Merge tag 'perf-core-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core

perf/core improvements and fixes:

 - Preparatory patches to use hw events in PMU syntax, from Jiri Olsa

 - Remaining backport of trace-cmd's libparseevent, from Namhyung Kim

 - Fix libtraceevent 'clean' make target, from Namhyung Kim

 - Teach ctags about libtraceevent error codes, from Namhyung Kim

 - Fix libtraceevent dependency files usage, from Namhyung Kim

 - Support hex number pretty printing in libtraceevent, fixing
   kvm output, from Namhyung Kim

 - Kill some die() usage in libtraceevent, from Namhyung Kim

 - Improve support for hw breakpoints parsing/pretty printing/testing,
  from Jiri Olsa

 - Clarify perf bench option naming, from Hitoshi Mitake

 - Look for ".note" ELF notes too, used in the kernel vdso, from Jiri Olsa

 - Fix internal PMU list usage, removing leak, from Robert Richter

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

13 files changed, 357 insertions, 177 deletions

diff --git a/tools/perf/Documentation/perf-bench.txt b/tools/perf/Documentation/perf-bench.txt
index f3c716a4cad..7065cd6fbdf 100644
--- a/tools/perf/Documentation/perf-bench.txt
+++ b/tools/perf/Documentation/perf-bench.txt
@@ -144,7 +144,7 @@ On x86-64, x86-64-unrolled, x86-64-movsq and x86-64-movsb are supported.
 Repeat memcpy invocation this number of times.
 
 -c::
---clock::
+--cycle::
 Use perf's cpu-cycles event instead of gettimeofday syscall.
 
 -o::
@@ -176,7 +176,7 @@ On x86-64, x86-64-unrolled, x86-64-stosq and x86-64-stosb are supported.
 Repeat memset invocation this number of times.
 
 -c::
---clock::
+--cycle::
 Use perf's cpu-cycles event instead of gettimeofday syscall.
 
 -o::
diff --git a/tools/perf/bench/mem-memcpy.c b/tools/perf/bench/mem-memcpy.c
index d990365cafa..02dad5d3359 100644
--- a/tools/perf/bench/mem-memcpy.c
+++ b/tools/perf/bench/mem-memcpy.c
@@ -24,8 +24,8 @@
 static const char       *length_str     = "1MB";
 static const char       *routine        = "default";
 static int              iterations      = 1;
-static bool             use_clock;
-static int              clock_fd;
+static bool             use_cycle;
+static int              cycle_fd;
 static bool             only_prefault;
 static bool             no_prefault;
 
@@ -37,7 +37,7 @@ static const struct option options[] = {
                     "Specify routine to copy"),
         OPT_INTEGER('i', "iterations", &iterations,
                     "repeat memcpy() invocation this number of times"),
-        OPT_BOOLEAN('c', "clock", &use_clock,
+        OPT_BOOLEAN('c', "cycle", &use_cycle,
                     "Use cycles event instead of gettimeofday() for measuring"),
         OPT_BOOLEAN('o', "only-prefault", &only_prefault,
                     "Show only the result with page faults before memcpy()"),
@@ -76,27 +76,27 @@ static const char * const bench_mem_memcpy_usage[] = {
         NULL
 };
 
-static struct perf_event_attr clock_attr = {
+static struct perf_event_attr cycle_attr = {
         .type           = PERF_TYPE_HARDWARE,
         .config         = PERF_COUNT_HW_CPU_CYCLES
 };
 
-static void init_clock(void)
+static void init_cycle(void)
 {
-        clock_fd = sys_perf_event_open(&clock_attr, getpid(), -1, -1, 0);
+        cycle_fd = sys_perf_event_open(&cycle_attr, getpid(), -1, -1, 0);
 
-        if (clock_fd < 0 && errno == ENOSYS)
+        if (cycle_fd < 0 && errno == ENOSYS)
                 die("No CONFIG_PERF_EVENTS=y kernel support configured?\n");
         else
-                BUG_ON(clock_fd < 0);
+                BUG_ON(cycle_fd < 0);
 }
 
-static u64 get_clock(void)
+static u64 get_cycle(void)
 {
         int ret;
         u64 clk;
 
-        ret = read(clock_fd, &clk, sizeof(u64));
+        ret = read(cycle_fd, &clk, sizeof(u64));
         BUG_ON(ret != sizeof(u64));
 
         return clk;
@@ -119,9 +119,9 @@ static void alloc_mem(void **dst, void **src, size_t length)
                 die("memory allocation failed - maybe length is too large?\n");
 }
 
-static u64 do_memcpy_clock(memcpy_t fn, size_t len, bool prefault)
+static u64 do_memcpy_cycle(memcpy_t fn, size_t len, bool prefault)
 {
-        u64 clock_start = 0ULL, clock_end = 0ULL;
+        u64 cycle_start = 0ULL, cycle_end = 0ULL;
         void *src = NULL, *dst = NULL;
         int i;
 
@@ -130,14 +130,14 @@ static u64 do_memcpy_clock(memcpy_t fn, size_t len, bool prefault)
         if (prefault)
                 fn(dst, src, len);
 
-        clock_start = get_clock();
+        cycle_start = get_cycle();
         for (i = 0; i < iterations; ++i)
                 fn(dst, src, len);
-        clock_end = get_clock();
+        cycle_end = get_cycle();
 
         free(src);
         free(dst);
-        return clock_end - clock_start;
+        return cycle_end - cycle_start;
 }
 
 static double do_memcpy_gettimeofday(memcpy_t fn, size_t len, bool prefault)
@@ -182,17 +182,17 @@ int bench_mem_memcpy(int argc, const char **argv,
         int i;
         size_t len;
         double result_bps[2];
-        u64 result_clock[2];
+        u64 result_cycle[2];
 
         argc = parse_options(argc, argv, options,
                              bench_mem_memcpy_usage, 0);
 
-        if (use_clock)
-                init_clock();
+        if (use_cycle)
+                init_cycle();
 
         len = (size_t)perf_atoll((char *)length_str);
 
-        result_clock[0] = result_clock[1] = 0ULL;
+        result_cycle[0] = result_cycle[1] = 0ULL;
         result_bps[0] = result_bps[1] = 0.0;
 
         if ((s64)len <= 0) {
@@ -223,11 +223,11 @@ int bench_mem_memcpy(int argc, const char **argv,
 
         if (!only_prefault && !no_prefault) {
                 /* show both of results */
-                if (use_clock) {
-                        result_clock[0] =
-                                do_memcpy_clock(routines[i].fn, len, false);
-                        result_clock[1] =
-                                do_memcpy_clock(routines[i].fn, len, true);
+                if (use_cycle) {
+                        result_cycle[0] =
+                                do_memcpy_cycle(routines[i].fn, len, false);
+                        result_cycle[1] =
+                                do_memcpy_cycle(routines[i].fn, len, true);
                 } else {
                         result_bps[0] =
                                 do_memcpy_gettimeofday(routines[i].fn,
@@ -237,9 +237,9 @@ int bench_mem_memcpy(int argc, const char **argv,
                                                 len, true);
                 }
         } else {
-                if (use_clock) {
-                        result_clock[pf] =
-                                do_memcpy_clock(routines[i].fn,
+                if (use_cycle) {
+                        result_cycle[pf] =
+                                do_memcpy_cycle(routines[i].fn,
                                                 len, only_prefault);
                 } else {
                         result_bps[pf] =
@@ -251,12 +251,12 @@ int bench_mem_memcpy(int argc, const char **argv,
         switch (bench_format) {
         case BENCH_FORMAT_DEFAULT:
                 if (!only_prefault && !no_prefault) {
-                        if (use_clock) {
-                                printf(" %14lf Clock/Byte\n",
-                                        (double)result_clock[0]
+                        if (use_cycle) {
+                                printf(" %14lf Cycle/Byte\n",
+                                        (double)result_cycle[0]
                                         / (double)len);
-                                printf(" %14lf Clock/Byte (with prefault)\n",
-                                        (double)result_clock[1]
+                                printf(" %14lf Cycle/Byte (with prefault)\n",
+                                        (double)result_cycle[1]
                                         / (double)len);
                         } else {
                                 print_bps(result_bps[0]);
@@ -265,9 +265,9 @@ int bench_mem_memcpy(int argc, const char **argv,
                                 printf(" (with prefault)\n");
                         }
                 } else {
-                        if (use_clock) {
-                                printf(" %14lf Clock/Byte",
-                                        (double)result_clock[pf]
+                        if (use_cycle) {
+                                printf(" %14lf Cycle/Byte",
+                                        (double)result_cycle[pf]
                                         / (double)len);
                         } else
                                 print_bps(result_bps[pf]);
@@ -277,17 +277,17 @@ int bench_mem_memcpy(int argc, const char **argv,
                 break;
         case BENCH_FORMAT_SIMPLE:
                 if (!only_prefault && !no_prefault) {
-                        if (use_clock) {
+                        if (use_cycle) {
                                 printf("%lf %lf\n",
-                                        (double)result_clock[0] / (double)len,
-                                        (double)result_clock[1] / (double)len);
+                                        (double)result_cycle[0] / (double)len,
+                                        (double)result_cycle[1] / (double)len);
                         } else {
                                 printf("%lf %lf\n",
                                         result_bps[0], result_bps[1]);
                         }
                 } else {
-                        if (use_clock) {
-                                printf("%lf\n", (double)result_clock[pf]
+                        if (use_cycle) {
+                                printf("%lf\n", (double)result_cycle[pf]
                                         / (double)len);
                         } else
                                 printf("%lf\n", result_bps[pf]);
diff --git a/tools/perf/bench/mem-memset.c b/tools/perf/bench/mem-memset.c
index bf0d5f55201..350cc955726 100644
--- a/tools/perf/bench/mem-memset.c
+++ b/tools/perf/bench/mem-memset.c
@@ -24,8 +24,8 @@
 static const char       *length_str     = "1MB";
 static const char       *routine        = "default";
 static int              iterations      = 1;
-static bool             use_clock;
-static int              clock_fd;
+static bool             use_cycle;
+static int              cycle_fd;
 static bool             only_prefault;
 static bool             no_prefault;
 
@@ -37,7 +37,7 @@ static const struct option options[] = {
                     "Specify routine to set"),
         OPT_INTEGER('i', "iterations", &iterations,
                     "repeat memset() invocation this number of times"),
-        OPT_BOOLEAN('c', "clock", &use_clock,
+        OPT_BOOLEAN('c', "cycle", &use_cycle,
                     "Use cycles event instead of gettimeofday() for measuring"),
         OPT_BOOLEAN('o', "only-prefault", &only_prefault,
                     "Show only the result with page faults before memset()"),
@@ -76,27 +76,27 @@ static const char * const bench_mem_memset_usage[] = {
         NULL
 };
 
-static struct perf_event_attr clock_attr = {
+static struct perf_event_attr cycle_attr = {
         .type           = PERF_TYPE_HARDWARE,
         .config         = PERF_COUNT_HW_CPU_CYCLES
 };
 
-static void init_clock(void)
+static void init_cycle(void)
 {
-        clock_fd = sys_perf_event_open(&clock_attr, getpid(), -1, -1, 0);
+        cycle_fd = sys_perf_event_open(&cycle_attr, getpid(), -1, -1, 0);
 
-        if (clock_fd < 0 && errno == ENOSYS)
+        if (cycle_fd < 0 && errno == ENOSYS)
                 die("No CONFIG_PERF_EVENTS=y kernel support configured?\n");
         else
-                BUG_ON(clock_fd < 0);
+                BUG_ON(cycle_fd < 0);
 }
 
-static u64 get_clock(void)
+static u64 get_cycle(void)
 {
         int ret;
         u64 clk;
 
-        ret = read(clock_fd, &clk, sizeof(u64));
+        ret = read(cycle_fd, &clk, sizeof(u64));
         BUG_ON(ret != sizeof(u64));
 
         return clk;
@@ -115,9 +115,9 @@ static void alloc_mem(void **dst, size_t length)
                 die("memory allocation failed - maybe length is too large?\n");
 }
 
-static u64 do_memset_clock(memset_t fn, size_t len, bool prefault)
+static u64 do_memset_cycle(memset_t fn, size_t len, bool prefault)
 {
-        u64 clock_start = 0ULL, clock_end = 0ULL;
+        u64 cycle_start = 0ULL, cycle_end = 0ULL;
         void *dst = NULL;
         int i;
 
@@ -126,13 +126,13 @@ static u64 do_memset_clock(memset_t fn, size_t len, bool prefault)
         if (prefault)
                 fn(dst, -1, len);
 
-        clock_start = get_clock();
+        cycle_start = get_cycle();
         for (i = 0; i < iterations; ++i)
                 fn(dst, i, len);
-        clock_end = get_clock();
+        cycle_end = get_cycle();
 
         free(dst);
-        return clock_end - clock_start;
+        return cycle_end - cycle_start;
 }
 
 static double do_memset_gettimeofday(memset_t fn, size_t len, bool prefault)
@@ -176,17 +176,17 @@ int bench_mem_memset(int argc, const char **argv,
         int i;
         size_t len;
         double result_bps[2];
-        u64 result_clock[2];
+        u64 result_cycle[2];
 
         argc = parse_options(argc, argv, options,
                              bench_mem_memset_usage, 0);
 
-        if (use_clock)
-                init_clock();
+        if (use_cycle)
+                init_cycle();
 
         len = (size_t)perf_atoll((char *)length_str);
 
-        result_clock[0] = result_clock[1] = 0ULL;
+        result_cycle[0] = result_cycle[1] = 0ULL;
         result_bps[0] = result_bps[1] = 0.0;
 
         if ((s64)len <= 0) {
@@ -217,11 +217,11 @@ int bench_mem_memset(int argc, const char **argv,
 
         if (!only_prefault && !no_prefault) {
                 /* show both of results */
-                if (use_clock) {
-                        result_clock[0] =
-                                do_memset_clock(routines[i].fn, len, false);
-                        result_clock[1] =
-                                do_memset_clock(routines[i].fn, len, true);
+                if (use_cycle) {
+                        result_cycle[0] =
+                                do_memset_cycle(routines[i].fn, len, false);
+                        result_cycle[1] =
+                                do_memset_cycle(routines[i].fn, len, true);
                 } else {
                         result_bps[0] =
                                 do_memset_gettimeofday(routines[i].fn,
@@ -231,9 +231,9 @@ int bench_mem_memset(int argc, const char **argv,
                                                 len, true);
                 }
         } else {
-                if (use_clock) {
-                        result_clock[pf] =
-                                do_memset_clock(routines[i].fn,
+                if (use_cycle) {
+                        result_cycle[pf] =
+                                do_memset_cycle(routines[i].fn,
                                                 len, only_prefault);
                 } else {
                         result_bps[pf] =
@@ -245,12 +245,12 @@ int bench_mem_memset(int argc, const char **argv,
         switch (bench_format) {
         case BENCH_FORMAT_DEFAULT:
                 if (!only_prefault && !no_prefault) {
-                        if (use_clock) {
-                                printf(" %14lf Clock/Byte\n",
-                                        (double)result_clock[0]
+                        if (use_cycle) {
+                                printf(" %14lf Cycle/Byte\n",
+                                        (double)result_cycle[0]
                                         / (double)len);
-                                printf(" %14lf Clock/Byte (with prefault)\n ",
-                                        (double)result_clock[1]
+                                printf(" %14lf Cycle/Byte (with prefault)\n ",
+                                        (double)result_cycle[1]
                                         / (double)len);
                         } else {
                                 print_bps(result_bps[0]);
@@ -259,9 +259,9 @@ int bench_mem_memset(int argc, const char **argv,
                                 printf(" (with prefault)\n");
                         }
                 } else {
-                        if (use_clock) {
-                                printf(" %14lf Clock/Byte",
-                                        (double)result_clock[pf]
+                        if (use_cycle) {
+                                printf(" %14lf Cycle/Byte",
+                                        (double)result_cycle[pf]
                                         / (double)len);
                         } else
                                 print_bps(result_bps[pf]);
@@ -271,17 +271,17 @@ int bench_mem_memset(int argc, const char **argv,
                 break;
         case BENCH_FORMAT_SIMPLE:
                 if (!only_prefault && !no_prefault) {
-                        if (use_clock) {
+                        if (use_cycle) {
                                 printf("%lf %lf\n",
-                                        (double)result_clock[0] / (double)len,
-                                        (double)result_clock[1] / (double)len);
+                                        (double)result_cycle[0] / (double)len,
+                                        (double)result_cycle[1] / (double)len);
                         } else {
                                 printf("%lf %lf\n",
                                         result_bps[0], result_bps[1]);
                         }
                 } else {
-                        if (use_clock) {
-                                printf("%lf\n", (double)result_clock[pf]
+                        if (use_cycle) {
+                                printf("%lf\n", (double)result_cycle[pf]
                                         / (double)len);
                         } else
                                 printf("%lf\n", result_bps[pf]);
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 3d1f6968f17..e8177136486 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -15,6 +15,7 @@
 #include "cpumap.h"
 #include "thread_map.h"
 #include "target.h"
+#include "../../../include/linux/hw_breakpoint.h"
 
 #define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y))
 #define GROUP_FD(group_fd, cpu) (*(int *)xyarray__entry(group_fd, cpu, 0))
@@ -152,6 +153,31 @@ static int perf_evsel__sw_name(struct perf_evsel *evsel, char *bf, size_t size)
         return r + perf_evsel__add_modifiers(evsel, bf + r, size - r);
 }
 
+static int __perf_evsel__bp_name(char *bf, size_t size, u64 addr, u64 type)
+{
+        int r;
+
+        r = scnprintf(bf, size, "mem:0x%" PRIx64 ":", addr);
+
+        if (type & HW_BREAKPOINT_R)
+                r += scnprintf(bf + r, size - r, "r");
+
+        if (type & HW_BREAKPOINT_W)
+                r += scnprintf(bf + r, size - r, "w");
+
+        if (type & HW_BREAKPOINT_X)
+                r += scnprintf(bf + r, size - r, "x");
+
+        return r;
+}
+
+static int perf_evsel__bp_name(struct perf_evsel *evsel, char *bf, size_t size)
+{
+        struct perf_event_attr *attr = &evsel->attr;
+        int r = __perf_evsel__bp_name(bf, size, attr->bp_addr, attr->bp_type);
+        return r + perf_evsel__add_modifiers(evsel, bf + r, size - r);
+}
+
 const char *perf_evsel__hw_cache[PERF_COUNT_HW_CACHE_MAX]
                                 [PERF_EVSEL__MAX_ALIASES] = {
  { "L1-dcache", "l1-d",         "l1d",          "L1-data",              },
@@ -285,6 +311,10 @@ const char *perf_evsel__name(struct perf_evsel *evsel)
                 scnprintf(bf, sizeof(bf), "%s", "unknown tracepoint");
                 break;
 
+        case PERF_TYPE_BREAKPOINT:
+                perf_evsel__bp_name(evsel, bf, sizeof(bf));
+                break;
+
         default:
                 scnprintf(bf, sizeof(bf), "%s", "unknown attr type");
                 break;
diff --git a/tools/perf/util/include/linux/kernel.h b/tools/perf/util/include/linux/kernel.h
index 1eb804fd3fb..b6842c1d02a 100644
--- a/tools/perf/util/include/linux/kernel.h
+++ b/tools/perf/util/include/linux/kernel.h
@@ -108,4 +108,14 @@ int eprintf(int level,
 #define pr_debug3(fmt, ...) pr_debugN(3, pr_fmt(fmt), ##__VA_ARGS__)
 #define pr_debug4(fmt, ...) pr_debugN(4, pr_fmt(fmt), ##__VA_ARGS__)
 
+/*
+ * This looks more complex than it should be. But we need to
+ * get the type for the ~ right in round_down (it needs to be
+ * as wide as the result!), and we want to evaluate the macro
+ * arguments just once each.
+ */
+#define __round_mask(x, y) ((__typeof__(x))((y)-1))
+#define round_up(x, y) ((((x)-1) | __round_mask(x, y))+1)
+#define round_down(x, y) ((x) & ~__round_mask(x, y))
+
 #endif
diff --git a/tools/perf/util/parse-events-test.c b/tools/perf/util/parse-events-test.c
index a0f61a2a683..1b997d2b89c 100644
--- a/tools/perf/util/parse-events-test.c
+++ b/tools/perf/util/parse-events-test.c
@@ -181,6 +181,22 @@ static int test__checkevent_breakpoint_w(struct perf_evlist *evlist)
         return 0;
 }
 
+static int test__checkevent_breakpoint_rw(struct perf_evlist *evlist)
+{
+        struct perf_evsel *evsel = list_entry(evlist->entries.next,
+                                              struct perf_evsel, node);
+
+        TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries);
+        TEST_ASSERT_VAL("wrong type",
+                        PERF_TYPE_BREAKPOINT == evsel->attr.type);
+        TEST_ASSERT_VAL("wrong config", 0 == evsel->attr.config);
+        TEST_ASSERT_VAL("wrong bp_type",
+                (HW_BREAKPOINT_R|HW_BREAKPOINT_W) == evsel->attr.bp_type);
+        TEST_ASSERT_VAL("wrong bp_len",
+                        HW_BREAKPOINT_LEN_4 == evsel->attr.bp_len);
+        return 0;
+}
+
 static int test__checkevent_tracepoint_modifier(struct perf_evlist *evlist)
 {
         struct perf_evsel *evsel = list_entry(evlist->entries.next,
@@ -309,6 +325,8 @@ static int test__checkevent_breakpoint_modifier(struct perf_evlist *evlist)
         TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel);
         TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
         TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+        TEST_ASSERT_VAL("wrong name",
+                        !strcmp(perf_evsel__name(evsel), "mem:0x0:rw:u"));
 
         return test__checkevent_breakpoint(evlist);
 }
@@ -322,6 +340,8 @@ static int test__checkevent_breakpoint_x_modifier(struct perf_evlist *evlist)
         TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
         TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
         TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+        TEST_ASSERT_VAL("wrong name",
+                        !strcmp(perf_evsel__name(evsel), "mem:0x0:x:k"));
 
         return test__checkevent_breakpoint_x(evlist);
 }
@@ -335,6 +355,8 @@ static int test__checkevent_breakpoint_r_modifier(struct perf_evlist *evlist)
         TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel);
         TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv);
         TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip);
+        TEST_ASSERT_VAL("wrong name",
+                        !strcmp(perf_evsel__name(evsel), "mem:0x0:r:hp"));
 
         return test__checkevent_breakpoint_r(evlist);
 }
@@ -348,10 +370,27 @@ static int test__checkevent_breakpoint_w_modifier(struct perf_evlist *evlist)
         TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel);
         TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
         TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip);
+        TEST_ASSERT_VAL("wrong name",
+                        !strcmp(perf_evsel__name(evsel), "mem:0x0:w:up"));
 
         return test__checkevent_breakpoint_w(evlist);
 }
 
+static int test__checkevent_breakpoint_rw_modifier(struct perf_evlist *evlist)
+{
+        struct perf_evsel *evsel = list_entry(evlist->entries.next,
+                                              struct perf_evsel, node);
+
+        TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user);
+        TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+        TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+        TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip);
+        TEST_ASSERT_VAL("wrong name",
+                        !strcmp(perf_evsel__name(evsel), "mem:0x0:rw:kp"));
+
+        return test__checkevent_breakpoint_rw(evlist);
+}
+
 static int test__checkevent_pmu(struct perf_evlist *evlist)
 {
 
@@ -585,10 +624,16 @@ static struct test__event_st test__events[] = {
                 .name  = "instructions:H",
                 .check = test__checkevent_exclude_guest_modifier,
         },
+        [26] = {
+                .name  = "mem:0:rw",
+                .check = test__checkevent_breakpoint_rw,
+        },
+        [27] = {
+                .name  = "mem:0:rw:kp",
+                .check = test__checkevent_breakpoint_rw_modifier,
+        },
 };
 
-#define TEST__EVENTS_CNT (sizeof(test__events) / sizeof(struct test__event_st))
-
 static struct test__event_st test__events_pmu[] = {
         [0] = {
                 .name  = "cpu/config=10,config1,config2=3,period=1000/u",
@@ -600,9 +645,6 @@ static struct test__event_st test__events_pmu[] = {
         },
 };
 
-#define TEST__EVENTS_PMU_CNT (sizeof(test__events_pmu) / \
-                              sizeof(struct test__event_st))
-
 struct test__term {
         const char *str;
         __u32 type;
@@ -718,21 +760,17 @@ int parse_events__test(void)
 {
         int ret;
 
-        do {
-                ret = test_events(test__events, TEST__EVENTS_CNT);
-                if (ret)
-                        break;
-
-                if (test_pmu()) {
-                        ret = test_events(test__events_pmu,
-                                          TEST__EVENTS_PMU_CNT);
-                        if (ret)
-                                break;
-                }
+#define TEST_EVENTS(tests)                              \
+do {                                                    \
+        ret = test_events(tests, ARRAY_SIZE(tests));    \
+        if (ret)                                        \
+                return ret;                             \
+} while (0)
 
-                ret = test_terms(test__terms, TEST__TERMS_CNT);
+        TEST_EVENTS(test__events);
 
-        } while (0);
+        if (test_pmu())
+                TEST_EVENTS(test__events_pmu);
 
-        return ret;
+        return test_terms(test__terms, ARRAY_SIZE(test__terms));
 }
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 0cc27da30dd..1aa721d7c10 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -19,8 +19,6 @@
 #define MAX_NAME_LEN 100
 
 struct event_symbol {
-        u8              type;
-        u64             config;
         const char      *symbol;
         const char      *alias;
 };
@@ -30,30 +28,86 @@ extern int parse_events_debug;
 #endif
 int parse_events_parse(void *data, void *scanner);
 
-#define CHW(x) .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_##x
-#define CSW(x) .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_##x
-
-static struct event_symbol event_symbols[] = {
-  { CHW(CPU_CYCLES),                    "cpu-cycles",                   "cycles"                },
-  { CHW(STALLED_CYCLES_FRONTEND),       "stalled-cycles-frontend",      "idle-cycles-frontend"  },
-  { CHW(STALLED_CYCLES_BACKEND),        "stalled-cycles-backend",       "idle-cycles-backend"   },
-  { CHW(INSTRUCTIONS),                  "instructions",                 ""                      },
-  { CHW(CACHE_REFERENCES),              "cache-references",             ""                      },
-  { CHW(CACHE_MISSES),                  "cache-misses",                 ""                      },
-  { CHW(BRANCH_INSTRUCTIONS),           "branch-instructions",          "branches"              },
-  { CHW(BRANCH_MISSES),                 "branch-misses",                ""                      },
-  { CHW(BUS_CYCLES),                    "bus-cycles",                   ""                      },
-  { CHW(REF_CPU_CYCLES),                "ref-cycles",                   ""                      },
-
-  { CSW(CPU_CLOCK),                     "cpu-clock",                    ""                      },
-  { CSW(TASK_CLOCK),                    "task-clock",                   ""                      },
-  { CSW(PAGE_FAULTS),                   "page-faults",                  "faults"                },
-  { CSW(PAGE_FAULTS_MIN),               "minor-faults",                 ""                      },
-  { CSW(PAGE_FAULTS_MAJ),               "major-faults",                 ""                      },
-  { CSW(CONTEXT_SWITCHES),              "context-switches",             "cs"                    },
-  { CSW(CPU_MIGRATIONS),                "cpu-migrations",               "migrations"            },
-  { CSW(ALIGNMENT_FAULTS),              "alignment-faults",             ""                      },
-  { CSW(EMULATION_FAULTS),              "emulation-faults",             ""                      },
+static struct event_symbol event_symbols_hw[PERF_COUNT_HW_MAX] = {
+        [PERF_COUNT_HW_CPU_CYCLES] = {
+                .symbol = "cpu-cycles",
+                .alias  = "cycles",
+        },
+        [PERF_COUNT_HW_INSTRUCTIONS] = {
+                .symbol = "instructions",
+                .alias  = "",
+        },
+        [PERF_COUNT_HW_CACHE_REFERENCES] = {
+                .symbol = "cache-references",
+                .alias  = "",
+        },
+        [PERF_COUNT_HW_CACHE_MISSES] = {
+                .symbol = "cache-misses",
+                .alias  = "",
+        },
+        [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = {
+                .symbol = "branch-instructions",
+                .alias  = "branches",
+        },
+        [PERF_COUNT_HW_BRANCH_MISSES] = {
+                .symbol = "branch-misses",
+                .alias  = "",
+        },
+        [PERF_COUNT_HW_BUS_CYCLES] = {
+                .symbol = "bus-cycles",
+                .alias  = "",
+        },
+        [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = {
+                .symbol = "stalled-cycles-frontend",
+                .alias  = "idle-cycles-frontend",
+        },
+        [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = {
+                .symbol = "stalled-cycles-backend",
+                .alias  = "idle-cycles-backend",
+        },
+        [PERF_COUNT_HW_REF_CPU_CYCLES] = {
+                .symbol = "ref-cycles",
+                .alias  = "",
+        },
+};
+
+static struct event_symbol event_symbols_sw[PERF_COUNT_SW_MAX] = {
+        [PERF_COUNT_SW_CPU_CLOCK] = {
+                .symbol = "cpu-clock",
+                .alias  = "",
+        },
+        [PERF_COUNT_SW_TASK_CLOCK] = {
+                .symbol = "task-clock",
+                .alias  = "",
+        },
+        [PERF_COUNT_SW_PAGE_FAULTS] = {
+                .symbol = "page-faults",
+                .alias  = "faults",
+        },
+        [PERF_COUNT_SW_CONTEXT_SWITCHES] = {
+                .symbol = "context-switches",
+                .alias  = "cs",
+        },
+        [PERF_COUNT_SW_CPU_MIGRATIONS] = {
+                .symbol = "cpu-migrations",
+                .alias  = "migrations",
+        },
+        [PERF_COUNT_SW_PAGE_FAULTS_MIN] = {
+                .symbol = "minor-faults",
+                .alias  = "",
+        },
+        [PERF_COUNT_SW_PAGE_FAULTS_MAJ] = {
+                .symbol = "major-faults",
+                .alias  = "",
+        },
+        [PERF_COUNT_SW_ALIGNMENT_FAULTS] = {
+                .symbol = "alignment-faults",
+                .alias  = "",
+        },
+        [PERF_COUNT_SW_EMULATION_FAULTS] = {
+                .symbol = "emulation-faults",
+                .alias  = "",
+        },
 };
 
 #define __PERF_EVENT_FIELD(config, name) \
@@ -383,21 +437,31 @@ parse_breakpoint_type(const char *type, struct perf_event_attr *attr)
                 if (!type || !type[i])
                         break;
 
+#define CHECK_SET_TYPE(bit)             \
+do {                                    \
+        if (attr->bp_type & bit)        \
+                return -EINVAL;         \
+        else                            \
+                attr->bp_type |= bit;   \
+} while (0)
+
                 switch (type[i]) {
                 case 'r':
-                        attr->bp_type |= HW_BREAKPOINT_R;
+                        CHECK_SET_TYPE(HW_BREAKPOINT_R);
                         break;
                 case 'w':
-                        attr->bp_type |= HW_BREAKPOINT_W;
+                        CHECK_SET_TYPE(HW_BREAKPOINT_W);
                         break;
                 case 'x':
-                        attr->bp_type |= HW_BREAKPOINT_X;
+                        CHECK_SET_TYPE(HW_BREAKPOINT_X);
                         break;
                 default:
                         return -EINVAL;
                 }
         }
 
+#undef CHECK_SET_TYPE
+
         if (!attr->bp_type) /* Default */
                 attr->bp_type = HW_BREAKPOINT_R | HW_BREAKPOINT_W;
 
@@ -408,7 +472,6 @@ int parse_events_add_breakpoint(struct list_head **list, int *idx,
                                 void *ptr, char *type)
 {
         struct perf_event_attr attr;
-        char name[MAX_NAME_LEN];
 
         memset(&attr, 0, sizeof(attr));
         attr.bp_addr = (unsigned long) ptr;
@@ -427,8 +490,7 @@ int parse_events_add_breakpoint(struct list_head **list, int *idx,
 
         attr.type = PERF_TYPE_BREAKPOINT;
 
-        snprintf(name, MAX_NAME_LEN, "mem:%p:%s", ptr, type ? type : "rw");
-        return add_event(list, idx, &attr, name);
+        return add_event(list, idx, &attr, NULL);
 }
 
 static int config_term(struct perf_event_attr *attr,
@@ -816,16 +878,13 @@ int is_valid_tracepoint(const char *event_string)
         return 0;
 }
 
-void print_events_type(u8 type)
+static void __print_events_type(u8 type, struct event_symbol *syms,
+                                unsigned max)
 {
-        struct event_symbol *syms = event_symbols;
-        unsigned int i;
         char name[64];
+        unsigned i;
 
-        for (i = 0; i < ARRAY_SIZE(event_symbols); i++, syms++) {
-                if (type != syms->type)
-                        continue;
-
+        for (i = 0; i < max ; i++, syms++) {
                 if (strlen(syms->alias))
                         snprintf(name, sizeof(name),  "%s OR %s",
                                  syms->symbol, syms->alias);
@@ -837,6 +896,14 @@ void print_events_type(u8 type)
         }
 }
 
+void print_events_type(u8 type)
+{
+        if (type == PERF_TYPE_SOFTWARE)
+                __print_events_type(type, event_symbols_sw, PERF_COUNT_SW_MAX);
+        else
+                __print_events_type(type, event_symbols_hw, PERF_COUNT_HW_MAX);
+}
+
 int print_hwcache_events(const char *event_glob)
 {
         unsigned int type, op, i, printed = 0;
@@ -864,26 +931,13 @@ int print_hwcache_events(const char *event_glob)
         return printed;
 }
 
-/*
- * Print the help text for the event symbols:
- */
-void print_events(const char *event_glob)
+static void print_symbol_events(const char *event_glob, unsigned type,
+                                struct event_symbol *syms, unsigned max)
 {
-        unsigned int i, type, prev_type = -1, printed = 0, ntypes_printed = 0;
-        struct event_symbol *syms = event_symbols;
+        unsigned i, printed = 0;
         char name[MAX_NAME_LEN];
 
-        printf("\n");
-        printf("List of pre-defined events (to be used in -e):\n");
-
-        for (i = 0; i < ARRAY_SIZE(event_symbols); i++, syms++) {
-                type = syms->type;
-
-                if (type != prev_type && printed) {
-                        printf("\n");
-                        printed = 0;
-                        ntypes_printed++;
-                }
+        for (i = 0; i < max; i++, syms++) {
 
                 if (event_glob != NULL && 
                     !(strglobmatch(syms->symbol, event_glob) ||
@@ -894,17 +948,31 @@ void print_events(const char *event_glob)
                         snprintf(name, MAX_NAME_LEN, "%s OR %s", syms->symbol, syms->alias);
                 else
                         strncpy(name, syms->symbol, MAX_NAME_LEN);
-                printf("  %-50s [%s]\n", name,
-                        event_type_descriptors[type]);
 
-                prev_type = type;
-                ++printed;
+                printf("  %-50s [%s]\n", name, event_type_descriptors[type]);
+
+                printed++;
         }
 
-        if (ntypes_printed) {
-                printed = 0;
+        if (printed)
                 printf("\n");
-        }
+}
+
+/*
+ * Print the help text for the event symbols:
+ */
+void print_events(const char *event_glob)
+{
+
+        printf("\n");
+        printf("List of pre-defined events (to be used in -e):\n");
+
+        print_symbol_events(event_glob, PERF_TYPE_HARDWARE,
+                            event_symbols_hw, PERF_COUNT_HW_MAX);
+
+        print_symbol_events(event_glob, PERF_TYPE_SOFTWARE,
+                            event_symbols_sw, PERF_COUNT_SW_MAX);
+
         print_hwcache_events(event_glob);
 
         if (event_glob != NULL)
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index 488362e1413..384ca74c6b2 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -56,7 +56,7 @@ static int sym(yyscan_t scanner, int type, int config)
         YYSTYPE *yylval = parse_events_get_lval(scanner);
 
         yylval->num = (type << 16) + config;
-        return PE_VALUE_SYM;
+        return type == PERF_TYPE_HARDWARE ? PE_VALUE_SYM_HW : PE_VALUE_SYM_SW;
 }
 
 static int term(yyscan_t scanner, int type)
@@ -76,7 +76,7 @@ num_hex		0x[a-fA-F0-9]+
 num_raw_hex     [a-fA-F0-9]+
 name            [a-zA-Z_*?][a-zA-Z0-9_*?]*
 modifier_event  [ukhpGH]{1,8}
-modifier_bp     [rwx]
+modifier_bp     [rwx]{1,3}
 
 %%
 
@@ -152,6 +152,7 @@ r{num_raw_hex}		{ return raw(yyscanner); }
 ,                       { return ','; }
 :                       { return ':'; }
 =                       { return '='; }
+\n                      { }
 
 <mem>{
 {modifier_bp}           { return str(yyscanner, PE_MODIFIER_BP); }
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index 9525c455d27..2bc5fbff2b5 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -26,14 +26,15 @@ do { \
 %}
 
 %token PE_START_EVENTS PE_START_TERMS
-%token PE_VALUE PE_VALUE_SYM PE_RAW PE_TERM
+%token PE_VALUE PE_VALUE_SYM_HW PE_VALUE_SYM_SW PE_RAW PE_TERM
 %token PE_NAME
 %token PE_MODIFIER_EVENT PE_MODIFIER_BP
 %token PE_NAME_CACHE_TYPE PE_NAME_CACHE_OP_RESULT
 %token PE_PREFIX_MEM PE_PREFIX_RAW
 %token PE_ERROR
 %type <num> PE_VALUE
-%type <num> PE_VALUE_SYM
+%type <num> PE_VALUE_SYM_HW
+%type <num> PE_VALUE_SYM_SW
 %type <num> PE_RAW
 %type <num> PE_TERM
 %type <str> PE_NAME
@@ -41,6 +42,7 @@ do { \
 %type <str> PE_NAME_CACHE_OP_RESULT
 %type <str> PE_MODIFIER_EVENT
 %type <str> PE_MODIFIER_BP
+%type <num> value_sym
 %type <head> event_config
 %type <term> event_term
 %type <head> event_pmu
@@ -109,8 +111,13 @@ PE_NAME '/' event_config '/'
         $$ = list;
 }
 
+value_sym:
+PE_VALUE_SYM_HW
+|
+PE_VALUE_SYM_SW
+
 event_legacy_symbol:
-PE_VALUE_SYM '/' event_config '/'
+value_sym '/' event_config '/'
 {
         struct parse_events_data__events *data = _data;
         struct list_head *list = NULL;
@@ -123,7 +130,7 @@ PE_VALUE_SYM '/' event_config '/'
         $$ = list;
 }
 |
-PE_VALUE_SYM sep_slash_dc
+value_sym sep_slash_dc
 {
         struct parse_events_data__events *data = _data;
         struct list_head *list = NULL;
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 74d0948ec36..67715a42cd6 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -72,7 +72,7 @@ static int pmu_format(char *name, struct list_head *format)
                  "%s/bus/event_source/devices/%s/format", sysfs, name);
 
         if (stat(path, &st) < 0)
-                return -1;
+                return 0;       /* no error if format does not exist */
 
         if (pmu_format_parse(path, format))
                 return -1;
@@ -252,6 +252,7 @@ static struct perf_pmu *pmu_lookup(char *name)
         list_splice(&aliases, &pmu->aliases);
         pmu->name = strdup(name);
         pmu->type = type;
+        list_add_tail(&pmu->list, &pmus);
         return pmu;
 }
 
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index b3620fe1276..02dfa19a467 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -209,6 +209,10 @@ static void define_event_symbols(struct event_format *event,
                 define_symbolic_values(args->symbol.symbols, ev_name,
                                        cur_field_name);
                 break;
+        case PRINT_HEX:
+                define_event_symbols(event, ev_name, args->hex.field);
+                define_event_symbols(event, ev_name, args->hex.size);
+                break;
         case PRINT_BSTRING:
         case PRINT_DYNAMIC_ARRAY:
         case PRINT_STRING:
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index a8ca2f8179a..ce4d1b0c386 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -166,6 +166,10 @@ static void define_event_symbols(struct event_format *event,
                 define_values(PRINT_SYMBOL, args->symbol.symbols, ev_name,
                               cur_field_name);
                 break;
+        case PRINT_HEX:
+                define_event_symbols(event, ev_name, args->hex.field);
+                define_event_symbols(event, ev_name, args->hex.size);
+                break;
         case PRINT_STRING:
                 break;
         case PRINT_TYPE:
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 994f4ffdcd0..50958bbeb26 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1478,14 +1478,31 @@ static int elf_read_build_id(Elf *elf, void *bf, size_t size)
                 goto out;
         }
 
-        sec = elf_section_by_name(elf, &ehdr, &shdr,
-                                  ".note.gnu.build-id", NULL);
-        if (sec == NULL) {
+        /*
+         * Check following sections for notes:
+         *   '.note.gnu.build-id'
+         *   '.notes'
+         *   '.note' (VDSO specific)
+         */
+        do {
+                sec = elf_section_by_name(elf, &ehdr, &shdr,
+                                          ".note.gnu.build-id", NULL);
+                if (sec)
+                        break;
+
                 sec = elf_section_by_name(elf, &ehdr, &shdr,
                                           ".notes", NULL);
-                if (sec == NULL)
-                        goto out;
-        }
+                if (sec)
+                        break;
+
+                sec = elf_section_by_name(elf, &ehdr, &shdr,
+                                          ".note", NULL);
+                if (sec)
+                        break;
+
+                return err;
+
+        } while (0);
 
         data = elf_getdata(sec, NULL);
         if (data == NULL)