running a CPU bound process (openssl speed), perf report currently shows: 93.84% 117726 qemu-kvm [unknown] [u] 0x00007fd7dcaea8e5 which is wrong. With this patch you get: 31.50% 39258 [guest/18772] [unknown] [u] 0x00007fd7dcaea8e5 31.50% 39236 [guest/11230] [unknown] [u] 0x0000000000a57340 30.84% 39232 [guest/18395] [unknown] [u] 0x00007f66f641e107 Tested-by: Jiri Olsa Signed-off-by: David Ahern Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Jiri Olsa Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1342826756-64663-4-git-send-email-dsahern@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/session.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 8e485592ca20..90ee39dd8ab2 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -918,7 +918,9 @@ static struct machine * { const u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; - if (cpumode == PERF_RECORD_MISC_GUEST_KERNEL && perf_guest) { + if (perf_guest && + ((cpumode == PERF_RECORD_MISC_GUEST_KERNEL) || + (cpumode == PERF_RECORD_MISC_GUEST_USER))) { u32 pid; if (event->header.type == PERF_RECORD_MMAP) -- cgit From adb5d2a487c55e5ca2ecc0b73c8f592e95d292c7 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Fri, 20 Jul 2012 17:25:49 -0600 Subject: perf kvm: Fix bug resolving guest kernel syms Guest kernel symbols are not resolved despite passing the information needed to resolve them. e.g., perf kvm --guest --guestmount=/tmp/guest-mount record -a -- sleep 1 perf kvm --guest --guestmount=/tmp/guest-mount report --stdio 36.55% [guest/11399] [unknown] [g] 0xffffffff81600bc8 33.19% [guest/10474] [unknown] [g] 0x00000000c0116e00 30.26% [guest/11094] [unknown] [g] 0xffffffff8100a288 43.69% [guest/10474] [unknown] [g] 0x00000000c0103d90 37.38% [guest/11399] [unknown] [g] 0xffffffff81600bc8 12.24% [guest/11094] [unknown] [g] 0xffffffff810aa91d 6.69% [guest/11094] [unknown] [u] 0x00007fa784d721c3 which is just pathetic. After a maddening 2 days sifting through perf minutia I found it -- id_hdr_size is not initialized for guest machines. This shows up on the report side as random garbage for the cpu and timestamp, e.g., 29816 7310572949125804849 0x1ac0 [0x50]: PERF_RECORD_MMAP ... That messes up the sample sorting such that synthesized guest maps are processed last. With this patch you get a much more helpful report: 12.11% [guest/11399] [guest.kernel.kallsyms.11399] [g] irqtime_account_process_tick 10.58% [guest/11399] [guest.kernel.kallsyms.11399] [g] run_timer_softirq 6.95% [guest/11094] [guest.kernel.kallsyms.11094] [g] printk_needs_cpu 6.50% [guest/11094] [guest.kernel.kallsyms.11094] [g] do_timer 6.45% [guest/11399] [guest.kernel.kallsyms.11399] [g] idle_balance 4.90% [guest/11094] [guest.kernel.kallsyms.11094] [g] native_read_tsc ... v2: - changed rbtree walk to use rb_first per Namhyung's suggestion Tested-by: Jiri Olsa Signed-off-by: David Ahern Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Jiri Olsa Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1342826756-64663-5-git-send-email-dsahern@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/map.c | 13 +++++++++++++ tools/perf/util/map.h | 1 + tools/perf/util/session.c | 1 + 3 files changed, 15 insertions(+) (limited to 'tools') diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index 8668569d4b2a..16d783d322b6 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -729,3 +729,16 @@ char *machine__mmap_name(struct machine *self, char *bf, size_t size) return bf; } + +void machines__set_id_hdr_size(struct rb_root *machines, u16 id_hdr_size) +{ + struct rb_node *node; + struct machine *machine; + + for (node = rb_first(machines); node; node = rb_next(node)) { + machine = rb_entry(node, struct machine, rb_node); + machine->id_hdr_size = id_hdr_size; + } + + return; +} diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h index c14c665d9a25..03a1e9b08b21 100644 --- a/tools/perf/util/map.h +++ b/tools/perf/util/map.h @@ -151,6 +151,7 @@ struct machine *machines__add(struct rb_root *self, pid_t pid, struct machine *machines__find_host(struct rb_root *self); struct machine *machines__find(struct rb_root *self, pid_t pid); struct machine *machines__findnew(struct rb_root *self, pid_t pid); +void machines__set_id_hdr_size(struct rb_root *self, u16 id_hdr_size); char *machine__mmap_name(struct machine *self, char *bf, size_t size); int machine__init(struct machine *self, const char *root_dir, pid_t pid); void machine__exit(struct machine *self); diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 90ee39dd8ab2..8e4f0755d2aa 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -87,6 +87,7 @@ void perf_session__update_sample_type(struct perf_session *self) self->sample_id_all = perf_evlist__sample_id_all(self->evlist); self->id_hdr_size = perf_evlist__id_hdr_size(self->evlist); self->host_machine.id_hdr_size = self->id_hdr_size; + machines__set_id_hdr_size(&self->machines, self->id_hdr_size); } int perf_session__create_kernel_maps(struct perf_session *self) -- cgit From c80c3c269011c67b8dabef5238af44a6d94e4d0e Mon Sep 17 00:00:00 2001 From: David Ahern Date: Fri, 20 Jul 2012 17:25:51 -0600 Subject: perf kvm: Limit repetitive guestmount message to once per directory After 7ed97ad use of the guestmount option without a subdir for *each* VM generates an error message for each sample related to that VM. Once per VM is enough. Signed-off-by: David Ahern Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Jiri Olsa Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1342826756-64663-7-git-send-email-dsahern@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/map.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index 16d783d322b6..cc33486ad9e2 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -8,6 +8,7 @@ #include #include "map.h" #include "thread.h" +#include "strlist.h" const char *map_type__name[MAP__NR_TYPES] = { [MAP__FUNCTION] = "Functions", @@ -695,7 +696,15 @@ struct machine *machines__findnew(struct rb_root *self, pid_t pid) (symbol_conf.guestmount)) { sprintf(path, "%s/%d", symbol_conf.guestmount, pid); if (access(path, R_OK)) { - pr_err("Can't access file %s\n", path); + static struct strlist *seen; + + if (!seen) + seen = strlist__new(true, NULL); + + if (!strlist__has_entry(seen, path)) { + pr_err("Can't access file %s\n", path); + strlist__add(seen, path); + } machine = NULL; goto out; } -- cgit From 78b961ff8e67207adb15959526cdea4cc50ae1ed Mon Sep 17 00:00:00 2001 From: David Ahern Date: Fri, 20 Jul 2012 17:25:52 -0600 Subject: perf tools: Dump exclude_{guest,host}, precise_ip header info too Adds the attributes to the event line in the header dump. From: event : name = cycles, type = 0, config = 0x0, config1 = 0x0, config2 = 0x0, excl_usr = 0, excl_kern = 0, ... to event : name = cycles, type = 0, config = 0x0, config1 = 0x0, config2 = 0x0, excl_usr = 0, excl_kern = 0, excl_host = 0, excl_guest = 0, precise_ip = 0, ... Signed-off-by: David Ahern Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Jiri Olsa Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/r/1342826756-64663-8-git-send-email-dsahern@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/header.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'tools') diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 5a47aba46759..3a6d20443330 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -1212,6 +1212,12 @@ static void print_event_desc(struct perf_header *ph, int fd, FILE *fp) attr.exclude_user, attr.exclude_kernel); + fprintf(fp, ", excl_host = %d, excl_guest = %d", + attr.exclude_host, + attr.exclude_guest); + + fprintf(fp, ", precise_ip = %d", attr.precise_ip); + if (nr) fprintf(fp, ", id = {"); -- cgit From 8760db726e2afcd1a78e2ff58965c6b35a5826cb Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 18 Jul 2012 19:10:55 +0200 Subject: perf hists: Return correct number of characters printed in callchain Include the omitted number of characters printed for the first entry. Not that it really matters because nobody seem to care about the number of printed characters for now. But just in case. Signed-off-by: Frederic Weisbecker Cc: David Ahern Cc: Jiri Olsa Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1342631456-7233-2-git-send-email-fweisbec@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/hist.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'tools') diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 514e2a4b367d..90dc35ae444a 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -708,7 +708,7 @@ static size_t callchain__fprintf_graph(FILE *fp, struct rb_root *root, bool printed = false; struct rb_node *node; int i = 0; - int ret; + int ret = 0; /* * If have one single callchain root, don't bother printing @@ -747,8 +747,9 @@ static size_t callchain__fprintf_graph(FILE *fp, struct rb_root *root, root = &cnode->rb_root; } - return __callchain__fprintf_graph(fp, root, total_samples, + ret += __callchain__fprintf_graph(fp, root, total_samples, 1, 1, left_margin); + return ret; } static size_t __callchain__fprintf_flat(FILE *fp, -- cgit From 0983cc0dbca45250cbb5984bec7c303ac265b8e5 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 18 Jul 2012 19:10:54 +0200 Subject: perf tools: Fix trace events storms due to weight demux Trace events have a period (weight) of 1 by default. This can be overriden on events definition by using the __perf_count() macro. For example, the sched_stat_runtime() is weighted with the runtime of the task that fired the event. By default, perf handles such weighted event by dividing it into individual events carrying a weight of 1. For example if sched_stat_runtime is fired and the task has run 5000000 nsecs, perf divides it into 5000000 events in the buffer. This behaviour makes weighted events unusable because they quickly fullfill the buffers and we lose most events. The commit 5d81e5cfb37a174e8ddc0413e2e70cdf05807ace ("events: Don't divide events if it has field period") solves this problem by sending only one event when PERF_SAMPLE_PERIOD flag is set. The weight is carried in the sample itself such that we don't need to demultiplex it anymore. This patch provides the last missing piece to use this feature by setting PERF_SAMPLE_PERIOD from perf tools when we deal with trace events. Before: $ ./perf record -e sched:* -a sleep 1 [ perf record: Woken up 3 times to write data ] [ perf record: Captured and wrote 1.619 MB perf.data (~70749 samples) ] Warning: Processed 16909 events and lost 1 chunks! Check IO/CPU overload! $ ./perf script perf 1894 [003] 824.898327: sched_migrate_task: comm=perf pid=1898 prio=120 orig_cpu=2 dest_cpu=0 perf 1894 [003] 824.898335: sched_stat_sleep: comm=perf pid=1898 delay=113179500 [ns] perf 1894 [003] 824.898336: sched_stat_sleep: comm=perf pid=1898 delay=113179500 [ns] perf 1894 [003] 824.898337: sched_stat_sleep: comm=perf pid=1898 delay=113179500 [ns] perf 1894 [003] 824.898338: sched_stat_sleep: comm=perf pid=1898 delay=113179500 [ns] perf 1894 [003] 824.898339: sched_stat_sleep: comm=perf pid=1898 delay=113179500 [ns] perf 1894 [003] 824.898340: sched_stat_sleep: comm=perf pid=1898 delay=113179500 [ns] perf 1894 [003] 824.898341: sched_stat_sleep: comm=perf pid=1898 delay=113179500 [ns] [...] After: $ ./perf record -e sched:* -a sleep 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.074 MB perf.data (~3228 samples) ] $ ./perf script perf 1461 [000] 554.286957: sched_migrate_task: comm=perf pid=1465 prio=120 orig_cpu=3 dest_cpu=1 perf 1461 [000] 554.286964: sched_stat_sleep: comm=perf pid=1465 delay=133047190 [ns] perf 1461 [000] 554.286967: sched_wakeup: comm=perf pid=1465 prio=120 success=1 target_cpu=001 swapper 0 [001] 554.286976: sched_stat_wait: comm=perf pid=1465 delay=0 [ns] swapper 0 [001] 554.286983: sched_switch: prev_comm=swapper/1 prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=perf [...] Signed-off-by: Frederic Weisbecker Cc: David Ahern Cc: Ingo Molnar Cc: Jiri Olsa Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1342631456-7233-1-git-send-email-fweisbec@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/evlist.c | 2 +- tools/perf/util/parse-events.c | 1 + 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index f74e9560350e..3edfd3483816 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -214,7 +214,7 @@ int perf_evlist__add_tracepoints(struct perf_evlist *evlist, attrs[i].type = PERF_TYPE_TRACEPOINT; attrs[i].config = err; attrs[i].sample_type = (PERF_SAMPLE_RAW | PERF_SAMPLE_TIME | - PERF_SAMPLE_CPU); + PERF_SAMPLE_CPU | PERF_SAMPLE_PERIOD); attrs[i].sample_period = 1; } diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 1aa721d7c10f..a729945838f5 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -377,6 +377,7 @@ static int add_tracepoint(struct list_head **list, int *idx, attr.sample_type |= PERF_SAMPLE_RAW; attr.sample_type |= PERF_SAMPLE_TIME; attr.sample_type |= PERF_SAMPLE_CPU; + attr.sample_type |= PERF_SAMPLE_PERIOD; attr.sample_period = 1; snprintf(name, MAX_NAME_LEN, "%s:%s", sys_name, evt_name); -- cgit From 6654f5d8bdaa438b1e60dfeb90f9d46ca969c012 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 18 Jul 2012 19:10:56 +0200 Subject: perf hists: Print newline between hists callchains Tiny cosmetic fix. The lack of a newline between hists callchains was looking slightly messy. Before: 0.24% swapper [kernel.kallsyms] [k] _raw_spin_lock_irq | --- _raw_spin_lock_irq run_timer_softirq __do_softirq call_softirq do_softirq irq_exit smp_apic_timer_interrupt apic_timer_interrupt default_idle amd_e400_idle cpu_idle start_secondary 0.10% perf [kernel.kallsyms] [k] lock_is_held | --- lock_is_held __might_sleep mutex_lock_nested perf_event_for_each_child perf_ioctl do_vfs_ioctl sys_ioctl system_call_fastpath ioctl cmd_record run_builtin main __libc_start_main After: 0.24% swapper [kernel.kallsyms] [k] _raw_spin_lock_irq | --- _raw_spin_lock_irq run_timer_softirq __do_softirq call_softirq do_softirq irq_exit smp_apic_timer_interrupt apic_timer_interrupt default_idle amd_e400_idle cpu_idle start_secondary 0.10% perf [kernel.kallsyms] [k] lock_is_held | --- lock_is_held __might_sleep mutex_lock_nested perf_event_for_each_child perf_ioctl do_vfs_ioctl sys_ioctl system_call_fastpath ioctl cmd_record run_builtin main __libc_start_main Signed-off-by: Frederic Weisbecker Cc: David Ahern Cc: Ingo Molnar Cc: Jiri Olsa Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1342631456-7233-3-git-send-email-fweisbec@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/hist.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'tools') diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 90dc35ae444a..f247ef2789a4 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -749,6 +749,8 @@ static size_t callchain__fprintf_graph(FILE *fp, struct rb_root *root, ret += __callchain__fprintf_graph(fp, root, total_samples, 1, 1, left_margin); + ret += fprintf(fp, "\n"); + return ret; } -- cgit From 44f24cb3156a1e7d2b6bb501b7f6153aed08994c Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Sun, 22 Jul 2012 14:14:32 +0200 Subject: perf symbols: Factor DSO symtab types to generic binary types Adding interface to access DSOs so it could be used from another place. New DSO binary type is added - making current SYMTAB__* types more general: DSO_BINARY_TYPE__* = SYMTAB__* Following function is added to return path based on the specified binary type: dso__binary_type_file Signed-off-by: Jiri Olsa Cc: Arun Sharma Cc: Benjamin Redelings Cc: Corey Ashford Cc: Cyrill Gorcunov Cc: Frank Ch. Eigler Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Masami Hiramatsu Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Robert Richter Cc: Stephane Eranian Cc: Tom Zanussi Cc: Ulrich Drepper Link: http://lkml.kernel.org/r/1342959280-5361-10-git-send-email-jolsa@redhat.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-top.c | 2 +- tools/perf/util/annotate.c | 2 +- tools/perf/util/symbol.c | 209 +++++++++++++++++++++++++++------------------ tools/perf/util/symbol.h | 34 ++++---- 4 files changed, 145 insertions(+), 102 deletions(-) (limited to 'tools') diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index e3cab5f088f8..35e86c6df713 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -125,7 +125,7 @@ static int perf_top__parse_source(struct perf_top *top, struct hist_entry *he) /* * We can't annotate with just /proc/kallsyms */ - if (map->dso->symtab_type == SYMTAB__KALLSYMS) { + if (map->dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS) { pr_err("Can't annotate %s: No vmlinux file was found in the " "path\n", sym->name); sleep(1); diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 8069dfb5ba77..7d3641f6332c 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -777,7 +777,7 @@ fallback: free_filename = false; } - if (dso->symtab_type == SYMTAB__KALLSYMS) { + if (dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS) { char bf[BUILD_ID_SIZE * 2 + 16] = " with build id "; char *build_id_msg = NULL; diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 66c132e52875..60677a63bc7d 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -48,6 +48,23 @@ struct symbol_conf symbol_conf = { .symfs = "", }; +static enum dso_binary_type binary_type_symtab[] = { + DSO_BINARY_TYPE__KALLSYMS, + DSO_BINARY_TYPE__GUEST_KALLSYMS, + DSO_BINARY_TYPE__JAVA_JIT, + DSO_BINARY_TYPE__DEBUGLINK, + DSO_BINARY_TYPE__BUILD_ID_CACHE, + DSO_BINARY_TYPE__FEDORA_DEBUGINFO, + DSO_BINARY_TYPE__UBUNTU_DEBUGINFO, + DSO_BINARY_TYPE__BUILDID_DEBUGINFO, + DSO_BINARY_TYPE__SYSTEM_PATH_DSO, + DSO_BINARY_TYPE__GUEST_KMODULE, + DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE, + DSO_BINARY_TYPE__NOT_FOUND, +}; + +#define DSO_BINARY_TYPE__SYMTAB_CNT sizeof(binary_type_symtab) + int dso__name_len(const struct dso *dso) { if (!dso) @@ -318,7 +335,7 @@ struct dso *dso__new(const char *name) dso__set_short_name(dso, dso->name); for (i = 0; i < MAP__NR_TYPES; ++i) dso->symbols[i] = dso->symbol_names[i] = RB_ROOT; - dso->symtab_type = SYMTAB__NOT_FOUND; + dso->symtab_type = DSO_BINARY_TYPE__NOT_FOUND; dso->loaded = 0; dso->sorted_by_name = 0; dso->has_build_id = 0; @@ -806,9 +823,9 @@ int dso__load_kallsyms(struct dso *dso, const char *filename, symbols__fixup_end(&dso->symbols[map->type]); if (dso->kernel == DSO_TYPE_GUEST_KERNEL) - dso->symtab_type = SYMTAB__GUEST_KALLSYMS; + dso->symtab_type = DSO_BINARY_TYPE__GUEST_KALLSYMS; else - dso->symtab_type = SYMTAB__KALLSYMS; + dso->symtab_type = DSO_BINARY_TYPE__KALLSYMS; return dso__split_kallsyms(dso, map, filter); } @@ -1660,32 +1677,110 @@ out: char dso__symtab_origin(const struct dso *dso) { static const char origin[] = { - [SYMTAB__KALLSYMS] = 'k', - [SYMTAB__JAVA_JIT] = 'j', - [SYMTAB__DEBUGLINK] = 'l', - [SYMTAB__BUILD_ID_CACHE] = 'B', - [SYMTAB__FEDORA_DEBUGINFO] = 'f', - [SYMTAB__UBUNTU_DEBUGINFO] = 'u', - [SYMTAB__BUILDID_DEBUGINFO] = 'b', - [SYMTAB__SYSTEM_PATH_DSO] = 'd', - [SYMTAB__SYSTEM_PATH_KMODULE] = 'K', - [SYMTAB__GUEST_KALLSYMS] = 'g', - [SYMTAB__GUEST_KMODULE] = 'G', + [DSO_BINARY_TYPE__KALLSYMS] = 'k', + [DSO_BINARY_TYPE__JAVA_JIT] = 'j', + [DSO_BINARY_TYPE__DEBUGLINK] = 'l', + [DSO_BINARY_TYPE__BUILD_ID_CACHE] = 'B', + [DSO_BINARY_TYPE__FEDORA_DEBUGINFO] = 'f', + [DSO_BINARY_TYPE__UBUNTU_DEBUGINFO] = 'u', + [DSO_BINARY_TYPE__BUILDID_DEBUGINFO] = 'b', + [DSO_BINARY_TYPE__SYSTEM_PATH_DSO] = 'd', + [DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE] = 'K', + [DSO_BINARY_TYPE__GUEST_KALLSYMS] = 'g', + [DSO_BINARY_TYPE__GUEST_KMODULE] = 'G', }; - if (dso == NULL || dso->symtab_type == SYMTAB__NOT_FOUND) + if (dso == NULL || dso->symtab_type == DSO_BINARY_TYPE__NOT_FOUND) return '!'; return origin[dso->symtab_type]; } +int dso__binary_type_file(struct dso *dso, enum dso_binary_type type, + char *root_dir, char *file, size_t size) +{ + char build_id_hex[BUILD_ID_SIZE * 2 + 1]; + int ret = 0; + + switch (type) { + case DSO_BINARY_TYPE__DEBUGLINK: { + char *debuglink; + + strncpy(file, dso->long_name, size); + debuglink = file + dso->long_name_len; + while (debuglink != file && *debuglink != '/') + debuglink--; + if (*debuglink == '/') + debuglink++; + filename__read_debuglink(dso->long_name, debuglink, + size - (debuglink - file)); + } + break; + case DSO_BINARY_TYPE__BUILD_ID_CACHE: + /* skip the locally configured cache if a symfs is given */ + if (symbol_conf.symfs[0] || + (dso__build_id_filename(dso, file, size) == NULL)) + ret = -1; + break; + + case DSO_BINARY_TYPE__FEDORA_DEBUGINFO: + snprintf(file, size, "%s/usr/lib/debug%s.debug", + symbol_conf.symfs, dso->long_name); + break; + + case DSO_BINARY_TYPE__UBUNTU_DEBUGINFO: + snprintf(file, size, "%s/usr/lib/debug%s", + symbol_conf.symfs, dso->long_name); + break; + + case DSO_BINARY_TYPE__BUILDID_DEBUGINFO: + if (!dso->has_build_id) { + ret = -1; + break; + } + + build_id__sprintf(dso->build_id, + sizeof(dso->build_id), + build_id_hex); + snprintf(file, size, + "%s/usr/lib/debug/.build-id/%.2s/%s.debug", + symbol_conf.symfs, build_id_hex, build_id_hex + 2); + break; + + case DSO_BINARY_TYPE__SYSTEM_PATH_DSO: + snprintf(file, size, "%s%s", + symbol_conf.symfs, dso->long_name); + break; + + case DSO_BINARY_TYPE__GUEST_KMODULE: + snprintf(file, size, "%s%s%s", symbol_conf.symfs, + root_dir, dso->long_name); + break; + + case DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE: + snprintf(file, size, "%s%s", symbol_conf.symfs, + dso->long_name); + break; + + default: + case DSO_BINARY_TYPE__KALLSYMS: + case DSO_BINARY_TYPE__GUEST_KALLSYMS: + case DSO_BINARY_TYPE__JAVA_JIT: + case DSO_BINARY_TYPE__NOT_FOUND: + ret = -1; + break; + } + + return ret; +} + int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter) { - int size = PATH_MAX; char *name; int ret = -1; int fd; + u_int i; struct machine *machine; - const char *root_dir; + char *root_dir = (char *) ""; int want_symtab; dso__set_loaded(dso, map->type); @@ -1700,7 +1795,7 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter) else machine = NULL; - name = malloc(size); + name = malloc(PATH_MAX); if (!name) return -1; @@ -1719,81 +1814,27 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter) } ret = dso__load_perf_map(dso, map, filter); - dso->symtab_type = ret > 0 ? SYMTAB__JAVA_JIT : - SYMTAB__NOT_FOUND; + dso->symtab_type = ret > 0 ? DSO_BINARY_TYPE__JAVA_JIT : + DSO_BINARY_TYPE__NOT_FOUND; return ret; } + if (machine) + root_dir = machine->root_dir; + /* Iterate over candidate debug images. * On the first pass, only load images if they have a full symtab. * Failing that, do a second pass where we accept .dynsym also */ want_symtab = 1; restart: - for (dso->symtab_type = SYMTAB__DEBUGLINK; - dso->symtab_type != SYMTAB__NOT_FOUND; - dso->symtab_type++) { - switch (dso->symtab_type) { - case SYMTAB__DEBUGLINK: { - char *debuglink; - strncpy(name, dso->long_name, size); - debuglink = name + dso->long_name_len; - while (debuglink != name && *debuglink != '/') - debuglink--; - if (*debuglink == '/') - debuglink++; - filename__read_debuglink(dso->long_name, debuglink, - size - (debuglink - name)); - } - break; - case SYMTAB__BUILD_ID_CACHE: - /* skip the locally configured cache if a symfs is given */ - if (symbol_conf.symfs[0] || - (dso__build_id_filename(dso, name, size) == NULL)) { - continue; - } - break; - case SYMTAB__FEDORA_DEBUGINFO: - snprintf(name, size, "%s/usr/lib/debug%s.debug", - symbol_conf.symfs, dso->long_name); - break; - case SYMTAB__UBUNTU_DEBUGINFO: - snprintf(name, size, "%s/usr/lib/debug%s", - symbol_conf.symfs, dso->long_name); - break; - case SYMTAB__BUILDID_DEBUGINFO: { - char build_id_hex[BUILD_ID_SIZE * 2 + 1]; - - if (!dso->has_build_id) - continue; + for (i = 0; i < DSO_BINARY_TYPE__SYMTAB_CNT; i++) { - build_id__sprintf(dso->build_id, - sizeof(dso->build_id), - build_id_hex); - snprintf(name, size, - "%s/usr/lib/debug/.build-id/%.2s/%s.debug", - symbol_conf.symfs, build_id_hex, build_id_hex + 2); - } - break; - case SYMTAB__SYSTEM_PATH_DSO: - snprintf(name, size, "%s%s", - symbol_conf.symfs, dso->long_name); - break; - case SYMTAB__GUEST_KMODULE: - if (map->groups && machine) - root_dir = machine->root_dir; - else - root_dir = ""; - snprintf(name, size, "%s%s%s", symbol_conf.symfs, - root_dir, dso->long_name); - break; + dso->symtab_type = binary_type_symtab[i]; - case SYMTAB__SYSTEM_PATH_KMODULE: - snprintf(name, size, "%s%s", symbol_conf.symfs, - dso->long_name); - break; - default:; - } + if (dso__binary_type_file(dso, dso->symtab_type, + root_dir, name, PATH_MAX)) + continue; /* Name is now the name of the next image to try */ fd = open(name, O_RDONLY); @@ -2010,9 +2051,9 @@ struct map *machine__new_module(struct machine *machine, u64 start, return NULL; if (machine__is_host(machine)) - dso->symtab_type = SYMTAB__SYSTEM_PATH_KMODULE; + dso->symtab_type = DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE; else - dso->symtab_type = SYMTAB__GUEST_KMODULE; + dso->symtab_type = DSO_BINARY_TYPE__GUEST_KMODULE; map_groups__insert(&machine->kmaps, map); return map; } diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index a884b99017f0..dc474f07bb2d 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -155,6 +155,21 @@ struct addr_location { s32 cpu; }; +enum dso_binary_type { + DSO_BINARY_TYPE__KALLSYMS = 0, + DSO_BINARY_TYPE__GUEST_KALLSYMS, + DSO_BINARY_TYPE__JAVA_JIT, + DSO_BINARY_TYPE__DEBUGLINK, + DSO_BINARY_TYPE__BUILD_ID_CACHE, + DSO_BINARY_TYPE__FEDORA_DEBUGINFO, + DSO_BINARY_TYPE__UBUNTU_DEBUGINFO, + DSO_BINARY_TYPE__BUILDID_DEBUGINFO, + DSO_BINARY_TYPE__SYSTEM_PATH_DSO, + DSO_BINARY_TYPE__GUEST_KMODULE, + DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE, + DSO_BINARY_TYPE__NOT_FOUND, +}; + enum dso_kernel_type { DSO_TYPE_USER = 0, DSO_TYPE_KERNEL, @@ -173,13 +188,13 @@ struct dso { struct rb_root symbol_names[MAP__NR_TYPES]; enum dso_kernel_type kernel; enum dso_swap_type needs_swap; + enum dso_binary_type symtab_type; u8 adjust_symbols:1; u8 has_build_id:1; u8 hit:1; u8 annotate_warned:1; u8 sname_alloc:1; u8 lname_alloc:1; - unsigned char symtab_type; u8 sorted_by_name; u8 loaded; u8 build_id[BUILD_ID_SIZE]; @@ -253,21 +268,6 @@ size_t dso__fprintf_symbols_by_name(struct dso *dso, enum map_type type, FILE *fp); size_t dso__fprintf(struct dso *dso, enum map_type type, FILE *fp); -enum symtab_type { - SYMTAB__KALLSYMS = 0, - SYMTAB__GUEST_KALLSYMS, - SYMTAB__JAVA_JIT, - SYMTAB__DEBUGLINK, - SYMTAB__BUILD_ID_CACHE, - SYMTAB__FEDORA_DEBUGINFO, - SYMTAB__UBUNTU_DEBUGINFO, - SYMTAB__BUILDID_DEBUGINFO, - SYMTAB__SYSTEM_PATH_DSO, - SYMTAB__GUEST_KMODULE, - SYMTAB__SYSTEM_PATH_KMODULE, - SYMTAB__NOT_FOUND, -}; - char dso__symtab_origin(const struct dso *dso); void dso__set_long_name(struct dso *dso, char *name); void dso__set_build_id(struct dso *dso, void *build_id); @@ -304,4 +304,6 @@ bool symbol_type__is_a(char symbol_type, enum map_type map_type); size_t machine__fprintf_vmlinux_path(struct machine *machine, FILE *fp); +int dso__binary_type_file(struct dso *dso, enum dso_binary_type type, + char *root_dir, char *file, size_t size); #endif /* __PERF_SYMBOL */ -- cgit From 949d160b6962c13fc071afefa22997780fcc94a5 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Sun, 22 Jul 2012 14:14:33 +0200 Subject: perf symbols: Add interface to read DSO image data Adding following interface for DSO object to allow reading of DSO image data: dso__data_fd - opens DSO and returns file descriptor Binary types are used to locate/open DSO in following order: DSO_BINARY_TYPE__BUILD_ID_CACHE DSO_BINARY_TYPE__SYSTEM_PATH_DSO In other word we first try to open DSO build-id path, and if that fails we try to open DSO system path. dso__data_read_offset - reads DSO data from specified offset dso__data_read_addr - reads DSO data from specified address/map. Signed-off-by: Jiri Olsa Cc: Arun Sharma Cc: Benjamin Redelings Cc: Corey Ashford Cc: Cyrill Gorcunov Cc: Frank Ch. Eigler Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Masami Hiramatsu Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Robert Richter Cc: Stephane Eranian Cc: Tom Zanussi Cc: Ulrich Drepper Link: http://lkml.kernel.org/r/1342959280-5361-11-git-send-email-jolsa@redhat.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/symbol.c | 109 +++++++++++++++++++++++++++++++++++++++++++++++ tools/perf/util/symbol.h | 8 ++++ 2 files changed, 117 insertions(+) (limited to 'tools') diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 60677a63bc7d..8131949d10f3 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -65,6 +65,14 @@ static enum dso_binary_type binary_type_symtab[] = { #define DSO_BINARY_TYPE__SYMTAB_CNT sizeof(binary_type_symtab) +static enum dso_binary_type binary_type_data[] = { + DSO_BINARY_TYPE__BUILD_ID_CACHE, + DSO_BINARY_TYPE__SYSTEM_PATH_DSO, + DSO_BINARY_TYPE__NOT_FOUND, +}; + +#define DSO_BINARY_TYPE__DATA_CNT sizeof(binary_type_data) + int dso__name_len(const struct dso *dso) { if (!dso) @@ -336,6 +344,7 @@ struct dso *dso__new(const char *name) for (i = 0; i < MAP__NR_TYPES; ++i) dso->symbols[i] = dso->symbol_names[i] = RB_ROOT; dso->symtab_type = DSO_BINARY_TYPE__NOT_FOUND; + dso->data_type = DSO_BINARY_TYPE__NOT_FOUND; dso->loaded = 0; dso->sorted_by_name = 0; dso->has_build_id = 0; @@ -2953,3 +2962,103 @@ struct map *dso__new_map(const char *name) return map; } + +static int open_dso(struct dso *dso, struct machine *machine) +{ + char *root_dir = (char *) ""; + char *name; + int fd; + + name = malloc(PATH_MAX); + if (!name) + return -ENOMEM; + + if (machine) + root_dir = machine->root_dir; + + if (dso__binary_type_file(dso, dso->data_type, + root_dir, name, PATH_MAX)) { + free(name); + return -EINVAL; + } + + fd = open(name, O_RDONLY); + free(name); + return fd; +} + +int dso__data_fd(struct dso *dso, struct machine *machine) +{ + int i = 0; + + if (dso->data_type != DSO_BINARY_TYPE__NOT_FOUND) + return open_dso(dso, machine); + + do { + int fd; + + dso->data_type = binary_type_data[i++]; + + fd = open_dso(dso, machine); + if (fd >= 0) + return fd; + + } while (dso->data_type != DSO_BINARY_TYPE__NOT_FOUND); + + return -EINVAL; +} + +static ssize_t dso_cache_read(struct dso *dso __used, u64 offset __used, + u8 *data __used, ssize_t size __used) +{ + return -EINVAL; +} + +static int dso_cache_add(struct dso *dso __used, u64 offset __used, + u8 *data __used, ssize_t size __used) +{ + return 0; +} + +static ssize_t read_dso_data(struct dso *dso, struct machine *machine, + u64 offset, u8 *data, ssize_t size) +{ + ssize_t rsize = -1; + int fd; + + fd = dso__data_fd(dso, machine); + if (fd < 0) + return -1; + + do { + if (-1 == lseek(fd, offset, SEEK_SET)) + break; + + rsize = read(fd, data, size); + if (-1 == rsize) + break; + + if (dso_cache_add(dso, offset, data, size)) + pr_err("Failed to add data int dso cache."); + + } while (0); + + close(fd); + return rsize; +} + +ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine, + u64 offset, u8 *data, ssize_t size) +{ + if (dso_cache_read(dso, offset, data, size)) + return read_dso_data(dso, machine, offset, data, size); + return 0; +} + +ssize_t dso__data_read_addr(struct dso *dso, struct map *map, + struct machine *machine, u64 addr, + u8 *data, ssize_t size) +{ + u64 offset = map->map_ip(map, addr); + return dso__data_read_offset(dso, machine, offset, data, size); +} diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index dc474f07bb2d..9b9ea00173af 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -189,6 +189,7 @@ struct dso { enum dso_kernel_type kernel; enum dso_swap_type needs_swap; enum dso_binary_type symtab_type; + enum dso_binary_type data_type; u8 adjust_symbols:1; u8 has_build_id:1; u8 hit:1; @@ -306,4 +307,11 @@ size_t machine__fprintf_vmlinux_path(struct machine *machine, FILE *fp); int dso__binary_type_file(struct dso *dso, enum dso_binary_type type, char *root_dir, char *file, size_t size); + +int dso__data_fd(struct dso *dso, struct machine *machine); +ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine, + u64 offset, u8 *data, ssize_t size); +ssize_t dso__data_read_addr(struct dso *dso, struct map *map, + struct machine *machine, u64 addr, + u8 *data, ssize_t size); #endif /* __PERF_SYMBOL */ -- cgit From 4dff624ae05bf3fb89f7653b3a55e7a5f1f1dadf Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Sun, 22 Jul 2012 14:14:39 +0200 Subject: perf symbols: Add dso data caching Adding dso data caching so we don't need to open/read/close, each time we want dso data. The DSO data caching affects following functions: dso__data_read_offset dso__data_read_addr Each DSO read tries to find the data (based on offset) inside the cache. If it's not present it fills the cache from file, and returns the data. If it is present, data are returned with no file read. Each data read is cached by reading cache page sized/aligned amount of DSO data. The cache page size is hardcoded to 4096. The cache is using RB tree with file offset as a sort key. Signed-off-by: Jiri Olsa Cc: Arun Sharma Cc: Benjamin Redelings Cc: Corey Ashford Cc: Cyrill Gorcunov Cc: Frank Ch. Eigler Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Masami Hiramatsu Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Robert Richter Cc: Stephane Eranian Cc: Tom Zanussi Cc: Ulrich Drepper Link: http://lkml.kernel.org/r/1342959280-5361-17-git-send-email-jolsa@redhat.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/symbol.c | 154 +++++++++++++++++++++++++++++++++++++++++------ tools/perf/util/symbol.h | 11 ++++ 2 files changed, 147 insertions(+), 18 deletions(-) (limited to 'tools') diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 8131949d10f3..fdad4eeeb429 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -29,6 +29,7 @@ #define NT_GNU_BUILD_ID 3 #endif +static void dso_cache__free(struct rb_root *root); static bool dso__build_id_equal(const struct dso *dso, u8 *build_id); static int elf_read_build_id(Elf *elf, void *bf, size_t size); static void dsos__add(struct list_head *head, struct dso *dso); @@ -343,6 +344,7 @@ struct dso *dso__new(const char *name) dso__set_short_name(dso, dso->name); for (i = 0; i < MAP__NR_TYPES; ++i) dso->symbols[i] = dso->symbol_names[i] = RB_ROOT; + dso->cache = RB_ROOT; dso->symtab_type = DSO_BINARY_TYPE__NOT_FOUND; dso->data_type = DSO_BINARY_TYPE__NOT_FOUND; dso->loaded = 0; @@ -378,6 +380,7 @@ void dso__delete(struct dso *dso) free((char *)dso->short_name); if (dso->lname_alloc) free(dso->long_name); + dso_cache__free(&dso->cache); free(dso); } @@ -3008,22 +3011,87 @@ int dso__data_fd(struct dso *dso, struct machine *machine) return -EINVAL; } -static ssize_t dso_cache_read(struct dso *dso __used, u64 offset __used, - u8 *data __used, ssize_t size __used) +static void +dso_cache__free(struct rb_root *root) { - return -EINVAL; + struct rb_node *next = rb_first(root); + + while (next) { + struct dso_cache *cache; + + cache = rb_entry(next, struct dso_cache, rb_node); + next = rb_next(&cache->rb_node); + rb_erase(&cache->rb_node, root); + free(cache); + } } -static int dso_cache_add(struct dso *dso __used, u64 offset __used, - u8 *data __used, ssize_t size __used) +static struct dso_cache* +dso_cache__find(struct rb_root *root, u64 offset) { - return 0; + struct rb_node **p = &root->rb_node; + struct rb_node *parent = NULL; + struct dso_cache *cache; + + while (*p != NULL) { + u64 end; + + parent = *p; + cache = rb_entry(parent, struct dso_cache, rb_node); + end = cache->offset + DSO__DATA_CACHE_SIZE; + + if (offset < cache->offset) + p = &(*p)->rb_left; + else if (offset >= end) + p = &(*p)->rb_right; + else + return cache; + } + return NULL; +} + +static void +dso_cache__insert(struct rb_root *root, struct dso_cache *new) +{ + struct rb_node **p = &root->rb_node; + struct rb_node *parent = NULL; + struct dso_cache *cache; + u64 offset = new->offset; + + while (*p != NULL) { + u64 end; + + parent = *p; + cache = rb_entry(parent, struct dso_cache, rb_node); + end = cache->offset + DSO__DATA_CACHE_SIZE; + + if (offset < cache->offset) + p = &(*p)->rb_left; + else if (offset >= end) + p = &(*p)->rb_right; + } + + rb_link_node(&new->rb_node, parent, p); + rb_insert_color(&new->rb_node, root); +} + +static ssize_t +dso_cache__memcpy(struct dso_cache *cache, u64 offset, + u8 *data, u64 size) +{ + u64 cache_offset = offset - cache->offset; + u64 cache_size = min(cache->size - cache_offset, size); + + memcpy(data, cache->data + cache_offset, cache_size); + return cache_size; } -static ssize_t read_dso_data(struct dso *dso, struct machine *machine, - u64 offset, u8 *data, ssize_t size) +static ssize_t +dso_cache__read(struct dso *dso, struct machine *machine, + u64 offset, u8 *data, ssize_t size) { - ssize_t rsize = -1; + struct dso_cache *cache; + ssize_t ret; int fd; fd = dso__data_fd(dso, machine); @@ -3031,28 +3099,78 @@ static ssize_t read_dso_data(struct dso *dso, struct machine *machine, return -1; do { - if (-1 == lseek(fd, offset, SEEK_SET)) + u64 cache_offset; + + ret = -ENOMEM; + + cache = zalloc(sizeof(*cache) + DSO__DATA_CACHE_SIZE); + if (!cache) break; - rsize = read(fd, data, size); - if (-1 == rsize) + cache_offset = offset & DSO__DATA_CACHE_MASK; + ret = -EINVAL; + + if (-1 == lseek(fd, cache_offset, SEEK_SET)) break; - if (dso_cache_add(dso, offset, data, size)) - pr_err("Failed to add data int dso cache."); + ret = read(fd, cache->data, DSO__DATA_CACHE_SIZE); + if (ret <= 0) + break; + + cache->offset = cache_offset; + cache->size = ret; + dso_cache__insert(&dso->cache, cache); + + ret = dso_cache__memcpy(cache, offset, data, size); } while (0); + if (ret <= 0) + free(cache); + close(fd); - return rsize; + return ret; +} + +static ssize_t dso_cache_read(struct dso *dso, struct machine *machine, + u64 offset, u8 *data, ssize_t size) +{ + struct dso_cache *cache; + + cache = dso_cache__find(&dso->cache, offset); + if (cache) + return dso_cache__memcpy(cache, offset, data, size); + else + return dso_cache__read(dso, machine, offset, data, size); } ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine, u64 offset, u8 *data, ssize_t size) { - if (dso_cache_read(dso, offset, data, size)) - return read_dso_data(dso, machine, offset, data, size); - return 0; + ssize_t r = 0; + u8 *p = data; + + do { + ssize_t ret; + + ret = dso_cache_read(dso, machine, offset, p, size); + if (ret < 0) + return ret; + + /* Reached EOF, return what we have. */ + if (!ret) + break; + + BUG_ON(ret > size); + + r += ret; + p += ret; + offset += ret; + size -= ret; + + } while (size); + + return r; } ssize_t dso__data_read_addr(struct dso *dso, struct map *map, diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index 9b9ea00173af..980d5f57373b 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -182,10 +182,21 @@ enum dso_swap_type { DSO_SWAP__YES, }; +#define DSO__DATA_CACHE_SIZE 4096 +#define DSO__DATA_CACHE_MASK ~(DSO__DATA_CACHE_SIZE - 1) + +struct dso_cache { + struct rb_node rb_node; + u64 offset; + u64 size; + char data[0]; +}; + struct dso { struct list_head node; struct rb_root symbols[MAP__NR_TYPES]; struct rb_root symbol_names[MAP__NR_TYPES]; + struct rb_root cache; enum dso_kernel_type kernel; enum dso_swap_type needs_swap; enum dso_binary_type symtab_type; -- cgit From f7add556534529ab18501ced98d7f3f2fc7f0621 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Sun, 22 Jul 2012 14:14:40 +0200 Subject: perf test: Add dso data caching tests Adding automated test for DSO data reading. Testing raw/cached reads from different file/cache locations. Signed-off-by: Jiri Olsa Cc: Arun Sharma Cc: Benjamin Redelings Cc: Corey Ashford Cc: Cyrill Gorcunov Cc: Frank Ch. Eigler Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Masami Hiramatsu Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Robert Richter Cc: Stephane Eranian Cc: Tom Zanussi Cc: Ulrich Drepper Link: http://lkml.kernel.org/r/1342959280-5361-18-git-send-email-jolsa@redhat.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Makefile | 1 + tools/perf/builtin-test.c | 4 ++ tools/perf/util/dso-test-data.c | 153 ++++++++++++++++++++++++++++++++++++++++ tools/perf/util/symbol.h | 1 + 4 files changed, 159 insertions(+) create mode 100644 tools/perf/util/dso-test-data.c (limited to 'tools') diff --git a/tools/perf/Makefile b/tools/perf/Makefile index 75d74e5db8d5..e8f057983ae4 100644 --- a/tools/perf/Makefile +++ b/tools/perf/Makefile @@ -354,6 +354,7 @@ LIB_OBJS += $(OUTPUT)util/usage.o LIB_OBJS += $(OUTPUT)util/wrapper.o LIB_OBJS += $(OUTPUT)util/sigchain.o LIB_OBJS += $(OUTPUT)util/symbol.o +LIB_OBJS += $(OUTPUT)util/dso-test-data.o LIB_OBJS += $(OUTPUT)util/color.o LIB_OBJS += $(OUTPUT)util/pager.o LIB_OBJS += $(OUTPUT)util/header.o diff --git a/tools/perf/builtin-test.c b/tools/perf/builtin-test.c index 5ce30305462b..d909eb74a0eb 100644 --- a/tools/perf/builtin-test.c +++ b/tools/perf/builtin-test.c @@ -1141,6 +1141,10 @@ static struct test { .desc = "Test perf pmu format parsing", .func = test__perf_pmu, }, + { + .desc = "Test dso data interface", + .func = dso__test_data, + }, { .func = NULL, }, diff --git a/tools/perf/util/dso-test-data.c b/tools/perf/util/dso-test-data.c new file mode 100644 index 000000000000..541cdc72c7df --- /dev/null +++ b/tools/perf/util/dso-test-data.c @@ -0,0 +1,153 @@ +#include "util.h" + +#include +#include +#include +#include +#include + +#include "symbol.h" + +#define TEST_ASSERT_VAL(text, cond) \ +do { \ + if (!(cond)) { \ + pr_debug("FAILED %s:%d %s\n", __FILE__, __LINE__, text); \ + return -1; \ + } \ +} while (0) + +static char *test_file(int size) +{ + static char buf_templ[] = "/tmp/test-XXXXXX"; + char *templ = buf_templ; + int fd, i; + unsigned char *buf; + + fd = mkostemp(templ, O_CREAT|O_WRONLY|O_TRUNC); + + buf = malloc(size); + if (!buf) { + close(fd); + return NULL; + } + + for (i = 0; i < size; i++) + buf[i] = (unsigned char) ((int) i % 10); + + if (size != write(fd, buf, size)) + templ = NULL; + + close(fd); + return templ; +} + +#define TEST_FILE_SIZE (DSO__DATA_CACHE_SIZE * 20) + +struct test_data_offset { + off_t offset; + u8 data[10]; + int size; +}; + +struct test_data_offset offsets[] = { + /* Fill first cache page. */ + { + .offset = 10, + .data = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9 }, + .size = 10, + }, + /* Read first cache page. */ + { + .offset = 10, + .data = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9 }, + .size = 10, + }, + /* Fill cache boundary pages. */ + { + .offset = DSO__DATA_CACHE_SIZE - DSO__DATA_CACHE_SIZE % 10, + .data = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9 }, + .size = 10, + }, + /* Read cache boundary pages. */ + { + .offset = DSO__DATA_CACHE_SIZE - DSO__DATA_CACHE_SIZE % 10, + .data = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9 }, + .size = 10, + }, + /* Fill final cache page. */ + { + .offset = TEST_FILE_SIZE - 10, + .data = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9 }, + .size = 10, + }, + /* Read final cache page. */ + { + .offset = TEST_FILE_SIZE - 10, + .data = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9 }, + .size = 10, + }, + /* Read final cache page. */ + { + .offset = TEST_FILE_SIZE - 3, + .data = { 7, 8, 9, 0, 0, 0, 0, 0, 0, 0 }, + .size = 3, + }, +}; + +int dso__test_data(void) +{ + struct machine machine; + struct dso *dso; + char *file = test_file(TEST_FILE_SIZE); + size_t i; + + TEST_ASSERT_VAL("No test file", file); + + memset(&machine, 0, sizeof(machine)); + + dso = dso__new((const char *)file); + + /* Basic 10 bytes tests. */ + for (i = 0; i < ARRAY_SIZE(offsets); i++) { + struct test_data_offset *data = &offsets[i]; + ssize_t size; + u8 buf[10]; + + memset(buf, 0, 10); + size = dso__data_read_offset(dso, &machine, data->offset, + buf, 10); + + TEST_ASSERT_VAL("Wrong size", size == data->size); + TEST_ASSERT_VAL("Wrong data", !memcmp(buf, data->data, 10)); + } + + /* Read cross multiple cache pages. */ + { + ssize_t size; + int c; + u8 *buf; + + buf = malloc(TEST_FILE_SIZE); + TEST_ASSERT_VAL("ENOMEM\n", buf); + + /* First iteration to fill caches, second one to read them. */ + for (c = 0; c < 2; c++) { + memset(buf, 0, TEST_FILE_SIZE); + size = dso__data_read_offset(dso, &machine, 10, + buf, TEST_FILE_SIZE); + + TEST_ASSERT_VAL("Wrong size", + size == (TEST_FILE_SIZE - 10)); + + for (i = 0; i < (size_t)size; i++) + TEST_ASSERT_VAL("Wrong data", + buf[i] == (i % 10)); + } + + free(buf); + } + + dso__delete(dso); + unlink(file); + return 0; +} diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index 980d5f57373b..1fe733a1e21f 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -325,4 +325,5 @@ ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine, ssize_t dso__data_read_addr(struct dso *dso, struct map *map, struct machine *machine, u64 addr, u8 *data, ssize_t size); +int dso__test_data(void); #endif /* __PERF_SYMBOL */ -- cgit From 4a841d650ea435c69e60675537f158a620697290 Mon Sep 17 00:00:00 2001 From: Jovi Zhang Date: Sun, 15 Jul 2012 03:03:10 +0800 Subject: perf tools: Make the breakpoint events sample period default to 1 There have one problem about hw_breakpoint perf event, as watched, the events reported to userspace is not correctly, sometime one trigger bp_event report several events, sometime bp_event cannot go through to user. The root cause is attr->freq is 1 passed to kernel defaultly in bp events, this make kernel calculate event period not as expect, make sample period to 1 will change attr->freq to 0, to fix this problem. This patch is similar with commit f92128 about tracepoint events: perf: Make the trace events sample period default to 1 Signed-off-by: Jovi Zhang Cc: Ingo Molnar Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/CACV3sbLF8taiCq_VYW-sgRJyupeMzg58C7ZXfMe3xZUiH_Mx6w@mail.gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/parse-events.c | 1 + 1 file changed, 1 insertion(+) (limited to 'tools') diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index a729945838f5..74a5af4d33ec 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -490,6 +490,7 @@ int parse_events_add_breakpoint(struct list_head **list, int *idx, attr.bp_len = HW_BREAKPOINT_LEN_4; attr.type = PERF_TYPE_BREAKPOINT; + attr.sample_period = 1; return add_event(list, idx, &attr, NULL); } -- cgit From 4cc49d4dc82a39a542a31c1f51ead08a46fd33f1 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Tue, 24 Jul 2012 00:06:54 +0300 Subject: perf tools: use XSI-complaint version of strerror_r() instead of GNU-specific MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Perf uses GNU-specific version of strerror_r(). The GNU-specific strerror_r() returns a pointer to a string containing the error message. This may be either a pointer to a string that the function stores in buf, or a pointer to some (immutable) static string (in which case buf is unused). In glibc-2.16 GNU version was marked with attribute warn_unused_result. It triggers few warnings in perf: util/target.c: In function ‘perf_target__strerror’: util/target.c:114:13: error: ignoring return value of ‘strerror_r’, declared with attribute warn_unused_result [-Werror=unused-result] ui/browsers/hists.c: In function ‘hist_browser__dump’: ui/browsers/hists.c:981:13: error: ignoring return value of ‘strerror_r’, declared with attribute warn_unused_result [-Werror=unused-result] They are bugs. Let's fix strerror_r() usage. Signed-off-by: Kirill A. Shutemov Acked-by: Ulrich Drepper Cc: Ingo Molnar Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Ulrich Drepper Link: http://lkml.kernel.org/r/20120723210654.GA25248@shutemov.name [ committer note: s/assert/BUG_ON/g ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/ui/browsers/hists.c | 4 ++-- tools/perf/util/target.c | 11 ++++++++++- 2 files changed, 12 insertions(+), 3 deletions(-) (limited to 'tools') diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index 482f0517b61e..413bd62eedb1 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -978,8 +978,8 @@ static int hist_browser__dump(struct hist_browser *browser) fp = fopen(filename, "w"); if (fp == NULL) { char bf[64]; - strerror_r(errno, bf, sizeof(bf)); - ui_helpline__fpush("Couldn't write to %s: %s", filename, bf); + const char *err = strerror_r(errno, bf, sizeof(bf)); + ui_helpline__fpush("Couldn't write to %s: %s", filename, err); return -1; } diff --git a/tools/perf/util/target.c b/tools/perf/util/target.c index 1064d5b148ad..3f59c496e64c 100644 --- a/tools/perf/util/target.c +++ b/tools/perf/util/target.c @@ -110,8 +110,17 @@ int perf_target__strerror(struct perf_target *target, int errnum, int idx; const char *msg; + BUG_ON(buflen > 0); + if (errnum >= 0) { - strerror_r(errnum, buf, buflen); + const char *err = strerror_r(errnum, buf, buflen); + + if (err != buf) { + size_t len = strlen(err); + char *c = mempcpy(buf, err, min(buflen - 1, len)); + *c = '\0'; + } + return 0; } -- cgit From 043d1a5c14e95212dbf48251051804ede1ed1862 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Tue, 24 Jul 2012 00:04:07 +0300 Subject: perf tools: Fix build error with bison 2.6 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Bison 2.6 started to generate parse_events_parse() declaration in header. In this case we have redundant redeclaration: util/parse-events.c:29:5: error: redundant redeclaration of ‘parse_events_parse’ [-Werror=redundant-decls] In file included from util/parse-events.c:14:0: util/parse-events-bison.h:99:5: note: previous declaration of ‘parse_events_parse’ was here cc1: all warnings being treated as errors Let's disable -Wredundant-decls for util/parse-events.c since it includes header we can't control. Signed-off-by: Kirill A. Shutemov Cc: Ingo Molnar Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20120723210407.GA25186@shutemov.name Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Makefile | 3 +++ 1 file changed, 3 insertions(+) (limited to 'tools') diff --git a/tools/perf/Makefile b/tools/perf/Makefile index e8f057983ae4..77f124fe57ad 100644 --- a/tools/perf/Makefile +++ b/tools/perf/Makefile @@ -804,6 +804,9 @@ $(OUTPUT)ui/browsers/map.o: ui/browsers/map.c $(OUTPUT)PERF-CFLAGS $(OUTPUT)util/rbtree.o: ../../lib/rbtree.c $(OUTPUT)PERF-CFLAGS $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $< +$(OUTPUT)util/parse-events.o: util/parse-events.c $(OUTPUT)PERF-CFLAGS + $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -Wno-redundant-decls $< + $(OUTPUT)util/scripting-engines/trace-event-perl.o: util/scripting-engines/trace-event-perl.c $(OUTPUT)PERF-CFLAGS $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow $< -- cgit From 52b5c0d485385d3c767d979496983ca2b6987f5c Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Fri, 6 Jul 2012 16:21:32 +0900 Subject: tools lib traceevent: Detect build environment changes Cross compiling perf requires setting ARCH and CROSS_COMPILE variables, but libtraceevent couldn't detect the changes so it ends up believing no recompiling is required. Thus the linker failed like: LINK perf ../lib/traceevent//libtraceevent.a: member ../lib/traceevent//libtraceevent.a(event-parse.o) in archive is not an object collect2: ld returned 1 exit status make: *** [perf] Error 1 This patch fixes this by adding TRACEEVENT-CFLAGS file like PERF-CFLAGS to track those changes. Signed-off-by: Namhyung Kim Cc: David Ahern Cc: Ingo Molnar Cc: Jiri Olsa Cc: Paul Mackerras Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1341559297-25725-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/lib/traceevent/Makefile | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) (limited to 'tools') diff --git a/tools/lib/traceevent/Makefile b/tools/lib/traceevent/Makefile index 46c2f6b7b123..14131cb0522d 100644 --- a/tools/lib/traceevent/Makefile +++ b/tools/lib/traceevent/Makefile @@ -207,7 +207,7 @@ libtraceevent.so: $(PEVENT_LIB_OBJS) libtraceevent.a: $(PEVENT_LIB_OBJS) $(Q)$(do_build_static_lib) -$(PEVENT_LIB_OBJS): %.o: $(src)/%.c +$(PEVENT_LIB_OBJS): %.o: $(src)/%.c TRACEEVENT-CFLAGS $(Q)$(do_fpic_compile) define make_version.h @@ -272,6 +272,16 @@ ifneq ($(dep_includes),) include $(dep_includes) endif +### Detect environment changes +TRACK_CFLAGS = $(subst ','\'',$(CFLAGS)):$(ARCH):$(CROSS_COMPILE) + +TRACEEVENT-CFLAGS: force + @FLAGS='$(TRACK_CFLAGS)'; \ + if test x"$$FLAGS" != x"`cat TRACEEVENT-CFLAGS 2>/dev/null`" ; then \ + echo 1>&2 " * new build flags or cross compiler"; \ + echo "$$FLAGS" >TRACEEVENT-CFLAGS; \ + fi + tags: force $(RM) tags find . -name '*.[ch]' | xargs ctags --extra=+f --c-kinds=+px \ @@ -297,7 +307,7 @@ install: install_lib clean: $(RM) *.o *~ $(TARGETS) *.a *.so $(VERSION_FILES) .*.d - $(RM) tags TAGS + $(RM) TRACEEVENT-CFLAGS tags TAGS endif # skip-makefile -- cgit From 52f18a2ff9b012a7efdbd520ca0dc0e118a8a837 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Fri, 6 Jul 2012 16:21:33 +0900 Subject: tools lib traceevent: Ignore TRACEEVENT-CFLAGS file The TRACEEVENT-CFLAGS file is used to detect any change on compiler flags. Just ignore it. Signed-off-by: Namhyung Kim Cc: David Ahern Cc: Ingo Molnar Cc: Jiri Olsa Cc: Paul Mackerras Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1341559297-25725-3-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/lib/traceevent/.gitignore | 1 + 1 file changed, 1 insertion(+) create mode 100644 tools/lib/traceevent/.gitignore (limited to 'tools') diff --git a/tools/lib/traceevent/.gitignore b/tools/lib/traceevent/.gitignore new file mode 100644 index 000000000000..35f56be5a4cd --- /dev/null +++ b/tools/lib/traceevent/.gitignore @@ -0,0 +1 @@ +TRACEEVENT-CFLAGS -- cgit From 8696329b7bcf32e69ad12d5975ad1497936d43ec Mon Sep 17 00:00:00 2001 From: Cody Schafer Date: Thu, 19 Jul 2012 20:05:25 -0700 Subject: perf annotate: Prevent overflow in size calculation A large enough symbol size causes an overflow in the size parameter to the histogram allocation, leading to a segfault in symbol__inc_addr_samples later on when this histogram is accessed. In the case of being called via perf-report, this returns back and gracefully ignores the sample, eventually ignoring the chained return value of perf_session_deliver_event in flush_sample_queue. Signed-off-by: Cody Schafer Acked-by: Namhyung Kim Cc: Ingo Molnar Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Sukadev Bhattiprolu Link: http://lkml.kernel.org/r/1342753525-4521-1-git-send-email-cody@linux.vnet.ibm.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/annotate.c | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 7d3641f6332c..3a282c0057d2 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -426,7 +426,18 @@ int symbol__alloc_hist(struct symbol *sym) { struct annotation *notes = symbol__annotation(sym); const size_t size = symbol__size(sym); - size_t sizeof_sym_hist = (sizeof(struct sym_hist) + size * sizeof(u64)); + size_t sizeof_sym_hist; + + /* Check for overflow when calculating sizeof_sym_hist */ + if (size > (SIZE_MAX - sizeof(struct sym_hist)) / sizeof(u64)) + return -1; + + sizeof_sym_hist = (sizeof(struct sym_hist) + size * sizeof(u64)); + + /* Check for overflow in zalloc argument */ + if (sizeof_sym_hist > (SIZE_MAX - sizeof(*notes->src)) + / symbol_conf.nr_events) + return -1; notes->src = zalloc(sizeof(*notes->src) + symbol_conf.nr_events * sizeof_sym_hist); if (notes->src == NULL) -- cgit