From 0a269a6bb3f86abb218b8632f13c4ecd9b6b92af Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Tue, 5 Jul 2016 08:56:03 +0200
Subject: [PATCH 01/66] perf hists: Introduce hist_entry__init function

Move the 'struct hist_entry' initialization code to a separate function.
It'll be useful and more clear for the following patches that introduce
allocation callbacks.

Releasing the hist_entry object in hist_entry__new function
(where it's allocated) rather than in hist_entry__init.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1467701765-26194-2-git-send-email-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/hist.c | 139 ++++++++++++++++++++++-------------------
 1 file changed, 73 insertions(+), 66 deletions(-)

diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index e1fcc8d7c01a8..04f3b52a319c6 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -352,86 +352,93 @@ void hists__delete_entries(struct hists *hists)
  * histogram, sorted on item, collects periods
  */
 
-static struct hist_entry *hist_entry__new(struct hist_entry *template,
-					  bool sample_self)
-{
-	size_t callchain_size = 0;
-	struct hist_entry *he;
+static int hist_entry__init(struct hist_entry *he,
+			    struct hist_entry *template,
+			    bool sample_self)
+{
+	*he = *template;
+
+	if (symbol_conf.cumulate_callchain) {
+		he->stat_acc = malloc(sizeof(he->stat));
+		if (he->stat_acc == NULL)
+			return -ENOMEM;
+		memcpy(he->stat_acc, &he->stat, sizeof(he->stat));
+		if (!sample_self)
+			memset(&he->stat, 0, sizeof(he->stat));
+	}
 
-	if (symbol_conf.use_callchain)
-		callchain_size = sizeof(struct callchain_root);
+	map__get(he->ms.map);
 
-	he = zalloc(sizeof(*he) + callchain_size);
+	if (he->branch_info) {
+		/*
+		 * This branch info is (a part of) allocated from
+		 * sample__resolve_bstack() and will be freed after
+		 * adding new entries.  So we need to save a copy.
+		 */
+		he->branch_info = malloc(sizeof(*he->branch_info));
+		if (he->branch_info == NULL) {
+			map__zput(he->ms.map);
+			free(he->stat_acc);
+			return -ENOMEM;
+		}
 
-	if (he != NULL) {
-		*he = *template;
+		memcpy(he->branch_info, template->branch_info,
+		       sizeof(*he->branch_info));
 
-		if (symbol_conf.cumulate_callchain) {
-			he->stat_acc = malloc(sizeof(he->stat));
-			if (he->stat_acc == NULL) {
-				free(he);
-				return NULL;
-			}
-			memcpy(he->stat_acc, &he->stat, sizeof(he->stat));
-			if (!sample_self)
-				memset(&he->stat, 0, sizeof(he->stat));
-		}
+		map__get(he->branch_info->from.map);
+		map__get(he->branch_info->to.map);
+	}
 
-		map__get(he->ms.map);
+	if (he->mem_info) {
+		map__get(he->mem_info->iaddr.map);
+		map__get(he->mem_info->daddr.map);
+	}
 
-		if (he->branch_info) {
-			/*
-			 * This branch info is (a part of) allocated from
-			 * sample__resolve_bstack() and will be freed after
-			 * adding new entries.  So we need to save a copy.
-			 */
-			he->branch_info = malloc(sizeof(*he->branch_info));
-			if (he->branch_info == NULL) {
-				map__zput(he->ms.map);
-				free(he->stat_acc);
-				free(he);
-				return NULL;
-			}
+	if (symbol_conf.use_callchain)
+		callchain_init(he->callchain);
 
-			memcpy(he->branch_info, template->branch_info,
-			       sizeof(*he->branch_info));
+	if (he->raw_data) {
+		he->raw_data = memdup(he->raw_data, he->raw_size);
 
-			map__get(he->branch_info->from.map);
-			map__get(he->branch_info->to.map);
+		if (he->raw_data == NULL) {
+			map__put(he->ms.map);
+			if (he->branch_info) {
+				map__put(he->branch_info->from.map);
+				map__put(he->branch_info->to.map);
+				free(he->branch_info);
+			}
+			if (he->mem_info) {
+				map__put(he->mem_info->iaddr.map);
+				map__put(he->mem_info->daddr.map);
+			}
+			free(he->stat_acc);
+			return -ENOMEM;
 		}
+	}
+	INIT_LIST_HEAD(&he->pairs.node);
+	thread__get(he->thread);
 
-		if (he->mem_info) {
-			map__get(he->mem_info->iaddr.map);
-			map__get(he->mem_info->daddr.map);
-		}
+	if (!symbol_conf.report_hierarchy)
+		he->leaf = true;
 
-		if (symbol_conf.use_callchain)
-			callchain_init(he->callchain);
+	return 0;
+}
 
-		if (he->raw_data) {
-			he->raw_data = memdup(he->raw_data, he->raw_size);
+static struct hist_entry *hist_entry__new(struct hist_entry *template,
+					  bool sample_self)
+{
+	size_t callchain_size = 0;
+	struct hist_entry *he;
+	int err = 0;
 
-			if (he->raw_data == NULL) {
-				map__put(he->ms.map);
-				if (he->branch_info) {
-					map__put(he->branch_info->from.map);
-					map__put(he->branch_info->to.map);
-					free(he->branch_info);
-				}
-				if (he->mem_info) {
-					map__put(he->mem_info->iaddr.map);
-					map__put(he->mem_info->daddr.map);
-				}
-				free(he->stat_acc);
-				free(he);
-				return NULL;
-			}
-		}
-		INIT_LIST_HEAD(&he->pairs.node);
-		thread__get(he->thread);
+	if (symbol_conf.use_callchain)
+		callchain_size = sizeof(struct callchain_root);
 
-		if (!symbol_conf.report_hierarchy)
-			he->leaf = true;
+	he = zalloc(sizeof(*he) + callchain_size);
+	if (he) {
+		err = hist_entry__init(he, template, sample_self);
+		if (err)
+			zfree(&he);
 	}
 
 	return he;

From f542e7670e48bc9d0aed351c1fd2ae0b65cc6f68 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Tue, 5 Jul 2016 08:56:04 +0200
Subject: [PATCH 02/66] perf hists: Introduce hist_entry_ops

Introducing allocation callbacks, that allows to extend current
hist_entry object into objects with special needs without polluting the
current hist_entry object.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1467701765-26194-3-git-send-email-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/hist.c | 31 +++++++++++++++++++++++++++----
 tools/perf/util/sort.h |  6 ++++++
 2 files changed, 33 insertions(+), 4 deletions(-)

diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 04f3b52a319c6..355b7601ddb7c 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -424,21 +424,42 @@ static int hist_entry__init(struct hist_entry *he,
 	return 0;
 }
 
+static void *hist_entry__zalloc(size_t size)
+{
+	return zalloc(size + sizeof(struct hist_entry));
+}
+
+static void hist_entry__free(void *ptr)
+{
+	free(ptr);
+}
+
+static struct hist_entry_ops default_ops = {
+	.new	= hist_entry__zalloc,
+	.free	= hist_entry__free,
+};
+
 static struct hist_entry *hist_entry__new(struct hist_entry *template,
 					  bool sample_self)
 {
+	struct hist_entry_ops *ops = template->ops;
 	size_t callchain_size = 0;
 	struct hist_entry *he;
 	int err = 0;
 
+	if (!ops)
+		ops = template->ops = &default_ops;
+
 	if (symbol_conf.use_callchain)
 		callchain_size = sizeof(struct callchain_root);
 
-	he = zalloc(sizeof(*he) + callchain_size);
+	he = ops->new(callchain_size);
 	if (he) {
 		err = hist_entry__init(he, template, sample_self);
-		if (err)
-			zfree(&he);
+		if (err) {
+			ops->free(he);
+			he = NULL;
+		}
 	}
 
 	return he;
@@ -1050,6 +1071,8 @@ hist_entry__collapse(struct hist_entry *left, struct hist_entry *right)
 
 void hist_entry__delete(struct hist_entry *he)
 {
+	struct hist_entry_ops *ops = he->ops;
+
 	thread__zput(he->thread);
 	map__zput(he->ms.map);
 
@@ -1074,7 +1097,7 @@ void hist_entry__delete(struct hist_entry *he)
 	free_callchain(he->callchain);
 	free(he->trace_output);
 	free(he->raw_data);
-	free(he);
+	ops->free(he);
 }
 
 /*
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index ebb59cacd092f..7ca37ea173955 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -67,6 +67,11 @@ struct hist_entry_diff {
 	};
 };
 
+struct hist_entry_ops {
+	void	*(*new)(size_t size);
+	void	(*free)(void *ptr);
+};
+
 /**
  * struct hist_entry - histogram entry
  *
@@ -125,6 +130,7 @@ struct hist_entry {
 	void			*trace_output;
 	struct perf_hpp_list	*hpp_list;
 	struct hist_entry	*parent_he;
+	struct hist_entry_ops	*ops;
 	union {
 		/* this is for hierarchical entry structure */
 		struct {

From a5051979f533afc65112cc42a20f25db08bf2272 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Tue, 5 Jul 2016 08:56:05 +0200
Subject: [PATCH 03/66] perf hists: Introduce hists__add_entry_ops function

Introducing hists__add_entry_ops function to allow using the allocation
callbacks externally.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1467701765-26194-4-git-send-email-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/hist.c | 42 +++++++++++++++++++++++++++++++++++-------
 tools/perf/util/hist.h | 11 +++++++++++
 2 files changed, 46 insertions(+), 7 deletions(-)

diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 355b7601ddb7c..a18d142cdca3c 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -559,13 +559,15 @@ static struct hist_entry *hists__findnew_entry(struct hists *hists,
 	return he;
 }
 
-struct hist_entry *hists__add_entry(struct hists *hists,
-				    struct addr_location *al,
-				    struct symbol *sym_parent,
-				    struct branch_info *bi,
-				    struct mem_info *mi,
-				    struct perf_sample *sample,
-				    bool sample_self)
+static struct hist_entry*
+__hists__add_entry(struct hists *hists,
+		   struct addr_location *al,
+		   struct symbol *sym_parent,
+		   struct branch_info *bi,
+		   struct mem_info *mi,
+		   struct perf_sample *sample,
+		   bool sample_self,
+		   struct hist_entry_ops *ops)
 {
 	struct hist_entry entry = {
 		.thread	= al->thread,
@@ -592,11 +594,37 @@ struct hist_entry *hists__add_entry(struct hists *hists,
 		.transaction = sample->transaction,
 		.raw_data = sample->raw_data,
 		.raw_size = sample->raw_size,
+		.ops = ops,
 	};
 
 	return hists__findnew_entry(hists, &entry, al, sample_self);
 }
 
+struct hist_entry *hists__add_entry(struct hists *hists,
+				    struct addr_location *al,
+				    struct symbol *sym_parent,
+				    struct branch_info *bi,
+				    struct mem_info *mi,
+				    struct perf_sample *sample,
+				    bool sample_self)
+{
+	return __hists__add_entry(hists, al, sym_parent, bi, mi,
+				  sample, sample_self, NULL);
+}
+
+struct hist_entry *hists__add_entry_ops(struct hists *hists,
+					struct hist_entry_ops *ops,
+					struct addr_location *al,
+					struct symbol *sym_parent,
+					struct branch_info *bi,
+					struct mem_info *mi,
+					struct perf_sample *sample,
+					bool sample_self)
+{
+	return __hists__add_entry(hists, al, sym_parent, bi, mi,
+				  sample, sample_self, ops);
+}
+
 static int
 iter_next_nop_entry(struct hist_entry_iter *iter __maybe_unused,
 		    struct addr_location *al __maybe_unused)
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 0a03e08be5036..49aa4fac148f9 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -10,6 +10,7 @@
 #include "ui/progress.h"
 
 struct hist_entry;
+struct hist_entry_ops;
 struct addr_location;
 struct symbol;
 
@@ -127,6 +128,16 @@ struct hist_entry *hists__add_entry(struct hists *hists,
 				    struct mem_info *mi,
 				    struct perf_sample *sample,
 				    bool sample_self);
+
+struct hist_entry *hists__add_entry_ops(struct hists *hists,
+					struct hist_entry_ops *ops,
+					struct addr_location *al,
+					struct symbol *sym_parent,
+					struct branch_info *bi,
+					struct mem_info *mi,
+					struct perf_sample *sample,
+					bool sample_self);
+
 int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al,
 			 int max_stack_depth, void *arg);
 

From c09615f29c70d4155986f55097a99ad8f2036ca1 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 5 Jul 2016 11:05:24 -0300
Subject: [PATCH 04/66] perf ui stdio: Add way to setup the color output mode
 selection

In --stdio we turn off color output when the output is not a tty,
which is not always desirable, for instance, in:

  perf annotate | more

the 'more' tool is perfectly capable of processing the escape sequences
for colored output.

Allow using the existing logic for .perfconfig's "color.ui" to be used
from the command line by providing a stdio__config_color() helper, that
will be used by annotate and report in follow up patches.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-1u4wjdbcc41dxndsb4klpa9y@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/ui/setup.c | 7 +++++++
 tools/perf/ui/ui.h    | 4 ++++
 2 files changed, 11 insertions(+)

diff --git a/tools/perf/ui/setup.c b/tools/perf/ui/setup.c
index ba51fa8a1176d..1f6b0994f4f41 100644
--- a/tools/perf/ui/setup.c
+++ b/tools/perf/ui/setup.c
@@ -60,6 +60,13 @@ static inline int setup_gtk_browser(void) { return -1; }
 static inline void exit_gtk_browser(bool wait_for_ok __maybe_unused) {}
 #endif
 
+int stdio__config_color(const struct option *opt __maybe_unused,
+			const char *mode, int unset __maybe_unused)
+{
+	perf_use_color_default = perf_config_colorbool("color.ui", mode, -1);
+	return 0;
+}
+
 void setup_browser(bool fallback_to_pager)
 {
 	if (use_browser < 2 && (!isatty(1) || dump_trace))
diff --git a/tools/perf/ui/ui.h b/tools/perf/ui/ui.h
index ab88383f8be85..4b6fb6c7a542c 100644
--- a/tools/perf/ui/ui.h
+++ b/tools/perf/ui/ui.h
@@ -26,4 +26,8 @@ static inline void ui__exit(bool wait_for_ok __maybe_unused) {}
 
 void ui__refresh_dimensions(bool force);
 
+struct option;
+
+int stdio__config_color(const struct option *opt, const char *mode, int unset);
+
 #endif /* _PERF_UI_H_ */

From 53fe4ba1da92892f5a76fdc51b699eeb6b808a3a Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 5 Jul 2016 11:08:17 -0300
Subject: [PATCH 05/66] perf annotate: Introduce --stdio-color to setup the
 color output mode selection

'perf annotate --stdio' will colorize entries with most hits and
possibly some other aspects of its output, but those colors gets
suppressed if we redirect the output to a non-tty, allow keeping the
colors by adding a new option, --stdio-color, now this use case will
also output escape sequences for colors:

  $ perf annotate --stdio-color | more

Based-on-a-patch-by: Peter Zijlstra <peterz@infradead.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-sjrnixani5pg6qez640gaxhf@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Documentation/perf-annotate.txt | 7 +++++++
 tools/perf/builtin-annotate.c              | 3 +++
 2 files changed, 10 insertions(+)

diff --git a/tools/perf/Documentation/perf-annotate.txt b/tools/perf/Documentation/perf-annotate.txt
index 778f54d4d0bd7..8ffbd272952d2 100644
--- a/tools/perf/Documentation/perf-annotate.txt
+++ b/tools/perf/Documentation/perf-annotate.txt
@@ -61,6 +61,13 @@ OPTIONS
 
 --stdio:: Use the stdio interface.
 
+--stdio-color::
+	'always', 'never' or 'auto', allowing configuring color output
+	via the command line, in addition to via "color.ui" .perfconfig.
+	Use '--stdio-color always' to generate color even when redirecting
+	to a pipe or file. Using just '--stdio-color' is equivalent to
+	using 'always'.
+
 --tui:: Use the TUI interface. Use of --tui requires a tty, if one is not
 	present, as when piping to other commands, the stdio interface is
 	used. This interfaces starts by centering on the line with more
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index b15e7683f38c9..9c1034d81b4fe 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -339,6 +339,9 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused)
 		    "Show event group information together"),
 	OPT_BOOLEAN(0, "show-total-period", &symbol_conf.show_total_period,
 		    "Show a column with the sum of periods"),
+	OPT_CALLBACK_DEFAULT(0, "stdio-color", NULL, "mode",
+			     "'always' (default), 'never' or 'auto' only applicable to --stdio mode",
+			     stdio__config_color, "always"),
 	OPT_END()
 	};
 	int ret = hists__init();

From 175b968b81ba3bef0b39618714eb23d6675a935c Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 5 Jul 2016 11:14:38 -0300
Subject: [PATCH 06/66] perf report: Introduce --stdio-color to setup the color
 output mode selection

'perf report --stdio' will colorize entries with most hits and possibly
some other aspects of its output, but those colors gets suppressed if we
redirect the output to a non-tty, allow keeping the colors by adding a
new option, --stdio-color, now this use case will also output escape
sequences for colors:

  $ perf annotate --stdio-color | more

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-3iuawqjldu4i8gziot7e3d5n@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Documentation/perf-report.txt | 7 +++++++
 tools/perf/builtin-report.c              | 3 +++
 2 files changed, 10 insertions(+)

diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index 9cbddc290affd..2d1746295abf1 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -265,6 +265,13 @@ OPTIONS
 
 --stdio:: Use the stdio interface.
 
+--stdio-color::
+	'always', 'never' or 'auto', allowing configuring color output
+	via the command line, in addition to via "color.ui" .perfconfig.
+	Use '--stdio-color always' to generate color even when redirecting
+	to a pipe or file. Using just '--stdio-color' is equivalent to
+	using 'always'.
+
 --tui:: Use the TUI interface, that is integrated with annotate and allows
         zooming into DSOs or threads, among other features. Use of --tui
 	requires a tty, if one is not present, as when piping to other
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index f6cb357986c6f..949e5a15c960e 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -817,6 +817,9 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 		    "Show raw trace event output (do not use print fmt or plugins)"),
 	OPT_BOOLEAN(0, "hierarchy", &symbol_conf.report_hierarchy,
 		    "Show entries in a hierarchy"),
+	OPT_CALLBACK_DEFAULT(0, "stdio-color", NULL, "mode",
+			     "'always' (default), 'never' or 'auto' only applicable to --stdio mode",
+			     stdio__config_color, "always"),
 	OPT_END()
 	};
 	struct perf_data_file file = {

From 0e91e6bfd3514fe30925891ec5f468b7d2c11d56 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 5 Jul 2016 14:42:31 -0300
Subject: [PATCH 07/66] perf trace beauty msg_flags: Remove MSG_TRYHARD

It is the same as MSG_DONTROUTE and is only defined together with
_GNU_SOURCE.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-q4vbov6jl0e0152y01kv2htw@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/trace/beauty/msg_flags.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/tools/perf/trace/beauty/msg_flags.c b/tools/perf/trace/beauty/msg_flags.c
index 07fa8a0acad6a..1106c8960cc4b 100644
--- a/tools/perf/trace/beauty/msg_flags.c
+++ b/tools/perf/trace/beauty/msg_flags.c
@@ -33,7 +33,6 @@ static size_t syscall_arg__scnprintf_msg_flags(char *bf, size_t size,
 	P_MSG_FLAG(OOB);
 	P_MSG_FLAG(PEEK);
 	P_MSG_FLAG(DONTROUTE);
-	P_MSG_FLAG(TRYHARD);
 	P_MSG_FLAG(CTRUNC);
 	P_MSG_FLAG(PROBE);
 	P_MSG_FLAG(TRUNC);

From f8e018704cdf2a741477b8fd8ee0a313caf87f72 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 5 Jul 2016 14:43:27 -0300
Subject: [PATCH 08/66] perf trace beauty flock: Add missing fcntl.h include

Those beautifiers need to make sure they include what they reference,
as changes in builtin-trace.c may end up removing needed stuff, like
when undefining _GNU_SOURCE.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-2etqhfmgv5jcnfwnkbwadns2@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/trace/beauty/flock.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/perf/trace/beauty/flock.c b/tools/perf/trace/beauty/flock.c
index 021bb48c63361..34b6348edb6ee 100644
--- a/tools/perf/trace/beauty/flock.c
+++ b/tools/perf/trace/beauty/flock.c
@@ -1,3 +1,4 @@
+#include <fcntl.h>
 
 static size_t syscall_arg__scnprintf_flock(char *bf, size_t size,
 					   struct syscall_arg *arg)

From 9d4a94cabcffd1f069666ddf9ad3cdc25565eec6 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 5 Jul 2016 14:43:27 -0300
Subject: [PATCH 09/66] perf trace beauty open_flags: Add missing headers

Those beautifiers need to make sure they include what they reference,
as changes in builtin-trace.c may end up removing needed stuff, like
when undefining _GNU_SOURCE.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-a9cz8za6lqutfapn5e7uum09@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/trace/beauty/open_flags.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/tools/perf/trace/beauty/open_flags.c b/tools/perf/trace/beauty/open_flags.c
index 0f3679e0cdcf7..9c3a4cb3bd35c 100644
--- a/tools/perf/trace/beauty/open_flags.c
+++ b/tools/perf/trace/beauty/open_flags.c
@@ -1,3 +1,6 @@
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
 
 static size_t syscall_arg__scnprintf_open_flags(char *bf, size_t size,
 					       struct syscall_arg *arg)

From 256763b01741ec74bbecb3021baee229727935e6 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 5 Jul 2016 14:43:27 -0300
Subject: [PATCH 10/66] perf trace beauty mmap: Add more conditional defines

Don't handle some flags only if they have its defines in headers at
time of building, define what is missing.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-czbmxb01xzcl3h2qxuzoqkj5@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/trace/beauty/mmap.c | 77 ++++++++++++++++++++++++----------
 1 file changed, 55 insertions(+), 22 deletions(-)

diff --git a/tools/perf/trace/beauty/mmap.c b/tools/perf/trace/beauty/mmap.c
index 3444a4d5382d1..d0a3a8e402e74 100644
--- a/tools/perf/trace/beauty/mmap.c
+++ b/tools/perf/trace/beauty/mmap.c
@@ -1,5 +1,9 @@
 #include <sys/mman.h>
 
+#ifndef PROT_SEM
+#define PROT_SEM 0x8
+#endif
+
 static size_t syscall_arg__scnprintf_mmap_prot(char *bf, size_t size,
 					       struct syscall_arg *arg)
 {
@@ -16,9 +20,7 @@ static size_t syscall_arg__scnprintf_mmap_prot(char *bf, size_t size,
 	P_MMAP_PROT(EXEC);
 	P_MMAP_PROT(READ);
 	P_MMAP_PROT(WRITE);
-#ifdef PROT_SEM
 	P_MMAP_PROT(SEM);
-#endif
 	P_MMAP_PROT(GROWSDOWN);
 	P_MMAP_PROT(GROWSUP);
 #undef P_MMAP_PROT
@@ -31,10 +33,31 @@ static size_t syscall_arg__scnprintf_mmap_prot(char *bf, size_t size,
 
 #define SCA_MMAP_PROT syscall_arg__scnprintf_mmap_prot
 
+#ifndef MAP_FIXED
+#define MAP_FIXED		     0x10
+#endif
+
+#ifndef MAP_ANONYMOUS
+#define MAP_ANONYMOUS		     0x20
+#endif
+
+#ifndef MAP_32BIT
+#define MAP_32BIT		     0x40
+#endif
+
 #ifndef MAP_STACK
-# define MAP_STACK		0x20000
+#define MAP_STACK		  0x20000
 #endif
 
+#ifndef MAP_HUGETLB
+#define MAP_HUGETLB		  0x40000
+#endif
+
+#ifndef MAP_UNINITIALIZED
+#define MAP_UNINITIALIZED	0x4000000
+#endif
+
+
 static size_t syscall_arg__scnprintf_mmap_flags(char *bf, size_t size,
 						struct syscall_arg *arg)
 {
@@ -48,26 +71,20 @@ static size_t syscall_arg__scnprintf_mmap_flags(char *bf, size_t size,
 
 	P_MMAP_FLAG(SHARED);
 	P_MMAP_FLAG(PRIVATE);
-#ifdef MAP_32BIT
 	P_MMAP_FLAG(32BIT);
-#endif
 	P_MMAP_FLAG(ANONYMOUS);
 	P_MMAP_FLAG(DENYWRITE);
 	P_MMAP_FLAG(EXECUTABLE);
 	P_MMAP_FLAG(FILE);
 	P_MMAP_FLAG(FIXED);
 	P_MMAP_FLAG(GROWSDOWN);
-#ifdef MAP_HUGETLB
 	P_MMAP_FLAG(HUGETLB);
-#endif
 	P_MMAP_FLAG(LOCKED);
 	P_MMAP_FLAG(NONBLOCK);
 	P_MMAP_FLAG(NORESERVE);
 	P_MMAP_FLAG(POPULATE);
 	P_MMAP_FLAG(STACK);
-#ifdef MAP_UNINITIALIZED
 	P_MMAP_FLAG(UNINITIALIZED);
-#endif
 #undef P_MMAP_FLAG
 
 	if (flags)
@@ -78,6 +95,13 @@ static size_t syscall_arg__scnprintf_mmap_flags(char *bf, size_t size,
 
 #define SCA_MMAP_FLAGS syscall_arg__scnprintf_mmap_flags
 
+#ifndef MREMAP_MAYMOVE
+#define MREMAP_MAYMOVE 1
+#endif
+#ifndef MREMAP_FIXED
+#define MREMAP_FIXED 2
+#endif
+
 static size_t syscall_arg__scnprintf_mremap_flags(char *bf, size_t size,
 						  struct syscall_arg *arg)
 {
@@ -90,9 +114,7 @@ static size_t syscall_arg__scnprintf_mremap_flags(char *bf, size_t size,
 	}
 
 	P_MREMAP_FLAG(MAYMOVE);
-#ifdef MREMAP_FIXED
 	P_MREMAP_FLAG(FIXED);
-#endif
 #undef P_MREMAP_FLAG
 
 	if (flags)
@@ -107,6 +129,10 @@ static size_t syscall_arg__scnprintf_mremap_flags(char *bf, size_t size,
 #define MADV_HWPOISON		100
 #endif
 
+#ifndef MADV_SOFT_OFFLINE
+#define MADV_SOFT_OFFLINE	101
+#endif
+
 #ifndef MADV_MERGEABLE
 #define MADV_MERGEABLE		 12
 #endif
@@ -115,6 +141,23 @@ static size_t syscall_arg__scnprintf_mremap_flags(char *bf, size_t size,
 #define MADV_UNMERGEABLE	 13
 #endif
 
+#ifndef MADV_HUGEPAGE
+#define MADV_HUGEPAGE		 14
+#endif
+
+#ifndef MADV_NOHUGEPAGE
+#define MADV_NOHUGEPAGE		 15
+#endif
+
+#ifndef MADV_DONTDUMP
+#define MADV_DONTDUMP		 16
+#endif
+
+#ifndef MADV_DODUMP
+#define MADV_DODUMP		 17
+#endif
+
+
 static size_t syscall_arg__scnprintf_madvise_behavior(char *bf, size_t size,
 						      struct syscall_arg *arg)
 {
@@ -131,24 +174,14 @@ static size_t syscall_arg__scnprintf_madvise_behavior(char *bf, size_t size,
 	P_MADV_BHV(DONTFORK);
 	P_MADV_BHV(DOFORK);
 	P_MADV_BHV(HWPOISON);
-#ifdef MADV_SOFT_OFFLINE
 	P_MADV_BHV(SOFT_OFFLINE);
-#endif
 	P_MADV_BHV(MERGEABLE);
 	P_MADV_BHV(UNMERGEABLE);
-#ifdef MADV_HUGEPAGE
 	P_MADV_BHV(HUGEPAGE);
-#endif
-#ifdef MADV_NOHUGEPAGE
 	P_MADV_BHV(NOHUGEPAGE);
-#endif
-#ifdef MADV_DONTDUMP
 	P_MADV_BHV(DONTDUMP);
-#endif
-#ifdef MADV_DODUMP
 	P_MADV_BHV(DODUMP);
-#endif
-#undef P_MADV_PHV
+#undef P_MADV_BHV
 	default: break;
 	}
 

From 4c7c224ac4a4735288bc9e5377e43844aa2c9393 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 5 Jul 2016 14:43:27 -0300
Subject: [PATCH 11/66] perf trace beauty flock: Add more conditional defines

Don't handle some flags only if they have its defines in headers at
time of building, define what is missing.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-pgoxanv1y6hfcnryxawzuskl@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/trace/beauty/flock.c | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/tools/perf/trace/beauty/flock.c b/tools/perf/trace/beauty/flock.c
index 34b6348edb6ee..74613703a14eb 100644
--- a/tools/perf/trace/beauty/flock.c
+++ b/tools/perf/trace/beauty/flock.c
@@ -1,5 +1,21 @@
 #include <fcntl.h>
 
+#ifndef LOCK_MAND
+#define LOCK_MAND	 32
+#endif
+
+#ifndef LOCK_READ
+#define LOCK_READ	 64
+#endif
+
+#ifndef LOCK_WRITE
+#define LOCK_WRITE	128
+#endif
+
+#ifndef LOCK_RW
+#define LOCK_RW		192
+#endif
+
 static size_t syscall_arg__scnprintf_flock(char *bf, size_t size,
 					   struct syscall_arg *arg)
 {

From ffe3a28a8b90879c21acf7a1a8f5277785b05ff6 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 5 Jul 2016 14:43:27 -0300
Subject: [PATCH 12/66] perf trace beauty open_flags: Add more conditional
 defines

Don't handle some flags only if they have its defines in headers at
time of building, define what is missing.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-wgjxeidwpowrvqgrxr080k6u@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/trace/beauty/open_flags.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/tools/perf/trace/beauty/open_flags.c b/tools/perf/trace/beauty/open_flags.c
index 9c3a4cb3bd35c..f55a4597fc383 100644
--- a/tools/perf/trace/beauty/open_flags.c
+++ b/tools/perf/trace/beauty/open_flags.c
@@ -2,6 +2,18 @@
 #include <sys/stat.h>
 #include <fcntl.h>
 
+#ifndef O_DIRECT
+#define O_DIRECT	00040000
+#endif
+
+#ifndef O_DIRECTORY
+#define O_DIRECTORY	00200000
+#endif
+
+#ifndef O_NOATIME
+#define O_NOATIME	01000000
+#endif
+
 static size_t syscall_arg__scnprintf_open_flags(char *bf, size_t size,
 					       struct syscall_arg *arg)
 {

From c8b5f2c96d1bf6cefcbe12f67dce0b892fe20512 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 6 Jul 2016 11:56:20 -0300
Subject: [PATCH 13/66] tools: Introduce str_error_r()

The tools so far have been using the strerror_r() GNU variant, that
returns a string, be it the buffer passed or something else.

But that, besides being tricky in cases where we expect that the
function using strerror_r() returns the error formatted in a provided
buffer (we have to check if it returned something else and copy that
instead), breaks the build on systems not using glibc, like Alpine
Linux, where musl libc is used.

So, introduce yet another wrapper, str_error_r(), that has the GNU
interface, but uses the portable XSI variant of strerror_r(), so that
users rest asured that the provided buffer is used and it is what is
returned.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-d4t42fnf48ytlk8rjxs822tf@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/linux/string.h                |  2 ++
 tools/lib/str_error_r.c                     | 26 +++++++++++++++++++++
 tools/perf/MANIFEST                         |  1 +
 tools/perf/arch/x86/tests/rdpmc.c           |  4 ++--
 tools/perf/builtin-buildid-cache.c          |  8 +++----
 tools/perf/builtin-help.c                   |  8 +++----
 tools/perf/builtin-kvm.c                    |  4 ++--
 tools/perf/builtin-probe.c                  |  2 +-
 tools/perf/builtin-record.c                 |  6 ++---
 tools/perf/builtin-sched.c                  |  2 +-
 tools/perf/builtin-stat.c                   |  4 ++--
 tools/perf/builtin-top.c                    |  6 ++---
 tools/perf/builtin-trace.c                  |  4 ++--
 tools/perf/perf.c                           |  6 ++---
 tools/perf/tests/backward-ring-buffer.c     |  4 ++--
 tools/perf/tests/bpf.c                      |  4 ++--
 tools/perf/tests/builtin-test.c             |  2 +-
 tools/perf/tests/event-times.c              |  2 +-
 tools/perf/tests/mmap-basic.c               |  6 ++---
 tools/perf/tests/openat-syscall-all-cpus.c  |  4 ++--
 tools/perf/tests/openat-syscall-tp-fields.c |  4 ++--
 tools/perf/tests/openat-syscall.c           |  2 +-
 tools/perf/tests/perf-record.c              |  8 +++----
 tools/perf/tests/sw-clock.c                 |  4 ++--
 tools/perf/tests/task-exit.c                |  4 ++--
 tools/perf/ui/browsers/hists.c              |  2 +-
 tools/perf/util/Build                       |  5 ++++
 tools/perf/util/bpf-loader.c                |  2 +-
 tools/perf/util/cloexec.c                   |  4 ++--
 tools/perf/util/data.c                      |  4 ++--
 tools/perf/util/debug.h                     |  2 +-
 tools/perf/util/dso.c                       |  6 ++---
 tools/perf/util/evlist.c                    |  4 ++--
 tools/perf/util/evsel.c                     |  2 +-
 tools/perf/util/llvm-utils.c                |  8 +++----
 tools/perf/util/probe-event.c               |  6 ++---
 tools/perf/util/probe-file.c                | 10 ++++----
 tools/perf/util/probe-finder.c              |  4 ++--
 tools/perf/util/python-ext-sources          |  1 +
 tools/perf/util/target.c                    |  2 +-
 tools/perf/util/util.h                      |  1 +
 41 files changed, 113 insertions(+), 77 deletions(-)
 create mode 100644 tools/lib/str_error_r.c

diff --git a/tools/include/linux/string.h b/tools/include/linux/string.h
index e26223f1f2872..b466d0228b579 100644
--- a/tools/include/linux/string.h
+++ b/tools/include/linux/string.h
@@ -12,4 +12,6 @@ int strtobool(const char *s, bool *res);
 extern size_t strlcpy(char *dest, const char *src, size_t size);
 #endif
 
+char *str_error_r(int errnum, char *buf, size_t buflen);
+
 #endif /* _LINUX_STRING_H_ */
diff --git a/tools/lib/str_error_r.c b/tools/lib/str_error_r.c
new file mode 100644
index 0000000000000..503ae072244cb
--- /dev/null
+++ b/tools/lib/str_error_r.c
@@ -0,0 +1,26 @@
+#undef _GNU_SOURCE
+#include <string.h>
+#include <stdio.h>
+#include <linux/string.h>
+
+/*
+ * The tools so far have been using the strerror_r() GNU variant, that returns
+ * a string, be it the buffer passed or something else.
+ *
+ * But that, besides being tricky in cases where we expect that the function
+ * using strerror_r() returns the error formatted in a provided buffer (we have
+ * to check if it returned something else and copy that instead), breaks the
+ * build on systems not using glibc, like Alpine Linux, where musl libc is
+ * used.
+ *
+ * So, introduce yet another wrapper, str_error_r(), that has the GNU
+ * interface, but uses the portable XSI variant of strerror_r(), so that users
+ * rest asured that the provided buffer is used and it is what is returned.
+ */
+char *str_error_r(int errnum, char *buf, size_t buflen)
+{
+	int err = strerror_r(errnum, buf, buflen);
+	if (err)
+		snprintf(buf, buflen, "INTERNAL ERROR: strerror_r(%d, %p, %zd)=%d", errnum, buf, buflen, err);
+	return buf;
+}
diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST
index 8c8c6b9ce9153..f18e781447bcc 100644
--- a/tools/perf/MANIFEST
+++ b/tools/perf/MANIFEST
@@ -29,6 +29,7 @@ tools/lib/symbol/kallsyms.c
 tools/lib/symbol/kallsyms.h
 tools/lib/find_bit.c
 tools/lib/bitmap.c
+tools/lib/str_error_r.c
 tools/include/asm/atomic.h
 tools/include/asm/barrier.h
 tools/include/asm/bug.h
diff --git a/tools/perf/arch/x86/tests/rdpmc.c b/tools/perf/arch/x86/tests/rdpmc.c
index 72193f19d6d75..a32d72e91ffa0 100644
--- a/tools/perf/arch/x86/tests/rdpmc.c
+++ b/tools/perf/arch/x86/tests/rdpmc.c
@@ -111,14 +111,14 @@ static int __test__rdpmc(void)
 	if (fd < 0) {
 		pr_err("Error: sys_perf_event_open() syscall returned "
 		       "with %d (%s)\n", fd,
-		       strerror_r(errno, sbuf, sizeof(sbuf)));
+		       str_error_r(errno, sbuf, sizeof(sbuf)));
 		return -1;
 	}
 
 	addr = mmap(NULL, page_size, PROT_READ, MAP_SHARED, fd, 0);
 	if (addr == (void *)(-1)) {
 		pr_err("Error: mmap() syscall returned with (%s)\n",
-		       strerror_r(errno, sbuf, sizeof(sbuf)));
+		       str_error_r(errno, sbuf, sizeof(sbuf)));
 		goto out_close;
 	}
 
diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c
index 76a4d03c7cd09..30e2b2cb24212 100644
--- a/tools/perf/builtin-buildid-cache.c
+++ b/tools/perf/builtin-buildid-cache.c
@@ -351,7 +351,7 @@ int cmd_buildid_cache(int argc, const char **argv,
 						continue;
 					}
 					pr_warning("Couldn't add %s: %s\n",
-						   pos->s, strerror_r(errno, sbuf, sizeof(sbuf)));
+						   pos->s, str_error_r(errno, sbuf, sizeof(sbuf)));
 				}
 
 			strlist__delete(list);
@@ -369,7 +369,7 @@ int cmd_buildid_cache(int argc, const char **argv,
 						continue;
 					}
 					pr_warning("Couldn't remove %s: %s\n",
-						   pos->s, strerror_r(errno, sbuf, sizeof(sbuf)));
+						   pos->s, str_error_r(errno, sbuf, sizeof(sbuf)));
 				}
 
 			strlist__delete(list);
@@ -387,7 +387,7 @@ int cmd_buildid_cache(int argc, const char **argv,
 						continue;
 					}
 					pr_warning("Couldn't remove %s: %s\n",
-						   pos->s, strerror_r(errno, sbuf, sizeof(sbuf)));
+						   pos->s, str_error_r(errno, sbuf, sizeof(sbuf)));
 				}
 
 			strlist__delete(list);
@@ -408,7 +408,7 @@ int cmd_buildid_cache(int argc, const char **argv,
 						continue;
 					}
 					pr_warning("Couldn't update %s: %s\n",
-						   pos->s, strerror_r(errno, sbuf, sizeof(sbuf)));
+						   pos->s, str_error_r(errno, sbuf, sizeof(sbuf)));
 				}
 
 			strlist__delete(list);
diff --git a/tools/perf/builtin-help.c b/tools/perf/builtin-help.c
index 268ab732b8aae..3bdb2c78a21b3 100644
--- a/tools/perf/builtin-help.c
+++ b/tools/perf/builtin-help.c
@@ -117,7 +117,7 @@ static void exec_woman_emacs(const char *path, const char *page)
 			free(man_page);
 		}
 		warning("failed to exec '%s': %s", path,
-			strerror_r(errno, sbuf, sizeof(sbuf)));
+			str_error_r(errno, sbuf, sizeof(sbuf)));
 	}
 }
 
@@ -150,7 +150,7 @@ static void exec_man_konqueror(const char *path, const char *page)
 			free(man_page);
 		}
 		warning("failed to exec '%s': %s", path,
-			strerror_r(errno, sbuf, sizeof(sbuf)));
+			str_error_r(errno, sbuf, sizeof(sbuf)));
 	}
 }
 
@@ -162,7 +162,7 @@ static void exec_man_man(const char *path, const char *page)
 		path = "man";
 	execlp(path, "man", page, NULL);
 	warning("failed to exec '%s': %s", path,
-		strerror_r(errno, sbuf, sizeof(sbuf)));
+		str_error_r(errno, sbuf, sizeof(sbuf)));
 }
 
 static void exec_man_cmd(const char *cmd, const char *page)
@@ -175,7 +175,7 @@ static void exec_man_cmd(const char *cmd, const char *page)
 		free(shell_cmd);
 	}
 	warning("failed to exec '%s': %s", cmd,
-		strerror_r(errno, sbuf, sizeof(sbuf)));
+		str_error_r(errno, sbuf, sizeof(sbuf)));
 }
 
 static void add_man_viewer(const char *name)
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index f4efef9d1eb3e..5e2127e04f838 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -1018,13 +1018,13 @@ static int kvm_live_open_events(struct perf_kvm_stat *kvm)
 	err = perf_evlist__open(evlist);
 	if (err < 0) {
 		printf("Couldn't create the events: %s\n",
-		       strerror_r(errno, sbuf, sizeof(sbuf)));
+		       str_error_r(errno, sbuf, sizeof(sbuf)));
 		goto out;
 	}
 
 	if (perf_evlist__mmap(evlist, kvm->opts.mmap_pages, false) < 0) {
 		ui__error("Failed to mmap the events: %s\n",
-			  strerror_r(errno, sbuf, sizeof(sbuf)));
+			  str_error_r(errno, sbuf, sizeof(sbuf)));
 		perf_evlist__close(evlist);
 		goto out;
 	}
diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c
index a1a5cd1b8d601..c6d890ad2c1a2 100644
--- a/tools/perf/builtin-probe.c
+++ b/tools/perf/builtin-probe.c
@@ -308,7 +308,7 @@ static void pr_err_with_code(const char *msg, int err)
 
 	pr_err("%s", msg);
 	pr_debug(" Reason: %s (Code: %d)",
-		 strerror_r(-err, sbuf, sizeof(sbuf)), err);
+		 str_error_r(-err, sbuf, sizeof(sbuf)), err);
 	pr_err("\n");
 }
 
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index b2b3b600adf53..d9f5cc3a36679 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -361,7 +361,7 @@ static int record__mmap_evlist(struct record *rec,
 			return -errno;
 		} else {
 			pr_err("failed to mmap with %d (%s)\n", errno,
-				strerror_r(errno, msg, sizeof(msg)));
+				str_error_r(errno, msg, sizeof(msg)));
 			if (errno)
 				return -errno;
 			else
@@ -407,7 +407,7 @@ static int record__open(struct record *rec)
 	if (perf_evlist__apply_filters(evlist, &pos)) {
 		error("failed to set filter \"%s\" on event %s with %d (%s)\n",
 			pos->filter, perf_evsel__name(pos), errno,
-			strerror_r(errno, msg, sizeof(msg)));
+			str_error_r(errno, msg, sizeof(msg)));
 		rc = -1;
 		goto out;
 	}
@@ -1003,7 +1003,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 
 	if (forks && workload_exec_errno) {
 		char msg[STRERR_BUFSIZE];
-		const char *emsg = strerror_r(workload_exec_errno, msg, sizeof(msg));
+		const char *emsg = str_error_r(workload_exec_errno, msg, sizeof(msg));
 		pr_err("Workload failed: %s\n", emsg);
 		err = -1;
 		goto out_child;
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index afa057666c2ad..0dfe8df2ab9b2 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -494,7 +494,7 @@ static int self_open_counters(struct perf_sched *sched, unsigned long cur_task)
 		}
 		pr_err("Error: sys_perf_event_open() syscall returned "
 		       "with %d (%s)\n%s", fd,
-		       strerror_r(errno, sbuf, sizeof(sbuf)), info);
+		       str_error_r(errno, sbuf, sizeof(sbuf)), info);
 		exit(EXIT_FAILURE);
 	}
 	return fd;
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index c367a43525e6e..8c5a3bfdfdd73 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -596,7 +596,7 @@ static int __run_perf_stat(int argc, const char **argv)
 	if (perf_evlist__apply_filters(evsel_list, &counter)) {
 		error("failed to set filter \"%s\" on event %s with %d (%s)\n",
 			counter->filter, perf_evsel__name(counter), errno,
-			strerror_r(errno, msg, sizeof(msg)));
+			str_error_r(errno, msg, sizeof(msg)));
 		return -1;
 	}
 
@@ -637,7 +637,7 @@ static int __run_perf_stat(int argc, const char **argv)
 		wait(&status);
 
 		if (workload_exec_errno) {
-			const char *emsg = strerror_r(workload_exec_errno, msg, sizeof(msg));
+			const char *emsg = str_error_r(workload_exec_errno, msg, sizeof(msg));
 			pr_err("Workload failed: %s\n", emsg);
 			return -1;
 		}
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 07fc7921980c0..bd108683fcb87 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -907,7 +907,7 @@ static int perf_top__start_counters(struct perf_top *top)
 
 	if (perf_evlist__mmap(evlist, opts->mmap_pages, false) < 0) {
 		ui__error("Failed to mmap with %d (%s)\n",
-			    errno, strerror_r(errno, msg, sizeof(msg)));
+			    errno, str_error_r(errno, msg, sizeof(msg)));
 		goto out_err;
 	}
 
@@ -1028,7 +1028,7 @@ static int __cmd_top(struct perf_top *top)
 
 out_err_cpu_topo: {
 	char errbuf[BUFSIZ];
-	const char *err = strerror_r(-ret, errbuf, sizeof(errbuf));
+	const char *err = str_error_r(-ret, errbuf, sizeof(errbuf));
 
 	ui__error("Could not read the CPU topology map: %s\n", err);
 	goto out_delete;
@@ -1295,7 +1295,7 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
 
 	if (perf_evlist__create_maps(top.evlist, target) < 0) {
 		ui__error("Couldn't create thread/CPU maps: %s\n",
-			  errno == ENOENT ? "No such process" : strerror_r(errno, errbuf, sizeof(errbuf)));
+			  errno == ENOENT ? "No such process" : str_error_r(errno, errbuf, sizeof(errbuf)));
 		goto out_delete_evlist;
 	}
 
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index cf90de811523b..e7e0b6e306b7c 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -1601,7 +1601,7 @@ static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel,
 		fprintf(trace->output, ") = %ld", ret);
 	} else if (ret < 0 && (sc->fmt->errmsg || sc->fmt->errpid)) {
 		char bf[STRERR_BUFSIZE];
-		const char *emsg = strerror_r(-ret, bf, sizeof(bf)),
+		const char *emsg = str_error_r(-ret, bf, sizeof(bf)),
 			   *e = audit_errno_to_name(-ret);
 
 		fprintf(trace->output, ") = -1 %s %s", e, emsg);
@@ -2402,7 +2402,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 	fprintf(trace->output,
 		"Failed to set filter \"%s\" on event %s with %d (%s)\n",
 		evsel->filter, perf_evsel__name(evsel), errno,
-		strerror_r(errno, errbuf, sizeof(errbuf)));
+		str_error_r(errno, errbuf, sizeof(errbuf)));
 	goto out_delete_evlist;
 }
 out_error_mem:
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index 8f219223f305e..f7d7dbbd2af67 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -374,7 +374,7 @@ static int run_builtin(struct cmd_struct *p, int argc, const char **argv)
 	/* Check for ENOSPC and EIO errors.. */
 	if (fflush(stdout)) {
 		fprintf(stderr, "write failure on standard output: %s",
-			strerror_r(errno, sbuf, sizeof(sbuf)));
+			str_error_r(errno, sbuf, sizeof(sbuf)));
 		goto out;
 	}
 	if (ferror(stdout)) {
@@ -383,7 +383,7 @@ static int run_builtin(struct cmd_struct *p, int argc, const char **argv)
 	}
 	if (fclose(stdout)) {
 		fprintf(stderr, "close failed on standard output: %s",
-			strerror_r(errno, sbuf, sizeof(sbuf)));
+			str_error_r(errno, sbuf, sizeof(sbuf)));
 		goto out;
 	}
 	status = 0;
@@ -615,7 +615,7 @@ int main(int argc, const char **argv)
 	}
 
 	fprintf(stderr, "Failed to run command '%s': %s\n",
-		cmd, strerror_r(errno, sbuf, sizeof(sbuf)));
+		cmd, str_error_r(errno, sbuf, sizeof(sbuf)));
 out:
 	return 1;
 }
diff --git a/tools/perf/tests/backward-ring-buffer.c b/tools/perf/tests/backward-ring-buffer.c
index e70313fac5a55..f20ea4c0d0cb9 100644
--- a/tools/perf/tests/backward-ring-buffer.c
+++ b/tools/perf/tests/backward-ring-buffer.c
@@ -60,7 +60,7 @@ static int do_test(struct perf_evlist *evlist, int mmap_pages,
 	err = perf_evlist__mmap(evlist, mmap_pages, true);
 	if (err < 0) {
 		pr_debug("perf_evlist__mmap: %s\n",
-			 strerror_r(errno, sbuf, sizeof(sbuf)));
+			 str_error_r(errno, sbuf, sizeof(sbuf)));
 		return TEST_FAIL;
 	}
 
@@ -124,7 +124,7 @@ int test__backward_ring_buffer(int subtest __maybe_unused)
 	err = perf_evlist__open(evlist);
 	if (err < 0) {
 		pr_debug("perf_evlist__open: %s\n",
-			 strerror_r(errno, sbuf, sizeof(sbuf)));
+			 str_error_r(errno, sbuf, sizeof(sbuf)));
 		goto out_delete_evlist;
 	}
 
diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c
index f31eed31c1a9c..da0d876139752 100644
--- a/tools/perf/tests/bpf.c
+++ b/tools/perf/tests/bpf.c
@@ -143,14 +143,14 @@ static int do_test(struct bpf_object *obj, int (*func)(void),
 	err = perf_evlist__open(evlist);
 	if (err < 0) {
 		pr_debug("perf_evlist__open: %s\n",
-			 strerror_r(errno, sbuf, sizeof(sbuf)));
+			 str_error_r(errno, sbuf, sizeof(sbuf)));
 		goto out_delete_evlist;
 	}
 
 	err = perf_evlist__mmap(evlist, opts.mmap_pages, false);
 	if (err < 0) {
 		pr_debug("perf_evlist__mmap: %s\n",
-			 strerror_r(errno, sbuf, sizeof(sbuf)));
+			 str_error_r(errno, sbuf, sizeof(sbuf)));
 		goto out_delete_evlist;
 	}
 
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 07c14e9f65466..c23cbf7335498 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -258,7 +258,7 @@ static int run_test(struct test *test, int subtest)
 
 	if (child < 0) {
 		pr_err("failed to fork test: %s\n",
-			strerror_r(errno, sbuf, sizeof(sbuf)));
+			str_error_r(errno, sbuf, sizeof(sbuf)));
 		return -1;
 	}
 
diff --git a/tools/perf/tests/event-times.c b/tools/perf/tests/event-times.c
index 9f5698ac81ae2..19ef77bd6eb41 100644
--- a/tools/perf/tests/event-times.c
+++ b/tools/perf/tests/event-times.c
@@ -37,7 +37,7 @@ static int attach__enable_on_exec(struct perf_evlist *evlist)
 	err = perf_evlist__open(evlist);
 	if (err < 0) {
 		pr_debug("perf_evlist__open: %s\n",
-			 strerror_r(errno, sbuf, sizeof(sbuf)));
+			 str_error_r(errno, sbuf, sizeof(sbuf)));
 		return err;
 	}
 
diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c
index aea33f5589c5b..5c9b931b7b66a 100644
--- a/tools/perf/tests/mmap-basic.c
+++ b/tools/perf/tests/mmap-basic.c
@@ -49,7 +49,7 @@ int test__basic_mmap(int subtest __maybe_unused)
 	sched_setaffinity(0, sizeof(cpu_set), &cpu_set);
 	if (sched_setaffinity(0, sizeof(cpu_set), &cpu_set) < 0) {
 		pr_debug("sched_setaffinity() failed on CPU %d: %s ",
-			 cpus->map[0], strerror_r(errno, sbuf, sizeof(sbuf)));
+			 cpus->map[0], str_error_r(errno, sbuf, sizeof(sbuf)));
 		goto out_free_cpus;
 	}
 
@@ -79,7 +79,7 @@ int test__basic_mmap(int subtest __maybe_unused)
 		if (perf_evsel__open(evsels[i], cpus, threads) < 0) {
 			pr_debug("failed to open counter: %s, "
 				 "tweak /proc/sys/kernel/perf_event_paranoid?\n",
-				 strerror_r(errno, sbuf, sizeof(sbuf)));
+				 str_error_r(errno, sbuf, sizeof(sbuf)));
 			goto out_delete_evlist;
 		}
 
@@ -89,7 +89,7 @@ int test__basic_mmap(int subtest __maybe_unused)
 
 	if (perf_evlist__mmap(evlist, 128, true) < 0) {
 		pr_debug("failed to mmap events: %d (%s)\n", errno,
-			 strerror_r(errno, sbuf, sizeof(sbuf)));
+			 str_error_r(errno, sbuf, sizeof(sbuf)));
 		goto out_delete_evlist;
 	}
 
diff --git a/tools/perf/tests/openat-syscall-all-cpus.c b/tools/perf/tests/openat-syscall-all-cpus.c
index ad1cb63139a79..265abb12dfffc 100644
--- a/tools/perf/tests/openat-syscall-all-cpus.c
+++ b/tools/perf/tests/openat-syscall-all-cpus.c
@@ -41,7 +41,7 @@ int test__openat_syscall_event_on_all_cpus(int subtest __maybe_unused)
 	if (perf_evsel__open(evsel, cpus, threads) < 0) {
 		pr_debug("failed to open counter: %s, "
 			 "tweak /proc/sys/kernel/perf_event_paranoid?\n",
-			 strerror_r(errno, sbuf, sizeof(sbuf)));
+			 str_error_r(errno, sbuf, sizeof(sbuf)));
 		goto out_evsel_delete;
 	}
 
@@ -62,7 +62,7 @@ int test__openat_syscall_event_on_all_cpus(int subtest __maybe_unused)
 		if (sched_setaffinity(0, sizeof(cpu_set), &cpu_set) < 0) {
 			pr_debug("sched_setaffinity() failed on CPU %d: %s ",
 				 cpus->map[cpu],
-				 strerror_r(errno, sbuf, sizeof(sbuf)));
+				 str_error_r(errno, sbuf, sizeof(sbuf)));
 			goto out_close_fd;
 		}
 		for (i = 0; i < ncalls; ++i) {
diff --git a/tools/perf/tests/openat-syscall-tp-fields.c b/tools/perf/tests/openat-syscall-tp-fields.c
index 4344fe482c1d2..942dbf43d7c74 100644
--- a/tools/perf/tests/openat-syscall-tp-fields.c
+++ b/tools/perf/tests/openat-syscall-tp-fields.c
@@ -51,14 +51,14 @@ int test__syscall_openat_tp_fields(int subtest __maybe_unused)
 	err = perf_evlist__open(evlist);
 	if (err < 0) {
 		pr_debug("perf_evlist__open: %s\n",
-			 strerror_r(errno, sbuf, sizeof(sbuf)));
+			 str_error_r(errno, sbuf, sizeof(sbuf)));
 		goto out_delete_evlist;
 	}
 
 	err = perf_evlist__mmap(evlist, UINT_MAX, false);
 	if (err < 0) {
 		pr_debug("perf_evlist__mmap: %s\n",
-			 strerror_r(errno, sbuf, sizeof(sbuf)));
+			 str_error_r(errno, sbuf, sizeof(sbuf)));
 		goto out_delete_evlist;
 	}
 
diff --git a/tools/perf/tests/openat-syscall.c b/tools/perf/tests/openat-syscall.c
index 1184f9ba64992..d7414128d7fe4 100644
--- a/tools/perf/tests/openat-syscall.c
+++ b/tools/perf/tests/openat-syscall.c
@@ -29,7 +29,7 @@ int test__openat_syscall_event(int subtest __maybe_unused)
 	if (perf_evsel__open_per_thread(evsel, threads) < 0) {
 		pr_debug("failed to open counter: %s, "
 			 "tweak /proc/sys/kernel/perf_event_paranoid?\n",
-			 strerror_r(errno, sbuf, sizeof(sbuf)));
+			 str_error_r(errno, sbuf, sizeof(sbuf)));
 		goto out_evsel_delete;
 	}
 
diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c
index b836ee6a8d9bb..3eb67a977b6ae 100644
--- a/tools/perf/tests/perf-record.c
+++ b/tools/perf/tests/perf-record.c
@@ -104,7 +104,7 @@ int test__PERF_RECORD(int subtest __maybe_unused)
 	err = sched__get_first_possible_cpu(evlist->workload.pid, &cpu_mask);
 	if (err < 0) {
 		pr_debug("sched__get_first_possible_cpu: %s\n",
-			 strerror_r(errno, sbuf, sizeof(sbuf)));
+			 str_error_r(errno, sbuf, sizeof(sbuf)));
 		goto out_delete_evlist;
 	}
 
@@ -115,7 +115,7 @@ int test__PERF_RECORD(int subtest __maybe_unused)
 	 */
 	if (sched_setaffinity(evlist->workload.pid, cpu_mask_size, &cpu_mask) < 0) {
 		pr_debug("sched_setaffinity: %s\n",
-			 strerror_r(errno, sbuf, sizeof(sbuf)));
+			 str_error_r(errno, sbuf, sizeof(sbuf)));
 		goto out_delete_evlist;
 	}
 
@@ -126,7 +126,7 @@ int test__PERF_RECORD(int subtest __maybe_unused)
 	err = perf_evlist__open(evlist);
 	if (err < 0) {
 		pr_debug("perf_evlist__open: %s\n",
-			 strerror_r(errno, sbuf, sizeof(sbuf)));
+			 str_error_r(errno, sbuf, sizeof(sbuf)));
 		goto out_delete_evlist;
 	}
 
@@ -138,7 +138,7 @@ int test__PERF_RECORD(int subtest __maybe_unused)
 	err = perf_evlist__mmap(evlist, opts.mmap_pages, false);
 	if (err < 0) {
 		pr_debug("perf_evlist__mmap: %s\n",
-			 strerror_r(errno, sbuf, sizeof(sbuf)));
+			 str_error_r(errno, sbuf, sizeof(sbuf)));
 		goto out_delete_evlist;
 	}
 
diff --git a/tools/perf/tests/sw-clock.c b/tools/perf/tests/sw-clock.c
index 36e8ce1550e30..4c9fd046d57b1 100644
--- a/tools/perf/tests/sw-clock.c
+++ b/tools/perf/tests/sw-clock.c
@@ -70,7 +70,7 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
 
 		err = -errno;
 		pr_debug("Couldn't open evlist: %s\nHint: check %s, using %" PRIu64 " in this test.\n",
-			 strerror_r(errno, sbuf, sizeof(sbuf)),
+			 str_error_r(errno, sbuf, sizeof(sbuf)),
 			 knob, (u64)attr.sample_freq);
 		goto out_delete_evlist;
 	}
@@ -78,7 +78,7 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
 	err = perf_evlist__mmap(evlist, 128, true);
 	if (err < 0) {
 		pr_debug("failed to mmap event: %d (%s)\n", errno,
-			 strerror_r(errno, sbuf, sizeof(sbuf)));
+			 str_error_r(errno, sbuf, sizeof(sbuf)));
 		goto out_delete_evlist;
 	}
 
diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c
index 2dfff7ac8ef31..01a5ba2788c60 100644
--- a/tools/perf/tests/task-exit.c
+++ b/tools/perf/tests/task-exit.c
@@ -91,13 +91,13 @@ int test__task_exit(int subtest __maybe_unused)
 	err = perf_evlist__open(evlist);
 	if (err < 0) {
 		pr_debug("Couldn't open the evlist: %s\n",
-			 strerror_r(-err, sbuf, sizeof(sbuf)));
+			 str_error_r(-err, sbuf, sizeof(sbuf)));
 		goto out_delete_evlist;
 	}
 
 	if (perf_evlist__mmap(evlist, 128, true) < 0) {
 		pr_debug("failed to mmap events: %d (%s)\n", errno,
-			 strerror_r(errno, sbuf, sizeof(sbuf)));
+			 str_error_r(errno, sbuf, sizeof(sbuf)));
 		goto out_delete_evlist;
 	}
 
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index e08b8f7b6d3f3..13d414384739d 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -2029,7 +2029,7 @@ static int hist_browser__dump(struct hist_browser *browser)
 	fp = fopen(filename, "w");
 	if (fp == NULL) {
 		char bf[64];
-		const char *err = strerror_r(errno, bf, sizeof(bf));
+		const char *err = str_error_r(errno, bf, sizeof(bf));
 		ui_helpline__fpush("Couldn't write to %s: %s", filename, err);
 		return -1;
 	}
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index fced8336e5fd3..a6a8053023120 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -70,6 +70,7 @@ libperf-y += stat.o
 libperf-y += stat-shadow.o
 libperf-y += record.o
 libperf-y += srcline.o
+libperf-y += str_error_r.o
 libperf-y += data.o
 libperf-y += tsc.o
 libperf-y += cloexec.o
@@ -173,6 +174,10 @@ $(OUTPUT)util/libstring.o: ../lib/string.c FORCE
 	$(call rule_mkdir)
 	$(call if_changed_dep,cc_o_c)
 
+$(OUTPUT)util/str_error_r.o: ../lib/str_error_r.c FORCE
+	$(call rule_mkdir)
+	$(call if_changed_dep,cc_o_c)
+
 $(OUTPUT)util/hweight.o: ../lib/hweight.c FORCE
 	$(call rule_mkdir)
 	$(call if_changed_dep,cc_o_c)
diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c
index dcc8845881aec..8445e89621fe9 100644
--- a/tools/perf/util/bpf-loader.c
+++ b/tools/perf/util/bpf-loader.c
@@ -1589,7 +1589,7 @@ bpf_loader_strerror(int err, char *buf, size_t size)
 		snprintf(buf, size, "Unknown bpf loader error %d", err);
 	else
 		snprintf(buf, size, "%s",
-			 strerror_r(err, sbuf, sizeof(sbuf)));
+			 str_error_r(err, sbuf, sizeof(sbuf)));
 
 	buf[size - 1] = '\0';
 	return -1;
diff --git a/tools/perf/util/cloexec.c b/tools/perf/util/cloexec.c
index 2babddaa24813..fde772db1d5c0 100644
--- a/tools/perf/util/cloexec.c
+++ b/tools/perf/util/cloexec.c
@@ -58,7 +58,7 @@ static int perf_flag_probe(void)
 
 	WARN_ONCE(err != EINVAL && err != EBUSY,
 		  "perf_event_open(..., PERF_FLAG_FD_CLOEXEC) failed with unexpected error %d (%s)\n",
-		  err, strerror_r(err, sbuf, sizeof(sbuf)));
+		  err, str_error_r(err, sbuf, sizeof(sbuf)));
 
 	/* not supported, confirm error related to PERF_FLAG_FD_CLOEXEC */
 	while (1) {
@@ -76,7 +76,7 @@ static int perf_flag_probe(void)
 
 	if (WARN_ONCE(fd < 0 && err != EBUSY,
 		      "perf_event_open(..., 0) failed unexpectedly with error %d (%s)\n",
-		      err, strerror_r(err, sbuf, sizeof(sbuf))))
+		      err, str_error_r(err, sbuf, sizeof(sbuf))))
 		return -1;
 
 	return 0;
diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c
index be83516155ee5..60bfc9ca1e22f 100644
--- a/tools/perf/util/data.c
+++ b/tools/perf/util/data.c
@@ -57,7 +57,7 @@ static int open_file_read(struct perf_data_file *file)
 		int err = errno;
 
 		pr_err("failed to open %s: %s", file->path,
-			strerror_r(err, sbuf, sizeof(sbuf)));
+			str_error_r(err, sbuf, sizeof(sbuf)));
 		if (err == ENOENT && !strcmp(file->path, "perf.data"))
 			pr_err("  (try 'perf record' first)");
 		pr_err("\n");
@@ -99,7 +99,7 @@ static int open_file_write(struct perf_data_file *file)
 
 	if (fd < 0)
 		pr_err("failed to open %s : %s\n", file->path,
-			strerror_r(errno, sbuf, sizeof(sbuf)));
+			str_error_r(errno, sbuf, sizeof(sbuf)));
 
 	return fd;
 }
diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h
index 14bafda79edae..d242adc3d5a2a 100644
--- a/tools/perf/util/debug.h
+++ b/tools/perf/util/debug.h
@@ -38,7 +38,7 @@ extern int debug_data_convert;
 #define pr_oe_time(t, fmt, ...)  pr_time_N(1, debug_ordered_events, t, pr_fmt(fmt), ##__VA_ARGS__)
 #define pr_oe_time2(t, fmt, ...) pr_time_N(2, debug_ordered_events, t, pr_fmt(fmt), ##__VA_ARGS__)
 
-#define STRERR_BUFSIZE	128	/* For the buffer size of strerror_r */
+#define STRERR_BUFSIZE	128	/* For the buffer size of str_error_r */
 
 int dump_printf(const char *fmt, ...) __attribute__((format(printf, 1, 2)));
 void trace_event(union perf_event *event);
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index e1de6cc4863e8..774f6ec884d50 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -335,7 +335,7 @@ static int do_open(char *name)
 			return fd;
 
 		pr_debug("dso open failed: %s\n",
-			 strerror_r(errno, sbuf, sizeof(sbuf)));
+			 str_error_r(errno, sbuf, sizeof(sbuf)));
 		if (!dso__data_open_cnt || errno != EMFILE)
 			break;
 
@@ -786,7 +786,7 @@ static int data_file_size(struct dso *dso, struct machine *machine)
 	if (fstat(dso->data.fd, &st) < 0) {
 		ret = -errno;
 		pr_err("dso cache fstat failed: %s\n",
-		       strerror_r(errno, sbuf, sizeof(sbuf)));
+		       str_error_r(errno, sbuf, sizeof(sbuf)));
 		dso->data.status = DSO_DATA_STATUS_ERROR;
 		goto out;
 	}
@@ -1366,7 +1366,7 @@ int dso__strerror_load(struct dso *dso, char *buf, size_t buflen)
 	BUG_ON(buflen == 0);
 
 	if (errnum >= 0) {
-		const char *err = strerror_r(errnum, buf, buflen);
+		const char *err = str_error_r(errnum, buf, buflen);
 
 		if (err != buf)
 			scnprintf(buf, buflen, "%s", err);
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 113507716044a..f2d478df8c3e4 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -1790,7 +1790,7 @@ int perf_evlist__strerror_open(struct perf_evlist *evlist,
 			       int err, char *buf, size_t size)
 {
 	int printed, value;
-	char sbuf[STRERR_BUFSIZE], *emsg = strerror_r(err, sbuf, sizeof(sbuf));
+	char sbuf[STRERR_BUFSIZE], *emsg = str_error_r(err, sbuf, sizeof(sbuf));
 
 	switch (err) {
 	case EACCES:
@@ -1842,7 +1842,7 @@ int perf_evlist__strerror_open(struct perf_evlist *evlist,
 
 int perf_evlist__strerror_mmap(struct perf_evlist *evlist, int err, char *buf, size_t size)
 {
-	char sbuf[STRERR_BUFSIZE], *emsg = strerror_r(err, sbuf, sizeof(sbuf));
+	char sbuf[STRERR_BUFSIZE], *emsg = str_error_r(err, sbuf, sizeof(sbuf));
 	int pages_attempted = evlist->mmap_len / 1024, pages_max_per_user, printed = 0;
 
 	switch (err) {
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 0fea724e735c3..d8c2298cd32a3 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -2419,7 +2419,7 @@ int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target,
 	"The sys_perf_event_open() syscall returned with %d (%s) for event (%s).\n"
 	"/bin/dmesg may provide additional information.\n"
 	"No CONFIG_PERF_EVENTS=y kernel support configured?",
-			 err, strerror_r(err, sbuf, sizeof(sbuf)),
+			 err, str_error_r(err, sbuf, sizeof(sbuf)),
 			 perf_evsel__name(evsel));
 }
 
diff --git a/tools/perf/util/llvm-utils.c b/tools/perf/util/llvm-utils.c
index 40b6f7269cb4c..282c30f6a51d9 100644
--- a/tools/perf/util/llvm-utils.c
+++ b/tools/perf/util/llvm-utils.c
@@ -106,7 +106,7 @@ read_from_pipe(const char *cmd, void **p_buf, size_t *p_read_sz)
 	file = popen(cmd, "r");
 	if (!file) {
 		pr_err("ERROR: unable to popen cmd: %s\n",
-		       strerror_r(errno, serr, sizeof(serr)));
+		       str_error_r(errno, serr, sizeof(serr)));
 		return -EINVAL;
 	}
 
@@ -140,7 +140,7 @@ read_from_pipe(const char *cmd, void **p_buf, size_t *p_read_sz)
 
 	if (ferror(file)) {
 		pr_err("ERROR: error occurred when reading from pipe: %s\n",
-		       strerror_r(errno, serr, sizeof(serr)));
+		       str_error_r(errno, serr, sizeof(serr)));
 		err = -EIO;
 		goto errout;
 	}
@@ -382,7 +382,7 @@ int llvm__compile_bpf(const char *path, void **p_obj_buf,
 	if (path[0] != '-' && realpath(path, abspath) == NULL) {
 		err = errno;
 		pr_err("ERROR: problems with path %s: %s\n",
-		       path, strerror_r(err, serr, sizeof(serr)));
+		       path, str_error_r(err, serr, sizeof(serr)));
 		return -err;
 	}
 
@@ -410,7 +410,7 @@ int llvm__compile_bpf(const char *path, void **p_obj_buf,
 	if (nr_cpus_avail <= 0) {
 		pr_err(
 "WARNING:\tunable to get available CPUs in this system: %s\n"
-"        \tUse 128 instead.\n", strerror_r(errno, serr, sizeof(serr)));
+"        \tUse 128 instead.\n", str_error_r(errno, serr, sizeof(serr)));
 		nr_cpus_avail = 128;
 	}
 	snprintf(nr_cpus_avail_str, sizeof(nr_cpus_avail_str), "%d",
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 0201f661ccb82..2b222a7955c9b 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -468,7 +468,7 @@ static struct debuginfo *open_debuginfo(const char *module, bool silent)
 		err = kernel_get_module_dso(module, &dso);
 		if (err < 0) {
 			if (!dso || dso->load_errno == 0) {
-				if (!strerror_r(-err, reason, STRERR_BUFSIZE))
+				if (!str_error_r(-err, reason, STRERR_BUFSIZE))
 					strcpy(reason, "(unknown)");
 			} else
 				dso__strerror_load(dso, reason, STRERR_BUFSIZE);
@@ -806,7 +806,7 @@ static int __show_one_line(FILE *fp, int l, bool skip, bool show_num)
 error:
 	if (ferror(fp)) {
 		pr_warning("File read error: %s\n",
-			   strerror_r(errno, sbuf, sizeof(sbuf)));
+			   str_error_r(errno, sbuf, sizeof(sbuf)));
 		return -1;
 	}
 	return 0;
@@ -886,7 +886,7 @@ static int __show_line_range(struct line_range *lr, const char *module,
 	fp = fopen(lr->path, "r");
 	if (fp == NULL) {
 		pr_warning("Failed to open %s: %s\n", lr->path,
-			   strerror_r(errno, sbuf, sizeof(sbuf)));
+			   str_error_r(errno, sbuf, sizeof(sbuf)));
 		return -errno;
 	}
 	/* Skip to starting line number */
diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c
index 5b563b2e8b1d1..98398b55a03f4 100644
--- a/tools/perf/util/probe-file.c
+++ b/tools/perf/util/probe-file.c
@@ -50,7 +50,7 @@ static void print_open_warning(int err, bool uprobe)
 	else
 		pr_warning("Failed to open %cprobe_events: %s\n",
 			   uprobe ? 'u' : 'k',
-			   strerror_r(-err, sbuf, sizeof(sbuf)));
+			   str_error_r(-err, sbuf, sizeof(sbuf)));
 }
 
 static void print_both_open_warning(int kerr, int uerr)
@@ -64,9 +64,9 @@ static void print_both_open_warning(int kerr, int uerr)
 	else {
 		char sbuf[STRERR_BUFSIZE];
 		pr_warning("Failed to open kprobe events: %s.\n",
-			   strerror_r(-kerr, sbuf, sizeof(sbuf)));
+			   str_error_r(-kerr, sbuf, sizeof(sbuf)));
 		pr_warning("Failed to open uprobe events: %s.\n",
-			   strerror_r(-uerr, sbuf, sizeof(sbuf)));
+			   str_error_r(-uerr, sbuf, sizeof(sbuf)));
 	}
 }
 
@@ -224,7 +224,7 @@ int probe_file__add_event(int fd, struct probe_trace_event *tev)
 		if (write(fd, buf, strlen(buf)) < (int)strlen(buf)) {
 			ret = -errno;
 			pr_warning("Failed to write event: %s\n",
-				   strerror_r(errno, sbuf, sizeof(sbuf)));
+				   str_error_r(errno, sbuf, sizeof(sbuf)));
 		}
 	}
 	free(buf);
@@ -262,7 +262,7 @@ static int __del_trace_probe_event(int fd, struct str_node *ent)
 	return 0;
 error:
 	pr_warning("Failed to delete event: %s\n",
-		   strerror_r(-ret, buf, sizeof(buf)));
+		   str_error_r(-ret, buf, sizeof(buf)));
 	return ret;
 }
 
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 1259839dbf6d4..f2d9ff064e2de 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -381,7 +381,7 @@ static int convert_variable_type(Dwarf_Die *vr_die,
 		if (ret >= 16)
 			ret = -E2BIG;
 		pr_warning("Failed to convert variable type: %s\n",
-			   strerror_r(-ret, sbuf, sizeof(sbuf)));
+			   str_error_r(-ret, sbuf, sizeof(sbuf)));
 		return ret;
 	}
 	tvar->type = strdup(buf);
@@ -809,7 +809,7 @@ static int find_lazy_match_lines(struct intlist *list,
 	fp = fopen(fname, "r");
 	if (!fp) {
 		pr_warning("Failed to open %s: %s\n", fname,
-			   strerror_r(errno, sbuf, sizeof(sbuf)));
+			   str_error_r(errno, sbuf, sizeof(sbuf)));
 		return -errno;
 	}
 
diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources
index 36c6862119e32..49210b7a7925b 100644
--- a/tools/perf/util/python-ext-sources
+++ b/tools/perf/util/python-ext-sources
@@ -13,6 +13,7 @@ util/cpumap.c
 ../lib/bitmap.c
 ../lib/find_bit.c
 ../lib/hweight.c
+../lib/str_error_r.c
 util/thread_map.c
 util/util.c
 util/xyarray.c
diff --git a/tools/perf/util/target.c b/tools/perf/util/target.c
index a53603b27e525..5898af4510ccf 100644
--- a/tools/perf/util/target.c
+++ b/tools/perf/util/target.c
@@ -121,7 +121,7 @@ int target__strerror(struct target *target, int errnum,
 	BUG_ON(buflen == 0);
 
 	if (errnum >= 0) {
-		const char *err = strerror_r(errnum, buf, buflen);
+		const char *err = str_error_r(errnum, buf, buflen);
 
 		if (err != buf)
 			scnprintf(buf, buflen, "%s", err);
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 1e8c3167b9fb3..2370cfb902b29 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -360,4 +360,5 @@ typedef void (*print_binary_t)(enum binary_printer_ops,
 void print_binary(unsigned char *data, size_t len,
 		  size_t bytes_per_line, print_binary_t printer,
 		  void *extra);
+
 #endif /* GIT_COMPAT_UTIL_H */

From 8a15858904c803450b6763d09f53d9a1dc7ab1c3 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 6 Jul 2016 12:14:56 -0300
Subject: [PATCH 14/66] perf bench: Add missing pthread.h include for CPU_*()
 macros

Cc: David Ahern <dsahern@gmail.com>
Cc: Davidlohr Bueso <dbueso@suse.de>
Cc: Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-48qbfv7tqs8n8ey74lbyfjtq@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/bench/futex-hash.c          | 6 +++---
 tools/perf/bench/futex-lock-pi.c       | 4 +++-
 tools/perf/bench/futex-requeue.c       | 4 +++-
 tools/perf/bench/futex-wake-parallel.c | 4 +++-
 tools/perf/bench/futex-wake.c          | 4 +++-
 tools/perf/bench/numa.c                | 4 +++-
 6 files changed, 18 insertions(+), 8 deletions(-)

diff --git a/tools/perf/bench/futex-hash.c b/tools/perf/bench/futex-hash.c
index 0999ac536d869..8fc1782f90f52 100644
--- a/tools/perf/bench/futex-hash.c
+++ b/tools/perf/bench/futex-hash.c
@@ -8,8 +8,10 @@
  * many threads and futexes as possible.
  */
 
+/* For the CLR_() macros */
+#include <pthread.h>
+
 #include "../perf.h"
-#include "../util/util.h"
 #include "../util/stat.h"
 #include <subcmd/parse-options.h>
 #include "../util/header.h"
@@ -17,9 +19,7 @@
 #include "futex.h"
 
 #include <err.h>
-#include <stdlib.h>
 #include <sys/time.h>
-#include <pthread.h>
 
 static unsigned int nthreads = 0;
 static unsigned int nsecs    = 10;
diff --git a/tools/perf/bench/futex-lock-pi.c b/tools/perf/bench/futex-lock-pi.c
index 6952db65508ab..be95506cc0d15 100644
--- a/tools/perf/bench/futex-lock-pi.c
+++ b/tools/perf/bench/futex-lock-pi.c
@@ -2,6 +2,9 @@
  * Copyright (C) 2015 Davidlohr Bueso.
  */
 
+/* For the CLR_() macros */
+#include <pthread.h>
+
 #include "../perf.h"
 #include "../util/util.h"
 #include "../util/stat.h"
@@ -13,7 +16,6 @@
 #include <err.h>
 #include <stdlib.h>
 #include <sys/time.h>
-#include <pthread.h>
 
 struct worker {
 	int tid;
diff --git a/tools/perf/bench/futex-requeue.c b/tools/perf/bench/futex-requeue.c
index 7182386830134..7d9712c8ff01a 100644
--- a/tools/perf/bench/futex-requeue.c
+++ b/tools/perf/bench/futex-requeue.c
@@ -8,6 +8,9 @@
  * requeues without waking up any tasks -- thus mimicking a regular futex_wait.
  */
 
+/* For the CLR_() macros */
+#include <pthread.h>
+
 #include "../perf.h"
 #include "../util/util.h"
 #include "../util/stat.h"
@@ -19,7 +22,6 @@
 #include <err.h>
 #include <stdlib.h>
 #include <sys/time.h>
-#include <pthread.h>
 
 static u_int32_t futex1 = 0, futex2 = 0;
 
diff --git a/tools/perf/bench/futex-wake-parallel.c b/tools/perf/bench/futex-wake-parallel.c
index 91aaf2a1fa905..aca12284d8af2 100644
--- a/tools/perf/bench/futex-wake-parallel.c
+++ b/tools/perf/bench/futex-wake-parallel.c
@@ -7,6 +7,9 @@
  * it can be used to measure futex_wake() changes.
  */
 
+/* For the CLR_() macros */
+#include <pthread.h>
+
 #include "../perf.h"
 #include "../util/util.h"
 #include "../util/stat.h"
@@ -18,7 +21,6 @@
 #include <err.h>
 #include <stdlib.h>
 #include <sys/time.h>
-#include <pthread.h>
 
 struct thread_data {
 	pthread_t worker;
diff --git a/tools/perf/bench/futex-wake.c b/tools/perf/bench/futex-wake.c
index f416bd705f661..877e680b28a8c 100644
--- a/tools/perf/bench/futex-wake.c
+++ b/tools/perf/bench/futex-wake.c
@@ -8,6 +8,9 @@
  * one or more tasks, and thus the waitqueue is never empty.
  */
 
+/* For the CLR_() macros */
+#include <pthread.h>
+
 #include "../perf.h"
 #include "../util/util.h"
 #include "../util/stat.h"
@@ -19,7 +22,6 @@
 #include <err.h>
 #include <stdlib.h>
 #include <sys/time.h>
-#include <pthread.h>
 
 /* all threads will block on the same futex */
 static u_int32_t futex1 = 0;
diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
index 7500d959d7eb0..f7f530081aa94 100644
--- a/tools/perf/bench/numa.c
+++ b/tools/perf/bench/numa.c
@@ -4,6 +4,9 @@
  * numa: Simulate NUMA-sensitive workload and measure their NUMA performance
  */
 
+/* For the CLR_() macros */
+#include <pthread.h>
+
 #include "../perf.h"
 #include "../builtin.h"
 #include "../util/util.h"
@@ -21,7 +24,6 @@
 #include <stdlib.h>
 #include <string.h>
 #include <unistd.h>
-#include <pthread.h>
 #include <sys/mman.h>
 #include <sys/time.h>
 #include <sys/resource.h>

From 1fbe7df819d9958f139b87014a2f0d5b34da76d5 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 6 Jul 2016 12:19:19 -0300
Subject: [PATCH 15/66] perf tests: Add missing pthread.h include for CPU_*()
 macros

Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-dfcynqzvecsu55zmpxub9jgv@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/mmap-basic.c              | 3 +++
 tools/perf/tests/openat-syscall-all-cpus.c | 3 +++
 tools/perf/tests/perf-record.c             | 3 +++
 3 files changed, 9 insertions(+)

diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c
index 5c9b931b7b66a..634bce9caebd3 100644
--- a/tools/perf/tests/mmap-basic.c
+++ b/tools/perf/tests/mmap-basic.c
@@ -1,3 +1,6 @@
+/* For the CLR_() macros */
+#include <pthread.h>
+
 #include "evlist.h"
 #include "evsel.h"
 #include "thread_map.h"
diff --git a/tools/perf/tests/openat-syscall-all-cpus.c b/tools/perf/tests/openat-syscall-all-cpus.c
index 265abb12dfffc..c8d9592eb142d 100644
--- a/tools/perf/tests/openat-syscall-all-cpus.c
+++ b/tools/perf/tests/openat-syscall-all-cpus.c
@@ -1,3 +1,6 @@
+/* For the CPU_* macros */
+#include <pthread.h>
+
 #include <api/fs/fs.h>
 #include <linux/err.h>
 #include "evsel.h"
diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c
index 3eb67a977b6ae..8f2e1de6d0eae 100644
--- a/tools/perf/tests/perf-record.c
+++ b/tools/perf/tests/perf-record.c
@@ -1,3 +1,6 @@
+/* For the CLR_() macros */
+#include <pthread.h>
+
 #include <sched.h>
 #include "evlist.h"
 #include "evsel.h"

From 48e1f91ad2cadcb5689a2a3b6ed141d45009b45e Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 5 Jul 2016 14:43:27 -0300
Subject: [PATCH 16/66] perf trace: Add conditional define for AT_FDCWD

This one was only defined if _GNU_SOURCE was set in older glibc
versions, check that and provide the define in such cases.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-ilsgsysr6s3mru7rf2befnu5@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-trace.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index e7e0b6e306b7c..570a78c706c2d 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -334,6 +334,10 @@ static size_t syscall_arg__scnprintf_fd(char *bf, size_t size,
 
 #define SCA_FD syscall_arg__scnprintf_fd
 
+#ifndef AT_FDCWD
+#define AT_FDCWD	-100
+#endif
+
 static size_t syscall_arg__scnprintf_fd_at(char *bf, size_t size,
 					   struct syscall_arg *arg)
 {

From ab6526b2ca2c2c3b383a24b2a0c68c5a8f71b820 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 5 Jul 2016 14:43:27 -0300
Subject: [PATCH 17/66] perf tests openat-syscall-tp-fields: Add some
 conditional defines

These were only defined if _GNU_SOURCE was set in older glibc versions,
check that and provide the defines in such cases.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-b8esouhpg4tk6vi4n3d7ipch@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/openat-syscall-tp-fields.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/tools/perf/tests/openat-syscall-tp-fields.c b/tools/perf/tests/openat-syscall-tp-fields.c
index 942dbf43d7c74..f52239fed3619 100644
--- a/tools/perf/tests/openat-syscall-tp-fields.c
+++ b/tools/perf/tests/openat-syscall-tp-fields.c
@@ -6,6 +6,13 @@
 #include "tests.h"
 #include "debug.h"
 
+#ifndef O_DIRECTORY
+#define O_DIRECTORY    00200000
+#endif
+#ifndef AT_FDCWD
+#define AT_FDCWD       -100
+#endif
+
 int test__syscall_openat_tp_fields(int subtest __maybe_unused)
 {
 	struct record_opts opts = {

From 9c304f6c715f1849bb5b0d450a600dc731a80bda Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 7 Jul 2016 11:01:46 -0300
Subject: [PATCH 18/66] perf bench: Disentangle headers

We should try avoiding that perf.h header, it includes way too much
stuff, making it difficult to use things like setting _GNU_SOURCE only
on a small set of headers.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Davidlohr Bueso <dbueso@suse.de>
Cc: Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-lb6eg9w1kzrwhv0gm3ho0h54@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/bench/futex-hash.c          | 8 ++++++--
 tools/perf/bench/futex-lock-pi.c       | 6 +++---
 tools/perf/bench/futex-requeue.c       | 6 +++---
 tools/perf/bench/futex-wake-parallel.c | 6 +++---
 tools/perf/bench/futex-wake.c          | 6 +++---
 5 files changed, 18 insertions(+), 14 deletions(-)

diff --git a/tools/perf/bench/futex-hash.c b/tools/perf/bench/futex-hash.c
index 8fc1782f90f52..caa9726ec9bd6 100644
--- a/tools/perf/bench/futex-hash.c
+++ b/tools/perf/bench/futex-hash.c
@@ -11,10 +11,14 @@
 /* For the CLR_() macros */
 #include <pthread.h>
 
-#include "../perf.h"
+#include <errno.h>
+#include <signal.h>
+#include <stdlib.h>
+#include <linux/kernel.h>
+#include <sys/time.h>
+
 #include "../util/stat.h"
 #include <subcmd/parse-options.h>
-#include "../util/header.h"
 #include "bench.h"
 #include "futex.h"
 
diff --git a/tools/perf/bench/futex-lock-pi.c b/tools/perf/bench/futex-lock-pi.c
index be95506cc0d15..e2ba0d6f64fea 100644
--- a/tools/perf/bench/futex-lock-pi.c
+++ b/tools/perf/bench/futex-lock-pi.c
@@ -5,11 +5,11 @@
 /* For the CLR_() macros */
 #include <pthread.h>
 
-#include "../perf.h"
-#include "../util/util.h"
+#include <signal.h>
 #include "../util/stat.h"
 #include <subcmd/parse-options.h>
-#include "../util/header.h"
+#include <linux/kernel.h>
+#include <errno.h>
 #include "bench.h"
 #include "futex.h"
 
diff --git a/tools/perf/bench/futex-requeue.c b/tools/perf/bench/futex-requeue.c
index 7d9712c8ff01a..7eceb0500900e 100644
--- a/tools/perf/bench/futex-requeue.c
+++ b/tools/perf/bench/futex-requeue.c
@@ -11,11 +11,11 @@
 /* For the CLR_() macros */
 #include <pthread.h>
 
-#include "../perf.h"
-#include "../util/util.h"
+#include <signal.h>
 #include "../util/stat.h"
 #include <subcmd/parse-options.h>
-#include "../util/header.h"
+#include <linux/kernel.h>
+#include <errno.h>
 #include "bench.h"
 #include "futex.h"
 
diff --git a/tools/perf/bench/futex-wake-parallel.c b/tools/perf/bench/futex-wake-parallel.c
index aca12284d8af2..8143b54ff119b 100644
--- a/tools/perf/bench/futex-wake-parallel.c
+++ b/tools/perf/bench/futex-wake-parallel.c
@@ -10,11 +10,11 @@
 /* For the CLR_() macros */
 #include <pthread.h>
 
-#include "../perf.h"
-#include "../util/util.h"
+#include <signal.h>
 #include "../util/stat.h"
 #include <subcmd/parse-options.h>
-#include "../util/header.h"
+#include <linux/kernel.h>
+#include <errno.h>
 #include "bench.h"
 #include "futex.h"
 
diff --git a/tools/perf/bench/futex-wake.c b/tools/perf/bench/futex-wake.c
index 877e680b28a8c..e978d5610e5ff 100644
--- a/tools/perf/bench/futex-wake.c
+++ b/tools/perf/bench/futex-wake.c
@@ -11,11 +11,11 @@
 /* For the CLR_() macros */
 #include <pthread.h>
 
-#include "../perf.h"
-#include "../util/util.h"
+#include <signal.h>
 #include "../util/stat.h"
 #include <subcmd/parse-options.h>
-#include "../util/header.h"
+#include <linux/kernel.h>
+#include <errno.h>
 #include "bench.h"
 #include "futex.h"
 

From cec07f53c398f22576df77052c4777dc13f14962 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 7 Jul 2016 18:28:43 -0300
Subject: [PATCH 19/66] perf tools: Move syscall number fallbacks from
 perf-sys.h to tools/arch/x86/include/asm/

And remove the empty tools/arch/x86/include/asm/unistd_{32,64}.h files
introduced by eae7a755ee81 ("perf tools, x86: Build perf on older
user-space as well").

This way we get closer to mirroring the kernel for cases where __NR_
can't be found for some include path/_GNU_SOURCE/whatever scenario.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-kpj6m3mbjw82kg6krk2z529e@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/arch/x86/include/asm/unistd_32.h  |  9 +++++++++
 tools/arch/x86/include/asm/unistd_64.h  |  9 +++++++++
 tools/perf/config/Makefile              |  1 +
 tools/perf/perf-sys.h                   | 18 ------------------
 tools/perf/util/include/asm/unistd_32.h |  1 -
 tools/perf/util/include/asm/unistd_64.h |  1 -
 6 files changed, 19 insertions(+), 20 deletions(-)
 create mode 100644 tools/arch/x86/include/asm/unistd_32.h
 create mode 100644 tools/arch/x86/include/asm/unistd_64.h
 delete mode 100644 tools/perf/util/include/asm/unistd_32.h
 delete mode 100644 tools/perf/util/include/asm/unistd_64.h

diff --git a/tools/arch/x86/include/asm/unistd_32.h b/tools/arch/x86/include/asm/unistd_32.h
new file mode 100644
index 0000000000000..cf33ab09273df
--- /dev/null
+++ b/tools/arch/x86/include/asm/unistd_32.h
@@ -0,0 +1,9 @@
+#ifndef __NR_perf_event_open
+# define __NR_perf_event_open 336
+#endif
+#ifndef __NR_futex
+# define __NR_futex 240
+#endif
+#ifndef __NR_gettid
+# define __NR_gettid 224
+#endif
diff --git a/tools/arch/x86/include/asm/unistd_64.h b/tools/arch/x86/include/asm/unistd_64.h
new file mode 100644
index 0000000000000..2c9835695b56e
--- /dev/null
+++ b/tools/arch/x86/include/asm/unistd_64.h
@@ -0,0 +1,9 @@
+#ifndef __NR_perf_event_open
+# define __NR_perf_event_open 298
+#endif
+#ifndef __NR_futex
+# define __NR_futex 202
+#endif
+#ifndef __NR_gettid
+# define __NR_gettid 186
+#endif
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index c7e269a7ca373..7d2ea691c11ba 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -209,6 +209,7 @@ CFLAGS += -I$(src-perf)/arch/$(ARCH)/include
 CFLAGS += -I$(srctree)/tools/include/
 CFLAGS += -I$(srctree)/arch/$(ARCH)/include/uapi
 CFLAGS += -I$(srctree)/arch/$(ARCH)/include
+CFLAGS += -I$(srctree)/tools/arch/$(ARCH)/include
 CFLAGS += -I$(srctree)/include/uapi
 CFLAGS += -I$(srctree)/include
 
diff --git a/tools/perf/perf-sys.h b/tools/perf/perf-sys.h
index 83a25cef82fdd..5cee8a3d0455c 100644
--- a/tools/perf/perf-sys.h
+++ b/tools/perf/perf-sys.h
@@ -11,29 +11,11 @@
 #if defined(__i386__)
 #define cpu_relax()	asm volatile("rep; nop" ::: "memory");
 #define CPUINFO_PROC	{"model name"}
-#ifndef __NR_perf_event_open
-# define __NR_perf_event_open 336
-#endif
-#ifndef __NR_futex
-# define __NR_futex 240
-#endif
-#ifndef __NR_gettid
-# define __NR_gettid 224
-#endif
 #endif
 
 #if defined(__x86_64__)
 #define cpu_relax()	asm volatile("rep; nop" ::: "memory");
 #define CPUINFO_PROC	{"model name"}
-#ifndef __NR_perf_event_open
-# define __NR_perf_event_open 298
-#endif
-#ifndef __NR_futex
-# define __NR_futex 202
-#endif
-#ifndef __NR_gettid
-# define __NR_gettid 186
-#endif
 #endif
 
 #ifdef __powerpc__
diff --git a/tools/perf/util/include/asm/unistd_32.h b/tools/perf/util/include/asm/unistd_32.h
deleted file mode 100644
index 8b137891791fe..0000000000000
--- a/tools/perf/util/include/asm/unistd_32.h
+++ /dev/null
@@ -1 +0,0 @@
-
diff --git a/tools/perf/util/include/asm/unistd_64.h b/tools/perf/util/include/asm/unistd_64.h
deleted file mode 100644
index 8b137891791fe..0000000000000
--- a/tools/perf/util/include/asm/unistd_64.h
+++ /dev/null
@@ -1 +0,0 @@
-

From 7ed0958ae877c0c470b5ff4c26e7ad9f676ef3ed Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 7 Jul 2016 11:06:58 -0300
Subject: [PATCH 20/66] perf strbuf: Add missing headers

We were only indirectly and by luck getting types, etc needed for this
file, fix it.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-gr8ejvzm7ojk6zwpeplyx9zu@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/strbuf.c | 2 +-
 tools/perf/util/strbuf.h | 3 +++
 2 files changed, 4 insertions(+), 1 deletion(-)

diff --git a/tools/perf/util/strbuf.c b/tools/perf/util/strbuf.c
index f95f682aa2b2c..817593908d47a 100644
--- a/tools/perf/util/strbuf.c
+++ b/tools/perf/util/strbuf.c
@@ -1,5 +1,5 @@
 #include "debug.h"
-#include "cache.h"
+#include "util.h"
 #include <linux/kernel.h>
 
 int prefixcmp(const char *str, const char *prefix)
diff --git a/tools/perf/util/strbuf.h b/tools/perf/util/strbuf.h
index 54b409297d4a0..b268a6648a5d6 100644
--- a/tools/perf/util/strbuf.h
+++ b/tools/perf/util/strbuf.h
@@ -40,6 +40,9 @@
 
 #include <assert.h>
 #include <stdarg.h>
+#include <stddef.h>
+#include <string.h>
+#include <sys/types.h>
 
 extern char strbuf_slopbuf[];
 struct strbuf {

From 380a71a22b5a3270fbcc57ef45b6108941a6852c Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 7 Jul 2016 11:17:38 -0300
Subject: [PATCH 21/66] perf quote: Disentangle headers

No need to include stdio.h from quote.h, also forward declare strbuf.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-k3kbcxhctpxvz6ckve3kv6c1@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/quote.c | 4 +++-
 tools/perf/util/quote.h | 3 ++-
 2 files changed, 5 insertions(+), 2 deletions(-)

diff --git a/tools/perf/util/quote.c b/tools/perf/util/quote.c
index c6d4ee2de752d..639d1da2f9786 100644
--- a/tools/perf/util/quote.c
+++ b/tools/perf/util/quote.c
@@ -1,5 +1,7 @@
-#include "cache.h"
+#include <stdlib.h>
+#include "strbuf.h"
 #include "quote.h"
+#include "util.h"
 
 /* Help to copy the thing properly quoted for the shell safety.
  * any single quote is replaced with '\'', any exclamation point
diff --git a/tools/perf/util/quote.h b/tools/perf/util/quote.h
index e1ec19146fb05..055ca45bed992 100644
--- a/tools/perf/util/quote.h
+++ b/tools/perf/util/quote.h
@@ -2,7 +2,6 @@
 #define __PERF_QUOTE_H
 
 #include <stddef.h>
-#include <stdio.h>
 
 /* Help to copy the thing properly quoted for the shell safety.
  * any single quote is replaced with '\'', any exclamation point
@@ -24,6 +23,8 @@
  * sq_quote() in a real application.
  */
 
+struct strbuf;
+
 int sq_quote_argv(struct strbuf *, const char **argv, size_t maxlen);
 
 #endif /* __PERF_QUOTE_H */

From 3ac55b1df0a7c5fb92890b23a620165b82f45c8a Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 7 Jul 2016 11:32:29 -0300
Subject: [PATCH 22/66] perf tests cpumap: Add missing headers

It was getting all sort of needed stuff by sheer luck, via indirect
includes, fix it.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-tvjgo39t8k0ye6dntv3knran@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/cpumap.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/tools/perf/tests/cpumap.c b/tools/perf/tests/cpumap.c
index c9ec5f83e42c9..f168a85992d0c 100644
--- a/tools/perf/tests/cpumap.c
+++ b/tools/perf/tests/cpumap.c
@@ -1,5 +1,12 @@
 #include "tests.h"
+#include <stdio.h>
 #include "cpumap.h"
+#include "event.h"
+#include <string.h>
+#include <linux/bitops.h>
+#include "debug.h"
+
+struct machine;
 
 static int process_event_mask(struct perf_tool *tool __maybe_unused,
 			 union perf_event *event,

From 16b91d5ed4d81483001822ade3c9ea8d50628b0b Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 7 Jul 2016 11:35:04 -0300
Subject: [PATCH 23/66] perf test fdarray: Add missing poll.h header

It uses poll() but was getting the needed header by chance, do it
explicitely.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-76b3c5imnl6p69j4lqewzu9l@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/fdarray.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/perf/tests/fdarray.c b/tools/perf/tests/fdarray.c
index 59dbd0550c517..a2b5ff9bf83d6 100644
--- a/tools/perf/tests/fdarray.c
+++ b/tools/perf/tests/fdarray.c
@@ -1,4 +1,5 @@
 #include <api/fd/array.h>
+#include <poll.h>
 #include "util/debug.h"
 #include "tests/tests.h"
 

From 10ca87fde70d9e7b25e576c491823915c80fa9f6 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 7 Jul 2016 11:35:50 -0300
Subject: [PATCH 24/66] perf tests x86 rdpmc: Add missing headers

Another case of a file using definitions and getting them by chance,
from indirect header inclusion, fix it.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-o3l1vi4gw2w6xyc6z4ig938s@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/arch/x86/tests/rdpmc.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/tools/perf/arch/x86/tests/rdpmc.c b/tools/perf/arch/x86/tests/rdpmc.c
index a32d72e91ffa0..500cf96db9790 100644
--- a/tools/perf/arch/x86/tests/rdpmc.c
+++ b/tools/perf/arch/x86/tests/rdpmc.c
@@ -1,12 +1,16 @@
+#include <errno.h>
 #include <unistd.h>
 #include <stdlib.h>
 #include <signal.h>
 #include <sys/mman.h>
+#include <sys/types.h>
+#include <sys/wait.h>
 #include <linux/types.h>
 #include "perf.h"
 #include "debug.h"
 #include "tests/tests.h"
 #include "cloexec.h"
+#include "util.h"
 #include "arch-tests.h"
 
 static u64 rdpmc(unsigned int counter)

From 16b7c9bda52a593fb3a7e3a9848d7596777a73f5 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 7 Jul 2016 11:37:08 -0300
Subject: [PATCH 25/66] perf tools: Add missing header to color.c

It uses isatty(), so needs unistd.h, include it.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-ivwuz8f68tb3sdcpguo9wmvx@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/color.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/perf/util/color.c b/tools/perf/util/color.c
index 1210ba555d07b..47a34b561f5da 100644
--- a/tools/perf/util/color.c
+++ b/tools/perf/util/color.c
@@ -3,6 +3,7 @@
 #include "config.h"
 #include "color.h"
 #include <math.h>
+#include <unistd.h>
 
 int perf_use_color_default = -1;
 

From 175729fc2c5144e9eee06b3483c5c9798f7062a5 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 7 Jul 2016 11:38:09 -0300
Subject: [PATCH 26/66] perf tools: Remove needless includes from cache.h

The cache.h header doesn't use any of the definitions in some of the
headers it includes, ditch them and fix the fallout, where files were
getting stuff they needed just because they were including it, sometimes
not using what it really exports at all.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-l6r2bmj8h1g3e01wr981on0n@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/arch/common.c      | 1 +
 tools/perf/tests/llvm.c       | 1 +
 tools/perf/ui/gtk/util.c      | 1 +
 tools/perf/ui/helpline.c      | 1 +
 tools/perf/ui/tui/setup.c     | 2 ++
 tools/perf/util/alias.c       | 1 +
 tools/perf/util/cache.h       | 3 ---
 tools/perf/util/levenshtein.c | 4 +++-
 tools/perf/util/llvm-utils.c  | 2 ++
 tools/perf/util/path.c        | 2 ++
 tools/perf/util/target.c      | 1 +
 11 files changed, 15 insertions(+), 4 deletions(-)

diff --git a/tools/perf/arch/common.c b/tools/perf/arch/common.c
index ee6966812a5a4..886dd2aaff0d8 100644
--- a/tools/perf/arch/common.c
+++ b/tools/perf/arch/common.c
@@ -1,6 +1,7 @@
 #include <stdio.h>
 #include <sys/utsname.h>
 #include "common.h"
+#include "../util/util.h"
 #include "../util/debug.h"
 
 const char *const arm_triplets[] = {
diff --git a/tools/perf/tests/llvm.c b/tools/perf/tests/llvm.c
index cff564fb4b667..b798a4bfd2389 100644
--- a/tools/perf/tests/llvm.c
+++ b/tools/perf/tests/llvm.c
@@ -5,6 +5,7 @@
 #include "llvm.h"
 #include "tests.h"
 #include "debug.h"
+#include "util.h"
 
 #ifdef HAVE_LIBBPF_SUPPORT
 static int test__bpf_parsing(void *obj_buf, size_t obj_buf_sz)
diff --git a/tools/perf/ui/gtk/util.c b/tools/perf/ui/gtk/util.c
index 52e7fc48af9f4..00b91921edb1f 100644
--- a/tools/perf/ui/gtk/util.c
+++ b/tools/perf/ui/gtk/util.c
@@ -1,4 +1,5 @@
 #include "../util.h"
+#include "../../util/util.h"
 #include "../../util/debug.h"
 #include "gtk.h"
 
diff --git a/tools/perf/ui/helpline.c b/tools/perf/ui/helpline.c
index 700fb3cfa1c73..5b74a7eba210b 100644
--- a/tools/perf/ui/helpline.c
+++ b/tools/perf/ui/helpline.c
@@ -5,6 +5,7 @@
 #include "../debug.h"
 #include "helpline.h"
 #include "ui.h"
+#include "../util.h"
 
 char ui_helpline__current[512];
 
diff --git a/tools/perf/ui/tui/setup.c b/tools/perf/ui/tui/setup.c
index 7dfeba0a91f37..4ea2ba861fc2f 100644
--- a/tools/perf/ui/tui/setup.c
+++ b/tools/perf/ui/tui/setup.c
@@ -1,3 +1,4 @@
+#include <errno.h>
 #include <signal.h>
 #include <stdbool.h>
 #ifdef HAVE_BACKTRACE_SUPPORT
@@ -6,6 +7,7 @@
 
 #include "../../util/cache.h"
 #include "../../util/debug.h"
+#include "../../util/util.h"
 #include "../browser.h"
 #include "../helpline.h"
 #include "../ui.h"
diff --git a/tools/perf/util/alias.c b/tools/perf/util/alias.c
index 6c80f830358b5..6455471d9cd1e 100644
--- a/tools/perf/util/alias.c
+++ b/tools/perf/util/alias.c
@@ -1,4 +1,5 @@
 #include "cache.h"
+#include "util.h"
 #include "config.h"
 
 static const char *alias_key;
diff --git a/tools/perf/util/cache.h b/tools/perf/util/cache.h
index 9f90e36b56fbe..512c0c83fbc6a 100644
--- a/tools/perf/util/cache.h
+++ b/tools/perf/util/cache.h
@@ -1,11 +1,8 @@
 #ifndef __PERF_CACHE_H
 #define __PERF_CACHE_H
 
-#include <stdbool.h>
-#include "util.h"
 #include "strbuf.h"
 #include <subcmd/pager.h>
-#include "../perf.h"
 #include "../ui/ui.h"
 
 #include <linux/string.h>
diff --git a/tools/perf/util/levenshtein.c b/tools/perf/util/levenshtein.c
index e521d1516df6e..f616e4f65b674 100644
--- a/tools/perf/util/levenshtein.c
+++ b/tools/perf/util/levenshtein.c
@@ -1,5 +1,7 @@
-#include "cache.h"
 #include "levenshtein.h"
+#include <errno.h>
+#include <stdlib.h>
+#include <string.h>
 
 /*
  * This function implements the Damerau-Levenshtein algorithm to
diff --git a/tools/perf/util/llvm-utils.c b/tools/perf/util/llvm-utils.c
index 282c30f6a51d9..bf7216b8731dd 100644
--- a/tools/perf/util/llvm-utils.c
+++ b/tools/perf/util/llvm-utils.c
@@ -3,12 +3,14 @@
  * Copyright (C) 2015, Huawei Inc.
  */
 
+#include <errno.h>
 #include <limits.h>
 #include <stdio.h>
 #include <stdlib.h>
 #include "debug.h"
 #include "llvm-utils.h"
 #include "config.h"
+#include "util.h"
 
 #define CLANG_BPF_CMD_DEFAULT_TEMPLATE				\
 		"$CLANG_EXEC -D__KERNEL__ -D__NR_CPUS__=$NR_CPUS "\
diff --git a/tools/perf/util/path.c b/tools/perf/util/path.c
index cff8bf0f87e8e..7c7630be5a897 100644
--- a/tools/perf/util/path.c
+++ b/tools/perf/util/path.c
@@ -11,6 +11,8 @@
  * which is what it's designed for.
  */
 #include "cache.h"
+#include "util.h"
+#include <limits.h>
 
 static char bad_path[] = "/bad-path/";
 /*
diff --git a/tools/perf/util/target.c b/tools/perf/util/target.c
index 5898af4510ccf..8cdcf4641c51d 100644
--- a/tools/perf/util/target.c
+++ b/tools/perf/util/target.c
@@ -7,6 +7,7 @@
  */
 
 #include "target.h"
+#include "util.h"
 #include "debug.h"
 
 #include <pwd.h>

From 5496bc0c0d255f2a8a3a4c36087eb3b72ff63ea0 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 7 Jul 2016 11:51:47 -0300
Subject: [PATCH 27/66] perf evsel: Uninline the is_function_event method

So that we don't have to carry a string.h header in evsel.h

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-2lwpm2aytdvvgo626zuat6et@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/evsel.c | 18 ++++++++++++++++++
 tools/perf/util/evsel.h | 18 +-----------------
 2 files changed, 19 insertions(+), 17 deletions(-)

diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index d8c2298cd32a3..ba0f59fa3d5dd 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -200,6 +200,24 @@ void perf_evsel__set_sample_id(struct perf_evsel *evsel,
 	evsel->attr.read_format |= PERF_FORMAT_ID;
 }
 
+/**
+ * perf_evsel__is_function_event - Return whether given evsel is a function
+ * trace event
+ *
+ * @evsel - evsel selector to be tested
+ *
+ * Return %true if event is function trace event
+ */
+bool perf_evsel__is_function_event(struct perf_evsel *evsel)
+{
+#define FUNCTION_EVENT "ftrace:function"
+
+	return evsel->name &&
+	       !strncmp(FUNCTION_EVENT, evsel->name, sizeof(FUNCTION_EVENT));
+
+#undef FUNCTION_EVENT
+}
+
 void perf_evsel__init(struct perf_evsel *evsel,
 		      struct perf_event_attr *attr, int idx)
 {
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 86fed7a2932bd..d73391e8740e4 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -355,23 +355,7 @@ static inline bool perf_evsel__is_group_event(struct perf_evsel *evsel)
 	return perf_evsel__is_group_leader(evsel) && evsel->nr_members > 1;
 }
 
-/**
- * perf_evsel__is_function_event - Return whether given evsel is a function
- * trace event
- *
- * @evsel - evsel selector to be tested
- *
- * Return %true if event is function trace event
- */
-static inline bool perf_evsel__is_function_event(struct perf_evsel *evsel)
-{
-#define FUNCTION_EVENT "ftrace:function"
-
-	return evsel->name &&
-	       !strncmp(FUNCTION_EVENT, evsel->name, sizeof(FUNCTION_EVENT));
-
-#undef FUNCTION_EVENT
-}
+bool perf_evsel__is_function_event(struct perf_evsel *evsel);
 
 static inline bool perf_evsel__is_bpf_output(struct perf_evsel *evsel)
 {

From d0761e37fe3fed7810ed8d6e130b79359f0c3e13 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 7 Jul 2016 15:42:33 -0300
Subject: [PATCH 28/66] perf tools: Uninline scnprintf() and vscnprint()

They were in tools/include/linux/kernel.h, requiring that it in turn
included stdio.h, which is way too heavy.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-855h8olnkot9v0dajuee1lo3@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/linux/kernel.h       | 28 +++-------------------------
 tools/lib/vsprintf.c               | 24 ++++++++++++++++++++++++
 tools/objtool/builtin-check.c      |  1 +
 tools/perf/MANIFEST                |  1 +
 tools/perf/util/Build              |  5 +++++
 tools/perf/util/color.c            |  2 ++
 tools/perf/util/dso.h              |  1 +
 tools/perf/util/help-unknown-cmd.c |  1 +
 tools/perf/util/python-ext-sources |  1 +
 9 files changed, 39 insertions(+), 25 deletions(-)
 create mode 100644 tools/lib/vsprintf.c

diff --git a/tools/include/linux/kernel.h b/tools/include/linux/kernel.h
index 76df53539c2a4..28607db02bd3e 100644
--- a/tools/include/linux/kernel.h
+++ b/tools/include/linux/kernel.h
@@ -2,8 +2,7 @@
 #define __TOOLS_LINUX_KERNEL_H
 
 #include <stdarg.h>
-#include <stdio.h>
-#include <stdlib.h>
+#include <stddef.h>
 #include <assert.h>
 
 #define DIV_ROUND_UP(n,d) (((n) + (d) - 1) / (d))
@@ -70,29 +69,8 @@
 #define cpu_to_le64(x)	(x)
 #define cpu_to_le32(x)	(x)
 
-static inline int
-vscnprintf(char *buf, size_t size, const char *fmt, va_list args)
-{
-	int i;
-	ssize_t ssize = size;
-
-	i = vsnprintf(buf, size, fmt, args);
-
-	return (i >= ssize) ? (ssize - 1) : i;
-}
-
-static inline int scnprintf(char * buf, size_t size, const char * fmt, ...)
-{
-	va_list args;
-	ssize_t ssize = size;
-	int i;
-
-	va_start(args, fmt);
-	i = vsnprintf(buf, size, fmt, args);
-	va_end(args);
-
-	return (i >= ssize) ? (ssize - 1) : i;
-}
+int vscnprintf(char *buf, size_t size, const char *fmt, va_list args);
+int scnprintf(char * buf, size_t size, const char * fmt, ...);
 
 /*
  * This looks more complex than it should be. But we need to
diff --git a/tools/lib/vsprintf.c b/tools/lib/vsprintf.c
new file mode 100644
index 0000000000000..45f9a06daa560
--- /dev/null
+++ b/tools/lib/vsprintf.c
@@ -0,0 +1,24 @@
+#include <sys/types.h>
+#include <linux/kernel.h>
+#include <stdio.h>
+
+int vscnprintf(char *buf, size_t size, const char *fmt, va_list args)
+{
+       int i = vsnprintf(buf, size, fmt, args);
+       ssize_t ssize = size;
+
+       return (i >= ssize) ? (ssize - 1) : i;
+}
+
+int scnprintf(char * buf, size_t size, const char * fmt, ...)
+{
+       ssize_t ssize = size;
+       va_list args;
+       int i;
+
+       va_start(args, fmt);
+       i = vsnprintf(buf, size, fmt, args);
+       va_end(args);
+
+       return (i >= ssize) ? (ssize - 1) : i;
+}
diff --git a/tools/objtool/builtin-check.c b/tools/objtool/builtin-check.c
index e8a1e69eb92c5..92d84b2770322 100644
--- a/tools/objtool/builtin-check.c
+++ b/tools/objtool/builtin-check.c
@@ -26,6 +26,7 @@
  */
 
 #include <string.h>
+#include <stdlib.h>
 #include <subcmd/parse-options.h>
 
 #include "builtin.h"
diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST
index f18e781447bcc..2bd8c310606cb 100644
--- a/tools/perf/MANIFEST
+++ b/tools/perf/MANIFEST
@@ -30,6 +30,7 @@ tools/lib/symbol/kallsyms.h
 tools/lib/find_bit.c
 tools/lib/bitmap.c
 tools/lib/str_error_r.c
+tools/lib/vsprintf.c
 tools/include/asm/atomic.h
 tools/include/asm/barrier.h
 tools/include/asm/bug.h
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index a6a8053023120..eda68f5828849 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -85,6 +85,7 @@ libperf-y += parse-regs-options.o
 libperf-y += term.o
 libperf-y += help-unknown-cmd.o
 libperf-y += mem-events.o
+libperf-y += vsprintf.o
 
 libperf-$(CONFIG_LIBBPF) += bpf-loader.o
 libperf-$(CONFIG_BPF_PROLOGUE) += bpf-prologue.o
@@ -181,3 +182,7 @@ $(OUTPUT)util/str_error_r.o: ../lib/str_error_r.c FORCE
 $(OUTPUT)util/hweight.o: ../lib/hweight.c FORCE
 	$(call rule_mkdir)
 	$(call if_changed_dep,cc_o_c)
+
+$(OUTPUT)util/vsprintf.o: ../lib/vsprintf.c FORCE
+	$(call rule_mkdir)
+	$(call if_changed_dep,cc_o_c)
diff --git a/tools/perf/util/color.c b/tools/perf/util/color.c
index 47a34b561f5da..dbbf89b050a5d 100644
--- a/tools/perf/util/color.c
+++ b/tools/perf/util/color.c
@@ -1,6 +1,8 @@
 #include <linux/kernel.h>
 #include "cache.h"
 #include "config.h"
+#include <stdlib.h>
+#include <stdio.h>
 #include "color.h"
 #include <math.h>
 #include <unistd.h>
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index a571f24895caa..ecc4bbd3f82e3 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -4,6 +4,7 @@
 #include <linux/atomic.h>
 #include <linux/types.h>
 #include <linux/rbtree.h>
+#include <sys/types.h>
 #include <stdbool.h>
 #include <pthread.h>
 #include <linux/types.h>
diff --git a/tools/perf/util/help-unknown-cmd.c b/tools/perf/util/help-unknown-cmd.c
index 776e285623452..2821f8d77e520 100644
--- a/tools/perf/util/help-unknown-cmd.c
+++ b/tools/perf/util/help-unknown-cmd.c
@@ -1,5 +1,6 @@
 #include "cache.h"
 #include "config.h"
+#include <stdio.h>
 #include <subcmd/help.h>
 #include "../builtin.h"
 #include "levenshtein.h"
diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources
index 49210b7a7925b..5065ec98049cf 100644
--- a/tools/perf/util/python-ext-sources
+++ b/tools/perf/util/python-ext-sources
@@ -14,6 +14,7 @@ util/cpumap.c
 ../lib/find_bit.c
 ../lib/hweight.c
 ../lib/str_error_r.c
+../lib/vsprintf.c
 util/thread_map.c
 util/util.c
 util/xyarray.c

From c3cec9e68f12d0046f991378391172958b5315d9 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Fri, 8 Jul 2016 15:21:37 -0300
Subject: [PATCH 29/66] tools lib traceevent: Use str_error_r()

To make it portable to non-glibc systems, that follow the XSI variant
instead of the GNU specific one that gets in place when _GNU_SOURCE is
defined.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-c1gn8x978qfop65m510wy43o@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/lib/traceevent/event-parse.c | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index a8b6357d1ffef..3a7bd175f73c3 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -31,6 +31,7 @@
 #include <errno.h>
 #include <stdint.h>
 #include <limits.h>
+#include <linux/string.h>
 
 #include <netinet/ip6.h>
 #include "event-parse.h"
@@ -6131,12 +6132,7 @@ int pevent_strerror(struct pevent *pevent __maybe_unused,
 	const char *msg;
 
 	if (errnum >= 0) {
-		msg = strerror_r(errnum, buf, buflen);
-		if (msg != buf) {
-			size_t len = strlen(msg);
-			memcpy(buf, msg, min(buflen - 1, len));
-			*(buf + min(buflen - 1, len)) = '\0';
-		}
+		str_error_r(errnum, buf, buflen);
 		return 0;
 	}
 

From b31e3e3316a78e4a2cf23be8e0d47e5e5a025bde Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Fri, 8 Jul 2016 15:26:50 -0300
Subject: [PATCH 30/66] tools lib api fs: Use str_error_r()

To make it portable to non-glibc systems, that follow the XSI variant
instead of the GNU specific one that gets in place when _GNU_SOURCE is
defined.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-mixgnh3iyajuqogn2opsocdy@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/lib/api/Makefile          | 1 +
 tools/lib/api/fs/tracing_path.c | 3 ++-
 2 files changed, 3 insertions(+), 1 deletion(-)

diff --git a/tools/lib/api/Makefile b/tools/lib/api/Makefile
index c7ceea6dd6cb7..0a6fda9837f7d 100644
--- a/tools/lib/api/Makefile
+++ b/tools/lib/api/Makefile
@@ -26,6 +26,7 @@ endif
 
 CFLAGS += -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64
 CFLAGS += -I$(srctree)/tools/lib/api
+CFLAGS += -I$(srctree)/tools/include
 
 RM = rm -f
 
diff --git a/tools/lib/api/fs/tracing_path.c b/tools/lib/api/fs/tracing_path.c
index a26bb5ea82830..251b7c342a87d 100644
--- a/tools/lib/api/fs/tracing_path.c
+++ b/tools/lib/api/fs/tracing_path.c
@@ -5,6 +5,7 @@
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
+#include <linux/string.h>
 #include <errno.h>
 #include <unistd.h>
 #include "fs.h"
@@ -118,7 +119,7 @@ static int strerror_open(int err, char *buf, size_t size, const char *filename)
 	}
 		break;
 	default:
-		snprintf(buf, size, "%s", strerror_r(err, sbuf, sizeof(sbuf)));
+		snprintf(buf, size, "%s", str_error_r(err, sbuf, sizeof(sbuf)));
 		break;
 	}
 

From 61a6445e463a3152590352d8634131955f531c6e Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Fri, 8 Jul 2016 15:38:51 -0300
Subject: [PATCH 31/66] tools lib: Guard the strlcpy() header with __GLIBC__

Better to whitelist it for libraries that require it (glibc) than
blacklist it with the ones that don't (uclibc, musl libc, etc).

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexey Brodkin <Alexey.Brodkin@synopsys.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Vineet Gupta <vgupta@synopsys.com>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-52ih0m63a2n63tanpy6yj682@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/linux/string.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/include/linux/string.h b/tools/include/linux/string.h
index b466d0228b579..b968794773116 100644
--- a/tools/include/linux/string.h
+++ b/tools/include/linux/string.h
@@ -8,7 +8,7 @@ void *memdup(const void *src, size_t len);
 
 int strtobool(const char *s, bool *res);
 
-#ifndef __UCLIBC__
+#ifdef __GLIBC__
 extern size_t strlcpy(char *dest, const char *src, size_t size);
 #endif
 

From 07eebccbca2c21f32b5142f1a55b3b6818c54116 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Fri, 8 Jul 2016 15:26:50 -0300
Subject: [PATCH 32/66] tools lib subcmd: Use str_error_r()

To make it portable to non-glibc systems, that follow the XSI variant
instead of the GNU specific one that gets in place when _GNU_SOURCE is
defined.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-bozcszy93tpgw9ad6qm3dhpx@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/lib/subcmd/run-command.c | 5 +++--
 tools/objtool/Build            | 5 +++++
 2 files changed, 8 insertions(+), 2 deletions(-)

diff --git a/tools/lib/subcmd/run-command.c b/tools/lib/subcmd/run-command.c
index f4f6c9eb8e596..911f83942723a 100644
--- a/tools/lib/subcmd/run-command.c
+++ b/tools/lib/subcmd/run-command.c
@@ -3,6 +3,7 @@
 #include <sys/stat.h>
 #include <fcntl.h>
 #include <string.h>
+#include <linux/string.h>
 #include <errno.h>
 #include <sys/wait.h>
 #include "subcmd-util.h"
@@ -109,7 +110,7 @@ int start_command(struct child_process *cmd)
 
 		if (cmd->dir && chdir(cmd->dir))
 			die("exec %s: cd to %s failed (%s)", cmd->argv[0],
-			    cmd->dir, strerror_r(errno, sbuf, sizeof(sbuf)));
+			    cmd->dir, str_error_r(errno, sbuf, sizeof(sbuf)));
 		if (cmd->env) {
 			for (; *cmd->env; cmd->env++) {
 				if (strchr(*cmd->env, '='))
@@ -173,7 +174,7 @@ static int wait_or_whine(pid_t pid)
 			if (errno == EINTR)
 				continue;
 			fprintf(stderr, " Error: waitpid failed (%s)",
-				strerror_r(errno, sbuf, sizeof(sbuf)));
+				str_error_r(errno, sbuf, sizeof(sbuf)));
 			return -ERR_RUN_COMMAND_WAITPID;
 		}
 		if (waiting != pid)
diff --git a/tools/objtool/Build b/tools/objtool/Build
index 0e89258a35412..2457916a39437 100644
--- a/tools/objtool/Build
+++ b/tools/objtool/Build
@@ -5,9 +5,14 @@ objtool-y += special.o
 objtool-y += objtool.o
 
 objtool-y += libstring.o
+objtool-y += str_error_r.o
 
 CFLAGS += -I$(srctree)/tools/lib
 
 $(OUTPUT)libstring.o: ../lib/string.c FORCE
 	$(call rule_mkdir)
 	$(call if_changed_dep,cc_o_c)
+
+$(OUTPUT)str_error_r.o: ../lib/str_error_r.c FORCE
+	$(call rule_mkdir)
+	$(call if_changed_dep,cc_o_c)

From 86695f59c952031e5596f286773d76268f3e3aad Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Mon, 11 Jul 2016 10:05:52 -0300
Subject: [PATCH 33/66] perf bench futex: Add missing compiler.h header

Since these files use __maybe_unused, and that is defined in
linux/compiler.h, include it.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Davidlohr Bueso <dbueso@suse.de>
Cc: Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-1llbf59ut6xon6ti88jm0n9j@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/bench/futex-hash.c          | 1 +
 tools/perf/bench/futex-lock-pi.c       | 1 +
 tools/perf/bench/futex-requeue.c       | 1 +
 tools/perf/bench/futex-wake-parallel.c | 1 +
 tools/perf/bench/futex-wake.c          | 1 +
 5 files changed, 5 insertions(+)

diff --git a/tools/perf/bench/futex-hash.c b/tools/perf/bench/futex-hash.c
index caa9726ec9bd6..8024cd5febd22 100644
--- a/tools/perf/bench/futex-hash.c
+++ b/tools/perf/bench/futex-hash.c
@@ -14,6 +14,7 @@
 #include <errno.h>
 #include <signal.h>
 #include <stdlib.h>
+#include <linux/compiler.h>
 #include <linux/kernel.h>
 #include <sys/time.h>
 
diff --git a/tools/perf/bench/futex-lock-pi.c b/tools/perf/bench/futex-lock-pi.c
index e2ba0d6f64fea..936d89d304835 100644
--- a/tools/perf/bench/futex-lock-pi.c
+++ b/tools/perf/bench/futex-lock-pi.c
@@ -8,6 +8,7 @@
 #include <signal.h>
 #include "../util/stat.h"
 #include <subcmd/parse-options.h>
+#include <linux/compiler.h>
 #include <linux/kernel.h>
 #include <errno.h>
 #include "bench.h"
diff --git a/tools/perf/bench/futex-requeue.c b/tools/perf/bench/futex-requeue.c
index 7eceb0500900e..f96e22ed9f873 100644
--- a/tools/perf/bench/futex-requeue.c
+++ b/tools/perf/bench/futex-requeue.c
@@ -14,6 +14,7 @@
 #include <signal.h>
 #include "../util/stat.h"
 #include <subcmd/parse-options.h>
+#include <linux/compiler.h>
 #include <linux/kernel.h>
 #include <errno.h>
 #include "bench.h"
diff --git a/tools/perf/bench/futex-wake-parallel.c b/tools/perf/bench/futex-wake-parallel.c
index 8143b54ff119b..4a2ecd7438ca0 100644
--- a/tools/perf/bench/futex-wake-parallel.c
+++ b/tools/perf/bench/futex-wake-parallel.c
@@ -13,6 +13,7 @@
 #include <signal.h>
 #include "../util/stat.h"
 #include <subcmd/parse-options.h>
+#include <linux/compiler.h>
 #include <linux/kernel.h>
 #include <errno.h>
 #include "bench.h"
diff --git a/tools/perf/bench/futex-wake.c b/tools/perf/bench/futex-wake.c
index e978d5610e5ff..87d8f4f292d95 100644
--- a/tools/perf/bench/futex-wake.c
+++ b/tools/perf/bench/futex-wake.c
@@ -14,6 +14,7 @@
 #include <signal.h>
 #include "../util/stat.h"
 #include <subcmd/parse-options.h>
+#include <linux/compiler.h>
 #include <linux/kernel.h>
 #include <errno.h>
 #include "bench.h"

From e083a21fcac9311ca425e600a15332f4792c56cc Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Mon, 11 Jul 2016 10:14:08 -0300
Subject: [PATCH 34/66] perf tools: event.h needs asm/perf_regs.h

As it uses PERF_REGS_MAX, fix it.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-2t232w0kcqu97xod8t2at2h0@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/event.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 8d363d5e65a2e..b32464b353aa4 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -8,6 +8,7 @@
 #include "map.h"
 #include "build-id.h"
 #include "perf_regs.h"
+#include <asm/perf_regs.h>
 
 struct mmap_event {
 	struct perf_event_header header;

From c4b6014e8bb0c8d47fe5c71ebc604f31091e5d3f Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Mon, 11 Jul 2016 10:28:48 -0300
Subject: [PATCH 35/66] tools: Add copy of perf_event.h to tools/include/linux/

We shouldn't use headers from the kernel sources directly, instead we
should use the system's headers or in cases where that isn't possible,
like with perf_event.h, where the introduction of kernel features such
as perf_event_attr.{write_backwards,sample_max_stack} and
PERF_EVENT_IOC_PAUSE_OUTPUT take some time to become available in
/usr/include/linux/perf_event.h we need a copy.

Do it and check for source code drift, emitting a warning when changes
are detected.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-v6aks5un3s5pehory6f42nrl@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/uapi/linux/perf_event.h | 983 ++++++++++++++++++++++++++
 tools/perf/MANIFEST                   |   3 +-
 tools/perf/Makefile.perf              |   3 +
 tools/perf/config/Makefile            |   1 +
 4 files changed, 988 insertions(+), 2 deletions(-)
 create mode 100644 tools/include/uapi/linux/perf_event.h

diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
new file mode 100644
index 0000000000000..c66a485a24ac8
--- /dev/null
+++ b/tools/include/uapi/linux/perf_event.h
@@ -0,0 +1,983 @@
+/*
+ * Performance events:
+ *
+ *    Copyright (C) 2008-2009, Thomas Gleixner <tglx@linutronix.de>
+ *    Copyright (C) 2008-2011, Red Hat, Inc., Ingo Molnar
+ *    Copyright (C) 2008-2011, Red Hat, Inc., Peter Zijlstra
+ *
+ * Data type definitions, declarations, prototypes.
+ *
+ *    Started by: Thomas Gleixner and Ingo Molnar
+ *
+ * For licencing details see kernel-base/COPYING
+ */
+#ifndef _UAPI_LINUX_PERF_EVENT_H
+#define _UAPI_LINUX_PERF_EVENT_H
+
+#include <linux/types.h>
+#include <linux/ioctl.h>
+#include <asm/byteorder.h>
+
+/*
+ * User-space ABI bits:
+ */
+
+/*
+ * attr.type
+ */
+enum perf_type_id {
+	PERF_TYPE_HARDWARE			= 0,
+	PERF_TYPE_SOFTWARE			= 1,
+	PERF_TYPE_TRACEPOINT			= 2,
+	PERF_TYPE_HW_CACHE			= 3,
+	PERF_TYPE_RAW				= 4,
+	PERF_TYPE_BREAKPOINT			= 5,
+
+	PERF_TYPE_MAX,				/* non-ABI */
+};
+
+/*
+ * Generalized performance event event_id types, used by the
+ * attr.event_id parameter of the sys_perf_event_open()
+ * syscall:
+ */
+enum perf_hw_id {
+	/*
+	 * Common hardware events, generalized by the kernel:
+	 */
+	PERF_COUNT_HW_CPU_CYCLES		= 0,
+	PERF_COUNT_HW_INSTRUCTIONS		= 1,
+	PERF_COUNT_HW_CACHE_REFERENCES		= 2,
+	PERF_COUNT_HW_CACHE_MISSES		= 3,
+	PERF_COUNT_HW_BRANCH_INSTRUCTIONS	= 4,
+	PERF_COUNT_HW_BRANCH_MISSES		= 5,
+	PERF_COUNT_HW_BUS_CYCLES		= 6,
+	PERF_COUNT_HW_STALLED_CYCLES_FRONTEND	= 7,
+	PERF_COUNT_HW_STALLED_CYCLES_BACKEND	= 8,
+	PERF_COUNT_HW_REF_CPU_CYCLES		= 9,
+
+	PERF_COUNT_HW_MAX,			/* non-ABI */
+};
+
+/*
+ * Generalized hardware cache events:
+ *
+ *       { L1-D, L1-I, LLC, ITLB, DTLB, BPU, NODE } x
+ *       { read, write, prefetch } x
+ *       { accesses, misses }
+ */
+enum perf_hw_cache_id {
+	PERF_COUNT_HW_CACHE_L1D			= 0,
+	PERF_COUNT_HW_CACHE_L1I			= 1,
+	PERF_COUNT_HW_CACHE_LL			= 2,
+	PERF_COUNT_HW_CACHE_DTLB		= 3,
+	PERF_COUNT_HW_CACHE_ITLB		= 4,
+	PERF_COUNT_HW_CACHE_BPU			= 5,
+	PERF_COUNT_HW_CACHE_NODE		= 6,
+
+	PERF_COUNT_HW_CACHE_MAX,		/* non-ABI */
+};
+
+enum perf_hw_cache_op_id {
+	PERF_COUNT_HW_CACHE_OP_READ		= 0,
+	PERF_COUNT_HW_CACHE_OP_WRITE		= 1,
+	PERF_COUNT_HW_CACHE_OP_PREFETCH		= 2,
+
+	PERF_COUNT_HW_CACHE_OP_MAX,		/* non-ABI */
+};
+
+enum perf_hw_cache_op_result_id {
+	PERF_COUNT_HW_CACHE_RESULT_ACCESS	= 0,
+	PERF_COUNT_HW_CACHE_RESULT_MISS		= 1,
+
+	PERF_COUNT_HW_CACHE_RESULT_MAX,		/* non-ABI */
+};
+
+/*
+ * Special "software" events provided by the kernel, even if the hardware
+ * does not support performance events. These events measure various
+ * physical and sw events of the kernel (and allow the profiling of them as
+ * well):
+ */
+enum perf_sw_ids {
+	PERF_COUNT_SW_CPU_CLOCK			= 0,
+	PERF_COUNT_SW_TASK_CLOCK		= 1,
+	PERF_COUNT_SW_PAGE_FAULTS		= 2,
+	PERF_COUNT_SW_CONTEXT_SWITCHES		= 3,
+	PERF_COUNT_SW_CPU_MIGRATIONS		= 4,
+	PERF_COUNT_SW_PAGE_FAULTS_MIN		= 5,
+	PERF_COUNT_SW_PAGE_FAULTS_MAJ		= 6,
+	PERF_COUNT_SW_ALIGNMENT_FAULTS		= 7,
+	PERF_COUNT_SW_EMULATION_FAULTS		= 8,
+	PERF_COUNT_SW_DUMMY			= 9,
+	PERF_COUNT_SW_BPF_OUTPUT		= 10,
+
+	PERF_COUNT_SW_MAX,			/* non-ABI */
+};
+
+/*
+ * Bits that can be set in attr.sample_type to request information
+ * in the overflow packets.
+ */
+enum perf_event_sample_format {
+	PERF_SAMPLE_IP				= 1U << 0,
+	PERF_SAMPLE_TID				= 1U << 1,
+	PERF_SAMPLE_TIME			= 1U << 2,
+	PERF_SAMPLE_ADDR			= 1U << 3,
+	PERF_SAMPLE_READ			= 1U << 4,
+	PERF_SAMPLE_CALLCHAIN			= 1U << 5,
+	PERF_SAMPLE_ID				= 1U << 6,
+	PERF_SAMPLE_CPU				= 1U << 7,
+	PERF_SAMPLE_PERIOD			= 1U << 8,
+	PERF_SAMPLE_STREAM_ID			= 1U << 9,
+	PERF_SAMPLE_RAW				= 1U << 10,
+	PERF_SAMPLE_BRANCH_STACK		= 1U << 11,
+	PERF_SAMPLE_REGS_USER			= 1U << 12,
+	PERF_SAMPLE_STACK_USER			= 1U << 13,
+	PERF_SAMPLE_WEIGHT			= 1U << 14,
+	PERF_SAMPLE_DATA_SRC			= 1U << 15,
+	PERF_SAMPLE_IDENTIFIER			= 1U << 16,
+	PERF_SAMPLE_TRANSACTION			= 1U << 17,
+	PERF_SAMPLE_REGS_INTR			= 1U << 18,
+
+	PERF_SAMPLE_MAX = 1U << 19,		/* non-ABI */
+};
+
+/*
+ * values to program into branch_sample_type when PERF_SAMPLE_BRANCH is set
+ *
+ * If the user does not pass priv level information via branch_sample_type,
+ * the kernel uses the event's priv level. Branch and event priv levels do
+ * not have to match. Branch priv level is checked for permissions.
+ *
+ * The branch types can be combined, however BRANCH_ANY covers all types
+ * of branches and therefore it supersedes all the other types.
+ */
+enum perf_branch_sample_type_shift {
+	PERF_SAMPLE_BRANCH_USER_SHIFT		= 0, /* user branches */
+	PERF_SAMPLE_BRANCH_KERNEL_SHIFT		= 1, /* kernel branches */
+	PERF_SAMPLE_BRANCH_HV_SHIFT		= 2, /* hypervisor branches */
+
+	PERF_SAMPLE_BRANCH_ANY_SHIFT		= 3, /* any branch types */
+	PERF_SAMPLE_BRANCH_ANY_CALL_SHIFT	= 4, /* any call branch */
+	PERF_SAMPLE_BRANCH_ANY_RETURN_SHIFT	= 5, /* any return branch */
+	PERF_SAMPLE_BRANCH_IND_CALL_SHIFT	= 6, /* indirect calls */
+	PERF_SAMPLE_BRANCH_ABORT_TX_SHIFT	= 7, /* transaction aborts */
+	PERF_SAMPLE_BRANCH_IN_TX_SHIFT		= 8, /* in transaction */
+	PERF_SAMPLE_BRANCH_NO_TX_SHIFT		= 9, /* not in transaction */
+	PERF_SAMPLE_BRANCH_COND_SHIFT		= 10, /* conditional branches */
+
+	PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT	= 11, /* call/ret stack */
+	PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT	= 12, /* indirect jumps */
+	PERF_SAMPLE_BRANCH_CALL_SHIFT		= 13, /* direct call */
+
+	PERF_SAMPLE_BRANCH_NO_FLAGS_SHIFT	= 14, /* no flags */
+	PERF_SAMPLE_BRANCH_NO_CYCLES_SHIFT	= 15, /* no cycles */
+
+	PERF_SAMPLE_BRANCH_MAX_SHIFT		/* non-ABI */
+};
+
+enum perf_branch_sample_type {
+	PERF_SAMPLE_BRANCH_USER		= 1U << PERF_SAMPLE_BRANCH_USER_SHIFT,
+	PERF_SAMPLE_BRANCH_KERNEL	= 1U << PERF_SAMPLE_BRANCH_KERNEL_SHIFT,
+	PERF_SAMPLE_BRANCH_HV		= 1U << PERF_SAMPLE_BRANCH_HV_SHIFT,
+
+	PERF_SAMPLE_BRANCH_ANY		= 1U << PERF_SAMPLE_BRANCH_ANY_SHIFT,
+	PERF_SAMPLE_BRANCH_ANY_CALL	= 1U << PERF_SAMPLE_BRANCH_ANY_CALL_SHIFT,
+	PERF_SAMPLE_BRANCH_ANY_RETURN	= 1U << PERF_SAMPLE_BRANCH_ANY_RETURN_SHIFT,
+	PERF_SAMPLE_BRANCH_IND_CALL	= 1U << PERF_SAMPLE_BRANCH_IND_CALL_SHIFT,
+	PERF_SAMPLE_BRANCH_ABORT_TX	= 1U << PERF_SAMPLE_BRANCH_ABORT_TX_SHIFT,
+	PERF_SAMPLE_BRANCH_IN_TX	= 1U << PERF_SAMPLE_BRANCH_IN_TX_SHIFT,
+	PERF_SAMPLE_BRANCH_NO_TX	= 1U << PERF_SAMPLE_BRANCH_NO_TX_SHIFT,
+	PERF_SAMPLE_BRANCH_COND		= 1U << PERF_SAMPLE_BRANCH_COND_SHIFT,
+
+	PERF_SAMPLE_BRANCH_CALL_STACK	= 1U << PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT,
+	PERF_SAMPLE_BRANCH_IND_JUMP	= 1U << PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT,
+	PERF_SAMPLE_BRANCH_CALL		= 1U << PERF_SAMPLE_BRANCH_CALL_SHIFT,
+
+	PERF_SAMPLE_BRANCH_NO_FLAGS	= 1U << PERF_SAMPLE_BRANCH_NO_FLAGS_SHIFT,
+	PERF_SAMPLE_BRANCH_NO_CYCLES	= 1U << PERF_SAMPLE_BRANCH_NO_CYCLES_SHIFT,
+
+	PERF_SAMPLE_BRANCH_MAX		= 1U << PERF_SAMPLE_BRANCH_MAX_SHIFT,
+};
+
+#define PERF_SAMPLE_BRANCH_PLM_ALL \
+	(PERF_SAMPLE_BRANCH_USER|\
+	 PERF_SAMPLE_BRANCH_KERNEL|\
+	 PERF_SAMPLE_BRANCH_HV)
+
+/*
+ * Values to determine ABI of the registers dump.
+ */
+enum perf_sample_regs_abi {
+	PERF_SAMPLE_REGS_ABI_NONE	= 0,
+	PERF_SAMPLE_REGS_ABI_32		= 1,
+	PERF_SAMPLE_REGS_ABI_64		= 2,
+};
+
+/*
+ * Values for the memory transaction event qualifier, mostly for
+ * abort events. Multiple bits can be set.
+ */
+enum {
+	PERF_TXN_ELISION        = (1 << 0), /* From elision */
+	PERF_TXN_TRANSACTION    = (1 << 1), /* From transaction */
+	PERF_TXN_SYNC           = (1 << 2), /* Instruction is related */
+	PERF_TXN_ASYNC          = (1 << 3), /* Instruction not related */
+	PERF_TXN_RETRY          = (1 << 4), /* Retry possible */
+	PERF_TXN_CONFLICT       = (1 << 5), /* Conflict abort */
+	PERF_TXN_CAPACITY_WRITE = (1 << 6), /* Capacity write abort */
+	PERF_TXN_CAPACITY_READ  = (1 << 7), /* Capacity read abort */
+
+	PERF_TXN_MAX	        = (1 << 8), /* non-ABI */
+
+	/* bits 32..63 are reserved for the abort code */
+
+	PERF_TXN_ABORT_MASK  = (0xffffffffULL << 32),
+	PERF_TXN_ABORT_SHIFT = 32,
+};
+
+/*
+ * The format of the data returned by read() on a perf event fd,
+ * as specified by attr.read_format:
+ *
+ * struct read_format {
+ *	{ u64		value;
+ *	  { u64		time_enabled; } && PERF_FORMAT_TOTAL_TIME_ENABLED
+ *	  { u64		time_running; } && PERF_FORMAT_TOTAL_TIME_RUNNING
+ *	  { u64		id;           } && PERF_FORMAT_ID
+ *	} && !PERF_FORMAT_GROUP
+ *
+ *	{ u64		nr;
+ *	  { u64		time_enabled; } && PERF_FORMAT_TOTAL_TIME_ENABLED
+ *	  { u64		time_running; } && PERF_FORMAT_TOTAL_TIME_RUNNING
+ *	  { u64		value;
+ *	    { u64	id;           } && PERF_FORMAT_ID
+ *	  }		cntr[nr];
+ *	} && PERF_FORMAT_GROUP
+ * };
+ */
+enum perf_event_read_format {
+	PERF_FORMAT_TOTAL_TIME_ENABLED		= 1U << 0,
+	PERF_FORMAT_TOTAL_TIME_RUNNING		= 1U << 1,
+	PERF_FORMAT_ID				= 1U << 2,
+	PERF_FORMAT_GROUP			= 1U << 3,
+
+	PERF_FORMAT_MAX = 1U << 4,		/* non-ABI */
+};
+
+#define PERF_ATTR_SIZE_VER0	64	/* sizeof first published struct */
+#define PERF_ATTR_SIZE_VER1	72	/* add: config2 */
+#define PERF_ATTR_SIZE_VER2	80	/* add: branch_sample_type */
+#define PERF_ATTR_SIZE_VER3	96	/* add: sample_regs_user */
+					/* add: sample_stack_user */
+#define PERF_ATTR_SIZE_VER4	104	/* add: sample_regs_intr */
+#define PERF_ATTR_SIZE_VER5	112	/* add: aux_watermark */
+
+/*
+ * Hardware event_id to monitor via a performance monitoring event:
+ *
+ * @sample_max_stack: Max number of frame pointers in a callchain,
+ *		      should be < /proc/sys/kernel/perf_event_max_stack
+ */
+struct perf_event_attr {
+
+	/*
+	 * Major type: hardware/software/tracepoint/etc.
+	 */
+	__u32			type;
+
+	/*
+	 * Size of the attr structure, for fwd/bwd compat.
+	 */
+	__u32			size;
+
+	/*
+	 * Type specific configuration information.
+	 */
+	__u64			config;
+
+	union {
+		__u64		sample_period;
+		__u64		sample_freq;
+	};
+
+	__u64			sample_type;
+	__u64			read_format;
+
+	__u64			disabled       :  1, /* off by default        */
+				inherit	       :  1, /* children inherit it   */
+				pinned	       :  1, /* must always be on PMU */
+				exclusive      :  1, /* only group on PMU     */
+				exclude_user   :  1, /* don't count user      */
+				exclude_kernel :  1, /* ditto kernel          */
+				exclude_hv     :  1, /* ditto hypervisor      */
+				exclude_idle   :  1, /* don't count when idle */
+				mmap           :  1, /* include mmap data     */
+				comm	       :  1, /* include comm data     */
+				freq           :  1, /* use freq, not period  */
+				inherit_stat   :  1, /* per task counts       */
+				enable_on_exec :  1, /* next exec enables     */
+				task           :  1, /* trace fork/exit       */
+				watermark      :  1, /* wakeup_watermark      */
+				/*
+				 * precise_ip:
+				 *
+				 *  0 - SAMPLE_IP can have arbitrary skid
+				 *  1 - SAMPLE_IP must have constant skid
+				 *  2 - SAMPLE_IP requested to have 0 skid
+				 *  3 - SAMPLE_IP must have 0 skid
+				 *
+				 *  See also PERF_RECORD_MISC_EXACT_IP
+				 */
+				precise_ip     :  2, /* skid constraint       */
+				mmap_data      :  1, /* non-exec mmap data    */
+				sample_id_all  :  1, /* sample_type all events */
+
+				exclude_host   :  1, /* don't count in host   */
+				exclude_guest  :  1, /* don't count in guest  */
+
+				exclude_callchain_kernel : 1, /* exclude kernel callchains */
+				exclude_callchain_user   : 1, /* exclude user callchains */
+				mmap2          :  1, /* include mmap with inode data     */
+				comm_exec      :  1, /* flag comm events that are due to an exec */
+				use_clockid    :  1, /* use @clockid for time fields */
+				context_switch :  1, /* context switch data */
+				write_backward :  1, /* Write ring buffer from end to beginning */
+				__reserved_1   : 36;
+
+	union {
+		__u32		wakeup_events;	  /* wakeup every n events */
+		__u32		wakeup_watermark; /* bytes before wakeup   */
+	};
+
+	__u32			bp_type;
+	union {
+		__u64		bp_addr;
+		__u64		config1; /* extension of config */
+	};
+	union {
+		__u64		bp_len;
+		__u64		config2; /* extension of config1 */
+	};
+	__u64	branch_sample_type; /* enum perf_branch_sample_type */
+
+	/*
+	 * Defines set of user regs to dump on samples.
+	 * See asm/perf_regs.h for details.
+	 */
+	__u64	sample_regs_user;
+
+	/*
+	 * Defines size of the user stack to dump on samples.
+	 */
+	__u32	sample_stack_user;
+
+	__s32	clockid;
+	/*
+	 * Defines set of regs to dump for each sample
+	 * state captured on:
+	 *  - precise = 0: PMU interrupt
+	 *  - precise > 0: sampled instruction
+	 *
+	 * See asm/perf_regs.h for details.
+	 */
+	__u64	sample_regs_intr;
+
+	/*
+	 * Wakeup watermark for AUX area
+	 */
+	__u32	aux_watermark;
+	__u16	sample_max_stack;
+	__u16	__reserved_2;	/* align to __u64 */
+};
+
+#define perf_flags(attr)	(*(&(attr)->read_format + 1))
+
+/*
+ * Ioctls that can be done on a perf event fd:
+ */
+#define PERF_EVENT_IOC_ENABLE		_IO ('$', 0)
+#define PERF_EVENT_IOC_DISABLE		_IO ('$', 1)
+#define PERF_EVENT_IOC_REFRESH		_IO ('$', 2)
+#define PERF_EVENT_IOC_RESET		_IO ('$', 3)
+#define PERF_EVENT_IOC_PERIOD		_IOW('$', 4, __u64)
+#define PERF_EVENT_IOC_SET_OUTPUT	_IO ('$', 5)
+#define PERF_EVENT_IOC_SET_FILTER	_IOW('$', 6, char *)
+#define PERF_EVENT_IOC_ID		_IOR('$', 7, __u64 *)
+#define PERF_EVENT_IOC_SET_BPF		_IOW('$', 8, __u32)
+#define PERF_EVENT_IOC_PAUSE_OUTPUT	_IOW('$', 9, __u32)
+
+enum perf_event_ioc_flags {
+	PERF_IOC_FLAG_GROUP		= 1U << 0,
+};
+
+/*
+ * Structure of the page that can be mapped via mmap
+ */
+struct perf_event_mmap_page {
+	__u32	version;		/* version number of this structure */
+	__u32	compat_version;		/* lowest version this is compat with */
+
+	/*
+	 * Bits needed to read the hw events in user-space.
+	 *
+	 *   u32 seq, time_mult, time_shift, index, width;
+	 *   u64 count, enabled, running;
+	 *   u64 cyc, time_offset;
+	 *   s64 pmc = 0;
+	 *
+	 *   do {
+	 *     seq = pc->lock;
+	 *     barrier()
+	 *
+	 *     enabled = pc->time_enabled;
+	 *     running = pc->time_running;
+	 *
+	 *     if (pc->cap_usr_time && enabled != running) {
+	 *       cyc = rdtsc();
+	 *       time_offset = pc->time_offset;
+	 *       time_mult   = pc->time_mult;
+	 *       time_shift  = pc->time_shift;
+	 *     }
+	 *
+	 *     index = pc->index;
+	 *     count = pc->offset;
+	 *     if (pc->cap_user_rdpmc && index) {
+	 *       width = pc->pmc_width;
+	 *       pmc = rdpmc(index - 1);
+	 *     }
+	 *
+	 *     barrier();
+	 *   } while (pc->lock != seq);
+	 *
+	 * NOTE: for obvious reason this only works on self-monitoring
+	 *       processes.
+	 */
+	__u32	lock;			/* seqlock for synchronization */
+	__u32	index;			/* hardware event identifier */
+	__s64	offset;			/* add to hardware event value */
+	__u64	time_enabled;		/* time event active */
+	__u64	time_running;		/* time event on cpu */
+	union {
+		__u64	capabilities;
+		struct {
+			__u64	cap_bit0		: 1, /* Always 0, deprecated, see commit 860f085b74e9 */
+				cap_bit0_is_deprecated	: 1, /* Always 1, signals that bit 0 is zero */
+
+				cap_user_rdpmc		: 1, /* The RDPMC instruction can be used to read counts */
+				cap_user_time		: 1, /* The time_* fields are used */
+				cap_user_time_zero	: 1, /* The time_zero field is used */
+				cap_____res		: 59;
+		};
+	};
+
+	/*
+	 * If cap_user_rdpmc this field provides the bit-width of the value
+	 * read using the rdpmc() or equivalent instruction. This can be used
+	 * to sign extend the result like:
+	 *
+	 *   pmc <<= 64 - width;
+	 *   pmc >>= 64 - width; // signed shift right
+	 *   count += pmc;
+	 */
+	__u16	pmc_width;
+
+	/*
+	 * If cap_usr_time the below fields can be used to compute the time
+	 * delta since time_enabled (in ns) using rdtsc or similar.
+	 *
+	 *   u64 quot, rem;
+	 *   u64 delta;
+	 *
+	 *   quot = (cyc >> time_shift);
+	 *   rem = cyc & (((u64)1 << time_shift) - 1);
+	 *   delta = time_offset + quot * time_mult +
+	 *              ((rem * time_mult) >> time_shift);
+	 *
+	 * Where time_offset,time_mult,time_shift and cyc are read in the
+	 * seqcount loop described above. This delta can then be added to
+	 * enabled and possible running (if index), improving the scaling:
+	 *
+	 *   enabled += delta;
+	 *   if (index)
+	 *     running += delta;
+	 *
+	 *   quot = count / running;
+	 *   rem  = count % running;
+	 *   count = quot * enabled + (rem * enabled) / running;
+	 */
+	__u16	time_shift;
+	__u32	time_mult;
+	__u64	time_offset;
+	/*
+	 * If cap_usr_time_zero, the hardware clock (e.g. TSC) can be calculated
+	 * from sample timestamps.
+	 *
+	 *   time = timestamp - time_zero;
+	 *   quot = time / time_mult;
+	 *   rem  = time % time_mult;
+	 *   cyc = (quot << time_shift) + (rem << time_shift) / time_mult;
+	 *
+	 * And vice versa:
+	 *
+	 *   quot = cyc >> time_shift;
+	 *   rem  = cyc & (((u64)1 << time_shift) - 1);
+	 *   timestamp = time_zero + quot * time_mult +
+	 *               ((rem * time_mult) >> time_shift);
+	 */
+	__u64	time_zero;
+	__u32	size;			/* Header size up to __reserved[] fields. */
+
+		/*
+		 * Hole for extension of the self monitor capabilities
+		 */
+
+	__u8	__reserved[118*8+4];	/* align to 1k. */
+
+	/*
+	 * Control data for the mmap() data buffer.
+	 *
+	 * User-space reading the @data_head value should issue an smp_rmb(),
+	 * after reading this value.
+	 *
+	 * When the mapping is PROT_WRITE the @data_tail value should be
+	 * written by userspace to reflect the last read data, after issueing
+	 * an smp_mb() to separate the data read from the ->data_tail store.
+	 * In this case the kernel will not over-write unread data.
+	 *
+	 * See perf_output_put_handle() for the data ordering.
+	 *
+	 * data_{offset,size} indicate the location and size of the perf record
+	 * buffer within the mmapped area.
+	 */
+	__u64   data_head;		/* head in the data section */
+	__u64	data_tail;		/* user-space written tail */
+	__u64	data_offset;		/* where the buffer starts */
+	__u64	data_size;		/* data buffer size */
+
+	/*
+	 * AUX area is defined by aux_{offset,size} fields that should be set
+	 * by the userspace, so that
+	 *
+	 *   aux_offset >= data_offset + data_size
+	 *
+	 * prior to mmap()ing it. Size of the mmap()ed area should be aux_size.
+	 *
+	 * Ring buffer pointers aux_{head,tail} have the same semantics as
+	 * data_{head,tail} and same ordering rules apply.
+	 */
+	__u64	aux_head;
+	__u64	aux_tail;
+	__u64	aux_offset;
+	__u64	aux_size;
+};
+
+#define PERF_RECORD_MISC_CPUMODE_MASK		(7 << 0)
+#define PERF_RECORD_MISC_CPUMODE_UNKNOWN	(0 << 0)
+#define PERF_RECORD_MISC_KERNEL			(1 << 0)
+#define PERF_RECORD_MISC_USER			(2 << 0)
+#define PERF_RECORD_MISC_HYPERVISOR		(3 << 0)
+#define PERF_RECORD_MISC_GUEST_KERNEL		(4 << 0)
+#define PERF_RECORD_MISC_GUEST_USER		(5 << 0)
+
+/*
+ * Indicates that /proc/PID/maps parsing are truncated by time out.
+ */
+#define PERF_RECORD_MISC_PROC_MAP_PARSE_TIMEOUT	(1 << 12)
+/*
+ * PERF_RECORD_MISC_MMAP_DATA and PERF_RECORD_MISC_COMM_EXEC are used on
+ * different events so can reuse the same bit position.
+ * Ditto PERF_RECORD_MISC_SWITCH_OUT.
+ */
+#define PERF_RECORD_MISC_MMAP_DATA		(1 << 13)
+#define PERF_RECORD_MISC_COMM_EXEC		(1 << 13)
+#define PERF_RECORD_MISC_SWITCH_OUT		(1 << 13)
+/*
+ * Indicates that the content of PERF_SAMPLE_IP points to
+ * the actual instruction that triggered the event. See also
+ * perf_event_attr::precise_ip.
+ */
+#define PERF_RECORD_MISC_EXACT_IP		(1 << 14)
+/*
+ * Reserve the last bit to indicate some extended misc field
+ */
+#define PERF_RECORD_MISC_EXT_RESERVED		(1 << 15)
+
+struct perf_event_header {
+	__u32	type;
+	__u16	misc;
+	__u16	size;
+};
+
+enum perf_event_type {
+
+	/*
+	 * If perf_event_attr.sample_id_all is set then all event types will
+	 * have the sample_type selected fields related to where/when
+	 * (identity) an event took place (TID, TIME, ID, STREAM_ID, CPU,
+	 * IDENTIFIER) described in PERF_RECORD_SAMPLE below, it will be stashed
+	 * just after the perf_event_header and the fields already present for
+	 * the existing fields, i.e. at the end of the payload. That way a newer
+	 * perf.data file will be supported by older perf tools, with these new
+	 * optional fields being ignored.
+	 *
+	 * struct sample_id {
+	 * 	{ u32			pid, tid; } && PERF_SAMPLE_TID
+	 * 	{ u64			time;     } && PERF_SAMPLE_TIME
+	 * 	{ u64			id;       } && PERF_SAMPLE_ID
+	 * 	{ u64			stream_id;} && PERF_SAMPLE_STREAM_ID
+	 * 	{ u32			cpu, res; } && PERF_SAMPLE_CPU
+	 *	{ u64			id;	  } && PERF_SAMPLE_IDENTIFIER
+	 * } && perf_event_attr::sample_id_all
+	 *
+	 * Note that PERF_SAMPLE_IDENTIFIER duplicates PERF_SAMPLE_ID.  The
+	 * advantage of PERF_SAMPLE_IDENTIFIER is that its position is fixed
+	 * relative to header.size.
+	 */
+
+	/*
+	 * The MMAP events record the PROT_EXEC mappings so that we can
+	 * correlate userspace IPs to code. They have the following structure:
+	 *
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *
+	 *	u32				pid, tid;
+	 *	u64				addr;
+	 *	u64				len;
+	 *	u64				pgoff;
+	 *	char				filename[];
+	 * 	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_MMAP			= 1,
+
+	/*
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *	u64				id;
+	 *	u64				lost;
+	 * 	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_LOST			= 2,
+
+	/*
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *
+	 *	u32				pid, tid;
+	 *	char				comm[];
+	 * 	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_COMM			= 3,
+
+	/*
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *	u32				pid, ppid;
+	 *	u32				tid, ptid;
+	 *	u64				time;
+	 * 	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_EXIT			= 4,
+
+	/*
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *	u64				time;
+	 *	u64				id;
+	 *	u64				stream_id;
+	 * 	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_THROTTLE			= 5,
+	PERF_RECORD_UNTHROTTLE			= 6,
+
+	/*
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *	u32				pid, ppid;
+	 *	u32				tid, ptid;
+	 *	u64				time;
+	 * 	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_FORK			= 7,
+
+	/*
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *	u32				pid, tid;
+	 *
+	 *	struct read_format		values;
+	 * 	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_READ			= 8,
+
+	/*
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *
+	 *	#
+	 *	# Note that PERF_SAMPLE_IDENTIFIER duplicates PERF_SAMPLE_ID.
+	 *	# The advantage of PERF_SAMPLE_IDENTIFIER is that its position
+	 *	# is fixed relative to header.
+	 *	#
+	 *
+	 *	{ u64			id;	  } && PERF_SAMPLE_IDENTIFIER
+	 *	{ u64			ip;	  } && PERF_SAMPLE_IP
+	 *	{ u32			pid, tid; } && PERF_SAMPLE_TID
+	 *	{ u64			time;     } && PERF_SAMPLE_TIME
+	 *	{ u64			addr;     } && PERF_SAMPLE_ADDR
+	 *	{ u64			id;	  } && PERF_SAMPLE_ID
+	 *	{ u64			stream_id;} && PERF_SAMPLE_STREAM_ID
+	 *	{ u32			cpu, res; } && PERF_SAMPLE_CPU
+	 *	{ u64			period;   } && PERF_SAMPLE_PERIOD
+	 *
+	 *	{ struct read_format	values;	  } && PERF_SAMPLE_READ
+	 *
+	 *	{ u64			nr,
+	 *	  u64			ips[nr];  } && PERF_SAMPLE_CALLCHAIN
+	 *
+	 *	#
+	 *	# The RAW record below is opaque data wrt the ABI
+	 *	#
+	 *	# That is, the ABI doesn't make any promises wrt to
+	 *	# the stability of its content, it may vary depending
+	 *	# on event, hardware, kernel version and phase of
+	 *	# the moon.
+	 *	#
+	 *	# In other words, PERF_SAMPLE_RAW contents are not an ABI.
+	 *	#
+	 *
+	 *	{ u32			size;
+	 *	  char                  data[size];}&& PERF_SAMPLE_RAW
+	 *
+	 *	{ u64                   nr;
+	 *        { u64 from, to, flags } lbr[nr];} && PERF_SAMPLE_BRANCH_STACK
+	 *
+	 * 	{ u64			abi; # enum perf_sample_regs_abi
+	 * 	  u64			regs[weight(mask)]; } && PERF_SAMPLE_REGS_USER
+	 *
+	 * 	{ u64			size;
+	 * 	  char			data[size];
+	 * 	  u64			dyn_size; } && PERF_SAMPLE_STACK_USER
+	 *
+	 *	{ u64			weight;   } && PERF_SAMPLE_WEIGHT
+	 *	{ u64			data_src; } && PERF_SAMPLE_DATA_SRC
+	 *	{ u64			transaction; } && PERF_SAMPLE_TRANSACTION
+	 *	{ u64			abi; # enum perf_sample_regs_abi
+	 *	  u64			regs[weight(mask)]; } && PERF_SAMPLE_REGS_INTR
+	 * };
+	 */
+	PERF_RECORD_SAMPLE			= 9,
+
+	/*
+	 * The MMAP2 records are an augmented version of MMAP, they add
+	 * maj, min, ino numbers to be used to uniquely identify each mapping
+	 *
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *
+	 *	u32				pid, tid;
+	 *	u64				addr;
+	 *	u64				len;
+	 *	u64				pgoff;
+	 *	u32				maj;
+	 *	u32				min;
+	 *	u64				ino;
+	 *	u64				ino_generation;
+	 *	u32				prot, flags;
+	 *	char				filename[];
+	 * 	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_MMAP2			= 10,
+
+	/*
+	 * Records that new data landed in the AUX buffer part.
+	 *
+	 * struct {
+	 * 	struct perf_event_header	header;
+	 *
+	 * 	u64				aux_offset;
+	 * 	u64				aux_size;
+	 *	u64				flags;
+	 * 	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_AUX				= 11,
+
+	/*
+	 * Indicates that instruction trace has started
+	 *
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *	u32				pid;
+	 *	u32				tid;
+	 * };
+	 */
+	PERF_RECORD_ITRACE_START		= 12,
+
+	/*
+	 * Records the dropped/lost sample number.
+	 *
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *
+	 *	u64				lost;
+	 *	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_LOST_SAMPLES		= 13,
+
+	/*
+	 * Records a context switch in or out (flagged by
+	 * PERF_RECORD_MISC_SWITCH_OUT). See also
+	 * PERF_RECORD_SWITCH_CPU_WIDE.
+	 *
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_SWITCH			= 14,
+
+	/*
+	 * CPU-wide version of PERF_RECORD_SWITCH with next_prev_pid and
+	 * next_prev_tid that are the next (switching out) or previous
+	 * (switching in) pid/tid.
+	 *
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *	u32				next_prev_pid;
+	 *	u32				next_prev_tid;
+	 *	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_SWITCH_CPU_WIDE		= 15,
+
+	PERF_RECORD_MAX,			/* non-ABI */
+};
+
+#define PERF_MAX_STACK_DEPTH		127
+#define PERF_MAX_CONTEXTS_PER_STACK	  8
+
+enum perf_callchain_context {
+	PERF_CONTEXT_HV			= (__u64)-32,
+	PERF_CONTEXT_KERNEL		= (__u64)-128,
+	PERF_CONTEXT_USER		= (__u64)-512,
+
+	PERF_CONTEXT_GUEST		= (__u64)-2048,
+	PERF_CONTEXT_GUEST_KERNEL	= (__u64)-2176,
+	PERF_CONTEXT_GUEST_USER		= (__u64)-2560,
+
+	PERF_CONTEXT_MAX		= (__u64)-4095,
+};
+
+/**
+ * PERF_RECORD_AUX::flags bits
+ */
+#define PERF_AUX_FLAG_TRUNCATED		0x01	/* record was truncated to fit */
+#define PERF_AUX_FLAG_OVERWRITE		0x02	/* snapshot from overwrite mode */
+
+#define PERF_FLAG_FD_NO_GROUP		(1UL << 0)
+#define PERF_FLAG_FD_OUTPUT		(1UL << 1)
+#define PERF_FLAG_PID_CGROUP		(1UL << 2) /* pid=cgroup id, per-cpu mode only */
+#define PERF_FLAG_FD_CLOEXEC		(1UL << 3) /* O_CLOEXEC */
+
+union perf_mem_data_src {
+	__u64 val;
+	struct {
+		__u64   mem_op:5,	/* type of opcode */
+			mem_lvl:14,	/* memory hierarchy level */
+			mem_snoop:5,	/* snoop mode */
+			mem_lock:2,	/* lock instr */
+			mem_dtlb:7,	/* tlb access */
+			mem_rsvd:31;
+	};
+};
+
+/* type of opcode (load/store/prefetch,code) */
+#define PERF_MEM_OP_NA		0x01 /* not available */
+#define PERF_MEM_OP_LOAD	0x02 /* load instruction */
+#define PERF_MEM_OP_STORE	0x04 /* store instruction */
+#define PERF_MEM_OP_PFETCH	0x08 /* prefetch */
+#define PERF_MEM_OP_EXEC	0x10 /* code (execution) */
+#define PERF_MEM_OP_SHIFT	0
+
+/* memory hierarchy (memory level, hit or miss) */
+#define PERF_MEM_LVL_NA		0x01  /* not available */
+#define PERF_MEM_LVL_HIT	0x02  /* hit level */
+#define PERF_MEM_LVL_MISS	0x04  /* miss level  */
+#define PERF_MEM_LVL_L1		0x08  /* L1 */
+#define PERF_MEM_LVL_LFB	0x10  /* Line Fill Buffer */
+#define PERF_MEM_LVL_L2		0x20  /* L2 */
+#define PERF_MEM_LVL_L3		0x40  /* L3 */
+#define PERF_MEM_LVL_LOC_RAM	0x80  /* Local DRAM */
+#define PERF_MEM_LVL_REM_RAM1	0x100 /* Remote DRAM (1 hop) */
+#define PERF_MEM_LVL_REM_RAM2	0x200 /* Remote DRAM (2 hops) */
+#define PERF_MEM_LVL_REM_CCE1	0x400 /* Remote Cache (1 hop) */
+#define PERF_MEM_LVL_REM_CCE2	0x800 /* Remote Cache (2 hops) */
+#define PERF_MEM_LVL_IO		0x1000 /* I/O memory */
+#define PERF_MEM_LVL_UNC	0x2000 /* Uncached memory */
+#define PERF_MEM_LVL_SHIFT	5
+
+/* snoop mode */
+#define PERF_MEM_SNOOP_NA	0x01 /* not available */
+#define PERF_MEM_SNOOP_NONE	0x02 /* no snoop */
+#define PERF_MEM_SNOOP_HIT	0x04 /* snoop hit */
+#define PERF_MEM_SNOOP_MISS	0x08 /* snoop miss */
+#define PERF_MEM_SNOOP_HITM	0x10 /* snoop hit modified */
+#define PERF_MEM_SNOOP_SHIFT	19
+
+/* locked instruction */
+#define PERF_MEM_LOCK_NA	0x01 /* not available */
+#define PERF_MEM_LOCK_LOCKED	0x02 /* locked transaction */
+#define PERF_MEM_LOCK_SHIFT	24
+
+/* TLB access */
+#define PERF_MEM_TLB_NA		0x01 /* not available */
+#define PERF_MEM_TLB_HIT	0x02 /* hit level */
+#define PERF_MEM_TLB_MISS	0x04 /* miss level */
+#define PERF_MEM_TLB_L1		0x08 /* L1 */
+#define PERF_MEM_TLB_L2		0x10 /* L2 */
+#define PERF_MEM_TLB_WK		0x20 /* Hardware Walker*/
+#define PERF_MEM_TLB_OS		0x40 /* OS fault handler */
+#define PERF_MEM_TLB_SHIFT	26
+
+#define PERF_MEM_S(a, s) \
+	(((__u64)PERF_MEM_##a##_##s) << PERF_MEM_##a##_SHIFT)
+
+/*
+ * single taken branch record layout:
+ *
+ *      from: source instruction (may not always be a branch insn)
+ *        to: branch target
+ *   mispred: branch target was mispredicted
+ * predicted: branch target was predicted
+ *
+ * support for mispred, predicted is optional. In case it
+ * is not supported mispred = predicted = 0.
+ *
+ *     in_tx: running in a hardware transaction
+ *     abort: aborting a hardware transaction
+ *    cycles: cycles from last branch (or 0 if not supported)
+ */
+struct perf_branch_entry {
+	__u64	from;
+	__u64	to;
+	__u64	mispred:1,  /* target mispredicted */
+		predicted:1,/* target predicted */
+		in_tx:1,    /* in transaction */
+		abort:1,    /* transaction abort */
+		cycles:16,  /* cycle count to last branch */
+		reserved:44;
+};
+
+#endif /* _UAPI_LINUX_PERF_EVENT_H */
diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST
index 2bd8c310606cb..0b1ebf3c08f66 100644
--- a/tools/perf/MANIFEST
+++ b/tools/perf/MANIFEST
@@ -54,6 +54,7 @@ tools/include/linux/hash.h
 tools/include/linux/kernel.h
 tools/include/linux/list.h
 tools/include/linux/log2.h
+tools/include/uapi/linux/perf_event.h
 tools/include/linux/poison.h
 tools/include/linux/rbtree.h
 tools/include/linux/rbtree_augmented.h
@@ -66,7 +67,6 @@ include/asm-generic/bitops/const_hweight.h
 include/asm-generic/bitops/fls64.h
 include/asm-generic/bitops/__fls.h
 include/asm-generic/bitops/fls.h
-include/linux/perf_event.h
 include/linux/list.h
 include/linux/hash.h
 include/linux/stringify.h
@@ -79,7 +79,6 @@ arch/*/lib/memset*.S
 arch/*/include/asm/*features.h
 include/linux/poison.h
 include/linux/hw_breakpoint.h
-include/uapi/linux/perf_event.h
 include/uapi/linux/bpf.h
 include/uapi/linux/bpf_common.h
 include/uapi/linux/const.h
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index d0a2cb11296fa..5e5f8cb1dd83d 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -345,6 +345,9 @@ export srctree OUTPUT RM CC LD AR CFLAGS V BISON FLEX AWK
 include $(srctree)/tools/build/Makefile.include
 
 $(PERF_IN): prepare FORCE
+	@(test -f ../../include/uapi/linux/perf_event.h && ( \
+        (diff -B ../include/uapi/linux/perf_event.h ../../include/uapi/linux/perf_event.h >/dev/null) \
+        || echo "Warning: tools/include/uapi/linux/perf_event.h differs from kernel" >&2 )) || true
 	$(Q)$(MAKE) $(build)=perf
 
 $(OUTPUT)perf: $(PERFLIBS) $(PERF_IN) $(LIBTRACEEVENT_DYNAMIC_LIST)
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index 7d2ea691c11ba..bbb22101be2e8 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -206,6 +206,7 @@ endif
 
 CFLAGS += -I$(src-perf)/util/include
 CFLAGS += -I$(src-perf)/arch/$(ARCH)/include
+CFLAGS += -I$(srctree)/tools/include/uapi
 CFLAGS += -I$(srctree)/tools/include/
 CFLAGS += -I$(srctree)/arch/$(ARCH)/include/uapi
 CFLAGS += -I$(srctree)/arch/$(ARCH)/include

From 7d7d1bf1d1dabe435ef50efb051724b8664749cb Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Mon, 11 Jul 2016 12:36:41 -0300
Subject: [PATCH 36/66] perf bench: Copy kernel files needed to build
 mem{cpy,set} x86_64 benchmarks

We can't access kernel files directly from tools/, so copy the required
bits, and make sure that we detect when the original files, in the
kernel, gets modified.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-z7e76274ch5j4nugv048qacb@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/arch/x86/include/asm/cpufeatures.h      | 316 ++++++++++++++++++
 .../arch/x86/include/asm/disabled-features.h  |  60 ++++
 .../arch/x86/include/asm/required-features.h  | 103 ++++++
 tools/arch/x86/lib/memcpy_64.S                | 297 ++++++++++++++++
 tools/arch/x86/lib/memset_64.S                | 138 ++++++++
 .../util => }/include/asm/alternative-asm.h   |   4 +-
 tools/perf/MANIFEST                           |   9 +-
 tools/perf/Makefile.perf                      |  15 +
 tools/perf/bench/mem-memcpy-x86-64-asm.S      |   2 +-
 tools/perf/bench/mem-memset-x86-64-asm.S      |   2 +-
 10 files changed, 939 insertions(+), 7 deletions(-)
 create mode 100644 tools/arch/x86/include/asm/cpufeatures.h
 create mode 100644 tools/arch/x86/include/asm/disabled-features.h
 create mode 100644 tools/arch/x86/include/asm/required-features.h
 create mode 100644 tools/arch/x86/lib/memcpy_64.S
 create mode 100644 tools/arch/x86/lib/memset_64.S
 rename tools/{perf/util => }/include/asm/alternative-asm.h (66%)

diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
new file mode 100644
index 0000000000000..4a413485f9eb8
--- /dev/null
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -0,0 +1,316 @@
+#ifndef _ASM_X86_CPUFEATURES_H
+#define _ASM_X86_CPUFEATURES_H
+
+#ifndef _ASM_X86_REQUIRED_FEATURES_H
+#include <asm/required-features.h>
+#endif
+
+#ifndef _ASM_X86_DISABLED_FEATURES_H
+#include <asm/disabled-features.h>
+#endif
+
+/*
+ * Defines x86 CPU feature bits
+ */
+#define NCAPINTS	18	/* N 32-bit words worth of info */
+#define NBUGINTS	1	/* N 32-bit bug flags */
+
+/*
+ * Note: If the comment begins with a quoted string, that string is used
+ * in /proc/cpuinfo instead of the macro name.  If the string is "",
+ * this feature bit is not displayed in /proc/cpuinfo at all.
+ */
+
+/* Intel-defined CPU features, CPUID level 0x00000001 (edx), word 0 */
+#define X86_FEATURE_FPU		( 0*32+ 0) /* Onboard FPU */
+#define X86_FEATURE_VME		( 0*32+ 1) /* Virtual Mode Extensions */
+#define X86_FEATURE_DE		( 0*32+ 2) /* Debugging Extensions */
+#define X86_FEATURE_PSE		( 0*32+ 3) /* Page Size Extensions */
+#define X86_FEATURE_TSC		( 0*32+ 4) /* Time Stamp Counter */
+#define X86_FEATURE_MSR		( 0*32+ 5) /* Model-Specific Registers */
+#define X86_FEATURE_PAE		( 0*32+ 6) /* Physical Address Extensions */
+#define X86_FEATURE_MCE		( 0*32+ 7) /* Machine Check Exception */
+#define X86_FEATURE_CX8		( 0*32+ 8) /* CMPXCHG8 instruction */
+#define X86_FEATURE_APIC	( 0*32+ 9) /* Onboard APIC */
+#define X86_FEATURE_SEP		( 0*32+11) /* SYSENTER/SYSEXIT */
+#define X86_FEATURE_MTRR	( 0*32+12) /* Memory Type Range Registers */
+#define X86_FEATURE_PGE		( 0*32+13) /* Page Global Enable */
+#define X86_FEATURE_MCA		( 0*32+14) /* Machine Check Architecture */
+#define X86_FEATURE_CMOV	( 0*32+15) /* CMOV instructions */
+					  /* (plus FCMOVcc, FCOMI with FPU) */
+#define X86_FEATURE_PAT		( 0*32+16) /* Page Attribute Table */
+#define X86_FEATURE_PSE36	( 0*32+17) /* 36-bit PSEs */
+#define X86_FEATURE_PN		( 0*32+18) /* Processor serial number */
+#define X86_FEATURE_CLFLUSH	( 0*32+19) /* CLFLUSH instruction */
+#define X86_FEATURE_DS		( 0*32+21) /* "dts" Debug Store */
+#define X86_FEATURE_ACPI	( 0*32+22) /* ACPI via MSR */
+#define X86_FEATURE_MMX		( 0*32+23) /* Multimedia Extensions */
+#define X86_FEATURE_FXSR	( 0*32+24) /* FXSAVE/FXRSTOR, CR4.OSFXSR */
+#define X86_FEATURE_XMM		( 0*32+25) /* "sse" */
+#define X86_FEATURE_XMM2	( 0*32+26) /* "sse2" */
+#define X86_FEATURE_SELFSNOOP	( 0*32+27) /* "ss" CPU self snoop */
+#define X86_FEATURE_HT		( 0*32+28) /* Hyper-Threading */
+#define X86_FEATURE_ACC		( 0*32+29) /* "tm" Automatic clock control */
+#define X86_FEATURE_IA64	( 0*32+30) /* IA-64 processor */
+#define X86_FEATURE_PBE		( 0*32+31) /* Pending Break Enable */
+
+/* AMD-defined CPU features, CPUID level 0x80000001, word 1 */
+/* Don't duplicate feature flags which are redundant with Intel! */
+#define X86_FEATURE_SYSCALL	( 1*32+11) /* SYSCALL/SYSRET */
+#define X86_FEATURE_MP		( 1*32+19) /* MP Capable. */
+#define X86_FEATURE_NX		( 1*32+20) /* Execute Disable */
+#define X86_FEATURE_MMXEXT	( 1*32+22) /* AMD MMX extensions */
+#define X86_FEATURE_FXSR_OPT	( 1*32+25) /* FXSAVE/FXRSTOR optimizations */
+#define X86_FEATURE_GBPAGES	( 1*32+26) /* "pdpe1gb" GB pages */
+#define X86_FEATURE_RDTSCP	( 1*32+27) /* RDTSCP */
+#define X86_FEATURE_LM		( 1*32+29) /* Long Mode (x86-64) */
+#define X86_FEATURE_3DNOWEXT	( 1*32+30) /* AMD 3DNow! extensions */
+#define X86_FEATURE_3DNOW	( 1*32+31) /* 3DNow! */
+
+/* Transmeta-defined CPU features, CPUID level 0x80860001, word 2 */
+#define X86_FEATURE_RECOVERY	( 2*32+ 0) /* CPU in recovery mode */
+#define X86_FEATURE_LONGRUN	( 2*32+ 1) /* Longrun power control */
+#define X86_FEATURE_LRTI	( 2*32+ 3) /* LongRun table interface */
+
+/* Other features, Linux-defined mapping, word 3 */
+/* This range is used for feature bits which conflict or are synthesized */
+#define X86_FEATURE_CXMMX	( 3*32+ 0) /* Cyrix MMX extensions */
+#define X86_FEATURE_K6_MTRR	( 3*32+ 1) /* AMD K6 nonstandard MTRRs */
+#define X86_FEATURE_CYRIX_ARR	( 3*32+ 2) /* Cyrix ARRs (= MTRRs) */
+#define X86_FEATURE_CENTAUR_MCR	( 3*32+ 3) /* Centaur MCRs (= MTRRs) */
+/* cpu types for specific tunings: */
+#define X86_FEATURE_K8		( 3*32+ 4) /* "" Opteron, Athlon64 */
+#define X86_FEATURE_K7		( 3*32+ 5) /* "" Athlon */
+#define X86_FEATURE_P3		( 3*32+ 6) /* "" P3 */
+#define X86_FEATURE_P4		( 3*32+ 7) /* "" P4 */
+#define X86_FEATURE_CONSTANT_TSC ( 3*32+ 8) /* TSC ticks at a constant rate */
+#define X86_FEATURE_UP		( 3*32+ 9) /* smp kernel running on up */
+#define X86_FEATURE_ART		( 3*32+10) /* Platform has always running timer (ART) */
+#define X86_FEATURE_ARCH_PERFMON ( 3*32+11) /* Intel Architectural PerfMon */
+#define X86_FEATURE_PEBS	( 3*32+12) /* Precise-Event Based Sampling */
+#define X86_FEATURE_BTS		( 3*32+13) /* Branch Trace Store */
+#define X86_FEATURE_SYSCALL32	( 3*32+14) /* "" syscall in ia32 userspace */
+#define X86_FEATURE_SYSENTER32	( 3*32+15) /* "" sysenter in ia32 userspace */
+#define X86_FEATURE_REP_GOOD	( 3*32+16) /* rep microcode works well */
+#define X86_FEATURE_MFENCE_RDTSC ( 3*32+17) /* "" Mfence synchronizes RDTSC */
+#define X86_FEATURE_LFENCE_RDTSC ( 3*32+18) /* "" Lfence synchronizes RDTSC */
+#define X86_FEATURE_ACC_POWER	( 3*32+19) /* AMD Accumulated Power Mechanism */
+#define X86_FEATURE_NOPL	( 3*32+20) /* The NOPL (0F 1F) instructions */
+#define X86_FEATURE_ALWAYS	( 3*32+21) /* "" Always-present feature */
+#define X86_FEATURE_XTOPOLOGY	( 3*32+22) /* cpu topology enum extensions */
+#define X86_FEATURE_TSC_RELIABLE ( 3*32+23) /* TSC is known to be reliable */
+#define X86_FEATURE_NONSTOP_TSC	( 3*32+24) /* TSC does not stop in C states */
+/* free, was #define X86_FEATURE_CLFLUSH_MONITOR ( 3*32+25) * "" clflush reqd with monitor */
+#define X86_FEATURE_EXTD_APICID	( 3*32+26) /* has extended APICID (8 bits) */
+#define X86_FEATURE_AMD_DCM     ( 3*32+27) /* multi-node processor */
+#define X86_FEATURE_APERFMPERF	( 3*32+28) /* APERFMPERF */
+#define X86_FEATURE_EAGER_FPU	( 3*32+29) /* "eagerfpu" Non lazy FPU restore */
+#define X86_FEATURE_NONSTOP_TSC_S3 ( 3*32+30) /* TSC doesn't stop in S3 state */
+#define X86_FEATURE_MCE_RECOVERY ( 3*32+31) /* cpu has recoverable machine checks */
+
+/* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */
+#define X86_FEATURE_XMM3	( 4*32+ 0) /* "pni" SSE-3 */
+#define X86_FEATURE_PCLMULQDQ	( 4*32+ 1) /* PCLMULQDQ instruction */
+#define X86_FEATURE_DTES64	( 4*32+ 2) /* 64-bit Debug Store */
+#define X86_FEATURE_MWAIT	( 4*32+ 3) /* "monitor" Monitor/Mwait support */
+#define X86_FEATURE_DSCPL	( 4*32+ 4) /* "ds_cpl" CPL Qual. Debug Store */
+#define X86_FEATURE_VMX		( 4*32+ 5) /* Hardware virtualization */
+#define X86_FEATURE_SMX		( 4*32+ 6) /* Safer mode */
+#define X86_FEATURE_EST		( 4*32+ 7) /* Enhanced SpeedStep */
+#define X86_FEATURE_TM2		( 4*32+ 8) /* Thermal Monitor 2 */
+#define X86_FEATURE_SSSE3	( 4*32+ 9) /* Supplemental SSE-3 */
+#define X86_FEATURE_CID		( 4*32+10) /* Context ID */
+#define X86_FEATURE_SDBG	( 4*32+11) /* Silicon Debug */
+#define X86_FEATURE_FMA		( 4*32+12) /* Fused multiply-add */
+#define X86_FEATURE_CX16	( 4*32+13) /* CMPXCHG16B */
+#define X86_FEATURE_XTPR	( 4*32+14) /* Send Task Priority Messages */
+#define X86_FEATURE_PDCM	( 4*32+15) /* Performance Capabilities */
+#define X86_FEATURE_PCID	( 4*32+17) /* Process Context Identifiers */
+#define X86_FEATURE_DCA		( 4*32+18) /* Direct Cache Access */
+#define X86_FEATURE_XMM4_1	( 4*32+19) /* "sse4_1" SSE-4.1 */
+#define X86_FEATURE_XMM4_2	( 4*32+20) /* "sse4_2" SSE-4.2 */
+#define X86_FEATURE_X2APIC	( 4*32+21) /* x2APIC */
+#define X86_FEATURE_MOVBE	( 4*32+22) /* MOVBE instruction */
+#define X86_FEATURE_POPCNT      ( 4*32+23) /* POPCNT instruction */
+#define X86_FEATURE_TSC_DEADLINE_TIMER	( 4*32+24) /* Tsc deadline timer */
+#define X86_FEATURE_AES		( 4*32+25) /* AES instructions */
+#define X86_FEATURE_XSAVE	( 4*32+26) /* XSAVE/XRSTOR/XSETBV/XGETBV */
+#define X86_FEATURE_OSXSAVE	( 4*32+27) /* "" XSAVE enabled in the OS */
+#define X86_FEATURE_AVX		( 4*32+28) /* Advanced Vector Extensions */
+#define X86_FEATURE_F16C	( 4*32+29) /* 16-bit fp conversions */
+#define X86_FEATURE_RDRAND	( 4*32+30) /* The RDRAND instruction */
+#define X86_FEATURE_HYPERVISOR	( 4*32+31) /* Running on a hypervisor */
+
+/* VIA/Cyrix/Centaur-defined CPU features, CPUID level 0xC0000001, word 5 */
+#define X86_FEATURE_XSTORE	( 5*32+ 2) /* "rng" RNG present (xstore) */
+#define X86_FEATURE_XSTORE_EN	( 5*32+ 3) /* "rng_en" RNG enabled */
+#define X86_FEATURE_XCRYPT	( 5*32+ 6) /* "ace" on-CPU crypto (xcrypt) */
+#define X86_FEATURE_XCRYPT_EN	( 5*32+ 7) /* "ace_en" on-CPU crypto enabled */
+#define X86_FEATURE_ACE2	( 5*32+ 8) /* Advanced Cryptography Engine v2 */
+#define X86_FEATURE_ACE2_EN	( 5*32+ 9) /* ACE v2 enabled */
+#define X86_FEATURE_PHE		( 5*32+10) /* PadLock Hash Engine */
+#define X86_FEATURE_PHE_EN	( 5*32+11) /* PHE enabled */
+#define X86_FEATURE_PMM		( 5*32+12) /* PadLock Montgomery Multiplier */
+#define X86_FEATURE_PMM_EN	( 5*32+13) /* PMM enabled */
+
+/* More extended AMD flags: CPUID level 0x80000001, ecx, word 6 */
+#define X86_FEATURE_LAHF_LM	( 6*32+ 0) /* LAHF/SAHF in long mode */
+#define X86_FEATURE_CMP_LEGACY	( 6*32+ 1) /* If yes HyperThreading not valid */
+#define X86_FEATURE_SVM		( 6*32+ 2) /* Secure virtual machine */
+#define X86_FEATURE_EXTAPIC	( 6*32+ 3) /* Extended APIC space */
+#define X86_FEATURE_CR8_LEGACY	( 6*32+ 4) /* CR8 in 32-bit mode */
+#define X86_FEATURE_ABM		( 6*32+ 5) /* Advanced bit manipulation */
+#define X86_FEATURE_SSE4A	( 6*32+ 6) /* SSE-4A */
+#define X86_FEATURE_MISALIGNSSE ( 6*32+ 7) /* Misaligned SSE mode */
+#define X86_FEATURE_3DNOWPREFETCH ( 6*32+ 8) /* 3DNow prefetch instructions */
+#define X86_FEATURE_OSVW	( 6*32+ 9) /* OS Visible Workaround */
+#define X86_FEATURE_IBS		( 6*32+10) /* Instruction Based Sampling */
+#define X86_FEATURE_XOP		( 6*32+11) /* extended AVX instructions */
+#define X86_FEATURE_SKINIT	( 6*32+12) /* SKINIT/STGI instructions */
+#define X86_FEATURE_WDT		( 6*32+13) /* Watchdog timer */
+#define X86_FEATURE_LWP		( 6*32+15) /* Light Weight Profiling */
+#define X86_FEATURE_FMA4	( 6*32+16) /* 4 operands MAC instructions */
+#define X86_FEATURE_TCE		( 6*32+17) /* translation cache extension */
+#define X86_FEATURE_NODEID_MSR	( 6*32+19) /* NodeId MSR */
+#define X86_FEATURE_TBM		( 6*32+21) /* trailing bit manipulations */
+#define X86_FEATURE_TOPOEXT	( 6*32+22) /* topology extensions CPUID leafs */
+#define X86_FEATURE_PERFCTR_CORE ( 6*32+23) /* core performance counter extensions */
+#define X86_FEATURE_PERFCTR_NB  ( 6*32+24) /* NB performance counter extensions */
+#define X86_FEATURE_BPEXT	(6*32+26) /* data breakpoint extension */
+#define X86_FEATURE_PTSC	( 6*32+27) /* performance time-stamp counter */
+#define X86_FEATURE_PERFCTR_L2	( 6*32+28) /* L2 performance counter extensions */
+#define X86_FEATURE_MWAITX	( 6*32+29) /* MWAIT extension (MONITORX/MWAITX) */
+
+/*
+ * Auxiliary flags: Linux defined - For features scattered in various
+ * CPUID levels like 0x6, 0xA etc, word 7.
+ *
+ * Reuse free bits when adding new feature flags!
+ */
+
+#define X86_FEATURE_CPB		( 7*32+ 2) /* AMD Core Performance Boost */
+#define X86_FEATURE_EPB		( 7*32+ 3) /* IA32_ENERGY_PERF_BIAS support */
+
+#define X86_FEATURE_HW_PSTATE	( 7*32+ 8) /* AMD HW-PState */
+#define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */
+
+#define X86_FEATURE_INTEL_PT	( 7*32+15) /* Intel Processor Trace */
+
+/* Virtualization flags: Linux defined, word 8 */
+#define X86_FEATURE_TPR_SHADOW  ( 8*32+ 0) /* Intel TPR Shadow */
+#define X86_FEATURE_VNMI        ( 8*32+ 1) /* Intel Virtual NMI */
+#define X86_FEATURE_FLEXPRIORITY ( 8*32+ 2) /* Intel FlexPriority */
+#define X86_FEATURE_EPT         ( 8*32+ 3) /* Intel Extended Page Table */
+#define X86_FEATURE_VPID        ( 8*32+ 4) /* Intel Virtual Processor ID */
+
+#define X86_FEATURE_VMMCALL     ( 8*32+15) /* Prefer vmmcall to vmcall */
+#define X86_FEATURE_XENPV       ( 8*32+16) /* "" Xen paravirtual guest */
+
+
+/* Intel-defined CPU features, CPUID level 0x00000007:0 (ebx), word 9 */
+#define X86_FEATURE_FSGSBASE	( 9*32+ 0) /* {RD/WR}{FS/GS}BASE instructions*/
+#define X86_FEATURE_TSC_ADJUST	( 9*32+ 1) /* TSC adjustment MSR 0x3b */
+#define X86_FEATURE_BMI1	( 9*32+ 3) /* 1st group bit manipulation extensions */
+#define X86_FEATURE_HLE		( 9*32+ 4) /* Hardware Lock Elision */
+#define X86_FEATURE_AVX2	( 9*32+ 5) /* AVX2 instructions */
+#define X86_FEATURE_SMEP	( 9*32+ 7) /* Supervisor Mode Execution Protection */
+#define X86_FEATURE_BMI2	( 9*32+ 8) /* 2nd group bit manipulation extensions */
+#define X86_FEATURE_ERMS	( 9*32+ 9) /* Enhanced REP MOVSB/STOSB */
+#define X86_FEATURE_INVPCID	( 9*32+10) /* Invalidate Processor Context ID */
+#define X86_FEATURE_RTM		( 9*32+11) /* Restricted Transactional Memory */
+#define X86_FEATURE_CQM		( 9*32+12) /* Cache QoS Monitoring */
+#define X86_FEATURE_MPX		( 9*32+14) /* Memory Protection Extension */
+#define X86_FEATURE_AVX512F	( 9*32+16) /* AVX-512 Foundation */
+#define X86_FEATURE_AVX512DQ	( 9*32+17) /* AVX-512 DQ (Double/Quad granular) Instructions */
+#define X86_FEATURE_RDSEED	( 9*32+18) /* The RDSEED instruction */
+#define X86_FEATURE_ADX		( 9*32+19) /* The ADCX and ADOX instructions */
+#define X86_FEATURE_SMAP	( 9*32+20) /* Supervisor Mode Access Prevention */
+#define X86_FEATURE_PCOMMIT	( 9*32+22) /* PCOMMIT instruction */
+#define X86_FEATURE_CLFLUSHOPT	( 9*32+23) /* CLFLUSHOPT instruction */
+#define X86_FEATURE_CLWB	( 9*32+24) /* CLWB instruction */
+#define X86_FEATURE_AVX512PF	( 9*32+26) /* AVX-512 Prefetch */
+#define X86_FEATURE_AVX512ER	( 9*32+27) /* AVX-512 Exponential and Reciprocal */
+#define X86_FEATURE_AVX512CD	( 9*32+28) /* AVX-512 Conflict Detection */
+#define X86_FEATURE_SHA_NI	( 9*32+29) /* SHA1/SHA256 Instruction Extensions */
+#define X86_FEATURE_AVX512BW	( 9*32+30) /* AVX-512 BW (Byte/Word granular) Instructions */
+#define X86_FEATURE_AVX512VL	( 9*32+31) /* AVX-512 VL (128/256 Vector Length) Extensions */
+
+/* Extended state features, CPUID level 0x0000000d:1 (eax), word 10 */
+#define X86_FEATURE_XSAVEOPT	(10*32+ 0) /* XSAVEOPT */
+#define X86_FEATURE_XSAVEC	(10*32+ 1) /* XSAVEC */
+#define X86_FEATURE_XGETBV1	(10*32+ 2) /* XGETBV with ECX = 1 */
+#define X86_FEATURE_XSAVES	(10*32+ 3) /* XSAVES/XRSTORS */
+
+/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:0 (edx), word 11 */
+#define X86_FEATURE_CQM_LLC	(11*32+ 1) /* LLC QoS if 1 */
+
+/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:1 (edx), word 12 */
+#define X86_FEATURE_CQM_OCCUP_LLC (12*32+ 0) /* LLC occupancy monitoring if 1 */
+#define X86_FEATURE_CQM_MBM_TOTAL (12*32+ 1) /* LLC Total MBM monitoring */
+#define X86_FEATURE_CQM_MBM_LOCAL (12*32+ 2) /* LLC Local MBM monitoring */
+
+/* AMD-defined CPU features, CPUID level 0x80000008 (ebx), word 13 */
+#define X86_FEATURE_CLZERO	(13*32+0) /* CLZERO instruction */
+#define X86_FEATURE_IRPERF	(13*32+1) /* Instructions Retired Count */
+
+/* Thermal and Power Management Leaf, CPUID level 0x00000006 (eax), word 14 */
+#define X86_FEATURE_DTHERM	(14*32+ 0) /* Digital Thermal Sensor */
+#define X86_FEATURE_IDA		(14*32+ 1) /* Intel Dynamic Acceleration */
+#define X86_FEATURE_ARAT	(14*32+ 2) /* Always Running APIC Timer */
+#define X86_FEATURE_PLN		(14*32+ 4) /* Intel Power Limit Notification */
+#define X86_FEATURE_PTS		(14*32+ 6) /* Intel Package Thermal Status */
+#define X86_FEATURE_HWP		(14*32+ 7) /* Intel Hardware P-states */
+#define X86_FEATURE_HWP_NOTIFY	(14*32+ 8) /* HWP Notification */
+#define X86_FEATURE_HWP_ACT_WINDOW (14*32+ 9) /* HWP Activity Window */
+#define X86_FEATURE_HWP_EPP	(14*32+10) /* HWP Energy Perf. Preference */
+#define X86_FEATURE_HWP_PKG_REQ (14*32+11) /* HWP Package Level Request */
+
+/* AMD SVM Feature Identification, CPUID level 0x8000000a (edx), word 15 */
+#define X86_FEATURE_NPT		(15*32+ 0) /* Nested Page Table support */
+#define X86_FEATURE_LBRV	(15*32+ 1) /* LBR Virtualization support */
+#define X86_FEATURE_SVML	(15*32+ 2) /* "svm_lock" SVM locking MSR */
+#define X86_FEATURE_NRIPS	(15*32+ 3) /* "nrip_save" SVM next_rip save */
+#define X86_FEATURE_TSCRATEMSR  (15*32+ 4) /* "tsc_scale" TSC scaling support */
+#define X86_FEATURE_VMCBCLEAN   (15*32+ 5) /* "vmcb_clean" VMCB clean bits support */
+#define X86_FEATURE_FLUSHBYASID (15*32+ 6) /* flush-by-ASID support */
+#define X86_FEATURE_DECODEASSISTS (15*32+ 7) /* Decode Assists support */
+#define X86_FEATURE_PAUSEFILTER (15*32+10) /* filtered pause intercept */
+#define X86_FEATURE_PFTHRESHOLD (15*32+12) /* pause filter threshold */
+#define X86_FEATURE_AVIC	(15*32+13) /* Virtual Interrupt Controller */
+
+/* Intel-defined CPU features, CPUID level 0x00000007:0 (ecx), word 16 */
+#define X86_FEATURE_PKU		(16*32+ 3) /* Protection Keys for Userspace */
+#define X86_FEATURE_OSPKE	(16*32+ 4) /* OS Protection Keys Enable */
+
+/* AMD-defined CPU features, CPUID level 0x80000007 (ebx), word 17 */
+#define X86_FEATURE_OVERFLOW_RECOV (17*32+0) /* MCA overflow recovery support */
+#define X86_FEATURE_SUCCOR	(17*32+1) /* Uncorrectable error containment and recovery */
+#define X86_FEATURE_SMCA	(17*32+3) /* Scalable MCA */
+
+/*
+ * BUG word(s)
+ */
+#define X86_BUG(x)		(NCAPINTS*32 + (x))
+
+#define X86_BUG_F00F		X86_BUG(0) /* Intel F00F */
+#define X86_BUG_FDIV		X86_BUG(1) /* FPU FDIV */
+#define X86_BUG_COMA		X86_BUG(2) /* Cyrix 6x86 coma */
+#define X86_BUG_AMD_TLB_MMATCH	X86_BUG(3) /* "tlb_mmatch" AMD Erratum 383 */
+#define X86_BUG_AMD_APIC_C1E	X86_BUG(4) /* "apic_c1e" AMD Erratum 400 */
+#define X86_BUG_11AP		X86_BUG(5) /* Bad local APIC aka 11AP */
+#define X86_BUG_FXSAVE_LEAK	X86_BUG(6) /* FXSAVE leaks FOP/FIP/FOP */
+#define X86_BUG_CLFLUSH_MONITOR	X86_BUG(7) /* AAI65, CLFLUSH required before MONITOR */
+#define X86_BUG_SYSRET_SS_ATTRS	X86_BUG(8) /* SYSRET doesn't fix up SS attrs */
+#define X86_BUG_NULL_SEG	X86_BUG(9) /* Nulling a selector preserves the base */
+#define X86_BUG_SWAPGS_FENCE	X86_BUG(10) /* SWAPGS without input dep on GS */
+
+
+#ifdef CONFIG_X86_32
+/*
+ * 64-bit kernels don't use X86_BUG_ESPFIX.  Make the define conditional
+ * to avoid confusion.
+ */
+#define X86_BUG_ESPFIX		X86_BUG(9) /* "" IRET to 16-bit SS corrupts ESP/RSP high bits */
+#endif
+
+#endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h
new file mode 100644
index 0000000000000..911e9358ceb18
--- /dev/null
+++ b/tools/arch/x86/include/asm/disabled-features.h
@@ -0,0 +1,60 @@
+#ifndef _ASM_X86_DISABLED_FEATURES_H
+#define _ASM_X86_DISABLED_FEATURES_H
+
+/* These features, although they might be available in a CPU
+ * will not be used because the compile options to support
+ * them are not present.
+ *
+ * This code allows them to be checked and disabled at
+ * compile time without an explicit #ifdef.  Use
+ * cpu_feature_enabled().
+ */
+
+#ifdef CONFIG_X86_INTEL_MPX
+# define DISABLE_MPX	0
+#else
+# define DISABLE_MPX	(1<<(X86_FEATURE_MPX & 31))
+#endif
+
+#ifdef CONFIG_X86_64
+# define DISABLE_VME		(1<<(X86_FEATURE_VME & 31))
+# define DISABLE_K6_MTRR	(1<<(X86_FEATURE_K6_MTRR & 31))
+# define DISABLE_CYRIX_ARR	(1<<(X86_FEATURE_CYRIX_ARR & 31))
+# define DISABLE_CENTAUR_MCR	(1<<(X86_FEATURE_CENTAUR_MCR & 31))
+#else
+# define DISABLE_VME		0
+# define DISABLE_K6_MTRR	0
+# define DISABLE_CYRIX_ARR	0
+# define DISABLE_CENTAUR_MCR	0
+#endif /* CONFIG_X86_64 */
+
+#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
+# define DISABLE_PKU		0
+# define DISABLE_OSPKE		0
+#else
+# define DISABLE_PKU		(1<<(X86_FEATURE_PKU & 31))
+# define DISABLE_OSPKE		(1<<(X86_FEATURE_OSPKE & 31))
+#endif /* CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS */
+
+/*
+ * Make sure to add features to the correct mask
+ */
+#define DISABLED_MASK0	(DISABLE_VME)
+#define DISABLED_MASK1	0
+#define DISABLED_MASK2	0
+#define DISABLED_MASK3	(DISABLE_CYRIX_ARR|DISABLE_CENTAUR_MCR|DISABLE_K6_MTRR)
+#define DISABLED_MASK4	0
+#define DISABLED_MASK5	0
+#define DISABLED_MASK6	0
+#define DISABLED_MASK7	0
+#define DISABLED_MASK8	0
+#define DISABLED_MASK9	(DISABLE_MPX)
+#define DISABLED_MASK10	0
+#define DISABLED_MASK11	0
+#define DISABLED_MASK12	0
+#define DISABLED_MASK13	0
+#define DISABLED_MASK14	0
+#define DISABLED_MASK15	0
+#define DISABLED_MASK16	(DISABLE_PKU|DISABLE_OSPKE)
+
+#endif /* _ASM_X86_DISABLED_FEATURES_H */
diff --git a/tools/arch/x86/include/asm/required-features.h b/tools/arch/x86/include/asm/required-features.h
new file mode 100644
index 0000000000000..4916144e3c426
--- /dev/null
+++ b/tools/arch/x86/include/asm/required-features.h
@@ -0,0 +1,103 @@
+#ifndef _ASM_X86_REQUIRED_FEATURES_H
+#define _ASM_X86_REQUIRED_FEATURES_H
+
+/* Define minimum CPUID feature set for kernel These bits are checked
+   really early to actually display a visible error message before the
+   kernel dies.  Make sure to assign features to the proper mask!
+
+   Some requirements that are not in CPUID yet are also in the
+   CONFIG_X86_MINIMUM_CPU_FAMILY which is checked too.
+
+   The real information is in arch/x86/Kconfig.cpu, this just converts
+   the CONFIGs into a bitmask */
+
+#ifndef CONFIG_MATH_EMULATION
+# define NEED_FPU	(1<<(X86_FEATURE_FPU & 31))
+#else
+# define NEED_FPU	0
+#endif
+
+#if defined(CONFIG_X86_PAE) || defined(CONFIG_X86_64)
+# define NEED_PAE	(1<<(X86_FEATURE_PAE & 31))
+#else
+# define NEED_PAE	0
+#endif
+
+#ifdef CONFIG_X86_CMPXCHG64
+# define NEED_CX8	(1<<(X86_FEATURE_CX8 & 31))
+#else
+# define NEED_CX8	0
+#endif
+
+#if defined(CONFIG_X86_CMOV) || defined(CONFIG_X86_64)
+# define NEED_CMOV	(1<<(X86_FEATURE_CMOV & 31))
+#else
+# define NEED_CMOV	0
+#endif
+
+#ifdef CONFIG_X86_USE_3DNOW
+# define NEED_3DNOW	(1<<(X86_FEATURE_3DNOW & 31))
+#else
+# define NEED_3DNOW	0
+#endif
+
+#if defined(CONFIG_X86_P6_NOP) || defined(CONFIG_X86_64)
+# define NEED_NOPL	(1<<(X86_FEATURE_NOPL & 31))
+#else
+# define NEED_NOPL	0
+#endif
+
+#ifdef CONFIG_MATOM
+# define NEED_MOVBE	(1<<(X86_FEATURE_MOVBE & 31))
+#else
+# define NEED_MOVBE	0
+#endif
+
+#ifdef CONFIG_X86_64
+#ifdef CONFIG_PARAVIRT
+/* Paravirtualized systems may not have PSE or PGE available */
+#define NEED_PSE	0
+#define NEED_PGE	0
+#else
+#define NEED_PSE	(1<<(X86_FEATURE_PSE) & 31)
+#define NEED_PGE	(1<<(X86_FEATURE_PGE) & 31)
+#endif
+#define NEED_MSR	(1<<(X86_FEATURE_MSR & 31))
+#define NEED_FXSR	(1<<(X86_FEATURE_FXSR & 31))
+#define NEED_XMM	(1<<(X86_FEATURE_XMM & 31))
+#define NEED_XMM2	(1<<(X86_FEATURE_XMM2 & 31))
+#define NEED_LM		(1<<(X86_FEATURE_LM & 31))
+#else
+#define NEED_PSE	0
+#define NEED_MSR	0
+#define NEED_PGE	0
+#define NEED_FXSR	0
+#define NEED_XMM	0
+#define NEED_XMM2	0
+#define NEED_LM		0
+#endif
+
+#define REQUIRED_MASK0	(NEED_FPU|NEED_PSE|NEED_MSR|NEED_PAE|\
+			 NEED_CX8|NEED_PGE|NEED_FXSR|NEED_CMOV|\
+			 NEED_XMM|NEED_XMM2)
+#define SSE_MASK	(NEED_XMM|NEED_XMM2)
+
+#define REQUIRED_MASK1	(NEED_LM|NEED_3DNOW)
+
+#define REQUIRED_MASK2	0
+#define REQUIRED_MASK3	(NEED_NOPL)
+#define REQUIRED_MASK4	(NEED_MOVBE)
+#define REQUIRED_MASK5	0
+#define REQUIRED_MASK6	0
+#define REQUIRED_MASK7	0
+#define REQUIRED_MASK8	0
+#define REQUIRED_MASK9	0
+#define REQUIRED_MASK10	0
+#define REQUIRED_MASK11	0
+#define REQUIRED_MASK12	0
+#define REQUIRED_MASK13	0
+#define REQUIRED_MASK14	0
+#define REQUIRED_MASK15	0
+#define REQUIRED_MASK16	0
+
+#endif /* _ASM_X86_REQUIRED_FEATURES_H */
diff --git a/tools/arch/x86/lib/memcpy_64.S b/tools/arch/x86/lib/memcpy_64.S
new file mode 100644
index 0000000000000..2ec0b0abbfaa8
--- /dev/null
+++ b/tools/arch/x86/lib/memcpy_64.S
@@ -0,0 +1,297 @@
+/* Copyright 2002 Andi Kleen */
+
+#include <linux/linkage.h>
+#include <asm/errno.h>
+#include <asm/cpufeatures.h>
+#include <asm/alternative-asm.h>
+
+/*
+ * We build a jump to memcpy_orig by default which gets NOPped out on
+ * the majority of x86 CPUs which set REP_GOOD. In addition, CPUs which
+ * have the enhanced REP MOVSB/STOSB feature (ERMS), change those NOPs
+ * to a jmp to memcpy_erms which does the REP; MOVSB mem copy.
+ */
+
+.weak memcpy
+
+/*
+ * memcpy - Copy a memory block.
+ *
+ * Input:
+ *  rdi destination
+ *  rsi source
+ *  rdx count
+ *
+ * Output:
+ * rax original destination
+ */
+ENTRY(__memcpy)
+ENTRY(memcpy)
+	ALTERNATIVE_2 "jmp memcpy_orig", "", X86_FEATURE_REP_GOOD, \
+		      "jmp memcpy_erms", X86_FEATURE_ERMS
+
+	movq %rdi, %rax
+	movq %rdx, %rcx
+	shrq $3, %rcx
+	andl $7, %edx
+	rep movsq
+	movl %edx, %ecx
+	rep movsb
+	ret
+ENDPROC(memcpy)
+ENDPROC(__memcpy)
+
+/*
+ * memcpy_erms() - enhanced fast string memcpy. This is faster and
+ * simpler than memcpy. Use memcpy_erms when possible.
+ */
+ENTRY(memcpy_erms)
+	movq %rdi, %rax
+	movq %rdx, %rcx
+	rep movsb
+	ret
+ENDPROC(memcpy_erms)
+
+ENTRY(memcpy_orig)
+	movq %rdi, %rax
+
+	cmpq $0x20, %rdx
+	jb .Lhandle_tail
+
+	/*
+	 * We check whether memory false dependence could occur,
+	 * then jump to corresponding copy mode.
+	 */
+	cmp  %dil, %sil
+	jl .Lcopy_backward
+	subq $0x20, %rdx
+.Lcopy_forward_loop:
+	subq $0x20,	%rdx
+
+	/*
+	 * Move in blocks of 4x8 bytes:
+	 */
+	movq 0*8(%rsi),	%r8
+	movq 1*8(%rsi),	%r9
+	movq 2*8(%rsi),	%r10
+	movq 3*8(%rsi),	%r11
+	leaq 4*8(%rsi),	%rsi
+
+	movq %r8,	0*8(%rdi)
+	movq %r9,	1*8(%rdi)
+	movq %r10,	2*8(%rdi)
+	movq %r11,	3*8(%rdi)
+	leaq 4*8(%rdi),	%rdi
+	jae  .Lcopy_forward_loop
+	addl $0x20,	%edx
+	jmp  .Lhandle_tail
+
+.Lcopy_backward:
+	/*
+	 * Calculate copy position to tail.
+	 */
+	addq %rdx,	%rsi
+	addq %rdx,	%rdi
+	subq $0x20,	%rdx
+	/*
+	 * At most 3 ALU operations in one cycle,
+	 * so append NOPS in the same 16 bytes trunk.
+	 */
+	.p2align 4
+.Lcopy_backward_loop:
+	subq $0x20,	%rdx
+	movq -1*8(%rsi),	%r8
+	movq -2*8(%rsi),	%r9
+	movq -3*8(%rsi),	%r10
+	movq -4*8(%rsi),	%r11
+	leaq -4*8(%rsi),	%rsi
+	movq %r8,		-1*8(%rdi)
+	movq %r9,		-2*8(%rdi)
+	movq %r10,		-3*8(%rdi)
+	movq %r11,		-4*8(%rdi)
+	leaq -4*8(%rdi),	%rdi
+	jae  .Lcopy_backward_loop
+
+	/*
+	 * Calculate copy position to head.
+	 */
+	addl $0x20,	%edx
+	subq %rdx,	%rsi
+	subq %rdx,	%rdi
+.Lhandle_tail:
+	cmpl $16,	%edx
+	jb   .Lless_16bytes
+
+	/*
+	 * Move data from 16 bytes to 31 bytes.
+	 */
+	movq 0*8(%rsi), %r8
+	movq 1*8(%rsi),	%r9
+	movq -2*8(%rsi, %rdx),	%r10
+	movq -1*8(%rsi, %rdx),	%r11
+	movq %r8,	0*8(%rdi)
+	movq %r9,	1*8(%rdi)
+	movq %r10,	-2*8(%rdi, %rdx)
+	movq %r11,	-1*8(%rdi, %rdx)
+	retq
+	.p2align 4
+.Lless_16bytes:
+	cmpl $8,	%edx
+	jb   .Lless_8bytes
+	/*
+	 * Move data from 8 bytes to 15 bytes.
+	 */
+	movq 0*8(%rsi),	%r8
+	movq -1*8(%rsi, %rdx),	%r9
+	movq %r8,	0*8(%rdi)
+	movq %r9,	-1*8(%rdi, %rdx)
+	retq
+	.p2align 4
+.Lless_8bytes:
+	cmpl $4,	%edx
+	jb   .Lless_3bytes
+
+	/*
+	 * Move data from 4 bytes to 7 bytes.
+	 */
+	movl (%rsi), %ecx
+	movl -4(%rsi, %rdx), %r8d
+	movl %ecx, (%rdi)
+	movl %r8d, -4(%rdi, %rdx)
+	retq
+	.p2align 4
+.Lless_3bytes:
+	subl $1, %edx
+	jb .Lend
+	/*
+	 * Move data from 1 bytes to 3 bytes.
+	 */
+	movzbl (%rsi), %ecx
+	jz .Lstore_1byte
+	movzbq 1(%rsi), %r8
+	movzbq (%rsi, %rdx), %r9
+	movb %r8b, 1(%rdi)
+	movb %r9b, (%rdi, %rdx)
+.Lstore_1byte:
+	movb %cl, (%rdi)
+
+.Lend:
+	retq
+ENDPROC(memcpy_orig)
+
+#ifndef CONFIG_UML
+/*
+ * memcpy_mcsafe - memory copy with machine check exception handling
+ * Note that we only catch machine checks when reading the source addresses.
+ * Writes to target are posted and don't generate machine checks.
+ */
+ENTRY(memcpy_mcsafe)
+	cmpl $8, %edx
+	/* Less than 8 bytes? Go to byte copy loop */
+	jb .L_no_whole_words
+
+	/* Check for bad alignment of source */
+	testl $7, %esi
+	/* Already aligned */
+	jz .L_8byte_aligned
+
+	/* Copy one byte at a time until source is 8-byte aligned */
+	movl %esi, %ecx
+	andl $7, %ecx
+	subl $8, %ecx
+	negl %ecx
+	subl %ecx, %edx
+.L_copy_leading_bytes:
+	movb (%rsi), %al
+	movb %al, (%rdi)
+	incq %rsi
+	incq %rdi
+	decl %ecx
+	jnz .L_copy_leading_bytes
+
+.L_8byte_aligned:
+	/* Figure out how many whole cache lines (64-bytes) to copy */
+	movl %edx, %ecx
+	andl $63, %edx
+	shrl $6, %ecx
+	jz .L_no_whole_cache_lines
+
+	/* Loop copying whole cache lines */
+.L_cache_w0: movq (%rsi), %r8
+.L_cache_w1: movq 1*8(%rsi), %r9
+.L_cache_w2: movq 2*8(%rsi), %r10
+.L_cache_w3: movq 3*8(%rsi), %r11
+	movq %r8, (%rdi)
+	movq %r9, 1*8(%rdi)
+	movq %r10, 2*8(%rdi)
+	movq %r11, 3*8(%rdi)
+.L_cache_w4: movq 4*8(%rsi), %r8
+.L_cache_w5: movq 5*8(%rsi), %r9
+.L_cache_w6: movq 6*8(%rsi), %r10
+.L_cache_w7: movq 7*8(%rsi), %r11
+	movq %r8, 4*8(%rdi)
+	movq %r9, 5*8(%rdi)
+	movq %r10, 6*8(%rdi)
+	movq %r11, 7*8(%rdi)
+	leaq 64(%rsi), %rsi
+	leaq 64(%rdi), %rdi
+	decl %ecx
+	jnz .L_cache_w0
+
+	/* Are there any trailing 8-byte words? */
+.L_no_whole_cache_lines:
+	movl %edx, %ecx
+	andl $7, %edx
+	shrl $3, %ecx
+	jz .L_no_whole_words
+
+	/* Copy trailing words */
+.L_copy_trailing_words:
+	movq (%rsi), %r8
+	mov %r8, (%rdi)
+	leaq 8(%rsi), %rsi
+	leaq 8(%rdi), %rdi
+	decl %ecx
+	jnz .L_copy_trailing_words
+
+	/* Any trailing bytes? */
+.L_no_whole_words:
+	andl %edx, %edx
+	jz .L_done_memcpy_trap
+
+	/* Copy trailing bytes */
+	movl %edx, %ecx
+.L_copy_trailing_bytes:
+	movb (%rsi), %al
+	movb %al, (%rdi)
+	incq %rsi
+	incq %rdi
+	decl %ecx
+	jnz .L_copy_trailing_bytes
+
+	/* Copy successful. Return zero */
+.L_done_memcpy_trap:
+	xorq %rax, %rax
+	ret
+ENDPROC(memcpy_mcsafe)
+
+	.section .fixup, "ax"
+	/* Return -EFAULT for any failure */
+.L_memcpy_mcsafe_fail:
+	mov	$-EFAULT, %rax
+	ret
+
+	.previous
+
+	_ASM_EXTABLE_FAULT(.L_copy_leading_bytes, .L_memcpy_mcsafe_fail)
+	_ASM_EXTABLE_FAULT(.L_cache_w0, .L_memcpy_mcsafe_fail)
+	_ASM_EXTABLE_FAULT(.L_cache_w1, .L_memcpy_mcsafe_fail)
+	_ASM_EXTABLE_FAULT(.L_cache_w3, .L_memcpy_mcsafe_fail)
+	_ASM_EXTABLE_FAULT(.L_cache_w3, .L_memcpy_mcsafe_fail)
+	_ASM_EXTABLE_FAULT(.L_cache_w4, .L_memcpy_mcsafe_fail)
+	_ASM_EXTABLE_FAULT(.L_cache_w5, .L_memcpy_mcsafe_fail)
+	_ASM_EXTABLE_FAULT(.L_cache_w6, .L_memcpy_mcsafe_fail)
+	_ASM_EXTABLE_FAULT(.L_cache_w7, .L_memcpy_mcsafe_fail)
+	_ASM_EXTABLE_FAULT(.L_copy_trailing_words, .L_memcpy_mcsafe_fail)
+	_ASM_EXTABLE_FAULT(.L_copy_trailing_bytes, .L_memcpy_mcsafe_fail)
+#endif
diff --git a/tools/arch/x86/lib/memset_64.S b/tools/arch/x86/lib/memset_64.S
new file mode 100644
index 0000000000000..e1229ecd2a820
--- /dev/null
+++ b/tools/arch/x86/lib/memset_64.S
@@ -0,0 +1,138 @@
+/* Copyright 2002 Andi Kleen, SuSE Labs */
+
+#include <linux/linkage.h>
+#include <asm/cpufeatures.h>
+#include <asm/alternative-asm.h>
+
+.weak memset
+
+/*
+ * ISO C memset - set a memory block to a byte value. This function uses fast
+ * string to get better performance than the original function. The code is
+ * simpler and shorter than the original function as well.
+ *
+ * rdi   destination
+ * rsi   value (char)
+ * rdx   count (bytes)
+ *
+ * rax   original destination
+ */
+ENTRY(memset)
+ENTRY(__memset)
+	/*
+	 * Some CPUs support enhanced REP MOVSB/STOSB feature. It is recommended
+	 * to use it when possible. If not available, use fast string instructions.
+	 *
+	 * Otherwise, use original memset function.
+	 */
+	ALTERNATIVE_2 "jmp memset_orig", "", X86_FEATURE_REP_GOOD, \
+		      "jmp memset_erms", X86_FEATURE_ERMS
+
+	movq %rdi,%r9
+	movq %rdx,%rcx
+	andl $7,%edx
+	shrq $3,%rcx
+	/* expand byte value  */
+	movzbl %sil,%esi
+	movabs $0x0101010101010101,%rax
+	imulq %rsi,%rax
+	rep stosq
+	movl %edx,%ecx
+	rep stosb
+	movq %r9,%rax
+	ret
+ENDPROC(memset)
+ENDPROC(__memset)
+
+/*
+ * ISO C memset - set a memory block to a byte value. This function uses
+ * enhanced rep stosb to override the fast string function.
+ * The code is simpler and shorter than the fast string function as well.
+ *
+ * rdi   destination
+ * rsi   value (char)
+ * rdx   count (bytes)
+ *
+ * rax   original destination
+ */
+ENTRY(memset_erms)
+	movq %rdi,%r9
+	movb %sil,%al
+	movq %rdx,%rcx
+	rep stosb
+	movq %r9,%rax
+	ret
+ENDPROC(memset_erms)
+
+ENTRY(memset_orig)
+	movq %rdi,%r10
+
+	/* expand byte value  */
+	movzbl %sil,%ecx
+	movabs $0x0101010101010101,%rax
+	imulq  %rcx,%rax
+
+	/* align dst */
+	movl  %edi,%r9d
+	andl  $7,%r9d
+	jnz  .Lbad_alignment
+.Lafter_bad_alignment:
+
+	movq  %rdx,%rcx
+	shrq  $6,%rcx
+	jz	 .Lhandle_tail
+
+	.p2align 4
+.Lloop_64:
+	decq  %rcx
+	movq  %rax,(%rdi)
+	movq  %rax,8(%rdi)
+	movq  %rax,16(%rdi)
+	movq  %rax,24(%rdi)
+	movq  %rax,32(%rdi)
+	movq  %rax,40(%rdi)
+	movq  %rax,48(%rdi)
+	movq  %rax,56(%rdi)
+	leaq  64(%rdi),%rdi
+	jnz    .Lloop_64
+
+	/* Handle tail in loops. The loops should be faster than hard
+	   to predict jump tables. */
+	.p2align 4
+.Lhandle_tail:
+	movl	%edx,%ecx
+	andl    $63&(~7),%ecx
+	jz 		.Lhandle_7
+	shrl	$3,%ecx
+	.p2align 4
+.Lloop_8:
+	decl   %ecx
+	movq  %rax,(%rdi)
+	leaq  8(%rdi),%rdi
+	jnz    .Lloop_8
+
+.Lhandle_7:
+	andl	$7,%edx
+	jz      .Lende
+	.p2align 4
+.Lloop_1:
+	decl    %edx
+	movb 	%al,(%rdi)
+	leaq	1(%rdi),%rdi
+	jnz     .Lloop_1
+
+.Lende:
+	movq	%r10,%rax
+	ret
+
+.Lbad_alignment:
+	cmpq $7,%rdx
+	jbe	.Lhandle_7
+	movq %rax,(%rdi)	/* unaligned store */
+	movq $8,%r8
+	subq %r9,%r8
+	addq %r8,%rdi
+	subq %r8,%rdx
+	jmp .Lafter_bad_alignment
+.Lfinal:
+ENDPROC(memset_orig)
diff --git a/tools/perf/util/include/asm/alternative-asm.h b/tools/include/asm/alternative-asm.h
similarity index 66%
rename from tools/perf/util/include/asm/alternative-asm.h
rename to tools/include/asm/alternative-asm.h
index 3a3a0f16456ae..2a4d1bfa29884 100644
--- a/tools/perf/util/include/asm/alternative-asm.h
+++ b/tools/include/asm/alternative-asm.h
@@ -1,5 +1,5 @@
-#ifndef _PERF_ASM_ALTERNATIVE_ASM_H
-#define _PERF_ASM_ALTERNATIVE_ASM_H
+#ifndef _TOOLS_ASM_ALTERNATIVE_ASM_H
+#define _TOOLS_ASM_ALTERNATIVE_ASM_H
 
 /* Just disable it so we can build arch/x86/lib/memcpy_64.S for perf bench: */
 
diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST
index 0b1ebf3c08f66..cf85d1cd1c919 100644
--- a/tools/perf/MANIFEST
+++ b/tools/perf/MANIFEST
@@ -12,6 +12,11 @@ tools/arch/sparc/include/asm/barrier_32.h
 tools/arch/sparc/include/asm/barrier_64.h
 tools/arch/tile/include/asm/barrier.h
 tools/arch/x86/include/asm/barrier.h
+tools/arch/x86/include/asm/cpufeatures.h
+tools/arch/x86/include/asm/disabled-features.h
+tools/arch/x86/include/asm/required-features.h
+tools/arch/x86/lib/memcpy_64.S
+tools/arch/x86/lib/memset_64.S
 tools/arch/xtensa/include/asm/barrier.h
 tools/scripts
 tools/build
@@ -31,6 +36,7 @@ tools/lib/find_bit.c
 tools/lib/bitmap.c
 tools/lib/str_error_r.c
 tools/lib/vsprintf.c
+tools/include/asm/alternative-asm.h
 tools/include/asm/atomic.h
 tools/include/asm/barrier.h
 tools/include/asm/bug.h
@@ -74,9 +80,6 @@ include/linux/swab.h
 arch/*/include/asm/unistd*.h
 arch/*/include/uapi/asm/unistd*.h
 arch/*/include/uapi/asm/perf_regs.h
-arch/*/lib/memcpy*.S
-arch/*/lib/memset*.S
-arch/*/include/asm/*features.h
 include/linux/poison.h
 include/linux/hw_breakpoint.h
 include/uapi/linux/bpf.h
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 5e5f8cb1dd83d..809735c6cb264 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -348,6 +348,21 @@ $(PERF_IN): prepare FORCE
 	@(test -f ../../include/uapi/linux/perf_event.h && ( \
         (diff -B ../include/uapi/linux/perf_event.h ../../include/uapi/linux/perf_event.h >/dev/null) \
         || echo "Warning: tools/include/uapi/linux/perf_event.h differs from kernel" >&2 )) || true
+	@(test -f ../../arch/x86/include/asm/disabled-features.h && ( \
+        (diff -B ../arch/x86/include/asm/disabled-features.h ../../arch/x86/include/asm/disabled-features.h >/dev/null) \
+        || echo "Warning: tools/arch/x86/include/asm/disabled-features.h differs from kernel" >&2 )) || true
+	@(test -f ../../arch/x86/include/asm/required-features.h && ( \
+        (diff -B ../arch/x86/include/asm/required-features.h ../../arch/x86/include/asm/required-features.h >/dev/null) \
+        || echo "Warning: tools/arch/x86/include/asm/required-features.h differs from kernel" >&2 )) || true
+	@(test -f ../../arch/x86/include/asm/cpufeatures.h && ( \
+        (diff -B ../arch/x86/include/asm/cpufeatures.h ../../arch/x86/include/asm/cpufeatures.h >/dev/null) \
+        || echo "Warning: tools/arch/x86/include/asm/cpufeatures.h differs from kernel" >&2 )) || true
+	@(test -f ../../arch/x86/lib/memcpy_64.S && ( \
+        (diff -B ../arch/x86/lib/memcpy_64.S ../../arch/x86/lib/memcpy_64.S >/dev/null) \
+        || echo "Warning: tools/arch/x86/lib/memcpy_64.S differs from kernel" >&2 )) || true
+	@(test -f ../../arch/x86/lib/memset_64.S && ( \
+        (diff -B ../arch/x86/lib/memset_64.S ../../arch/x86/lib/memset_64.S >/dev/null) \
+        || echo "Warning: tools/arch/x86/lib/memset_64.S differs from kernel" >&2 )) || true
 	$(Q)$(MAKE) $(build)=perf
 
 $(OUTPUT)perf: $(PERFLIBS) $(PERF_IN) $(LIBTRACEEVENT_DYNAMIC_LIST)
diff --git a/tools/perf/bench/mem-memcpy-x86-64-asm.S b/tools/perf/bench/mem-memcpy-x86-64-asm.S
index 5c3cce082cb88..f700369bb0f6e 100644
--- a/tools/perf/bench/mem-memcpy-x86-64-asm.S
+++ b/tools/perf/bench/mem-memcpy-x86-64-asm.S
@@ -6,7 +6,7 @@
 #define globl p2align 4; .globl
 #define _ASM_EXTABLE_FAULT(x, y)
 
-#include "../../../arch/x86/lib/memcpy_64.S"
+#include "../../arch/x86/lib/memcpy_64.S"
 /*
  * We need to provide note.GNU-stack section, saying that we want
  * NOT executable stack. Otherwise the final linking will assume that
diff --git a/tools/perf/bench/mem-memset-x86-64-asm.S b/tools/perf/bench/mem-memset-x86-64-asm.S
index de278784c866a..58407aa24c1bf 100644
--- a/tools/perf/bench/mem-memset-x86-64-asm.S
+++ b/tools/perf/bench/mem-memset-x86-64-asm.S
@@ -1,7 +1,7 @@
 #define memset MEMSET /* don't hide glibc's memset() */
 #define altinstr_replacement text
 #define globl p2align 4; .globl
-#include "../../../arch/x86/lib/memset_64.S"
+#include "../../arch/x86/lib/memset_64.S"
 
 /*
  * We need to provide note.GNU-stack section, saying that we want

From 971e827bffef781dd089a402fe602ff20c1f1819 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Mon, 11 Jul 2016 16:38:05 -0300
Subject: [PATCH 37/66] tools lib bpf: Copy bpf.h and bpf_common.h from the
 kernel

To allow the build to complete on older systems, where those files are
either not uptodate, lacking some recent additions or not present at
all.

And check if the copy drifts from the kernel, as in this synthetic test:

    BUILD:   Doing 'make -j4' parallel build
  Warning: tools/include/linux/bpf.h differs from kernel
  Warning: tools/include/linux/bpf_common.h differs from kernel

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-5plvi2gq4x469dcyybiu226q@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/uapi/linux/bpf.h        | 389 ++++++++++++++++++++++++++
 tools/include/uapi/linux/bpf_common.h |  55 ++++
 tools/lib/bpf/Makefile                |   8 +-
 tools/perf/MANIFEST                   |   5 +-
 tools/perf/config/Makefile            |   5 +-
 5 files changed, 456 insertions(+), 6 deletions(-)
 create mode 100644 tools/include/uapi/linux/bpf.h
 create mode 100644 tools/include/uapi/linux/bpf_common.h

diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
new file mode 100644
index 0000000000000..406459b935a27
--- /dev/null
+++ b/tools/include/uapi/linux/bpf.h
@@ -0,0 +1,389 @@
+/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#ifndef _UAPI__LINUX_BPF_H__
+#define _UAPI__LINUX_BPF_H__
+
+#include <linux/types.h>
+#include <linux/bpf_common.h>
+
+/* Extended instruction set based on top of classic BPF */
+
+/* instruction classes */
+#define BPF_ALU64	0x07	/* alu mode in double word width */
+
+/* ld/ldx fields */
+#define BPF_DW		0x18	/* double word */
+#define BPF_XADD	0xc0	/* exclusive add */
+
+/* alu/jmp fields */
+#define BPF_MOV		0xb0	/* mov reg to reg */
+#define BPF_ARSH	0xc0	/* sign extending arithmetic shift right */
+
+/* change endianness of a register */
+#define BPF_END		0xd0	/* flags for endianness conversion: */
+#define BPF_TO_LE	0x00	/* convert to little-endian */
+#define BPF_TO_BE	0x08	/* convert to big-endian */
+#define BPF_FROM_LE	BPF_TO_LE
+#define BPF_FROM_BE	BPF_TO_BE
+
+#define BPF_JNE		0x50	/* jump != */
+#define BPF_JSGT	0x60	/* SGT is signed '>', GT in x86 */
+#define BPF_JSGE	0x70	/* SGE is signed '>=', GE in x86 */
+#define BPF_CALL	0x80	/* function call */
+#define BPF_EXIT	0x90	/* function return */
+
+/* Register numbers */
+enum {
+	BPF_REG_0 = 0,
+	BPF_REG_1,
+	BPF_REG_2,
+	BPF_REG_3,
+	BPF_REG_4,
+	BPF_REG_5,
+	BPF_REG_6,
+	BPF_REG_7,
+	BPF_REG_8,
+	BPF_REG_9,
+	BPF_REG_10,
+	__MAX_BPF_REG,
+};
+
+/* BPF has 10 general purpose 64-bit registers and stack frame. */
+#define MAX_BPF_REG	__MAX_BPF_REG
+
+struct bpf_insn {
+	__u8	code;		/* opcode */
+	__u8	dst_reg:4;	/* dest register */
+	__u8	src_reg:4;	/* source register */
+	__s16	off;		/* signed offset */
+	__s32	imm;		/* signed immediate constant */
+};
+
+/* BPF syscall commands, see bpf(2) man-page for details. */
+enum bpf_cmd {
+	BPF_MAP_CREATE,
+	BPF_MAP_LOOKUP_ELEM,
+	BPF_MAP_UPDATE_ELEM,
+	BPF_MAP_DELETE_ELEM,
+	BPF_MAP_GET_NEXT_KEY,
+	BPF_PROG_LOAD,
+	BPF_OBJ_PIN,
+	BPF_OBJ_GET,
+};
+
+enum bpf_map_type {
+	BPF_MAP_TYPE_UNSPEC,
+	BPF_MAP_TYPE_HASH,
+	BPF_MAP_TYPE_ARRAY,
+	BPF_MAP_TYPE_PROG_ARRAY,
+	BPF_MAP_TYPE_PERF_EVENT_ARRAY,
+	BPF_MAP_TYPE_PERCPU_HASH,
+	BPF_MAP_TYPE_PERCPU_ARRAY,
+	BPF_MAP_TYPE_STACK_TRACE,
+};
+
+enum bpf_prog_type {
+	BPF_PROG_TYPE_UNSPEC,
+	BPF_PROG_TYPE_SOCKET_FILTER,
+	BPF_PROG_TYPE_KPROBE,
+	BPF_PROG_TYPE_SCHED_CLS,
+	BPF_PROG_TYPE_SCHED_ACT,
+	BPF_PROG_TYPE_TRACEPOINT,
+};
+
+#define BPF_PSEUDO_MAP_FD	1
+
+/* flags for BPF_MAP_UPDATE_ELEM command */
+#define BPF_ANY		0 /* create new element or update existing */
+#define BPF_NOEXIST	1 /* create new element if it didn't exist */
+#define BPF_EXIST	2 /* update existing element */
+
+#define BPF_F_NO_PREALLOC	(1U << 0)
+
+union bpf_attr {
+	struct { /* anonymous struct used by BPF_MAP_CREATE command */
+		__u32	map_type;	/* one of enum bpf_map_type */
+		__u32	key_size;	/* size of key in bytes */
+		__u32	value_size;	/* size of value in bytes */
+		__u32	max_entries;	/* max number of entries in a map */
+		__u32	map_flags;	/* prealloc or not */
+	};
+
+	struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */
+		__u32		map_fd;
+		__aligned_u64	key;
+		union {
+			__aligned_u64 value;
+			__aligned_u64 next_key;
+		};
+		__u64		flags;
+	};
+
+	struct { /* anonymous struct used by BPF_PROG_LOAD command */
+		__u32		prog_type;	/* one of enum bpf_prog_type */
+		__u32		insn_cnt;
+		__aligned_u64	insns;
+		__aligned_u64	license;
+		__u32		log_level;	/* verbosity level of verifier */
+		__u32		log_size;	/* size of user buffer */
+		__aligned_u64	log_buf;	/* user supplied buffer */
+		__u32		kern_version;	/* checked when prog_type=kprobe */
+	};
+
+	struct { /* anonymous struct used by BPF_OBJ_* commands */
+		__aligned_u64	pathname;
+		__u32		bpf_fd;
+	};
+} __attribute__((aligned(8)));
+
+/* integer value in 'imm' field of BPF_CALL instruction selects which helper
+ * function eBPF program intends to call
+ */
+enum bpf_func_id {
+	BPF_FUNC_unspec,
+	BPF_FUNC_map_lookup_elem, /* void *map_lookup_elem(&map, &key) */
+	BPF_FUNC_map_update_elem, /* int map_update_elem(&map, &key, &value, flags) */
+	BPF_FUNC_map_delete_elem, /* int map_delete_elem(&map, &key) */
+	BPF_FUNC_probe_read,      /* int bpf_probe_read(void *dst, int size, void *src) */
+	BPF_FUNC_ktime_get_ns,    /* u64 bpf_ktime_get_ns(void) */
+	BPF_FUNC_trace_printk,    /* int bpf_trace_printk(const char *fmt, int fmt_size, ...) */
+	BPF_FUNC_get_prandom_u32, /* u32 prandom_u32(void) */
+	BPF_FUNC_get_smp_processor_id, /* u32 raw_smp_processor_id(void) */
+
+	/**
+	 * skb_store_bytes(skb, offset, from, len, flags) - store bytes into packet
+	 * @skb: pointer to skb
+	 * @offset: offset within packet from skb->mac_header
+	 * @from: pointer where to copy bytes from
+	 * @len: number of bytes to store into packet
+	 * @flags: bit 0 - if true, recompute skb->csum
+	 *         other bits - reserved
+	 * Return: 0 on success
+	 */
+	BPF_FUNC_skb_store_bytes,
+
+	/**
+	 * l3_csum_replace(skb, offset, from, to, flags) - recompute IP checksum
+	 * @skb: pointer to skb
+	 * @offset: offset within packet where IP checksum is located
+	 * @from: old value of header field
+	 * @to: new value of header field
+	 * @flags: bits 0-3 - size of header field
+	 *         other bits - reserved
+	 * Return: 0 on success
+	 */
+	BPF_FUNC_l3_csum_replace,
+
+	/**
+	 * l4_csum_replace(skb, offset, from, to, flags) - recompute TCP/UDP checksum
+	 * @skb: pointer to skb
+	 * @offset: offset within packet where TCP/UDP checksum is located
+	 * @from: old value of header field
+	 * @to: new value of header field
+	 * @flags: bits 0-3 - size of header field
+	 *         bit 4 - is pseudo header
+	 *         other bits - reserved
+	 * Return: 0 on success
+	 */
+	BPF_FUNC_l4_csum_replace,
+
+	/**
+	 * bpf_tail_call(ctx, prog_array_map, index) - jump into another BPF program
+	 * @ctx: context pointer passed to next program
+	 * @prog_array_map: pointer to map which type is BPF_MAP_TYPE_PROG_ARRAY
+	 * @index: index inside array that selects specific program to run
+	 * Return: 0 on success
+	 */
+	BPF_FUNC_tail_call,
+
+	/**
+	 * bpf_clone_redirect(skb, ifindex, flags) - redirect to another netdev
+	 * @skb: pointer to skb
+	 * @ifindex: ifindex of the net device
+	 * @flags: bit 0 - if set, redirect to ingress instead of egress
+	 *         other bits - reserved
+	 * Return: 0 on success
+	 */
+	BPF_FUNC_clone_redirect,
+
+	/**
+	 * u64 bpf_get_current_pid_tgid(void)
+	 * Return: current->tgid << 32 | current->pid
+	 */
+	BPF_FUNC_get_current_pid_tgid,
+
+	/**
+	 * u64 bpf_get_current_uid_gid(void)
+	 * Return: current_gid << 32 | current_uid
+	 */
+	BPF_FUNC_get_current_uid_gid,
+
+	/**
+	 * bpf_get_current_comm(char *buf, int size_of_buf)
+	 * stores current->comm into buf
+	 * Return: 0 on success
+	 */
+	BPF_FUNC_get_current_comm,
+
+	/**
+	 * bpf_get_cgroup_classid(skb) - retrieve a proc's classid
+	 * @skb: pointer to skb
+	 * Return: classid if != 0
+	 */
+	BPF_FUNC_get_cgroup_classid,
+	BPF_FUNC_skb_vlan_push, /* bpf_skb_vlan_push(skb, vlan_proto, vlan_tci) */
+	BPF_FUNC_skb_vlan_pop,  /* bpf_skb_vlan_pop(skb) */
+
+	/**
+	 * bpf_skb_[gs]et_tunnel_key(skb, key, size, flags)
+	 * retrieve or populate tunnel metadata
+	 * @skb: pointer to skb
+	 * @key: pointer to 'struct bpf_tunnel_key'
+	 * @size: size of 'struct bpf_tunnel_key'
+	 * @flags: room for future extensions
+	 * Retrun: 0 on success
+	 */
+	BPF_FUNC_skb_get_tunnel_key,
+	BPF_FUNC_skb_set_tunnel_key,
+	BPF_FUNC_perf_event_read,	/* u64 bpf_perf_event_read(&map, index) */
+	/**
+	 * bpf_redirect(ifindex, flags) - redirect to another netdev
+	 * @ifindex: ifindex of the net device
+	 * @flags: bit 0 - if set, redirect to ingress instead of egress
+	 *         other bits - reserved
+	 * Return: TC_ACT_REDIRECT
+	 */
+	BPF_FUNC_redirect,
+
+	/**
+	 * bpf_get_route_realm(skb) - retrieve a dst's tclassid
+	 * @skb: pointer to skb
+	 * Return: realm if != 0
+	 */
+	BPF_FUNC_get_route_realm,
+
+	/**
+	 * bpf_perf_event_output(ctx, map, index, data, size) - output perf raw sample
+	 * @ctx: struct pt_regs*
+	 * @map: pointer to perf_event_array map
+	 * @index: index of event in the map
+	 * @data: data on stack to be output as raw data
+	 * @size: size of data
+	 * Return: 0 on success
+	 */
+	BPF_FUNC_perf_event_output,
+	BPF_FUNC_skb_load_bytes,
+
+	/**
+	 * bpf_get_stackid(ctx, map, flags) - walk user or kernel stack and return id
+	 * @ctx: struct pt_regs*
+	 * @map: pointer to stack_trace map
+	 * @flags: bits 0-7 - numer of stack frames to skip
+	 *         bit 8 - collect user stack instead of kernel
+	 *         bit 9 - compare stacks by hash only
+	 *         bit 10 - if two different stacks hash into the same stackid
+	 *                  discard old
+	 *         other bits - reserved
+	 * Return: >= 0 stackid on success or negative error
+	 */
+	BPF_FUNC_get_stackid,
+
+	/**
+	 * bpf_csum_diff(from, from_size, to, to_size, seed) - calculate csum diff
+	 * @from: raw from buffer
+	 * @from_size: length of from buffer
+	 * @to: raw to buffer
+	 * @to_size: length of to buffer
+	 * @seed: optional seed
+	 * Return: csum result
+	 */
+	BPF_FUNC_csum_diff,
+
+	/**
+	 * bpf_skb_[gs]et_tunnel_opt(skb, opt, size)
+	 * retrieve or populate tunnel options metadata
+	 * @skb: pointer to skb
+	 * @opt: pointer to raw tunnel option data
+	 * @size: size of @opt
+	 * Return: 0 on success for set, option size for get
+	 */
+	BPF_FUNC_skb_get_tunnel_opt,
+	BPF_FUNC_skb_set_tunnel_opt,
+	__BPF_FUNC_MAX_ID,
+};
+
+/* All flags used by eBPF helper functions, placed here. */
+
+/* BPF_FUNC_skb_store_bytes flags. */
+#define BPF_F_RECOMPUTE_CSUM		(1ULL << 0)
+#define BPF_F_INVALIDATE_HASH		(1ULL << 1)
+
+/* BPF_FUNC_l3_csum_replace and BPF_FUNC_l4_csum_replace flags.
+ * First 4 bits are for passing the header field size.
+ */
+#define BPF_F_HDR_FIELD_MASK		0xfULL
+
+/* BPF_FUNC_l4_csum_replace flags. */
+#define BPF_F_PSEUDO_HDR		(1ULL << 4)
+#define BPF_F_MARK_MANGLED_0		(1ULL << 5)
+
+/* BPF_FUNC_clone_redirect and BPF_FUNC_redirect flags. */
+#define BPF_F_INGRESS			(1ULL << 0)
+
+/* BPF_FUNC_skb_set_tunnel_key and BPF_FUNC_skb_get_tunnel_key flags. */
+#define BPF_F_TUNINFO_IPV6		(1ULL << 0)
+
+/* BPF_FUNC_get_stackid flags. */
+#define BPF_F_SKIP_FIELD_MASK		0xffULL
+#define BPF_F_USER_STACK		(1ULL << 8)
+#define BPF_F_FAST_STACK_CMP		(1ULL << 9)
+#define BPF_F_REUSE_STACKID		(1ULL << 10)
+
+/* BPF_FUNC_skb_set_tunnel_key flags. */
+#define BPF_F_ZERO_CSUM_TX		(1ULL << 1)
+#define BPF_F_DONT_FRAGMENT		(1ULL << 2)
+
+/* BPF_FUNC_perf_event_output flags. */
+#define BPF_F_INDEX_MASK		0xffffffffULL
+#define BPF_F_CURRENT_CPU		BPF_F_INDEX_MASK
+
+/* user accessible mirror of in-kernel sk_buff.
+ * new fields can only be added to the end of this structure
+ */
+struct __sk_buff {
+	__u32 len;
+	__u32 pkt_type;
+	__u32 mark;
+	__u32 queue_mapping;
+	__u32 protocol;
+	__u32 vlan_present;
+	__u32 vlan_tci;
+	__u32 vlan_proto;
+	__u32 priority;
+	__u32 ingress_ifindex;
+	__u32 ifindex;
+	__u32 tc_index;
+	__u32 cb[5];
+	__u32 hash;
+	__u32 tc_classid;
+	__u32 data;
+	__u32 data_end;
+};
+
+struct bpf_tunnel_key {
+	__u32 tunnel_id;
+	union {
+		__u32 remote_ipv4;
+		__u32 remote_ipv6[4];
+	};
+	__u8 tunnel_tos;
+	__u8 tunnel_ttl;
+	__u16 tunnel_ext;
+	__u32 tunnel_label;
+};
+
+#endif /* _UAPI__LINUX_BPF_H__ */
diff --git a/tools/include/uapi/linux/bpf_common.h b/tools/include/uapi/linux/bpf_common.h
new file mode 100644
index 0000000000000..a5c220e0828f3
--- /dev/null
+++ b/tools/include/uapi/linux/bpf_common.h
@@ -0,0 +1,55 @@
+#ifndef _UAPI__LINUX_BPF_COMMON_H__
+#define _UAPI__LINUX_BPF_COMMON_H__
+
+/* Instruction classes */
+#define BPF_CLASS(code) ((code) & 0x07)
+#define		BPF_LD		0x00
+#define		BPF_LDX		0x01
+#define		BPF_ST		0x02
+#define		BPF_STX		0x03
+#define		BPF_ALU		0x04
+#define		BPF_JMP		0x05
+#define		BPF_RET		0x06
+#define		BPF_MISC        0x07
+
+/* ld/ldx fields */
+#define BPF_SIZE(code)  ((code) & 0x18)
+#define		BPF_W		0x00
+#define		BPF_H		0x08
+#define		BPF_B		0x10
+#define BPF_MODE(code)  ((code) & 0xe0)
+#define		BPF_IMM		0x00
+#define		BPF_ABS		0x20
+#define		BPF_IND		0x40
+#define		BPF_MEM		0x60
+#define		BPF_LEN		0x80
+#define		BPF_MSH		0xa0
+
+/* alu/jmp fields */
+#define BPF_OP(code)    ((code) & 0xf0)
+#define		BPF_ADD		0x00
+#define		BPF_SUB		0x10
+#define		BPF_MUL		0x20
+#define		BPF_DIV		0x30
+#define		BPF_OR		0x40
+#define		BPF_AND		0x50
+#define		BPF_LSH		0x60
+#define		BPF_RSH		0x70
+#define		BPF_NEG		0x80
+#define		BPF_MOD		0x90
+#define		BPF_XOR		0xa0
+
+#define		BPF_JA		0x00
+#define		BPF_JEQ		0x10
+#define		BPF_JGT		0x20
+#define		BPF_JGE		0x30
+#define		BPF_JSET        0x40
+#define BPF_SRC(code)   ((code) & 0x08)
+#define		BPF_K		0x00
+#define		BPF_X		0x08
+
+#ifndef BPF_MAXINSNS
+#define BPF_MAXINSNS 4096
+#endif
+
+#endif /* _UAPI__LINUX_BPF_COMMON_H__ */
diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index fc1bc75ae56d4..62d89d50fcbd0 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -68,7 +68,7 @@ FEATURE_USER = .libbpf
 FEATURE_TESTS = libelf libelf-getphdrnum libelf-mmap bpf
 FEATURE_DISPLAY = libelf bpf
 
-INCLUDES = -I. -I$(srctree)/tools/include -I$(srctree)/arch/$(ARCH)/include/uapi -I$(srctree)/include/uapi
+INCLUDES = -I. -I$(srctree)/tools/include -I$(srctree)/tools/arch/$(ARCH)/include/uapi -I$(srctree)/tools/include/uapi
 FEATURE_CHECK_CFLAGS-bpf = $(INCLUDES)
 
 check_feat := 1
@@ -154,6 +154,12 @@ all: fixdep $(VERSION_FILES) all_cmd
 all_cmd: $(CMD_TARGETS)
 
 $(BPF_IN): force elfdep bpfdep
+	@(test -f ../../../include/uapi/linux/bpf.h -a -f ../../../include/uapi/linux/bpf.h && ( \
+	(diff -B ../../include/uapi/linux/bpf.h ../../../include/uapi/linux/bpf.h >/dev/null) || \
+	echo "Warning: tools/include/uapi/linux/bpf.h differs from kernel" >&2 )) || true
+	@(test -f ../../../include/uapi/linux/bpf_common.h -a -f ../../../include/uapi/linux/bpf_common.h && ( \
+	(diff -B ../../include/uapi/linux/bpf_common.h ../../../include/uapi/linux/bpf_common.h >/dev/null) || \
+	echo "Warning: tools/include/uapi/linux/bpf_common.h differs from kernel" >&2 )) || true
 	$(Q)$(MAKE) $(build)=libbpf
 
 $(OUTPUT)libbpf.so: $(BPF_IN)
diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST
index cf85d1cd1c919..a300cbb135414 100644
--- a/tools/perf/MANIFEST
+++ b/tools/perf/MANIFEST
@@ -23,7 +23,6 @@ tools/build
 tools/arch/x86/include/asm/atomic.h
 tools/arch/x86/include/asm/rmwcc.h
 tools/lib/traceevent
-tools/lib/bpf
 tools/lib/api
 tools/lib/bpf
 tools/lib/subcmd
@@ -60,6 +59,8 @@ tools/include/linux/hash.h
 tools/include/linux/kernel.h
 tools/include/linux/list.h
 tools/include/linux/log2.h
+tools/include/uapi/linux/bpf.h
+tools/include/uapi/linux/bpf_common.h
 tools/include/uapi/linux/perf_event.h
 tools/include/linux/poison.h
 tools/include/linux/rbtree.h
@@ -82,8 +83,6 @@ arch/*/include/uapi/asm/unistd*.h
 arch/*/include/uapi/asm/perf_regs.h
 include/linux/poison.h
 include/linux/hw_breakpoint.h
-include/uapi/linux/bpf.h
-include/uapi/linux/bpf_common.h
 include/uapi/linux/const.h
 include/uapi/linux/swab.h
 include/uapi/linux/hw_breakpoint.h
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index bbb22101be2e8..d629e5f5abdce 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -115,7 +115,7 @@ endif
 FEATURE_CHECK_CFLAGS-libbabeltrace := $(LIBBABELTRACE_CFLAGS)
 FEATURE_CHECK_LDFLAGS-libbabeltrace := $(LIBBABELTRACE_LDFLAGS) -lbabeltrace-ctf
 
-FEATURE_CHECK_CFLAGS-bpf = -I. -I$(srctree)/tools/include -I$(srctree)/arch/$(ARCH)/include/uapi -I$(srctree)/include/uapi
+FEATURE_CHECK_CFLAGS-bpf = -I. -I$(srctree)/tools/include -I$(srctree)/tools/arch/$(ARCH)/include/uapi -I$(srctree)/tools/include/uapi
 # include ARCH specific config
 -include $(src-perf)/arch/$(ARCH)/Makefile
 
@@ -210,7 +210,8 @@ CFLAGS += -I$(srctree)/tools/include/uapi
 CFLAGS += -I$(srctree)/tools/include/
 CFLAGS += -I$(srctree)/arch/$(ARCH)/include/uapi
 CFLAGS += -I$(srctree)/arch/$(ARCH)/include
-CFLAGS += -I$(srctree)/tools/arch/$(ARCH)/include
+CFLAGS += -I$(srctree)/tools/arch/$(ARCH)/include/uapi
+CFLAGS += -I$(srctree)/tools/arch/$(ARCH)/
 CFLAGS += -I$(srctree)/include/uapi
 CFLAGS += -I$(srctree)/include
 

From 12f020338a2ca5db99db40b3cf8e4df88744c541 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Mon, 11 Jul 2016 21:16:52 -0300
Subject: [PATCH 38/66] tools: Copy uapi/asm/perf_regs.h from the kernel

To allow the build to complete on older systems, where those files are
either not uptodate, lacking some recent additions or not present at
all.

And check if the copy drifts from the kernel.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-sxf7rpow2blsno5f7t6n0sqz@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/arch/arm/include/uapi/asm/perf_regs.h   | 23 +++++++++
 tools/arch/arm64/include/uapi/asm/perf_regs.h | 40 +++++++++++++++
 .../arch/powerpc/include/uapi/asm/perf_regs.h | 50 +++++++++++++++++++
 tools/arch/x86/include/uapi/asm/perf_regs.h   | 33 ++++++++++++
 tools/perf/MANIFEST                           |  2 +-
 tools/perf/Makefile.perf                      | 12 +++++
 tools/perf/config/Makefile                    |  3 +-
 7 files changed, 161 insertions(+), 2 deletions(-)
 create mode 100644 tools/arch/arm/include/uapi/asm/perf_regs.h
 create mode 100644 tools/arch/arm64/include/uapi/asm/perf_regs.h
 create mode 100644 tools/arch/powerpc/include/uapi/asm/perf_regs.h
 create mode 100644 tools/arch/x86/include/uapi/asm/perf_regs.h

diff --git a/tools/arch/arm/include/uapi/asm/perf_regs.h b/tools/arch/arm/include/uapi/asm/perf_regs.h
new file mode 100644
index 0000000000000..ce59448458b22
--- /dev/null
+++ b/tools/arch/arm/include/uapi/asm/perf_regs.h
@@ -0,0 +1,23 @@
+#ifndef _ASM_ARM_PERF_REGS_H
+#define _ASM_ARM_PERF_REGS_H
+
+enum perf_event_arm_regs {
+	PERF_REG_ARM_R0,
+	PERF_REG_ARM_R1,
+	PERF_REG_ARM_R2,
+	PERF_REG_ARM_R3,
+	PERF_REG_ARM_R4,
+	PERF_REG_ARM_R5,
+	PERF_REG_ARM_R6,
+	PERF_REG_ARM_R7,
+	PERF_REG_ARM_R8,
+	PERF_REG_ARM_R9,
+	PERF_REG_ARM_R10,
+	PERF_REG_ARM_FP,
+	PERF_REG_ARM_IP,
+	PERF_REG_ARM_SP,
+	PERF_REG_ARM_LR,
+	PERF_REG_ARM_PC,
+	PERF_REG_ARM_MAX,
+};
+#endif /* _ASM_ARM_PERF_REGS_H */
diff --git a/tools/arch/arm64/include/uapi/asm/perf_regs.h b/tools/arch/arm64/include/uapi/asm/perf_regs.h
new file mode 100644
index 0000000000000..172b8317ee49f
--- /dev/null
+++ b/tools/arch/arm64/include/uapi/asm/perf_regs.h
@@ -0,0 +1,40 @@
+#ifndef _ASM_ARM64_PERF_REGS_H
+#define _ASM_ARM64_PERF_REGS_H
+
+enum perf_event_arm_regs {
+	PERF_REG_ARM64_X0,
+	PERF_REG_ARM64_X1,
+	PERF_REG_ARM64_X2,
+	PERF_REG_ARM64_X3,
+	PERF_REG_ARM64_X4,
+	PERF_REG_ARM64_X5,
+	PERF_REG_ARM64_X6,
+	PERF_REG_ARM64_X7,
+	PERF_REG_ARM64_X8,
+	PERF_REG_ARM64_X9,
+	PERF_REG_ARM64_X10,
+	PERF_REG_ARM64_X11,
+	PERF_REG_ARM64_X12,
+	PERF_REG_ARM64_X13,
+	PERF_REG_ARM64_X14,
+	PERF_REG_ARM64_X15,
+	PERF_REG_ARM64_X16,
+	PERF_REG_ARM64_X17,
+	PERF_REG_ARM64_X18,
+	PERF_REG_ARM64_X19,
+	PERF_REG_ARM64_X20,
+	PERF_REG_ARM64_X21,
+	PERF_REG_ARM64_X22,
+	PERF_REG_ARM64_X23,
+	PERF_REG_ARM64_X24,
+	PERF_REG_ARM64_X25,
+	PERF_REG_ARM64_X26,
+	PERF_REG_ARM64_X27,
+	PERF_REG_ARM64_X28,
+	PERF_REG_ARM64_X29,
+	PERF_REG_ARM64_LR,
+	PERF_REG_ARM64_SP,
+	PERF_REG_ARM64_PC,
+	PERF_REG_ARM64_MAX,
+};
+#endif /* _ASM_ARM64_PERF_REGS_H */
diff --git a/tools/arch/powerpc/include/uapi/asm/perf_regs.h b/tools/arch/powerpc/include/uapi/asm/perf_regs.h
new file mode 100644
index 0000000000000..6a93209748a15
--- /dev/null
+++ b/tools/arch/powerpc/include/uapi/asm/perf_regs.h
@@ -0,0 +1,50 @@
+#ifndef _UAPI_ASM_POWERPC_PERF_REGS_H
+#define _UAPI_ASM_POWERPC_PERF_REGS_H
+
+enum perf_event_powerpc_regs {
+	PERF_REG_POWERPC_R0,
+	PERF_REG_POWERPC_R1,
+	PERF_REG_POWERPC_R2,
+	PERF_REG_POWERPC_R3,
+	PERF_REG_POWERPC_R4,
+	PERF_REG_POWERPC_R5,
+	PERF_REG_POWERPC_R6,
+	PERF_REG_POWERPC_R7,
+	PERF_REG_POWERPC_R8,
+	PERF_REG_POWERPC_R9,
+	PERF_REG_POWERPC_R10,
+	PERF_REG_POWERPC_R11,
+	PERF_REG_POWERPC_R12,
+	PERF_REG_POWERPC_R13,
+	PERF_REG_POWERPC_R14,
+	PERF_REG_POWERPC_R15,
+	PERF_REG_POWERPC_R16,
+	PERF_REG_POWERPC_R17,
+	PERF_REG_POWERPC_R18,
+	PERF_REG_POWERPC_R19,
+	PERF_REG_POWERPC_R20,
+	PERF_REG_POWERPC_R21,
+	PERF_REG_POWERPC_R22,
+	PERF_REG_POWERPC_R23,
+	PERF_REG_POWERPC_R24,
+	PERF_REG_POWERPC_R25,
+	PERF_REG_POWERPC_R26,
+	PERF_REG_POWERPC_R27,
+	PERF_REG_POWERPC_R28,
+	PERF_REG_POWERPC_R29,
+	PERF_REG_POWERPC_R30,
+	PERF_REG_POWERPC_R31,
+	PERF_REG_POWERPC_NIP,
+	PERF_REG_POWERPC_MSR,
+	PERF_REG_POWERPC_ORIG_R3,
+	PERF_REG_POWERPC_CTR,
+	PERF_REG_POWERPC_LINK,
+	PERF_REG_POWERPC_XER,
+	PERF_REG_POWERPC_CCR,
+	PERF_REG_POWERPC_SOFTE,
+	PERF_REG_POWERPC_TRAP,
+	PERF_REG_POWERPC_DAR,
+	PERF_REG_POWERPC_DSISR,
+	PERF_REG_POWERPC_MAX,
+};
+#endif /* _UAPI_ASM_POWERPC_PERF_REGS_H */
diff --git a/tools/arch/x86/include/uapi/asm/perf_regs.h b/tools/arch/x86/include/uapi/asm/perf_regs.h
new file mode 100644
index 0000000000000..3f2207bfd17b0
--- /dev/null
+++ b/tools/arch/x86/include/uapi/asm/perf_regs.h
@@ -0,0 +1,33 @@
+#ifndef _ASM_X86_PERF_REGS_H
+#define _ASM_X86_PERF_REGS_H
+
+enum perf_event_x86_regs {
+	PERF_REG_X86_AX,
+	PERF_REG_X86_BX,
+	PERF_REG_X86_CX,
+	PERF_REG_X86_DX,
+	PERF_REG_X86_SI,
+	PERF_REG_X86_DI,
+	PERF_REG_X86_BP,
+	PERF_REG_X86_SP,
+	PERF_REG_X86_IP,
+	PERF_REG_X86_FLAGS,
+	PERF_REG_X86_CS,
+	PERF_REG_X86_SS,
+	PERF_REG_X86_DS,
+	PERF_REG_X86_ES,
+	PERF_REG_X86_FS,
+	PERF_REG_X86_GS,
+	PERF_REG_X86_R8,
+	PERF_REG_X86_R9,
+	PERF_REG_X86_R10,
+	PERF_REG_X86_R11,
+	PERF_REG_X86_R12,
+	PERF_REG_X86_R13,
+	PERF_REG_X86_R14,
+	PERF_REG_X86_R15,
+
+	PERF_REG_X86_32_MAX = PERF_REG_X86_GS + 1,
+	PERF_REG_X86_64_MAX = PERF_REG_X86_R15 + 1,
+};
+#endif /* _ASM_X86_PERF_REGS_H */
diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST
index a300cbb135414..d15c052ccb7b3 100644
--- a/tools/perf/MANIFEST
+++ b/tools/perf/MANIFEST
@@ -80,7 +80,7 @@ include/linux/stringify.h
 include/linux/swab.h
 arch/*/include/asm/unistd*.h
 arch/*/include/uapi/asm/unistd*.h
-arch/*/include/uapi/asm/perf_regs.h
+tools/arch/*/include/uapi/asm/perf_regs.h
 include/linux/poison.h
 include/linux/hw_breakpoint.h
 include/uapi/linux/const.h
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 809735c6cb264..34b91ba8b425a 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -363,6 +363,18 @@ $(PERF_IN): prepare FORCE
 	@(test -f ../../arch/x86/lib/memset_64.S && ( \
         (diff -B ../arch/x86/lib/memset_64.S ../../arch/x86/lib/memset_64.S >/dev/null) \
         || echo "Warning: tools/arch/x86/lib/memset_64.S differs from kernel" >&2 )) || true
+	@(test -f ../../arch/arm/include/uapi/asm/perf_regs.h && ( \
+        (diff -B ../arch/arm/include/uapi/asm/perf_regs.h ../../arch/arm/include/uapi/asm/perf_regs.h >/dev/null) \
+        || echo "Warning: tools/arch/arm/include/uapi/asm/perf_regs.h differs from kernel" >&2 )) || true
+	@(test -f ../../arch/arm64/include/uapi/asm/perf_regs.h && ( \
+        (diff -B ../arch/arm64/include/uapi/asm/perf_regs.h ../../arch/arm64/include/uapi/asm/perf_regs.h >/dev/null) \
+        || echo "Warning: tools/arch/arm64/include/uapi/asm/perf_regs.h differs from kernel" >&2 )) || true
+	@(test -f ../../arch/powerpc/include/uapi/asm/perf_regs.h && ( \
+        (diff -B ../arch/powerpc/include/uapi/asm/perf_regs.h ../../arch/powerpc/include/uapi/asm/perf_regs.h >/dev/null) \
+        || echo "Warning: tools/arch/powerpc/include/uapi/asm/perf_regs.h differs from kernel" >&2 )) || true
+	@(test -f ../../arch/x86/include/uapi/asm/perf_regs.h && ( \
+        (diff -B ../arch/x86/include/uapi/asm/perf_regs.h ../../arch/x86/include/uapi/asm/perf_regs.h >/dev/null) \
+        || echo "Warning: tools/arch/x86/include/uapi/asm/perf_regs.h differs from kernel" >&2 )) || true
 	$(Q)$(MAKE) $(build)=perf
 
 $(OUTPUT)perf: $(PERFLIBS) $(PERF_IN) $(LIBTRACEEVENT_DYNAMIC_LIST)
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index d629e5f5abdce..49a2130682830 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -208,9 +208,10 @@ CFLAGS += -I$(src-perf)/util/include
 CFLAGS += -I$(src-perf)/arch/$(ARCH)/include
 CFLAGS += -I$(srctree)/tools/include/uapi
 CFLAGS += -I$(srctree)/tools/include/
+CFLAGS += -I$(srctree)/tools/arch/$(ARCH)/include/uapi
+CFLAGS += -I$(srctree)/tools/arch/$(ARCH)/include/
 CFLAGS += -I$(srctree)/arch/$(ARCH)/include/uapi
 CFLAGS += -I$(srctree)/arch/$(ARCH)/include
-CFLAGS += -I$(srctree)/tools/arch/$(ARCH)/include/uapi
 CFLAGS += -I$(srctree)/tools/arch/$(ARCH)/
 CFLAGS += -I$(srctree)/include/uapi
 CFLAGS += -I$(srctree)/include

From 4ffde492461d5c2111bf64366b633e554b4aa925 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Mon, 11 Jul 2016 23:22:30 -0300
Subject: [PATCH 39/66] perf test bpf: Use epoll_wait() instead of
 epoll_pwait()

The prototype for epoll_wait() is available in older distros, so use it
instead of epoll_pwait() (removing the last NULL arg, the sigmask,
makes it the same thing anyway) to avoid breaking the build.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-pwiwizloxt0jujy8em80qut3@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/bpf-script-example.c | 4 ++--
 tools/perf/tests/bpf.c                | 6 +++---
 2 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/tools/perf/tests/bpf-script-example.c b/tools/perf/tests/bpf-script-example.c
index 0ec9c2c031649..e53bc91fa2604 100644
--- a/tools/perf/tests/bpf-script-example.c
+++ b/tools/perf/tests/bpf-script-example.c
@@ -31,8 +31,8 @@ struct bpf_map_def SEC("maps") flip_table = {
 	.max_entries = 1,
 };
 
-SEC("func=sys_epoll_pwait")
-int bpf_func__sys_epoll_pwait(void *ctx)
+SEC("func=sys_epoll_wait")
+int bpf_func__sys_epoll_wait(void *ctx)
 {
 	int ind =0;
 	int *flag = bpf_map_lookup_elem(&flip_table, &ind);
diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c
index da0d876139752..fc54064b91860 100644
--- a/tools/perf/tests/bpf.c
+++ b/tools/perf/tests/bpf.c
@@ -13,13 +13,13 @@
 
 #ifdef HAVE_LIBBPF_SUPPORT
 
-static int epoll_pwait_loop(void)
+static int epoll_wait_loop(void)
 {
 	int i;
 
 	/* Should fail NR_ITERS times */
 	for (i = 0; i < NR_ITERS; i++)
-		epoll_pwait(-(i + 1), NULL, 0, 0, NULL);
+		epoll_wait(-(i + 1), NULL, 0, 0);
 	return 0;
 }
 
@@ -61,7 +61,7 @@ static struct {
 		"[basic_bpf_test]",
 		"fix 'perf test LLVM' first",
 		"load bpf object failed",
-		&epoll_pwait_loop,
+		&epoll_wait_loop,
 		(NR_ITERS + 1) / 2,
 	},
 #ifdef HAVE_BPF_PROLOGUE

From 4998a1224686d74ab7f7789787f7f7f904c75dfc Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Mon, 11 Jul 2016 23:37:18 -0300
Subject: [PATCH 40/66] tools: Copy uapi/linux/hw_breakpoint.h from the kernel

To allow the build to complete on older systems, where those files are
either not uptodate, lacking some recent additions or not present at
all.

And check if the copy drifts from the kernel.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-3jz31pz4nw526uko5da9e7o3@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/uapi/linux/hw_breakpoint.h | 30 ++++++++++++++++++++++++
 tools/perf/MANIFEST                      |  3 +--
 tools/perf/Makefile.perf                 |  3 +++
 3 files changed, 34 insertions(+), 2 deletions(-)
 create mode 100644 tools/include/uapi/linux/hw_breakpoint.h

diff --git a/tools/include/uapi/linux/hw_breakpoint.h b/tools/include/uapi/linux/hw_breakpoint.h
new file mode 100644
index 0000000000000..b04000a2296a1
--- /dev/null
+++ b/tools/include/uapi/linux/hw_breakpoint.h
@@ -0,0 +1,30 @@
+#ifndef _UAPI_LINUX_HW_BREAKPOINT_H
+#define _UAPI_LINUX_HW_BREAKPOINT_H
+
+enum {
+	HW_BREAKPOINT_LEN_1 = 1,
+	HW_BREAKPOINT_LEN_2 = 2,
+	HW_BREAKPOINT_LEN_4 = 4,
+	HW_BREAKPOINT_LEN_8 = 8,
+};
+
+enum {
+	HW_BREAKPOINT_EMPTY	= 0,
+	HW_BREAKPOINT_R		= 1,
+	HW_BREAKPOINT_W		= 2,
+	HW_BREAKPOINT_RW	= HW_BREAKPOINT_R | HW_BREAKPOINT_W,
+	HW_BREAKPOINT_X		= 4,
+	HW_BREAKPOINT_INVALID   = HW_BREAKPOINT_RW | HW_BREAKPOINT_X,
+};
+
+enum bp_type_idx {
+	TYPE_INST 	= 0,
+#ifdef CONFIG_HAVE_MIXED_BREAKPOINTS_REGS
+	TYPE_DATA	= 0,
+#else
+	TYPE_DATA	= 1,
+#endif
+	TYPE_MAX
+};
+
+#endif /* _UAPI_LINUX_HW_BREAKPOINT_H */
diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST
index d15c052ccb7b3..a4aefaeff3550 100644
--- a/tools/perf/MANIFEST
+++ b/tools/perf/MANIFEST
@@ -61,6 +61,7 @@ tools/include/linux/list.h
 tools/include/linux/log2.h
 tools/include/uapi/linux/bpf.h
 tools/include/uapi/linux/bpf_common.h
+tools/include/uapi/linux/hw_breakpoint.h
 tools/include/uapi/linux/perf_event.h
 tools/include/linux/poison.h
 tools/include/linux/rbtree.h
@@ -82,10 +83,8 @@ arch/*/include/asm/unistd*.h
 arch/*/include/uapi/asm/unistd*.h
 tools/arch/*/include/uapi/asm/perf_regs.h
 include/linux/poison.h
-include/linux/hw_breakpoint.h
 include/uapi/linux/const.h
 include/uapi/linux/swab.h
-include/uapi/linux/hw_breakpoint.h
 arch/x86/include/asm/svm.h
 arch/x86/include/asm/vmx.h
 arch/x86/include/asm/kvm_host.h
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 34b91ba8b425a..0d07672c3af78 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -348,6 +348,9 @@ $(PERF_IN): prepare FORCE
 	@(test -f ../../include/uapi/linux/perf_event.h && ( \
         (diff -B ../include/uapi/linux/perf_event.h ../../include/uapi/linux/perf_event.h >/dev/null) \
         || echo "Warning: tools/include/uapi/linux/perf_event.h differs from kernel" >&2 )) || true
+	@(test -f ../../include/uapi/linux/hw_breakpoint.h && ( \
+        (diff -B ../include/uapi/linux/hw_breakpoint.h ../../include/uapi/linux/hw_breakpoint.h >/dev/null) \
+        || echo "Warning: tools/include/uapi/linux/hw_breakpoint.h differs from kernel" >&2 )) || true
 	@(test -f ../../arch/x86/include/asm/disabled-features.h && ( \
         (diff -B ../arch/x86/include/asm/disabled-features.h ../../arch/x86/include/asm/disabled-features.h >/dev/null) \
         || echo "Warning: tools/arch/x86/include/asm/disabled-features.h differs from kernel" >&2 )) || true

From c7007e983682b31d91e9ad7c3e85c49ffcc3651f Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 12 Jul 2016 10:29:31 -0300
Subject: [PATCH 41/66] perf tools: Introduce weak alternative to
 sched_getcpu()

Which is just a wrapper for sys_getcpu and is not present in at least
musl libc.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-kblef7svmhr0g93kkx78envg@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/arch/x86/include/asm/unistd_32.h |  3 +++
 tools/arch/x86/include/asm/unistd_64.h |  3 +++
 tools/perf/util/cloexec.c              | 14 ++++++++++----
 tools/perf/util/util.h                 |  4 ++++
 4 files changed, 20 insertions(+), 4 deletions(-)

diff --git a/tools/arch/x86/include/asm/unistd_32.h b/tools/arch/x86/include/asm/unistd_32.h
index cf33ab09273df..88b3f8c8920ca 100644
--- a/tools/arch/x86/include/asm/unistd_32.h
+++ b/tools/arch/x86/include/asm/unistd_32.h
@@ -7,3 +7,6 @@
 #ifndef __NR_gettid
 # define __NR_gettid 224
 #endif
+#ifndef __NR_getcpu
+# define __NR_getcpu 318
+#endif
diff --git a/tools/arch/x86/include/asm/unistd_64.h b/tools/arch/x86/include/asm/unistd_64.h
index 2c9835695b56e..fbdb70ee8837e 100644
--- a/tools/arch/x86/include/asm/unistd_64.h
+++ b/tools/arch/x86/include/asm/unistd_64.h
@@ -7,3 +7,6 @@
 #ifndef __NR_gettid
 # define __NR_gettid 186
 #endif
+#ifndef __NR_getcpu
+# define __NR_getcpu 309
+#endif
diff --git a/tools/perf/util/cloexec.c b/tools/perf/util/cloexec.c
index fde772db1d5c0..f0dcd0ee0afaa 100644
--- a/tools/perf/util/cloexec.c
+++ b/tools/perf/util/cloexec.c
@@ -4,18 +4,24 @@
 #include "cloexec.h"
 #include "asm/bug.h"
 #include "debug.h"
+#include <unistd.h>
+#include <asm/unistd.h>
+#include <sys/syscall.h>
 
 static unsigned long flag = PERF_FLAG_FD_CLOEXEC;
 
-#ifdef __GLIBC_PREREQ
-#if !__GLIBC_PREREQ(2, 6)
 int __weak sched_getcpu(void)
 {
+#ifdef __NR_getcpu
+	unsigned cpu;
+	int err = syscall(__NR_getcpu, &cpu, NULL, NULL);
+	if (!err)
+		return cpu;
+#else
 	errno = ENOSYS;
+#endif
 	return -1;
 }
-#endif
-#endif
 
 static int perf_flag_probe(void)
 {
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 2370cfb902b29..d8d41ef8da576 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -361,4 +361,8 @@ void print_binary(unsigned char *data, size_t len,
 		  size_t bytes_per_line, print_binary_t printer,
 		  void *extra);
 
+#ifndef __GLIBC__
+extern int sched_getcpu(void);
+#endif
+
 #endif /* GIT_COMPAT_UTIL_H */

From a395b35d339174bc42bb22ef729a1ef67639bbb3 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 12 Jul 2016 10:30:39 -0300
Subject: [PATCH 42/66] perf tools: Remove unneeded magic.h include from util.h

Not used anymore, IIRC it was for useless PROC_FS_MAGIC procfs checks,
but those are long gone.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-v027did3kvj0vz7bofgzkw29@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/util.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index d8d41ef8da576..6178cab823749 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -72,7 +72,6 @@
 #include <sys/ioctl.h>
 #include <inttypes.h>
 #include <linux/kernel.h>
-#include <linux/magic.h>
 #include <linux/types.h>
 #include <sys/ttydefaults.h>
 #include <api/fs/tracing_path.h>

From e3e1d7e077688c81ee3326d1bf04550549b8a004 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 12 Jul 2016 10:44:40 -0300
Subject: [PATCH 43/66] perf trace: Remove unused sys/ptrace.h include

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-ogtjqc0hxm961djgiwboe2q7@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-trace.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 570a78c706c2d..b8c6766301db9 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -43,7 +43,6 @@
 #include <linux/err.h>
 #include <linux/filter.h>
 #include <linux/audit.h>
-#include <sys/ptrace.h>
 #include <linux/random.h>
 #include <linux/stringify.h>
 

From f2d3adf46d5763e7154e303e972c891999a4da43 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 12 Jul 2016 10:54:45 -0300
Subject: [PATCH 44/66] kvm arm/arm64: Remove trailing whitespace from headers

Noticed while making a copy of these files to tools/ where those kernel
files were being directly accessed, which we're not allowing anymore to
avoid that changes in the kernel side break tooling.

Cc: Christoffer Dall <christoffer.dall@linaro.org>
Cc: Eric Auger <eric.auger@linaro.org>
Cc: Marc Zyngier <marc.zyngier@arm.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-82thftcdhj2j5wt6ir4vuyhk@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 arch/arm/include/uapi/asm/kvm.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/arm/include/uapi/asm/kvm.h b/arch/arm/include/uapi/asm/kvm.h
index df3f60cb1168a..a2b3eb313a25c 100644
--- a/arch/arm/include/uapi/asm/kvm.h
+++ b/arch/arm/include/uapi/asm/kvm.h
@@ -139,8 +139,8 @@ struct kvm_arch_memory_slot {
 #define ARM_CP15_REG64(...) __ARM_CP15_REG64(__VA_ARGS__)
 
 #define KVM_REG_ARM_TIMER_CTL		ARM_CP15_REG32(0, 14, 3, 1)
-#define KVM_REG_ARM_TIMER_CNT		ARM_CP15_REG64(1, 14) 
-#define KVM_REG_ARM_TIMER_CVAL		ARM_CP15_REG64(3, 14) 
+#define KVM_REG_ARM_TIMER_CNT		ARM_CP15_REG64(1, 14)
+#define KVM_REG_ARM_TIMER_CVAL		ARM_CP15_REG64(3, 14)
 
 /* Normal registers are mapped as coprocessor 16. */
 #define KVM_REG_ARM_CORE		(0x0010 << KVM_REG_ARM_COPROC_SHIFT)

From dd7bd1093622621a910cbb6a77c7addeb20c9984 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 12 Jul 2016 10:57:25 -0300
Subject: [PATCH 45/66] tools: Copy the header files needed by perf tools

Those kernel files were being directly accessed, which we're not
allowing anymore to avoid that changes in the kernel side break tooling.

Warn if these copies drift from the original files.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Yarygin <yarygin@linux.vnet.ibm.com>
Cc: Christoffer Dall <christoffer.dall@linaro.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Eric Auger <eric.auger@linaro.org>
Cc: Hemant Kumar <hemant@linux.vnet.ibm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Marc Zyngier <marc.zyngier@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Cc: Wang Nan <wangnan0@huawei.com>
Cc: Yunlong Song <yunlong.song@huawei.com>
Link: http://lkml.kernel.org/n/tip-mnopguymhnwzjhw3mowllvsy@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/arch/arm/include/uapi/asm/kvm.h       | 224 +++++++
 tools/arch/arm64/include/uapi/asm/kvm.h     | 258 +++++++++
 tools/arch/mips/include/uapi/asm/kvm.h      | 208 +++++++
 tools/arch/powerpc/include/uapi/asm/kvm.h   | 612 ++++++++++++++++++++
 tools/arch/s390/include/uapi/asm/kvm.h      | 192 ++++++
 tools/arch/s390/include/uapi/asm/kvm_perf.h |  25 +
 tools/arch/s390/include/uapi/asm/sie.h      | 250 ++++++++
 tools/arch/x86/include/uapi/asm/kvm.h       | 360 ++++++++++++
 tools/arch/x86/include/uapi/asm/kvm_perf.h  |  16 +
 tools/arch/x86/include/uapi/asm/svm.h       | 178 ++++++
 tools/arch/x86/include/uapi/asm/vmx.h       | 136 +++++
 tools/perf/MANIFEST                         |  15 +-
 tools/perf/Makefile.perf                    |  30 +
 13 files changed, 2495 insertions(+), 9 deletions(-)
 create mode 100644 tools/arch/arm/include/uapi/asm/kvm.h
 create mode 100644 tools/arch/arm64/include/uapi/asm/kvm.h
 create mode 100644 tools/arch/mips/include/uapi/asm/kvm.h
 create mode 100644 tools/arch/powerpc/include/uapi/asm/kvm.h
 create mode 100644 tools/arch/s390/include/uapi/asm/kvm.h
 create mode 100644 tools/arch/s390/include/uapi/asm/kvm_perf.h
 create mode 100644 tools/arch/s390/include/uapi/asm/sie.h
 create mode 100644 tools/arch/x86/include/uapi/asm/kvm.h
 create mode 100644 tools/arch/x86/include/uapi/asm/kvm_perf.h
 create mode 100644 tools/arch/x86/include/uapi/asm/svm.h
 create mode 100644 tools/arch/x86/include/uapi/asm/vmx.h

diff --git a/tools/arch/arm/include/uapi/asm/kvm.h b/tools/arch/arm/include/uapi/asm/kvm.h
new file mode 100644
index 0000000000000..a2b3eb313a25c
--- /dev/null
+++ b/tools/arch/arm/include/uapi/asm/kvm.h
@@ -0,0 +1,224 @@
+/*
+ * Copyright (C) 2012 - Virtual Open Systems and Columbia University
+ * Author: Christoffer Dall <c.dall@virtualopensystems.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ */
+
+#ifndef __ARM_KVM_H__
+#define __ARM_KVM_H__
+
+#include <linux/types.h>
+#include <linux/psci.h>
+#include <asm/ptrace.h>
+
+#define __KVM_HAVE_GUEST_DEBUG
+#define __KVM_HAVE_IRQ_LINE
+#define __KVM_HAVE_READONLY_MEM
+
+#define KVM_REG_SIZE(id)						\
+	(1U << (((id) & KVM_REG_SIZE_MASK) >> KVM_REG_SIZE_SHIFT))
+
+/* Valid for svc_regs, abt_regs, und_regs, irq_regs in struct kvm_regs */
+#define KVM_ARM_SVC_sp		svc_regs[0]
+#define KVM_ARM_SVC_lr		svc_regs[1]
+#define KVM_ARM_SVC_spsr	svc_regs[2]
+#define KVM_ARM_ABT_sp		abt_regs[0]
+#define KVM_ARM_ABT_lr		abt_regs[1]
+#define KVM_ARM_ABT_spsr	abt_regs[2]
+#define KVM_ARM_UND_sp		und_regs[0]
+#define KVM_ARM_UND_lr		und_regs[1]
+#define KVM_ARM_UND_spsr	und_regs[2]
+#define KVM_ARM_IRQ_sp		irq_regs[0]
+#define KVM_ARM_IRQ_lr		irq_regs[1]
+#define KVM_ARM_IRQ_spsr	irq_regs[2]
+
+/* Valid only for fiq_regs in struct kvm_regs */
+#define KVM_ARM_FIQ_r8		fiq_regs[0]
+#define KVM_ARM_FIQ_r9		fiq_regs[1]
+#define KVM_ARM_FIQ_r10		fiq_regs[2]
+#define KVM_ARM_FIQ_fp		fiq_regs[3]
+#define KVM_ARM_FIQ_ip		fiq_regs[4]
+#define KVM_ARM_FIQ_sp		fiq_regs[5]
+#define KVM_ARM_FIQ_lr		fiq_regs[6]
+#define KVM_ARM_FIQ_spsr	fiq_regs[7]
+
+struct kvm_regs {
+	struct pt_regs usr_regs;	/* R0_usr - R14_usr, PC, CPSR */
+	unsigned long svc_regs[3];	/* SP_svc, LR_svc, SPSR_svc */
+	unsigned long abt_regs[3];	/* SP_abt, LR_abt, SPSR_abt */
+	unsigned long und_regs[3];	/* SP_und, LR_und, SPSR_und */
+	unsigned long irq_regs[3];	/* SP_irq, LR_irq, SPSR_irq */
+	unsigned long fiq_regs[8];	/* R8_fiq - R14_fiq, SPSR_fiq */
+};
+
+/* Supported Processor Types */
+#define KVM_ARM_TARGET_CORTEX_A15	0
+#define KVM_ARM_TARGET_CORTEX_A7	1
+#define KVM_ARM_NUM_TARGETS		2
+
+/* KVM_ARM_SET_DEVICE_ADDR ioctl id encoding */
+#define KVM_ARM_DEVICE_TYPE_SHIFT	0
+#define KVM_ARM_DEVICE_TYPE_MASK	(0xffff << KVM_ARM_DEVICE_TYPE_SHIFT)
+#define KVM_ARM_DEVICE_ID_SHIFT		16
+#define KVM_ARM_DEVICE_ID_MASK		(0xffff << KVM_ARM_DEVICE_ID_SHIFT)
+
+/* Supported device IDs */
+#define KVM_ARM_DEVICE_VGIC_V2		0
+
+/* Supported VGIC address types  */
+#define KVM_VGIC_V2_ADDR_TYPE_DIST	0
+#define KVM_VGIC_V2_ADDR_TYPE_CPU	1
+
+#define KVM_VGIC_V2_DIST_SIZE		0x1000
+#define KVM_VGIC_V2_CPU_SIZE		0x2000
+
+#define KVM_ARM_VCPU_POWER_OFF		0 /* CPU is started in OFF state */
+#define KVM_ARM_VCPU_PSCI_0_2		1 /* CPU uses PSCI v0.2 */
+
+struct kvm_vcpu_init {
+	__u32 target;
+	__u32 features[7];
+};
+
+struct kvm_sregs {
+};
+
+struct kvm_fpu {
+};
+
+struct kvm_guest_debug_arch {
+};
+
+struct kvm_debug_exit_arch {
+};
+
+struct kvm_sync_regs {
+};
+
+struct kvm_arch_memory_slot {
+};
+
+/* If you need to interpret the index values, here is the key: */
+#define KVM_REG_ARM_COPROC_MASK		0x000000000FFF0000
+#define KVM_REG_ARM_COPROC_SHIFT	16
+#define KVM_REG_ARM_32_OPC2_MASK	0x0000000000000007
+#define KVM_REG_ARM_32_OPC2_SHIFT	0
+#define KVM_REG_ARM_OPC1_MASK		0x0000000000000078
+#define KVM_REG_ARM_OPC1_SHIFT		3
+#define KVM_REG_ARM_CRM_MASK		0x0000000000000780
+#define KVM_REG_ARM_CRM_SHIFT		7
+#define KVM_REG_ARM_32_CRN_MASK		0x0000000000007800
+#define KVM_REG_ARM_32_CRN_SHIFT	11
+
+#define ARM_CP15_REG_SHIFT_MASK(x,n) \
+	(((x) << KVM_REG_ARM_ ## n ## _SHIFT) & KVM_REG_ARM_ ## n ## _MASK)
+
+#define __ARM_CP15_REG(op1,crn,crm,op2) \
+	(KVM_REG_ARM | (15 << KVM_REG_ARM_COPROC_SHIFT) | \
+	ARM_CP15_REG_SHIFT_MASK(op1, OPC1) | \
+	ARM_CP15_REG_SHIFT_MASK(crn, 32_CRN) | \
+	ARM_CP15_REG_SHIFT_MASK(crm, CRM) | \
+	ARM_CP15_REG_SHIFT_MASK(op2, 32_OPC2))
+
+#define ARM_CP15_REG32(...) (__ARM_CP15_REG(__VA_ARGS__) | KVM_REG_SIZE_U32)
+
+#define __ARM_CP15_REG64(op1,crm) \
+	(__ARM_CP15_REG(op1, 0, crm, 0) | KVM_REG_SIZE_U64)
+#define ARM_CP15_REG64(...) __ARM_CP15_REG64(__VA_ARGS__)
+
+#define KVM_REG_ARM_TIMER_CTL		ARM_CP15_REG32(0, 14, 3, 1)
+#define KVM_REG_ARM_TIMER_CNT		ARM_CP15_REG64(1, 14)
+#define KVM_REG_ARM_TIMER_CVAL		ARM_CP15_REG64(3, 14)
+
+/* Normal registers are mapped as coprocessor 16. */
+#define KVM_REG_ARM_CORE		(0x0010 << KVM_REG_ARM_COPROC_SHIFT)
+#define KVM_REG_ARM_CORE_REG(name)	(offsetof(struct kvm_regs, name) / 4)
+
+/* Some registers need more space to represent values. */
+#define KVM_REG_ARM_DEMUX		(0x0011 << KVM_REG_ARM_COPROC_SHIFT)
+#define KVM_REG_ARM_DEMUX_ID_MASK	0x000000000000FF00
+#define KVM_REG_ARM_DEMUX_ID_SHIFT	8
+#define KVM_REG_ARM_DEMUX_ID_CCSIDR	(0x00 << KVM_REG_ARM_DEMUX_ID_SHIFT)
+#define KVM_REG_ARM_DEMUX_VAL_MASK	0x00000000000000FF
+#define KVM_REG_ARM_DEMUX_VAL_SHIFT	0
+
+/* VFP registers: we could overload CP10 like ARM does, but that's ugly. */
+#define KVM_REG_ARM_VFP			(0x0012 << KVM_REG_ARM_COPROC_SHIFT)
+#define KVM_REG_ARM_VFP_MASK		0x000000000000FFFF
+#define KVM_REG_ARM_VFP_BASE_REG	0x0
+#define KVM_REG_ARM_VFP_FPSID		0x1000
+#define KVM_REG_ARM_VFP_FPSCR		0x1001
+#define KVM_REG_ARM_VFP_MVFR1		0x1006
+#define KVM_REG_ARM_VFP_MVFR0		0x1007
+#define KVM_REG_ARM_VFP_FPEXC		0x1008
+#define KVM_REG_ARM_VFP_FPINST		0x1009
+#define KVM_REG_ARM_VFP_FPINST2		0x100A
+
+/* Device Control API: ARM VGIC */
+#define KVM_DEV_ARM_VGIC_GRP_ADDR	0
+#define KVM_DEV_ARM_VGIC_GRP_DIST_REGS	1
+#define KVM_DEV_ARM_VGIC_GRP_CPU_REGS	2
+#define   KVM_DEV_ARM_VGIC_CPUID_SHIFT	32
+#define   KVM_DEV_ARM_VGIC_CPUID_MASK	(0xffULL << KVM_DEV_ARM_VGIC_CPUID_SHIFT)
+#define   KVM_DEV_ARM_VGIC_OFFSET_SHIFT	0
+#define   KVM_DEV_ARM_VGIC_OFFSET_MASK	(0xffffffffULL << KVM_DEV_ARM_VGIC_OFFSET_SHIFT)
+#define KVM_DEV_ARM_VGIC_GRP_NR_IRQS	3
+#define KVM_DEV_ARM_VGIC_GRP_CTRL       4
+#define   KVM_DEV_ARM_VGIC_CTRL_INIT    0
+
+/* KVM_IRQ_LINE irq field index values */
+#define KVM_ARM_IRQ_TYPE_SHIFT		24
+#define KVM_ARM_IRQ_TYPE_MASK		0xff
+#define KVM_ARM_IRQ_VCPU_SHIFT		16
+#define KVM_ARM_IRQ_VCPU_MASK		0xff
+#define KVM_ARM_IRQ_NUM_SHIFT		0
+#define KVM_ARM_IRQ_NUM_MASK		0xffff
+
+/* irq_type field */
+#define KVM_ARM_IRQ_TYPE_CPU		0
+#define KVM_ARM_IRQ_TYPE_SPI		1
+#define KVM_ARM_IRQ_TYPE_PPI		2
+
+/* out-of-kernel GIC cpu interrupt injection irq_number field */
+#define KVM_ARM_IRQ_CPU_IRQ		0
+#define KVM_ARM_IRQ_CPU_FIQ		1
+
+/*
+ * This used to hold the highest supported SPI, but it is now obsolete
+ * and only here to provide source code level compatibility with older
+ * userland. The highest SPI number can be set via KVM_DEV_ARM_VGIC_GRP_NR_IRQS.
+ */
+#ifndef __KERNEL__
+#define KVM_ARM_IRQ_GIC_MAX		127
+#endif
+
+/* One single KVM irqchip, ie. the VGIC */
+#define KVM_NR_IRQCHIPS          1
+
+/* PSCI interface */
+#define KVM_PSCI_FN_BASE		0x95c1ba5e
+#define KVM_PSCI_FN(n)			(KVM_PSCI_FN_BASE + (n))
+
+#define KVM_PSCI_FN_CPU_SUSPEND		KVM_PSCI_FN(0)
+#define KVM_PSCI_FN_CPU_OFF		KVM_PSCI_FN(1)
+#define KVM_PSCI_FN_CPU_ON		KVM_PSCI_FN(2)
+#define KVM_PSCI_FN_MIGRATE		KVM_PSCI_FN(3)
+
+#define KVM_PSCI_RET_SUCCESS		PSCI_RET_SUCCESS
+#define KVM_PSCI_RET_NI			PSCI_RET_NOT_SUPPORTED
+#define KVM_PSCI_RET_INVAL		PSCI_RET_INVALID_PARAMS
+#define KVM_PSCI_RET_DENIED		PSCI_RET_DENIED
+
+#endif /* __ARM_KVM_H__ */
diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h
new file mode 100644
index 0000000000000..f209ea151dca8
--- /dev/null
+++ b/tools/arch/arm64/include/uapi/asm/kvm.h
@@ -0,0 +1,258 @@
+/*
+ * Copyright (C) 2012,2013 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * Derived from arch/arm/include/uapi/asm/kvm.h:
+ * Copyright (C) 2012 - Virtual Open Systems and Columbia University
+ * Author: Christoffer Dall <c.dall@virtualopensystems.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __ARM_KVM_H__
+#define __ARM_KVM_H__
+
+#define KVM_SPSR_EL1	0
+#define KVM_SPSR_SVC	KVM_SPSR_EL1
+#define KVM_SPSR_ABT	1
+#define KVM_SPSR_UND	2
+#define KVM_SPSR_IRQ	3
+#define KVM_SPSR_FIQ	4
+#define KVM_NR_SPSR	5
+
+#ifndef __ASSEMBLY__
+#include <linux/psci.h>
+#include <linux/types.h>
+#include <asm/ptrace.h>
+
+#define __KVM_HAVE_GUEST_DEBUG
+#define __KVM_HAVE_IRQ_LINE
+#define __KVM_HAVE_READONLY_MEM
+
+#define KVM_REG_SIZE(id)						\
+	(1U << (((id) & KVM_REG_SIZE_MASK) >> KVM_REG_SIZE_SHIFT))
+
+struct kvm_regs {
+	struct user_pt_regs regs;	/* sp = sp_el0 */
+
+	__u64	sp_el1;
+	__u64	elr_el1;
+
+	__u64	spsr[KVM_NR_SPSR];
+
+	struct user_fpsimd_state fp_regs;
+};
+
+/*
+ * Supported CPU Targets - Adding a new target type is not recommended,
+ * unless there are some special registers not supported by the
+ * genericv8 syreg table.
+ */
+#define KVM_ARM_TARGET_AEM_V8		0
+#define KVM_ARM_TARGET_FOUNDATION_V8	1
+#define KVM_ARM_TARGET_CORTEX_A57	2
+#define KVM_ARM_TARGET_XGENE_POTENZA	3
+#define KVM_ARM_TARGET_CORTEX_A53	4
+/* Generic ARM v8 target */
+#define KVM_ARM_TARGET_GENERIC_V8	5
+
+#define KVM_ARM_NUM_TARGETS		6
+
+/* KVM_ARM_SET_DEVICE_ADDR ioctl id encoding */
+#define KVM_ARM_DEVICE_TYPE_SHIFT	0
+#define KVM_ARM_DEVICE_TYPE_MASK	(0xffff << KVM_ARM_DEVICE_TYPE_SHIFT)
+#define KVM_ARM_DEVICE_ID_SHIFT		16
+#define KVM_ARM_DEVICE_ID_MASK		(0xffff << KVM_ARM_DEVICE_ID_SHIFT)
+
+/* Supported device IDs */
+#define KVM_ARM_DEVICE_VGIC_V2		0
+
+/* Supported VGIC address types  */
+#define KVM_VGIC_V2_ADDR_TYPE_DIST	0
+#define KVM_VGIC_V2_ADDR_TYPE_CPU	1
+
+#define KVM_VGIC_V2_DIST_SIZE		0x1000
+#define KVM_VGIC_V2_CPU_SIZE		0x2000
+
+/* Supported VGICv3 address types  */
+#define KVM_VGIC_V3_ADDR_TYPE_DIST	2
+#define KVM_VGIC_V3_ADDR_TYPE_REDIST	3
+
+#define KVM_VGIC_V3_DIST_SIZE		SZ_64K
+#define KVM_VGIC_V3_REDIST_SIZE		(2 * SZ_64K)
+
+#define KVM_ARM_VCPU_POWER_OFF		0 /* CPU is started in OFF state */
+#define KVM_ARM_VCPU_EL1_32BIT		1 /* CPU running a 32bit VM */
+#define KVM_ARM_VCPU_PSCI_0_2		2 /* CPU uses PSCI v0.2 */
+#define KVM_ARM_VCPU_PMU_V3		3 /* Support guest PMUv3 */
+
+struct kvm_vcpu_init {
+	__u32 target;
+	__u32 features[7];
+};
+
+struct kvm_sregs {
+};
+
+struct kvm_fpu {
+};
+
+/*
+ * See v8 ARM ARM D7.3: Debug Registers
+ *
+ * The architectural limit is 16 debug registers of each type although
+ * in practice there are usually less (see ID_AA64DFR0_EL1).
+ *
+ * Although the control registers are architecturally defined as 32
+ * bits wide we use a 64 bit structure here to keep parity with
+ * KVM_GET/SET_ONE_REG behaviour which treats all system registers as
+ * 64 bit values. It also allows for the possibility of the
+ * architecture expanding the control registers without having to
+ * change the userspace ABI.
+ */
+#define KVM_ARM_MAX_DBG_REGS 16
+struct kvm_guest_debug_arch {
+	__u64 dbg_bcr[KVM_ARM_MAX_DBG_REGS];
+	__u64 dbg_bvr[KVM_ARM_MAX_DBG_REGS];
+	__u64 dbg_wcr[KVM_ARM_MAX_DBG_REGS];
+	__u64 dbg_wvr[KVM_ARM_MAX_DBG_REGS];
+};
+
+struct kvm_debug_exit_arch {
+	__u32 hsr;
+	__u64 far;	/* used for watchpoints */
+};
+
+/*
+ * Architecture specific defines for kvm_guest_debug->control
+ */
+
+#define KVM_GUESTDBG_USE_SW_BP		(1 << 16)
+#define KVM_GUESTDBG_USE_HW		(1 << 17)
+
+struct kvm_sync_regs {
+};
+
+struct kvm_arch_memory_slot {
+};
+
+/* If you need to interpret the index values, here is the key: */
+#define KVM_REG_ARM_COPROC_MASK		0x000000000FFF0000
+#define KVM_REG_ARM_COPROC_SHIFT	16
+
+/* Normal registers are mapped as coprocessor 16. */
+#define KVM_REG_ARM_CORE		(0x0010 << KVM_REG_ARM_COPROC_SHIFT)
+#define KVM_REG_ARM_CORE_REG(name)	(offsetof(struct kvm_regs, name) / sizeof(__u32))
+
+/* Some registers need more space to represent values. */
+#define KVM_REG_ARM_DEMUX		(0x0011 << KVM_REG_ARM_COPROC_SHIFT)
+#define KVM_REG_ARM_DEMUX_ID_MASK	0x000000000000FF00
+#define KVM_REG_ARM_DEMUX_ID_SHIFT	8
+#define KVM_REG_ARM_DEMUX_ID_CCSIDR	(0x00 << KVM_REG_ARM_DEMUX_ID_SHIFT)
+#define KVM_REG_ARM_DEMUX_VAL_MASK	0x00000000000000FF
+#define KVM_REG_ARM_DEMUX_VAL_SHIFT	0
+
+/* AArch64 system registers */
+#define KVM_REG_ARM64_SYSREG		(0x0013 << KVM_REG_ARM_COPROC_SHIFT)
+#define KVM_REG_ARM64_SYSREG_OP0_MASK	0x000000000000c000
+#define KVM_REG_ARM64_SYSREG_OP0_SHIFT	14
+#define KVM_REG_ARM64_SYSREG_OP1_MASK	0x0000000000003800
+#define KVM_REG_ARM64_SYSREG_OP1_SHIFT	11
+#define KVM_REG_ARM64_SYSREG_CRN_MASK	0x0000000000000780
+#define KVM_REG_ARM64_SYSREG_CRN_SHIFT	7
+#define KVM_REG_ARM64_SYSREG_CRM_MASK	0x0000000000000078
+#define KVM_REG_ARM64_SYSREG_CRM_SHIFT	3
+#define KVM_REG_ARM64_SYSREG_OP2_MASK	0x0000000000000007
+#define KVM_REG_ARM64_SYSREG_OP2_SHIFT	0
+
+#define ARM64_SYS_REG_SHIFT_MASK(x,n) \
+	(((x) << KVM_REG_ARM64_SYSREG_ ## n ## _SHIFT) & \
+	KVM_REG_ARM64_SYSREG_ ## n ## _MASK)
+
+#define __ARM64_SYS_REG(op0,op1,crn,crm,op2) \
+	(KVM_REG_ARM64 | KVM_REG_ARM64_SYSREG | \
+	ARM64_SYS_REG_SHIFT_MASK(op0, OP0) | \
+	ARM64_SYS_REG_SHIFT_MASK(op1, OP1) | \
+	ARM64_SYS_REG_SHIFT_MASK(crn, CRN) | \
+	ARM64_SYS_REG_SHIFT_MASK(crm, CRM) | \
+	ARM64_SYS_REG_SHIFT_MASK(op2, OP2))
+
+#define ARM64_SYS_REG(...) (__ARM64_SYS_REG(__VA_ARGS__) | KVM_REG_SIZE_U64)
+
+#define KVM_REG_ARM_TIMER_CTL		ARM64_SYS_REG(3, 3, 14, 3, 1)
+#define KVM_REG_ARM_TIMER_CNT		ARM64_SYS_REG(3, 3, 14, 3, 2)
+#define KVM_REG_ARM_TIMER_CVAL		ARM64_SYS_REG(3, 3, 14, 0, 2)
+
+/* Device Control API: ARM VGIC */
+#define KVM_DEV_ARM_VGIC_GRP_ADDR	0
+#define KVM_DEV_ARM_VGIC_GRP_DIST_REGS	1
+#define KVM_DEV_ARM_VGIC_GRP_CPU_REGS	2
+#define   KVM_DEV_ARM_VGIC_CPUID_SHIFT	32
+#define   KVM_DEV_ARM_VGIC_CPUID_MASK	(0xffULL << KVM_DEV_ARM_VGIC_CPUID_SHIFT)
+#define   KVM_DEV_ARM_VGIC_OFFSET_SHIFT	0
+#define   KVM_DEV_ARM_VGIC_OFFSET_MASK	(0xffffffffULL << KVM_DEV_ARM_VGIC_OFFSET_SHIFT)
+#define KVM_DEV_ARM_VGIC_GRP_NR_IRQS	3
+#define KVM_DEV_ARM_VGIC_GRP_CTRL	4
+#define   KVM_DEV_ARM_VGIC_CTRL_INIT	0
+
+/* Device Control API on vcpu fd */
+#define KVM_ARM_VCPU_PMU_V3_CTRL	0
+#define   KVM_ARM_VCPU_PMU_V3_IRQ	0
+#define   KVM_ARM_VCPU_PMU_V3_INIT	1
+
+/* KVM_IRQ_LINE irq field index values */
+#define KVM_ARM_IRQ_TYPE_SHIFT		24
+#define KVM_ARM_IRQ_TYPE_MASK		0xff
+#define KVM_ARM_IRQ_VCPU_SHIFT		16
+#define KVM_ARM_IRQ_VCPU_MASK		0xff
+#define KVM_ARM_IRQ_NUM_SHIFT		0
+#define KVM_ARM_IRQ_NUM_MASK		0xffff
+
+/* irq_type field */
+#define KVM_ARM_IRQ_TYPE_CPU		0
+#define KVM_ARM_IRQ_TYPE_SPI		1
+#define KVM_ARM_IRQ_TYPE_PPI		2
+
+/* out-of-kernel GIC cpu interrupt injection irq_number field */
+#define KVM_ARM_IRQ_CPU_IRQ		0
+#define KVM_ARM_IRQ_CPU_FIQ		1
+
+/*
+ * This used to hold the highest supported SPI, but it is now obsolete
+ * and only here to provide source code level compatibility with older
+ * userland. The highest SPI number can be set via KVM_DEV_ARM_VGIC_GRP_NR_IRQS.
+ */
+#ifndef __KERNEL__
+#define KVM_ARM_IRQ_GIC_MAX		127
+#endif
+
+/* One single KVM irqchip, ie. the VGIC */
+#define KVM_NR_IRQCHIPS          1
+
+/* PSCI interface */
+#define KVM_PSCI_FN_BASE		0x95c1ba5e
+#define KVM_PSCI_FN(n)			(KVM_PSCI_FN_BASE + (n))
+
+#define KVM_PSCI_FN_CPU_SUSPEND		KVM_PSCI_FN(0)
+#define KVM_PSCI_FN_CPU_OFF		KVM_PSCI_FN(1)
+#define KVM_PSCI_FN_CPU_ON		KVM_PSCI_FN(2)
+#define KVM_PSCI_FN_MIGRATE		KVM_PSCI_FN(3)
+
+#define KVM_PSCI_RET_SUCCESS		PSCI_RET_SUCCESS
+#define KVM_PSCI_RET_NI			PSCI_RET_NOT_SUPPORTED
+#define KVM_PSCI_RET_INVAL		PSCI_RET_INVALID_PARAMS
+#define KVM_PSCI_RET_DENIED		PSCI_RET_DENIED
+
+#endif
+
+#endif /* __ARM_KVM_H__ */
diff --git a/tools/arch/mips/include/uapi/asm/kvm.h b/tools/arch/mips/include/uapi/asm/kvm.h
new file mode 100644
index 0000000000000..6985eb59b0853
--- /dev/null
+++ b/tools/arch/mips/include/uapi/asm/kvm.h
@@ -0,0 +1,208 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 2012  MIPS Technologies, Inc.  All rights reserved.
+ * Copyright (C) 2013 Cavium, Inc.
+ * Authors: Sanjay Lal <sanjayl@kymasys.com>
+ */
+
+#ifndef __LINUX_KVM_MIPS_H
+#define __LINUX_KVM_MIPS_H
+
+#include <linux/types.h>
+
+/*
+ * KVM MIPS specific structures and definitions.
+ *
+ * Some parts derived from the x86 version of this file.
+ */
+
+/*
+ * for KVM_GET_REGS and KVM_SET_REGS
+ *
+ * If Config[AT] is zero (32-bit CPU), the register contents are
+ * stored in the lower 32-bits of the struct kvm_regs fields and sign
+ * extended to 64-bits.
+ */
+struct kvm_regs {
+	/* out (KVM_GET_REGS) / in (KVM_SET_REGS) */
+	__u64 gpr[32];
+	__u64 hi;
+	__u64 lo;
+	__u64 pc;
+};
+
+/*
+ * for KVM_GET_FPU and KVM_SET_FPU
+ */
+struct kvm_fpu {
+};
+
+
+/*
+ * For MIPS, we use KVM_SET_ONE_REG and KVM_GET_ONE_REG to access various
+ * registers.  The id field is broken down as follows:
+ *
+ *  bits[63..52] - As per linux/kvm.h
+ *  bits[51..32] - Must be zero.
+ *  bits[31..16] - Register set.
+ *
+ * Register set = 0: GP registers from kvm_regs (see definitions below).
+ *
+ * Register set = 1: CP0 registers.
+ *  bits[15..8]  - Must be zero.
+ *  bits[7..3]   - Register 'rd'  index.
+ *  bits[2..0]   - Register 'sel' index.
+ *
+ * Register set = 2: KVM specific registers (see definitions below).
+ *
+ * Register set = 3: FPU / MSA registers (see definitions below).
+ *
+ * Other sets registers may be added in the future.  Each set would
+ * have its own identifier in bits[31..16].
+ */
+
+#define KVM_REG_MIPS_GP		(KVM_REG_MIPS | 0x0000000000000000ULL)
+#define KVM_REG_MIPS_CP0	(KVM_REG_MIPS | 0x0000000000010000ULL)
+#define KVM_REG_MIPS_KVM	(KVM_REG_MIPS | 0x0000000000020000ULL)
+#define KVM_REG_MIPS_FPU	(KVM_REG_MIPS | 0x0000000000030000ULL)
+
+
+/*
+ * KVM_REG_MIPS_GP - General purpose registers from kvm_regs.
+ */
+
+#define KVM_REG_MIPS_R0		(KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 |  0)
+#define KVM_REG_MIPS_R1		(KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 |  1)
+#define KVM_REG_MIPS_R2		(KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 |  2)
+#define KVM_REG_MIPS_R3		(KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 |  3)
+#define KVM_REG_MIPS_R4		(KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 |  4)
+#define KVM_REG_MIPS_R5		(KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 |  5)
+#define KVM_REG_MIPS_R6		(KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 |  6)
+#define KVM_REG_MIPS_R7		(KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 |  7)
+#define KVM_REG_MIPS_R8		(KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 |  8)
+#define KVM_REG_MIPS_R9		(KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 |  9)
+#define KVM_REG_MIPS_R10	(KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 10)
+#define KVM_REG_MIPS_R11	(KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 11)
+#define KVM_REG_MIPS_R12	(KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 12)
+#define KVM_REG_MIPS_R13	(KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 13)
+#define KVM_REG_MIPS_R14	(KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 14)
+#define KVM_REG_MIPS_R15	(KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 15)
+#define KVM_REG_MIPS_R16	(KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 16)
+#define KVM_REG_MIPS_R17	(KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 17)
+#define KVM_REG_MIPS_R18	(KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 18)
+#define KVM_REG_MIPS_R19	(KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 19)
+#define KVM_REG_MIPS_R20	(KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 20)
+#define KVM_REG_MIPS_R21	(KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 21)
+#define KVM_REG_MIPS_R22	(KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 22)
+#define KVM_REG_MIPS_R23	(KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 23)
+#define KVM_REG_MIPS_R24	(KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 24)
+#define KVM_REG_MIPS_R25	(KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 25)
+#define KVM_REG_MIPS_R26	(KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 26)
+#define KVM_REG_MIPS_R27	(KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 27)
+#define KVM_REG_MIPS_R28	(KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 28)
+#define KVM_REG_MIPS_R29	(KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 29)
+#define KVM_REG_MIPS_R30	(KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 30)
+#define KVM_REG_MIPS_R31	(KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 31)
+
+#define KVM_REG_MIPS_HI		(KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 32)
+#define KVM_REG_MIPS_LO		(KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 33)
+#define KVM_REG_MIPS_PC		(KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 34)
+
+
+/*
+ * KVM_REG_MIPS_KVM - KVM specific control registers.
+ */
+
+/*
+ * CP0_Count control
+ * DC:    Set 0: Master disable CP0_Count and set COUNT_RESUME to now
+ *        Set 1: Master re-enable CP0_Count with unchanged bias, handling timer
+ *               interrupts since COUNT_RESUME
+ *        This can be used to freeze the timer to get a consistent snapshot of
+ *        the CP0_Count and timer interrupt pending state, while also resuming
+ *        safely without losing time or guest timer interrupts.
+ * Other: Reserved, do not change.
+ */
+#define KVM_REG_MIPS_COUNT_CTL	    (KVM_REG_MIPS_KVM | KVM_REG_SIZE_U64 | 0)
+#define KVM_REG_MIPS_COUNT_CTL_DC	0x00000001
+
+/*
+ * CP0_Count resume monotonic nanoseconds
+ * The monotonic nanosecond time of the last set of COUNT_CTL.DC (master
+ * disable). Any reads and writes of Count related registers while
+ * COUNT_CTL.DC=1 will appear to occur at this time. When COUNT_CTL.DC is
+ * cleared again (master enable) any timer interrupts since this time will be
+ * emulated.
+ * Modifications to times in the future are rejected.
+ */
+#define KVM_REG_MIPS_COUNT_RESUME   (KVM_REG_MIPS_KVM | KVM_REG_SIZE_U64 | 1)
+/*
+ * CP0_Count rate in Hz
+ * Specifies the rate of the CP0_Count timer in Hz. Modifications occur without
+ * discontinuities in CP0_Count.
+ */
+#define KVM_REG_MIPS_COUNT_HZ	    (KVM_REG_MIPS_KVM | KVM_REG_SIZE_U64 | 2)
+
+
+/*
+ * KVM_REG_MIPS_FPU - Floating Point and MIPS SIMD Architecture (MSA) registers.
+ *
+ *  bits[15..8]  - Register subset (see definitions below).
+ *  bits[7..5]   - Must be zero.
+ *  bits[4..0]   - Register number within register subset.
+ */
+
+#define KVM_REG_MIPS_FPR	(KVM_REG_MIPS_FPU | 0x0000000000000000ULL)
+#define KVM_REG_MIPS_FCR	(KVM_REG_MIPS_FPU | 0x0000000000000100ULL)
+#define KVM_REG_MIPS_MSACR	(KVM_REG_MIPS_FPU | 0x0000000000000200ULL)
+
+/*
+ * KVM_REG_MIPS_FPR - Floating point / Vector registers.
+ */
+#define KVM_REG_MIPS_FPR_32(n)	(KVM_REG_MIPS_FPR | KVM_REG_SIZE_U32  | (n))
+#define KVM_REG_MIPS_FPR_64(n)	(KVM_REG_MIPS_FPR | KVM_REG_SIZE_U64  | (n))
+#define KVM_REG_MIPS_VEC_128(n)	(KVM_REG_MIPS_FPR | KVM_REG_SIZE_U128 | (n))
+
+/*
+ * KVM_REG_MIPS_FCR - Floating point control registers.
+ */
+#define KVM_REG_MIPS_FCR_IR	(KVM_REG_MIPS_FCR | KVM_REG_SIZE_U32 |  0)
+#define KVM_REG_MIPS_FCR_CSR	(KVM_REG_MIPS_FCR | KVM_REG_SIZE_U32 | 31)
+
+/*
+ * KVM_REG_MIPS_MSACR - MIPS SIMD Architecture (MSA) control registers.
+ */
+#define KVM_REG_MIPS_MSA_IR	 (KVM_REG_MIPS_MSACR | KVM_REG_SIZE_U32 |  0)
+#define KVM_REG_MIPS_MSA_CSR	 (KVM_REG_MIPS_MSACR | KVM_REG_SIZE_U32 |  1)
+
+
+/*
+ * KVM MIPS specific structures and definitions
+ *
+ */
+struct kvm_debug_exit_arch {
+	__u64 epc;
+};
+
+/* for KVM_SET_GUEST_DEBUG */
+struct kvm_guest_debug_arch {
+};
+
+/* definition of registers in kvm_run */
+struct kvm_sync_regs {
+};
+
+/* dummy definition */
+struct kvm_sregs {
+};
+
+struct kvm_mips_interrupt {
+	/* in */
+	__u32 cpu;
+	__u32 irq;
+};
+
+#endif /* __LINUX_KVM_MIPS_H */
diff --git a/tools/arch/powerpc/include/uapi/asm/kvm.h b/tools/arch/powerpc/include/uapi/asm/kvm.h
new file mode 100644
index 0000000000000..c93cf35ce3795
--- /dev/null
+++ b/tools/arch/powerpc/include/uapi/asm/kvm.h
@@ -0,0 +1,612 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ *
+ * Copyright IBM Corp. 2007
+ *
+ * Authors: Hollis Blanchard <hollisb@us.ibm.com>
+ */
+
+#ifndef __LINUX_KVM_POWERPC_H
+#define __LINUX_KVM_POWERPC_H
+
+#include <linux/types.h>
+
+/* Select powerpc specific features in <linux/kvm.h> */
+#define __KVM_HAVE_SPAPR_TCE
+#define __KVM_HAVE_PPC_SMT
+#define __KVM_HAVE_IRQCHIP
+#define __KVM_HAVE_IRQ_LINE
+#define __KVM_HAVE_GUEST_DEBUG
+
+struct kvm_regs {
+	__u64 pc;
+	__u64 cr;
+	__u64 ctr;
+	__u64 lr;
+	__u64 xer;
+	__u64 msr;
+	__u64 srr0;
+	__u64 srr1;
+	__u64 pid;
+
+	__u64 sprg0;
+	__u64 sprg1;
+	__u64 sprg2;
+	__u64 sprg3;
+	__u64 sprg4;
+	__u64 sprg5;
+	__u64 sprg6;
+	__u64 sprg7;
+
+	__u64 gpr[32];
+};
+
+#define KVM_SREGS_E_IMPL_NONE	0
+#define KVM_SREGS_E_IMPL_FSL	1
+
+#define KVM_SREGS_E_FSL_PIDn	(1 << 0) /* PID1/PID2 */
+
+/*
+ * Feature bits indicate which sections of the sregs struct are valid,
+ * both in KVM_GET_SREGS and KVM_SET_SREGS.  On KVM_SET_SREGS, registers
+ * corresponding to unset feature bits will not be modified.  This allows
+ * restoring a checkpoint made without that feature, while keeping the
+ * default values of the new registers.
+ *
+ * KVM_SREGS_E_BASE contains:
+ * CSRR0/1 (refers to SRR2/3 on 40x)
+ * ESR
+ * DEAR
+ * MCSR
+ * TSR
+ * TCR
+ * DEC
+ * TB
+ * VRSAVE (USPRG0)
+ */
+#define KVM_SREGS_E_BASE		(1 << 0)
+
+/*
+ * KVM_SREGS_E_ARCH206 contains:
+ *
+ * PIR
+ * MCSRR0/1
+ * DECAR
+ * IVPR
+ */
+#define KVM_SREGS_E_ARCH206		(1 << 1)
+
+/*
+ * Contains EPCR, plus the upper half of 64-bit registers
+ * that are 32-bit on 32-bit implementations.
+ */
+#define KVM_SREGS_E_64			(1 << 2)
+
+#define KVM_SREGS_E_SPRG8		(1 << 3)
+#define KVM_SREGS_E_MCIVPR		(1 << 4)
+
+/*
+ * IVORs are used -- contains IVOR0-15, plus additional IVORs
+ * in combination with an appropriate feature bit.
+ */
+#define KVM_SREGS_E_IVOR		(1 << 5)
+
+/*
+ * Contains MAS0-4, MAS6-7, TLBnCFG, MMUCFG.
+ * Also TLBnPS if MMUCFG[MAVN] = 1.
+ */
+#define KVM_SREGS_E_ARCH206_MMU		(1 << 6)
+
+/* DBSR, DBCR, IAC, DAC, DVC */
+#define KVM_SREGS_E_DEBUG		(1 << 7)
+
+/* Enhanced debug -- DSRR0/1, SPRG9 */
+#define KVM_SREGS_E_ED			(1 << 8)
+
+/* Embedded Floating Point (SPE) -- IVOR32-34 if KVM_SREGS_E_IVOR */
+#define KVM_SREGS_E_SPE			(1 << 9)
+
+/*
+ * DEPRECATED! USE ONE_REG FOR THIS ONE!
+ * External Proxy (EXP) -- EPR
+ */
+#define KVM_SREGS_EXP			(1 << 10)
+
+/* External PID (E.PD) -- EPSC/EPLC */
+#define KVM_SREGS_E_PD			(1 << 11)
+
+/* Processor Control (E.PC) -- IVOR36-37 if KVM_SREGS_E_IVOR */
+#define KVM_SREGS_E_PC			(1 << 12)
+
+/* Page table (E.PT) -- EPTCFG */
+#define KVM_SREGS_E_PT			(1 << 13)
+
+/* Embedded Performance Monitor (E.PM) -- IVOR35 if KVM_SREGS_E_IVOR */
+#define KVM_SREGS_E_PM			(1 << 14)
+
+/*
+ * Special updates:
+ *
+ * Some registers may change even while a vcpu is not running.
+ * To avoid losing these changes, by default these registers are
+ * not updated by KVM_SET_SREGS.  To force an update, set the bit
+ * in u.e.update_special corresponding to the register to be updated.
+ *
+ * The update_special field is zero on return from KVM_GET_SREGS.
+ *
+ * When restoring a checkpoint, the caller can set update_special
+ * to 0xffffffff to ensure that everything is restored, even new features
+ * that the caller doesn't know about.
+ */
+#define KVM_SREGS_E_UPDATE_MCSR		(1 << 0)
+#define KVM_SREGS_E_UPDATE_TSR		(1 << 1)
+#define KVM_SREGS_E_UPDATE_DEC		(1 << 2)
+#define KVM_SREGS_E_UPDATE_DBSR		(1 << 3)
+
+/*
+ * In KVM_SET_SREGS, reserved/pad fields must be left untouched from a
+ * previous KVM_GET_REGS.
+ *
+ * Unless otherwise indicated, setting any register with KVM_SET_SREGS
+ * directly sets its value.  It does not trigger any special semantics such
+ * as write-one-to-clear.  Calling KVM_SET_SREGS on an unmodified struct
+ * just received from KVM_GET_SREGS is always a no-op.
+ */
+struct kvm_sregs {
+	__u32 pvr;
+	union {
+		struct {
+			__u64 sdr1;
+			struct {
+				struct {
+					__u64 slbe;
+					__u64 slbv;
+				} slb[64];
+			} ppc64;
+			struct {
+				__u32 sr[16];
+				__u64 ibat[8];
+				__u64 dbat[8];
+			} ppc32;
+		} s;
+		struct {
+			union {
+				struct { /* KVM_SREGS_E_IMPL_FSL */
+					__u32 features; /* KVM_SREGS_E_FSL_ */
+					__u32 svr;
+					__u64 mcar;
+					__u32 hid0;
+
+					/* KVM_SREGS_E_FSL_PIDn */
+					__u32 pid1, pid2;
+				} fsl;
+				__u8 pad[256];
+			} impl;
+
+			__u32 features; /* KVM_SREGS_E_ */
+			__u32 impl_id;	/* KVM_SREGS_E_IMPL_ */
+			__u32 update_special; /* KVM_SREGS_E_UPDATE_ */
+			__u32 pir;	/* read-only */
+			__u64 sprg8;
+			__u64 sprg9;	/* E.ED */
+			__u64 csrr0;
+			__u64 dsrr0;	/* E.ED */
+			__u64 mcsrr0;
+			__u32 csrr1;
+			__u32 dsrr1;	/* E.ED */
+			__u32 mcsrr1;
+			__u32 esr;
+			__u64 dear;
+			__u64 ivpr;
+			__u64 mcivpr;
+			__u64 mcsr;	/* KVM_SREGS_E_UPDATE_MCSR */
+
+			__u32 tsr;	/* KVM_SREGS_E_UPDATE_TSR */
+			__u32 tcr;
+			__u32 decar;
+			__u32 dec;	/* KVM_SREGS_E_UPDATE_DEC */
+
+			/*
+			 * Userspace can read TB directly, but the
+			 * value reported here is consistent with "dec".
+			 *
+			 * Read-only.
+			 */
+			__u64 tb;
+
+			__u32 dbsr;	/* KVM_SREGS_E_UPDATE_DBSR */
+			__u32 dbcr[3];
+			/*
+			 * iac/dac registers are 64bit wide, while this API
+			 * interface provides only lower 32 bits on 64 bit
+			 * processors. ONE_REG interface is added for 64bit
+			 * iac/dac registers.
+			 */
+			__u32 iac[4];
+			__u32 dac[2];
+			__u32 dvc[2];
+			__u8 num_iac;	/* read-only */
+			__u8 num_dac;	/* read-only */
+			__u8 num_dvc;	/* read-only */
+			__u8 pad;
+
+			__u32 epr;	/* EXP */
+			__u32 vrsave;	/* a.k.a. USPRG0 */
+			__u32 epcr;	/* KVM_SREGS_E_64 */
+
+			__u32 mas0;
+			__u32 mas1;
+			__u64 mas2;
+			__u64 mas7_3;
+			__u32 mas4;
+			__u32 mas6;
+
+			__u32 ivor_low[16]; /* IVOR0-15 */
+			__u32 ivor_high[18]; /* IVOR32+, plus room to expand */
+
+			__u32 mmucfg;	/* read-only */
+			__u32 eptcfg;	/* E.PT, read-only */
+			__u32 tlbcfg[4];/* read-only */
+			__u32 tlbps[4]; /* read-only */
+
+			__u32 eplc, epsc; /* E.PD */
+		} e;
+		__u8 pad[1020];
+	} u;
+};
+
+struct kvm_fpu {
+	__u64 fpr[32];
+};
+
+/*
+ * Defines for h/w breakpoint, watchpoint (read, write or both) and
+ * software breakpoint.
+ * These are used as "type" in KVM_SET_GUEST_DEBUG ioctl and "status"
+ * for KVM_DEBUG_EXIT.
+ */
+#define KVMPPC_DEBUG_NONE		0x0
+#define KVMPPC_DEBUG_BREAKPOINT		(1UL << 1)
+#define KVMPPC_DEBUG_WATCH_WRITE	(1UL << 2)
+#define KVMPPC_DEBUG_WATCH_READ		(1UL << 3)
+struct kvm_debug_exit_arch {
+	__u64 address;
+	/*
+	 * exiting to userspace because of h/w breakpoint, watchpoint
+	 * (read, write or both) and software breakpoint.
+	 */
+	__u32 status;
+	__u32 reserved;
+};
+
+/* for KVM_SET_GUEST_DEBUG */
+struct kvm_guest_debug_arch {
+	struct {
+		/* H/W breakpoint/watchpoint address */
+		__u64 addr;
+		/*
+		 * Type denotes h/w breakpoint, read watchpoint, write
+		 * watchpoint or watchpoint (both read and write).
+		 */
+		__u32 type;
+		__u32 reserved;
+	} bp[16];
+};
+
+/* Debug related defines */
+/*
+ * kvm_guest_debug->control is a 32 bit field. The lower 16 bits are generic
+ * and upper 16 bits are architecture specific. Architecture specific defines
+ * that ioctl is for setting hardware breakpoint or software breakpoint.
+ */
+#define KVM_GUESTDBG_USE_SW_BP		0x00010000
+#define KVM_GUESTDBG_USE_HW_BP		0x00020000
+
+/* definition of registers in kvm_run */
+struct kvm_sync_regs {
+};
+
+#define KVM_INTERRUPT_SET	-1U
+#define KVM_INTERRUPT_UNSET	-2U
+#define KVM_INTERRUPT_SET_LEVEL	-3U
+
+#define KVM_CPU_440		1
+#define KVM_CPU_E500V2		2
+#define KVM_CPU_3S_32		3
+#define KVM_CPU_3S_64		4
+#define KVM_CPU_E500MC		5
+
+/* for KVM_CAP_SPAPR_TCE */
+struct kvm_create_spapr_tce {
+	__u64 liobn;
+	__u32 window_size;
+};
+
+/* for KVM_CAP_SPAPR_TCE_64 */
+struct kvm_create_spapr_tce_64 {
+	__u64 liobn;
+	__u32 page_shift;
+	__u32 flags;
+	__u64 offset;	/* in pages */
+	__u64 size;	/* in pages */
+};
+
+/* for KVM_ALLOCATE_RMA */
+struct kvm_allocate_rma {
+	__u64 rma_size;
+};
+
+/* for KVM_CAP_PPC_RTAS */
+struct kvm_rtas_token_args {
+	char name[120];
+	__u64 token;	/* Use a token of 0 to undefine a mapping */
+};
+
+struct kvm_book3e_206_tlb_entry {
+	__u32 mas8;
+	__u32 mas1;
+	__u64 mas2;
+	__u64 mas7_3;
+};
+
+struct kvm_book3e_206_tlb_params {
+	/*
+	 * For mmu types KVM_MMU_FSL_BOOKE_NOHV and KVM_MMU_FSL_BOOKE_HV:
+	 *
+	 * - The number of ways of TLB0 must be a power of two between 2 and
+	 *   16.
+	 * - TLB1 must be fully associative.
+	 * - The size of TLB0 must be a multiple of the number of ways, and
+	 *   the number of sets must be a power of two.
+	 * - The size of TLB1 may not exceed 64 entries.
+	 * - TLB0 supports 4 KiB pages.
+	 * - The page sizes supported by TLB1 are as indicated by
+	 *   TLB1CFG (if MMUCFG[MAVN] = 0) or TLB1PS (if MMUCFG[MAVN] = 1)
+	 *   as returned by KVM_GET_SREGS.
+	 * - TLB2 and TLB3 are reserved, and their entries in tlb_sizes[]
+	 *   and tlb_ways[] must be zero.
+	 *
+	 * tlb_ways[n] = tlb_sizes[n] means the array is fully associative.
+	 *
+	 * KVM will adjust TLBnCFG based on the sizes configured here,
+	 * though arrays greater than 2048 entries will have TLBnCFG[NENTRY]
+	 * set to zero.
+	 */
+	__u32 tlb_sizes[4];
+	__u32 tlb_ways[4];
+	__u32 reserved[8];
+};
+
+/* For KVM_PPC_GET_HTAB_FD */
+struct kvm_get_htab_fd {
+	__u64	flags;
+	__u64	start_index;
+	__u64	reserved[2];
+};
+
+/* Values for kvm_get_htab_fd.flags */
+#define KVM_GET_HTAB_BOLTED_ONLY	((__u64)0x1)
+#define KVM_GET_HTAB_WRITE		((__u64)0x2)
+
+/*
+ * Data read on the file descriptor is formatted as a series of
+ * records, each consisting of a header followed by a series of
+ * `n_valid' HPTEs (16 bytes each), which are all valid.  Following
+ * those valid HPTEs there are `n_invalid' invalid HPTEs, which
+ * are not represented explicitly in the stream.  The same format
+ * is used for writing.
+ */
+struct kvm_get_htab_header {
+	__u32	index;
+	__u16	n_valid;
+	__u16	n_invalid;
+};
+
+/* Per-vcpu XICS interrupt controller state */
+#define KVM_REG_PPC_ICP_STATE	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x8c)
+
+#define  KVM_REG_PPC_ICP_CPPR_SHIFT	56	/* current proc priority */
+#define  KVM_REG_PPC_ICP_CPPR_MASK	0xff
+#define  KVM_REG_PPC_ICP_XISR_SHIFT	32	/* interrupt status field */
+#define  KVM_REG_PPC_ICP_XISR_MASK	0xffffff
+#define  KVM_REG_PPC_ICP_MFRR_SHIFT	24	/* pending IPI priority */
+#define  KVM_REG_PPC_ICP_MFRR_MASK	0xff
+#define  KVM_REG_PPC_ICP_PPRI_SHIFT	16	/* pending irq priority */
+#define  KVM_REG_PPC_ICP_PPRI_MASK	0xff
+
+/* Device control API: PPC-specific devices */
+#define KVM_DEV_MPIC_GRP_MISC		1
+#define   KVM_DEV_MPIC_BASE_ADDR	0	/* 64-bit */
+
+#define KVM_DEV_MPIC_GRP_REGISTER	2	/* 32-bit */
+#define KVM_DEV_MPIC_GRP_IRQ_ACTIVE	3	/* 32-bit */
+
+/* One-Reg API: PPC-specific registers */
+#define KVM_REG_PPC_HIOR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x1)
+#define KVM_REG_PPC_IAC1	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x2)
+#define KVM_REG_PPC_IAC2	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x3)
+#define KVM_REG_PPC_IAC3	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x4)
+#define KVM_REG_PPC_IAC4	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x5)
+#define KVM_REG_PPC_DAC1	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x6)
+#define KVM_REG_PPC_DAC2	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x7)
+#define KVM_REG_PPC_DABR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x8)
+#define KVM_REG_PPC_DSCR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x9)
+#define KVM_REG_PPC_PURR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xa)
+#define KVM_REG_PPC_SPURR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xb)
+#define KVM_REG_PPC_DAR		(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc)
+#define KVM_REG_PPC_DSISR	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xd)
+#define KVM_REG_PPC_AMR		(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xe)
+#define KVM_REG_PPC_UAMOR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xf)
+
+#define KVM_REG_PPC_MMCR0	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x10)
+#define KVM_REG_PPC_MMCR1	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x11)
+#define KVM_REG_PPC_MMCRA	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x12)
+#define KVM_REG_PPC_MMCR2	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x13)
+#define KVM_REG_PPC_MMCRS	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x14)
+#define KVM_REG_PPC_SIAR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x15)
+#define KVM_REG_PPC_SDAR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x16)
+#define KVM_REG_PPC_SIER	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x17)
+
+#define KVM_REG_PPC_PMC1	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x18)
+#define KVM_REG_PPC_PMC2	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x19)
+#define KVM_REG_PPC_PMC3	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x1a)
+#define KVM_REG_PPC_PMC4	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x1b)
+#define KVM_REG_PPC_PMC5	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x1c)
+#define KVM_REG_PPC_PMC6	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x1d)
+#define KVM_REG_PPC_PMC7	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x1e)
+#define KVM_REG_PPC_PMC8	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x1f)
+
+/* 32 floating-point registers */
+#define KVM_REG_PPC_FPR0	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x20)
+#define KVM_REG_PPC_FPR(n)	(KVM_REG_PPC_FPR0 + (n))
+#define KVM_REG_PPC_FPR31	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x3f)
+
+/* 32 VMX/Altivec vector registers */
+#define KVM_REG_PPC_VR0		(KVM_REG_PPC | KVM_REG_SIZE_U128 | 0x40)
+#define KVM_REG_PPC_VR(n)	(KVM_REG_PPC_VR0 + (n))
+#define KVM_REG_PPC_VR31	(KVM_REG_PPC | KVM_REG_SIZE_U128 | 0x5f)
+
+/* 32 double-width FP registers for VSX */
+/* High-order halves overlap with FP regs */
+#define KVM_REG_PPC_VSR0	(KVM_REG_PPC | KVM_REG_SIZE_U128 | 0x60)
+#define KVM_REG_PPC_VSR(n)	(KVM_REG_PPC_VSR0 + (n))
+#define KVM_REG_PPC_VSR31	(KVM_REG_PPC | KVM_REG_SIZE_U128 | 0x7f)
+
+/* FP and vector status/control registers */
+#define KVM_REG_PPC_FPSCR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x80)
+/*
+ * VSCR register is documented as a 32-bit register in the ISA, but it can
+ * only be accesses via a vector register. Expose VSCR as a 32-bit register
+ * even though the kernel represents it as a 128-bit vector.
+ */
+#define KVM_REG_PPC_VSCR	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x81)
+
+/* Virtual processor areas */
+/* For SLB & DTL, address in high (first) half, length in low half */
+#define KVM_REG_PPC_VPA_ADDR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x82)
+#define KVM_REG_PPC_VPA_SLB	(KVM_REG_PPC | KVM_REG_SIZE_U128 | 0x83)
+#define KVM_REG_PPC_VPA_DTL	(KVM_REG_PPC | KVM_REG_SIZE_U128 | 0x84)
+
+#define KVM_REG_PPC_EPCR	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x85)
+#define KVM_REG_PPC_EPR		(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x86)
+
+/* Timer Status Register OR/CLEAR interface */
+#define KVM_REG_PPC_OR_TSR	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x87)
+#define KVM_REG_PPC_CLEAR_TSR	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x88)
+#define KVM_REG_PPC_TCR		(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x89)
+#define KVM_REG_PPC_TSR		(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x8a)
+
+/* Debugging: Special instruction for software breakpoint */
+#define KVM_REG_PPC_DEBUG_INST	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x8b)
+
+/* MMU registers */
+#define KVM_REG_PPC_MAS0	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x8c)
+#define KVM_REG_PPC_MAS1	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x8d)
+#define KVM_REG_PPC_MAS2	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x8e)
+#define KVM_REG_PPC_MAS7_3	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x8f)
+#define KVM_REG_PPC_MAS4	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x90)
+#define KVM_REG_PPC_MAS6	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x91)
+#define KVM_REG_PPC_MMUCFG	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x92)
+/*
+ * TLBnCFG fields TLBnCFG_N_ENTRY and TLBnCFG_ASSOC can be changed only using
+ * KVM_CAP_SW_TLB ioctl
+ */
+#define KVM_REG_PPC_TLB0CFG	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x93)
+#define KVM_REG_PPC_TLB1CFG	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x94)
+#define KVM_REG_PPC_TLB2CFG	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x95)
+#define KVM_REG_PPC_TLB3CFG	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x96)
+#define KVM_REG_PPC_TLB0PS	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x97)
+#define KVM_REG_PPC_TLB1PS	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x98)
+#define KVM_REG_PPC_TLB2PS	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x99)
+#define KVM_REG_PPC_TLB3PS	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x9a)
+#define KVM_REG_PPC_EPTCFG	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x9b)
+
+/* Timebase offset */
+#define KVM_REG_PPC_TB_OFFSET	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x9c)
+
+/* POWER8 registers */
+#define KVM_REG_PPC_SPMC1	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x9d)
+#define KVM_REG_PPC_SPMC2	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x9e)
+#define KVM_REG_PPC_IAMR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x9f)
+#define KVM_REG_PPC_TFHAR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xa0)
+#define KVM_REG_PPC_TFIAR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xa1)
+#define KVM_REG_PPC_TEXASR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xa2)
+#define KVM_REG_PPC_FSCR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xa3)
+#define KVM_REG_PPC_PSPB	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xa4)
+#define KVM_REG_PPC_EBBHR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xa5)
+#define KVM_REG_PPC_EBBRR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xa6)
+#define KVM_REG_PPC_BESCR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xa7)
+#define KVM_REG_PPC_TAR		(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xa8)
+#define KVM_REG_PPC_DPDES	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xa9)
+#define KVM_REG_PPC_DAWR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xaa)
+#define KVM_REG_PPC_DAWRX	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xab)
+#define KVM_REG_PPC_CIABR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xac)
+#define KVM_REG_PPC_IC		(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xad)
+#define KVM_REG_PPC_VTB		(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xae)
+#define KVM_REG_PPC_CSIGR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xaf)
+#define KVM_REG_PPC_TACR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xb0)
+#define KVM_REG_PPC_TCSCR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xb1)
+#define KVM_REG_PPC_PID		(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xb2)
+#define KVM_REG_PPC_ACOP	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xb3)
+
+#define KVM_REG_PPC_VRSAVE	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xb4)
+#define KVM_REG_PPC_LPCR	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xb5)
+#define KVM_REG_PPC_LPCR_64	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xb5)
+#define KVM_REG_PPC_PPR		(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xb6)
+
+/* Architecture compatibility level */
+#define KVM_REG_PPC_ARCH_COMPAT	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xb7)
+
+#define KVM_REG_PPC_DABRX	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xb8)
+#define KVM_REG_PPC_WORT	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xb9)
+#define KVM_REG_PPC_SPRG9	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xba)
+#define KVM_REG_PPC_DBSR	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xbb)
+
+/* Transactional Memory checkpointed state:
+ * This is all GPRs, all VSX regs and a subset of SPRs
+ */
+#define KVM_REG_PPC_TM		(KVM_REG_PPC | 0x80000000)
+/* TM GPRs */
+#define KVM_REG_PPC_TM_GPR0	(KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0)
+#define KVM_REG_PPC_TM_GPR(n)	(KVM_REG_PPC_TM_GPR0 + (n))
+#define KVM_REG_PPC_TM_GPR31	(KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x1f)
+/* TM VSX */
+#define KVM_REG_PPC_TM_VSR0	(KVM_REG_PPC_TM | KVM_REG_SIZE_U128 | 0x20)
+#define KVM_REG_PPC_TM_VSR(n)	(KVM_REG_PPC_TM_VSR0 + (n))
+#define KVM_REG_PPC_TM_VSR63	(KVM_REG_PPC_TM | KVM_REG_SIZE_U128 | 0x5f)
+/* TM SPRS */
+#define KVM_REG_PPC_TM_CR	(KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x60)
+#define KVM_REG_PPC_TM_LR	(KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x61)
+#define KVM_REG_PPC_TM_CTR	(KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x62)
+#define KVM_REG_PPC_TM_FPSCR	(KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x63)
+#define KVM_REG_PPC_TM_AMR	(KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x64)
+#define KVM_REG_PPC_TM_PPR	(KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x65)
+#define KVM_REG_PPC_TM_VRSAVE	(KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x66)
+#define KVM_REG_PPC_TM_VSCR	(KVM_REG_PPC_TM | KVM_REG_SIZE_U32 | 0x67)
+#define KVM_REG_PPC_TM_DSCR	(KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x68)
+#define KVM_REG_PPC_TM_TAR	(KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x69)
+
+/* PPC64 eXternal Interrupt Controller Specification */
+#define KVM_DEV_XICS_GRP_SOURCES	1	/* 64-bit source attributes */
+
+/* Layout of 64-bit source attribute values */
+#define  KVM_XICS_DESTINATION_SHIFT	0
+#define  KVM_XICS_DESTINATION_MASK	0xffffffffULL
+#define  KVM_XICS_PRIORITY_SHIFT	32
+#define  KVM_XICS_PRIORITY_MASK		0xff
+#define  KVM_XICS_LEVEL_SENSITIVE	(1ULL << 40)
+#define  KVM_XICS_MASKED		(1ULL << 41)
+#define  KVM_XICS_PENDING		(1ULL << 42)
+
+#endif /* __LINUX_KVM_POWERPC_H */
diff --git a/tools/arch/s390/include/uapi/asm/kvm.h b/tools/arch/s390/include/uapi/asm/kvm.h
new file mode 100644
index 0000000000000..3b8e99ef9d58d
--- /dev/null
+++ b/tools/arch/s390/include/uapi/asm/kvm.h
@@ -0,0 +1,192 @@
+#ifndef __LINUX_KVM_S390_H
+#define __LINUX_KVM_S390_H
+/*
+ * KVM s390 specific structures and definitions
+ *
+ * Copyright IBM Corp. 2008
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License (version 2 only)
+ * as published by the Free Software Foundation.
+ *
+ *    Author(s): Carsten Otte <cotte@de.ibm.com>
+ *               Christian Borntraeger <borntraeger@de.ibm.com>
+ */
+#include <linux/types.h>
+
+#define __KVM_S390
+#define __KVM_HAVE_GUEST_DEBUG
+
+/* Device control API: s390-specific devices */
+#define KVM_DEV_FLIC_GET_ALL_IRQS	1
+#define KVM_DEV_FLIC_ENQUEUE		2
+#define KVM_DEV_FLIC_CLEAR_IRQS		3
+#define KVM_DEV_FLIC_APF_ENABLE		4
+#define KVM_DEV_FLIC_APF_DISABLE_WAIT	5
+#define KVM_DEV_FLIC_ADAPTER_REGISTER	6
+#define KVM_DEV_FLIC_ADAPTER_MODIFY	7
+#define KVM_DEV_FLIC_CLEAR_IO_IRQ	8
+/*
+ * We can have up to 4*64k pending subchannels + 8 adapter interrupts,
+ * as well as up  to ASYNC_PF_PER_VCPU*KVM_MAX_VCPUS pfault done interrupts.
+ * There are also sclp and machine checks. This gives us
+ * sizeof(kvm_s390_irq)*(4*65536+8+64*64+1+1) = 72 * 266250 = 19170000
+ * Lets round up to 8192 pages.
+ */
+#define KVM_S390_MAX_FLOAT_IRQS	266250
+#define KVM_S390_FLIC_MAX_BUFFER	0x2000000
+
+struct kvm_s390_io_adapter {
+	__u32 id;
+	__u8 isc;
+	__u8 maskable;
+	__u8 swap;
+	__u8 pad;
+};
+
+#define KVM_S390_IO_ADAPTER_MASK 1
+#define KVM_S390_IO_ADAPTER_MAP 2
+#define KVM_S390_IO_ADAPTER_UNMAP 3
+
+struct kvm_s390_io_adapter_req {
+	__u32 id;
+	__u8 type;
+	__u8 mask;
+	__u16 pad0;
+	__u64 addr;
+};
+
+/* kvm attr_group  on vm fd */
+#define KVM_S390_VM_MEM_CTRL		0
+#define KVM_S390_VM_TOD			1
+#define KVM_S390_VM_CRYPTO		2
+#define KVM_S390_VM_CPU_MODEL		3
+
+/* kvm attributes for mem_ctrl */
+#define KVM_S390_VM_MEM_ENABLE_CMMA	0
+#define KVM_S390_VM_MEM_CLR_CMMA	1
+#define KVM_S390_VM_MEM_LIMIT_SIZE	2
+
+#define KVM_S390_NO_MEM_LIMIT		U64_MAX
+
+/* kvm attributes for KVM_S390_VM_TOD */
+#define KVM_S390_VM_TOD_LOW		0
+#define KVM_S390_VM_TOD_HIGH		1
+
+/* kvm attributes for KVM_S390_VM_CPU_MODEL */
+/* processor related attributes are r/w */
+#define KVM_S390_VM_CPU_PROCESSOR	0
+struct kvm_s390_vm_cpu_processor {
+	__u64 cpuid;
+	__u16 ibc;
+	__u8  pad[6];
+	__u64 fac_list[256];
+};
+
+/* machine related attributes are r/o */
+#define KVM_S390_VM_CPU_MACHINE		1
+struct kvm_s390_vm_cpu_machine {
+	__u64 cpuid;
+	__u32 ibc;
+	__u8  pad[4];
+	__u64 fac_mask[256];
+	__u64 fac_list[256];
+};
+
+/* kvm attributes for crypto */
+#define KVM_S390_VM_CRYPTO_ENABLE_AES_KW	0
+#define KVM_S390_VM_CRYPTO_ENABLE_DEA_KW	1
+#define KVM_S390_VM_CRYPTO_DISABLE_AES_KW	2
+#define KVM_S390_VM_CRYPTO_DISABLE_DEA_KW	3
+
+/* for KVM_GET_REGS and KVM_SET_REGS */
+struct kvm_regs {
+	/* general purpose regs for s390 */
+	__u64 gprs[16];
+};
+
+/* for KVM_GET_SREGS and KVM_SET_SREGS */
+struct kvm_sregs {
+	__u32 acrs[16];
+	__u64 crs[16];
+};
+
+/* for KVM_GET_FPU and KVM_SET_FPU */
+struct kvm_fpu {
+	__u32 fpc;
+	__u64 fprs[16];
+};
+
+#define KVM_GUESTDBG_USE_HW_BP		0x00010000
+
+#define KVM_HW_BP			1
+#define KVM_HW_WP_WRITE			2
+#define KVM_SINGLESTEP			4
+
+struct kvm_debug_exit_arch {
+	__u64 addr;
+	__u8 type;
+	__u8 pad[7]; /* Should be set to 0 */
+};
+
+struct kvm_hw_breakpoint {
+	__u64 addr;
+	__u64 phys_addr;
+	__u64 len;
+	__u8 type;
+	__u8 pad[7]; /* Should be set to 0 */
+};
+
+/* for KVM_SET_GUEST_DEBUG */
+struct kvm_guest_debug_arch {
+	__u32 nr_hw_bp;
+	__u32 pad; /* Should be set to 0 */
+	struct kvm_hw_breakpoint __user *hw_bp;
+};
+
+/* for KVM_SYNC_PFAULT and KVM_REG_S390_PFTOKEN */
+#define KVM_S390_PFAULT_TOKEN_INVALID	0xffffffffffffffffULL
+
+#define KVM_SYNC_PREFIX (1UL << 0)
+#define KVM_SYNC_GPRS   (1UL << 1)
+#define KVM_SYNC_ACRS   (1UL << 2)
+#define KVM_SYNC_CRS    (1UL << 3)
+#define KVM_SYNC_ARCH0  (1UL << 4)
+#define KVM_SYNC_PFAULT (1UL << 5)
+#define KVM_SYNC_VRS    (1UL << 6)
+#define KVM_SYNC_RICCB  (1UL << 7)
+#define KVM_SYNC_FPRS   (1UL << 8)
+/* definition of registers in kvm_run */
+struct kvm_sync_regs {
+	__u64 prefix;	/* prefix register */
+	__u64 gprs[16];	/* general purpose registers */
+	__u32 acrs[16];	/* access registers */
+	__u64 crs[16];	/* control registers */
+	__u64 todpr;	/* tod programmable register [ARCH0] */
+	__u64 cputm;	/* cpu timer [ARCH0] */
+	__u64 ckc;	/* clock comparator [ARCH0] */
+	__u64 pp;	/* program parameter [ARCH0] */
+	__u64 gbea;	/* guest breaking-event address [ARCH0] */
+	__u64 pft;	/* pfault token [PFAULT] */
+	__u64 pfs;	/* pfault select [PFAULT] */
+	__u64 pfc;	/* pfault compare [PFAULT] */
+	union {
+		__u64 vrs[32][2];	/* vector registers (KVM_SYNC_VRS) */
+		__u64 fprs[16];		/* fp registers (KVM_SYNC_FPRS) */
+	};
+	__u8  reserved[512];	/* for future vector expansion */
+	__u32 fpc;		/* valid on KVM_SYNC_VRS or KVM_SYNC_FPRS */
+	__u8 padding[52];	/* riccb needs to be 64byte aligned */
+	__u8 riccb[64];		/* runtime instrumentation controls block */
+};
+
+#define KVM_REG_S390_TODPR	(KVM_REG_S390 | KVM_REG_SIZE_U32 | 0x1)
+#define KVM_REG_S390_EPOCHDIFF	(KVM_REG_S390 | KVM_REG_SIZE_U64 | 0x2)
+#define KVM_REG_S390_CPU_TIMER  (KVM_REG_S390 | KVM_REG_SIZE_U64 | 0x3)
+#define KVM_REG_S390_CLOCK_COMP (KVM_REG_S390 | KVM_REG_SIZE_U64 | 0x4)
+#define KVM_REG_S390_PFTOKEN	(KVM_REG_S390 | KVM_REG_SIZE_U64 | 0x5)
+#define KVM_REG_S390_PFCOMPARE	(KVM_REG_S390 | KVM_REG_SIZE_U64 | 0x6)
+#define KVM_REG_S390_PFSELECT	(KVM_REG_S390 | KVM_REG_SIZE_U64 | 0x7)
+#define KVM_REG_S390_PP		(KVM_REG_S390 | KVM_REG_SIZE_U64 | 0x8)
+#define KVM_REG_S390_GBEA	(KVM_REG_S390 | KVM_REG_SIZE_U64 | 0x9)
+#endif
diff --git a/tools/arch/s390/include/uapi/asm/kvm_perf.h b/tools/arch/s390/include/uapi/asm/kvm_perf.h
new file mode 100644
index 0000000000000..397282727e218
--- /dev/null
+++ b/tools/arch/s390/include/uapi/asm/kvm_perf.h
@@ -0,0 +1,25 @@
+/*
+ * Definitions for perf-kvm on s390
+ *
+ * Copyright 2014 IBM Corp.
+ * Author(s): Alexander Yarygin <yarygin@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License (version 2 only)
+ * as published by the Free Software Foundation.
+ */
+
+#ifndef __LINUX_KVM_PERF_S390_H
+#define __LINUX_KVM_PERF_S390_H
+
+#include <asm/sie.h>
+
+#define DECODE_STR_LEN 40
+
+#define VCPU_ID "id"
+
+#define KVM_ENTRY_TRACE "kvm:kvm_s390_sie_enter"
+#define KVM_EXIT_TRACE "kvm:kvm_s390_sie_exit"
+#define KVM_EXIT_REASON "icptcode"
+
+#endif
diff --git a/tools/arch/s390/include/uapi/asm/sie.h b/tools/arch/s390/include/uapi/asm/sie.h
new file mode 100644
index 0000000000000..8fb5d4a6dd25b
--- /dev/null
+++ b/tools/arch/s390/include/uapi/asm/sie.h
@@ -0,0 +1,250 @@
+#ifndef _UAPI_ASM_S390_SIE_H
+#define _UAPI_ASM_S390_SIE_H
+
+#define diagnose_codes						\
+	{ 0x10, "DIAG (0x10) release pages" },			\
+	{ 0x44, "DIAG (0x44) time slice end" },			\
+	{ 0x9c, "DIAG (0x9c) time slice end directed" },	\
+	{ 0x204, "DIAG (0x204) logical-cpu utilization" },	\
+	{ 0x258, "DIAG (0x258) page-reference services" },	\
+	{ 0x288, "DIAG (0x288) watchdog functions" },		\
+	{ 0x308, "DIAG (0x308) ipl functions" },		\
+	{ 0x500, "DIAG (0x500) KVM virtio functions" },		\
+	{ 0x501, "DIAG (0x501) KVM breakpoint" }
+
+#define sigp_order_codes					\
+	{ 0x01, "SIGP sense" },					\
+	{ 0x02, "SIGP external call" },				\
+	{ 0x03, "SIGP emergency signal" },			\
+	{ 0x04, "SIGP start" },					\
+	{ 0x05, "SIGP stop" },					\
+	{ 0x06, "SIGP restart" },				\
+	{ 0x09, "SIGP stop and store status" },			\
+	{ 0x0b, "SIGP initial cpu reset" },			\
+	{ 0x0c, "SIGP cpu reset" },				\
+	{ 0x0d, "SIGP set prefix" },				\
+	{ 0x0e, "SIGP store status at address" },		\
+	{ 0x12, "SIGP set architecture" },			\
+	{ 0x13, "SIGP conditional emergency signal" },		\
+	{ 0x15, "SIGP sense running" },				\
+	{ 0x16, "SIGP set multithreading"},			\
+	{ 0x17, "SIGP store additional status ait address"}
+
+#define icpt_prog_codes						\
+	{ 0x0001, "Prog Operation" },				\
+	{ 0x0002, "Prog Privileged Operation" },		\
+	{ 0x0003, "Prog Execute" },				\
+	{ 0x0004, "Prog Protection" },				\
+	{ 0x0005, "Prog Addressing" },				\
+	{ 0x0006, "Prog Specification" },			\
+	{ 0x0007, "Prog Data" },				\
+	{ 0x0008, "Prog Fixedpoint overflow" },			\
+	{ 0x0009, "Prog Fixedpoint divide" },			\
+	{ 0x000A, "Prog Decimal overflow" },			\
+	{ 0x000B, "Prog Decimal divide" },			\
+	{ 0x000C, "Prog HFP exponent overflow" },		\
+	{ 0x000D, "Prog HFP exponent underflow" },		\
+	{ 0x000E, "Prog HFP significance" },			\
+	{ 0x000F, "Prog HFP divide" },				\
+	{ 0x0010, "Prog Segment translation" },			\
+	{ 0x0011, "Prog Page translation" },			\
+	{ 0x0012, "Prog Translation specification" },		\
+	{ 0x0013, "Prog Special operation" },			\
+	{ 0x0015, "Prog Operand" },				\
+	{ 0x0016, "Prog Trace table" },				\
+	{ 0x0017, "Prog ASNtranslation specification" },	\
+	{ 0x001C, "Prog Spaceswitch event" },			\
+	{ 0x001D, "Prog HFP square root" },			\
+	{ 0x001F, "Prog PCtranslation specification" },		\
+	{ 0x0020, "Prog AFX translation" },			\
+	{ 0x0021, "Prog ASX translation" },			\
+	{ 0x0022, "Prog LX translation" },			\
+	{ 0x0023, "Prog EX translation" },			\
+	{ 0x0024, "Prog Primary authority" },			\
+	{ 0x0025, "Prog Secondary authority" },			\
+	{ 0x0026, "Prog LFXtranslation exception" },		\
+	{ 0x0027, "Prog LSXtranslation exception" },		\
+	{ 0x0028, "Prog ALET specification" },			\
+	{ 0x0029, "Prog ALEN translation" },			\
+	{ 0x002A, "Prog ALE sequence" },			\
+	{ 0x002B, "Prog ASTE validity" },			\
+	{ 0x002C, "Prog ASTE sequence" },			\
+	{ 0x002D, "Prog Extended authority" },			\
+	{ 0x002E, "Prog LSTE sequence" },			\
+	{ 0x002F, "Prog ASTE instance" },			\
+	{ 0x0030, "Prog Stack full" },				\
+	{ 0x0031, "Prog Stack empty" },				\
+	{ 0x0032, "Prog Stack specification" },			\
+	{ 0x0033, "Prog Stack type" },				\
+	{ 0x0034, "Prog Stack operation" },			\
+	{ 0x0039, "Prog Region first translation" },		\
+	{ 0x003A, "Prog Region second translation" },		\
+	{ 0x003B, "Prog Region third translation" },		\
+	{ 0x0040, "Prog Monitor event" },			\
+	{ 0x0080, "Prog PER event" },				\
+	{ 0x0119, "Prog Crypto operation" }
+
+#define exit_code_ipa0(ipa0, opcode, mnemonic)		\
+	{ (ipa0 << 8 | opcode), #ipa0 " " mnemonic }
+#define exit_code(opcode, mnemonic)			\
+	{ opcode, mnemonic }
+
+#define icpt_insn_codes				\
+	exit_code_ipa0(0x01, 0x01, "PR"),	\
+	exit_code_ipa0(0x01, 0x04, "PTFF"),	\
+	exit_code_ipa0(0x01, 0x07, "SCKPF"),	\
+	exit_code_ipa0(0xAA, 0x00, "RINEXT"),	\
+	exit_code_ipa0(0xAA, 0x01, "RION"),	\
+	exit_code_ipa0(0xAA, 0x02, "TRIC"),	\
+	exit_code_ipa0(0xAA, 0x03, "RIOFF"),	\
+	exit_code_ipa0(0xAA, 0x04, "RIEMIT"),	\
+	exit_code_ipa0(0xB2, 0x02, "STIDP"),	\
+	exit_code_ipa0(0xB2, 0x04, "SCK"),	\
+	exit_code_ipa0(0xB2, 0x05, "STCK"),	\
+	exit_code_ipa0(0xB2, 0x06, "SCKC"),	\
+	exit_code_ipa0(0xB2, 0x07, "STCKC"),	\
+	exit_code_ipa0(0xB2, 0x08, "SPT"),	\
+	exit_code_ipa0(0xB2, 0x09, "STPT"),	\
+	exit_code_ipa0(0xB2, 0x0d, "PTLB"),	\
+	exit_code_ipa0(0xB2, 0x10, "SPX"),	\
+	exit_code_ipa0(0xB2, 0x11, "STPX"),	\
+	exit_code_ipa0(0xB2, 0x12, "STAP"),	\
+	exit_code_ipa0(0xB2, 0x14, "SIE"),	\
+	exit_code_ipa0(0xB2, 0x16, "SETR"),	\
+	exit_code_ipa0(0xB2, 0x17, "STETR"),	\
+	exit_code_ipa0(0xB2, 0x18, "PC"),	\
+	exit_code_ipa0(0xB2, 0x20, "SERVC"),	\
+	exit_code_ipa0(0xB2, 0x21, "IPTE"),	\
+	exit_code_ipa0(0xB2, 0x28, "PT"),	\
+	exit_code_ipa0(0xB2, 0x29, "ISKE"),	\
+	exit_code_ipa0(0xB2, 0x2a, "RRBE"),	\
+	exit_code_ipa0(0xB2, 0x2b, "SSKE"),	\
+	exit_code_ipa0(0xB2, 0x2c, "TB"),	\
+	exit_code_ipa0(0xB2, 0x2e, "PGIN"),	\
+	exit_code_ipa0(0xB2, 0x2f, "PGOUT"),	\
+	exit_code_ipa0(0xB2, 0x30, "CSCH"),	\
+	exit_code_ipa0(0xB2, 0x31, "HSCH"),	\
+	exit_code_ipa0(0xB2, 0x32, "MSCH"),	\
+	exit_code_ipa0(0xB2, 0x33, "SSCH"),	\
+	exit_code_ipa0(0xB2, 0x34, "STSCH"),	\
+	exit_code_ipa0(0xB2, 0x35, "TSCH"),	\
+	exit_code_ipa0(0xB2, 0x36, "TPI"),	\
+	exit_code_ipa0(0xB2, 0x37, "SAL"),	\
+	exit_code_ipa0(0xB2, 0x38, "RSCH"),	\
+	exit_code_ipa0(0xB2, 0x39, "STCRW"),	\
+	exit_code_ipa0(0xB2, 0x3a, "STCPS"),	\
+	exit_code_ipa0(0xB2, 0x3b, "RCHP"),	\
+	exit_code_ipa0(0xB2, 0x3c, "SCHM"),	\
+	exit_code_ipa0(0xB2, 0x40, "BAKR"),	\
+	exit_code_ipa0(0xB2, 0x48, "PALB"),	\
+	exit_code_ipa0(0xB2, 0x4c, "TAR"),	\
+	exit_code_ipa0(0xB2, 0x50, "CSP"),	\
+	exit_code_ipa0(0xB2, 0x54, "MVPG"),	\
+	exit_code_ipa0(0xB2, 0x58, "BSG"),	\
+	exit_code_ipa0(0xB2, 0x5a, "BSA"),	\
+	exit_code_ipa0(0xB2, 0x5f, "CHSC"),	\
+	exit_code_ipa0(0xB2, 0x74, "SIGA"),	\
+	exit_code_ipa0(0xB2, 0x76, "XSCH"),	\
+	exit_code_ipa0(0xB2, 0x78, "STCKE"),	\
+	exit_code_ipa0(0xB2, 0x7c, "STCKF"),	\
+	exit_code_ipa0(0xB2, 0x7d, "STSI"),	\
+	exit_code_ipa0(0xB2, 0xb0, "STFLE"),	\
+	exit_code_ipa0(0xB2, 0xb1, "STFL"),	\
+	exit_code_ipa0(0xB2, 0xb2, "LPSWE"),	\
+	exit_code_ipa0(0xB2, 0xf8, "TEND"),	\
+	exit_code_ipa0(0xB2, 0xfc, "TABORT"),	\
+	exit_code_ipa0(0xB9, 0x1e, "KMAC"),	\
+	exit_code_ipa0(0xB9, 0x28, "PCKMO"),	\
+	exit_code_ipa0(0xB9, 0x2a, "KMF"),	\
+	exit_code_ipa0(0xB9, 0x2b, "KMO"),	\
+	exit_code_ipa0(0xB9, 0x2d, "KMCTR"),	\
+	exit_code_ipa0(0xB9, 0x2e, "KM"),	\
+	exit_code_ipa0(0xB9, 0x2f, "KMC"),	\
+	exit_code_ipa0(0xB9, 0x3e, "KIMD"),	\
+	exit_code_ipa0(0xB9, 0x3f, "KLMD"),	\
+	exit_code_ipa0(0xB9, 0x8a, "CSPG"),	\
+	exit_code_ipa0(0xB9, 0x8d, "EPSW"),	\
+	exit_code_ipa0(0xB9, 0x8e, "IDTE"),	\
+	exit_code_ipa0(0xB9, 0x8f, "CRDTE"),	\
+	exit_code_ipa0(0xB9, 0x9c, "EQBS"),	\
+	exit_code_ipa0(0xB9, 0xa2, "PTF"),	\
+	exit_code_ipa0(0xB9, 0xab, "ESSA"),	\
+	exit_code_ipa0(0xB9, 0xae, "RRBM"),	\
+	exit_code_ipa0(0xB9, 0xaf, "PFMF"),	\
+	exit_code_ipa0(0xE3, 0x03, "LRAG"),	\
+	exit_code_ipa0(0xE3, 0x13, "LRAY"),	\
+	exit_code_ipa0(0xE3, 0x25, "NTSTG"),	\
+	exit_code_ipa0(0xE5, 0x00, "LASP"),	\
+	exit_code_ipa0(0xE5, 0x01, "TPROT"),	\
+	exit_code_ipa0(0xE5, 0x60, "TBEGIN"),	\
+	exit_code_ipa0(0xE5, 0x61, "TBEGINC"),	\
+	exit_code_ipa0(0xEB, 0x25, "STCTG"),	\
+	exit_code_ipa0(0xEB, 0x2f, "LCTLG"),	\
+	exit_code_ipa0(0xEB, 0x60, "LRIC"),	\
+	exit_code_ipa0(0xEB, 0x61, "STRIC"),	\
+	exit_code_ipa0(0xEB, 0x62, "MRIC"),	\
+	exit_code_ipa0(0xEB, 0x8a, "SQBS"),	\
+	exit_code_ipa0(0xC8, 0x01, "ECTG"),	\
+	exit_code(0x0a, "SVC"),			\
+	exit_code(0x80, "SSM"),			\
+	exit_code(0x82, "LPSW"),		\
+	exit_code(0x83, "DIAG"),		\
+	exit_code(0xae, "SIGP"),		\
+	exit_code(0xac, "STNSM"),		\
+	exit_code(0xad, "STOSM"),		\
+	exit_code(0xb1, "LRA"),			\
+	exit_code(0xb6, "STCTL"),		\
+	exit_code(0xb7, "LCTL"),		\
+	exit_code(0xee, "PLO")
+
+#define sie_intercept_code					\
+	{ 0x00, "Host interruption" },				\
+	{ 0x04, "Instruction" },				\
+	{ 0x08, "Program interruption" },			\
+	{ 0x0c, "Instruction and program interruption" },	\
+	{ 0x10, "External request" },				\
+	{ 0x14, "External interruption" },			\
+	{ 0x18, "I/O request" },				\
+	{ 0x1c, "Wait state" },					\
+	{ 0x20, "Validity" },					\
+	{ 0x28, "Stop request" },				\
+	{ 0x2c, "Operation exception" },			\
+	{ 0x38, "Partial-execution" },				\
+	{ 0x3c, "I/O interruption" },				\
+	{ 0x40, "I/O instruction" },				\
+	{ 0x48, "Timing subset" }
+
+/*
+ * This is the simple interceptable instructions decoder.
+ *
+ * It will be used as userspace interface and it can be used in places
+ * that does not allow to use general decoder functions,
+ * such as trace events declarations.
+ *
+ * Some userspace tools may want to parse this code
+ * and would be confused by switch(), if() and other statements,
+ * but they can understand conditional operator.
+ */
+#define INSN_DECODE_IPA0(ipa0, insn, rshift, mask)		\
+	(insn >> 56) == (ipa0) ?				\
+		((ipa0 << 8) | ((insn >> rshift) & mask)) :
+
+#define INSN_DECODE(insn) (insn >> 56)
+
+/*
+ * The macro icpt_insn_decoder() takes an intercepted instruction
+ * and returns a key, which can be used to find a mnemonic name
+ * of the instruction in the icpt_insn_codes table.
+ */
+#define icpt_insn_decoder(insn) (		\
+	INSN_DECODE_IPA0(0x01, insn, 48, 0xff)	\
+	INSN_DECODE_IPA0(0xaa, insn, 48, 0x0f)	\
+	INSN_DECODE_IPA0(0xb2, insn, 48, 0xff)	\
+	INSN_DECODE_IPA0(0xb9, insn, 48, 0xff)	\
+	INSN_DECODE_IPA0(0xe3, insn, 48, 0xff)	\
+	INSN_DECODE_IPA0(0xe5, insn, 48, 0xff)	\
+	INSN_DECODE_IPA0(0xeb, insn, 16, 0xff)	\
+	INSN_DECODE_IPA0(0xc8, insn, 48, 0x0f)	\
+	INSN_DECODE(insn))
+
+#endif /* _UAPI_ASM_S390_SIE_H */
diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h
new file mode 100644
index 0000000000000..739c0c5940226
--- /dev/null
+++ b/tools/arch/x86/include/uapi/asm/kvm.h
@@ -0,0 +1,360 @@
+#ifndef _ASM_X86_KVM_H
+#define _ASM_X86_KVM_H
+
+/*
+ * KVM x86 specific structures and definitions
+ *
+ */
+
+#include <linux/types.h>
+#include <linux/ioctl.h>
+
+#define DE_VECTOR 0
+#define DB_VECTOR 1
+#define BP_VECTOR 3
+#define OF_VECTOR 4
+#define BR_VECTOR 5
+#define UD_VECTOR 6
+#define NM_VECTOR 7
+#define DF_VECTOR 8
+#define TS_VECTOR 10
+#define NP_VECTOR 11
+#define SS_VECTOR 12
+#define GP_VECTOR 13
+#define PF_VECTOR 14
+#define MF_VECTOR 16
+#define AC_VECTOR 17
+#define MC_VECTOR 18
+#define XM_VECTOR 19
+#define VE_VECTOR 20
+
+/* Select x86 specific features in <linux/kvm.h> */
+#define __KVM_HAVE_PIT
+#define __KVM_HAVE_IOAPIC
+#define __KVM_HAVE_IRQ_LINE
+#define __KVM_HAVE_MSI
+#define __KVM_HAVE_USER_NMI
+#define __KVM_HAVE_GUEST_DEBUG
+#define __KVM_HAVE_MSIX
+#define __KVM_HAVE_MCE
+#define __KVM_HAVE_PIT_STATE2
+#define __KVM_HAVE_XEN_HVM
+#define __KVM_HAVE_VCPU_EVENTS
+#define __KVM_HAVE_DEBUGREGS
+#define __KVM_HAVE_XSAVE
+#define __KVM_HAVE_XCRS
+#define __KVM_HAVE_READONLY_MEM
+
+/* Architectural interrupt line count. */
+#define KVM_NR_INTERRUPTS 256
+
+struct kvm_memory_alias {
+	__u32 slot;  /* this has a different namespace than memory slots */
+	__u32 flags;
+	__u64 guest_phys_addr;
+	__u64 memory_size;
+	__u64 target_phys_addr;
+};
+
+/* for KVM_GET_IRQCHIP and KVM_SET_IRQCHIP */
+struct kvm_pic_state {
+	__u8 last_irr;	/* edge detection */
+	__u8 irr;		/* interrupt request register */
+	__u8 imr;		/* interrupt mask register */
+	__u8 isr;		/* interrupt service register */
+	__u8 priority_add;	/* highest irq priority */
+	__u8 irq_base;
+	__u8 read_reg_select;
+	__u8 poll;
+	__u8 special_mask;
+	__u8 init_state;
+	__u8 auto_eoi;
+	__u8 rotate_on_auto_eoi;
+	__u8 special_fully_nested_mode;
+	__u8 init4;		/* true if 4 byte init */
+	__u8 elcr;		/* PIIX edge/trigger selection */
+	__u8 elcr_mask;
+};
+
+#define KVM_IOAPIC_NUM_PINS  24
+struct kvm_ioapic_state {
+	__u64 base_address;
+	__u32 ioregsel;
+	__u32 id;
+	__u32 irr;
+	__u32 pad;
+	union {
+		__u64 bits;
+		struct {
+			__u8 vector;
+			__u8 delivery_mode:3;
+			__u8 dest_mode:1;
+			__u8 delivery_status:1;
+			__u8 polarity:1;
+			__u8 remote_irr:1;
+			__u8 trig_mode:1;
+			__u8 mask:1;
+			__u8 reserve:7;
+			__u8 reserved[4];
+			__u8 dest_id;
+		} fields;
+	} redirtbl[KVM_IOAPIC_NUM_PINS];
+};
+
+#define KVM_IRQCHIP_PIC_MASTER   0
+#define KVM_IRQCHIP_PIC_SLAVE    1
+#define KVM_IRQCHIP_IOAPIC       2
+#define KVM_NR_IRQCHIPS          3
+
+#define KVM_RUN_X86_SMM		 (1 << 0)
+
+/* for KVM_GET_REGS and KVM_SET_REGS */
+struct kvm_regs {
+	/* out (KVM_GET_REGS) / in (KVM_SET_REGS) */
+	__u64 rax, rbx, rcx, rdx;
+	__u64 rsi, rdi, rsp, rbp;
+	__u64 r8,  r9,  r10, r11;
+	__u64 r12, r13, r14, r15;
+	__u64 rip, rflags;
+};
+
+/* for KVM_GET_LAPIC and KVM_SET_LAPIC */
+#define KVM_APIC_REG_SIZE 0x400
+struct kvm_lapic_state {
+	char regs[KVM_APIC_REG_SIZE];
+};
+
+struct kvm_segment {
+	__u64 base;
+	__u32 limit;
+	__u16 selector;
+	__u8  type;
+	__u8  present, dpl, db, s, l, g, avl;
+	__u8  unusable;
+	__u8  padding;
+};
+
+struct kvm_dtable {
+	__u64 base;
+	__u16 limit;
+	__u16 padding[3];
+};
+
+
+/* for KVM_GET_SREGS and KVM_SET_SREGS */
+struct kvm_sregs {
+	/* out (KVM_GET_SREGS) / in (KVM_SET_SREGS) */
+	struct kvm_segment cs, ds, es, fs, gs, ss;
+	struct kvm_segment tr, ldt;
+	struct kvm_dtable gdt, idt;
+	__u64 cr0, cr2, cr3, cr4, cr8;
+	__u64 efer;
+	__u64 apic_base;
+	__u64 interrupt_bitmap[(KVM_NR_INTERRUPTS + 63) / 64];
+};
+
+/* for KVM_GET_FPU and KVM_SET_FPU */
+struct kvm_fpu {
+	__u8  fpr[8][16];
+	__u16 fcw;
+	__u16 fsw;
+	__u8  ftwx;  /* in fxsave format */
+	__u8  pad1;
+	__u16 last_opcode;
+	__u64 last_ip;
+	__u64 last_dp;
+	__u8  xmm[16][16];
+	__u32 mxcsr;
+	__u32 pad2;
+};
+
+struct kvm_msr_entry {
+	__u32 index;
+	__u32 reserved;
+	__u64 data;
+};
+
+/* for KVM_GET_MSRS and KVM_SET_MSRS */
+struct kvm_msrs {
+	__u32 nmsrs; /* number of msrs in entries */
+	__u32 pad;
+
+	struct kvm_msr_entry entries[0];
+};
+
+/* for KVM_GET_MSR_INDEX_LIST */
+struct kvm_msr_list {
+	__u32 nmsrs; /* number of msrs in entries */
+	__u32 indices[0];
+};
+
+
+struct kvm_cpuid_entry {
+	__u32 function;
+	__u32 eax;
+	__u32 ebx;
+	__u32 ecx;
+	__u32 edx;
+	__u32 padding;
+};
+
+/* for KVM_SET_CPUID */
+struct kvm_cpuid {
+	__u32 nent;
+	__u32 padding;
+	struct kvm_cpuid_entry entries[0];
+};
+
+struct kvm_cpuid_entry2 {
+	__u32 function;
+	__u32 index;
+	__u32 flags;
+	__u32 eax;
+	__u32 ebx;
+	__u32 ecx;
+	__u32 edx;
+	__u32 padding[3];
+};
+
+#define KVM_CPUID_FLAG_SIGNIFCANT_INDEX		(1 << 0)
+#define KVM_CPUID_FLAG_STATEFUL_FUNC		(1 << 1)
+#define KVM_CPUID_FLAG_STATE_READ_NEXT		(1 << 2)
+
+/* for KVM_SET_CPUID2 */
+struct kvm_cpuid2 {
+	__u32 nent;
+	__u32 padding;
+	struct kvm_cpuid_entry2 entries[0];
+};
+
+/* for KVM_GET_PIT and KVM_SET_PIT */
+struct kvm_pit_channel_state {
+	__u32 count; /* can be 65536 */
+	__u16 latched_count;
+	__u8 count_latched;
+	__u8 status_latched;
+	__u8 status;
+	__u8 read_state;
+	__u8 write_state;
+	__u8 write_latch;
+	__u8 rw_mode;
+	__u8 mode;
+	__u8 bcd;
+	__u8 gate;
+	__s64 count_load_time;
+};
+
+struct kvm_debug_exit_arch {
+	__u32 exception;
+	__u32 pad;
+	__u64 pc;
+	__u64 dr6;
+	__u64 dr7;
+};
+
+#define KVM_GUESTDBG_USE_SW_BP		0x00010000
+#define KVM_GUESTDBG_USE_HW_BP		0x00020000
+#define KVM_GUESTDBG_INJECT_DB		0x00040000
+#define KVM_GUESTDBG_INJECT_BP		0x00080000
+
+/* for KVM_SET_GUEST_DEBUG */
+struct kvm_guest_debug_arch {
+	__u64 debugreg[8];
+};
+
+struct kvm_pit_state {
+	struct kvm_pit_channel_state channels[3];
+};
+
+#define KVM_PIT_FLAGS_HPET_LEGACY  0x00000001
+
+struct kvm_pit_state2 {
+	struct kvm_pit_channel_state channels[3];
+	__u32 flags;
+	__u32 reserved[9];
+};
+
+struct kvm_reinject_control {
+	__u8 pit_reinject;
+	__u8 reserved[31];
+};
+
+/* When set in flags, include corresponding fields on KVM_SET_VCPU_EVENTS */
+#define KVM_VCPUEVENT_VALID_NMI_PENDING	0x00000001
+#define KVM_VCPUEVENT_VALID_SIPI_VECTOR	0x00000002
+#define KVM_VCPUEVENT_VALID_SHADOW	0x00000004
+#define KVM_VCPUEVENT_VALID_SMM		0x00000008
+
+/* Interrupt shadow states */
+#define KVM_X86_SHADOW_INT_MOV_SS	0x01
+#define KVM_X86_SHADOW_INT_STI		0x02
+
+/* for KVM_GET/SET_VCPU_EVENTS */
+struct kvm_vcpu_events {
+	struct {
+		__u8 injected;
+		__u8 nr;
+		__u8 has_error_code;
+		__u8 pad;
+		__u32 error_code;
+	} exception;
+	struct {
+		__u8 injected;
+		__u8 nr;
+		__u8 soft;
+		__u8 shadow;
+	} interrupt;
+	struct {
+		__u8 injected;
+		__u8 pending;
+		__u8 masked;
+		__u8 pad;
+	} nmi;
+	__u32 sipi_vector;
+	__u32 flags;
+	struct {
+		__u8 smm;
+		__u8 pending;
+		__u8 smm_inside_nmi;
+		__u8 latched_init;
+	} smi;
+	__u32 reserved[9];
+};
+
+/* for KVM_GET/SET_DEBUGREGS */
+struct kvm_debugregs {
+	__u64 db[4];
+	__u64 dr6;
+	__u64 dr7;
+	__u64 flags;
+	__u64 reserved[9];
+};
+
+/* for KVM_CAP_XSAVE */
+struct kvm_xsave {
+	__u32 region[1024];
+};
+
+#define KVM_MAX_XCRS	16
+
+struct kvm_xcr {
+	__u32 xcr;
+	__u32 reserved;
+	__u64 value;
+};
+
+struct kvm_xcrs {
+	__u32 nr_xcrs;
+	__u32 flags;
+	struct kvm_xcr xcrs[KVM_MAX_XCRS];
+	__u64 padding[16];
+};
+
+/* definition of registers in kvm_run */
+struct kvm_sync_regs {
+};
+
+#define KVM_X86_QUIRK_LINT0_REENABLED	(1 << 0)
+#define KVM_X86_QUIRK_CD_NW_CLEARED	(1 << 1)
+
+#endif /* _ASM_X86_KVM_H */
diff --git a/tools/arch/x86/include/uapi/asm/kvm_perf.h b/tools/arch/x86/include/uapi/asm/kvm_perf.h
new file mode 100644
index 0000000000000..3bb964f88aa14
--- /dev/null
+++ b/tools/arch/x86/include/uapi/asm/kvm_perf.h
@@ -0,0 +1,16 @@
+#ifndef _ASM_X86_KVM_PERF_H
+#define _ASM_X86_KVM_PERF_H
+
+#include <asm/svm.h>
+#include <asm/vmx.h>
+#include <asm/kvm.h>
+
+#define DECODE_STR_LEN 20
+
+#define VCPU_ID "vcpu_id"
+
+#define KVM_ENTRY_TRACE "kvm:kvm_entry"
+#define KVM_EXIT_TRACE "kvm:kvm_exit"
+#define KVM_EXIT_REASON "exit_reason"
+
+#endif /* _ASM_X86_KVM_PERF_H */
diff --git a/tools/arch/x86/include/uapi/asm/svm.h b/tools/arch/x86/include/uapi/asm/svm.h
new file mode 100644
index 0000000000000..3725e145aa58c
--- /dev/null
+++ b/tools/arch/x86/include/uapi/asm/svm.h
@@ -0,0 +1,178 @@
+#ifndef _UAPI__SVM_H
+#define _UAPI__SVM_H
+
+#define SVM_EXIT_READ_CR0      0x000
+#define SVM_EXIT_READ_CR2      0x002
+#define SVM_EXIT_READ_CR3      0x003
+#define SVM_EXIT_READ_CR4      0x004
+#define SVM_EXIT_READ_CR8      0x008
+#define SVM_EXIT_WRITE_CR0     0x010
+#define SVM_EXIT_WRITE_CR2     0x012
+#define SVM_EXIT_WRITE_CR3     0x013
+#define SVM_EXIT_WRITE_CR4     0x014
+#define SVM_EXIT_WRITE_CR8     0x018
+#define SVM_EXIT_READ_DR0      0x020
+#define SVM_EXIT_READ_DR1      0x021
+#define SVM_EXIT_READ_DR2      0x022
+#define SVM_EXIT_READ_DR3      0x023
+#define SVM_EXIT_READ_DR4      0x024
+#define SVM_EXIT_READ_DR5      0x025
+#define SVM_EXIT_READ_DR6      0x026
+#define SVM_EXIT_READ_DR7      0x027
+#define SVM_EXIT_WRITE_DR0     0x030
+#define SVM_EXIT_WRITE_DR1     0x031
+#define SVM_EXIT_WRITE_DR2     0x032
+#define SVM_EXIT_WRITE_DR3     0x033
+#define SVM_EXIT_WRITE_DR4     0x034
+#define SVM_EXIT_WRITE_DR5     0x035
+#define SVM_EXIT_WRITE_DR6     0x036
+#define SVM_EXIT_WRITE_DR7     0x037
+#define SVM_EXIT_EXCP_BASE     0x040
+#define SVM_EXIT_INTR          0x060
+#define SVM_EXIT_NMI           0x061
+#define SVM_EXIT_SMI           0x062
+#define SVM_EXIT_INIT          0x063
+#define SVM_EXIT_VINTR         0x064
+#define SVM_EXIT_CR0_SEL_WRITE 0x065
+#define SVM_EXIT_IDTR_READ     0x066
+#define SVM_EXIT_GDTR_READ     0x067
+#define SVM_EXIT_LDTR_READ     0x068
+#define SVM_EXIT_TR_READ       0x069
+#define SVM_EXIT_IDTR_WRITE    0x06a
+#define SVM_EXIT_GDTR_WRITE    0x06b
+#define SVM_EXIT_LDTR_WRITE    0x06c
+#define SVM_EXIT_TR_WRITE      0x06d
+#define SVM_EXIT_RDTSC         0x06e
+#define SVM_EXIT_RDPMC         0x06f
+#define SVM_EXIT_PUSHF         0x070
+#define SVM_EXIT_POPF          0x071
+#define SVM_EXIT_CPUID         0x072
+#define SVM_EXIT_RSM           0x073
+#define SVM_EXIT_IRET          0x074
+#define SVM_EXIT_SWINT         0x075
+#define SVM_EXIT_INVD          0x076
+#define SVM_EXIT_PAUSE         0x077
+#define SVM_EXIT_HLT           0x078
+#define SVM_EXIT_INVLPG        0x079
+#define SVM_EXIT_INVLPGA       0x07a
+#define SVM_EXIT_IOIO          0x07b
+#define SVM_EXIT_MSR           0x07c
+#define SVM_EXIT_TASK_SWITCH   0x07d
+#define SVM_EXIT_FERR_FREEZE   0x07e
+#define SVM_EXIT_SHUTDOWN      0x07f
+#define SVM_EXIT_VMRUN         0x080
+#define SVM_EXIT_VMMCALL       0x081
+#define SVM_EXIT_VMLOAD        0x082
+#define SVM_EXIT_VMSAVE        0x083
+#define SVM_EXIT_STGI          0x084
+#define SVM_EXIT_CLGI          0x085
+#define SVM_EXIT_SKINIT        0x086
+#define SVM_EXIT_RDTSCP        0x087
+#define SVM_EXIT_ICEBP         0x088
+#define SVM_EXIT_WBINVD        0x089
+#define SVM_EXIT_MONITOR       0x08a
+#define SVM_EXIT_MWAIT         0x08b
+#define SVM_EXIT_MWAIT_COND    0x08c
+#define SVM_EXIT_XSETBV        0x08d
+#define SVM_EXIT_NPF           0x400
+#define SVM_EXIT_AVIC_INCOMPLETE_IPI		0x401
+#define SVM_EXIT_AVIC_UNACCELERATED_ACCESS	0x402
+
+#define SVM_EXIT_ERR           -1
+
+#define SVM_EXIT_REASONS \
+	{ SVM_EXIT_READ_CR0,    "read_cr0" }, \
+	{ SVM_EXIT_READ_CR2,    "read_cr2" }, \
+	{ SVM_EXIT_READ_CR3,    "read_cr3" }, \
+	{ SVM_EXIT_READ_CR4,    "read_cr4" }, \
+	{ SVM_EXIT_READ_CR8,    "read_cr8" }, \
+	{ SVM_EXIT_WRITE_CR0,   "write_cr0" }, \
+	{ SVM_EXIT_WRITE_CR2,   "write_cr2" }, \
+	{ SVM_EXIT_WRITE_CR3,   "write_cr3" }, \
+	{ SVM_EXIT_WRITE_CR4,   "write_cr4" }, \
+	{ SVM_EXIT_WRITE_CR8,   "write_cr8" }, \
+	{ SVM_EXIT_READ_DR0,    "read_dr0" }, \
+	{ SVM_EXIT_READ_DR1,    "read_dr1" }, \
+	{ SVM_EXIT_READ_DR2,    "read_dr2" }, \
+	{ SVM_EXIT_READ_DR3,    "read_dr3" }, \
+	{ SVM_EXIT_READ_DR4,    "read_dr4" }, \
+	{ SVM_EXIT_READ_DR5,    "read_dr5" }, \
+	{ SVM_EXIT_READ_DR6,    "read_dr6" }, \
+	{ SVM_EXIT_READ_DR7,    "read_dr7" }, \
+	{ SVM_EXIT_WRITE_DR0,   "write_dr0" }, \
+	{ SVM_EXIT_WRITE_DR1,   "write_dr1" }, \
+	{ SVM_EXIT_WRITE_DR2,   "write_dr2" }, \
+	{ SVM_EXIT_WRITE_DR3,   "write_dr3" }, \
+	{ SVM_EXIT_WRITE_DR4,   "write_dr4" }, \
+	{ SVM_EXIT_WRITE_DR5,   "write_dr5" }, \
+	{ SVM_EXIT_WRITE_DR6,   "write_dr6" }, \
+	{ SVM_EXIT_WRITE_DR7,   "write_dr7" }, \
+	{ SVM_EXIT_EXCP_BASE + DE_VECTOR,       "DE excp" }, \
+	{ SVM_EXIT_EXCP_BASE + DB_VECTOR,       "DB excp" }, \
+	{ SVM_EXIT_EXCP_BASE + BP_VECTOR,       "BP excp" }, \
+	{ SVM_EXIT_EXCP_BASE + OF_VECTOR,       "OF excp" }, \
+	{ SVM_EXIT_EXCP_BASE + BR_VECTOR,       "BR excp" }, \
+	{ SVM_EXIT_EXCP_BASE + UD_VECTOR,       "UD excp" }, \
+	{ SVM_EXIT_EXCP_BASE + NM_VECTOR,       "NM excp" }, \
+	{ SVM_EXIT_EXCP_BASE + DF_VECTOR,       "DF excp" }, \
+	{ SVM_EXIT_EXCP_BASE + TS_VECTOR,       "TS excp" }, \
+	{ SVM_EXIT_EXCP_BASE + NP_VECTOR,       "NP excp" }, \
+	{ SVM_EXIT_EXCP_BASE + SS_VECTOR,       "SS excp" }, \
+	{ SVM_EXIT_EXCP_BASE + GP_VECTOR,       "GP excp" }, \
+	{ SVM_EXIT_EXCP_BASE + PF_VECTOR,       "PF excp" }, \
+	{ SVM_EXIT_EXCP_BASE + MF_VECTOR,       "MF excp" }, \
+	{ SVM_EXIT_EXCP_BASE + AC_VECTOR,       "AC excp" }, \
+	{ SVM_EXIT_EXCP_BASE + MC_VECTOR,       "MC excp" }, \
+	{ SVM_EXIT_EXCP_BASE + XM_VECTOR,       "XF excp" }, \
+	{ SVM_EXIT_INTR,        "interrupt" }, \
+	{ SVM_EXIT_NMI,         "nmi" }, \
+	{ SVM_EXIT_SMI,         "smi" }, \
+	{ SVM_EXIT_INIT,        "init" }, \
+	{ SVM_EXIT_VINTR,       "vintr" }, \
+	{ SVM_EXIT_CR0_SEL_WRITE, "cr0_sel_write" }, \
+	{ SVM_EXIT_IDTR_READ,   "read_idtr" }, \
+	{ SVM_EXIT_GDTR_READ,   "read_gdtr" }, \
+	{ SVM_EXIT_LDTR_READ,   "read_ldtr" }, \
+	{ SVM_EXIT_TR_READ,     "read_rt" }, \
+	{ SVM_EXIT_IDTR_WRITE,  "write_idtr" }, \
+	{ SVM_EXIT_GDTR_WRITE,  "write_gdtr" }, \
+	{ SVM_EXIT_LDTR_WRITE,  "write_ldtr" }, \
+	{ SVM_EXIT_TR_WRITE,    "write_rt" }, \
+	{ SVM_EXIT_RDTSC,       "rdtsc" }, \
+	{ SVM_EXIT_RDPMC,       "rdpmc" }, \
+	{ SVM_EXIT_PUSHF,       "pushf" }, \
+	{ SVM_EXIT_POPF,        "popf" }, \
+	{ SVM_EXIT_CPUID,       "cpuid" }, \
+	{ SVM_EXIT_RSM,         "rsm" }, \
+	{ SVM_EXIT_IRET,        "iret" }, \
+	{ SVM_EXIT_SWINT,       "swint" }, \
+	{ SVM_EXIT_INVD,        "invd" }, \
+	{ SVM_EXIT_PAUSE,       "pause" }, \
+	{ SVM_EXIT_HLT,         "hlt" }, \
+	{ SVM_EXIT_INVLPG,      "invlpg" }, \
+	{ SVM_EXIT_INVLPGA,     "invlpga" }, \
+	{ SVM_EXIT_IOIO,        "io" }, \
+	{ SVM_EXIT_MSR,         "msr" }, \
+	{ SVM_EXIT_TASK_SWITCH, "task_switch" }, \
+	{ SVM_EXIT_FERR_FREEZE, "ferr_freeze" }, \
+	{ SVM_EXIT_SHUTDOWN,    "shutdown" }, \
+	{ SVM_EXIT_VMRUN,       "vmrun" }, \
+	{ SVM_EXIT_VMMCALL,     "hypercall" }, \
+	{ SVM_EXIT_VMLOAD,      "vmload" }, \
+	{ SVM_EXIT_VMSAVE,      "vmsave" }, \
+	{ SVM_EXIT_STGI,        "stgi" }, \
+	{ SVM_EXIT_CLGI,        "clgi" }, \
+	{ SVM_EXIT_SKINIT,      "skinit" }, \
+	{ SVM_EXIT_RDTSCP,      "rdtscp" }, \
+	{ SVM_EXIT_ICEBP,       "icebp" }, \
+	{ SVM_EXIT_WBINVD,      "wbinvd" }, \
+	{ SVM_EXIT_MONITOR,     "monitor" }, \
+	{ SVM_EXIT_MWAIT,       "mwait" }, \
+	{ SVM_EXIT_XSETBV,      "xsetbv" }, \
+	{ SVM_EXIT_NPF,         "npf" }, \
+	{ SVM_EXIT_AVIC_INCOMPLETE_IPI,		"avic_incomplete_ipi" }, \
+	{ SVM_EXIT_AVIC_UNACCELERATED_ACCESS,   "avic_unaccelerated_access" }, \
+	{ SVM_EXIT_ERR,         "invalid_guest_state" }
+
+
+#endif /* _UAPI__SVM_H */
diff --git a/tools/arch/x86/include/uapi/asm/vmx.h b/tools/arch/x86/include/uapi/asm/vmx.h
new file mode 100644
index 0000000000000..5b15d94a33f81
--- /dev/null
+++ b/tools/arch/x86/include/uapi/asm/vmx.h
@@ -0,0 +1,136 @@
+/*
+ * vmx.h: VMX Architecture related definitions
+ * Copyright (c) 2004, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc., 59 Temple
+ * Place - Suite 330, Boston, MA 02111-1307 USA.
+ *
+ * A few random additions are:
+ * Copyright (C) 2006 Qumranet
+ *    Avi Kivity <avi@qumranet.com>
+ *    Yaniv Kamay <yaniv@qumranet.com>
+ *
+ */
+#ifndef _UAPIVMX_H
+#define _UAPIVMX_H
+
+
+#define VMX_EXIT_REASONS_FAILED_VMENTRY         0x80000000
+
+#define EXIT_REASON_EXCEPTION_NMI       0
+#define EXIT_REASON_EXTERNAL_INTERRUPT  1
+#define EXIT_REASON_TRIPLE_FAULT        2
+
+#define EXIT_REASON_PENDING_INTERRUPT   7
+#define EXIT_REASON_NMI_WINDOW          8
+#define EXIT_REASON_TASK_SWITCH         9
+#define EXIT_REASON_CPUID               10
+#define EXIT_REASON_HLT                 12
+#define EXIT_REASON_INVD                13
+#define EXIT_REASON_INVLPG              14
+#define EXIT_REASON_RDPMC               15
+#define EXIT_REASON_RDTSC               16
+#define EXIT_REASON_VMCALL              18
+#define EXIT_REASON_VMCLEAR             19
+#define EXIT_REASON_VMLAUNCH            20
+#define EXIT_REASON_VMPTRLD             21
+#define EXIT_REASON_VMPTRST             22
+#define EXIT_REASON_VMREAD              23
+#define EXIT_REASON_VMRESUME            24
+#define EXIT_REASON_VMWRITE             25
+#define EXIT_REASON_VMOFF               26
+#define EXIT_REASON_VMON                27
+#define EXIT_REASON_CR_ACCESS           28
+#define EXIT_REASON_DR_ACCESS           29
+#define EXIT_REASON_IO_INSTRUCTION      30
+#define EXIT_REASON_MSR_READ            31
+#define EXIT_REASON_MSR_WRITE           32
+#define EXIT_REASON_INVALID_STATE       33
+#define EXIT_REASON_MSR_LOAD_FAIL       34
+#define EXIT_REASON_MWAIT_INSTRUCTION   36
+#define EXIT_REASON_MONITOR_TRAP_FLAG   37
+#define EXIT_REASON_MONITOR_INSTRUCTION 39
+#define EXIT_REASON_PAUSE_INSTRUCTION   40
+#define EXIT_REASON_MCE_DURING_VMENTRY  41
+#define EXIT_REASON_TPR_BELOW_THRESHOLD 43
+#define EXIT_REASON_APIC_ACCESS         44
+#define EXIT_REASON_EOI_INDUCED         45
+#define EXIT_REASON_EPT_VIOLATION       48
+#define EXIT_REASON_EPT_MISCONFIG       49
+#define EXIT_REASON_INVEPT              50
+#define EXIT_REASON_RDTSCP              51
+#define EXIT_REASON_PREEMPTION_TIMER    52
+#define EXIT_REASON_INVVPID             53
+#define EXIT_REASON_WBINVD              54
+#define EXIT_REASON_XSETBV              55
+#define EXIT_REASON_APIC_WRITE          56
+#define EXIT_REASON_INVPCID             58
+#define EXIT_REASON_PML_FULL            62
+#define EXIT_REASON_XSAVES              63
+#define EXIT_REASON_XRSTORS             64
+#define EXIT_REASON_PCOMMIT             65
+
+#define VMX_EXIT_REASONS \
+	{ EXIT_REASON_EXCEPTION_NMI,         "EXCEPTION_NMI" }, \
+	{ EXIT_REASON_EXTERNAL_INTERRUPT,    "EXTERNAL_INTERRUPT" }, \
+	{ EXIT_REASON_TRIPLE_FAULT,          "TRIPLE_FAULT" }, \
+	{ EXIT_REASON_PENDING_INTERRUPT,     "PENDING_INTERRUPT" }, \
+	{ EXIT_REASON_NMI_WINDOW,            "NMI_WINDOW" }, \
+	{ EXIT_REASON_TASK_SWITCH,           "TASK_SWITCH" }, \
+	{ EXIT_REASON_CPUID,                 "CPUID" }, \
+	{ EXIT_REASON_HLT,                   "HLT" }, \
+	{ EXIT_REASON_INVLPG,                "INVLPG" }, \
+	{ EXIT_REASON_RDPMC,                 "RDPMC" }, \
+	{ EXIT_REASON_RDTSC,                 "RDTSC" }, \
+	{ EXIT_REASON_VMCALL,                "VMCALL" }, \
+	{ EXIT_REASON_VMCLEAR,               "VMCLEAR" }, \
+	{ EXIT_REASON_VMLAUNCH,              "VMLAUNCH" }, \
+	{ EXIT_REASON_VMPTRLD,               "VMPTRLD" }, \
+	{ EXIT_REASON_VMPTRST,               "VMPTRST" }, \
+	{ EXIT_REASON_VMREAD,                "VMREAD" }, \
+	{ EXIT_REASON_VMRESUME,              "VMRESUME" }, \
+	{ EXIT_REASON_VMWRITE,               "VMWRITE" }, \
+	{ EXIT_REASON_VMOFF,                 "VMOFF" }, \
+	{ EXIT_REASON_VMON,                  "VMON" }, \
+	{ EXIT_REASON_CR_ACCESS,             "CR_ACCESS" }, \
+	{ EXIT_REASON_DR_ACCESS,             "DR_ACCESS" }, \
+	{ EXIT_REASON_IO_INSTRUCTION,        "IO_INSTRUCTION" }, \
+	{ EXIT_REASON_MSR_READ,              "MSR_READ" }, \
+	{ EXIT_REASON_MSR_WRITE,             "MSR_WRITE" }, \
+	{ EXIT_REASON_MWAIT_INSTRUCTION,     "MWAIT_INSTRUCTION" }, \
+	{ EXIT_REASON_MONITOR_TRAP_FLAG,     "MONITOR_TRAP_FLAG" }, \
+	{ EXIT_REASON_MONITOR_INSTRUCTION,   "MONITOR_INSTRUCTION" }, \
+	{ EXIT_REASON_PAUSE_INSTRUCTION,     "PAUSE_INSTRUCTION" }, \
+	{ EXIT_REASON_MCE_DURING_VMENTRY,    "MCE_DURING_VMENTRY" }, \
+	{ EXIT_REASON_TPR_BELOW_THRESHOLD,   "TPR_BELOW_THRESHOLD" }, \
+	{ EXIT_REASON_APIC_ACCESS,           "APIC_ACCESS" }, \
+	{ EXIT_REASON_EPT_VIOLATION,         "EPT_VIOLATION" }, \
+	{ EXIT_REASON_EPT_MISCONFIG,         "EPT_MISCONFIG" }, \
+	{ EXIT_REASON_INVEPT,                "INVEPT" }, \
+	{ EXIT_REASON_PREEMPTION_TIMER,      "PREEMPTION_TIMER" }, \
+	{ EXIT_REASON_WBINVD,                "WBINVD" }, \
+	{ EXIT_REASON_APIC_WRITE,            "APIC_WRITE" }, \
+	{ EXIT_REASON_EOI_INDUCED,           "EOI_INDUCED" }, \
+	{ EXIT_REASON_INVALID_STATE,         "INVALID_STATE" }, \
+	{ EXIT_REASON_MSR_LOAD_FAIL,         "MSR_LOAD_FAIL" }, \
+	{ EXIT_REASON_INVD,                  "INVD" }, \
+	{ EXIT_REASON_INVVPID,               "INVVPID" }, \
+	{ EXIT_REASON_INVPCID,               "INVPCID" }, \
+	{ EXIT_REASON_XSAVES,                "XSAVES" }, \
+	{ EXIT_REASON_XRSTORS,               "XRSTORS" }, \
+	{ EXIT_REASON_PCOMMIT,               "PCOMMIT" }
+
+#define VMX_ABORT_SAVE_GUEST_MSR_FAIL        1
+#define VMX_ABORT_LOAD_HOST_MSR_FAIL         4
+
+#endif /* _UAPIVMX_H */
diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST
index a4aefaeff3550..db7cfb42a6750 100644
--- a/tools/perf/MANIFEST
+++ b/tools/perf/MANIFEST
@@ -15,8 +15,14 @@ tools/arch/x86/include/asm/barrier.h
 tools/arch/x86/include/asm/cpufeatures.h
 tools/arch/x86/include/asm/disabled-features.h
 tools/arch/x86/include/asm/required-features.h
+tools/arch/x86/include/uapi/asm/svm.h
+tools/arch/x86/include/uapi/asm/vmx.h
+tools/arch/x86/include/uapi/asm/kvm.h
+tools/arch/x86/include/uapi/asm/kvm_perf.h
 tools/arch/x86/lib/memcpy_64.S
 tools/arch/x86/lib/memset_64.S
+tools/arch/s390/include/uapi/asm/kvm_perf.h
+tools/arch/s390/include/uapi/asm/sie.h
 tools/arch/xtensa/include/asm/barrier.h
 tools/scripts
 tools/build
@@ -85,12 +91,3 @@ tools/arch/*/include/uapi/asm/perf_regs.h
 include/linux/poison.h
 include/uapi/linux/const.h
 include/uapi/linux/swab.h
-arch/x86/include/asm/svm.h
-arch/x86/include/asm/vmx.h
-arch/x86/include/asm/kvm_host.h
-arch/x86/include/uapi/asm/svm.h
-arch/x86/include/uapi/asm/vmx.h
-arch/x86/include/uapi/asm/kvm.h
-arch/x86/include/uapi/asm/kvm_perf.h
-arch/s390/include/uapi/asm/sie.h
-arch/s390/include/uapi/asm/kvm_perf.h
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 0d07672c3af78..feb2c66b110ba 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -378,6 +378,36 @@ $(PERF_IN): prepare FORCE
 	@(test -f ../../arch/x86/include/uapi/asm/perf_regs.h && ( \
         (diff -B ../arch/x86/include/uapi/asm/perf_regs.h ../../arch/x86/include/uapi/asm/perf_regs.h >/dev/null) \
         || echo "Warning: tools/arch/x86/include/uapi/asm/perf_regs.h differs from kernel" >&2 )) || true
+	@(test -f ../../arch/x86/include/uapi/asm/kvm.h && ( \
+        (diff -B ../arch/x86/include/uapi/asm/kvm.h ../../arch/x86/include/uapi/asm/kvm.h >/dev/null) \
+        || echo "Warning: tools/arch/x86/include/uapi/asm/kvm.h differs from kernel" >&2 )) || true
+	@(test -f ../../arch/x86/include/uapi/asm/kvm_perf.h && ( \
+        (diff -B ../arch/x86/include/uapi/asm/kvm_perf.h ../../arch/x86/include/uapi/asm/kvm_perf.h >/dev/null) \
+        || echo "Warning: tools/arch/x86/include/uapi/asm/kvm_perf.h differs from kernel" >&2 )) || true
+	@(test -f ../../arch/x86/include/uapi/asm/svm.h && ( \
+        (diff -B ../arch/x86/include/uapi/asm/svm.h ../../arch/x86/include/uapi/asm/svm.h >/dev/null) \
+        || echo "Warning: tools/arch/x86/include/uapi/asm/svm.h differs from kernel" >&2 )) || true
+	@(test -f ../../arch/x86/include/uapi/asm/vmx.h && ( \
+        (diff -B ../arch/x86/include/uapi/asm/vmx.h ../../arch/x86/include/uapi/asm/vmx.h >/dev/null) \
+        || echo "Warning: tools/arch/x86/include/uapi/asm/vmx.h differs from kernel" >&2 )) || true
+	@(test -f ../../arch/powerpc/include/uapi/asm/kvm.h && ( \
+        (diff -B ../arch/powerpc/include/uapi/asm/kvm.h ../../arch/powerpc/include/uapi/asm/kvm.h >/dev/null) \
+        || echo "Warning: tools/arch/powerpc/include/uapi/asm/kvm.h differs from kernel" >&2 )) || true
+	@(test -f ../../arch/s390/include/uapi/asm/kvm.h && ( \
+        (diff -B ../arch/s390/include/uapi/asm/kvm.h ../../arch/s390/include/uapi/asm/kvm.h >/dev/null) \
+        || echo "Warning: tools/arch/s390/include/uapi/asm/kvm.h differs from kernel" >&2 )) || true
+	@(test -f ../../arch/s390/include/uapi/asm/kvm_perf.h && ( \
+        (diff -B ../arch/s390/include/uapi/asm/kvm_perf.h ../../arch/s390/include/uapi/asm/kvm_perf.h >/dev/null) \
+        || echo "Warning: tools/arch/s390/include/uapi/asm/kvm_perf.h differs from kernel" >&2 )) || true
+	@(test -f ../../arch/s390/include/uapi/asm/sie.h && ( \
+        (diff -B ../arch/s390/include/uapi/asm/sie.h ../../arch/s390/include/uapi/asm/sie.h >/dev/null) \
+        || echo "Warning: tools/arch/s390/include/uapi/asm/sie.h differs from kernel" >&2 )) || true
+	@(test -f ../../arch/arm/include/uapi/asm/kvm.h && ( \
+        (diff -B ../arch/arm/include/uapi/asm/kvm.h ../../arch/arm/include/uapi/asm/kvm.h >/dev/null) \
+        || echo "Warning: tools/arch/arm/include/uapi/asm/kvm.h differs from kernel" >&2 )) || true
+	@(test -f ../../arch/arm64/include/uapi/asm/kvm.h && ( \
+        (diff -B ../arch/arm64/include/uapi/asm/kvm.h ../../arch/arm64/include/uapi/asm/kvm.h >/dev/null) \
+        || echo "Warning: tools/arch/arm64/include/uapi/asm/kvm.h differs from kernel" >&2 )) || true
 	$(Q)$(MAKE) $(build)=perf
 
 $(OUTPUT)perf: $(PERFLIBS) $(PERF_IN) $(LIBTRACEEVENT_DYNAMIC_LIST)

From 9a3dc28bb015fc730f7ffc49b7b0abf830b56b61 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 12 Jul 2016 11:01:17 -0300
Subject: [PATCH 46/66] perf tools: Fallback to reading sysfs to get cacheline
 size

On systems where sysconf(_SC_LEVEL1_DCACHE_LINESIZE) is not available,
such as musl LIBC and Android's bionic libc.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Chris Phlipot <cphlipot0@gmail.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-772obxzby758g7m2wmzcejxz@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/perf.c | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index f7d7dbbd2af67..4b2ff021434c2 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -497,6 +497,16 @@ void pthread__unblock_sigwinch(void)
 	pthread_sigmask(SIG_UNBLOCK, &set, NULL);
 }
 
+#ifdef _SC_LEVEL1_DCACHE_LINESIZE
+#define cache_line_size(cacheline_sizep) *cacheline_sizep = sysconf(_SC_LEVEL1_DCACHE_LINESIZE)
+#else
+static void cache_line_size(int *cacheline_sizep)
+{
+	if (sysfs__read_int("devices/system/cpu/cpu0/cache/index0/coherency_line_size", cacheline_sizep))
+		perror("cannot determine cache line size");
+}
+#endif
+
 int main(int argc, const char **argv)
 {
 	const char *cmd;
@@ -509,7 +519,7 @@ int main(int argc, const char **argv)
 
 	/* The page_size is placed in util object. */
 	page_size = sysconf(_SC_PAGE_SIZE);
-	cacheline_size = sysconf(_SC_LEVEL1_DCACHE_LINESIZE);
+	cache_line_size(&cacheline_size);
 
 	if (sysctl__read_int("kernel/perf_event_max_stack", &value) == 0)
 		sysctl_perf_event_max_stack = value;

From e53e6bb8eba683ec1f18947410f39ab77efb098b Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 12 Jul 2016 11:02:37 -0300
Subject: [PATCH 47/66] perf trace beauty futex_op: Add missing defines for
 older systems

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-6qkuhv2mrcxmpy5sasc3c9tf@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/trace/beauty/futex_op.c | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/tools/perf/trace/beauty/futex_op.c b/tools/perf/trace/beauty/futex_op.c
index e2476211f22da..bfd3359b09b66 100644
--- a/tools/perf/trace/beauty/futex_op.c
+++ b/tools/perf/trace/beauty/futex_op.c
@@ -1,5 +1,21 @@
 #include <linux/futex.h>
 
+#ifndef FUTEX_WAIT_BITSET
+#define FUTEX_WAIT_BITSET	  9
+#endif
+#ifndef FUTEX_WAKE_BITSET
+#define FUTEX_WAKE_BITSET	 10
+#endif
+#ifndef FUTEX_WAIT_REQUEUE_PI
+#define FUTEX_WAIT_REQUEUE_PI	 11
+#endif
+#ifndef FUTEX_CMP_REQUEUE_PI
+#define FUTEX_CMP_REQUEUE_PI	 12
+#endif
+#ifndef FUTEX_CLOCK_REALTIME
+#define FUTEX_CLOCK_REALTIME	256
+#endif
+
 static size_t syscall_arg__scnprintf_futex_op(char *bf, size_t size, struct syscall_arg *arg)
 {
 	enum syscall_futex_args {

From 6e6fec966dcd9eb47952b39def2dee975f3502ff Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 12 Jul 2016 11:03:20 -0300
Subject: [PATCH 48/66] perf trace beauty seccomp: Remove seccomp.h include

All we need from it is already conditionally defined, and this header
file is not present in older systems, so ditch it.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-3jxpz9gwahk4e7ltqtnr1rjg@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/trace/beauty/seccomp.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/tools/perf/trace/beauty/seccomp.c b/tools/perf/trace/beauty/seccomp.c
index 213c5a7e3e921..356441bce27da 100644
--- a/tools/perf/trace/beauty/seccomp.c
+++ b/tools/perf/trace/beauty/seccomp.c
@@ -1,5 +1,3 @@
-#include <linux/seccomp.h>
-
 #ifndef SECCOMP_SET_MODE_STRICT
 #define SECCOMP_SET_MODE_STRICT 0
 #endif

From cc31078cf13f67c489ad6a5c48dea657f5f88d11 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 12 Jul 2016 11:04:13 -0300
Subject: [PATCH 49/66] perf symbols: Provide a GElf_Nhdr typedef

This one can be safely defined to be Elf64_Nhdr, as it is in elfutils's
libelf, but not on musl libc, as both Elf64_Nhdr and  Elf32_Nhdr have
the same layout.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-w8z8614l03lc8bip4ijbywbt@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/symbol-elf.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 6f15b92cbf701..79a6a190f41df 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -16,6 +16,7 @@
 #define EM_AARCH64	183  /* ARM 64 bit */
 #endif
 
+typedef Elf64_Nhdr GElf_Nhdr;
 
 #ifdef HAVE_CPLUS_DEMANGLE_SUPPORT
 extern char *cplus_demangle(const char *, int);

From 39f54862a935e14a448cbd68d6a6bef68d026dbe Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 12 Jul 2016 11:05:26 -0300
Subject: [PATCH 50/66] perf script python: Silence -Werror=maybe-uninitialized
 on gcc 5.3.0

Sounds like a compiler bug, but to silence it, initialize those
variables to NULL.

Noticed on:

Target: x86_64-alpine-linux-musl
Configured with: /home/buildozer/aports/main/gcc/src/gcc-5.3.0/configure
--prefix=/usr --mandir=/usr/share/man --infodir=/usr/share/info
--build=x86_64-alpine-linux-musl --host=x86_64-alpine-linux-musl
--target=x86_64-alpine-linux-musl --with-pkgversion='Alpine 5.3.0'
--enable-checking=release --disable-fixed-point --disable-libstdcxx-pch
--disable-multilib --disable-nls --disable-werror --disable-symvers
--enable-__cxa_atexit --enable-esp --enable-cloog-backend
--enable-languages=c,c++,objc,java,fortran,ada --disable-libssp
--disable-libmudflap --disable-libsanitizer --enable-shared
--enable-threads --enable-tls --with-system-zlib
Thread model: posix
gcc version 5.3.0 (Alpine 5.3.0)

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-zyvsjvbl45o7hzcuz78wu2xi@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/scripting-engines/trace-event-python.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index ff134700bf30d..6ac6b7a33f423 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -273,7 +273,7 @@ static PyObject *get_field_numeric_entry(struct event_format *event,
 		struct format_field *field, void *data)
 {
 	bool is_array = field->flags & FIELD_IS_ARRAY;
-	PyObject *obj, *list = NULL;
+	PyObject *obj = NULL, *list = NULL;
 	unsigned long long val;
 	unsigned int item_size, n_items, i;
 
@@ -392,7 +392,7 @@ static void python_process_tracepoint(struct perf_sample *sample,
 				      struct addr_location *al)
 {
 	struct event_format *event = evsel->tp_format;
-	PyObject *handler, *context, *t, *obj, *callchain;
+	PyObject *handler, *context, *t, *obj = NULL, *callchain;
 	PyObject *dict = NULL;
 	static char handler_name[256];
 	struct format_field *field;

From bb9707077b4ee5f77bc9939b057ff8a0d410296f Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 12 Jul 2016 11:12:18 -0300
Subject: [PATCH 51/66] tools: Copy the bitsperlong.h files from the kernel

We use it in bitops/__ffs.h and bitops/atomic.h, that we also got from
the kernel, but were getting it from either newer systems that carry it
in /usr/include, or from the kernel sources, that we decided not to
touch from tools/ code. Fix it.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-lwqvgbuitjmrdpjmjp6zqnyx@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 .../arch/alpha/include/uapi/asm/bitsperlong.h |  8 ++++++
 .../arch/arm64/include/uapi/asm/bitsperlong.h | 23 ++++++++++++++++
 tools/arch/frv/include/uapi/asm/bitsperlong.h |  1 +
 tools/arch/h8300/include/asm/bitsperlong.h    | 14 ++++++++++
 .../hexagon/include/uapi/asm/bitsperlong.h    | 26 +++++++++++++++++++
 .../arch/ia64/include/uapi/asm/bitsperlong.h  |  8 ++++++
 .../arch/m32r/include/uapi/asm/bitsperlong.h  |  1 +
 .../microblaze/include/uapi/asm/bitsperlong.h |  1 +
 .../arch/mips/include/uapi/asm/bitsperlong.h  |  8 ++++++
 .../mn10300/include/uapi/asm/bitsperlong.h    |  1 +
 .../parisc/include/uapi/asm/bitsperlong.h     | 14 ++++++++++
 .../powerpc/include/uapi/asm/bitsperlong.h    | 12 +++++++++
 .../arch/s390/include/uapi/asm/bitsperlong.h  | 12 +++++++++
 .../arch/score/include/uapi/asm/bitsperlong.h |  6 +++++
 .../arch/sparc/include/uapi/asm/bitsperlong.h | 12 +++++++++
 .../arch/tile/include/uapi/asm/bitsperlong.h  | 26 +++++++++++++++++++
 tools/arch/x86/include/uapi/asm/bitsperlong.h | 12 +++++++++
 tools/include/asm-generic/bitops/__ffs.h      |  1 +
 tools/include/asm-generic/bitops/atomic.h     |  1 +
 tools/include/asm-generic/bitsperlong.h       | 25 ++++++++++++++++++
 tools/include/uapi/asm-generic/bitsperlong.h  | 15 +++++++++++
 21 files changed, 227 insertions(+)
 create mode 100644 tools/arch/alpha/include/uapi/asm/bitsperlong.h
 create mode 100644 tools/arch/arm64/include/uapi/asm/bitsperlong.h
 create mode 100644 tools/arch/frv/include/uapi/asm/bitsperlong.h
 create mode 100644 tools/arch/h8300/include/asm/bitsperlong.h
 create mode 100644 tools/arch/hexagon/include/uapi/asm/bitsperlong.h
 create mode 100644 tools/arch/ia64/include/uapi/asm/bitsperlong.h
 create mode 100644 tools/arch/m32r/include/uapi/asm/bitsperlong.h
 create mode 100644 tools/arch/microblaze/include/uapi/asm/bitsperlong.h
 create mode 100644 tools/arch/mips/include/uapi/asm/bitsperlong.h
 create mode 100644 tools/arch/mn10300/include/uapi/asm/bitsperlong.h
 create mode 100644 tools/arch/parisc/include/uapi/asm/bitsperlong.h
 create mode 100644 tools/arch/powerpc/include/uapi/asm/bitsperlong.h
 create mode 100644 tools/arch/s390/include/uapi/asm/bitsperlong.h
 create mode 100644 tools/arch/score/include/uapi/asm/bitsperlong.h
 create mode 100644 tools/arch/sparc/include/uapi/asm/bitsperlong.h
 create mode 100644 tools/arch/tile/include/uapi/asm/bitsperlong.h
 create mode 100644 tools/arch/x86/include/uapi/asm/bitsperlong.h
 create mode 100644 tools/include/asm-generic/bitsperlong.h
 create mode 100644 tools/include/uapi/asm-generic/bitsperlong.h

diff --git a/tools/arch/alpha/include/uapi/asm/bitsperlong.h b/tools/arch/alpha/include/uapi/asm/bitsperlong.h
new file mode 100644
index 0000000000000..ad57f78682038
--- /dev/null
+++ b/tools/arch/alpha/include/uapi/asm/bitsperlong.h
@@ -0,0 +1,8 @@
+#ifndef __ASM_ALPHA_BITSPERLONG_H
+#define __ASM_ALPHA_BITSPERLONG_H
+
+#define __BITS_PER_LONG 64
+
+#include <asm-generic/bitsperlong.h>
+
+#endif /* __ASM_ALPHA_BITSPERLONG_H */
diff --git a/tools/arch/arm64/include/uapi/asm/bitsperlong.h b/tools/arch/arm64/include/uapi/asm/bitsperlong.h
new file mode 100644
index 0000000000000..fce9c2924fa34
--- /dev/null
+++ b/tools/arch/arm64/include/uapi/asm/bitsperlong.h
@@ -0,0 +1,23 @@
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+#ifndef __ASM_BITSPERLONG_H
+#define __ASM_BITSPERLONG_H
+
+#define __BITS_PER_LONG 64
+
+#include <asm-generic/bitsperlong.h>
+
+#endif	/* __ASM_BITSPERLONG_H */
diff --git a/tools/arch/frv/include/uapi/asm/bitsperlong.h b/tools/arch/frv/include/uapi/asm/bitsperlong.h
new file mode 100644
index 0000000000000..6dc0bb0c13b29
--- /dev/null
+++ b/tools/arch/frv/include/uapi/asm/bitsperlong.h
@@ -0,0 +1 @@
+#include <asm-generic/bitsperlong.h>
diff --git a/tools/arch/h8300/include/asm/bitsperlong.h b/tools/arch/h8300/include/asm/bitsperlong.h
new file mode 100644
index 0000000000000..e140e46729ac9
--- /dev/null
+++ b/tools/arch/h8300/include/asm/bitsperlong.h
@@ -0,0 +1,14 @@
+#ifndef __ASM_H8300_BITS_PER_LONG
+#define __ASM_H8300_BITS_PER_LONG
+
+#include <asm-generic/bitsperlong.h>
+
+#if !defined(__ASSEMBLY__)
+/* h8300-unknown-linux required long */
+#define __kernel_size_t __kernel_size_t
+typedef unsigned long	__kernel_size_t;
+typedef long		__kernel_ssize_t;
+typedef long		__kernel_ptrdiff_t;
+#endif
+
+#endif /* __ASM_H8300_BITS_PER_LONG */
diff --git a/tools/arch/hexagon/include/uapi/asm/bitsperlong.h b/tools/arch/hexagon/include/uapi/asm/bitsperlong.h
new file mode 100644
index 0000000000000..4a658151383d2
--- /dev/null
+++ b/tools/arch/hexagon/include/uapi/asm/bitsperlong.h
@@ -0,0 +1,26 @@
+/*
+ * Copyright (c) 2010-2011, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA.
+ */
+
+#ifndef __ASM_HEXAGON_BITSPERLONG_H
+#define __ASM_HEXAGON_BITSPERLONG_H
+
+#define __BITS_PER_LONG 32
+
+#include <asm-generic/bitsperlong.h>
+
+#endif
diff --git a/tools/arch/ia64/include/uapi/asm/bitsperlong.h b/tools/arch/ia64/include/uapi/asm/bitsperlong.h
new file mode 100644
index 0000000000000..ec4db3c970b77
--- /dev/null
+++ b/tools/arch/ia64/include/uapi/asm/bitsperlong.h
@@ -0,0 +1,8 @@
+#ifndef __ASM_IA64_BITSPERLONG_H
+#define __ASM_IA64_BITSPERLONG_H
+
+#define __BITS_PER_LONG 64
+
+#include <asm-generic/bitsperlong.h>
+
+#endif /* __ASM_IA64_BITSPERLONG_H */
diff --git a/tools/arch/m32r/include/uapi/asm/bitsperlong.h b/tools/arch/m32r/include/uapi/asm/bitsperlong.h
new file mode 100644
index 0000000000000..6dc0bb0c13b29
--- /dev/null
+++ b/tools/arch/m32r/include/uapi/asm/bitsperlong.h
@@ -0,0 +1 @@
+#include <asm-generic/bitsperlong.h>
diff --git a/tools/arch/microblaze/include/uapi/asm/bitsperlong.h b/tools/arch/microblaze/include/uapi/asm/bitsperlong.h
new file mode 100644
index 0000000000000..6dc0bb0c13b29
--- /dev/null
+++ b/tools/arch/microblaze/include/uapi/asm/bitsperlong.h
@@ -0,0 +1 @@
+#include <asm-generic/bitsperlong.h>
diff --git a/tools/arch/mips/include/uapi/asm/bitsperlong.h b/tools/arch/mips/include/uapi/asm/bitsperlong.h
new file mode 100644
index 0000000000000..3e4c10a8e7876
--- /dev/null
+++ b/tools/arch/mips/include/uapi/asm/bitsperlong.h
@@ -0,0 +1,8 @@
+#ifndef __ASM_MIPS_BITSPERLONG_H
+#define __ASM_MIPS_BITSPERLONG_H
+
+#define __BITS_PER_LONG _MIPS_SZLONG
+
+#include <asm-generic/bitsperlong.h>
+
+#endif /* __ASM_MIPS_BITSPERLONG_H */
diff --git a/tools/arch/mn10300/include/uapi/asm/bitsperlong.h b/tools/arch/mn10300/include/uapi/asm/bitsperlong.h
new file mode 100644
index 0000000000000..6dc0bb0c13b29
--- /dev/null
+++ b/tools/arch/mn10300/include/uapi/asm/bitsperlong.h
@@ -0,0 +1 @@
+#include <asm-generic/bitsperlong.h>
diff --git a/tools/arch/parisc/include/uapi/asm/bitsperlong.h b/tools/arch/parisc/include/uapi/asm/bitsperlong.h
new file mode 100644
index 0000000000000..e0a23c7bdd432
--- /dev/null
+++ b/tools/arch/parisc/include/uapi/asm/bitsperlong.h
@@ -0,0 +1,14 @@
+#ifndef __ASM_PARISC_BITSPERLONG_H
+#define __ASM_PARISC_BITSPERLONG_H
+
+#if defined(__LP64__)
+#define __BITS_PER_LONG 64
+#define SHIFT_PER_LONG 6
+#else
+#define __BITS_PER_LONG 32
+#define SHIFT_PER_LONG 5
+#endif
+
+#include <asm-generic/bitsperlong.h>
+
+#endif /* __ASM_PARISC_BITSPERLONG_H */
diff --git a/tools/arch/powerpc/include/uapi/asm/bitsperlong.h b/tools/arch/powerpc/include/uapi/asm/bitsperlong.h
new file mode 100644
index 0000000000000..5f1659032c408
--- /dev/null
+++ b/tools/arch/powerpc/include/uapi/asm/bitsperlong.h
@@ -0,0 +1,12 @@
+#ifndef __ASM_POWERPC_BITSPERLONG_H
+#define __ASM_POWERPC_BITSPERLONG_H
+
+#if defined(__powerpc64__)
+# define __BITS_PER_LONG 64
+#else
+# define __BITS_PER_LONG 32
+#endif
+
+#include <asm-generic/bitsperlong.h>
+
+#endif /* __ASM_POWERPC_BITSPERLONG_H */
diff --git a/tools/arch/s390/include/uapi/asm/bitsperlong.h b/tools/arch/s390/include/uapi/asm/bitsperlong.h
new file mode 100644
index 0000000000000..e351ea2ad43e7
--- /dev/null
+++ b/tools/arch/s390/include/uapi/asm/bitsperlong.h
@@ -0,0 +1,12 @@
+#ifndef __ASM_S390_BITSPERLONG_H
+#define __ASM_S390_BITSPERLONG_H
+
+#ifndef __s390x__
+#define __BITS_PER_LONG 32
+#else
+#define __BITS_PER_LONG 64
+#endif
+
+#include <asm-generic/bitsperlong.h>
+
+#endif /* __ASM_S390_BITSPERLONG_H */
diff --git a/tools/arch/score/include/uapi/asm/bitsperlong.h b/tools/arch/score/include/uapi/asm/bitsperlong.h
new file mode 100644
index 0000000000000..86ff337aa4597
--- /dev/null
+++ b/tools/arch/score/include/uapi/asm/bitsperlong.h
@@ -0,0 +1,6 @@
+#ifndef _ASM_SCORE_BITSPERLONG_H
+#define _ASM_SCORE_BITSPERLONG_H
+
+#include <asm-generic/bitsperlong.h>
+
+#endif /* _ASM_SCORE_BITSPERLONG_H */
diff --git a/tools/arch/sparc/include/uapi/asm/bitsperlong.h b/tools/arch/sparc/include/uapi/asm/bitsperlong.h
new file mode 100644
index 0000000000000..b62dd907d7c35
--- /dev/null
+++ b/tools/arch/sparc/include/uapi/asm/bitsperlong.h
@@ -0,0 +1,12 @@
+#ifndef __ASM_ALPHA_BITSPERLONG_H
+#define __ASM_ALPHA_BITSPERLONG_H
+
+#if defined(__sparc__) && defined(__arch64__)
+#define __BITS_PER_LONG 64
+#else
+#define __BITS_PER_LONG 32
+#endif
+
+#include <asm-generic/bitsperlong.h>
+
+#endif /* __ASM_ALPHA_BITSPERLONG_H */
diff --git a/tools/arch/tile/include/uapi/asm/bitsperlong.h b/tools/arch/tile/include/uapi/asm/bitsperlong.h
new file mode 100644
index 0000000000000..58c771f2af2f5
--- /dev/null
+++ b/tools/arch/tile/include/uapi/asm/bitsperlong.h
@@ -0,0 +1,26 @@
+/*
+ * Copyright 2010 Tilera Corporation. All Rights Reserved.
+ *
+ *   This program is free software; you can redistribute it and/or
+ *   modify it under the terms of the GNU General Public License
+ *   as published by the Free Software Foundation, version 2.
+ *
+ *   This program is distributed in the hope that it will be useful, but
+ *   WITHOUT ANY WARRANTY; without even the implied warranty of
+ *   MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ *   NON INFRINGEMENT.  See the GNU General Public License for
+ *   more details.
+ */
+
+#ifndef _ASM_TILE_BITSPERLONG_H
+#define _ASM_TILE_BITSPERLONG_H
+
+#ifdef __LP64__
+# define __BITS_PER_LONG 64
+#else
+# define __BITS_PER_LONG 32
+#endif
+
+#include <asm-generic/bitsperlong.h>
+
+#endif /* _ASM_TILE_BITSPERLONG_H */
diff --git a/tools/arch/x86/include/uapi/asm/bitsperlong.h b/tools/arch/x86/include/uapi/asm/bitsperlong.h
new file mode 100644
index 0000000000000..6e23c543cd80b
--- /dev/null
+++ b/tools/arch/x86/include/uapi/asm/bitsperlong.h
@@ -0,0 +1,12 @@
+#ifndef __ASM_X86_BITSPERLONG_H
+#define __ASM_X86_BITSPERLONG_H
+
+#if defined(__x86_64__) && !defined(__ILP32__)
+# define __BITS_PER_LONG 64
+#else
+# define __BITS_PER_LONG 32
+#endif
+
+#include <asm-generic/bitsperlong.h>
+
+#endif /* __ASM_X86_BITSPERLONG_H */
diff --git a/tools/include/asm-generic/bitops/__ffs.h b/tools/include/asm-generic/bitops/__ffs.h
index c94175015a82a..b3accfdf24b9b 100644
--- a/tools/include/asm-generic/bitops/__ffs.h
+++ b/tools/include/asm-generic/bitops/__ffs.h
@@ -2,6 +2,7 @@
 #define _TOOLS_LINUX_ASM_GENERIC_BITOPS___FFS_H_
 
 #include <asm/types.h>
+#include <asm/bitsperlong.h>
 
 /**
  * __ffs - find first bit in word.
diff --git a/tools/include/asm-generic/bitops/atomic.h b/tools/include/asm-generic/bitops/atomic.h
index 4bccd7c3d5d65..18663f59d72f7 100644
--- a/tools/include/asm-generic/bitops/atomic.h
+++ b/tools/include/asm-generic/bitops/atomic.h
@@ -2,6 +2,7 @@
 #define _TOOLS_LINUX_ASM_GENERIC_BITOPS_ATOMIC_H_
 
 #include <asm/types.h>
+#include <asm/bitsperlong.h>
 
 static inline void set_bit(int nr, unsigned long *addr)
 {
diff --git a/tools/include/asm-generic/bitsperlong.h b/tools/include/asm-generic/bitsperlong.h
new file mode 100644
index 0000000000000..d1d70aa190210
--- /dev/null
+++ b/tools/include/asm-generic/bitsperlong.h
@@ -0,0 +1,25 @@
+#ifndef __ASM_GENERIC_BITS_PER_LONG
+#define __ASM_GENERIC_BITS_PER_LONG
+
+#include <uapi/asm-generic/bitsperlong.h>
+
+
+#ifdef CONFIG_64BIT
+#define BITS_PER_LONG 64
+#else
+#define BITS_PER_LONG 32
+#endif /* CONFIG_64BIT */
+
+/*
+ * FIXME: The check currently breaks x86-64 build, so it's
+ * temporarily disabled. Please fix x86-64 and reenable
+ */
+#if 0 && BITS_PER_LONG != __BITS_PER_LONG
+#error Inconsistent word size. Check asm/bitsperlong.h
+#endif
+
+#ifndef BITS_PER_LONG_LONG
+#define BITS_PER_LONG_LONG 64
+#endif
+
+#endif /* __ASM_GENERIC_BITS_PER_LONG */
diff --git a/tools/include/uapi/asm-generic/bitsperlong.h b/tools/include/uapi/asm-generic/bitsperlong.h
new file mode 100644
index 0000000000000..23e6c416b85fc
--- /dev/null
+++ b/tools/include/uapi/asm-generic/bitsperlong.h
@@ -0,0 +1,15 @@
+#ifndef _UAPI__ASM_GENERIC_BITS_PER_LONG
+#define _UAPI__ASM_GENERIC_BITS_PER_LONG
+
+/*
+ * There seems to be no way of detecting this automatically from user
+ * space, so 64 bit architectures should override this in their
+ * bitsperlong.h. In particular, an architecture that supports
+ * both 32 and 64 bit user space must not rely on CONFIG_64BIT
+ * to decide it, but rather check a compiler provided macro.
+ */
+#ifndef __BITS_PER_LONG
+#define __BITS_PER_LONG 32
+#endif
+
+#endif /* _UAPI__ASM_GENERIC_BITS_PER_LONG */

From 1d4489d0ec141fe77eb79ce9bf9179d0342cb809 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 12 Jul 2016 11:31:39 -0300
Subject: [PATCH 52/66] perf tools: Add the tools/ stringify copy to the
 MANIFEST

So that we don't end up using the kernel one when building out of tree,
via a detached tarball.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Fixes: 737ef7d32cb4 ("tools include: Copy linux/stringify.h from the kernel")
Link: http://lkml.kernel.org/n/tip-t8yn1d7y0magk889ymc8jlai@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/MANIFEST | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST
index db7cfb42a6750..923eda2e7d527 100644
--- a/tools/perf/MANIFEST
+++ b/tools/perf/MANIFEST
@@ -73,6 +73,7 @@ tools/include/linux/poison.h
 tools/include/linux/rbtree.h
 tools/include/linux/rbtree_augmented.h
 tools/include/linux/string.h
+tools/include/linux/stringify.h
 tools/include/linux/types.h
 tools/include/linux/err.h
 tools/include/linux/bitmap.h
@@ -83,7 +84,6 @@ include/asm-generic/bitops/__fls.h
 include/asm-generic/bitops/fls.h
 include/linux/list.h
 include/linux/hash.h
-include/linux/stringify.h
 include/linux/swab.h
 arch/*/include/asm/unistd*.h
 arch/*/include/uapi/asm/unistd*.h

From 3c7752f7ab6d591d07f0851321d6ab1ace46e6fb Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Mon, 11 Jul 2016 23:39:58 -0300
Subject: [PATCH 53/66] perf tools: Don't add kernel directories to the header
 search path

We've decided not to access kernel source files because changes there
could break the tooling side, this is one more step in that direction.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-ar0hupkxl45h5hk09l2rprj3@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/config/Makefile | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index 49a2130682830..97d47140a6378 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -210,11 +210,7 @@ CFLAGS += -I$(srctree)/tools/include/uapi
 CFLAGS += -I$(srctree)/tools/include/
 CFLAGS += -I$(srctree)/tools/arch/$(ARCH)/include/uapi
 CFLAGS += -I$(srctree)/tools/arch/$(ARCH)/include/
-CFLAGS += -I$(srctree)/arch/$(ARCH)/include/uapi
-CFLAGS += -I$(srctree)/arch/$(ARCH)/include
 CFLAGS += -I$(srctree)/tools/arch/$(ARCH)/
-CFLAGS += -I$(srctree)/include/uapi
-CFLAGS += -I$(srctree)/include
 
 # $(obj-perf)      for generated common-cmds.h
 # $(obj-perf)/util for generated bison/flex headers

From c8a3f7de76717a994c208e137156c077b1e93092 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 12 Jul 2016 12:16:35 -0300
Subject: [PATCH 54/66] perf intel-pt-decoder: Avoid checking code drift on
 busibox's diff

That doesn't have -I to match lines.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-7nz9hnbk7a9p91ou927ye5yh@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/intel-pt-decoder/Build | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/tools/perf/util/intel-pt-decoder/Build b/tools/perf/util/intel-pt-decoder/Build
index 0611d619a42e6..9b742ea8bfe84 100644
--- a/tools/perf/util/intel-pt-decoder/Build
+++ b/tools/perf/util/intel-pt-decoder/Build
@@ -7,8 +7,11 @@ $(OUTPUT)util/intel-pt-decoder/inat-tables.c: $(inat_tables_script) $(inat_table
 	$(call rule_mkdir)
 	@$(call echo-cmd,gen)$(AWK) -f $(inat_tables_script) $(inat_tables_maps) > $@ || rm -f $@
 
+# Busybox's diff doesn't have -I, avoid warning in the case
+
 $(OUTPUT)util/intel-pt-decoder/intel-pt-insn-decoder.o: util/intel-pt-decoder/intel-pt-insn-decoder.c util/intel-pt-decoder/inat.c $(OUTPUT)util/intel-pt-decoder/inat-tables.c
-	@(test -d ../../kernel -a -d ../../tools -a -d ../perf && (( \
+	@(diff -I 2>&1 | grep -q 'option requires an argument' && \
+	test -d ../../kernel -a -d ../../tools -a -d ../perf && (( \
 	diff -B -I'^#include' util/intel-pt-decoder/insn.c ../../arch/x86/lib/insn.c >/dev/null && \
 	diff -B -I'^#include' util/intel-pt-decoder/inat.c ../../arch/x86/lib/inat.c >/dev/null && \
 	diff -B util/intel-pt-decoder/x86-opcode-map.txt ../../arch/x86/lib/x86-opcode-map.txt >/dev/null && \

From 1c1a3a4729aae712c55e001e151ef008d030d4a7 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 12 Jul 2016 12:19:09 -0300
Subject: [PATCH 55/66] perf tools: Add feature detection for gelf_getnote()

That is not present on some libelf implementations, such as the one used
in Alpine Linux: libelf-0.8.13.

This ends up disabling the SDT code, that relies on this function.

One alternative would be to provide an weak fallback implementation or
the open coded variant used by the buildid sysfs notes reading code.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ananth N Mavinakayanahalli <ananth@linux.vnet.ibm.com>
Cc: Brendan Gregg <brendan.d.gregg@gmail.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Hemant Kumar <hemant@linux.vnet.ibm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-82lh22ybedy9b9lych8xj12g@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/build/Makefile.feature                   | 1 +
 tools/build/feature/Makefile                   | 4 ++++
 tools/build/feature/test-all.c                 | 5 +++++
 tools/build/feature/test-libelf-gelf_getnote.c | 7 +++++++
 tools/perf/config/Makefile                     | 6 ++++++
 tools/perf/util/build-id.c                     | 2 +-
 tools/perf/util/probe-file.c                   | 2 ++
 tools/perf/util/symbol-elf.c                   | 2 ++
 8 files changed, 28 insertions(+), 1 deletion(-)
 create mode 100644 tools/build/feature/test-libelf-gelf_getnote.c

diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature
index 3dd529bb06047..fe12bee574180 100644
--- a/tools/build/Makefile.feature
+++ b/tools/build/Makefile.feature
@@ -40,6 +40,7 @@ FEATURE_TESTS_BASIC :=			\
 	libbfd				\
 	libelf				\
 	libelf-getphdrnum		\
+	libelf-gelf_getnote		\
 	libelf-getshdrstrndx		\
 	libelf-mmap			\
 	libnuma				\
diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile
index 674711629ef0b..d6017c1abdb00 100644
--- a/tools/build/feature/Makefile
+++ b/tools/build/feature/Makefile
@@ -17,6 +17,7 @@ FILES=					\
 	test-cplus-demangle.bin		\
 	test-libelf.bin			\
 	test-libelf-getphdrnum.bin	\
+	test-libelf-gelf_getnote.bin	\
 	test-libelf-getshdrstrndx.bin	\
 	test-libelf-mmap.bin		\
 	test-libnuma.bin		\
@@ -99,6 +100,9 @@ $(OUTPUT)test-libelf-mmap.bin:
 $(OUTPUT)test-libelf-getphdrnum.bin:
 	$(BUILD) -lelf
 
+$(OUTPUT)test-libelf-gelf_getnote.bin:
+	$(BUILD) -lelf
+
 $(OUTPUT)test-libelf-getshdrstrndx.bin:
 	$(BUILD) -lelf
 
diff --git a/tools/build/feature/test-all.c b/tools/build/feature/test-all.c
index 7433cca333067..843aed024a3a9 100644
--- a/tools/build/feature/test-all.c
+++ b/tools/build/feature/test-all.c
@@ -49,6 +49,10 @@
 # include "test-libelf-getphdrnum.c"
 #undef main
 
+#define main main_test_libelf_gelf_getnote
+# include "test-libelf-gelf_getnote.c"
+#undef main
+
 #define main main_test_libelf_getshdrstrndx
 # include "test-libelf-getshdrstrndx.c"
 #undef main
@@ -153,6 +157,7 @@ int main(int argc, char *argv[])
 	main_test_dwarf();
 	main_test_dwarf_getlocations();
 	main_test_libelf_getphdrnum();
+	main_test_libelf_gelf_getnote();
 	main_test_libelf_getshdrstrndx();
 	main_test_libunwind();
 	main_test_libaudit();
diff --git a/tools/build/feature/test-libelf-gelf_getnote.c b/tools/build/feature/test-libelf-gelf_getnote.c
new file mode 100644
index 0000000000000..d78cf4d5271f1
--- /dev/null
+++ b/tools/build/feature/test-libelf-gelf_getnote.c
@@ -0,0 +1,7 @@
+#include <stdlib.h>
+#include <gelf.h>
+
+int main(void)
+{
+	return gelf_getnote(NULL, 0, NULL, NULL, NULL);
+}
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index 97d47140a6378..5ac4280607794 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -309,6 +309,12 @@ ifndef NO_LIBELF
     CFLAGS += -DHAVE_ELF_GETPHDRNUM_SUPPORT
   endif
 
+  ifeq ($(feature-libelf-gelf_getnote), 1)
+    CFLAGS += -DHAVE_GELF_GETNOTE_SUPPORT
+  else
+    msg := $(warning gelf_getnote() not found on libelf, SDT support disabled);
+  endif
+
   ifeq ($(feature-libelf-getshdrstrndx), 1)
     CFLAGS += -DHAVE_ELF_GETSHDRSTRNDX_SUPPORT
   endif
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index e1a16408da9ce..1e504e40dac88 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -533,7 +533,7 @@ int build_id_cache__list_build_ids(const char *pathname,
 	return ret;
 }
 
-#ifdef HAVE_LIBELF_SUPPORT
+#if defined(HAVE_LIBELF_SUPPORT) && defined(HAVE_GELF_GETNOTE_SUPPORT)
 static int build_id_cache__add_sdt_cache(const char *sbuild_id,
 					  const char *realname)
 {
diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c
index 98398b55a03f4..e705a742ee1ed 100644
--- a/tools/perf/util/probe-file.c
+++ b/tools/perf/util/probe-file.c
@@ -624,6 +624,7 @@ int probe_cache__add_entry(struct probe_cache *pcache,
 	return ret;
 }
 
+#ifdef HAVE_GELF_GETNOTE_SUPPORT
 static unsigned long long sdt_note__get_addr(struct sdt_note *note)
 {
 	return note->bit32 ? (unsigned long long)note->addr.a32[0]
@@ -682,6 +683,7 @@ int probe_cache__scan_sdt(struct probe_cache *pcache, const char *pathname)
 	cleanup_sdt_note_list(&sdtlist);
 	return ret;
 }
+#endif
 
 static int probe_cache_entry__write(struct probe_cache_entry *entry, int fd)
 {
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 79a6a190f41df..cebf98ec27bc4 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -1790,6 +1790,7 @@ void kcore_extract__delete(struct kcore_extract *kce)
 	unlink(kce->extract_filename);
 }
 
+#ifdef HAVE_GELF_GETNOTE_SUPPORT
 /**
  * populate_sdt_note : Parse raw data and identify SDT note
  * @elf: elf of the opened file
@@ -2041,6 +2042,7 @@ int sdt_notes__get_count(struct list_head *start)
 		count++;
 	return count;
 }
+#endif
 
 void symbol__elf_init(void)
 {

From cae15db74999edb96dd9f5bbd4d55849391dd92b Mon Sep 17 00:00:00 2001
From: David Tolnay <dtolnay@gmail.com>
Date: Sat, 9 Jul 2016 00:20:00 -0700
Subject: [PATCH 56/66] perf symbols: Add Rust demangling

Rust demangling is another step after bfd demangling. Add a diagnosis to
identify mangled Rust symbols based on the hash that the Rust mangler appends
as the last path component, as well as other characteristics.  Add a demangler
to reconstruct the original symbol.

Committer notes:

How I tested it:

Enabled COPR on Fedora 24 and then installed the 'rust-binary' package,
with it:

  $ cat src/main.rs
  fn main() {
      println!("Hello, world!");
  }
  $ cat Cargo.toml
  [package]

  name = "hello_world"
  version = "0.0.1"
  authors = [ "Arnaldo Carvalho de Melo <acme@kernel.org>" ]

  $ perf record cargo bench
   Compiling hello_world v0.0.1 (file:///home/acme/projects/hello_world)
     Running target/release/hello_world-d4b9dab4b2a47d75

  running 0 tests

  test result: ok. 0 passed; 0 failed; 0 ignored; 0 measured

  [ perf record: Woken up 1 times to write data ]
  [ perf record: Captured and wrote 0.096 MB perf.data (1457 samples) ]
  $

Before this patch:

  $ perf report --stdio --dsos librbml-e8edd0fd.so
  # dso: librbml-e8edd0fd.so
  #
  # Total Lost Samples: 0
  #
  # Samples: 1K of event 'cycles:u'
  # Event count (approx.): 979599126
  #
  # Overhead  Command  Symbol
  # ........  .......  .............................................................................................................
  #
       1.78%  rustc    [.] rbml::reader::maybe_get_doc::hb9d387df6024b15b
       1.50%  rustc    [.] _$LT$reader..DocsIterator$LT$$u27$a$GT$$u20$as$u20$std..iter..Iterator$GT$::next::hd9af9e60d79a35c8
       1.20%  rustc    [.] rbml::reader::doc_at::hc88107fba445af31
       0.46%  rustc    [.] _$LT$reader..TaggedDocsIterator$LT$$u27$a$GT$$u20$as$u20$std..iter..Iterator$GT$::next::h0cb40e696e4bb489
       0.35%  rustc    [.] rbml::reader::Decoder::_next_int::h66eef7825a398bc3
       0.29%  rustc    [.] rbml::reader::Decoder::_next_sub::h8e5266005580b836
       0.15%  rustc    [.] rbml::reader::get_doc::h094521c645459139
       0.14%  rustc    [.] _$LT$reader..Decoder$LT$$u27$doc$GT$$u20$as$u20$serialize..Decoder$GT$::read_u32::h0acea2fff9669327
       0.07%  rustc    [.] rbml::reader::Decoder::next_doc::h6714d469c9dfaf91
       0.07%  rustc    [.] _ZN4rbml6reader10doc_as_u6417h930b740aa94f1d3aE@plt
       0.06%  rustc    [.] _fini
  $

After:

  $ perf report --stdio --dsos librbml-e8edd0fd.so
  # dso: librbml-e8edd0fd.so
  #
  # Total Lost Samples: 0
  #
  # Samples: 1K of event 'cycles:u'
  # Event count (approx.): 979599126
  #
  # Overhead  Command  Symbol
  # ........  .......  .................................................................
  #
     1.78%  rustc    [.] rbml::reader::maybe_get_doc
     1.50%  rustc    [.] <reader::DocsIterator<'a> as std::iter::Iterator>::next
     1.20%  rustc    [.] rbml::reader::doc_at
     0.46%  rustc    [.] <reader::TaggedDocsIterator<'a> as std::iter::Iterator>::next
     0.35%  rustc    [.] rbml::reader::Decoder::_next_int
     0.29%  rustc    [.] rbml::reader::Decoder::_next_sub
     0.15%  rustc    [.] rbml::reader::get_doc
     0.14%  rustc    [.] <reader::Decoder<'doc> as serialize::Decoder>::read_u32
     0.07%  rustc    [.] rbml::reader::Decoder::next_doc
     0.07%  rustc    [.] _ZN4rbml6reader10doc_as_u6417h930b740aa94f1d3aE@plt
     0.06%  rustc    [.] _fini
  $

Signed-off-by: David Tolnay <dtolnay@gmail.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/5780B7FA.3030602@gmail.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/Build           |   1 +
 tools/perf/util/demangle-rust.c | 269 ++++++++++++++++++++++++++++++++
 tools/perf/util/demangle-rust.h |   7 +
 tools/perf/util/symbol-elf.c    |   8 +
 4 files changed, 285 insertions(+)
 create mode 100644 tools/perf/util/demangle-rust.c
 create mode 100644 tools/perf/util/demangle-rust.h

diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index eda68f5828849..2fa7d8b698731 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -113,6 +113,7 @@ libperf-y += scripting-engines/
 libperf-$(CONFIG_ZLIB) += zlib.o
 libperf-$(CONFIG_LZMA) += lzma.o
 libperf-y += demangle-java.o
+libperf-y += demangle-rust.o
 
 ifdef CONFIG_JITDUMP
 libperf-$(CONFIG_LIBELF) += jitdump.o
diff --git a/tools/perf/util/demangle-rust.c b/tools/perf/util/demangle-rust.c
new file mode 100644
index 0000000000000..f9dafa888c063
--- /dev/null
+++ b/tools/perf/util/demangle-rust.c
@@ -0,0 +1,269 @@
+#include <string.h>
+#include "util.h"
+#include "debug.h"
+
+#include "demangle-rust.h"
+
+/*
+ * Mangled Rust symbols look like this:
+ *
+ *     _$LT$std..sys..fd..FileDesc$u20$as$u20$core..ops..Drop$GT$::drop::hc68340e1baa4987a
+ *
+ * The original symbol is:
+ *
+ *     <std::sys::fd::FileDesc as core::ops::Drop>::drop
+ *
+ * The last component of the path is a 64-bit hash in lowercase hex, prefixed
+ * with "h". Rust does not have a global namespace between crates, an illusion
+ * which Rust maintains by using the hash to distinguish things that would
+ * otherwise have the same symbol.
+ *
+ * Any path component not starting with a XID_Start character is prefixed with
+ * "_".
+ *
+ * The following escape sequences are used:
+ *
+ *     ","  =>  $C$
+ *     "@"  =>  $SP$
+ *     "*"  =>  $BP$
+ *     "&"  =>  $RF$
+ *     "<"  =>  $LT$
+ *     ">"  =>  $GT$
+ *     "("  =>  $LP$
+ *     ")"  =>  $RP$
+ *     " "  =>  $u20$
+ *     "'"  =>  $u27$
+ *     "["  =>  $u5b$
+ *     "]"  =>  $u5d$
+ *     "~"  =>  $u7e$
+ *
+ * A double ".." means "::" and a single "." means "-".
+ *
+ * The only characters allowed in the mangled symbol are a-zA-Z0-9 and _.:$
+ */
+
+static const char *hash_prefix = "::h";
+static const size_t hash_prefix_len = 3;
+static const size_t hash_len = 16;
+
+static bool is_prefixed_hash(const char *start);
+static bool looks_like_rust(const char *sym, size_t len);
+static bool unescape(const char **in, char **out, const char *seq, char value);
+
+/*
+ * INPUT:
+ *     sym: symbol that has been through BFD-demangling
+ *
+ * This function looks for the following indicators:
+ *
+ *  1. The hash must consist of "h" followed by 16 lowercase hex digits.
+ *
+ *  2. As a sanity check, the hash must use between 5 and 15 of the 16 possible
+ *     hex digits. This is true of 99.9998% of hashes so once in your life you
+ *     may see a false negative. The point is to notice path components that
+ *     could be Rust hashes but are probably not, like "haaaaaaaaaaaaaaaa". In
+ *     this case a false positive (non-Rust symbol has an important path
+ *     component removed because it looks like a Rust hash) is worse than a
+ *     false negative (the rare Rust symbol is not demangled) so this sets the
+ *     balance in favor of false negatives.
+ *
+ *  3. There must be no characters other than a-zA-Z0-9 and _.:$
+ *
+ *  4. There must be no unrecognized $-sign sequences.
+ *
+ *  5. There must be no sequence of three or more dots in a row ("...").
+ */
+bool
+rust_is_mangled(const char *sym)
+{
+	size_t len, len_without_hash;
+
+	if (!sym)
+		return false;
+
+	len = strlen(sym);
+	if (len <= hash_prefix_len + hash_len)
+		/* Not long enough to contain "::h" + hash + something else */
+		return false;
+
+	len_without_hash = len - (hash_prefix_len + hash_len);
+	if (!is_prefixed_hash(sym + len_without_hash))
+		return false;
+
+	return looks_like_rust(sym, len_without_hash);
+}
+
+/*
+ * A hash is the prefix "::h" followed by 16 lowercase hex digits. The hex
+ * digits must comprise between 5 and 15 (inclusive) distinct digits.
+ */
+static bool is_prefixed_hash(const char *str)
+{
+	const char *end;
+	bool seen[16];
+	size_t i;
+	int count;
+
+	if (strncmp(str, hash_prefix, hash_prefix_len))
+		return false;
+	str += hash_prefix_len;
+
+	memset(seen, false, sizeof(seen));
+	for (end = str + hash_len; str < end; str++)
+		if (*str >= '0' && *str <= '9')
+			seen[*str - '0'] = true;
+		else if (*str >= 'a' && *str <= 'f')
+			seen[*str - 'a' + 10] = true;
+		else
+			return false;
+
+	/* Count how many distinct digits seen */
+	count = 0;
+	for (i = 0; i < 16; i++)
+		if (seen[i])
+			count++;
+
+	return count >= 5 && count <= 15;
+}
+
+static bool looks_like_rust(const char *str, size_t len)
+{
+	const char *end = str + len;
+
+	while (str < end)
+		switch (*str) {
+		case '$':
+			if (!strncmp(str, "$C$", 3))
+				str += 3;
+			else if (!strncmp(str, "$SP$", 4)
+					|| !strncmp(str, "$BP$", 4)
+					|| !strncmp(str, "$RF$", 4)
+					|| !strncmp(str, "$LT$", 4)
+					|| !strncmp(str, "$GT$", 4)
+					|| !strncmp(str, "$LP$", 4)
+					|| !strncmp(str, "$RP$", 4))
+				str += 4;
+			else if (!strncmp(str, "$u20$", 5)
+					|| !strncmp(str, "$u27$", 5)
+					|| !strncmp(str, "$u5b$", 5)
+					|| !strncmp(str, "$u5d$", 5)
+					|| !strncmp(str, "$u7e$", 5))
+				str += 5;
+			else
+				return false;
+			break;
+		case '.':
+			/* Do not allow three or more consecutive dots */
+			if (!strncmp(str, "...", 3))
+				return false;
+			/* Fall through */
+		case 'a' ... 'z':
+		case 'A' ... 'Z':
+		case '0' ... '9':
+		case '_':
+		case ':':
+			str++;
+			break;
+		default:
+			return false;
+		}
+
+	return true;
+}
+
+/*
+ * INPUT:
+ *     sym: symbol for which rust_is_mangled(sym) returns true
+ *
+ * The input is demangled in-place because the mangled name is always longer
+ * than the demangled one.
+ */
+void
+rust_demangle_sym(char *sym)
+{
+	const char *in;
+	char *out;
+	const char *end;
+
+	if (!sym)
+		return;
+
+	in = sym;
+	out = sym;
+	end = sym + strlen(sym) - (hash_prefix_len + hash_len);
+
+	while (in < end)
+		switch (*in) {
+		case '$':
+			if (!(unescape(&in, &out, "$C$", ',')
+					|| unescape(&in, &out, "$SP$", '@')
+					|| unescape(&in, &out, "$BP$", '*')
+					|| unescape(&in, &out, "$RF$", '&')
+					|| unescape(&in, &out, "$LT$", '<')
+					|| unescape(&in, &out, "$GT$", '>')
+					|| unescape(&in, &out, "$LP$", '(')
+					|| unescape(&in, &out, "$RP$", ')')
+					|| unescape(&in, &out, "$u20$", ' ')
+					|| unescape(&in, &out, "$u27$", '\'')
+					|| unescape(&in, &out, "$u5b$", '[')
+					|| unescape(&in, &out, "$u5d$", ']')
+					|| unescape(&in, &out, "$u7e$", '~'))) {
+				pr_err("demangle-rust: unexpected escape sequence");
+				goto done;
+			}
+			break;
+		case '_':
+			/*
+			 * If this is the start of a path component and the next
+			 * character is an escape sequence, ignore the
+			 * underscore. The mangler inserts an underscore to make
+			 * sure the path component begins with a XID_Start
+			 * character.
+			 */
+			if ((in == sym || in[-1] == ':') && in[1] == '$')
+				in++;
+			else
+				*out++ = *in++;
+			break;
+		case '.':
+			if (in[1] == '.') {
+				/* ".." becomes "::" */
+				*out++ = ':';
+				*out++ = ':';
+				in += 2;
+			} else {
+				/* "." becomes "-" */
+				*out++ = '-';
+				in++;
+			}
+			break;
+		case 'a' ... 'z':
+		case 'A' ... 'Z':
+		case '0' ... '9':
+		case ':':
+			*out++ = *in++;
+			break;
+		default:
+			pr_err("demangle-rust: unexpected character '%c' in symbol\n",
+				*in);
+			goto done;
+		}
+
+done:
+	*out = '\0';
+}
+
+static bool unescape(const char **in, char **out, const char *seq, char value)
+{
+	size_t len = strlen(seq);
+
+	if (strncmp(*in, seq, len))
+		return false;
+
+	**out = value;
+
+	*in += len;
+	*out += 1;
+
+	return true;
+}
diff --git a/tools/perf/util/demangle-rust.h b/tools/perf/util/demangle-rust.h
new file mode 100644
index 0000000000000..7b41ead7e0ddf
--- /dev/null
+++ b/tools/perf/util/demangle-rust.h
@@ -0,0 +1,7 @@
+#ifndef __PERF_DEMANGLE_RUST
+#define __PERF_DEMANGLE_RUST 1
+
+bool rust_is_mangled(const char *str);
+void rust_demangle_sym(char *str);
+
+#endif /* __PERF_DEMANGLE_RUST */
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index cebf98ec27bc4..a34321e9b44d8 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -7,6 +7,7 @@
 
 #include "symbol.h"
 #include "demangle-java.h"
+#include "demangle-rust.h"
 #include "machine.h"
 #include "vdso.h"
 #include <symbol/kallsyms.h>
@@ -1081,6 +1082,13 @@ int dso__load_sym(struct dso *dso, struct map *map,
 			demangled = bfd_demangle(NULL, elf_name, demangle_flags);
 			if (demangled == NULL)
 				demangled = java_demangle_sym(elf_name, JAVA_DEMANGLE_NORET);
+			else if (rust_is_mangled(demangled))
+				/*
+				 * Input to Rust demangling is the BFD-demangled
+				 * name which it Rust-demangles in place.
+				 */
+				rust_demangle_sym(demangled);
+
 			if (demangled != NULL)
 				elf_name = demangled;
 		}

From 7cb5c5acaba9fa0b90ca11275f19131d3eca35c2 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Sun, 10 Jul 2016 13:07:53 +0200
Subject: [PATCH 57/66] perf evlist: Make event2evsel public

It will be used outside of evlist.c object in folowing patches.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1468148882-10362-2-git-send-email-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/evlist.c | 4 ++--
 tools/perf/util/evlist.h | 3 +++
 2 files changed, 5 insertions(+), 2 deletions(-)

diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index f2d478df8c3e4..862e69c2690d1 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -651,8 +651,8 @@ static int perf_evlist__event2id(struct perf_evlist *evlist,
 	return 0;
 }
 
-static struct perf_evsel *perf_evlist__event2evsel(struct perf_evlist *evlist,
-						   union perf_event *event)
+struct perf_evsel *perf_evlist__event2evsel(struct perf_evlist *evlist,
+					    union perf_event *event)
 {
 	struct perf_evsel *first = perf_evlist__first(evlist);
 	struct hlist_head *head;
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 872912b392c9f..afd087761a475 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -323,4 +323,7 @@ void perf_event_attr__set_max_precise_ip(struct perf_event_attr *attr);
 
 struct perf_evsel *
 perf_evlist__find_evsel_by_str(struct perf_evlist *evlist, const char *str);
+
+struct perf_evsel *perf_evlist__event2evsel(struct perf_evlist *evlist,
+					    union perf_event *event);
 #endif /* __PERF_EVLIST_H */

From 71fe1052af98fc5b615c067425aeb6fe39a0368c Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Sun, 10 Jul 2016 13:07:54 +0200
Subject: [PATCH 58/66] perf tools: Introduce trace_event__tp_format_id()

To get struct event_format object from tracepoint ID.  It will be used
in following patches.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1468148882-10362-3-git-send-email-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/trace-event.c | 8 ++++++++
 tools/perf/util/trace-event.h | 2 ++
 2 files changed, 10 insertions(+)

diff --git a/tools/perf/util/trace-event.c b/tools/perf/util/trace-event.c
index 8ae051e0ec790..c330780674fcf 100644
--- a/tools/perf/util/trace-event.c
+++ b/tools/perf/util/trace-event.c
@@ -105,3 +105,11 @@ trace_event__tp_format(const char *sys, const char *name)
 
 	return tp_format(sys, name);
 }
+
+struct event_format *trace_event__tp_format_id(int id)
+{
+	if (!tevent_initialized && trace_event__init2())
+		return ERR_PTR(-ENOMEM);
+
+	return pevent_find_event(tevent.pevent, id);
+}
diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h
index bce5b1dac2682..b0af9c81bb0df 100644
--- a/tools/perf/util/trace-event.h
+++ b/tools/perf/util/trace-event.h
@@ -23,6 +23,8 @@ int trace_event__register_resolver(struct machine *machine,
 struct event_format*
 trace_event__tp_format(const char *sys, const char *name);
 
+struct event_format *trace_event__tp_format_id(int id);
+
 int bigendian(void);
 
 void event_format__fprintf(struct event_format *event,

From ad4e3c04587c01c2e2b00c0e6a414dbededa6c55 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Sun, 10 Jul 2016 13:07:55 +0200
Subject: [PATCH 59/66] perf python: Init perf_event_attr::size in perf.evsel
 constructor

Currently 0 is passed as perf_event_attr::size, which could block usage
of new features.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1468148882-10362-4-git-send-email-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/python.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index 65c6c73d28fe4..d0c1267741eec 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -653,6 +653,7 @@ static int pyrf_evsel__init(struct pyrf_evsel *pevsel,
 	attr.precise_ip	    = precise_ip;
 	attr.mmap_data	    = mmap_data;
 	attr.sample_id_all  = sample_id_all;
+	attr.size	    = sizeof(attr);
 
 	perf_evsel__init(&pevsel->evsel, &attr, idx);
 	return 0;

From e8968e654191390a1300f0847250353a1c9da30d Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Sun, 10 Jul 2016 13:07:56 +0200
Subject: [PATCH 60/66] perf python: Fix pyrf_evlist__read_on_cpu event
 consuming

We can't consume the event before parsing it. Under heavy load we could
get caught by kernel writer overwriting the event we're trying to parse.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1468148882-10362-5-git-send-email-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/python.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index d0c1267741eec..c68ef03191142 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -865,12 +865,14 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist,
 		PyObject *pyevent = pyrf_event__new(event);
 		struct pyrf_event *pevent = (struct pyrf_event *)pyevent;
 
-		perf_evlist__mmap_consume(evlist, cpu);
-
 		if (pyevent == NULL)
 			return PyErr_NoMemory();
 
 		err = perf_evlist__parse_sample(evlist, event, &pevent->sample);
+
+		/* Consume the even only after we parsed it out. */
+		perf_evlist__mmap_consume(evlist, cpu);
+
 		if (err)
 			return PyErr_Format(PyExc_OSError,
 					    "perf: can't parse sample, err=%d", err);

From 85e37de3a993b9e407398f792b996acad27f4cdc Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Sun, 10 Jul 2016 13:07:57 +0200
Subject: [PATCH 61/66] perf python: Put perf.event objects into dictionary

Make perf.event object parts of the perf module dictionary so we can
address them by name.

The following objects/names are added:

  mmap_event
  lost_event
  comm_event
  task_event
  throttle_event
  task_event
  read_event
  sample_event
  switch_event

We can now use it in python script like:
  ...
  event = evlist.read_on_cpu(cpu)
  ...
  if not isinstance(event, perf.sample_event):

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1468148882-10362-6-git-send-email-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/python.c | 27 +++++++++++++++++++++++++++
 1 file changed, 27 insertions(+)

diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index c68ef03191142..fc277e486d17c 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -1103,6 +1103,33 @@ PyMODINIT_FUNC initperf(void)
 	Py_INCREF(&pyrf_evsel__type);
 	PyModule_AddObject(module, "evsel", (PyObject*)&pyrf_evsel__type);
 
+	Py_INCREF(&pyrf_mmap_event__type);
+	PyModule_AddObject(module, "mmap_event", (PyObject *)&pyrf_mmap_event__type);
+
+	Py_INCREF(&pyrf_lost_event__type);
+	PyModule_AddObject(module, "lost_event", (PyObject *)&pyrf_lost_event__type);
+
+	Py_INCREF(&pyrf_comm_event__type);
+	PyModule_AddObject(module, "comm_event", (PyObject *)&pyrf_comm_event__type);
+
+	Py_INCREF(&pyrf_task_event__type);
+	PyModule_AddObject(module, "task_event", (PyObject *)&pyrf_task_event__type);
+
+	Py_INCREF(&pyrf_throttle_event__type);
+	PyModule_AddObject(module, "throttle_event", (PyObject *)&pyrf_throttle_event__type);
+
+	Py_INCREF(&pyrf_task_event__type);
+	PyModule_AddObject(module, "task_event", (PyObject *)&pyrf_task_event__type);
+
+	Py_INCREF(&pyrf_read_event__type);
+	PyModule_AddObject(module, "read_event", (PyObject *)&pyrf_read_event__type);
+
+	Py_INCREF(&pyrf_sample_event__type);
+	PyModule_AddObject(module, "sample_event", (PyObject *)&pyrf_sample_event__type);
+
+	Py_INCREF(&pyrf_context_switch_event__type);
+	PyModule_AddObject(module, "switch_event", (PyObject *)&pyrf_context_switch_event__type);
+
 	Py_INCREF(&pyrf_thread_map__type);
 	PyModule_AddObject(module, "thread_map", (PyObject*)&pyrf_thread_map__type);
 

From 1075fbb22f095c857930190e30fd3ae422d424b6 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Sun, 10 Jul 2016 13:07:58 +0200
Subject: [PATCH 62/66] perf python: Add perf.tracepoint method

To get id of the tracepoint from subsystem and name strings. The
interface is:

  id = perf.tracepoint(sys, name)

In case of error -1 is returned.

It will be used to get python tracepoint event's config value for
tracepoint event.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1468148882-10362-7-git-send-email-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/python.c | 26 ++++++++++++++++++++++++++
 1 file changed, 26 insertions(+)

diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index fc277e486d17c..45fdd4a687217 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -2,6 +2,7 @@
 #include <structmember.h>
 #include <inttypes.h>
 #include <poll.h>
+#include <linux/err.h>
 #include "evlist.h"
 #include "evsel.h"
 #include "event.h"
@@ -1076,7 +1077,32 @@ static struct {
 	{ .name = NULL, },
 };
 
+static PyObject *pyrf__tracepoint(struct pyrf_evsel *pevsel,
+				  PyObject *args, PyObject *kwargs)
+{
+	struct event_format *tp_format;
+	static char *kwlist[] = { "sys", "name", NULL };
+	char *sys  = NULL;
+	char *name = NULL;
+
+	if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|ss", kwlist,
+					 &sys, &name))
+		return NULL;
+
+	tp_format = trace_event__tp_format(sys, name);
+	if (IS_ERR(tp_format))
+		return PyInt_FromLong(-1);
+
+	return PyInt_FromLong(tp_format->id);
+}
+
 static PyMethodDef perf__methods[] = {
+	{
+		.ml_name  = "tracepoint",
+		.ml_meth  = (PyCFunction) pyrf__tracepoint,
+		.ml_flags = METH_VARARGS | METH_KEYWORDS,
+		.ml_doc	  = PyDoc_STR("Get tracepoint config.")
+	},
 	{ .ml_name = NULL, }
 };
 

From 377f698db12150a1cf79987dca1d3990fa14a1f8 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Sun, 10 Jul 2016 13:07:59 +0200
Subject: [PATCH 63/66] perf python: Add struct evsel into struct pyrf_event

To be able to find out event configuration info during sample parsing.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1468148882-10362-8-git-send-email-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/python.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index 45fdd4a687217..dc7adaa3a02c9 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -48,6 +48,7 @@ PyMODINIT_FUNC initperf(void);
 
 struct pyrf_event {
 	PyObject_HEAD
+	struct perf_evsel *evsel;
 	struct perf_sample sample;
 	union perf_event   event;
 };
@@ -865,11 +866,18 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist,
 	if (event != NULL) {
 		PyObject *pyevent = pyrf_event__new(event);
 		struct pyrf_event *pevent = (struct pyrf_event *)pyevent;
+		struct perf_evsel *evsel;
 
 		if (pyevent == NULL)
 			return PyErr_NoMemory();
 
-		err = perf_evlist__parse_sample(evlist, event, &pevent->sample);
+		evsel = perf_evlist__event2evsel(evlist, event);
+		if (!evsel)
+			return Py_None;
+
+		pevent->evsel = evsel;
+
+		err = perf_evsel__parse_sample(evsel, event, &pevent->sample);
 
 		/* Consume the even only after we parsed it out. */
 		perf_evlist__mmap_consume(evlist, cpu);

From bae57e3825a3dded15f61cd20c6757d60ad6c712 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Sun, 10 Jul 2016 13:08:00 +0200
Subject: [PATCH 64/66] perf python: Add support to resolve tracepoint fields

Adding tp_getattro callback for sample event. It resolves tracepoint
fields in runtime.

It's now possible to access tracepoint fields in normal fashion like
hardcoded ones (see the example in the next patch).

Reported-and-Tested-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1468148882-10362-9-git-send-email-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/python.c | 92 ++++++++++++++++++++++++++++++++++++++++
 1 file changed, 92 insertions(+)

diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index dc7adaa3a02c9..d32f970337186 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -290,6 +290,97 @@ static PyObject *pyrf_sample_event__repr(struct pyrf_event *pevent)
 	return ret;
 }
 
+static bool is_tracepoint(struct pyrf_event *pevent)
+{
+	return pevent->evsel->attr.type == PERF_TYPE_TRACEPOINT;
+}
+
+static int is_printable_array(char *p, unsigned int len)
+{
+	unsigned int i;
+
+	for (i = 0; i < len; i++) {
+		if (!isprint(p[i]) && !isspace(p[i]))
+			return 0;
+	}
+
+	return 1;
+}
+
+static PyObject*
+tracepoint_field(struct pyrf_event *pe, struct format_field *field)
+{
+	struct pevent *pevent = field->event->pevent;
+	void *data = pe->sample.raw_data;
+	PyObject *ret = NULL;
+	unsigned long long val;
+	unsigned int offset, len;
+
+	if (field->flags & FIELD_IS_ARRAY) {
+		offset = field->offset;
+		len    = field->size;
+		if (field->flags & FIELD_IS_DYNAMIC) {
+			val     = pevent_read_number(pevent, data + offset, len);
+			offset  = val;
+			len     = offset >> 16;
+			offset &= 0xffff;
+		}
+		if (field->flags & FIELD_IS_STRING &&
+		    is_printable_array(data + offset, len)) {
+			ret = PyString_FromString((char *)data + offset);
+		} else {
+			ret = PyByteArray_FromStringAndSize((const char *) data + offset, len);
+			field->flags &= ~FIELD_IS_STRING;
+		}
+	} else {
+		val = pevent_read_number(pevent, data + field->offset,
+					 field->size);
+		if (field->flags & FIELD_IS_POINTER)
+			ret = PyLong_FromUnsignedLong((unsigned long) val);
+		else if (field->flags & FIELD_IS_SIGNED)
+			ret = PyLong_FromLong((long) val);
+		else
+			ret = PyLong_FromUnsignedLong((unsigned long) val);
+	}
+
+	return ret;
+}
+
+static PyObject*
+get_tracepoint_field(struct pyrf_event *pevent, PyObject *attr_name)
+{
+	const char *str = PyString_AsString(PyObject_Str(attr_name));
+	struct perf_evsel *evsel = pevent->evsel;
+	struct format_field *field;
+
+	if (!evsel->tp_format) {
+		struct event_format *tp_format;
+
+		tp_format = trace_event__tp_format_id(evsel->attr.config);
+		if (!tp_format)
+			return NULL;
+
+		evsel->tp_format = tp_format;
+	}
+
+	field = pevent_find_any_field(evsel->tp_format, str);
+	if (!field)
+		return NULL;
+
+	return tracepoint_field(pevent, field);
+}
+
+static PyObject*
+pyrf_sample_event__getattro(struct pyrf_event *pevent, PyObject *attr_name)
+{
+	PyObject *obj = NULL;
+
+	if (is_tracepoint(pevent))
+		obj = get_tracepoint_field(pevent, attr_name);
+
+	return obj ?: PyObject_GenericGetAttr((PyObject *) pevent, attr_name);
+}
+
 static PyTypeObject pyrf_sample_event__type = {
 	PyVarObject_HEAD_INIT(NULL, 0)
 	.tp_name	= "perf.sample_event",
@@ -298,6 +389,7 @@ static PyTypeObject pyrf_sample_event__type = {
 	.tp_doc		= pyrf_sample_event__doc,
 	.tp_members	= pyrf_sample_event__members,
 	.tp_repr	= (reprfunc)pyrf_sample_event__repr,
+	.tp_getattro	= (getattrofunc) pyrf_sample_event__getattro,
 };
 
 static char pyrf_context_switch_event__doc[] = PyDoc_STR("perf context_switch event object.");

From 9881d7df9dddef24e34949a4510245e156746c21 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Sun, 10 Jul 2016 13:08:01 +0200
Subject: [PATCH 65/66] perf python: Add tracepoint example

To show how to enable a tracepoint and access its fields.

Committer note:

Testing it:

  # ls -l /tmp/build/perf/python/perf.so
  -rwxrwxr-x. 1 acme acme 1563256 Jul 12 16:19 /tmp/build/perf/python/perf.so
  # export PYTHONPATH=/tmp/build/perf/python/
  # tools/perf/python/tracepoint.py 2> /dev/null | head -200 | tail -10
  time 76345337296548 prev_comm=swapper/0 prev_pid=0 prev_prio=120 prev_state=0x0 ==> next_comm=tracepoint.py- next_pid=18479 next_prio=120
  time 76345338520479 prev_comm=gnome-shelln-b prev_pid=2186 prev_prio=120 prev_state=0x1 ==> next_comm=swapper/1 next_pid=0 next_prio=120
  time 76345337309942 prev_comm=tracepoint.py- prev_pid=18479 prev_prio=120 prev_state=0x1 ==> next_comm=swapper/0 next_pid=0 next_prio=120
  time 76345337312302 prev_comm=swapper/0 prev_pid=0 prev_prio=120 prev_state=0x0 ==> next_comm=tracepoint.py- next_pid=18479 next_prio=120
  time 76345337324927 prev_comm=tracepoint.py- prev_pid=18479 prev_prio=120 prev_state=0x1 ==> next_comm=swapper/0 next_pid=0 next_prio=120
  time 76345337327115 prev_comm=swapper/0 prev_pid=0 prev_prio=120 prev_state=0x0 ==> next_comm=tracepoint.py- next_pid=18479 next_prio=120
  time 76345338621750 prev_comm=swapper/2 prev_pid=0 prev_prio=120 prev_state=0x0 ==> next_comm=rcuos/2 next_pid=29 next_prio=120
  time 76345338607922 prev_comm=swapper/3 prev_pid=0 prev_prio=120 prev_state=0x0 ==> next_comm=rcu_sched next_pid=7 next_prio=120
  time 76345337338817 prev_comm=tracepoint.py- prev_pid=18479 prev_prio=120 prev_state=0x1 ==> next_comm=swapper/0 next_pid=0 next_prio=120
  time 76345338627156 prev_comm=swapper/1 prev_pid=0 prev_prio=120 prev_state=0x0 ==> next_comm=head-terminal- next_pid=18480 next_prio=120
  #
  # strip /tmp/build/perf/python/perf.so
  # ls -l /tmp/build/perf/python/perf.so
  -rwxrwxr-x. 1 acme acme 319616 Jul 12 16:25 /tmp/build/perf/python/perf.so

Reported-and-Tested-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1468148882-10362-10-git-send-email-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/python/tracepoint.py | 47 +++++++++++++++++++++++++++++++++
 1 file changed, 47 insertions(+)
 create mode 100755 tools/perf/python/tracepoint.py

diff --git a/tools/perf/python/tracepoint.py b/tools/perf/python/tracepoint.py
new file mode 100755
index 0000000000000..eb4dbed57de7e
--- /dev/null
+++ b/tools/perf/python/tracepoint.py
@@ -0,0 +1,47 @@
+#! /usr/bin/python
+# -*- python -*-
+# -*- coding: utf-8 -*-
+
+import perf
+
+class tracepoint(perf.evsel):
+    def __init__(self, sys, name):
+        config = perf.tracepoint(sys, name)
+        perf.evsel.__init__(self,
+                            type   = perf.TYPE_TRACEPOINT,
+                            config = config,
+                            freq = 0, sample_period = 1, wakeup_events = 1,
+                            sample_type = perf.SAMPLE_PERIOD | perf.SAMPLE_TID | perf.SAMPLE_CPU | perf.SAMPLE_RAW | perf.SAMPLE_TIME)
+
+def main():
+    tp      = tracepoint("sched", "sched_switch")
+    cpus    = perf.cpu_map()
+    threads = perf.thread_map(-1)
+
+    evlist = perf.evlist(cpus, threads)
+    evlist.add(tp)
+    evlist.open()
+    evlist.mmap()
+
+    while True:
+        evlist.poll(timeout = -1)
+        for cpu in cpus:
+            event = evlist.read_on_cpu(cpu)
+            if not event:
+                continue
+
+            if not isinstance(event, perf.sample_event):
+                continue
+
+            print "time %u prev_comm=%s prev_pid=%d prev_prio=%d prev_state=0x%x ==> next_comm=%s next_pid=%d next_prio=%d" % (
+                   event.sample_time,
+                   event.prev_comm,
+                   event.prev_pid,
+                   event.prev_prio,
+                   event.prev_state,
+                   event.next_comm,
+                   event.next_pid,
+                   event.next_prio)
+
+if __name__ == '__main__':
+    main()

From 6d248fbda59c51ef5f2e90e11551d9e17aeb226f Mon Sep 17 00:00:00 2001
From: Steven Rostedt <rostedt@goodmis.org>
Date: Tue, 12 Jul 2016 09:33:06 -0400
Subject: [PATCH 66/66] tools lib traceevent: Add filter on task CPU id

Add a 'CPU' special field to allow the filter in trace-cmd report to
filter on the task's CPU.

By adding a special field 'CPU' (all caps) the user can now filter out
tasks based on which CPU they are on. This is useful when filtering out
(or in) a bunch of threads.

  -F 'CPU == 0'

Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: http://lkml.kernel.org/r/20160712093306.5b058103@gandalf.local.home
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/lib/traceevent/parse-filter.c | 18 +++++++++++++++---
 1 file changed, 15 insertions(+), 3 deletions(-)

diff --git a/tools/lib/traceevent/parse-filter.c b/tools/lib/traceevent/parse-filter.c
index 88cccea3ca991..7c214ceb93860 100644
--- a/tools/lib/traceevent/parse-filter.c
+++ b/tools/lib/traceevent/parse-filter.c
@@ -28,11 +28,16 @@
 #include "event-utils.h"
 
 #define COMM "COMM"
+#define CPU "CPU"
 
 static struct format_field comm = {
 	.name = "COMM",
 };
 
+static struct format_field cpu = {
+	.name = "CPU",
+};
+
 struct event_list {
 	struct event_list	*next;
 	struct event_format	*event;
@@ -382,14 +387,17 @@ create_arg_item(struct event_format *event, const char *token,
 		/* Consider this a field */
 		field = pevent_find_any_field(event, token);
 		if (!field) {
-			if (strcmp(token, COMM) != 0) {
+			/* If token is 'COMM' or 'CPU' then it is special */
+			if (strcmp(token, COMM) == 0) {
+				field = &comm;
+			} else if (strcmp(token, CPU) == 0) {
+				field = &cpu;
+			} else {
 				/* not a field, Make it false */
 				arg->type = FILTER_ARG_BOOLEAN;
 				arg->boolean.value = FILTER_FALSE;
 				break;
 			}
-			/* If token is 'COMM' then it is special */
-			field = &comm;
 		}
 		arg->type = FILTER_ARG_FIELD;
 		arg->field.field = field;
@@ -1718,6 +1726,10 @@ get_value(struct event_format *event,
 		return (unsigned long)name;
 	}
 
+	/* Handle our dummy "cpu" field */
+	if (field == &cpu)
+		return record->cpu;
+
 	pevent_read_number_field(field, record->data, &val);
 
 	if (!(field->flags & FIELD_IS_SIGNED))