Merge branch 'perf/core' into oprofile/master

Merge reason: Resolve conflicts with Don's NMI rework:

    commit 9c48f1c629ecfa114850c03f875c6691003214de
    Author: Don Zickus <dzickus@redhat.com>
    Date:   Fri Sep 30 15:06:21 2011 -0400
    x86, nmi: Wire up NMI handlers to new routines

Conflicts:
	arch/x86/oprofile/nmi_timer_int.c

Signed-off-by: Robert Richter <robert.richter@amd.com>

32 files changed, 546 insertions, 160 deletions

diff --git a/tools/perf/Documentation/perf-annotate.txt b/tools/perf/Documentation/perf-annotate.txt
index 98a31e3181a5..0102d83600db 100644
--- a/tools/perf/Documentation/perf-annotate.txt
+++ b/tools/perf/Documentation/perf-annotate.txt
@@ -83,6 +83,9 @@ OPTIONS
 --symfs=<directory>::
         Look for files with symbols relative to this directory.
 
+-M::
+--disassembler-style=:: Set disassembler style for objdump.
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-report[1]
diff --git a/tools/perf/Documentation/perf-buildid-list.txt b/tools/perf/Documentation/perf-buildid-list.txt
index 5eaac6f26d51..cc22325ffd1b 100644
--- a/tools/perf/Documentation/perf-buildid-list.txt
+++ b/tools/perf/Documentation/perf-buildid-list.txt
@@ -16,6 +16,9 @@ This command displays the buildids found in a perf.data file, so that other
 tools can be used to fetch packages with matching symbol tables for use by
 perf report.
 
+It can also be used to show the build id of the running kernel or in an ELF
+file using -i/--input.
+
 OPTIONS
 -------
 -H::
@@ -27,6 +30,9 @@ OPTIONS
 -f::
 --force::
 	Don't do ownership validation.
+-k::
+--kernel::
+	Show running kernel build id.
 -v::
 --verbose::
 	Be more verbose.
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index 04253c07d19a..6349b6c0e3ec 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -134,6 +134,9 @@ OPTIONS
 	CPUs are specified with -: 0-2. Default is to report samples on all
 	CPUs.
 
+-M::
+--disassembler-style=:: Set disassembler style for objdump.
+
 SEE ALSO
 --------
 linkperf:perf-stat[1]
diff --git a/tools/perf/Documentation/perf-sched.txt b/tools/perf/Documentation/perf-sched.txt
index 46822d5fde1c..5b212b57f70b 100644
--- a/tools/perf/Documentation/perf-sched.txt
+++ b/tools/perf/Documentation/perf-sched.txt
@@ -8,7 +8,7 @@ perf-sched - Tool to trace/measure scheduler properties (latencies)
 SYNOPSIS
 --------
 [verse]
-'perf sched' {record|latency|map|replay|trace}
+'perf sched' {record|latency|map|replay|script}
 
 DESCRIPTION
 -----------
@@ -20,8 +20,8 @@ There are five variants of perf sched:
   'perf sched latency' to report the per task scheduling latencies
   and other scheduling properties of the workload.
 
-  'perf sched trace' to see a detailed trace of the workload that
-  was recorded.
+  'perf sched script' to see a detailed trace of the workload that
+   was recorded (aliased to 'perf script' for now).
 
   'perf sched replay' to simulate the workload that was recorded
   via perf sched record. (this is done by starting up mockup threads
diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 08394c4879a8..8966b9ab2014 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -95,12 +95,21 @@ corresponding events, i.e., they always refer to events defined earlier on the c
 line.
 
 -o file::
--output file::
+--output file::
 Print the output into the designated file.
 
 --append::
 Append to the output file designated with the -o option. Ignored if -o is not specified.
 
+--log-fd::
+
+Log output to fd, instead of stderr.  Complementary to --output, and mutually exclusive
+with it.  --append may be used here.  Examples:
+     3>results  perf stat --log-fd 3          -- $cmd
+     3>>results perf stat --log-fd 3 --append -- $cmd
+
+
+
 EXAMPLES
 --------
 
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 3b8f7b80376b..e9d5c271db69 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -30,6 +30,8 @@ endif
 # Define EXTRA_CFLAGS=-m64 or EXTRA_CFLAGS=-m32 as appropriate for cross-builds.
 #
 # Define NO_DWARF if you do not want debug-info analysis feature at all.
+#
+# Define WERROR=0 to disable treating any warnings as errors.
 
 $(OUTPUT)PERF-VERSION-FILE: .FORCE-PERF-VERSION-FILE
 	@$(SHELL_PATH) util/PERF-VERSION-GEN $(OUTPUT)
@@ -63,6 +65,11 @@ ifeq ($(ARCH),x86_64)
 	endif
 endif
 
+# Treat warnings as errors unless directed not to
+ifneq ($(WERROR),0)
+	CFLAGS_WERROR := -Werror
+endif
+
 #
 # Include saner warnings here, which can catch bugs:
 #
@@ -95,7 +102,7 @@ ifndef PERF_DEBUG
   CFLAGS_OPTIMIZE = -O6
 endif
 
-CFLAGS = -fno-omit-frame-pointer -ggdb3 -Wall -Wextra -std=gnu99 -Werror $(CFLAGS_OPTIMIZE) -D_FORTIFY_SOURCE=2 $(EXTRA_WARNINGS) $(EXTRA_CFLAGS)
+CFLAGS = -fno-omit-frame-pointer -ggdb3 -Wall -Wextra -std=gnu99 $(CFLAGS_WERROR) $(CFLAGS_OPTIMIZE) -D_FORTIFY_SOURCE=2 $(EXTRA_WARNINGS) $(EXTRA_CFLAGS)
 EXTLIBS = -lpthread -lrt -lelf -lm
 ALL_CFLAGS = $(CFLAGS) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64
 ALL_LDFLAGS = $(LDFLAGS)
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index c5be28851f01..cf68819f7453 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -273,6 +273,8 @@ static const struct option options[] = {
 		    "Interleave source code with assembly code (default)"),
 	OPT_BOOLEAN('0', "asm-raw", &symbol_conf.annotate_asm_raw,
 		    "Display raw encoding of assembly instructions (default)"),
+	OPT_STRING('M', "disassembler-style", &disassembler_style, "disassembler style",
+		   "Specify disassembler style (e.g. -M intel for intel syntax)"),
 	OPT_END()
 };
 
diff --git a/tools/perf/builtin-buildid-list.c b/tools/perf/builtin-buildid-list.c
index 5af32ae9031e..cb690a65bf02 100644
--- a/tools/perf/builtin-buildid-list.c
+++ b/tools/perf/builtin-buildid-list.c
@@ -1,7 +1,8 @@
 /*
  * builtin-buildid-list.c
  *
- * Builtin buildid-list command: list buildids in perf.data
+ * Builtin buildid-list command: list buildids in perf.data, in the running
+ * kernel and in ELF files.
  *
  * Copyright (C) 2009, Red Hat Inc.
  * Copyright (C) 2009, Arnaldo Carvalho de Melo <acme@redhat.com>
@@ -15,8 +16,11 @@
 #include "util/session.h"
 #include "util/symbol.h"
 
+#include <libelf.h>
+
 static char const *input_name = "perf.data";
 static bool force;
+static bool show_kernel;
 static bool with_hits;
 
 static const char * const buildid_list_usage[] = {
@@ -29,12 +33,13 @@ static const struct option options[] = {
 	OPT_STRING('i', "input", &input_name, "file",
 		    "input file name"),
 	OPT_BOOLEAN('f', "force", &force, "don't complain, do it"),
+	OPT_BOOLEAN('k', "kernel", &show_kernel, "Show current kernel build id"),
 	OPT_INCR('v', "verbose", &verbose,
 		    "be more verbose"),
 	OPT_END()
 };
 
-static int __cmd_buildid_list(void)
+static int perf_session__list_build_ids(void)
 {
 	struct perf_session *session;
 
@@ -52,6 +57,49 @@ static int __cmd_buildid_list(void)
 	return 0;
 }
 
+static int sysfs__fprintf_build_id(FILE *fp)
+{
+	u8 kallsyms_build_id[BUILD_ID_SIZE];
+	char sbuild_id[BUILD_ID_SIZE * 2 + 1];
+
+	if (sysfs__read_build_id("/sys/kernel/notes", kallsyms_build_id,
+				 sizeof(kallsyms_build_id)) != 0)
+		return -1;
+
+	build_id__sprintf(kallsyms_build_id, sizeof(kallsyms_build_id),
+			  sbuild_id);
+	fprintf(fp, "%s\n", sbuild_id);
+	return 0;
+}
+
+static int filename__fprintf_build_id(const char *name, FILE *fp)
+{
+	u8 build_id[BUILD_ID_SIZE];
+	char sbuild_id[BUILD_ID_SIZE * 2 + 1];
+
+	if (filename__read_build_id(name, build_id,
+				    sizeof(build_id)) != sizeof(build_id))
+		return 0;
+
+	build_id__sprintf(build_id, sizeof(build_id), sbuild_id);
+	return fprintf(fp, "%s\n", sbuild_id);
+}
+
+static int __cmd_buildid_list(void)
+{
+	if (show_kernel)
+		return sysfs__fprintf_build_id(stdout);
+
+	elf_version(EV_CURRENT);
+	/*
+ 	 * See if this is an ELF file first:
+ 	 */
+	if (filename__fprintf_build_id(input_name, stdout))
+		return 0;
+
+	return perf_session__list_build_ids();
+}
+
 int cmd_buildid_list(int argc, const char **argv, const char *prefix __used)
 {
 	argc = parse_options(argc, argv, options, buildid_list_usage, 0);
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 6b0519f885e4..dd6467872f60 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -73,6 +73,7 @@ static off_t			post_processing_offset;
 
 static struct perf_session	*session;
 static const char		*cpu_list;
+static const char               *progname;
 
 static void advance_output(size_t size)
 {
@@ -137,17 +138,29 @@ static void mmap_read(struct perf_mmap *md)
 
 static volatile int done = 0;
 static volatile int signr = -1;
+static volatile int child_finished = 0;
 
 static void sig_handler(int sig)
 {
+	if (sig == SIGCHLD)
+		child_finished = 1;
+
 	done = 1;
 	signr = sig;
 }
 
 static void sig_atexit(void)
 {
-	if (child_pid > 0)
-		kill(child_pid, SIGTERM);
+	int status;
+
+	if (child_pid > 0) {
+		if (!child_finished)
+			kill(child_pid, SIGTERM);
+
+		wait(&status);
+		if (WIFSIGNALED(status))
+			psignal(WTERMSIG(status), progname);
+	}
 
 	if (signr == -1 || signr == SIGUSR1)
 		return;
@@ -161,6 +174,7 @@ static void config_attr(struct perf_evsel *evsel, struct perf_evlist *evlist)
 	struct perf_event_attr *attr = &evsel->attr;
 	int track = !evsel->idx; /* only the first counter needs these */
 
+	attr->disabled		= 1;
 	attr->inherit		= !no_inherit;
 	attr->read_format	= PERF_FORMAT_TOTAL_TIME_ENABLED |
 				  PERF_FORMAT_TOTAL_TIME_RUNNING |
@@ -445,6 +459,8 @@ static int __cmd_record(int argc, const char **argv)
 	char buf;
 	struct machine *machine;
 
+	progname = argv[0];
+
 	page_size = sysconf(_SC_PAGE_SIZE);
 
 	atexit(sig_atexit);
@@ -671,6 +687,8 @@ static int __cmd_record(int argc, const char **argv)
 		}
 	}
 
+	perf_evlist__enable(evsel_list);
+
 	/*
 	 * Let the child rip
 	 */
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index d7ff277bdb78..3d58334909a5 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -229,10 +229,7 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist,
 
 	list_for_each_entry(pos, &evlist->entries, node) {
 		struct hists *hists = &pos->hists;
-		const char *evname = NULL;
-
-		if (rb_first(&hists->entries) != rb_last(&hists->entries))
-			evname = event_name(pos);
+		const char *evname = event_name(pos);
 
 		hists__fprintf_nr_sample_events(hists, evname, stdout);
 		hists__fprintf(hists, NULL, false, stdout);
@@ -487,6 +484,8 @@ static const struct option options[] = {
 	OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory",
 		    "Look for files with symbols relative to this directory"),
 	OPT_STRING('c', "cpu", &cpu_list, "cpu", "list of cpus to profile"),
+	OPT_STRING('M', "disassembler-style", &disassembler_style, "disassembler style",
+		   "Specify disassembler style (e.g. -M intel for intel syntax)"),
 	OPT_END()
 };
 
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index bec64a9e741c..7ce65f52415e 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -196,6 +196,7 @@ static bool			csv_output			= false;
 static bool			group				= false;
 static const char		*output_name			= NULL;
 static FILE			*output				= NULL;
+static int			output_fd;
 
 static volatile int done = 0;
 
@@ -253,8 +254,13 @@ static double avg_stats(struct stats *stats)
  */
 static double stddev_stats(struct stats *stats)
 {
-	double variance = stats->M2 / (stats->n - 1);
-	double variance_mean = variance / stats->n;
+	double variance, variance_mean;
+
+	if (!stats->n)
+		return 0.0;
+
+	variance = stats->M2 / (stats->n - 1);
+	variance_mean = variance / stats->n;
 
 	return sqrt(variance_mean);
 }
@@ -489,6 +495,8 @@ static int run_perf_stat(int argc __used, const char **argv)
 	if (forks) {
 		close(go_pipe[1]);
 		wait(&status);
+		if (WIFSIGNALED(status))
+			psignal(WTERMSIG(status), argv[0]);
 	} else {
 		while(!done) sleep(1);
 	}
@@ -522,7 +530,7 @@ static void print_noise_pct(double total, double avg)
 
 	if (csv_output)
 		fprintf(output, "%s%.2f%%", csv_sep, pct);
-	else
+	else if (pct)
 		fprintf(output, "  ( +-%6.2f%% )", pct);
 }
 
@@ -1080,6 +1088,8 @@ static const struct option options[] = {
 	OPT_STRING('o', "output", &output_name, "file",
 		    "output file name"),
 	OPT_BOOLEAN(0, "append", &append_file, "append to the output file"),
+	OPT_INTEGER(0, "log-fd", &output_fd,
+		    "log output to fd, instead of stderr"),
 	OPT_END()
 };
 
@@ -1166,6 +1176,10 @@ int cmd_stat(int argc, const char **argv, const char *prefix __used)
 	if (output_name && strcmp(output_name, "-"))
 		output = NULL;
 
+	if (output_name && output_fd) {
+		fprintf(stderr, "cannot use both --output and --log-fd\n");
+		usage_with_options(stat_usage, options);
+	}
 	if (!output) {
 		struct timespec tm;
 		mode = append_file ? "a" : "w";
@@ -1177,18 +1191,27 @@ int cmd_stat(int argc, const char **argv, const char *prefix __used)
 		}
 		clock_gettime(CLOCK_REALTIME, &tm);
 		fprintf(output, "# started on %s\n", ctime(&tm.tv_sec));
+	} else if (output_fd != 2) {
+		mode = append_file ? "a" : "w";
+		output = fdopen(output_fd, mode);
+		if (!output) {
+			perror("Failed opening logfd");
+			return -errno;
+		}
 	}
 
-	if (csv_sep)
+	if (csv_sep) {
 		csv_output = true;
-	else
+		if (!strcmp(csv_sep, "\\t"))
+			csv_sep = "\t";
+	} else
 		csv_sep = DEFAULT_SEPARATOR;
 
 	/*
 	 * let the spreadsheet do the pretty-printing
 	 */
 	if (csv_output) {
-		/* User explicitely passed -B? */
+		/* User explicitly passed -B? */
 		if (big_num_opt == 1) {
 			fprintf(stderr, "-B option not supported with -x\n");
 			usage_with_options(stat_usage, options);
diff --git a/tools/perf/builtin-test.c b/tools/perf/builtin-test.c
index 55f4c76f2821..efe696f936e2 100644
--- a/tools/perf/builtin-test.c
+++ b/tools/perf/builtin-test.c
@@ -561,7 +561,7 @@ static int test__basic_mmap(void)
 		}
 
 		err = perf_event__parse_sample(event, attr.sample_type, sample_size,
-					       false, &sample);
+					       false, &sample, false);
 		if (err) {
 			pr_err("Can't parse sample, err = %d\n", err);
 			goto out_munmap;
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index a43433f08300..5ede7d7c9239 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -191,7 +191,8 @@ static void __zero_source_counters(struct sym_entry *syme)
 	symbol__annotate_zero_histograms(sym);
 }
 
-static void record_precise_ip(struct sym_entry *syme, int counter, u64 ip)
+static void record_precise_ip(struct sym_entry *syme, struct map *map,
+			      int counter, u64 ip)
 {
 	struct annotation *notes;
 	struct symbol *sym;
@@ -205,8 +206,8 @@ static void record_precise_ip(struct sym_entry *syme, int counter, u64 ip)
 	if (pthread_mutex_trylock(&notes->lock))
 		return;
 
-	ip = syme->map->map_ip(syme->map, ip);
-	symbol__inc_addr_samples(sym, syme->map, counter, ip);
+	ip = map->map_ip(map, ip);
+	symbol__inc_addr_samples(sym, map, counter, ip);
 
 	pthread_mutex_unlock(&notes->lock);
 }
@@ -250,7 +251,7 @@ static void __list_insert_active_sym(struct sym_entry *syme)
 	list_add(&syme->node, &top.active_symbols);
 }
 
-static void print_sym_table(struct perf_session *session)
+static void print_sym_table(void)
 {
 	char bf[160];
 	int printed = 0;
@@ -270,10 +271,11 @@ static void print_sym_table(struct perf_session *session)
 
 	printf("%-*.*s\n", win_width, win_width, graph_dotted_line);
 
-	if (session->hists.stats.total_lost != 0) {
+	if (top.total_lost_warned != top.session->hists.stats.total_lost) {
+		top.total_lost_warned = top.session->hists.stats.total_lost;
 		color_fprintf(stdout, PERF_COLOR_RED, "WARNING:");
 		printf(" LOST %" PRIu64 " events, Check IO/CPU overload\n",
-		       session->hists.stats.total_lost);
+		       top.total_lost_warned);
 	}
 
 	if (top.sym_filter_entry) {
@@ -474,7 +476,7 @@ static int key_mapped(int c)
 	return 0;
 }
 
-static void handle_keypress(struct perf_session *session, int c)
+static void handle_keypress(int c)
 {
 	if (!key_mapped(c)) {
 		struct pollfd stdin_poll = { .fd = 0, .events = POLLIN };
@@ -550,7 +552,7 @@ static void handle_keypress(struct perf_session *session, int c)
 		case 'Q':
 			printf("exiting.\n");
 			if (dump_symtab)
-				perf_session__fprintf_dsos(session, stderr);
+				perf_session__fprintf_dsos(top.session, stderr);
 			exit(0);
 		case 's':
 			prompt_symbol(&top.sym_filter_entry, "Enter details symbol");
@@ -602,7 +604,6 @@ static void *display_thread(void *arg __used)
 	struct pollfd stdin_poll = { .fd = 0, .events = POLLIN };
 	struct termios tc, save;
 	int delay_msecs, c;
-	struct perf_session *session = (struct perf_session *) arg;
 
 	tcgetattr(0, &save);
 	tc = save;
@@ -617,13 +618,13 @@ repeat:
 	getc(stdin);
 
 	do {
-		print_sym_table(session);
+		print_sym_table();
 	} while (!poll(&stdin_poll, 1, delay_msecs) == 1);
 
 	c = getc(stdin);
 	tcsetattr(0, TCSAFLUSH, &save);
 
-	handle_keypress(session, c);
+	handle_keypress(c);
 	goto repeat;
 
 	return NULL;
@@ -810,7 +811,7 @@ static void perf_event__process_sample(const union perf_event *event,
 		evsel = perf_evlist__id2evsel(top.evlist, sample->id);
 		assert(evsel != NULL);
 		syme->count[evsel->idx]++;
-		record_precise_ip(syme, evsel->idx, ip);
+		record_precise_ip(syme, al.map, evsel->idx, ip);
 		pthread_mutex_lock(&top.active_symbols_lock);
 		if (list_empty(&syme->node) || !syme->node.next) {
 			static bool first = true;
@@ -935,27 +936,27 @@ static int __cmd_top(void)
 	 * FIXME: perf_session__new should allow passing a O_MMAP, so that all this
 	 * mmap reading, etc is encapsulated in it. Use O_WRONLY for now.
 	 */
-	struct perf_session *session = perf_session__new(NULL, O_WRONLY, false, false, NULL);
-	if (session == NULL)
+	top.session = perf_session__new(NULL, O_WRONLY, false, false, NULL);
+	if (top.session == NULL)
 		return -ENOMEM;
 
 	if (top.target_tid != -1)
 		perf_event__synthesize_thread_map(top.evlist->threads,
-						  perf_event__process, session);
+						  perf_event__process, top.session);
 	else
-		perf_event__synthesize_threads(perf_event__process, session);
+		perf_event__synthesize_threads(perf_event__process, top.session);
 
 	start_counters(top.evlist);
-	session->evlist = top.evlist;
-	perf_session__update_sample_type(session);
+	top.session->evlist = top.evlist;
+	perf_session__update_sample_type(top.session);
 
 	/* Wait for a minimal set of events before starting the snapshot */
 	poll(top.evlist->pollfd, top.evlist->nr_fds, 100);
 
-	perf_session__mmap_read(session);
+	perf_session__mmap_read(top.session);
 
 	if (pthread_create(&thread, NULL, (use_browser > 0 ? display_thread_tui :
-							     display_thread), session)) {
+							     display_thread), NULL)) {
 		printf("Could not create display thread.\n");
 		exit(-1);
 	}
@@ -973,7 +974,7 @@ static int __cmd_top(void)
 	while (1) {
 		u64 hits = top.samples;
 
-		perf_session__mmap_read(session);
+		perf_session__mmap_read(top.session);
 
 		if (hits == top.samples)
 			ret = poll(top.evlist->pollfd, top.evlist->nr_fds, 100);
diff --git a/tools/perf/scripts/python/bin/net_dropmonitor-record b/tools/perf/scripts/python/bin/net_dropmonitor-record
new file mode 100755
index 000000000000..423fb81dadae
--- /dev/null
+++ b/tools/perf/scripts/python/bin/net_dropmonitor-record
@@ -0,0 +1,2 @@
+#!/bin/bash
+perf record -e skb:kfree_skb $@
diff --git a/tools/perf/scripts/python/bin/net_dropmonitor-report b/tools/perf/scripts/python/bin/net_dropmonitor-report
new file mode 100755
index 000000000000..8d698f5a06aa
--- /dev/null
+++ b/tools/perf/scripts/python/bin/net_dropmonitor-report
@@ -0,0 +1,4 @@
+#!/bin/bash
+# description: display a table of dropped frames
+
+perf script -s "$PERF_EXEC_PATH"/scripts/python/net_dropmonitor.py $@
diff --git a/tools/perf/scripts/python/net_dropmonitor.py b/tools/perf/scripts/python/net_dropmonitor.py
new file mode 100755
index 000000000000..a4ffc9500023
--- /dev/null
+++ b/tools/perf/scripts/python/net_dropmonitor.py
@@ -0,0 +1,72 @@
+# Monitor the system for dropped packets and proudce a report of drop locations and counts
+
+import os
+import sys
+
+sys.path.append(os.environ['PERF_EXEC_PATH'] + \
+		'/scripts/python/Perf-Trace-Util/lib/Perf/Trace')
+
+from perf_trace_context import *
+from Core import *
+from Util import *
+
+drop_log = {}
+kallsyms = []
+
+def get_kallsyms_table():
+	global kallsyms
+	try:
+		f = open("/proc/kallsyms", "r")
+		linecount = 0
+		for line in f:
+			linecount = linecount+1
+		f.seek(0)
+	except:
+		return
+
+
+	j = 0
+	for line in f:
+		loc = int(line.split()[0], 16)
+		name = line.split()[2]
+		j = j +1
+		if ((j % 100) == 0):
+			print "\r" + str(j) + "/" + str(linecount),
+		kallsyms.append({ 'loc': loc, 'name' : name})
+
+	print "\r" + str(j) + "/" + str(linecount)
+	kallsyms.sort()
+	return
+
+def get_sym(sloc):
+	loc = int(sloc)
+	for i in kallsyms:
+		if (i['loc'] >= loc):
+			return (i['name'], i['loc']-loc)
+	return (None, 0)
+
+def print_drop_table():
+	print "%25s %25s %25s" % ("LOCATION", "OFFSET", "COUNT")
+	for i in drop_log.keys():
+		(sym, off) = get_sym(i)
+		if sym == None:
+			sym = i
+		print "%25s %25s %25s" % (sym, off, drop_log[i])
+
+
+def trace_begin():
+	print "Starting trace (Ctrl-C to dump results)"
+
+def trace_end():
+	print "Gathering kallsyms data"
+	get_kallsyms_table()
+	print_drop_table()
+
+# called from perf, when it finds a correspoinding event
+def skb__kfree_skb(name, context, cpu, sec, nsec, pid, comm,
+			skbaddr, protocol, location):
+	slocation = str(location)
+	try:
+		drop_log[slocation] = drop_log[slocation] + 1
+	except:
+		drop_log[slocation] = 1
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 01d36ba54053..bc8f4773d4d8 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -16,6 +16,8 @@
 #include "annotate.h"
 #include <pthread.h>
 
+const char 	*disassembler_style;
+
 int symbol__annotate_init(struct map *map __used, struct symbol *sym)
 {
 	struct annotation *notes = symbol__annotation(sym);
@@ -323,9 +325,11 @@ fallback:
 		 dso, dso->long_name, sym, sym->name);
 
 	snprintf(command, sizeof(command),
-		 "objdump --start-address=0x%016" PRIx64
+		 "objdump %s%s --start-address=0x%016" PRIx64
 		 " --stop-address=0x%016" PRIx64
 		 " -d %s %s -C %s|grep -v %s|expand",
+		 disassembler_style ? "-M " : "",
+		 disassembler_style ? disassembler_style : "",
 		 map__rip_2objdump(map, sym->start),
 		 map__rip_2objdump(map, sym->end),
 		 symbol_conf.annotate_asm_raw ? "" : "--no-show-raw",
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index c2c286896801..6ede1286ee71 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -100,4 +100,6 @@ int symbol__tui_annotate(struct symbol *sym, struct map *map, int evidx,
 			 int refresh);
 #endif
 
+extern const char	*disassembler_style;
+
 #endif	/* __PERF_ANNOTATE_H */
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 3c1b8a632101..437f8ca679a0 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -169,12 +169,17 @@ static int perf_event__synthesize_mmap_events(union perf_event *event,
 			continue;
 		pbf += n + 3;
 		if (*pbf == 'x') { /* vm_exec */
+			char anonstr[] = "//anon\n";
 			char *execname = strchr(bf, '/');
 
 			/* Catch VDSO */
 			if (execname == NULL)
 				execname = strstr(bf, "[vdso]");
 
+			/* Catch anonymous mmaps */
+			if ((execname == NULL) && !strstr(bf, "["))
+				execname = anonstr;
+
 			if (execname == NULL)
 				continue;
 
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 1d7f66488a88..357a85b85248 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -186,6 +186,6 @@ const char *perf_event__name(unsigned int id);
 
 int perf_event__parse_sample(const union perf_event *event, u64 type,
 			     int sample_size, bool sample_id_all,
-			     struct perf_sample *sample);
+			     struct perf_sample *sample, bool swapped);
 
 #endif /* __PERF_RECORD_H */
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index c12bd476c6f7..72e9f4886b6d 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -113,6 +113,19 @@ void perf_evlist__disable(struct perf_evlist *evlist)
 	}
 }
 
+void perf_evlist__enable(struct perf_evlist *evlist)
+{
+	int cpu, thread;
+	struct perf_evsel *pos;
+
+	for (cpu = 0; cpu < evlist->cpus->nr; cpu++) {
+		list_for_each_entry(pos, &evlist->entries, node) {
+			for (thread = 0; thread < evlist->threads->nr; thread++)
+				ioctl(FD(pos, cpu, thread), PERF_EVENT_IOC_ENABLE);
+		}
+	}
+}
+
 int perf_evlist__alloc_pollfd(struct perf_evlist *evlist)
 {
 	int nfds = evlist->cpus->nr * evlist->threads->nr * evlist->nr_entries;
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index ce85ae9ae57a..f34915002745 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -54,6 +54,7 @@ int perf_evlist__mmap(struct perf_evlist *evlist, int pages, bool overwrite);
 void perf_evlist__munmap(struct perf_evlist *evlist);
 
 void perf_evlist__disable(struct perf_evlist *evlist);
+void perf_evlist__enable(struct perf_evlist *evlist);
 
 static inline void perf_evlist__set_maps(struct perf_evlist *evlist,
 					 struct cpu_map *cpus,
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index a03a36b7908a..e389815078d3 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -7,6 +7,8 @@
  * Released under the GPL v2. (and only v2, not any later version)
  */
 
+#include <byteswap.h>
+#include "asm/bug.h"
 #include "evsel.h"
 #include "evlist.h"
 #include "util.h"
@@ -342,10 +344,20 @@ static bool sample_overlap(const union perf_event *event,
 
 int perf_event__parse_sample(const union perf_event *event, u64 type,
 			     int sample_size, bool sample_id_all,
-			     struct perf_sample *data)
+			     struct perf_sample *data, bool swapped)
 {
 	const u64 *array;
 
+	/*
+	 * used for cross-endian analysis. See git commit 65014ab3
+	 * for why this goofiness is needed.
+	 */
+	union {
+		u64 val64;
+		u32 val32[2];
+	} u;
+
+
 	data->cpu = data->pid = data->tid = -1;
 	data->stream_id = data->id = data->time = -1ULL;
 
@@ -366,9 +378,16 @@ int perf_event__parse_sample(const union perf_event *event, u64 type,
 	}
 
 	if (type & PERF_SAMPLE_TID) {
-		u32 *p = (u32 *)array;
-		data->pid = p[0];
-		data->tid = p[1];
+		u.val64 = *array;
+		if (swapped) {
+			/* undo swap of u64, then swap on individual u32s */
+			u.val64 = bswap_64(u.val64);
+			u.val32[0] = bswap_32(u.val32[0]);
+			u.val32[1] = bswap_32(u.val32[1]);
+		}
+
+		data->pid = u.val32[0];
+		data->tid = u.val32[1];
 		array++;
 	}
 
@@ -395,8 +414,15 @@ int perf_event__parse_sample(const union perf_event *event, u64 type,
 	}
 
 	if (type & PERF_SAMPLE_CPU) {
-		u32 *p = (u32 *)array;
-		data->cpu = *p;
+
+		u.val64 = *array;
+		if (swapped) {
+			/* undo swap of u64, then swap on individual u32s */
+			u.val64 = bswap_64(u.val64);
+			u.val32[0] = bswap_32(u.val32[0]);
+		}
+
+		data->cpu = u.val32[0];
 		array++;
 	}
 
@@ -423,18 +449,27 @@ int perf_event__parse_sample(const union perf_event *event, u64 type,
 	}
 
 	if (type & PERF_SAMPLE_RAW) {
-		u32 *p = (u32 *)array;
+		const u64 *pdata;
+
+		u.val64 = *array;
+		if (WARN_ONCE(swapped,
+			      "Endianness of raw data not corrected!\n")) {
+			/* undo swap of u64, then swap on individual u32s */
+			u.val64 = bswap_64(u.val64);
+			u.val32[0] = bswap_32(u.val32[0]);
+			u.val32[1] = bswap_32(u.val32[1]);
+		}
 
 		if (sample_overlap(event, array, sizeof(u32)))
 			return -EFAULT;
 
-		data->raw_size = *p;
-		p++;
+		data->raw_size = u.val32[0];
+		pdata = (void *) array + sizeof(u32);
 
-		if (sample_overlap(event, p, data->raw_size))
+		if (sample_overlap(event, pdata, data->raw_size))
 			return -EFAULT;
 
-		data->raw_data = p;
+		data->raw_data = (void *) pdata;
 	}
 
 	return 0;
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index a16ecab5229d..9cf0d4393c8d 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -18,6 +18,13 @@ static inline int is_anon_memory(const char *filename)
 	return strcmp(filename, "//anon") == 0;
 }
 
+static inline int is_no_dso_memory(const char *filename)
+{
+	return !strcmp(filename, "[stack]") ||
+	       !strcmp(filename, "[vdso]")  ||
+	       !strcmp(filename, "[heap]");
+}
+
 void map__init(struct map *self, enum map_type type,
 	       u64 start, u64 end, u64 pgoff, struct dso *dso)
 {
@@ -42,9 +49,10 @@ struct map *map__new(struct list_head *dsos__list, u64 start, u64 len,
 	if (self != NULL) {
 		char newfilename[PATH_MAX];
 		struct dso *dso;
-		int anon;
+		int anon, no_dso;
 
 		anon = is_anon_memory(filename);
+		no_dso = is_no_dso_memory(filename);
 
 		if (anon) {
 			snprintf(newfilename, sizeof(newfilename), "/tmp/perf-%d.map", pid);
@@ -57,12 +65,16 @@ struct map *map__new(struct list_head *dsos__list, u64 start, u64 len,
 
 		map__init(self, type, start, start + len, pgoff, dso);
 
-		if (anon) {
-set_identity:
+		if (anon || no_dso) {
 			self->map_ip = self->unmap_ip = identity__map_ip;
-		} else if (strcmp(filename, "[vdso]") == 0) {
-			dso__set_loaded(dso, self->type);
-			goto set_identity;
+
+			/*
+			 * Set memory without DSO as loaded. All map__find_*
+			 * functions still return NULL, and we avoid the
+			 * unnecessary map__load warning.
+			 */
+			if (no_dso)
+				dso__set_loaded(dso, self->type);
 		}
 	}
 	return self;
@@ -220,55 +232,55 @@ u64 map__objdump_2ip(struct map *map, u64 addr)
 	return ip;
 }
 
-void map_groups__init(struct map_groups *self)
+void map_groups__init(struct map_groups *mg)
 {
 	int i;
 	for (i = 0; i < MAP__NR_TYPES; ++i) {
-		self->maps[i] = RB_ROOT;
-		INIT_LIST_HEAD(&self->removed_maps[i]);
+		mg->maps[i] = RB_ROOT;
+		INIT_LIST_HEAD(&mg->removed_maps[i]);
 	}
-	self->machine = NULL;
+	mg->machine = NULL;
 }
 
-static void maps__delete(struct rb_root *self)
+static void maps__delete(struct rb_root *maps)
 {
-	struct rb_node *next = rb_first(self);
+	struct rb_node *next = rb_first(maps);
 
 	while (next) {
 		struct map *pos = rb_entry(next, struct map, rb_node);
 
 		next = rb_next(&pos->rb_node);
-		rb_erase(&pos->rb_node, self);
+		rb_erase(&pos->rb_node, maps);
 		map__delete(pos);
 	}
 }
 
-static void maps__delete_removed(struct list_head *self)
+static void maps__delete_removed(struct list_head *maps)
 {
 	struct map *pos, *n;
 
-	list_for_each_entry_safe(pos, n, self, node) {
+	list_for_each_entry_safe(pos, n, maps, node) {
 		list_del(&pos->node);
 		map__delete(pos);
 	}
 }
 
-void map_groups__exit(struct map_groups *self)
+void map_groups__exit(struct map_groups *mg)
 {
 	int i;
 
 	for (i = 0; i < MAP__NR_TYPES; ++i) {
-		maps__delete(&self->maps[i]);
-		maps__delete_removed(&self->removed_maps[i]);
+		maps__delete(&mg->maps[i]);
+		maps__delete_removed(&mg->removed_maps[i]);
 	}
 }
 
-void map_groups__flush(struct map_groups *self)
+void map_groups__flush(struct map_groups *mg)
 {
 	int type;
 
 	for (type = 0; type < MAP__NR_TYPES; type++) {
-		struct rb_root *root = &self->maps[type];
+		struct rb_root *root = &mg->maps[type];
 		struct rb_node *next = rb_first(root);
 
 		while (next) {
@@ -280,17 +292,17 @@ void map_groups__flush(struct map_groups *self)
 			 * instance in some hist_entry instances, so
 			 * just move them to a separate list.
 			 */
-			list_add_tail(&pos->node, &self->removed_maps[pos->type]);
+			list_add_tail(&pos->node, &mg->removed_maps[pos->type]);
 		}
 	}
 }
 
-struct symbol *map_groups__find_symbol(struct map_groups *self,
+struct symbol *map_groups__find_symbol(struct map_groups *mg,
 				       enum map_type type, u64 addr,
 				       struct map **mapp,
 				       symbol_filter_t filter)
 {
-	struct map *map = map_groups__find(self, type, addr);
+	struct map *map = map_groups__find(mg, type, addr);
 
 	if (map != NULL) {
 		if (mapp != NULL)
@@ -301,7 +313,7 @@ struct symbol *map_groups__find_symbol(struct map_groups *self,
 	return NULL;
 }
 
-struct symbol *map_groups__find_symbol_by_name(struct map_groups *self,
+struct symbol *map_groups__find_symbol_by_name(struct map_groups *mg,
 					       enum map_type type,
 					       const char *name,
 					       struct map **mapp,
@@ -309,7 +321,7 @@ struct symbol *map_groups__find_symbol_by_name(struct map_groups *self,
 {
 	struct rb_node *nd;
 
-	for (nd = rb_first(&self->maps[type]); nd; nd = rb_next(nd)) {
+	for (nd = rb_first(&mg->maps[type]); nd; nd = rb_next(nd)) {
 		struct map *pos = rb_entry(nd, struct map, rb_node);
 		struct symbol *sym = map__find_symbol_by_name(pos, name, filter);
 
@@ -323,13 +335,13 @@ struct symbol *map_groups__find_symbol_by_name(struct map_groups *self,
 	return NULL;
 }
 
-size_t __map_groups__fprintf_maps(struct map_groups *self,
+size_t __map_groups__fprintf_maps(struct map_groups *mg,
 				  enum map_type type, int verbose, FILE *fp)
 {
 	size_t printed = fprintf(fp, "%s:\n", map_type__name[type]);
 	struct rb_node *nd;
 
-	for (nd = rb_first(&self->maps[type]); nd; nd = rb_next(nd)) {
+	for (nd = rb_first(&mg->maps[type]); nd; nd = rb_next(nd)) {
 		struct map *pos = rb_entry(nd, struct map, rb_node);
 		printed += fprintf(fp, "Map:");
 		printed += map__fprintf(pos, fp);
@@ -342,22 +354,22 @@ size_t __map_groups__fprintf_maps(struct map_groups *self,
 	return printed;
 }
 
-size_t map_groups__fprintf_maps(struct map_groups *self, int verbose, FILE *fp)
+size_t map_groups__fprintf_maps(struct map_groups *mg, int verbose, FILE *fp)
 {
 	size_t printed = 0, i;
 	for (i = 0; i < MAP__NR_TYPES; ++i)
-		printed += __map_groups__fprintf_maps(self, i, verbose, fp);
+		printed += __map_groups__fprintf_maps(mg, i, verbose, fp);
 	return printed;
 }
 
-static size_t __map_groups__fprintf_removed_maps(struct map_groups *self,
+static size_t __map_groups__fprintf_removed_maps(struct map_groups *mg,
 						 enum map_type type,
 						 int verbose, FILE *fp)
 {
 	struct map *pos;
 	size_t printed = 0;
 
-	list_for_each_entry(pos, &self->removed_maps[type], node) {
+	list_for_each_entry(pos, &mg->removed_maps[type], node) {
 		printed += fprintf(fp, "Map:");
 		printed += map__fprintf(pos, fp);
 		if (verbose > 1) {
@@ -368,26 +380,26 @@ static size_t __map_groups__fprintf_removed_maps(struct map_groups *self,
 	return printed;
 }
 
-static size_t map_groups__fprintf_removed_maps(struct map_groups *self,
+static size_t map_groups__fprintf_removed_maps(struct map_groups *mg,
 					       int verbose, FILE *fp)
 {
 	size_t printed = 0, i;
 	for (i = 0; i < MAP__NR_TYPES; ++i)
-		printed += __map_groups__fprintf_removed_maps(self, i, verbose, fp);
+		printed += __map_groups__fprintf_removed_maps(mg, i, verbose, fp);
 	return printed;
 }
 
-size_t map_groups__fprintf(struct map_groups *self, int verbose, FILE *fp)
+size_t map_groups__fprintf(struct map_groups *mg, int verbose, FILE *fp)
 {
-	size_t printed = map_groups__fprintf_maps(self, verbose, fp);
+	size_t printed = map_groups__fprintf_maps(mg, verbose, fp);
 	printed += fprintf(fp, "Removed maps:\n");
-	return printed + map_groups__fprintf_removed_maps(self, verbose, fp);
+	return printed + map_groups__fprintf_removed_maps(mg, verbose, fp);
 }
 
-int map_groups__fixup_overlappings(struct map_groups *self, struct map *map,
+int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map,
 				   int verbose, FILE *fp)
 {
-	struct rb_root *root = &self->maps[map->type];
+	struct rb_root *root = &mg->maps[map->type];
 	struct rb_node *next = rb_first(root);
 	int err = 0;
 
@@ -418,7 +430,7 @@ int map_groups__fixup_overlappings(struct map_groups *self, struct map *map,
 			}
 
 			before->end = map->start - 1;
-			map_groups__insert(self, before);
+			map_groups__insert(mg, before);
 			if (verbose >= 2)
 				map__fprintf(before, fp);
 		}
@@ -432,7 +444,7 @@ int map_groups__fixup_overlappings(struct map_groups *self, struct map *map,
 			}
 
 			after->start = map->end + 1;
-			map_groups__insert(self, after);
+			map_groups__insert(mg, after);
 			if (verbose >= 2)
 				map__fprintf(after, fp);
 		}
@@ -441,7 +453,7 @@ move_map:
 		 * If we have references, just move them to a separate list.
 		 */
 		if (pos->referenced)
-			list_add_tail(&pos->node, &self->removed_maps[map->type]);
+			list_add_tail(&pos->node, &mg->removed_maps[map->type]);
 		else
 			map__delete(pos);
 
@@ -455,7 +467,7 @@ move_map:
 /*
  * XXX This should not really _copy_ te maps, but refcount them.
  */
-int map_groups__clone(struct map_groups *self,
+int map_groups__clone(struct map_groups *mg,
 		      struct map_groups *parent, enum map_type type)
 {
 	struct rb_node *nd;
@@ -464,7 +476,7 @@ int map_groups__clone(struct map_groups *self,
 		struct map *new = map__clone(map);
 		if (new == NULL)
 			return -ENOMEM;
-		map_groups__insert(self, new);
+		map_groups__insert(mg, new);
 	}
 	return 0;
 }
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index b397c0383728..890d85545d0f 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -123,17 +123,17 @@ void map__fixup_end(struct map *self);
 
 void map__reloc_vmlinux(struct map *self);
 
-size_t __map_groups__fprintf_maps(struct map_groups *self,
+size_t __map_groups__fprintf_maps(struct map_groups *mg,
 				  enum map_type type, int verbose, FILE *fp);
 void maps__insert(struct rb_root *maps, struct map *map);
-void maps__remove(struct rb_root *self, struct map *map);
+void maps__remove(struct rb_root *maps, struct map *map);
 struct map *maps__find(struct rb_root *maps, u64 addr);
-void map_groups__init(struct map_groups *self);
-void map_groups__exit(struct map_groups *self);
-int map_groups__clone(struct map_groups *self,
+void map_groups__init(struct map_groups *mg);
+void map_groups__exit(struct map_groups *mg);
+int map_groups__clone(struct map_groups *mg,
 		      struct map_groups *parent, enum map_type type);
-size_t map_groups__fprintf(struct map_groups *self, int verbose, FILE *fp);
-size_t map_groups__fprintf_maps(struct map_groups *self, int verbose, FILE *fp);
+size_t map_groups__fprintf(struct map_groups *mg, int verbose, FILE *fp);
+size_t map_groups__fprintf_maps(struct map_groups *mg, int verbose, FILE *fp);
 
 typedef void (*machine__process_t)(struct machine *self, void *data);
 
@@ -162,29 +162,29 @@ static inline bool machine__is_host(struct machine *self)
 	return self ? self->pid == HOST_KERNEL_ID : false;
 }
 
-static inline void map_groups__insert(struct map_groups *self, struct map *map)
+static inline void map_groups__insert(struct map_groups *mg, struct map *map)
 {
-	maps__insert(&self->maps[map->type], map);
-	map->groups = self;
+	maps__insert(&mg->maps[map->type], map);
+	map->groups = mg;
 }
 
-static inline void map_groups__remove(struct map_groups *self, struct map *map)
+static inline void map_groups__remove(struct map_groups *mg, struct map *map)
 {
-	maps__remove(&self->maps[map->type], map);
+	maps__remove(&mg->maps[map->type], map);
 }
 
-static inline struct map *map_groups__find(struct map_groups *self,
+static inline struct map *map_groups__find(struct map_groups *mg,
 					   enum map_type type, u64 addr)
 {
-	return maps__find(&self->maps[type], addr);
+	return maps__find(&mg->maps[type], addr);
 }
 
-struct symbol *map_groups__find_symbol(struct map_groups *self,
+struct symbol *map_groups__find_symbol(struct map_groups *mg,
 				       enum map_type type, u64 addr,
 				       struct map **mapp,
 				       symbol_filter_t filter);
 
-struct symbol *map_groups__find_symbol_by_name(struct map_groups *self,
+struct symbol *map_groups__find_symbol_by_name(struct map_groups *mg,
 					       enum map_type type,
 					       const char *name,
 					       struct map **mapp,
@@ -208,11 +208,11 @@ struct symbol *machine__find_kernel_function(struct machine *self, u64 addr,
 }
 
 static inline
-struct symbol *map_groups__find_function_by_name(struct map_groups *self,
+struct symbol *map_groups__find_function_by_name(struct map_groups *mg,
 						 const char *name, struct map **mapp,
 						 symbol_filter_t filter)
 {
-	return map_groups__find_symbol_by_name(self, MAP__FUNCTION, name, mapp, filter);
+	return map_groups__find_symbol_by_name(mg, MAP__FUNCTION, name, mapp, filter);
 }
 
 static inline
@@ -225,13 +225,13 @@ struct symbol *machine__find_kernel_function_by_name(struct machine *self,
 						 filter);
 }
 
-int map_groups__fixup_overlappings(struct map_groups *self, struct map *map,
+int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map,
 				   int verbose, FILE *fp);
 
-struct map *map_groups__find_by_name(struct map_groups *self,
+struct map *map_groups__find_by_name(struct map_groups *mg,
 				     enum map_type type, const char *name);
 struct map *machine__new_module(struct machine *self, u64 start, const char *filename);
 
-void map_groups__flush(struct map_groups *self);
+void map_groups__flush(struct map_groups *mg);
 
 #endif /* __PERF_MAP_H */
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 555fc3864b90..5d732621a462 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -659,7 +659,7 @@ static int find_variable(Dwarf_Die *sc_die, struct probe_finder *pf)
 		if (!die_find_variable_at(&pf->cu_die, pf->pvar->var, 0, &vr_die))
 			ret = -ENOENT;
 	}
-	if (ret == 0)
+	if (ret >= 0)
 		ret = convert_variable(&vr_die, pf);
 
 	if (ret < 0)
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index cbc8f215d4b7..7624324efad4 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -803,7 +803,7 @@ 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_evsel__sample_size(first),
-					       sample_id_all, &pevent->sample);
+					       sample_id_all, &pevent->sample, false);
 		if (err)
 			return PyErr_Format(PyExc_OSError,
 					    "perf: can't parse sample, err=%d", err);
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 170601e67d6b..974d0cbee5e9 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -162,7 +162,8 @@ static inline int perf_session__parse_sample(struct perf_session *session,
 {
 	return perf_event__parse_sample(event, session->sample_type,
 					session->sample_size,
-					session->sample_id_all, sample);
+					session->sample_id_all, sample,
+					session->header.needs_swap);
 }
 
 struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session,
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 401e220566fd..1ee8f1e40f18 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -151,11 +151,17 @@ sort__sym_cmp(struct hist_entry *left, struct hist_entry *right)
 {
 	u64 ip_l, ip_r;
 
+	if (!left->ms.sym && !right->ms.sym)
+		return right->level - left->level;
+
+	if (!left->ms.sym || !right->ms.sym)
+		return cmp_null(left->ms.sym, right->ms.sym);
+
 	if (left->ms.sym == right->ms.sym)
 		return 0;
 
-	ip_l = left->ms.sym ? left->ms.sym->start : left->ip;
-	ip_r = right->ms.sym ? right->ms.sym->start : right->ip;
+	ip_l = left->ms.sym->start;
+	ip_r = right->ms.sym->start;
 
 	return (int64_t)(ip_r - ip_l);
 }
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 245e60d6b4e7..077df15ee705 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -76,16 +76,104 @@ static void dso__set_sorted_by_name(struct dso *dso, enum map_type type)
 
 bool symbol_type__is_a(char symbol_type, enum map_type map_type)
 {
+	symbol_type = toupper(symbol_type);
+
 	switch (map_type) {
 	case MAP__FUNCTION:
 		return symbol_type == 'T' || symbol_type == 'W';
 	case MAP__VARIABLE:
-		return symbol_type == 'D' || symbol_type == 'd';
+		return symbol_type == 'D';
 	default:
 		return false;
 	}
 }
 
+static int prefix_underscores_count(const char *str)
+{
+	const char *tail = str;
+
+	while (*tail == '_')
+		tail++;
+
+	return tail - str;
+}
+
+#define SYMBOL_A 0
+#define SYMBOL_B 1
+
+static int choose_best_symbol(struct symbol *syma, struct symbol *symb)
+{
+	s64 a;
+	s64 b;
+
+	/* Prefer a symbol with non zero length */
+	a = syma->end - syma->start;
+	b = symb->end - symb->start;
+	if ((b == 0) && (a > 0))
+		return SYMBOL_A;
+	else if ((a == 0) && (b > 0))
+		return SYMBOL_B;
+
+	/* Prefer a non weak symbol over a weak one */
+	a = syma->binding == STB_WEAK;
+	b = symb->binding == STB_WEAK;
+	if (b && !a)
+		return SYMBOL_A;
+	if (a && !b)
+		return SYMBOL_B;
+
+	/* Prefer a global symbol over a non global one */
+	a = syma->binding == STB_GLOBAL;
+	b = symb->binding == STB_GLOBAL;
+	if (a && !b)
+		return SYMBOL_A;
+	if (b && !a)
+		return SYMBOL_B;
+
+	/* Prefer a symbol with less underscores */
+	a = prefix_underscores_count(syma->name);
+	b = prefix_underscores_count(symb->name);
+	if (b > a)
+		return SYMBOL_A;
+	else if (a > b)
+		return SYMBOL_B;
+
+	/* If all else fails, choose the symbol with the longest name */
+	if (strlen(syma->name) >= strlen(symb->name))
+		return SYMBOL_A;
+	else
+		return SYMBOL_B;
+}
+
+static void symbols__fixup_duplicate(struct rb_root *symbols)
+{
+	struct rb_node *nd;
+	struct symbol *curr, *next;
+
+	nd = rb_first(symbols);
+
+	while (nd) {
+		curr = rb_entry(nd, struct symbol, rb_node);
+again:
+		nd = rb_next(&curr->rb_node);
+		next = rb_entry(nd, struct symbol, rb_node);
+
+		if (!nd)
+			break;
+
+		if (curr->start != next->start)
+			continue;
+
+		if (choose_best_symbol(curr, next) == SYMBOL_A) {
+			rb_erase(&next->rb_node, symbols);
+			goto again;
+		} else {
+			nd = rb_next(&curr->rb_node);
+			rb_erase(&curr->rb_node, symbols);
+		}
+	}
+}
+
 static void symbols__fixup_end(struct rb_root *symbols)
 {
 	struct rb_node *nd, *prevnd = rb_first(symbols);
@@ -440,18 +528,11 @@ int kallsyms__parse(const char *filename, void *arg,
 	char *line = NULL;
 	size_t n;
 	int err = -1;
-	u64 prev_start = 0;
-	char prev_symbol_type = 0;
-	char *prev_symbol_name;
 	FILE *file = fopen(filename, "r");
 
 	if (file == NULL)
 		goto out_failure;
 
-	prev_symbol_name = malloc(KSYM_NAME_LEN);
-	if (prev_symbol_name == NULL)
-		goto out_close;
-
 	err = 0;
 
 	while (!feof(file)) {
@@ -472,7 +553,7 @@ int kallsyms__parse(const char *filename, void *arg,
 		if (len + 2 >= line_len)
 			continue;
 
-		symbol_type = toupper(line[len]);
+		symbol_type = line[len];
 		len += 2;
 		symbol_name = line + len;
 		len = line_len - len;
@@ -482,24 +563,18 @@ int kallsyms__parse(const char *filename, void *arg,
 			break;
 		}
 
-		if (prev_symbol_type) {
-			u64 end = start;
-			if (end != prev_start)
-				--end;
-			err = process_symbol(arg, prev_symbol_name,
-					     prev_symbol_type, prev_start, end);
-			if (err)
-				break;
-		}
-
-		memcpy(prev_symbol_name, symbol_name, len + 1);
-		prev_symbol_type = symbol_type;
-		prev_start = start;
+		/*
+		 * module symbols are not sorted so we add all
+		 * symbols with zero length and rely on
+		 * symbols__fixup_end() to fix it up.
+		 */
+		err = process_symbol(arg, symbol_name,
+				     symbol_type, start, start);
+		if (err)
+			break;
 	}
 
-	free(prev_symbol_name);
 	free(line);
-out_close:
 	fclose(file);
 	return err;
 
@@ -705,6 +780,9 @@ int dso__load_kallsyms(struct dso *dso, const char *filename,
 	if (dso__load_all_kallsyms(dso, filename, map) < 0)
 		return -1;
 
+	symbols__fixup_duplicate(&dso->symbols[map->type]);
+	symbols__fixup_end(&dso->symbols[map->type]);
+
 	if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
 		dso->symtab_type = SYMTAB__GUEST_KALLSYMS;
 	else
@@ -1094,8 +1172,7 @@ static int dso__load_sym(struct dso *dso, struct map *map, const char *name,
 	if (dso->has_build_id) {
 		u8 build_id[BUILD_ID_SIZE];
 
-		if (elf_read_build_id(elf, build_id,
-				      BUILD_ID_SIZE) != BUILD_ID_SIZE)
+		if (elf_read_build_id(elf, build_id, BUILD_ID_SIZE) < 0)
 			goto out_elf_end;
 
 		if (!dso__build_id_equal(dso, build_id))
@@ -1113,6 +1190,8 @@ static int dso__load_sym(struct dso *dso, struct map *map, const char *name,
 	}
 
 	opdsec = elf_section_by_name(elf, &ehdr, &opdshdr, ".opd", &opdidx);
+	if (opdshdr.sh_type != SHT_PROGBITS)
+		opdsec = NULL;
 	if (opdsec)
 		opddata = elf_rawdata(opdsec, NULL);
 
@@ -1278,6 +1357,7 @@ new_symbol:
 	 * For misannotated, zeroed, ASM function sizes.
 	 */
 	if (nr > 0) {
+		symbols__fixup_duplicate(&dso->symbols[map->type]);
 		symbols__fixup_end(&dso->symbols[map->type]);
 		if (kmap) {
 			/*
@@ -1364,8 +1444,8 @@ static int elf_read_build_id(Elf *elf, void *bf, size_t size)
 	ptr = data->d_buf;
 	while (ptr < (data->d_buf + data->d_size)) {
 		GElf_Nhdr *nhdr = ptr;
-		int namesz = NOTE_ALIGN(nhdr->n_namesz),
-		    descsz = NOTE_ALIGN(nhdr->n_descsz);
+		size_t namesz = NOTE_ALIGN(nhdr->n_namesz),
+		       descsz = NOTE_ALIGN(nhdr->n_descsz);
 		const char *name;
 
 		ptr += sizeof(*nhdr);
@@ -1374,8 +1454,10 @@ static int elf_read_build_id(Elf *elf, void *bf, size_t size)
 		if (nhdr->n_type == NT_GNU_BUILD_ID &&
 		    nhdr->n_namesz == sizeof("GNU")) {
 			if (memcmp(name, "GNU", sizeof("GNU")) == 0) {
-				memcpy(bf, ptr, BUILD_ID_SIZE);
-				err = BUILD_ID_SIZE;
+				size_t sz = min(size, descsz);
+				memcpy(bf, ptr, sz);
+				memset(bf + sz, 0, size - sz);
+				err = descsz;
 				break;
 			}
 		}
@@ -1427,7 +1509,7 @@ int sysfs__read_build_id(const char *filename, void *build_id, size_t size)
 	while (1) {
 		char bf[BUFSIZ];
 		GElf_Nhdr nhdr;
-		int namesz, descsz;
+		size_t namesz, descsz;
 
 		if (read(fd, &nhdr, sizeof(nhdr)) != sizeof(nhdr))
 			break;
@@ -1436,15 +1518,16 @@ int sysfs__read_build_id(const char *filename, void *build_id, size_t size)
 		descsz = NOTE_ALIGN(nhdr.n_descsz);
 		if (nhdr.n_type == NT_GNU_BUILD_ID &&
 		    nhdr.n_namesz == sizeof("GNU")) {
-			if (read(fd, bf, namesz) != namesz)
+			if (read(fd, bf, namesz) != (ssize_t)namesz)
 				break;
 			if (memcmp(bf, "GNU", sizeof("GNU")) == 0) {
-				if (read(fd, build_id,
-				    BUILD_ID_SIZE) == BUILD_ID_SIZE) {
+				size_t sz = min(descsz, size);
+				if (read(fd, build_id, sz) == (ssize_t)sz) {
+					memset(build_id + sz, 0, size - sz);
 					err = 0;
 					break;
 				}
-			} else if (read(fd, bf, descsz) != descsz)
+			} else if (read(fd, bf, descsz) != (ssize_t)descsz)
 				break;
 		} else {
 			int n = namesz + descsz;
diff --git a/tools/perf/util/top.h b/tools/perf/util/top.h
index bfbf95bcc603..b07b0410463c 100644
--- a/tools/perf/util/top.h
+++ b/tools/perf/util/top.h
@@ -10,6 +10,7 @@
 
 struct perf_evlist;
 struct perf_evsel;
+struct perf_session;
 
 struct sym_entry {
 	struct rb_node		rb_node;
@@ -38,6 +39,7 @@ struct perf_top {
 	u64		   kernel_samples, us_samples;
 	u64		   exact_samples;
 	u64		   guest_us_samples, guest_kernel_samples;
+	u64		   total_lost_warned;
 	int		   print_entries, count_filter, delay_secs;
 	int		   display_weighted, freq, rb_entries;
 	pid_t		   target_pid, target_tid;
@@ -45,6 +47,7 @@ struct perf_top {
 	const char	   *cpu_list;
 	struct sym_entry   *sym_filter_entry;
 	struct perf_evsel  *sym_evsel;
+	struct perf_session *session;
 };
 
 size_t perf_top__header_snprintf(struct perf_top *top, char *bf, size_t size);
diff --git a/tools/perf/util/ui/browsers/top.c b/tools/perf/util/ui/browsers/top.c
index 88403cf8396a..9b6b43b32ac8 100644
--- a/tools/perf/util/ui/browsers/top.c
+++ b/tools/perf/util/ui/browsers/top.c
@@ -11,10 +11,12 @@
 #include "../helpline.h"
 #include "../libslang.h"
 #include "../util.h"
+#include "../ui.h"
 #include "../../evlist.h"
 #include "../../hist.h"
 #include "../../sort.h"
 #include "../../symbol.h"
+#include "../../session.h"
 #include "../../top.h"
 
 struct perf_top_browser {
@@ -43,10 +45,10 @@ static void perf_top_browser__write(struct ui_browser *browser, void *entry, int
 
 	if (top->evlist->nr_entries == 1 || !top->display_weighted) {
 		slsmg_printf("%20.2f ", syme->weight);
-		width -= 24;
+		width -= 21;
 	} else {
 		slsmg_printf("%9.1f %10ld ", syme->weight, syme->snap_count);
-		width -= 23;
+		width -= 20;
 	}
 
 	slsmg_printf("%4.1f%%", pcnt);
@@ -143,6 +145,25 @@ do_annotation:
 	symbol__tui_annotate(sym, syme->map, 0, top->delay_secs * 1000);
 }
 
+static void perf_top_browser__warn_lost(struct perf_top_browser *browser)
+{
+	struct perf_top *top = browser->b.priv;
+	char msg[128];
+	int len;
+
+	top->total_lost_warned = top->session->hists.stats.total_lost;
+	pthread_mutex_lock(&ui__lock);
+	ui_browser__set_color(&browser->b, HE_COLORSET_TOP);
+	len = snprintf(msg, sizeof(msg),
+		      " WARNING: LOST %" PRIu64 " events, Check IO/CPU overload",
+		      top->total_lost_warned);
+	if (len > browser->b.width)
+		len = browser->b.width;
+	SLsmg_gotorc(0, browser->b.width - len);
+	slsmg_write_nstring(msg, len);
+	pthread_mutex_unlock(&ui__lock);
+}
+
 static int perf_top_browser__run(struct perf_top_browser *browser)
 {
 	int key;
@@ -174,6 +195,9 @@ static int perf_top_browser__run(struct perf_top_browser *browser)
 			ui_browser__set_color(&browser->b, NEWT_COLORSET_ROOT);
 			SLsmg_gotorc(0, 0);
 			slsmg_write_nstring(title, browser->b.width);
+
+			if (top->total_lost_warned != top->session->hists.stats.total_lost)
+				perf_top_browser__warn_lost(browser);
 			break;
 		case 'a':
 		case NEWT_KEY_RIGHT: