Merge remote-tracking branch 'tip/auto-latest'

58 files changed, 1431 insertions, 209 deletions

diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index cddd5d06e1cb..3603556fa0d9 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -280,6 +280,7 @@
 /* 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 */
+#define X86_FEATURE_AVX512_VPOPCNTDQ (16*32+14) /* POPCNT for vectors of DW/QW */
 
 /* AMD-defined CPU features, CPUID level 0x80000007 (ebx), word 17 */
 #define X86_FEATURE_OVERFLOW_RECOV (17*32+0) /* MCA overflow recovery support */
diff --git a/tools/arch/x86/include/uapi/asm/vmx.h b/tools/arch/x86/include/uapi/asm/vmx.h
index 37fee272618f..14458658e988 100644
--- a/tools/arch/x86/include/uapi/asm/vmx.h
+++ b/tools/arch/x86/include/uapi/asm/vmx.h
@@ -65,6 +65,8 @@
 #define EXIT_REASON_TPR_BELOW_THRESHOLD 43
 #define EXIT_REASON_APIC_ACCESS         44
 #define EXIT_REASON_EOI_INDUCED         45
+#define EXIT_REASON_GDTR_IDTR           46
+#define EXIT_REASON_LDTR_TR             47
 #define EXIT_REASON_EPT_VIOLATION       48
 #define EXIT_REASON_EPT_MISCONFIG       49
 #define EXIT_REASON_INVEPT              50
@@ -113,6 +115,8 @@
 	{ EXIT_REASON_MCE_DURING_VMENTRY,    "MCE_DURING_VMENTRY" }, \
 	{ EXIT_REASON_TPR_BELOW_THRESHOLD,   "TPR_BELOW_THRESHOLD" }, \
 	{ EXIT_REASON_APIC_ACCESS,           "APIC_ACCESS" }, \
+	{ EXIT_REASON_GDTR_IDTR,	     "GDTR_IDTR" }, \
+	{ EXIT_REASON_LDTR_TR,		     "LDTR_TR" }, \
 	{ EXIT_REASON_EPT_VIOLATION,         "EPT_VIOLATION" }, \
 	{ EXIT_REASON_EPT_MISCONFIG,         "EPT_MISCONFIG" }, \
 	{ EXIT_REASON_INVEPT,                "INVEPT" }, \
@@ -129,6 +133,7 @@
 	{ EXIT_REASON_XRSTORS,               "XRSTORS" }
 
 #define VMX_ABORT_SAVE_GUEST_MSR_FAIL        1
+#define VMX_ABORT_LOAD_HOST_PDPTE_FAIL       2
 #define VMX_ABORT_LOAD_HOST_MSR_FAIL         4
 
 #endif /* _UAPIVMX_H */
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 84e6b35da4bd..e6cd62b1264b 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -28,6 +28,7 @@
 #include <fcntl.h>
 #include <errno.h>
 #include <asm/unistd.h>
+#include <linux/err.h>
 #include <linux/kernel.h>
 #include <linux/bpf.h>
 #include <linux/list.h>
@@ -779,7 +780,7 @@ static int
 bpf_program__collect_reloc(struct bpf_program *prog,
 			   size_t nr_maps, GElf_Shdr *shdr,
 			   Elf_Data *data, Elf_Data *symbols,
-			   int maps_shndx)
+			   int maps_shndx, struct bpf_map *maps)
 {
 	int i, nrels;
 
@@ -829,7 +830,15 @@ bpf_program__collect_reloc(struct bpf_program *prog,
 			return -LIBBPF_ERRNO__RELOC;
 		}
 
-		map_idx = sym.st_value / sizeof(struct bpf_map_def);
+		/* TODO: 'maps' is sorted. We can use bsearch to make it faster. */
+		for (map_idx = 0; map_idx < nr_maps; map_idx++) {
+			if (maps[map_idx].offset == sym.st_value) {
+				pr_debug("relocation: find map %zd (%s) for insn %u\n",
+					 map_idx, maps[map_idx].name, insn_idx);
+				break;
+			}
+		}
+
 		if (map_idx >= nr_maps) {
 			pr_warning("bpf relocation: map_idx %d large than %d\n",
 				   (int)map_idx, (int)nr_maps - 1);
@@ -953,7 +962,8 @@ static int bpf_object__collect_reloc(struct bpf_object *obj)
 		err = bpf_program__collect_reloc(prog, nr_maps,
 						 shdr, data,
 						 obj->efile.symbols,
-						 obj->efile.maps_shndx);
+						 obj->efile.maps_shndx,
+						 obj->maps);
 		if (err)
 			return err;
 	}
@@ -1419,37 +1429,33 @@ static void bpf_program__set_type(struct bpf_program *prog,
 	prog->type = type;
 }
 
-int bpf_program__set_tracepoint(struct bpf_program *prog)
-{
-	if (!prog)
-		return -EINVAL;
-	bpf_program__set_type(prog, BPF_PROG_TYPE_TRACEPOINT);
-	return 0;
-}
-
-int bpf_program__set_kprobe(struct bpf_program *prog)
-{
-	if (!prog)
-		return -EINVAL;
-	bpf_program__set_type(prog, BPF_PROG_TYPE_KPROBE);
-	return 0;
-}
-
 static bool bpf_program__is_type(struct bpf_program *prog,
 				 enum bpf_prog_type type)
 {
 	return prog ? (prog->type == type) : false;
 }
 
-bool bpf_program__is_tracepoint(struct bpf_program *prog)
-{
-	return bpf_program__is_type(prog, BPF_PROG_TYPE_TRACEPOINT);
-}
-
-bool bpf_program__is_kprobe(struct bpf_program *prog)
-{
-	return bpf_program__is_type(prog, BPF_PROG_TYPE_KPROBE);
-}
+#define BPF_PROG_TYPE_FNS(NAME, TYPE)			\
+int bpf_program__set_##NAME(struct bpf_program *prog)	\
+{							\
+	if (!prog)					\
+		return -EINVAL;				\
+	bpf_program__set_type(prog, TYPE);		\
+	return 0;					\
+}							\
+							\
+bool bpf_program__is_##NAME(struct bpf_program *prog)	\
+{							\
+	return bpf_program__is_type(prog, TYPE);	\
+}							\
+
+BPF_PROG_TYPE_FNS(socket_filter, BPF_PROG_TYPE_SOCKET_FILTER);
+BPF_PROG_TYPE_FNS(kprobe, BPF_PROG_TYPE_KPROBE);
+BPF_PROG_TYPE_FNS(sched_cls, BPF_PROG_TYPE_SCHED_CLS);
+BPF_PROG_TYPE_FNS(sched_act, BPF_PROG_TYPE_SCHED_ACT);
+BPF_PROG_TYPE_FNS(tracepoint, BPF_PROG_TYPE_TRACEPOINT);
+BPF_PROG_TYPE_FNS(xdp, BPF_PROG_TYPE_XDP);
+BPF_PROG_TYPE_FNS(perf_event, BPF_PROG_TYPE_PERF_EVENT);
 
 int bpf_map__fd(struct bpf_map *map)
 {
@@ -1537,3 +1543,10 @@ bpf_object__find_map_by_offset(struct bpf_object *obj, size_t offset)
 	}
 	return ERR_PTR(-ENOENT);
 }
+
+long libbpf_get_error(const void *ptr)
+{
+	if (IS_ERR(ptr))
+		return PTR_ERR(ptr);
+	return 0;
+}
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index a5a8b86a06fe..4014d1ba5e3d 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -22,8 +22,8 @@
 #define __BPF_LIBBPF_H
 
 #include <stdio.h>
+#include <stdint.h>
 #include <stdbool.h>
-#include <linux/err.h>
 #include <sys/types.h>  // for size_t
 
 enum libbpf_errno {
@@ -174,11 +174,21 @@ int bpf_program__nth_fd(struct bpf_program *prog, int n);
 /*
  * Adjust type of bpf program. Default is kprobe.
  */
+int bpf_program__set_socket_filter(struct bpf_program *prog);
 int bpf_program__set_tracepoint(struct bpf_program *prog);
 int bpf_program__set_kprobe(struct bpf_program *prog);
+int bpf_program__set_sched_cls(struct bpf_program *prog);
+int bpf_program__set_sched_act(struct bpf_program *prog);
+int bpf_program__set_xdp(struct bpf_program *prog);
+int bpf_program__set_perf_event(struct bpf_program *prog);
 
+bool bpf_program__is_socket_filter(struct bpf_program *prog);
 bool bpf_program__is_tracepoint(struct bpf_program *prog);
 bool bpf_program__is_kprobe(struct bpf_program *prog);
+bool bpf_program__is_sched_cls(struct bpf_program *prog);
+bool bpf_program__is_sched_act(struct bpf_program *prog);
+bool bpf_program__is_xdp(struct bpf_program *prog);
+bool bpf_program__is_perf_event(struct bpf_program *prog);
 
 /*
  * We don't need __attribute__((packed)) now since it is
@@ -224,4 +234,6 @@ int bpf_map__set_priv(struct bpf_map *map, void *priv,
 		      bpf_map_clear_priv_t clear_priv);
 void *bpf_map__priv(struct bpf_map *map);
 
+long libbpf_get_error(const void *ptr);
+
 #endif
diff --git a/tools/lib/subcmd/parse-options.h b/tools/lib/subcmd/parse-options.h
index 11c3be3bcce7..f054ca1b899d 100644
--- a/tools/lib/subcmd/parse-options.h
+++ b/tools/lib/subcmd/parse-options.h
@@ -1,6 +1,7 @@
 #ifndef __SUBCMD_PARSE_OPTIONS_H
 #define __SUBCMD_PARSE_OPTIONS_H
 
+#include <linux/kernel.h>
 #include <stdbool.h>
 #include <stdint.h>
 
@@ -132,32 +133,32 @@ struct option {
 #define OPT_UINTEGER(s, l, v, h)    { .type = OPTION_UINTEGER, .short_name = (s), .long_name = (l), .value = check_vtype(v, unsigned int *), .help = (h) }
 #define OPT_LONG(s, l, v, h)        { .type = OPTION_LONG, .short_name = (s), .long_name = (l), .value = check_vtype(v, long *), .help = (h) }
 #define OPT_U64(s, l, v, h)         { .type = OPTION_U64, .short_name = (s), .long_name = (l), .value = check_vtype(v, u64 *), .help = (h) }
-#define OPT_STRING(s, l, v, a, h)   { .type = OPTION_STRING,  .short_name = (s), .long_name = (l), .value = check_vtype(v, const char **), (a), .help = (h) }
+#define OPT_STRING(s, l, v, a, h)   { .type = OPTION_STRING,  .short_name = (s), .long_name = (l), .value = check_vtype(v, const char **), .argh = (a), .help = (h) }
 #define OPT_STRING_OPTARG(s, l, v, a, h, d) \
 	{ .type = OPTION_STRING,  .short_name = (s), .long_name = (l), \
-	  .value = check_vtype(v, const char **), (a), .help = (h), \
+	  .value = check_vtype(v, const char **), .argh =(a), .help = (h), \
 	  .flags = PARSE_OPT_OPTARG, .defval = (intptr_t)(d) }
 #define OPT_STRING_OPTARG_SET(s, l, v, os, a, h, d) \
 	{ .type = OPTION_STRING, .short_name = (s), .long_name = (l), \
-	  .value = check_vtype(v, const char **), (a), .help = (h), \
+	  .value = check_vtype(v, const char **), .argh = (a), .help = (h), \
 	  .flags = PARSE_OPT_OPTARG, .defval = (intptr_t)(d), \
 	  .set = check_vtype(os, bool *)}
-#define OPT_STRING_NOEMPTY(s, l, v, a, h)   { .type = OPTION_STRING,  .short_name = (s), .long_name = (l), .value = check_vtype(v, const char **), (a), .help = (h), .flags = PARSE_OPT_NOEMPTY}
+#define OPT_STRING_NOEMPTY(s, l, v, a, h)   { .type = OPTION_STRING,  .short_name = (s), .long_name = (l), .value = check_vtype(v, const char **), .argh = (a), .help = (h), .flags = PARSE_OPT_NOEMPTY}
 #define OPT_DATE(s, l, v, h) \
 	{ .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), .argh = "time", .help = (h), .callback = parse_opt_approxidate_cb }
 #define OPT_CALLBACK(s, l, v, a, h, f) \
-	{ .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), (a), .help = (h), .callback = (f) }
+	{ .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), .argh = (a), .help = (h), .callback = (f) }
 #define OPT_CALLBACK_NOOPT(s, l, v, a, h, f) \
-	{ .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), (a), .help = (h), .callback = (f), .flags = PARSE_OPT_NOARG }
+	{ .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), .argh = (a), .help = (h), .callback = (f), .flags = PARSE_OPT_NOARG }
 #define OPT_CALLBACK_DEFAULT(s, l, v, a, h, f, d) \
-	{ .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), (a), .help = (h), .callback = (f), .defval = (intptr_t)d, .flags = PARSE_OPT_LASTARG_DEFAULT }
+	{ .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), .argh = (a), .help = (h), .callback = (f), .defval = (intptr_t)d, .flags = PARSE_OPT_LASTARG_DEFAULT }
 #define OPT_CALLBACK_DEFAULT_NOOPT(s, l, v, a, h, f, d) \
 	{ .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l),\
-	.value = (v), (a), .help = (h), .callback = (f), .defval = (intptr_t)d,\
+	.value = (v), .arg = (a), .help = (h), .callback = (f), .defval = (intptr_t)d,\
 	.flags = PARSE_OPT_LASTARG_DEFAULT | PARSE_OPT_NOARG}
 #define OPT_CALLBACK_OPTARG(s, l, v, d, a, h, f) \
 	{ .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), \
-	  .value = (v), (a), .help = (h), .callback = (f), \
+	  .value = (v), .argh = (a), .help = (h), .callback = (f), \
 	  .flags = PARSE_OPT_OPTARG, .data = (d) }
 
 /* parse_options() will filter out the processed options and leave the
diff --git a/tools/perf/Build b/tools/perf/Build
index b12d5d1666e3..9b79f8d7db50 100644
--- a/tools/perf/Build
+++ b/tools/perf/Build
@@ -3,10 +3,12 @@ perf-y += builtin-annotate.o
 perf-y += builtin-config.o
 perf-y += builtin-diff.o
 perf-y += builtin-evlist.o
+perf-y += builtin-ftrace.o
 perf-y += builtin-help.o
 perf-y += builtin-sched.o
 perf-y += builtin-buildid-list.o
 perf-y += builtin-buildid-cache.o
+perf-y += builtin-kallsyms.o
 perf-y += builtin-list.o
 perf-y += builtin-record.o
 perf-y += builtin-report.o
@@ -39,8 +41,7 @@ CFLAGS_builtin-help.o      += $(paths)
 CFLAGS_builtin-timechart.o += $(paths)
 CFLAGS_perf.o              += -DPERF_HTML_PATH="BUILD_STR($(htmldir_SQ))"	\
 			      -DPERF_EXEC_PATH="BUILD_STR($(perfexecdir_SQ))"	\
-			      -DPREFIX="BUILD_STR($(prefix_SQ))"		\
-			      -include $(OUTPUT)PERF-VERSION-FILE
+			      -DPREFIX="BUILD_STR($(prefix_SQ))"
 CFLAGS_builtin-trace.o	   += -DSTRACE_GROUPS_DIR="BUILD_STR($(STRACE_GROUPS_DIR_SQ))"
 CFLAGS_builtin-report.o	   += -DTIPDIR="BUILD_STR($(tipdir_SQ))"
 CFLAGS_builtin-report.o	   += -DDOCDIR="BUILD_STR($(srcdir_SQ)/Documentation)"
diff --git a/tools/perf/Documentation/perf-c2c.txt b/tools/perf/Documentation/perf-c2c.txt
index 3f06730c7f47..2da07e51e119 100644
--- a/tools/perf/Documentation/perf-c2c.txt
+++ b/tools/perf/Documentation/perf-c2c.txt
@@ -248,7 +248,7 @@ output fields set for caheline offsets output:
              Code address, Code symbol, Shared Object, Source line
   dso   - coalesced by shared object
 
-By default the coalescing is setup with 'pid,tid,iaddr'.
+By default the coalescing is setup with 'pid,iaddr'.
 
 STDIO OUTPUT
 ------------
diff --git a/tools/perf/Documentation/perf-ftrace.txt b/tools/perf/Documentation/perf-ftrace.txt
new file mode 100644
index 000000000000..2d96de6132a9
--- /dev/null
+++ b/tools/perf/Documentation/perf-ftrace.txt
@@ -0,0 +1,36 @@
+perf-ftrace(1)
+=============
+
+NAME
+----
+perf-ftrace - simple wrapper for kernel's ftrace functionality
+
+
+SYNOPSIS
+--------
+[verse]
+'perf ftrace' <command>
+
+DESCRIPTION
+-----------
+The 'perf ftrace' command is a simple wrapper of kernel's ftrace
+functionality.  It only supports single thread tracing currently and
+just reads trace_pipe in text and then write it to stdout.
+
+The following options apply to perf ftrace.
+
+OPTIONS
+-------
+
+-t::
+--tracer=::
+	Tracer to use: function_graph or function.
+
+-v::
+--verbose=::
+        Verbosity level.
+
+
+SEE ALSO
+--------
+linkperf:perf-record[1], linkperf:perf-trace[1]
diff --git a/tools/perf/Documentation/perf-kallsyms.txt b/tools/perf/Documentation/perf-kallsyms.txt
new file mode 100644
index 000000000000..954ea9e21236
--- /dev/null
+++ b/tools/perf/Documentation/perf-kallsyms.txt
@@ -0,0 +1,24 @@
+perf-kallsyms(1)
+==============
+
+NAME
+----
+perf-kallsyms - Searches running kernel for symbols
+
+SYNOPSIS
+--------
+[verse]
+'perf kallsyms <options> symbol_name[,symbol_name...]'
+
+DESCRIPTION
+-----------
+This command searches the running kernel kallsyms file for the given symbol(s)
+and prints information about it, including the DSO, the kallsyms begin/end
+addresses and the addresses in the ELF kallsyms symbol table (for symbols in
+modules).
+
+OPTIONS
+-------
+-v::
+--verbose=::
+	Increase verbosity level, showing details about symbol table loading, etc.
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 5054d9147f0f..27256bc68eda 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -421,9 +421,19 @@ Configure all used events to run in user space.
 --timestamp-filename
 Append timestamp to output file name.
 
---switch-output::
+--switch-output[=mode]::
 Generate multiple perf.data files, timestamp prefixed, switching to a new one
-when receiving a SIGUSR2.
+based on 'mode' value:
+  "signal" - when receiving a SIGUSR2 (default value) or
+  <size>   - when reaching the size threshold, size is expected to
+             be a number with appended unit character - B/K/M/G
+  <time>   - when reaching the time threshold, size is expected to
+             be a number with appended unit character - s/m/h/d
+
+             Note: the precision of  the size  threshold  hugely depends
+             on your configuration  - the number and size of  your  ring
+             buffers (-m). It is generally more precise for higher sizes
+             (like >5M), for lower values expect different sizes.
 
 A possible use case is to, given an external event, slice the perf.data file
 that gets then processed, possibly via a perf script, to decide if that
diff --git a/tools/perf/Documentation/perf-sched.txt b/tools/perf/Documentation/perf-sched.txt
index 76173969ab80..d33deddb0146 100644
--- a/tools/perf/Documentation/perf-sched.txt
+++ b/tools/perf/Documentation/perf-sched.txt
@@ -143,6 +143,8 @@ OPTIONS for 'perf sched timehist'
 	stop time is not given (i.e, time string is 'x.y,') then analysis goes
 	to end of file.
 
+--state::
+	Show task state when it switched out.
 
 SEE ALSO
 --------
diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index 5dc5c6a09ac4..4ed5f239ba7d 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -36,7 +36,7 @@ There are several variants of perf script:
 
   'perf script report <script> [args]' to run and display the results
   of <script>.  <script> is the name displayed in the output of 'perf
-  trace --list' i.e. the actual script name minus any language
+  script --list' i.e. the actual script name minus any language
   extension.  The perf.data output from a previous run of 'perf script
   record <script>' is used and should be present for this command to
   succeed.  [args] refers to the (mainly optional) args expected by
@@ -76,7 +76,7 @@ OPTIONS
 	Any command you can specify in a shell.
 
 -D::
---dump-raw-script=::
+--dump-raw-trace=::
         Display verbose dump of the trace data.
 
 -L::
diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documentation/perf-trace.txt
index 781b019751a4..afd728672b6f 100644
--- a/tools/perf/Documentation/perf-trace.txt
+++ b/tools/perf/Documentation/perf-trace.txt
@@ -35,7 +35,10 @@ OPTIONS
 
 -e::
 --expr::
-	List of syscalls to show, currently only syscall names.
+--event::
+	List of syscalls and other perf events (tracepoints, HW cache events,
+	etc) to show.
+	See 'perf list' for a complete list of events.
 	Prefixing with ! shows all syscalls but the ones specified.  You may
 	need to escape it.
 
@@ -135,9 +138,6 @@ the thread executes on the designated CPUs. Default is to monitor all CPUs.
 --kernel-syscall-graph::
 	 Show the kernel callchains on the syscall exit path.
 
---event::
-	Trace other events, see 'perf list' for a complete list.
-
 --max-stack::
         Set the stack depth limit when parsing the callchain, anything
         beyond the specified depth will be ignored. Note that at this point
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index 76c84f0eec52..03cf947755b9 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -291,8 +291,10 @@ else
       endif
     endif
     ifneq ($(feature-dwarf), 1)
-      msg := $(warning No libdw.h found or old libdw.h found or elfutils is older than 0.138, disables dwarf support. Please install new elfutils-devel/libdw-dev);
-      NO_DWARF := 1
+      ifndef NO_DWARF
+        msg := $(warning No libdw.h found or old libdw.h found or elfutils is older than 0.138, disables dwarf support. Please install new elfutils-devel/libdw-dev);
+        NO_DWARF := 1
+      endif
     else
       ifneq ($(feature-dwarf_getlocations), 1)
         msg := $(warning Old libdw.h, finding variables at given 'perf probe' point will not work, install elfutils-devel/libdw-dev >= 0.157);
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 8bb16aa9d661..4da19b6ba94a 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -661,6 +661,7 @@ ifndef NO_PERF_READ_VDSOX32
 endif
 ifndef NO_JVMTI
 	$(call QUIET_INSTALL, $(LIBJVMTI)) \
+		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(libdir_SQ)'; \
 		$(INSTALL) $(OUTPUT)$(LIBJVMTI) '$(DESTDIR_SQ)$(libdir_SQ)';
 endif
 	$(call QUIET_INSTALL, libexec) \
diff --git a/tools/perf/arch/arm64/include/dwarf-regs-table.h b/tools/perf/arch/arm64/include/dwarf-regs-table.h
index 26759363f921..36e375f5a211 100644
--- a/tools/perf/arch/arm64/include/dwarf-regs-table.h
+++ b/tools/perf/arch/arm64/include/dwarf-regs-table.h
@@ -2,12 +2,12 @@
 /* This is included in perf/util/dwarf-regs.c */
 
 static const char * const aarch64_regstr_tbl[] = {
-	"%r0", "%r1", "%r2", "%r3", "%r4",
-	"%r5", "%r6", "%r7", "%r8", "%r9",
-	"%r10", "%r11", "%r12", "%r13", "%r14",
-	"%r15", "%r16", "%r17", "%r18", "%r19",
-	"%r20", "%r21", "%r22", "%r23", "%r24",
-	"%r25", "%r26", "%r27", "%r28", "%r29",
+	"%x0", "%x1", "%x2", "%x3", "%x4",
+	"%x5", "%x6", "%x7", "%x8", "%x9",
+	"%x10", "%x11", "%x12", "%x13", "%x14",
+	"%x15", "%x16", "%x17", "%x18", "%x19",
+	"%x20", "%x21", "%x22", "%x23", "%x24",
+	"%x25", "%x26", "%x27", "%x28", "%x29",
 	"%lr", "%sp",
 };
 #endif
diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c
index f8ca7a4ebabc..e2b21723bbf8 100644
--- a/tools/perf/builtin-c2c.c
+++ b/tools/perf/builtin-c2c.c
@@ -58,7 +58,7 @@ struct c2c_hist_entry {
 	struct hist_entry	he;
 };
 
-static char const *coalesce_default = "pid,tid,iaddr";
+static char const *coalesce_default = "pid,iaddr";
 
 struct perf_c2c {
 	struct perf_tool	tool;
@@ -2476,6 +2476,7 @@ static int build_cl_output(char *cl_sort, bool no_source)
 		"mean_rmt,"
 		"mean_lcl,"
 		"mean_load,"
+		"tot_recs,"
 		"cpucnt,",
 		add_sym ? "symbol," : "",
 		add_dso ? "dso," : "",
diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c
new file mode 100644
index 000000000000..d05658d2b8f1
--- /dev/null
+++ b/tools/perf/builtin-ftrace.c
@@ -0,0 +1,243 @@
+/*
+ * builtin-ftrace.c
+ *
+ * Copyright (c) 2013  LG Electronics,  Namhyung Kim <namhyung@kernel.org>
+ *
+ * Released under the GPL v2.
+ */
+
+#include "builtin.h"
+#include "perf.h"
+
+#include <unistd.h>
+#include <signal.h>
+
+#include "debug.h"
+#include <subcmd/parse-options.h>
+#include "evlist.h"
+#include "target.h"
+#include "thread_map.h"
+
+
+#define DEFAULT_TRACER  "function_graph"
+
+struct perf_ftrace {
+	struct perf_evlist *evlist;
+	struct target target;
+	const char *tracer;
+};
+
+static bool done;
+
+static void sig_handler(int sig __maybe_unused)
+{
+	done = true;
+}
+
+/*
+ * perf_evlist__prepare_workload will send a SIGUSR1 if the fork fails, since
+ * we asked by setting its exec_error to the function below,
+ * ftrace__workload_exec_failed_signal.
+ *
+ * XXX We need to handle this more appropriately, emitting an error, etc.
+ */
+static void ftrace__workload_exec_failed_signal(int signo __maybe_unused,
+						siginfo_t *info __maybe_unused,
+						void *ucontext __maybe_unused)
+{
+	/* workload_exec_errno = info->si_value.sival_int; */
+	done = true;
+}
+
+static int write_tracing_file(const char *name, const char *val)
+{
+	char *file;
+	int fd, ret = -1;
+	ssize_t size = strlen(val);
+
+	file = get_tracing_file(name);
+	if (!file) {
+		pr_debug("cannot get tracing file: %s\n", name);
+		return -1;
+	}
+
+	fd = open(file, O_WRONLY);
+	if (fd < 0) {
+		pr_debug("cannot open tracing file: %s\n", name);
+		goto out;
+	}
+
+	if (write(fd, val, size) == size)
+		ret = 0;
+	else
+		pr_debug("write '%s' to tracing/%s failed\n", val, name);
+
+	close(fd);
+out:
+	put_tracing_file(file);
+	return ret;
+}
+
+static int reset_tracing_files(struct perf_ftrace *ftrace __maybe_unused)
+{
+	if (write_tracing_file("tracing_on", "0") < 0)
+		return -1;
+
+	if (write_tracing_file("current_tracer", "nop") < 0)
+		return -1;
+
+	if (write_tracing_file("set_ftrace_pid", " ") < 0)
+		return -1;
+
+	return 0;
+}
+
+static int __cmd_ftrace(struct perf_ftrace *ftrace, int argc, const char **argv)
+{
+	char *trace_file;
+	int trace_fd;
+	char *trace_pid;
+	char buf[4096];
+	struct pollfd pollfd = {
+		.events = POLLIN,
+	};
+
+	if (geteuid() != 0) {
+		pr_err("ftrace only works for root!\n");
+		return -1;
+	}
+
+	if (argc < 1)
+		return -1;
+
+	signal(SIGINT, sig_handler);
+	signal(SIGUSR1, sig_handler);
+	signal(SIGCHLD, sig_handler);
+
+	reset_tracing_files(ftrace);
+
+	/* reset ftrace buffer */
+	if (write_tracing_file("trace", "0") < 0)
+		goto out;
+
+	if (perf_evlist__prepare_workload(ftrace->evlist, &ftrace->target,
+					  argv, false, ftrace__workload_exec_failed_signal) < 0)
+		goto out;
+
+	if (write_tracing_file("current_tracer", ftrace->tracer) < 0) {
+		pr_err("failed to set current_tracer to %s\n", ftrace->tracer);
+		goto out;
+	}
+
+	if (asprintf(&trace_pid, "%d", thread_map__pid(ftrace->evlist->threads, 0)) < 0) {
+		pr_err("failed to allocate pid string\n");
+		goto out;
+	}
+
+	if (write_tracing_file("set_ftrace_pid", trace_pid) < 0) {
+		pr_err("failed to set pid: %s\n", trace_pid);
+		goto out_free_pid;
+	}
+
+	trace_file = get_tracing_file("trace_pipe");
+	if (!trace_file) {
+		pr_err("failed to open trace_pipe\n");
+		goto out_free_pid;
+	}
+
+	trace_fd = open(trace_file, O_RDONLY);
+
+	put_tracing_file(trace_file);
+
+	if (trace_fd < 0) {
+		pr_err("failed to open trace_pipe\n");
+		goto out_free_pid;
+	}
+
+	fcntl(trace_fd, F_SETFL, O_NONBLOCK);
+	pollfd.fd = trace_fd;
+
+	if (write_tracing_file("tracing_on", "1") < 0) {
+		pr_err("can't enable tracing\n");
+		goto out_close_fd;
+	}
+
+	perf_evlist__start_workload(ftrace->evlist);
+
+	while (!done) {
+		if (poll(&pollfd, 1, -1) < 0)
+			break;
+
+		if (pollfd.revents & POLLIN) {
+			int n = read(trace_fd, buf, sizeof(buf));
+			if (n < 0)
+				break;
+			if (fwrite(buf, n, 1, stdout) != 1)
+				break;
+		}
+	}
+
+	write_tracing_file("tracing_on", "0");
+
+	/* read remaining buffer contents */
+	while (true) {
+		int n = read(trace_fd, buf, sizeof(buf));
+		if (n <= 0)
+			break;
+		if (fwrite(buf, n, 1, stdout) != 1)
+			break;
+	}
+
+out_close_fd:
+	close(trace_fd);
+out_free_pid:
+	free(trace_pid);
+out:
+	reset_tracing_files(ftrace);
+
+	return done ? 0 : -1;
+}
+
+int cmd_ftrace(int argc, const char **argv, const char *prefix __maybe_unused)
+{
+	int ret;
+	struct perf_ftrace ftrace = {
+		.tracer = "function_graph",
+		.target = { .uid = UINT_MAX, },
+	};
+	const char * const ftrace_usage[] = {
+		"perf ftrace [<options>] <command>",
+		"perf ftrace [<options>] -- <command> [<options>]",
+		NULL
+	};
+	const struct option ftrace_options[] = {
+	OPT_STRING('t', "tracer", &ftrace.tracer, "tracer",
+		   "tracer to use: function_graph(default) or function"),
+	OPT_INCR('v', "verbose", &verbose,
+		 "be more verbose"),
+	OPT_END()
+	};
+
+	argc = parse_options(argc, argv, ftrace_options, ftrace_usage,
+			    PARSE_OPT_STOP_AT_NON_OPTION);
+	if (!argc)
+		usage_with_options(ftrace_usage, ftrace_options);
+
+	ftrace.evlist = perf_evlist__new();
+	if (ftrace.evlist == NULL)
+		return -ENOMEM;
+
+	ret = perf_evlist__create_maps(ftrace.evlist, &ftrace.target);
+	if (ret < 0)
+		goto out_delete_evlist;
+
+	if (ftrace.tracer == NULL)
+		ftrace.tracer = DEFAULT_TRACER;
+
+	ret = __cmd_ftrace(&ftrace, argc, argv);
+
+out_delete_evlist:
+	perf_evlist__delete(ftrace.evlist);
+
+	return ret;
+}
diff --git a/tools/perf/builtin-help.c b/tools/perf/builtin-help.c
index 3bdb2c78a21b..93da24a638be 100644
--- a/tools/perf/builtin-help.c
+++ b/tools/perf/builtin-help.c
@@ -434,7 +434,7 @@ int cmd_help(int argc, const char **argv, const char *prefix __maybe_unused)
 	const char * const builtin_help_subcommands[] = {
 		"buildid-cache", "buildid-list", "diff", "evlist", "help", "list",
 		"record", "report", "bench", "stat", "timechart", "top", "annotate",
-		"script", "sched", "kmem", "lock", "kvm", "test", "inject", "mem", "data",
+		"script", "sched", "kallsyms", "kmem", "lock", "kvm", "test", "inject", "mem", "data",
 #ifdef HAVE_LIBELF_SUPPORT
 		"probe",
 #endif
diff --git a/tools/perf/builtin-kallsyms.c b/tools/perf/builtin-kallsyms.c
new file mode 100644
index 000000000000..224bfc454b4a
--- /dev/null
+++ b/tools/perf/builtin-kallsyms.c
@@ -0,0 +1,67 @@
+/*
+ * builtin-kallsyms.c
+ *
+ * Builtin command: Look for a symbol in the running kernel and its modules
+ *
+ * Copyright (C) 2017, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+ *
+ * Released under the GPL v2. (and only v2, not any later version)
+ */
+#include "builtin.h"
+#include <linux/compiler.h>
+#include <subcmd/parse-options.h>
+#include "debug.h"
+#include "machine.h"
+#include "symbol.h"
+
+static int __cmd_kallsyms(int argc, const char **argv)
+{
+	int i;
+	struct machine *machine = machine__new_kallsyms();
+
+	if (machine == NULL) {
+		pr_err("Couldn't read /proc/kallsyms\n");
+		return -1;
+	}
+
+	for (i = 0; i < argc; ++i) {
+		struct map *map;
+		struct symbol *symbol = machine__find_kernel_function_by_name(machine, argv[i], &map);
+
+		if (symbol == NULL) {
+			printf("%s: not found\n", argv[i]);
+			continue;
+		}
+
+		printf("%s: %s %s %#" PRIx64 "-%#" PRIx64 " (%#" PRIx64 "-%#" PRIx64")\n",
+			symbol->name, map->dso->short_name, map->dso->long_name,
+			map->unmap_ip(map, symbol->start), map->unmap_ip(map, symbol->end),
+			symbol->start, symbol->end);
+	}
+
+	machine__delete(machine);
+	return 0;
+}
+
+int cmd_kallsyms(int argc, const char **argv, const char *prefix __maybe_unused)
+{
+	const struct option options[] = {
+	OPT_INCR('v', "verbose", &verbose, "be more verbose (show counter open errors, etc)"),
+	OPT_END()
+	};
+	const char * const kallsyms_usage[] = {
+		"perf kallsyms [<options>] symbol_name",
+		NULL
+	};
+
+	argc = parse_options(argc, argv, options, kallsyms_usage, 0);
+	if (argc < 1)
+		usage_with_options(kallsyms_usage, options);
+
+	symbol_conf.sort_by_name = true;
+	symbol_conf.try_vmlinux_path = (symbol_conf.vmlinux_name == NULL);
+	if (symbol__init(NULL) < 0)
+		return -1;
+
+	return __cmd_kallsyms(argc, argv);
+}
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 4ec10e9427d9..33a9eaaf9db4 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -46,6 +46,15 @@
 #include <asm/bug.h>
 #include <linux/time64.h>
 
+struct switch_output {
+	bool		 enabled;
+	bool		 signal;
+	unsigned long	 size;
+	unsigned long	 time;
+	const char	*str;
+	bool		 set;
+};
+
 struct record {
 	struct perf_tool	tool;
 	struct record_opts	opts;
@@ -62,10 +71,33 @@ struct record {
 	bool			no_buildid_cache_set;
 	bool			buildid_all;
 	bool			timestamp_filename;
-	bool			switch_output;
+	struct switch_output	switch_output;
 	unsigned long long	samples;
 };
 
+static volatile int auxtrace_record__snapshot_started;
+static DEFINE_TRIGGER(auxtrace_snapshot_trigger);
+static DEFINE_TRIGGER(switch_output_trigger);
+
+static bool switch_output_signal(struct record *rec)
+{
+	return rec->switch_output.signal &&
+	       trigger_is_ready(&switch_output_trigger);
+}
+
+static bool switch_output_size(struct record *rec)
+{
+	return rec->switch_output.size &&
+	       trigger_is_ready(&switch_output_trigger) &&
+	       (rec->bytes_written >= rec->switch_output.size);
+}
+
+static bool switch_output_time(struct record *rec)
+{
+	return rec->switch_output.time &&
+	       trigger_is_ready(&switch_output_trigger);
+}
+
 static int record__write(struct record *rec, void *bf, size_t size)
 {
 	if (perf_data_file__write(rec->session->file, bf, size) < 0) {
@@ -74,6 +106,10 @@ static int record__write(struct record *rec, void *bf, size_t size)
 	}
 
 	rec->bytes_written += size;
+
+	if (switch_output_size(rec))
+		trigger_hit(&switch_output_trigger);
+
 	return 0;
 }
 
@@ -193,10 +229,6 @@ static volatile int done;
 static volatile int signr = -1;
 static volatile int child_finished;
 
-static volatile int auxtrace_record__snapshot_started;
-static DEFINE_TRIGGER(auxtrace_snapshot_trigger);
-static DEFINE_TRIGGER(switch_output_trigger);
-
 static void sig_handler(int sig)
 {
 	if (sig == SIGCHLD)
@@ -712,6 +744,7 @@ static void workload_exec_failed_signal(int signo __maybe_unused,
 }
 
 static void snapshot_sig_handler(int sig);
+static void alarm_sig_handler(int sig);
 
 int __weak
 perf_event__synth_time_conv(const struct perf_event_mmap_page *pc __maybe_unused,
@@ -842,11 +875,11 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 	signal(SIGTERM, sig_handler);
 	signal(SIGSEGV, sigsegv_handler);
 
-	if (rec->opts.auxtrace_snapshot_mode || rec->switch_output) {
+	if (rec->opts.auxtrace_snapshot_mode || rec->switch_output.enabled) {
 		signal(SIGUSR2, snapshot_sig_handler);
 		if (rec->opts.auxtrace_snapshot_mode)
 			trigger_on(&auxtrace_snapshot_trigger);
-		if (rec->switch_output)
+		if (rec->switch_output.enabled)
 			trigger_on(&switch_output_trigger);
 	} else {
 		signal(SIGUSR2, SIG_IGN);
@@ -1043,6 +1076,10 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 				err = fd;
 				goto out_child;
 			}
+
+			/* re-arm the alarm */
+			if (rec->switch_output.time)
+				alarm(rec->switch_output.time);
 		}
 
 		if (hits == rec->samples) {
@@ -1352,6 +1389,78 @@ out_free:
 	return ret;
 }
 
+static void switch_output_size_warn(struct record *rec)
+{
+	u64 wakeup_size = perf_evlist__mmap_size(rec->opts.mmap_pages);
+	struct switch_output *s = &rec->switch_output;
+
+	wakeup_size /= 2;
+
+	if (s->size < wakeup_size) {
+		char buf[100];
+
+		unit_number__scnprintf(buf, sizeof(buf), wakeup_size);
+		pr_warning("WARNING: switch-output data size lower than "
+			   "wakeup kernel buffer size (%s) "
+			   "expect bigger perf.data sizes\n", buf);
+	}
+}
+
+static int switch_output_setup(struct record *rec)
+{
+	struct switch_output *s = &rec->switch_output;
+	static struct parse_tag tags_size[] = {
+		{ .tag  = 'B', .mult = 1       },
+		{ .tag  = 'K', .mult = 1 << 10 },
+		{ .tag  = 'M', .mult = 1 << 20 },
+		{ .tag  = 'G', .mult = 1 << 30 },
+		{ .tag  = 0 },
+	};
+	static struct parse_tag tags_time[] = {
+		{ .tag  = 's', .mult = 1        },
+		{ .tag  = 'm', .mult = 60       },
+		{ .tag  = 'h', .mult = 60*60    },
+		{ .tag  = 'd', .mult = 60*60*24 },
+		{ .tag  = 0 },
+	};
+	unsigned long val;
+
+	if (!s->set)
+		return 0;
+
+	if (!strcmp(s->str, "signal")) {
+		s->signal = true;
+		pr_debug("switch-output with SIGUSR2 signal\n");
+		goto enabled;
+	}
+
+	val = parse_tag_value(s->str, tags_size);
+	if (val != (unsigned long) -1) {
+		s->size = val;
+		pr_debug("switch-output with %s size threshold\n", s->str);
+		goto enabled;
+	}
+
+	val = parse_tag_value(s->str, tags_time);
+	if (val != (unsigned long) -1) {
+		s->time = val;
+		pr_debug("switch-output with %s time threshold (%lu seconds)\n",
+			 s->str, s->time);
+		goto enabled;
+	}
+
+	return -1;
+
+enabled:
+	rec->timestamp_filename = true;
+	s->enabled              = true;
+
+	if (s->size && !rec->opts.no_buffering)
+		switch_output_size_warn(rec);
+
+	return 0;
+}
+
 static const char * const __record_usage[] = {
 	"perf record [<options>] [<command>]",
 	"perf record [<options>] -- <command> [<options>]",
@@ -1519,8 +1628,10 @@ static struct option __record_options[] = {
 		    "Record build-id of all DSOs regardless of hits"),
 	OPT_BOOLEAN(0, "timestamp-filename", &record.timestamp_filename,
 		    "append timestamp to output filename"),
-	OPT_BOOLEAN(0, "switch-output", &record.switch_output,
-		    "Switch output when receive SIGUSR2"),
+	OPT_STRING_OPTARG_SET(0, "switch-output", &record.switch_output.str,
+			  &record.switch_output.set, "signal,size,time",
+			  "Switch output when receive SIGUSR2 or cross size,time threshold",
+			  "signal"),
 	OPT_BOOLEAN(0, "dry-run", &dry_run,
 		    "Parse options then exit"),
 	OPT_END()
@@ -1578,8 +1689,15 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
 		return -EINVAL;
 	}
 
-	if (rec->switch_output)
-		rec->timestamp_filename = true;
+	if (switch_output_setup(rec)) {
+		parse_options_usage(record_usage, record_options, "switch-output", 0);
+		return -EINVAL;
+	}
+
+	if (rec->switch_output.time) {
+		signal(SIGALRM, alarm_sig_handler);
+		alarm(rec->switch_output.time);
+	}
 
 	if (!rec->itr) {
 		rec->itr = auxtrace_record__init(rec->evlist, &err);
@@ -1629,7 +1747,7 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
 
 	if (rec->no_buildid_cache || rec->no_buildid) {
 		disable_buildid_cache();
-	} else if (rec->switch_output) {
+	} else if (rec->switch_output.enabled) {
 		/*
 		 * In 'perf record --switch-output', disable buildid
 		 * generation by default to reduce data file switching
@@ -1721,6 +1839,8 @@ out:
 
 static void snapshot_sig_handler(int sig __maybe_unused)
 {
+	struct record *rec = &record;
+
 	if (trigger_is_ready(&auxtrace_snapshot_trigger)) {
 		trigger_hit(&auxtrace_snapshot_trigger);
 		auxtrace_record__snapshot_started = 1;
@@ -1728,6 +1848,14 @@ static void snapshot_sig_handler(int sig __maybe_unused)
 			trigger_error(&auxtrace_snapshot_trigger);
 	}
 
-	if (trigger_is_ready(&switch_output_trigger))
+	if (switch_output_signal(rec))
+		trigger_hit(&switch_output_trigger);
+}
+
+static void alarm_sig_handler(int sig __maybe_unused)
+{
+	struct record *rec = &record;
+
+	if (switch_output_time(rec))
 		trigger_hit(&switch_output_trigger);
 }
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index 5b134b0d1ff3..daceb3202200 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -77,6 +77,22 @@ struct sched_atom {
 
 #define TASK_STATE_TO_CHAR_STR "RSDTtZXxKWP"
 
+/* task state bitmask, copied from include/linux/sched.h */
+#define TASK_RUNNING		0
+#define TASK_INTERRUPTIBLE	1
+#define TASK_UNINTERRUPTIBLE	2
+#define __TASK_STOPPED		4
+#define __TASK_TRACED		8
+/* in tsk->exit_state */
+#define EXIT_DEAD		16
+#define EXIT_ZOMBIE		32
+#define EXIT_TRACE		(EXIT_ZOMBIE | EXIT_DEAD)
+/* in tsk->state again */
+#define TASK_DEAD		64
+#define TASK_WAKEKILL		128
+#define TASK_WAKING		256
+#define TASK_PARKED		512
+
 enum thread_state {
 	THREAD_SLEEPING = 0,
 	THREAD_WAIT_CPU,
@@ -206,6 +222,7 @@ struct perf_sched {
 	bool		show_cpu_visual;
 	bool		show_wakeups;
 	bool		show_migrations;
+	bool		show_state;
 	u64		skipped_samples;
 	const char	*time_str;
 	struct perf_time_interval ptime;
@@ -216,13 +233,20 @@ struct perf_sched {
 struct thread_runtime {
 	u64 last_time;      /* time of previous sched in/out event */
 	u64 dt_run;         /* run time */
-	u64 dt_wait;        /* time between CPU access (off cpu) */
+	u64 dt_sleep;       /* time between CPU access by sleep (off cpu) */
+	u64 dt_iowait;      /* time between CPU access by iowait (off cpu) */
+	u64 dt_preempt;     /* time between CPU access by preempt (off cpu) */
 	u64 dt_delay;       /* time between wakeup and sched-in */
 	u64 ready_to_run;   /* time of wakeup */
 
 	struct stats run_stats;
 	u64 total_run_time;
+	u64 total_sleep_time;
+	u64 total_iowait_time;
+	u64 total_preempt_time;
+	u64 total_delay_time;
 
+	int last_state;
 	u64 migrations;
 };
 
@@ -1821,6 +1845,9 @@ static void timehist_header(struct perf_sched *sched)
 	printf(" %-*s  %9s  %9s  %9s", comm_width,
 		"task name", "wait time", "sch delay", "run time");
 
+	if (sched->show_state)
+		printf("  %s", "state");
+
 	printf("\n");
 
 	/*
@@ -1831,9 +1858,14 @@ static void timehist_header(struct perf_sched *sched)
 	if (sched->show_cpu_visual)
 		printf(" %*s ", ncpus, "");
 
-	printf(" %-*s  %9s  %9s  %9s\n", comm_width,
+	printf(" %-*s  %9s  %9s  %9s", comm_width,
 	       "[tid/pid]", "(msec)", "(msec)", "(msec)");
 
+	if (sched->show_state)
+		printf("  %5s", "");
+
+	printf("\n");
+
 	/*
 	 * separator
 	 */
@@ -1846,18 +1878,34 @@ static void timehist_header(struct perf_sched *sched)
 		graph_dotted_line, graph_dotted_line, graph_dotted_line,
 		graph_dotted_line);
 
+	if (sched->show_state)
+		printf("  %.5s", graph_dotted_line);
+
 	printf("\n");
 }
 
+static char task_state_char(struct thread *thread, int state)
+{
+	static const char state_to_char[] = TASK_STATE_TO_CHAR_STR;
+	unsigned bit = state ? ffs(state) : 0;
+
+	/* 'I' for idle */
+	if (thread->tid == 0)
+		return 'I';
+
+	return bit < sizeof(state_to_char) - 1 ? state_to_char[bit] : '?';
+}
+
 static void timehist_print_sample(struct perf_sched *sched,
 				  struct perf_sample *sample,
 				  struct addr_location *al,
 				  struct thread *thread,
-				  u64 t)
+				  u64 t, int state)
 {
 	struct thread_runtime *tr = thread__priv(thread);
 	u32 max_cpus = sched->max_cpu + 1;
 	char tstr[64];
+	u64 wait_time;
 
 	timestamp__scnprintf_usec(t, tstr, sizeof(tstr));
 	printf("%15s [%04d] ", tstr, sample->cpu);
@@ -1880,10 +1928,15 @@ static void timehist_print_sample(struct perf_sched *sched,
 
 	printf(" %-*s ", comm_width, timehist_get_commstr(thread));
 
-	print_sched_time(tr->dt_wait, 6);
+	wait_time = tr->dt_sleep + tr->dt_iowait + tr->dt_preempt;
+	print_sched_time(wait_time, 6);
+
 	print_sched_time(tr->dt_delay, 6);
 	print_sched_time(tr->dt_run, 6);
 
+	if (sched->show_state)
+		printf(" %5c ", task_state_char(thread, state));
+
 	if (sched->show_wakeups)
 		printf("  %-*s", comm_width, "");
 
@@ -1930,8 +1983,11 @@ static void timehist_update_runtime_stats(struct thread_runtime *r,
 					 u64 t, u64 tprev)
 {
 	r->dt_delay   = 0;
-	r->dt_wait    = 0;
+	r->dt_sleep   = 0;
+	r->dt_iowait  = 0;
+	r->dt_preempt = 0;
 	r->dt_run     = 0;
+
 	if (tprev) {
 		r->dt_run = t - tprev;
 		if (r->ready_to_run) {
@@ -1943,12 +1999,25 @@ static void timehist_update_runtime_stats(struct thread_runtime *r,
 
 		if (r->last_time > tprev)
 			pr_debug("time travel: last sched out time for task > previous sched_switch event\n");
-		else if (r->last_time)
-			r->dt_wait = tprev - r->last_time;
+		else if (r->last_time) {
+			u64 dt_wait = tprev - r->last_time;
+
+			if (r->last_state == TASK_RUNNING)
+				r->dt_preempt = dt_wait;
+			else if (r->last_state == TASK_UNINTERRUPTIBLE)
+				r->dt_iowait = dt_wait;
+			else
+				r->dt_sleep = dt_wait;
+		}
 	}
 
 	update_stats(&r->run_stats, r->dt_run);
-	r->total_run_time += r->dt_run;
+
+	r->total_run_time     += r->dt_run;
+	r->total_delay_time   += r->dt_delay;
+	r->total_sleep_time   += r->dt_sleep;
+	r->total_iowait_time  += r->dt_iowait;
+	r->total_preempt_time += r->dt_preempt;
 }
 
 static bool is_idle_sample(struct perf_sample *sample,
@@ -2373,6 +2442,8 @@ static int timehist_sched_change_event(struct perf_tool *tool,
 	struct thread_runtime *tr = NULL;
 	u64 tprev, t = sample->time;
 	int rc = 0;
+	int state = perf_evsel__intval(evsel, sample, "prev_state");
+
 
 	if (machine__resolve(machine, &al, sample) < 0) {
 		pr_err("problem processing %d event. skipping it\n",
@@ -2447,8 +2518,10 @@ static int timehist_sched_change_event(struct perf_tool *tool,
 			 * time.  we only care total run time and run stat.
 			 */
 			last_tr->dt_run = 0;
-			last_tr->dt_wait = 0;
 			last_tr->dt_delay = 0;
+			last_tr->dt_sleep = 0;
+			last_tr->dt_iowait = 0;
+			last_tr->dt_preempt = 0;
 
 			if (itr->cursor.nr)
 				callchain_append(&itr->callchain, &itr->cursor, t - tprev);
@@ -2458,7 +2531,7 @@ static int timehist_sched_change_event(struct perf_tool *tool,
 	}
 
 	if (!sched->summary_only)
-		timehist_print_sample(sched, sample, &al, thread, t);
+		timehist_print_sample(sched, sample, &al, thread, t, state);
 
 out:
 	if (sched->hist_time.start == 0 && t >= ptime->start)
@@ -2470,6 +2543,9 @@ out:
 		/* time of this sched_switch event becomes last time task seen */
 		tr->last_time = sample->time;
 
+		/* last state is used to determine where to account wait time */
+		tr->last_state = state;
+
 		/* sched out event for task so reset ready to run time */
 		tr->ready_to_run = 0;
 	}
@@ -2526,7 +2602,26 @@ static void print_thread_runtime(struct thread *t,
 	printf("\n");
 }
 
+static void print_thread_waittime(struct thread *t,
+				  struct thread_runtime *r)
+{
+	printf("%*s   %5d  %9" PRIu64 " ",
+	       comm_width, timehist_get_commstr(t), t->ppid,
+	       (u64) r->run_stats.n);
+
+	print_sched_time(r->total_run_time, 8);
+	print_sched_time(r->total_sleep_time, 6);
+	printf(" ");
+	print_sched_time(r->total_iowait_time, 6);
+	printf(" ");
+	print_sched_time(r->total_preempt_time, 6);
+	printf(" ");
+	print_sched_time(r->total_delay_time, 6);
+	printf("\n");
+}
+
 struct total_run_stats {
+	struct perf_sched *sched;
 	u64  sched_count;
 	u64  task_count;
 	u64  total_run_time;
@@ -2545,7 +2640,11 @@ static int __show_thread_runtime(struct thread *t, void *priv)
 		stats->task_count++;
 		stats->sched_count += r->run_stats.n;
 		stats->total_run_time += r->total_run_time;
-		print_thread_runtime(t, r);
+
+		if (stats->sched->show_state)
+			print_thread_waittime(t, r);
+		else
+			print_thread_runtime(t, r);
 	}
 
 	return 0;
@@ -2633,18 +2732,24 @@ static void timehist_print_summary(struct perf_sched *sched,
 	u64 hist_time = sched->hist_time.end - sched->hist_time.start;
 
 	memset(&totals, 0, sizeof(totals));
+	totals.sched = sched;
 
 	if (sched->idle_hist) {
 		printf("\nIdle-time summary\n");
 		printf("%*s  parent  sched-out  ", comm_width, "comm");
 		printf("  idle-time   min-idle    avg-idle    max-idle  stddev  migrations\n");
+	} else if (sched->show_state) {
+		printf("\nWait-time summary\n");
+		printf("%*s  parent   sched-in  ", comm_width, "comm");
+		printf("   run-time      sleep      iowait     preempt       delay\n");
 	} else {
 		printf("\nRuntime summary\n");
 		printf("%*s  parent   sched-in  ", comm_width, "comm");
 		printf("   run-time    min-run     avg-run     max-run  stddev  migrations\n");
 	}
 	printf("%*s            (count)  ", comm_width, "");
-	printf("     (msec)     (msec)      (msec)      (msec)       %%\n");
+	printf("     (msec)     (msec)      (msec)      (msec)       %s\n",
+	       sched->show_state ? "(msec)" : "%");
 	printf("%.117s\n", graph_dotted_line);
 
 	machine__for_each_thread(m, show_thread_runtime, &totals);
@@ -3240,6 +3345,7 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused)
 	OPT_BOOLEAN('I', "idle-hist", &sched.idle_hist, "Show idle events only"),
 	OPT_STRING(0, "time", &sched.time_str, "str",
 		   "Time span for analysis (start,stop)"),
+	OPT_BOOLEAN(0, "state", &sched.show_state, "Show task state when sched-out"),
 	OPT_PARENT(sched_options)
 	};
 
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 2f3ff69fc4e7..c0783b4f7b6c 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -2180,7 +2180,7 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 		    "Show the mmap events"),
 	OPT_BOOLEAN('\0', "show-switch-events", &script.show_switch_events,
 		    "Show context switch events (if recorded)"),
-	OPT_BOOLEAN('f', "force", &file.force, "don't complain, do it"),
+	OPT_BOOLEAN('f', "force", &symbol_conf.force, "don't complain, do it"),
 	OPT_BOOLEAN(0, "ns", &nanosecs,
 		    "Use 9 decimal places when displaying time"),
 	OPT_CALLBACK_OPTARG(0, "itrace", &itrace_synth_opts, NULL, "opts",
@@ -2212,6 +2212,7 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 			     PARSE_OPT_STOP_AT_NON_OPTION);
 
 	file.path = input_name;
+	file.force = symbol_conf.force;
 
 	if (argc > 1 && !strncmp(argv[0], "rec", strlen("rec"))) {
 		rec_script_path = get_script_path(argv[1], RECORD_SUFFIX);
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 206bf72b77fc..40ef9b293d1b 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -40,6 +40,7 @@
 
 #include <libaudit.h> /* FIXME: Still needed for audit_errno_to_name */
 #include <stdlib.h>
+#include <string.h>
 #include <linux/err.h>
 #include <linux/filter.h>
 #include <linux/audit.h>
@@ -2699,6 +2700,91 @@ static void evlist__set_evsel_handler(struct perf_evlist *evlist, void *handler)
 		evsel->handler = handler;
 }
 
+/*
+ * XXX: Hackish, just splitting the combined -e+--event (syscalls
+ * (raw_syscalls:{sys_{enter,exit}} + events (tracepoints, HW, SW, etc) to use
+ * existing facilities unchanged (trace->ev_qualifier + parse_options()).
+ *
+ * It'd be better to introduce a parse_options() variant that would return a
+ * list with the terms it didn't match to an event...
+ */
+static int trace__parse_events_option(const struct option *opt, const char *str,
+				      int unset __maybe_unused)
+{
+	struct trace *trace = (struct trace *)opt->value;
+	const char *s = str;
+	char *sep = NULL, *lists[2] = { NULL, NULL, };
+	int len = strlen(str), err = -1, list;
+	char *strace_groups_dir = system_path(STRACE_GROUPS_DIR);
+	char group_name[PATH_MAX];
+
+	if (strace_groups_dir == NULL)
+		return -1;
+
+	if (*s == '!') {
+		++s;
+		trace->not_ev_qualifier = true;
+	}
+
+	while (1) {
+		if ((sep = strchr(s, ',')) != NULL)
+			*sep = '\0';
+
+		list = 0;
+		if (syscalltbl__id(trace->sctbl, s) >= 0) {
+			list = 1;
+		} else {
+			path__join(group_name, sizeof(group_name), strace_groups_dir, s);
+			if (access(group_name, R_OK) == 0)
+				list = 1;
+		}
+
+		if (lists[list]) {
+			sprintf(lists[list] + strlen(lists[list]), ",%s", s);
+		} else {
+			lists[list] = malloc(len);
+			if (lists[list] == NULL)
+				goto out;
+			strcpy(lists[list], s);
+		}
+
+		if (!sep)
+			break;
+
+		*sep = ',';
+		s = sep + 1;
+	}
+
+	if (lists[1] != NULL) {
+		struct strlist_config slist_config = {
+			.dirname = strace_groups_dir,
+		};
+
+		trace->ev_qualifier = strlist__new(lists[1], &slist_config);
+		if (trace->ev_qualifier == NULL) {
+			fputs("Not enough memory to parse event qualifier", trace->output);
+			goto out;
+		}
+
+		if (trace__validate_ev_qualifier(trace))
+			goto out;
+	}
+
+	err = 0;
+
+	if (lists[0]) {
+		struct option o = OPT_CALLBACK('e', "event", &trace->evlist, "event",
+					       "event selector. use 'perf list' to list available events",
+					       parse_events_option);
+		err = parse_events_option(&o, lists[0], 0);
+	}
+out:
+	if (sep)
+		*sep = ',';
+
+	return err;
+}
+
 int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
 {
 	const char *trace_usage[] = {
@@ -2730,15 +2816,15 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
 		.max_stack = UINT_MAX,
 	};
 	const char *output_name = NULL;
-	const char *ev_qualifier_str = NULL;
 	const struct option trace_options[] = {
-	OPT_CALLBACK(0, "event", &trace.evlist, "event",
-		     "event selector. use 'perf list' to list available events",
-		     parse_events_option),
+	OPT_CALLBACK('e', "event", &trace, "event",
+		     "event/syscall selector. use 'perf list' to list available events",
+		     trace__parse_events_option),
 	OPT_BOOLEAN(0, "comm", &trace.show_comm,
 		    "show the thread COMM next to its id"),
 	OPT_BOOLEAN(0, "tool_stats", &trace.show_tool_stats, "show tool stats"),
-	OPT_STRING('e', "expr", &ev_qualifier_str, "expr", "list of syscalls to trace"),
+	OPT_CALLBACK(0, "expr", &trace, "expr", "list of syscalls/events to trace",
+		     trace__parse_events_option),
 	OPT_STRING('o', "output", &output_name, "file", "output file name"),
 	OPT_STRING('i', "input", &input_name, "file", "Analyze events in file"),
 	OPT_STRING('p', "pid", &trace.opts.target.pid, "pid",
@@ -2863,7 +2949,7 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
 		return -1;
 	}
 
-	if (!trace.trace_syscalls && ev_qualifier_str) {
+	if (!trace.trace_syscalls && trace.ev_qualifier) {
 		pr_err("The -e option can't be used with --no-syscalls.\n");
 		goto out;
 	}
@@ -2878,28 +2964,6 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
 
 	trace.open_id = syscalltbl__id(trace.sctbl, "open");
 
-	if (ev_qualifier_str != NULL) {
-		const char *s = ev_qualifier_str;
-		struct strlist_config slist_config = {
-			.dirname = system_path(STRACE_GROUPS_DIR),
-		};
-
-		trace.not_ev_qualifier = *s == '!';
-		if (trace.not_ev_qualifier)
-			++s;
-		trace.ev_qualifier = strlist__new(s, &slist_config);
-		if (trace.ev_qualifier == NULL) {
-			fputs("Not enough memory to parse event qualifier",
-			      trace.output);
-			err = -ENOMEM;
-			goto out_close;
-		}
-
-		err = trace__validate_ev_qualifier(&trace);
-		if (err)
-			goto out_close;
-	}
-
 	err = target__validate(&trace.opts.target);
 	if (err) {
 		target__strerror(&trace.opts.target, err, bf, sizeof(bf));
diff --git a/tools/perf/builtin.h b/tools/perf/builtin.h
index 0bcf68e98ccc..036e1e35b1a8 100644
--- a/tools/perf/builtin.h
+++ b/tools/perf/builtin.h
@@ -23,6 +23,7 @@ int cmd_diff(int argc, const char **argv, const char *prefix);
 int cmd_evlist(int argc, const char **argv, const char *prefix);
 int cmd_help(int argc, const char **argv, const char *prefix);
 int cmd_sched(int argc, const char **argv, const char *prefix);
+int cmd_kallsyms(int argc, const char **argv, const char *prefix);
 int cmd_list(int argc, const char **argv, const char *prefix);
 int cmd_record(int argc, const char **argv, const char *prefix);
 int cmd_report(int argc, const char **argv, const char *prefix);
@@ -40,6 +41,7 @@ int cmd_trace(int argc, const char **argv, const char *prefix);
 int cmd_inject(int argc, const char **argv, const char *prefix);
 int cmd_mem(int argc, const char **argv, const char *prefix);
 int cmd_data(int argc, const char **argv, const char *prefix);
+int cmd_ftrace(int argc, const char **argv, const char *prefix);
 
 int find_scripts(char **scripts_array, char **scripts_path_array);
 #endif
diff --git a/tools/perf/command-list.txt b/tools/perf/command-list.txt
index ab5cbaa170d0..ac3efd396a72 100644
--- a/tools/perf/command-list.txt
+++ b/tools/perf/command-list.txt
@@ -11,7 +11,9 @@ perf-data			mainporcelain common
 perf-diff			mainporcelain common
 perf-config			mainporcelain common
 perf-evlist			mainporcelain common
+perf-ftrace			mainporcelain common
 perf-inject			mainporcelain common
+perf-kallsyms			mainporcelain common
 perf-kmem			mainporcelain common
 perf-kvm			mainporcelain common
 perf-list			mainporcelain common
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index aa23b3347d6b..34bcf90f8871 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -29,7 +29,6 @@ const char perf_usage_string[] =
 const char perf_more_info_string[] =
 	"See 'perf help COMMAND' for more information on a specific command.";
 
-int use_browser = -1;
 static int use_pager = -1;
 const char *input_name;
 
@@ -47,6 +46,7 @@ static struct cmd_struct commands[] = {
 	{ "diff",	cmd_diff,	0 },
 	{ "evlist",	cmd_evlist,	0 },
 	{ "help",	cmd_help,	0 },
+	{ "kallsyms",	cmd_kallsyms,	0 },
 	{ "list",	cmd_list,	0 },
 	{ "record",	cmd_record,	0 },
 	{ "report",	cmd_report,	0 },
@@ -71,6 +71,7 @@ static struct cmd_struct commands[] = {
 	{ "inject",	cmd_inject,	0 },
 	{ "mem",	cmd_mem,	0 },
 	{ "data",	cmd_data,	0 },
+	{ "ftrace",	cmd_ftrace,	0 },
 };
 
 struct pager_config {
@@ -329,8 +330,6 @@ static int handle_alias(int *argcp, const char ***argv)
 	return ret;
 }
 
-const char perf_version_string[] = PERF_VERSION;
-
 #define RUN_SETUP	(1<<0)
 #define USE_PAGER	(1<<1)
 
diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build
index 6676c2dd6dcb..1cb3d9b540e9 100644
--- a/tools/perf/tests/Build
+++ b/tools/perf/tests/Build
@@ -44,6 +44,7 @@ perf-y += is_printable_array.o
 perf-y += bitmap.o
 perf-y += perf-hooks.o
 perf-y += clang.o
+perf-y += unit_number__scnprintf.o
 
 $(OUTPUT)tests/llvm-src-base.c: tests/bpf-script-example.c tests/Build
 	$(call rule_mkdir)
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index a77dcc0d24e3..37e326bfd2dc 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -247,6 +247,10 @@ static struct test generic_tests[] = {
 		}
 	},
 	{
+		.desc = "unit_number__scnprintf",
+		.func = test__unit_number__scnprint,
+	},
+	{
 		.func = NULL,
 	},
 };
diff --git a/tools/perf/tests/llvm.c b/tools/perf/tests/llvm.c
index 02a33ebcd992..d357dab72e68 100644
--- a/tools/perf/tests/llvm.c
+++ b/tools/perf/tests/llvm.c
@@ -13,7 +13,7 @@ static int test__bpf_parsing(void *obj_buf, size_t obj_buf_sz)
 	struct bpf_object *obj;
 
 	obj = bpf_object__open_buffer(obj_buf, obj_buf_sz, NULL);
-	if (IS_ERR(obj))
+	if (libbpf_get_error(obj))
 		return TEST_FAIL;
 	bpf_object__close(obj);
 	return TEST_OK;
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index a512f0c8ff5b..1fa9b9d83aa5 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -96,6 +96,7 @@ int test__perf_hooks(int subtest);
 int test__clang(int subtest);
 const char *test__clang_subtest_get_desc(int subtest);
 int test__clang_subtest_get_nr(void);
+int test__unit_number__scnprint(int subtest);
 
 #if defined(__arm__) || defined(__aarch64__)
 #ifdef HAVE_DWARF_UNWIND_SUPPORT
diff --git a/tools/perf/tests/unit_number__scnprintf.c b/tools/perf/tests/unit_number__scnprintf.c
new file mode 100644
index 000000000000..623c2aa53c4a
--- /dev/null
+++ b/tools/perf/tests/unit_number__scnprintf.c
@@ -0,0 +1,37 @@
+#include <linux/compiler.h>
+#include <linux/types.h>
+#include "tests.h"
+#include "util.h"
+#include "debug.h"
+
+int test__unit_number__scnprint(int subtest __maybe_unused)
+{
+	struct {
+		u64		 n;
+		const char	*str;
+	} test[] = {
+		{ 1,			"1B"	},
+		{ 10*1024,		"10K"	},
+		{ 20*1024*1024,		"20M"	},
+		{ 30*1024*1024*1024ULL,	"30G"	},
+		{ 0,			"0B"	},
+		{ 0,			NULL	},
+	};
+	unsigned i = 0;
+
+	while (test[i].str) {
+		char buf[100];
+
+		unit_number__scnprintf(buf, sizeof(buf), test[i].n);
+
+		pr_debug("n %" PRIu64 ", str '%s', buf '%s'\n",
+			 test[i].n, test[i].str, buf);
+
+		if (strcmp(test[i].str, buf))
+			return TEST_FAIL;
+
+		i++;
+	}
+
+	return TEST_OK;
+}
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index 641b40234a9d..fc4fb669ceee 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -501,8 +501,8 @@ static int hierarchy_set_folding(struct hist_browser *hb, struct hist_entry *he,
 	return n;
 }
 
-static void hist_entry__set_folding(struct hist_entry *he,
-				    struct hist_browser *hb, bool unfold)
+static void __hist_entry__set_folding(struct hist_entry *he,
+				      struct hist_browser *hb, bool unfold)
 {
 	hist_entry__init_have_children(he);
 	he->unfolded = unfold ? he->has_children : false;
@@ -520,12 +520,34 @@ static void hist_entry__set_folding(struct hist_entry *he,
 		he->nr_rows = 0;
 }
 
+static void hist_entry__set_folding(struct hist_entry *he,
+				    struct hist_browser *browser, bool unfold)
+{
+	double percent;
+
+	percent = hist_entry__get_percent_limit(he);
+	if (he->filtered || percent < browser->min_pcnt)
+		return;
+
+	__hist_entry__set_folding(he, browser, unfold);
+
+	if (!he->depth || unfold)
+		browser->nr_hierarchy_entries++;
+	if (he->leaf)
+		browser->nr_callchain_rows += he->nr_rows;
+	else if (unfold && !hist_entry__has_hierarchy_children(he, browser->min_pcnt)) {
+		browser->nr_hierarchy_entries++;
+		he->has_no_entry = true;
+		he->nr_rows = 1;
+	} else
+		he->has_no_entry = false;
+}
+
 static void
 __hist_browser__set_folding(struct hist_browser *browser, bool unfold)
 {
 	struct rb_node *nd;
 	struct hist_entry *he;
-	double percent;
 
 	nd = rb_first(&browser->hists->entries);
 	while (nd) {
@@ -535,21 +557,6 @@ __hist_browser__set_folding(struct hist_browser *browser, bool unfold)
 		nd = __rb_hierarchy_next(nd, HMD_FORCE_CHILD);
 
 		hist_entry__set_folding(he, browser, unfold);
-
-		percent = hist_entry__get_percent_limit(he);
-		if (he->filtered || percent < browser->min_pcnt)
-			continue;
-
-		if (!he->depth || unfold)
-			browser->nr_hierarchy_entries++;
-		if (he->leaf)
-			browser->nr_callchain_rows += he->nr_rows;
-		else if (unfold && !hist_entry__has_hierarchy_children(he, browser->min_pcnt)) {
-			browser->nr_hierarchy_entries++;
-			he->has_no_entry = true;
-			he->nr_rows = 1;
-		} else
-			he->has_no_entry = false;
 	}
 }
 
@@ -564,6 +571,15 @@ static void hist_browser__set_folding(struct hist_browser *browser, bool unfold)
 	ui_browser__reset_index(&browser->b);
 }
 
+static void hist_browser__set_folding_selected(struct hist_browser *browser, bool unfold)
+{
+	if (!browser->he_selection)
+		return;
+
+	hist_entry__set_folding(browser->he_selection, browser, unfold);
+	browser->b.nr_entries = hist_browser__nr_entries(browser);
+}
+
 static void ui_browser__warn_lost_events(struct ui_browser *browser)
 {
 	ui_browser__warning(browser, 4,
@@ -637,10 +653,18 @@ int hist_browser__run(struct hist_browser *browser, const char *help)
 			/* Collapse the whole world. */
 			hist_browser__set_folding(browser, false);
 			break;
+		case 'c':
+			/* Collapse the selected entry. */
+			hist_browser__set_folding_selected(browser, false);
+			break;
 		case 'E':
 			/* Expand the whole world. */
 			hist_browser__set_folding(browser, true);
 			break;
+		case 'e':
+			/* Expand the selected entry. */
+			hist_browser__set_folding_selected(browser, true);
+			break;
 		case 'H':
 			browser->show_headers = !browser->show_headers;
 			hist_browser__update_rows(browser);
diff --git a/tools/perf/ui/setup.c b/tools/perf/ui/setup.c
index 1f6b0994f4f4..50d13e58210f 100644
--- a/tools/perf/ui/setup.c
+++ b/tools/perf/ui/setup.c
@@ -7,6 +7,7 @@
 
 pthread_mutex_t ui__lock = PTHREAD_MUTEX_INITIALIZER;
 void *perf_gtk_handle;
+int use_browser = -1;
 
 #ifdef HAVE_GTK2_SUPPORT
 static int setup_gtk_browser(void)
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 3840e3a87057..5da376bc1afc 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -162,6 +162,7 @@ CFLAGS_rbtree.o        += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ET
 CFLAGS_libstring.o     += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
 CFLAGS_hweight.o       += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
 CFLAGS_parse-events.o  += -Wno-redundant-decls
+CFLAGS_header.o        += -include $(OUTPUT)PERF-VERSION-FILE
 
 $(OUTPUT)util/kallsyms.o: ../lib/symbol/kallsyms.c FORCE
 	$(call rule_mkdir)
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index d2c6cdd9d42b..28d41e709128 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -9,6 +9,13 @@
 #include "debug.h"
 #include "vdso.h"
 
+static const char * const debuglink_paths[] = {
+	"%.0s%s",
+	"%s/%s",
+	"%s/.debug/%s",
+	"/usr/lib/debug%s/%s"
+};
+
 char dso__symtab_origin(const struct dso *dso)
 {
 	static const char origin[] = {
@@ -44,24 +51,43 @@ int dso__read_binary_type_filename(const struct dso *dso,
 	size_t len;
 
 	switch (type) {
-	case DSO_BINARY_TYPE__DEBUGLINK: {
-		char *debuglink;
+	case DSO_BINARY_TYPE__DEBUGLINK:
+	{
+		const char *last_slash;
+		char dso_dir[PATH_MAX];
+		char symfile[PATH_MAX];
+		unsigned int i;
 
 		len = __symbol__join_symfs(filename, size, dso->long_name);
-		debuglink = filename + len;
-		while (debuglink != filename && *debuglink != '/')
-			debuglink--;
-		if (*debuglink == '/')
-			debuglink++;
+		last_slash = filename + len;
+		while (last_slash != filename && *last_slash != '/')
+			last_slash--;
 
-		ret = -1;
-		if (!is_regular_file(filename))
+		strncpy(dso_dir, filename, last_slash - filename);
+		dso_dir[last_slash-filename] = '\0';
+
+		if (!is_regular_file(filename)) {
+			ret = -1;
+			break;
+		}
+
+		ret = filename__read_debuglink(filename, symfile, PATH_MAX);
+		if (ret)
 			break;
 
-		ret = filename__read_debuglink(filename, debuglink,
-					       size - (debuglink - filename));
+		/* Check predefined locations where debug file might reside */
+		ret = -1;
+		for (i = 0; i < ARRAY_SIZE(debuglink_paths); i++) {
+			snprintf(filename, size,
+					debuglink_paths[i], dso_dir, symfile);
+			if (is_regular_file(filename)) {
+				ret = 0;
+				break;
+			}
 		}
+
 		break;
+	}
 	case DSO_BINARY_TYPE__BUILD_ID_CACHE:
 		if (dso__build_id_filename(dso, filename, size) == NULL)
 			ret = -1;
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index d92e02006fb8..b601f2814a30 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -1184,7 +1184,7 @@ unsigned long perf_event_mlock_kb_in_pages(void)
 	return pages;
 }
 
-static size_t perf_evlist__mmap_size(unsigned long pages)
+size_t perf_evlist__mmap_size(unsigned long pages)
 {
 	if (pages == UINT_MAX)
 		pages = perf_event_mlock_kb_in_pages();
@@ -1224,12 +1224,16 @@ static long parse_pages_arg(const char *str, unsigned long min,
 	if (pages == 0 && min == 0) {
 		/* leave number of pages at 0 */
 	} else if (!is_power_of_2(pages)) {
+		char buf[100];
+
 		/* round pages up to next power of 2 */
 		pages = roundup_pow_of_two(pages);
 		if (!pages)
 			return -EINVAL;
-		pr_info("rounding mmap pages size to %lu bytes (%lu pages)\n",
-			pages * page_size, pages);
+
+		unit_number__scnprintf(buf, sizeof(buf), pages * page_size);
+		pr_info("rounding mmap pages size to %s (%lu pages)\n",
+			buf, pages);
 	}
 
 	if (pages > max)
@@ -1797,7 +1801,7 @@ int perf_evlist__start_workload(struct perf_evlist *evlist)
 		 */
 		ret = write(evlist->workload.cork_fd, &bf, 1);
 		if (ret < 0)
-			perror("enable to write to pipe");
+			perror("unable to write to pipe");
 
 		close(evlist->workload.cork_fd);
 		return ret;
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 4fd034f22d2f..389b9ccdf8c7 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -218,6 +218,8 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
 		      bool overwrite);
 void perf_evlist__munmap(struct perf_evlist *evlist);
 
+size_t perf_evlist__mmap_size(unsigned long pages);
+
 void perf_evlist__disable(struct perf_evlist *evlist);
 void perf_evlist__enable(struct perf_evlist *evlist);
 void perf_evlist__toggle_enable(struct perf_evlist *evlist);
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index d89c9c7ef4e5..c567d9f0aa92 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -41,6 +41,8 @@ static const u64 __perf_magic2_sw = 0x50455246494c4532ULL;
 
 #define PERF_MAGIC	__perf_magic2
 
+const char perf_version_string[] = PERF_VERSION;
+
 struct perf_file_attr {
 	struct perf_event_attr	attr;
 	struct perf_file_section	ids;
@@ -2801,8 +2803,10 @@ static int perf_evsel__prepare_tracepoint_event(struct perf_evsel *evsel,
 	}
 
 	event = pevent_find_event(pevent, evsel->attr.config);
-	if (event == NULL)
+	if (event == NULL) {
+		pr_debug("cannot find event format for %d\n", (int)evsel->attr.config);
 		return -1;
+	}
 
 	if (!evsel->name) {
 		snprintf(bf, sizeof(bf), "%s:%s", event->system, event->name);
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 9b33bef54581..747a034d1ff3 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -87,6 +87,25 @@ out_delete:
 	return NULL;
 }
 
+struct machine *machine__new_kallsyms(void)
+{
+	struct machine *machine = machine__new_host();
+	/*
+	 * FIXME:
+	 * 1) MAP__FUNCTION will go away when we stop loading separate maps for
+	 *    functions and data objects.
+	 * 2) We should switch to machine__load_kallsyms(), i.e. not explicitely
+	 *    ask for not using the kcore parsing code, once this one is fixed
+	 *    to create a map per module.
+	 */
+	if (machine && __machine__load_kallsyms(machine, "/proc/kallsyms", MAP__FUNCTION, true) <= 0) {
+		machine__delete(machine);
+		machine = NULL;
+	}
+
+	return machine;
+}
+
 static void dsos__purge(struct dsos *dsos)
 {
 	struct dso *pos, *n;
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index 354de6e56109..a28305029711 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -129,6 +129,7 @@ char *machine__mmap_name(struct machine *machine, char *bf, size_t size);
 void machines__set_comm_exec(struct machines *machines, bool comm_exec);
 
 struct machine *machine__new_host(void);
+struct machine *machine__new_kallsyms(void);
 int machine__init(struct machine *machine, const char *root_dir, pid_t pid);
 void machine__exit(struct machine *machine);
 void machine__delete_threads(struct machine *machine);
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index dc6ccaa4e927..78b16100567d 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -94,32 +94,10 @@ static int pmu_format(const char *name, struct list_head *format)
 	return 0;
 }
 
-static int perf_pmu__parse_scale(struct perf_pmu_alias *alias, char *dir, char *name)
+static int convert_scale(const char *scale, char **end, double *sval)
 {
-	struct stat st;
-	ssize_t sret;
-	char scale[128];
-	int fd, ret = -1;
-	char path[PATH_MAX];
 	char *lc;
-
-	snprintf(path, PATH_MAX, "%s/%s.scale", dir, name);
-
-	fd = open(path, O_RDONLY);
-	if (fd == -1)
-		return -1;
-
-	if (fstat(fd, &st) < 0)
-		goto error;
-
-	sret = read(fd, scale, sizeof(scale)-1);
-	if (sret < 0)
-		goto error;
-
-	if (scale[sret - 1] == '\n')
-		scale[sret - 1] = '\0';
-	else
-		scale[sret] = '\0';
+	int ret = 0;
 
 	/*
 	 * save current locale
@@ -134,7 +112,7 @@ static int perf_pmu__parse_scale(struct perf_pmu_alias *alias, char *dir, char *
 	lc = strdup(lc);
 	if (!lc) {
 		ret = -ENOMEM;
-		goto error;
+		goto out;
 	}
 
 	/*
@@ -144,14 +122,42 @@ static int perf_pmu__parse_scale(struct perf_pmu_alias *alias, char *dir, char *
 	 */
 	setlocale(LC_NUMERIC, "C");
 
-	alias->scale = strtod(scale, NULL);
+	*sval = strtod(scale, end);
 
+out:
 	/* restore locale */
 	setlocale(LC_NUMERIC, lc);
-
 	free(lc);
+	return ret;
+}
+
+static int perf_pmu__parse_scale(struct perf_pmu_alias *alias, char *dir, char *name)
+{
+	struct stat st;
+	ssize_t sret;
+	char scale[128];
+	int fd, ret = -1;
+	char path[PATH_MAX];
+
+	snprintf(path, PATH_MAX, "%s/%s.scale", dir, name);
+
+	fd = open(path, O_RDONLY);
+	if (fd == -1)
+		return -1;
+
+	if (fstat(fd, &st) < 0)
+		goto error;
+
+	sret = read(fd, scale, sizeof(scale)-1);
+	if (sret < 0)
+		goto error;
+
+	if (scale[sret - 1] == '\n')
+		scale[sret - 1] = '\0';
+	else
+		scale[sret] = '\0';
 
-	ret = 0;
+	ret = convert_scale(scale, NULL, &alias->scale);
 error:
 	close(fd);
 	return ret;
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 6a6f44dd594b..2c1bca240597 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -3023,20 +3023,17 @@ static int try_to_find_absolute_address(struct perf_probe_event *pev,
 
 	tev->nargs = pev->nargs;
 	tev->args = zalloc(sizeof(struct probe_trace_arg) * tev->nargs);
-	if (!tev->args) {
-		err = -ENOMEM;
+	if (!tev->args)
 		goto errout;
-	}
+
 	for (i = 0; i < tev->nargs; i++)
 		copy_to_probe_trace_arg(&tev->args[i], &pev->args[i]);
 
 	return 1;
 
 errout:
-	if (*tevs) {
-		clear_probe_trace_events(*tevs, 1);
-		*tevs = NULL;
-	}
+	clear_probe_trace_events(*tevs, 1);
+	*tevs = NULL;
 	return err;
 }
 
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index e74adfbd6a2e..ecabc26ad1ee 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -351,8 +351,10 @@ static void perl_process_tracepoint(struct perf_sample *sample,
 	if (evsel->attr.type != PERF_TYPE_TRACEPOINT)
 		return;
 
-	if (!event)
-		die("ug! no event found for type %" PRIu64, (u64)evsel->attr.config);
+	if (!event) {
+		pr_debug("ug! no event found for type %" PRIu64, (u64)evsel->attr.config);
+		return;
+	}
 
 	pid = raw_field_value(event, "common_pid", data);
 
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index f268201048a0..349c68144e55 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1191,7 +1191,7 @@ static int
 	u64 sample_type = evsel->attr.sample_type;
 	u64 read_format = evsel->attr.read_format;
 
-	/* Standard sample delievery. */
+	/* Standard sample delivery. */
 	if (!(sample_type & PERF_SAMPLE_READ))
 		return tool->sample(tool, event, sample, evsel, machine);
 
diff --git a/tools/perf/util/trace-event-info.c b/tools/perf/util/trace-event-info.c
index d995743cb673..ceb0e2720223 100644
--- a/tools/perf/util/trace-event-info.c
+++ b/tools/perf/util/trace-event-info.c
@@ -42,7 +42,7 @@
 #include "evsel.h"
 #include "debug.h"
 
-#define VERSION "0.5"
+#define VERSION "0.6"
 
 static int output_fd;
 
@@ -379,6 +379,34 @@ out:
 	return err;
 }
 
+static int record_saved_cmdline(void)
+{
+	unsigned int size;
+	char *path;
+	struct stat st;
+	int ret, err = 0;
+
+	path = get_tracing_file("saved_cmdlines");
+	if (!path) {
+		pr_debug("can't get tracing/saved_cmdline");
+		return -ENOMEM;
+	}
+
+	ret = stat(path, &st);
+	if (ret < 0) {
+		/* not found */
+		size = 0;
+		if (write(output_fd, &size, 8) != 8)
+			err = -EIO;
+		goto out;
+	}
+	err = record_file(path, 8);
+
+out:
+	put_tracing_file(path);
+	return err;
+}
+
 static void
 put_tracepoints_path(struct tracepoint_path *tps)
 {
@@ -539,6 +567,9 @@ struct tracing_data *tracing_data_get(struct list_head *pattrs,
 	if (err)
 		goto out;
 	err = record_ftrace_printk();
+	if (err)
+		goto out;
+	err = record_saved_cmdline();
 
 out:
 	/*
diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c
index 33b52eaa39db..de0078e21408 100644
--- a/tools/perf/util/trace-event-parse.c
+++ b/tools/perf/util/trace-event-parse.c
@@ -160,6 +160,23 @@ void parse_ftrace_printk(struct pevent *pevent,
 	}
 }
 
+void parse_saved_cmdline(struct pevent *pevent,
+			 char *file, unsigned int size __maybe_unused)
+{
+	char *comm;
+	char *line;
+	char *next = NULL;
+	int pid;
+
+	line = strtok_r(file, "\n", &next);
+	while (line) {
+		sscanf(line, "%d %ms", &pid, &comm);
+		pevent_register_comm(pevent, comm, pid);
+		free(comm);
+		line = strtok_r(NULL, "\n", &next);
+	}
+}
+
 int parse_ftrace_file(struct pevent *pevent, char *buf, unsigned long size)
 {
 	return pevent_parse_event(pevent, buf, size, "ftrace");
diff --git a/tools/perf/util/trace-event-read.c b/tools/perf/util/trace-event-read.c
index b67a0ccf5ab9..27420159bf69 100644
--- a/tools/perf/util/trace-event-read.c
+++ b/tools/perf/util/trace-event-read.c
@@ -260,39 +260,53 @@ static int read_header_files(struct pevent *pevent)
 
 static int read_ftrace_file(struct pevent *pevent, unsigned long long size)
 {
+	int ret;
 	char *buf;
 
 	buf = malloc(size);
-	if (buf == NULL)
+	if (buf == NULL) {
+		pr_debug("memory allocation failure\n");
 		return -1;
+	}
 
-	if (do_read(buf, size) < 0) {
-		free(buf);
-		return -1;
+	ret = do_read(buf, size);
+	if (ret < 0) {
+		pr_debug("error reading ftrace file.\n");
+		goto out;
 	}
 
-	parse_ftrace_file(pevent, buf, size);
+	ret = parse_ftrace_file(pevent, buf, size);
+	if (ret < 0)
+		pr_debug("error parsing ftrace file.\n");
+out:
 	free(buf);
-	return 0;
+	return ret;
 }
 
 static int read_event_file(struct pevent *pevent, char *sys,
 			    unsigned long long size)
 {
+	int ret;
 	char *buf;
 
 	buf = malloc(size);
-	if (buf == NULL)
+	if (buf == NULL) {
+		pr_debug("memory allocation failure\n");
 		return -1;
+	}
 
-	if (do_read(buf, size) < 0) {
+	ret = do_read(buf, size);
+	if (ret < 0) {
 		free(buf);
-		return -1;
+		goto out;
 	}
 
-	parse_event_file(pevent, buf, size, sys);
+	ret = parse_event_file(pevent, buf, size, sys);
+	if (ret < 0)
+		pr_debug("error parsing event file.\n");
+out:
 	free(buf);
-	return 0;
+	return ret;
 }
 
 static int read_ftrace_files(struct pevent *pevent)
@@ -341,6 +355,36 @@ static int read_event_files(struct pevent *pevent)
 	return 0;
 }
 
+static int read_saved_cmdline(struct pevent *pevent)
+{
+	unsigned long long size;
+	char *buf;
+	int ret;
+
+	/* it can have 0 size */
+	size = read8(pevent);
+	if (!size)
+		return 0;
+
+	buf = malloc(size + 1);
+	if (buf == NULL) {
+		pr_debug("memory allocation failure\n");
+		return -1;
+	}
+
+	ret = do_read(buf, size);
+	if (ret < 0) {
+		pr_debug("error reading saved cmdlines\n");
+		goto out;
+	}
+
+	parse_saved_cmdline(pevent, buf, size);
+	ret = 0;
+out:
+	free(buf);
+	return ret;
+}
+
 ssize_t trace_report(int fd, struct trace_event *tevent, bool __repipe)
 {
 	char buf[BUFSIZ];
@@ -379,10 +423,11 @@ ssize_t trace_report(int fd, struct trace_event *tevent, bool __repipe)
 		return -1;
 	if (show_version)
 		printf("version = %s\n", version);
-	free(version);
 
-	if (do_read(buf, 1) < 0)
+	if (do_read(buf, 1) < 0) {
+		free(version);
 		return -1;
+	}
 	file_bigendian = buf[0];
 	host_bigendian = bigendian();
 
@@ -423,6 +468,11 @@ ssize_t trace_report(int fd, struct trace_event *tevent, bool __repipe)
 	err = read_ftrace_printk(pevent);
 	if (err)
 		goto out;
+	if (atof(version) >= 0.6) {
+		err = read_saved_cmdline(pevent);
+		if (err)
+			goto out;
+	}
 
 	size = trace_data_size;
 	repipe = false;
@@ -438,5 +488,6 @@ ssize_t trace_report(int fd, struct trace_event *tevent, bool __repipe)
 out:
 	if (pevent)
 		trace_event__cleanup(tevent);
+	free(version);
 	return size;
 }
diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h
index b0af9c81bb0d..1fbc044f9eb0 100644
--- a/tools/perf/util/trace-event.h
+++ b/tools/perf/util/trace-event.h
@@ -42,6 +42,7 @@ raw_field_value(struct event_format *event, const char *name, void *data);
 
 void parse_proc_kallsyms(struct pevent *pevent, char *file, unsigned int size);
 void parse_ftrace_printk(struct pevent *pevent, char *file, unsigned int size);
+void parse_saved_cmdline(struct pevent *pevent, char *file, unsigned int size);
 
 ssize_t trace_report(int fd, struct trace_event *tevent, bool repipe);
 
diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c
index 6fec84dff3f7..bfb9b7987692 100644
--- a/tools/perf/util/unwind-libunwind-local.c
+++ b/tools/perf/util/unwind-libunwind-local.c
@@ -35,6 +35,7 @@
 #include "util.h"
 #include "debug.h"
 #include "asm/bug.h"
+#include "dso.h"
 
 extern int
 UNW_OBJ(dwarf_search_unwind_table) (unw_addr_space_t as,
@@ -297,15 +298,58 @@ static int read_unwind_spec_debug_frame(struct dso *dso,
 	int fd;
 	u64 ofs = dso->data.debug_frame_offset;
 
+	/* debug_frame can reside in:
+	 *  - dso
+	 *  - debug pointed by symsrc_filename
+	 *  - gnu_debuglink, which doesn't necessary
+	 *    has to be pointed by symsrc_filename
+	 */
 	if (ofs == 0) {
 		fd = dso__data_get_fd(dso, machine);
-		if (fd < 0)
-			return -EINVAL;
+		if (fd >= 0) {
+			ofs = elf_section_offset(fd, ".debug_frame");
+			dso__data_put_fd(dso);
+		}
+
+		if (ofs <= 0) {
+			fd = open(dso->symsrc_filename, O_RDONLY);
+			if (fd >= 0) {
+				ofs = elf_section_offset(fd, ".debug_frame");
+				close(fd);
+			}
+		}
+
+		if (ofs <= 0) {
+			char *debuglink = malloc(PATH_MAX);
+			int ret = 0;
+
+			ret = dso__read_binary_type_filename(
+				dso, DSO_BINARY_TYPE__DEBUGLINK,
+				machine->root_dir, debuglink, PATH_MAX);
+			if (!ret) {
+				fd = open(debuglink, O_RDONLY);
+				if (fd >= 0) {
+					ofs = elf_section_offset(fd,
+							".debug_frame");
+					close(fd);
+				}
+			}
+			if (ofs > 0) {
+				if (dso->symsrc_filename != NULL) {
+					pr_warning(
+						"%s: overwrite symsrc(%s,%s)\n",
+							__func__,
+							dso->symsrc_filename,
+							debuglink);
+					free(dso->symsrc_filename);
+				}
+				dso->symsrc_filename = debuglink;
+			} else {
+				free(debuglink);
+			}
+		}
 
-		/* Check the .debug_frame section for unwinding info */
-		ofs = elf_section_offset(fd, ".debug_frame");
 		dso->data.debug_frame_offset = ofs;
-		dso__data_put_fd(dso);
 	}
 
 	*offset = ofs;
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 9ddd98827d12..bf29aed16bd6 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -789,3 +789,16 @@ int is_printable_array(char *p, unsigned int len)
 	}
 	return 1;
 }
+
+int unit_number__scnprintf(char *buf, size_t size, u64 n)
+{
+	char unit[4] = "BKMG";
+	int i = 0;
+
+	while (((n / 1024) > 1) && (i < 3)) {
+		n /= 1024;
+		i++;
+	}
+
+	return scnprintf(buf, size, "%" PRIu64 "%c", n, unit[i]);
+}
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 1d639e38aa82..6e8be174ec0b 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -363,4 +363,5 @@ int is_printable_array(char *p, unsigned int len);
 
 int timestamp__scnprintf_usec(u64 timestamp, char *buf, size_t sz);
 
+int unit_number__scnprintf(char *buf, size_t size, u64 n);
 #endif /* GIT_COMPAT_UTIL_H */
diff --git a/tools/testing/selftests/locking/ww_mutex.sh b/tools/testing/selftests/locking/ww_mutex.sh
new file mode 100644
index 000000000000..6905da965f3b
--- /dev/null
+++ b/tools/testing/selftests/locking/ww_mutex.sh
@@ -0,0 +1,10 @@
+#!/bin/sh
+# Runs API tests for struct ww_mutex (Wait/Wound mutexes)
+
+if /sbin/modprobe -q test-ww_mutex; then
+       /sbin/modprobe -q -r test-ww_mutex
+       echo "locking/ww_mutex: ok"
+else
+       echo "locking/ww_mutex: [FAIL]"
+       exit 1
+fi
diff --git a/tools/testing/selftests/rcutorture/configs/lock/CFLIST b/tools/testing/selftests/rcutorture/configs/lock/CFLIST
index b9611c523723..41bae5824339 100644
--- a/tools/testing/selftests/rcutorture/configs/lock/CFLIST
+++ b/tools/testing/selftests/rcutorture/configs/lock/CFLIST
@@ -4,3 +4,4 @@ LOCK03
 LOCK04
 LOCK05
 LOCK06
+LOCK07
diff --git a/tools/testing/selftests/rcutorture/configs/lock/LOCK07 b/tools/testing/selftests/rcutorture/configs/lock/LOCK07
new file mode 100644
index 000000000000..1d1da1477fc3
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/lock/LOCK07
@@ -0,0 +1,6 @@
+CONFIG_SMP=y
+CONFIG_NR_CPUS=4
+CONFIG_HOTPLUG_CPU=y
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
diff --git a/tools/testing/selftests/rcutorture/configs/lock/LOCK07.boot b/tools/testing/selftests/rcutorture/configs/lock/LOCK07.boot
new file mode 100644
index 000000000000..97dadd1a9e45
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/lock/LOCK07.boot
@@ -0,0 +1 @@
+locktorture.torture_type=ww_mutex_lock
diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile
index 8c1cb423cfe6..25d4067c11e4 100644
--- a/tools/testing/selftests/x86/Makefile
+++ b/tools/testing/selftests/x86/Makefile
@@ -10,7 +10,7 @@ TARGETS_C_BOTHBITS := single_step_syscall sysret_ss_attrs syscall_nt ptrace_sysc
 TARGETS_C_32BIT_ONLY := entry_from_vm86 syscall_arg_fault test_syscall_vdso unwind_vdso \
 			test_FCMOV test_FCOMI test_FISTTP \
 			vdso_restorer
-TARGETS_C_64BIT_ONLY := fsgsbase
+TARGETS_C_64BIT_ONLY := fsgsbase sysret_rip
 
 TARGETS_C_32BIT_ALL := $(TARGETS_C_BOTHBITS) $(TARGETS_C_32BIT_ONLY)
 TARGETS_C_64BIT_ALL := $(TARGETS_C_BOTHBITS) $(TARGETS_C_64BIT_ONLY)
diff --git a/tools/testing/selftests/x86/sysret_rip.c b/tools/testing/selftests/x86/sysret_rip.c
new file mode 100644
index 000000000000..d85ec5b3671c
--- /dev/null
+++ b/tools/testing/selftests/x86/sysret_rip.c
@@ -0,0 +1,195 @@
+/*
+ * sigreturn.c - tests that x86 avoids Intel SYSRET pitfalls
+ * Copyright (c) 2014-2016 Andrew Lutomirski
+ *
+ * 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.
+ */
+
+#define _GNU_SOURCE
+
+#include <stdlib.h>
+#include <unistd.h>
+#include <stdio.h>
+#include <string.h>
+#include <inttypes.h>
+#include <sys/signal.h>
+#include <sys/ucontext.h>
+#include <sys/syscall.h>
+#include <err.h>
+#include <stddef.h>
+#include <stdbool.h>
+#include <setjmp.h>
+#include <sys/user.h>
+#include <sys/mman.h>
+#include <assert.h>
+
+
+asm (
+	".pushsection \".text\", \"ax\"\n\t"
+	".balign 4096\n\t"
+	"test_page: .globl test_page\n\t"
+	".fill 4094,1,0xcc\n\t"
+	"test_syscall_insn:\n\t"
+	"syscall\n\t"
+	".ifne . - test_page - 4096\n\t"
+	".error \"test page is not one page long\"\n\t"
+	".endif\n\t"
+	".popsection"
+    );
+
+extern const char test_page[];
+static void const *current_test_page_addr = test_page;
+
+static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *),
+		       int flags)
+{
+	struct sigaction sa;
+	memset(&sa, 0, sizeof(sa));
+	sa.sa_sigaction = handler;
+	sa.sa_flags = SA_SIGINFO | flags;
+	sigemptyset(&sa.sa_mask);
+	if (sigaction(sig, &sa, 0))
+		err(1, "sigaction");
+}
+
+static void clearhandler(int sig)
+{
+	struct sigaction sa;
+	memset(&sa, 0, sizeof(sa));
+	sa.sa_handler = SIG_DFL;
+	sigemptyset(&sa.sa_mask);
+	if (sigaction(sig, &sa, 0))
+		err(1, "sigaction");
+}
+
+/* State used by our signal handlers. */
+static gregset_t initial_regs;
+
+static volatile unsigned long rip;
+
+static void sigsegv_for_sigreturn_test(int sig, siginfo_t *info, void *ctx_void)
+{
+	ucontext_t *ctx = (ucontext_t*)ctx_void;
+
+	if (rip != ctx->uc_mcontext.gregs[REG_RIP]) {
+		printf("[FAIL]\tRequested RIP=0x%lx but got RIP=0x%lx\n",
+		       rip, (unsigned long)ctx->uc_mcontext.gregs[REG_RIP]);
+		fflush(stdout);
+		_exit(1);
+	}
+
+	memcpy(&ctx->uc_mcontext.gregs, &initial_regs, sizeof(gregset_t));
+
+	printf("[OK]\tGot SIGSEGV at RIP=0x%lx\n", rip);
+}
+
+static void sigusr1(int sig, siginfo_t *info, void *ctx_void)
+{
+	ucontext_t *ctx = (ucontext_t*)ctx_void;
+
+	memcpy(&initial_regs, &ctx->uc_mcontext.gregs, sizeof(gregset_t));
+
+	/* Set IP and CX to match so that SYSRET can happen. */
+	ctx->uc_mcontext.gregs[REG_RIP] = rip;
+	ctx->uc_mcontext.gregs[REG_RCX] = rip;
+
+	/* R11 and EFLAGS should already match. */
+	assert(ctx->uc_mcontext.gregs[REG_EFL] ==
+	       ctx->uc_mcontext.gregs[REG_R11]);
+
+	sethandler(SIGSEGV, sigsegv_for_sigreturn_test, SA_RESETHAND);
+
+	return;
+}
+
+static void test_sigreturn_to(unsigned long ip)
+{
+	rip = ip;
+	printf("[RUN]\tsigreturn to 0x%lx\n", ip);
+	raise(SIGUSR1);
+}
+
+static jmp_buf jmpbuf;
+
+static void sigsegv_for_fallthrough(int sig, siginfo_t *info, void *ctx_void)
+{
+	ucontext_t *ctx = (ucontext_t*)ctx_void;
+
+	if (rip != ctx->uc_mcontext.gregs[REG_RIP]) {
+		printf("[FAIL]\tExpected SIGSEGV at 0x%lx but got RIP=0x%lx\n",
+		       rip, (unsigned long)ctx->uc_mcontext.gregs[REG_RIP]);
+		fflush(stdout);
+		_exit(1);
+	}
+
+	siglongjmp(jmpbuf, 1);
+}
+
+static void test_syscall_fallthrough_to(unsigned long ip)
+{
+	void *new_address = (void *)(ip - 4096);
+	void *ret;
+
+	printf("[RUN]\tTrying a SYSCALL that falls through to 0x%lx\n", ip);
+
+	ret = mremap((void *)current_test_page_addr, 4096, 4096,
+		     MREMAP_MAYMOVE | MREMAP_FIXED, new_address);
+	if (ret == MAP_FAILED) {
+		if (ip <= (1UL << 47) - PAGE_SIZE) {
+			err(1, "mremap to %p", new_address);
+		} else {
+			printf("[OK]\tmremap to %p failed\n", new_address);
+			return;
+		}
+	}
+
+	if (ret != new_address)
+		errx(1, "mremap malfunctioned: asked for %p but got %p\n",
+		     new_address, ret);
+
+	current_test_page_addr = new_address;
+	rip = ip;
+
+	if (sigsetjmp(jmpbuf, 1) == 0) {
+		asm volatile ("call *%[syscall_insn]" :: "a" (SYS_getpid),
+			      [syscall_insn] "rm" (ip - 2));
+		errx(1, "[FAIL]\tSyscall trampoline returned");
+	}
+
+	printf("[OK]\tWe survived\n");
+}
+
+int main()
+{
+	/*
+	 * When the kernel returns from a slow-path syscall, it will
+	 * detect whether SYSRET is appropriate.  If it incorrectly
+	 * thinks that SYSRET is appropriate when RIP is noncanonical,
+	 * it'll crash on Intel CPUs.
+	 */
+	sethandler(SIGUSR1, sigusr1, 0);
+	for (int i = 47; i < 64; i++)
+		test_sigreturn_to(1UL<<i);
+
+	clearhandler(SIGUSR1);
+
+	sethandler(SIGSEGV, sigsegv_for_fallthrough, 0);
+
+	/* One extra test to check that we didn't screw up the mremap logic. */
+	test_syscall_fallthrough_to((1UL << 47) - 2*PAGE_SIZE);
+
+	/* These are the interesting cases. */
+	for (int i = 47; i < 64; i++) {
+		test_syscall_fallthrough_to((1UL<<i) - PAGE_SIZE);
+		test_syscall_fallthrough_to(1UL<<i);
+	}
+
+	return 0;
+}