1 files changed, 225 insertions, 76 deletions

diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index f9f77bee0b1b..bbc746aa5716 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -18,6 +18,7 @@
 #include <unistd.h>
 
 #include "parse-events.h"
+#include "parse-options.h"
 
 #include <sys/mman.h>
 
@@ -49,6 +50,18 @@ struct perf_evlist *perf_evlist__new(void)
         return evlist;
 }
 
+struct perf_evlist *perf_evlist__new_default(void)
+{
+        struct perf_evlist *evlist = perf_evlist__new();
+
+        if (evlist && perf_evlist__add_default(evlist)) {
+                perf_evlist__delete(evlist);
+                evlist = NULL;
+        }
+
+        return evlist;
+}
+
 /**
  * perf_evlist__set_id_pos - set the positions of event ids.
  * @evlist: selected event list
@@ -104,6 +117,8 @@ void perf_evlist__delete(struct perf_evlist *evlist)
 void perf_evlist__add(struct perf_evlist *evlist, struct perf_evsel *entry)
 {
         list_add_tail(&entry->node, &evlist->entries);
+        entry->idx = evlist->nr_entries;
+
         if (!evlist->nr_entries++)
                 perf_evlist__set_id_pos(evlist);
 }
@@ -152,7 +167,7 @@ int perf_evlist__add_default(struct perf_evlist *evlist)
 
         event_attr_init(&attr);
 
-        evsel = perf_evsel__new(&attr, 0);
+        evsel = perf_evsel__new(&attr);
         if (evsel == NULL)
                 goto error;
 
@@ -177,7 +192,7 @@ static int perf_evlist__add_attrs(struct perf_evlist *evlist,
         size_t i;
 
         for (i = 0; i < nr_attrs; i++) {
-                evsel = perf_evsel__new(attrs + i, evlist->nr_entries + i);
+                evsel = perf_evsel__new_idx(attrs + i, evlist->nr_entries + i);
                 if (evsel == NULL)
                         goto out_delete_partial_list;
                 list_add_tail(&evsel->node, &head);
@@ -236,13 +251,12 @@ perf_evlist__find_tracepoint_by_name(struct perf_evlist *evlist,
 int perf_evlist__add_newtp(struct perf_evlist *evlist,
                            const char *sys, const char *name, void *handler)
 {
-        struct perf_evsel *evsel;
+        struct perf_evsel *evsel = perf_evsel__newtp(sys, name);
 
-        evsel = perf_evsel__newtp(sys, name, evlist->nr_entries);
         if (evsel == NULL)
                 return -1;
 
-        evsel->handler.func = handler;
+        evsel->handler = handler;
         perf_evlist__add(evlist, evsel);
         return 0;
 }
@@ -527,7 +541,7 @@ union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx)
                 if ((old & md->mask) + size != ((old + size) & md->mask)) {
                         unsigned int offset = old;
                         unsigned int len = min(sizeof(*event), size), cpy;
-                        void *dst = &md->event_copy;
+                        void *dst = md->event_copy;
 
                         do {
                                 cpy = min(md->mask + 1 - (offset & md->mask), len);
@@ -537,7 +551,7 @@ union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx)
                                 len -= cpy;
                         } while (len);
 
-                        event = &md->event_copy;
+                        event = (union perf_event *) md->event_copy;
                 }
 
                 old += size;
@@ -545,12 +559,19 @@ union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx)
 
         md->prev = old;
 
-        if (!evlist->overwrite)
-                perf_mmap__write_tail(md, old);
-
         return event;
 }
 
+void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx)
+{
+        if (!evlist->overwrite) {
+                struct perf_mmap *md = &evlist->mmap[idx];
+                unsigned int old = md->prev;
+
+                perf_mmap__write_tail(md, old);
+        }
+}
+
 static void __perf_evlist__munmap(struct perf_evlist *evlist, int idx)
 {
         if (evlist->mmap[idx].base != NULL) {
@@ -587,6 +608,8 @@ static int __perf_evlist__mmap(struct perf_evlist *evlist,
         evlist->mmap[idx].base = mmap(NULL, evlist->mmap_len, prot,
                                       MAP_SHARED, fd, 0);
         if (evlist->mmap[idx].base == MAP_FAILED) {
+                pr_debug2("failed to mmap perf event ring buffer, error %d\n",
+                          errno);
                 evlist->mmap[idx].base = NULL;
                 return -1;
         }
@@ -595,9 +618,36 @@ static int __perf_evlist__mmap(struct perf_evlist *evlist,
         return 0;
 }
 
-static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist, int prot, int mask)
+static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx,
+                                       int prot, int mask, int cpu, int thread,
+                                       int *output)
 {
         struct perf_evsel *evsel;
+
+        list_for_each_entry(evsel, &evlist->entries, node) {
+                int fd = FD(evsel, cpu, thread);
+
+                if (*output == -1) {
+                        *output = fd;
+                        if (__perf_evlist__mmap(evlist, idx, prot, mask,
+                                                *output) < 0)
+                                return -1;
+                } else {
+                        if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT, *output) != 0)
+                                return -1;
+                }
+
+                if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
+                    perf_evlist__id_add_fd(evlist, evsel, cpu, thread, fd) < 0)
+                        return -1;
+        }
+
+        return 0;
+}
+
+static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist, int prot,
+                                     int mask)
+{
         int cpu, thread;
         int nr_cpus = cpu_map__nr(evlist->cpus);
         int nr_threads = thread_map__nr(evlist->threads);
@@ -607,23 +657,9 @@ static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist, int prot, int m
                 int output = -1;
 
                 for (thread = 0; thread < nr_threads; thread++) {
-                        list_for_each_entry(evsel, &evlist->entries, node) {
-                                int fd = FD(evsel, cpu, thread);
-
-                                if (output == -1) {
-                                        output = fd;
-                                        if (__perf_evlist__mmap(evlist, cpu,
-                                                                prot, mask, output) < 0)
-                                                goto out_unmap;
-                                } else {
-                                        if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT, output) != 0)
-                                                goto out_unmap;
-                                }
-
-                                if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
-                                    perf_evlist__id_add_fd(evlist, evsel, cpu, thread, fd) < 0)
-                                        goto out_unmap;
-                        }
+                        if (perf_evlist__mmap_per_evsel(evlist, cpu, prot, mask,
+                                                        cpu, thread, &output))
+                                goto out_unmap;
                 }
         }
 
@@ -635,9 +671,9 @@ out_unmap:
         return -1;
 }
 
-static int perf_evlist__mmap_per_thread(struct perf_evlist *evlist, int prot, int mask)
+static int perf_evlist__mmap_per_thread(struct perf_evlist *evlist, int prot,
+                                        int mask)
 {
-        struct perf_evsel *evsel;
         int thread;
         int nr_threads = thread_map__nr(evlist->threads);
 
@@ -645,23 +681,9 @@ static int perf_evlist__mmap_per_thread(struct perf_evlist *evlist, int prot, in
         for (thread = 0; thread < nr_threads; thread++) {
                 int output = -1;
 
-                list_for_each_entry(evsel, &evlist->entries, node) {
-                        int fd = FD(evsel, 0, thread);
-
-                        if (output == -1) {
-                                output = fd;
-                                if (__perf_evlist__mmap(evlist, thread,
-                                                        prot, mask, output) < 0)
-                                        goto out_unmap;
-                        } else {
-                                if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT, output) != 0)
-                                        goto out_unmap;
-                        }
-
-                        if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
-                            perf_evlist__id_add_fd(evlist, evsel, 0, thread, fd) < 0)
-                                goto out_unmap;
-                }
+                if (perf_evlist__mmap_per_evsel(evlist, thread, prot, mask, 0,
+                                                thread, &output))
+                        goto out_unmap;
         }
 
         return 0;
@@ -672,20 +694,90 @@ out_unmap:
         return -1;
 }
 
-/** perf_evlist__mmap - Create per cpu maps to receive events
- *
- * @evlist - list of events
- * @pages - map length in pages
- * @overwrite - overwrite older events?
- *
- * If overwrite is false the user needs to signal event consuption using:
- *
- *      struct perf_mmap *m = &evlist->mmap[cpu];
- *      unsigned int head = perf_mmap__read_head(m);
+static size_t perf_evlist__mmap_size(unsigned long pages)
+{
+        /* 512 kiB: default amount of unprivileged mlocked memory */
+        if (pages == UINT_MAX)
+                pages = (512 * 1024) / page_size;
+        else if (!is_power_of_2(pages))
+                return 0;
+
+        return (pages + 1) * page_size;
+}
+
+static long parse_pages_arg(const char *str, unsigned long min,
+                            unsigned long max)
+{
+        unsigned long pages, val;
+        static struct parse_tag tags[] = {
+                { .tag  = 'B', .mult = 1       },
+                { .tag  = 'K', .mult = 1 << 10 },
+                { .tag  = 'M', .mult = 1 << 20 },
+                { .tag  = 'G', .mult = 1 << 30 },
+                { .tag  = 0 },
+        };
+
+        if (str == NULL)
+                return -EINVAL;
+
+        val = parse_tag_value(str, tags);
+        if (val != (unsigned long) -1) {
+                /* we got file size value */
+                pages = PERF_ALIGN(val, page_size) / page_size;
+        } else {
+                /* we got pages count value */
+                char *eptr;
+                pages = strtoul(str, &eptr, 10);
+                if (*eptr != '\0')
+                        return -EINVAL;
+        }
+
+        if ((pages == 0) && (min == 0)) {
+                /* leave number of pages at 0 */
+        } else if (pages < (1UL << 31) && !is_power_of_2(pages)) {
+                /* round pages up to next power of 2 */
+                pages = next_pow2(pages);
+                pr_info("rounding mmap pages size to %lu bytes (%lu pages)\n",
+                        pages * page_size, pages);
+        }
+
+        if (pages > max)
+                return -EINVAL;
+
+        return pages;
+}
+
+int perf_evlist__parse_mmap_pages(const struct option *opt, const char *str,
+                                  int unset __maybe_unused)
+{
+        unsigned int *mmap_pages = opt->value;
+        unsigned long max = UINT_MAX;
+        long pages;
+
+        if (max < SIZE_MAX / page_size)
+                max = SIZE_MAX / page_size;
+
+        pages = parse_pages_arg(str, 1, max);
+        if (pages < 0) {
+                pr_err("Invalid argument for --mmap_pages/-m\n");
+                return -1;
+        }
+
+        *mmap_pages = pages;
+        return 0;
+}
+
+/**
+ * perf_evlist__mmap - Create mmaps to receive events.
+ * @evlist: list of events
+ * @pages: map length in pages
+ * @overwrite: overwrite older events?
  *
- *      perf_mmap__write_tail(m, head)
+ * If @overwrite is %false the user needs to signal event consumption using
+ * perf_mmap__write_tail().  Using perf_evlist__mmap_read() does this
+ * automatically.
  *
- * Using perf_evlist__read_on_cpu does this automatically.
+ * Return: %0 on success, negative error code otherwise.
  */
 int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
                       bool overwrite)
@@ -695,14 +787,6 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
         const struct thread_map *threads = evlist->threads;
         int prot = PROT_READ | (overwrite ? 0 : PROT_WRITE), mask;
 
-        /* 512 kiB: default amount of unprivileged mlocked memory */
-        if (pages == UINT_MAX)
-                pages = (512 * 1024) / page_size;
-        else if (!is_power_of_2(pages))
-                return -EINVAL;
-
-        mask = pages * page_size - 1;
-
         if (evlist->mmap == NULL && perf_evlist__alloc_mmap(evlist) < 0)
                 return -ENOMEM;
 
@@ -710,7 +794,9 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
                 return -ENOMEM;
 
         evlist->overwrite = overwrite;
-        evlist->mmap_len = (pages + 1) * page_size;
+        evlist->mmap_len = perf_evlist__mmap_size(pages);
+        pr_debug("mmap size %zuB\n", evlist->mmap_len);
+        mask = evlist->mmap_len - page_size - 1;
 
         list_for_each_entry(evsel, &evlist->entries, node) {
                 if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
@@ -725,8 +811,7 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
         return perf_evlist__mmap_per_cpu(evlist, prot, mask);
 }
 
-int perf_evlist__create_maps(struct perf_evlist *evlist,
-                             struct perf_target *target)
+int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target)
 {
         evlist->threads = thread_map__new_str(target->pid, target->tid,
                                               target->uid);
@@ -734,9 +819,11 @@ int perf_evlist__create_maps(struct perf_evlist *evlist,
         if (evlist->threads == NULL)
                 return -1;
 
-        if (perf_target__has_task(target))
+        if (target->force_per_cpu)
+                evlist->cpus = cpu_map__new(target->cpu_list);
+        else if (target__has_task(target))
                 evlist->cpus = cpu_map__dummy_new();
-        else if (!perf_target__has_cpu(target) && !target->uses_mmap)
+        else if (!target__has_cpu(target) && !target->uses_mmap)
                 evlist->cpus = cpu_map__dummy_new();
         else
                 evlist->cpus = cpu_map__new(target->cpu_list);
@@ -945,8 +1032,7 @@ out_err:
         return err;
 }
 
-int perf_evlist__prepare_workload(struct perf_evlist *evlist,
-                                  struct perf_target *target,
+int perf_evlist__prepare_workload(struct perf_evlist *evlist, struct target *target,
                                   const char *argv[], bool pipe_output,
                                   bool want_signal)
 {
@@ -998,7 +1084,7 @@ int perf_evlist__prepare_workload(struct perf_evlist *evlist,
                 exit(-1);
         }
 
-        if (perf_target__none(target))
+        if (target__none(target))
                 evlist->threads->map[0] = evlist->workload.pid;
 
         close(child_ready_pipe[1]);
@@ -1064,5 +1150,68 @@ size_t perf_evlist__fprintf(struct perf_evlist *evlist, FILE *fp)
                                    perf_evsel__name(evsel));
         }
 
-        return printed + fprintf(fp, "\n");;
+        return printed + fprintf(fp, "\n");
+}
+
+int perf_evlist__strerror_tp(struct perf_evlist *evlist __maybe_unused,
+                             int err, char *buf, size_t size)
+{
+        char sbuf[128];
+
+        switch (err) {
+        case ENOENT:
+                scnprintf(buf, size, "%s",
+                          "Error:\tUnable to find debugfs\n"
+                          "Hint:\tWas your kernel was compiled with debugfs support?\n"
+                          "Hint:\tIs the debugfs filesystem mounted?\n"
+                          "Hint:\tTry 'sudo mount -t debugfs nodev /sys/kernel/debug'");
+                break;
+        case EACCES:
+                scnprintf(buf, size,
+                          "Error:\tNo permissions to read %s/tracing/events/raw_syscalls\n"
+                          "Hint:\tTry 'sudo mount -o remount,mode=755 %s'\n",
+                          debugfs_mountpoint, debugfs_mountpoint);
+                break;
+        default:
+                scnprintf(buf, size, "%s", strerror_r(err, sbuf, sizeof(sbuf)));
+                break;
+        }
+
+        return 0;
+}
+
+int perf_evlist__strerror_open(struct perf_evlist *evlist __maybe_unused,
+                               int err, char *buf, size_t size)
+{
+        int printed, value;
+        char sbuf[128], *emsg = strerror_r(err, sbuf, sizeof(sbuf));
+
+        switch (err) {
+        case EACCES:
+        case EPERM:
+                printed = scnprintf(buf, size,
+                                    "Error:\t%s.\n"
+                                    "Hint:\tCheck /proc/sys/kernel/perf_event_paranoid setting.", emsg);
+
+                if (filename__read_int("/proc/sys/kernel/perf_event_paranoid", &value))
+                        break;
+
+                printed += scnprintf(buf + printed, size - printed, "\nHint:\t");
+
+                if (value >= 2) {
+                        printed += scnprintf(buf + printed, size - printed,
+                                             "For your workloads it needs to be <= 1\nHint:\t");
+                }
+                printed += scnprintf(buf + printed, size - printed,
+                                     "For system wide tracing it needs to be set to -1");
+
+                printed += scnprintf(buf + printed, size - printed,
+                                    ".\nHint:\tThe current value is %d.", value);
+                break;
+        default:
+                scnprintf(buf, size, "%s", emsg);
+                break;
+        }
+
+        return 0;
 }