Merge branch 'perf/urgent' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

12 files changed, 161 insertions, 65 deletions

diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 6635fcd11ca5..3c1b8a632101 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -35,22 +35,6 @@ const char *perf_event__name(unsigned int id)
         return perf_event__names[id];
 }
 
-int perf_sample_size(u64 sample_type)
-{
-        u64 mask = sample_type & PERF_SAMPLE_MASK;
-        int size = 0;
-        int i;
-
-        for (i = 0; i < 64; i++) {
-                if (mask & (1ULL << i))
-                        size++;
-        }
-
-        size *= sizeof(u64);
-
-        return size;
-}
-
 static struct perf_sample synth_sample = {
         .pid       = -1,
         .tid       = -1,
@@ -553,9 +537,18 @@ static int perf_event__process_kernel_mmap(union perf_event *event,
                         goto out_problem;
 
                 perf_event__set_kernel_mmap_len(event, machine->vmlinux_maps);
-                perf_session__set_kallsyms_ref_reloc_sym(machine->vmlinux_maps,
-                                                         symbol_name,
-                                                         event->mmap.pgoff);
+
+                /*
+                 * Avoid using a zero address (kptr_restrict) for the ref reloc
+                 * symbol. Effectively having zero here means that at record
+                 * time /proc/sys/kernel/kptr_restrict was non zero.
+                 */
+                if (event->mmap.pgoff != 0) {
+                        perf_session__set_kallsyms_ref_reloc_sym(machine->vmlinux_maps,
+                                                                 symbol_name,
+                                                                 event->mmap.pgoff);
+                }
+
                 if (machine__is_default_guest(machine)) {
                         /*
                          * preload dso of guest kernel and modules
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index c08332871408..1d7f66488a88 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -82,8 +82,6 @@ struct perf_sample {
         struct ip_callchain *callchain;
 };
 
-int perf_sample_size(u64 sample_type);
-
 #define BUILD_ID_SIZE 20
 
 struct build_id_event {
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 50aa34879c33..b021ea9265c3 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -12,7 +12,6 @@
 #include "evlist.h"
 #include "evsel.h"
 #include "util.h"
-#include "debug.h"
 
 #include <sys/mman.h>
 
@@ -257,19 +256,15 @@ int perf_evlist__alloc_mmap(struct perf_evlist *evlist)
         return evlist->mmap != NULL ? 0 : -ENOMEM;
 }
 
-static int __perf_evlist__mmap(struct perf_evlist *evlist, struct perf_evsel *evsel,
+static int __perf_evlist__mmap(struct perf_evlist *evlist,
                                int idx, int prot, int mask, int fd)
 {
         evlist->mmap[idx].prev = 0;
         evlist->mmap[idx].mask = mask;
         evlist->mmap[idx].base = mmap(NULL, evlist->mmap_len, prot,
                                       MAP_SHARED, fd, 0);
-        if (evlist->mmap[idx].base == MAP_FAILED) {
-                if (evlist->cpus->map[idx] == -1 && evsel->attr.inherit)
-                        ui__warning("Inherit is not allowed on per-task "
-                                    "events using mmap.\n");
+        if (evlist->mmap[idx].base == MAP_FAILED)
                 return -1;
-        }
 
         perf_evlist__add_pollfd(evlist, fd);
         return 0;
@@ -289,7 +284,7 @@ static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist, int prot, int m
 
                                 if (output == -1) {
                                         output = fd;
-                                        if (__perf_evlist__mmap(evlist, evsel, cpu,
+                                        if (__perf_evlist__mmap(evlist, cpu,
                                                                 prot, mask, output) < 0)
                                                 goto out_unmap;
                                 } else {
@@ -329,7 +324,7 @@ static int perf_evlist__mmap_per_thread(struct perf_evlist *evlist, int prot, in
 
                         if (output == -1) {
                                 output = fd;
-                                if (__perf_evlist__mmap(evlist, evsel, thread,
+                                if (__perf_evlist__mmap(evlist, thread,
                                                         prot, mask, output) < 0)
                                         goto out_unmap;
                         } else {
@@ -460,33 +455,46 @@ int perf_evlist__set_filters(struct perf_evlist *evlist)
         return 0;
 }
 
-u64 perf_evlist__sample_type(struct perf_evlist *evlist)
+bool perf_evlist__valid_sample_type(const struct perf_evlist *evlist)
 {
-        struct perf_evsel *pos;
-        u64 type = 0;
-
-        list_for_each_entry(pos, &evlist->entries, node) {
-                if (!type)
-                        type = pos->attr.sample_type;
-                else if (type != pos->attr.sample_type)
-                        die("non matching sample_type");
+        struct perf_evsel *pos, *first;
+
+        pos = first = list_entry(evlist->entries.next, struct perf_evsel, node);
+
+        list_for_each_entry_continue(pos, &evlist->entries, node) {
+                if (first->attr.sample_type != pos->attr.sample_type)
+                        return false;
         }
 
-        return type;
+        return true;
 }
 
-bool perf_evlist__sample_id_all(const struct perf_evlist *evlist)
+u64 perf_evlist__sample_type(const struct perf_evlist *evlist)
+{
+        struct perf_evsel *first;
+
+        first = list_entry(evlist->entries.next, struct perf_evsel, node);
+        return first->attr.sample_type;
+}
+
+bool perf_evlist__valid_sample_id_all(const struct perf_evlist *evlist)
 {
-        bool value = false, first = true;
-        struct perf_evsel *pos;
-
-        list_for_each_entry(pos, &evlist->entries, node) {
-                if (first) {
-                        value = pos->attr.sample_id_all;
-                        first = false;
-                } else if (value != pos->attr.sample_id_all)
-                        die("non matching sample_id_all");
+        struct perf_evsel *pos, *first;
+
+        pos = first = list_entry(evlist->entries.next, struct perf_evsel, node);
+
+        list_for_each_entry_continue(pos, &evlist->entries, node) {
+                if (first->attr.sample_id_all != pos->attr.sample_id_all)
+                        return false;
         }
 
-        return value;
+        return true;
+}
+
+bool perf_evlist__sample_id_all(const struct perf_evlist *evlist)
+{
+        struct perf_evsel *first;
+
+        first = list_entry(evlist->entries.next, struct perf_evsel, node);
+        return first->attr.sample_id_all;
 }
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 0a1ef1f051f0..b2b862374f37 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -66,7 +66,9 @@ int perf_evlist__create_maps(struct perf_evlist *evlist, pid_t target_pid,
 void perf_evlist__delete_maps(struct perf_evlist *evlist);
 int perf_evlist__set_filters(struct perf_evlist *evlist);
 
-u64 perf_evlist__sample_type(struct perf_evlist *evlist);
-bool perf_evlist__sample_id_all(const struct perf_evlist *evlist);
+u64 perf_evlist__sample_type(const struct perf_evlist *evlist);
+bool perf_evlist__sample_id_all(const const struct perf_evlist *evlist);
 
+bool perf_evlist__valid_sample_type(const struct perf_evlist *evlist);
+bool perf_evlist__valid_sample_id_all(const struct perf_evlist *evlist);
 #endif /* __PERF_EVLIST_H */
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index ee0fe0dffa71..0239eb87b232 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -15,6 +15,22 @@
 
 #define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y))
 
+int __perf_evsel__sample_size(u64 sample_type)
+{
+        u64 mask = sample_type & PERF_SAMPLE_MASK;
+        int size = 0;
+        int i;
+
+        for (i = 0; i < 64; i++) {
+                if (mask & (1ULL << i))
+                        size++;
+        }
+
+        size *= sizeof(u64);
+
+        return size;
+}
+
 void perf_evsel__init(struct perf_evsel *evsel,
                       struct perf_event_attr *attr, int idx)
 {
@@ -35,7 +51,17 @@ struct perf_evsel *perf_evsel__new(struct perf_event_attr *attr, int idx)
 
 int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
 {
+        int cpu, thread;
         evsel->fd = xyarray__new(ncpus, nthreads, sizeof(int));
+
+        if (evsel->fd) {
+                for (cpu = 0; cpu < ncpus; cpu++) {
+                        for (thread = 0; thread < nthreads; thread++) {
+                                FD(evsel, cpu, thread) = -1;
+                        }
+                }
+        }
+
         return evsel->fd != NULL ? 0 : -ENOMEM;
 }
 
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index f79bb2c09a6c..7e9366e4490b 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -149,4 +149,11 @@ static inline int perf_evsel__read_scaled(struct perf_evsel *evsel,
         return __perf_evsel__read(evsel, ncpus, nthreads, true);
 }
 
+int __perf_evsel__sample_size(u64 sample_type);
+
+static inline int perf_evsel__sample_size(struct perf_evsel *evsel)
+{
+        return __perf_evsel__sample_size(evsel->attr.sample_type);
+}
+
 #endif /* __PERF_EVSEL_H */
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 0717bebc7649..afb0849fe530 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -193,9 +193,13 @@ int build_id_cache__add_s(const char *sbuild_id, const char *debugdir,
              *linkname = malloc(size), *targetname;
         int len, err = -1;
 
-        if (is_kallsyms)
+        if (is_kallsyms) {
+                if (symbol_conf.kptr_restrict) {
+                        pr_debug("Not caching a kptr_restrict'ed /proc/kallsyms\n");
+                        return 0;
+                }
                 realname = (char *)name;
-        else
+        } else
                 realname = realpath(name, NULL);
 
         if (realname == NULL || filename == NULL || linkname == NULL)
diff --git a/tools/perf/util/include/linux/const.h b/tools/perf/util/include/linux/const.h
new file mode 100644
index 000000000000..1b476c9ae649
--- /dev/null
+++ b/tools/perf/util/include/linux/const.h
@@ -0,0 +1 @@
+#include "../../../../include/linux/const.h"
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index 69436b3200a4..a9ac0504aabd 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -674,7 +674,7 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist,
         struct perf_evlist *evlist = &pevlist->evlist;
         union perf_event *event;
         int sample_id_all = 1, cpu;
-        static char *kwlist[] = {"sample_id_all", NULL, NULL};
+        static char *kwlist[] = {"cpu", "sample_id_all", NULL, NULL};
         int err;
 
         if (!PyArg_ParseTupleAndKeywords(args, kwargs, "i|i", kwlist,
@@ -692,16 +692,14 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist,
 
                 first = list_entry(evlist->entries.next, struct perf_evsel, node);
                 err = perf_event__parse_sample(event, first->attr.sample_type,
-                                               perf_sample_size(first->attr.sample_type),
+                                               perf_evsel__sample_size(first),
                                                sample_id_all, &pevent->sample);
-                if (err) {
-                        pr_err("Can't parse sample, err = %d\n", err);
-                        goto end;
-                }
-
+                if (err)
+                        return PyErr_Format(PyExc_OSError,
+                                            "perf: can't parse sample, err=%d", err);
                 return pyevent;
         }
-end:
+
         Py_INCREF(Py_None);
         return Py_None;
 }
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 64500fc78799..f5a8fbdd3f76 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -58,6 +58,16 @@ static int perf_session__open(struct perf_session *self, bool force)
                 goto out_close;
         }
 
+        if (!perf_evlist__valid_sample_type(self->evlist)) {
+                pr_err("non matching sample_type");
+                goto out_close;
+        }
+
+        if (!perf_evlist__valid_sample_id_all(self->evlist)) {
+                pr_err("non matching sample_id_all");
+                goto out_close;
+        }
+
         self->size = input_stat.st_size;
         return 0;
 
@@ -97,7 +107,7 @@ out:
 void perf_session__update_sample_type(struct perf_session *self)
 {
         self->sample_type = perf_evlist__sample_type(self->evlist);
-        self->sample_size = perf_sample_size(self->sample_type);
+        self->sample_size = __perf_evsel__sample_size(self->sample_type);
         self->sample_id_all = perf_evlist__sample_id_all(self->evlist);
         perf_session__id_header_size(self);
 }
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 516876dfbe52..eec196329fd9 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -676,9 +676,30 @@ discard_symbol:		rb_erase(&pos->rb_node, root);
         return count + moved;
 }
 
+static bool symbol__restricted_filename(const char *filename,
+                                        const char *restricted_filename)
+{
+        bool restricted = false;
+
+        if (symbol_conf.kptr_restrict) {
+                char *r = realpath(filename, NULL);
+
+                if (r != NULL) {
+                        restricted = strcmp(r, restricted_filename) == 0;
+                        free(r);
+                        return restricted;
+                }
+        }
+
+        return restricted;
+}
+
 int dso__load_kallsyms(struct dso *dso, const char *filename,
                        struct map *map, symbol_filter_t filter)
 {
+        if (symbol__restricted_filename(filename, "/proc/kallsyms"))
+                return -1;
+
         if (dso__load_all_kallsyms(dso, filename, map) < 0)
                 return -1;
 
@@ -1790,6 +1811,9 @@ static int machine__create_modules(struct machine *machine)
                 modules = path;
         }
 
+        if (symbol__restricted_filename(path, "/proc/modules"))
+                return -1;
+
         file = fopen(modules, "r");
         if (file == NULL)
                 return -1;
@@ -2239,6 +2263,9 @@ static u64 machine__get_kernel_start_addr(struct machine *machine)
                 }
         }
 
+        if (symbol__restricted_filename(filename, "/proc/kallsyms"))
+                return 0;
+
         if (kallsyms__parse(filename, &args, symbol__in_kernel) <= 0)
                 return 0;
 
@@ -2410,6 +2437,25 @@ static int setup_list(struct strlist **list, const char *list_str,
         return 0;
 }
 
+static bool symbol__read_kptr_restrict(void)
+{
+        bool value = false;
+
+        if (geteuid() != 0) {
+                FILE *fp = fopen("/proc/sys/kernel/kptr_restrict", "r");
+                if (fp != NULL) {
+                        char line[8];
+
+                        if (fgets(line, sizeof(line), fp) != NULL)
+                                value = atoi(line) != 0;
+
+                        fclose(fp);
+                }
+        }
+
+        return value;
+}
+
 int symbol__init(void)
 {
         const char *symfs;
@@ -2456,6 +2502,8 @@ int symbol__init(void)
         if (symfs != symbol_conf.symfs)
                 free((void *)symfs);
 
+        symbol_conf.kptr_restrict = symbol__read_kptr_restrict();
+
         symbol_conf.initialized = true;
         return 0;
 
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 242de0101a86..325ee36a9d29 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -75,7 +75,8 @@ struct symbol_conf {
                         use_callchain,
                         exclude_other,
                         show_cpu_utilization,
-                        initialized;
+                        initialized,
+                        kptr_restrict;
         const char      *vmlinux_name,
                         *kallsyms_name,
                         *source_prefix,