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

167 files changed, 5520 insertions, 1021 deletions

diff --git a/tools/perf/.gitignore b/tools/perf/.gitignore
index 3db3db9278be..643cc4ba6872 100644
--- a/tools/perf/.gitignore
+++ b/tools/perf/.gitignore
@@ -31,3 +31,5 @@ config.mak.autogen
 .config-detected
 util/intel-pt-decoder/inat-tables.c
 arch/*/include/generated/
+pmu-events/pmu-events.c
+pmu-events/jevents
diff --git a/tools/perf/Build b/tools/perf/Build
index 9b79f8d7db50..bd8eeb60533c 100644
--- a/tools/perf/Build
+++ b/tools/perf/Build
@@ -50,5 +50,6 @@ libperf-y += util/
 libperf-y += arch/
 libperf-y += ui/
 libperf-y += scripts/
+libperf-y += trace/beauty/
 
 gtk-y += ui/gtk/
diff --git a/tools/perf/Documentation/perf-ftrace.txt b/tools/perf/Documentation/perf-ftrace.txt
index 2d96de6132a9..6e6a8b22c859 100644
--- a/tools/perf/Documentation/perf-ftrace.txt
+++ b/tools/perf/Documentation/perf-ftrace.txt
@@ -30,6 +30,24 @@ OPTIONS
 --verbose=::
         Verbosity level.
 
+-p::
+--pid=::
+	Trace on existing process id (comma separated list).
+
+-a::
+--all-cpus::
+	Force system-wide collection.  Scripts run without a <command>
+	normally use -a by default, while scripts run with a <command>
+	normally don't - this option allows the latter to be run in
+	system-wide mode.
+
+-C::
+--cpu=::
+	Only trace for the list of CPUs provided.  Multiple CPUs can
+	be provided as a comma separated list with no space like: 0,1.
+	Ranges of CPUs are specified with -: 0-2.
+	Default is to trace on all online CPUs.
+
 
 SEE ALSO
 --------
diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt
index 41857cce5e86..f709de54707b 100644
--- a/tools/perf/Documentation/perf-list.txt
+++ b/tools/perf/Documentation/perf-list.txt
@@ -8,7 +8,7 @@ perf-list - List all symbolic event types
 SYNOPSIS
 --------
 [verse]
-'perf list' [--no-desc] [--long-desc] [hw|sw|cache|tracepoint|pmu|event_glob]
+'perf list' [--no-desc] [--long-desc] [hw|sw|cache|tracepoint|pmu|sdt|event_glob]
 
 DESCRIPTION
 -----------
@@ -24,6 +24,10 @@ Don't print descriptions.
 --long-desc::
 Print longer event descriptions.
 
+--details::
+Print how named events are resolved internally into perf events, and also
+any extra expressions computed by perf stat.
+
 
 [[EVENT_MODIFIERS]]
 EVENT MODIFIERS
@@ -240,6 +244,8 @@ To limit the list use:
 
 . 'pmu' to print the kernel supplied PMU events.
 
+. 'sdt' to list all Statically Defined Tracepoint events.
+
 . If none of the above is matched, it will apply the supplied glob to all
   events, printing the ones that match.
 
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index b16003ec14a7..ea3789d05e5e 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -347,6 +347,9 @@ Enable weightened sampling. An additional weight is recorded per sample and can
 displayed with the weight and local_weight sort keys.  This currently works for TSX
 abort events and some memory events in precise mode on modern Intel CPUs.
 
+--namespaces::
+Record events of type PERF_RECORD_NAMESPACES.
+
 --transaction::
 Record transaction flags for transaction related events.
 
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index c04cc0647c16..37a175914157 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -72,7 +72,8 @@ OPTIONS
 --sort=::
 	Sort histogram entries by given key(s) - multiple keys can be specified
 	in CSV format.  Following sort keys are available:
-	pid, comm, dso, symbol, parent, cpu, socket, srcline, weight, local_weight.
+	pid, comm, dso, symbol, parent, cpu, socket, srcline, weight,
+	local_weight, cgroup_id.
 
 	Each key has following meaning:
 
@@ -80,6 +81,7 @@ OPTIONS
 	- pid: command and tid of the task
 	- dso: name of library or module executed at the time of sample
 	- symbol: name of function executed at the time of sample
+	- symbol_size: size of function executed at the time of sample
 	- parent: name of function matched to the parent regex filter. Unmatched
 	entries are displayed as "[other]".
 	- cpu: cpu number the task ran at the time of sample
@@ -91,6 +93,7 @@ OPTIONS
 	- weight: Event specific weight, e.g. memory latency or transaction
 	abort cost. This is the global weight.
 	- local_weight: Local weight version of the weight above.
+	- cgroup_id: ID derived from cgroup namespace device and inode numbers.
 	- transaction: Transaction abort flags.
 	- overhead: Overhead percentage of sample
 	- overhead_sys: Overhead percentage of sample running in system mode
@@ -172,6 +175,9 @@ OPTIONS
 	By default, every sort keys not specified in -F will be appended
 	automatically.
 
+	If the keys starts with a prefix '+', then it will append the specified
+        field(s) to the default field order. For example: perf report -F +period,sample.
+
 -p::
 --parent=<regex>::
         A regex filter to identify parent. The parent is a caller of this
@@ -229,6 +235,7 @@ OPTIONS
 	sort_key can be:
 	- function: compare on functions (default)
 	- address: compare on individual code addresses
+	- srcline: compare on source filename and line number
 
 	branch can be:
 	- branch: include last branch information in callgraph when available.
@@ -424,6 +431,10 @@ include::itrace.txt[]
 --hierarchy::
 	Enable hierarchical output.
 
+--inline::
+	If a callgraph address belongs to an inlined function, the inline stack
+	will be printed. Each entry is function name or file/line.
+
 include::callchain-overhead-calculation.txt[]
 
 SEE ALSO
diff --git a/tools/perf/Documentation/perf-sched.txt b/tools/perf/Documentation/perf-sched.txt
index d33deddb0146..a092a2499e8f 100644
--- a/tools/perf/Documentation/perf-sched.txt
+++ b/tools/perf/Documentation/perf-sched.txt
@@ -132,6 +132,10 @@ OPTIONS for 'perf sched timehist'
 --migrations::
 	Show migration events.
 
+-n::
+--next::
+	Show next task.
+
 -I::
 --idle-hist::
 	Show idle-related events only.
diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index 4ed5f239ba7d..cb0eda3925e6 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -116,7 +116,7 @@ OPTIONS
 --fields::
         Comma separated list of fields to print. Options are:
         comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff,
-        srcline, period, iregs, brstack, brstacksym, flags, bpf-output,
+        srcline, period, iregs, brstack, brstacksym, flags, bpf-output, brstackinsn,
         callindent, insn, insnlen. Field list can be prepended with the type, trace, sw or hw,
         to indicate to which event type the field list applies.
         e.g., -F sw:comm,tid,time,ip,sym  and -F trace:time,cpu,trace
@@ -189,15 +189,20 @@ OPTIONS
 	i.e., -F "" is not allowed.
 
 	The brstack output includes branch related information with raw addresses using the
-	/v/v/v/v/ syntax in the following order:
+	/v/v/v/v/cycles syntax in the following order:
 	FROM: branch source instruction
 	TO  : branch target instruction
         M/P/-: M=branch target mispredicted or branch direction was mispredicted, P=target predicted or direction predicted, -=not supported
 	X/- : X=branch inside a transactional region, -=not in transaction region or not supported
 	A/- : A=TSX abort entry, -=not aborted region or not supported
+	cycles
 
 	The brstacksym is identical to brstack, except that the FROM and TO addresses are printed in a symbolic form if possible.
 
+	When brstackinsn is specified the full assembler sequences of branch sequences for each sample
+	is printed. This is the full execution path leading to the sample. This is only supported when the
+	sample was recorded with perf record -b or -j any.
+
 -k::
 --vmlinux=<file>::
         vmlinux pathname
@@ -248,6 +253,9 @@ OPTIONS
 --show-mmap-events
 	Display mmap related events (e.g. MMAP, MMAP2).
 
+--show-namespace-events
+	Display namespace events i.e. events of type PERF_RECORD_NAMESPACES.
+
 --show-switch-events
 	Display context switch events i.e. events of type PERF_RECORD_SWITCH or
 	PERF_RECORD_SWITCH_CPU_WIDE.
@@ -299,6 +307,10 @@ include::itrace.txt[]
 	stop time is not given (i.e, time string is 'x.y,') then analysis goes
 	to end of file.
 
+--max-blocks::
+	Set the maximum number of program blocks to print with brstackasm for
+	each sample.
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-script-perl[1],
diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index aecf2a87e7d6..bd0e4417f2be 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -94,8 +94,7 @@ to activate system-wide monitoring. Default is to count on all CPUs.
 
 -A::
 --no-aggr::
-Do not aggregate counts across all monitored CPUs in system-wide mode (-a).
-This option is only valid in system-wide mode.
+Do not aggregate counts across all monitored CPUs.
 
 -n::
 --null::
@@ -237,6 +236,9 @@ To interpret the results it is usually needed to know on which
 CPUs the workload runs on. If needed the CPUs can be forced using
 taskset.
 
+--no-merge::
+Do not merge results from same PMUs.
+
 EXAMPLES
 --------
 
diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST
index 8672f835ae4e..89018c7311a4 100644
--- a/tools/perf/MANIFEST
+++ b/tools/perf/MANIFEST
@@ -12,6 +12,7 @@ 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/cmpxchg.h
 tools/arch/x86/include/asm/cpufeatures.h
 tools/arch/x86/include/asm/disabled-features.h
 tools/arch/x86/include/asm/required-features.h
@@ -72,12 +73,15 @@ tools/include/uapi/asm-generic/mman-common.h
 tools/include/uapi/asm-generic/mman.h
 tools/include/uapi/linux/bpf.h
 tools/include/uapi/linux/bpf_common.h
+tools/include/uapi/linux/fcntl.h
 tools/include/uapi/linux/hw_breakpoint.h
 tools/include/uapi/linux/mman.h
 tools/include/uapi/linux/perf_event.h
+tools/include/uapi/linux/stat.h
 tools/include/linux/poison.h
 tools/include/linux/rbtree.h
 tools/include/linux/rbtree_augmented.h
+tools/include/linux/refcount.h
 tools/include/linux/string.h
 tools/include/linux/stringify.h
 tools/include/linux/types.h
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index 27c9fbca7bd9..2b656de99495 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -317,6 +317,10 @@ ifdef NO_DWARF
   NO_LIBDW_DWARF_UNWIND := 1
 endif
 
+ifeq ($(feature-sched_getcpu), 1)
+  CFLAGS += -DHAVE_SCHED_GETCPU_SUPPORT
+endif
+
 ifndef NO_LIBELF
   CFLAGS += -DHAVE_LIBELF_SUPPORT
   EXTLIBS += -lelf
diff --git a/tools/perf/arch/powerpc/util/perf_regs.c b/tools/perf/arch/powerpc/util/perf_regs.c
index a3c3e1ce6807..4268f7762e25 100644
--- a/tools/perf/arch/powerpc/util/perf_regs.c
+++ b/tools/perf/arch/powerpc/util/perf_regs.c
@@ -1,5 +1,10 @@
+#include <string.h>
+#include <regex.h>
+
 #include "../../perf.h"
+#include "../../util/util.h"
 #include "../../util/perf_regs.h"
+#include "../../util/debug.h"
 
 const struct sample_reg sample_reg_masks[] = {
 	SMPL_REG(r0, PERF_REG_POWERPC_R0),
@@ -47,3 +52,109 @@ const struct sample_reg sample_reg_masks[] = {
 	SMPL_REG(dsisr, PERF_REG_POWERPC_DSISR),
 	SMPL_REG_END
 };
+
+/* REG or %rREG */
+#define SDT_OP_REGEX1  "^(%r)?([1-2]?[0-9]|3[0-1])$"
+
+/* -NUM(REG) or NUM(REG) or -NUM(%rREG) or NUM(%rREG) */
+#define SDT_OP_REGEX2  "^(\\-)?([0-9]+)\\((%r)?([1-2]?[0-9]|3[0-1])\\)$"
+
+static regex_t sdt_op_regex1, sdt_op_regex2;
+
+static int sdt_init_op_regex(void)
+{
+	static int initialized;
+	int ret = 0;
+
+	if (initialized)
+		return 0;
+
+	ret = regcomp(&sdt_op_regex1, SDT_OP_REGEX1, REG_EXTENDED);
+	if (ret)
+		goto error;
+
+	ret = regcomp(&sdt_op_regex2, SDT_OP_REGEX2, REG_EXTENDED);
+	if (ret)
+		goto free_regex1;
+
+	initialized = 1;
+	return 0;
+
+free_regex1:
+	regfree(&sdt_op_regex1);
+error:
+	pr_debug4("Regex compilation error.\n");
+	return ret;
+}
+
+/*
+ * Parse OP and convert it into uprobe format, which is, +/-NUM(%gprREG).
+ * Possible variants of OP are:
+ *	Format		Example
+ *	-------------------------
+ *	NUM(REG)	48(18)
+ *	-NUM(REG)	-48(18)
+ *	NUM(%rREG)	48(%r18)
+ *	-NUM(%rREG)	-48(%r18)
+ *	REG		18
+ *	%rREG		%r18
+ *	iNUM		i0
+ *	i-NUM		i-1
+ *
+ * SDT marker arguments on Powerpc uses %rREG form with -mregnames flag
+ * and REG form with -mno-regnames. Here REG is general purpose register,
+ * which is in 0 to 31 range.
+ */
+int arch_sdt_arg_parse_op(char *old_op, char **new_op)
+{
+	int ret, new_len;
+	regmatch_t rm[5];
+	char prefix;
+
+	/* Constant argument. Uprobe does not support it */
+	if (old_op[0] == 'i') {
+		pr_debug4("Skipping unsupported SDT argument: %s\n", old_op);
+		return SDT_ARG_SKIP;
+	}
+
+	ret = sdt_init_op_regex();
+	if (ret < 0)
+		return ret;
+
+	if (!regexec(&sdt_op_regex1, old_op, 3, rm, 0)) {
+		/* REG or %rREG --> %gprREG */
+
+		new_len = 5;	/* % g p r NULL */
+		new_len += (int)(rm[2].rm_eo - rm[2].rm_so);
+
+		*new_op = zalloc(new_len);
+		if (!*new_op)
+			return -ENOMEM;
+
+		scnprintf(*new_op, new_len, "%%gpr%.*s",
+			(int)(rm[2].rm_eo - rm[2].rm_so), old_op + rm[2].rm_so);
+	} else if (!regexec(&sdt_op_regex2, old_op, 5, rm, 0)) {
+		/*
+		 * -NUM(REG) or NUM(REG) or -NUM(%rREG) or NUM(%rREG) -->
+		 *	+/-NUM(%gprREG)
+		 */
+		prefix = (rm[1].rm_so == -1) ? '+' : '-';
+
+		new_len = 8;	/* +/- ( % g p r ) NULL */
+		new_len += (int)(rm[2].rm_eo - rm[2].rm_so);
+		new_len += (int)(rm[4].rm_eo - rm[4].rm_so);
+
+		*new_op = zalloc(new_len);
+		if (!*new_op)
+			return -ENOMEM;
+
+		scnprintf(*new_op, new_len, "%c%.*s(%%gpr%.*s)", prefix,
+			(int)(rm[2].rm_eo - rm[2].rm_so), old_op + rm[2].rm_so,
+			(int)(rm[4].rm_eo - rm[4].rm_so), old_op + rm[4].rm_so);
+	} else {
+		pr_debug4("Skipping unsupported SDT argument: %s\n", old_op);
+		return SDT_ARG_SKIP;
+	}
+
+	return SDT_ARG_VALID;
+}
diff --git a/tools/perf/arch/powerpc/util/sym-handling.c b/tools/perf/arch/powerpc/util/sym-handling.c
index 1030a6e504bb..39dbe512b9fc 100644
--- a/tools/perf/arch/powerpc/util/sym-handling.c
+++ b/tools/perf/arch/powerpc/util/sym-handling.c
@@ -10,6 +10,7 @@
 #include "symbol.h"
 #include "map.h"
 #include "probe-event.h"
+#include "probe-file.h"
 
 #ifdef HAVE_LIBELF_SUPPORT
 bool elf__needs_adjust_symbols(GElf_Ehdr ehdr)
@@ -79,13 +80,18 @@ void arch__fix_tev_from_maps(struct perf_probe_event *pev,
 	 * However, if the user specifies an offset, we fall back to using the
 	 * GEP since all userspace applications (objdump/readelf) show function
 	 * disassembly with offsets from the GEP.
-	 *
-	 * In addition, we shouldn't specify an offset for kretprobes.
 	 */
-	if (pev->point.offset || (!pev->uprobes && pev->point.retprobe) ||
-	    !map || !sym)
+	if (pev->point.offset || !map || !sym)
 		return;
 
+	/* For kretprobes, add an offset only if the kernel supports it */
+	if (!pev->uprobes && pev->point.retprobe) {
+#ifdef HAVE_LIBELF_SUPPORT
+		if (!kretprobe_offset_is_supported())
+#endif
+			return;
+	}
+
 	lep_offset = PPC64_LOCAL_ENTRY_OFFSET(sym->arch_sym);
 
 	if (map->dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS)
diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
index e93ef0b38db8..5aef183e2f85 100644
--- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
@@ -338,6 +338,7 @@
 329	common	pkey_mprotect		sys_pkey_mprotect
 330	common	pkey_alloc		sys_pkey_alloc
 331	common	pkey_free		sys_pkey_free
+332	common	statx			sys_statx
 
 #
 # x32-specific system call numbers start at 512 to avoid cache impact
diff --git a/tools/perf/arch/x86/util/perf_regs.c b/tools/perf/arch/x86/util/perf_regs.c
index c5db14f36cc7..3bf3548c5e2d 100644
--- a/tools/perf/arch/x86/util/perf_regs.c
+++ b/tools/perf/arch/x86/util/perf_regs.c
@@ -1,5 +1,10 @@
+#include <string.h>
+#include <regex.h>
+
 #include "../../perf.h"
+#include "../../util/util.h"
 #include "../../util/perf_regs.h"
+#include "../../util/debug.h"
 
 const struct sample_reg sample_reg_masks[] = {
 	SMPL_REG(AX, PERF_REG_X86_AX),
@@ -26,3 +31,224 @@ const struct sample_reg sample_reg_masks[] = {
 #endif
 	SMPL_REG_END
 };
+
+struct sdt_name_reg {
+	const char *sdt_name;
+	const char *uprobe_name;
+};
+#define SDT_NAME_REG(n, m) {.sdt_name = "%" #n, .uprobe_name = "%" #m}
+#define SDT_NAME_REG_END {.sdt_name = NULL, .uprobe_name = NULL}
+
+static const struct sdt_name_reg sdt_reg_tbl[] = {
+	SDT_NAME_REG(eax, ax),
+	SDT_NAME_REG(rax, ax),
+	SDT_NAME_REG(al,  ax),
+	SDT_NAME_REG(ah,  ax),
+	SDT_NAME_REG(ebx, bx),
+	SDT_NAME_REG(rbx, bx),
+	SDT_NAME_REG(bl,  bx),
+	SDT_NAME_REG(bh,  bx),
+	SDT_NAME_REG(ecx, cx),
+	SDT_NAME_REG(rcx, cx),
+	SDT_NAME_REG(cl,  cx),
+	SDT_NAME_REG(ch,  cx),
+	SDT_NAME_REG(edx, dx),
+	SDT_NAME_REG(rdx, dx),
+	SDT_NAME_REG(dl,  dx),
+	SDT_NAME_REG(dh,  dx),
+	SDT_NAME_REG(esi, si),
+	SDT_NAME_REG(rsi, si),
+	SDT_NAME_REG(sil, si),
+	SDT_NAME_REG(edi, di),
+	SDT_NAME_REG(rdi, di),
+	SDT_NAME_REG(dil, di),
+	SDT_NAME_REG(ebp, bp),
+	SDT_NAME_REG(rbp, bp),
+	SDT_NAME_REG(bpl, bp),
+	SDT_NAME_REG(rsp, sp),
+	SDT_NAME_REG(esp, sp),
+	SDT_NAME_REG(spl, sp),
+
+	/* rNN registers */
+	SDT_NAME_REG(r8b,  r8),
+	SDT_NAME_REG(r8w,  r8),
+	SDT_NAME_REG(r8d,  r8),
+	SDT_NAME_REG(r9b,  r9),
+	SDT_NAME_REG(r9w,  r9),
+	SDT_NAME_REG(r9d,  r9),
+	SDT_NAME_REG(r10b, r10),
+	SDT_NAME_REG(r10w, r10),
+	SDT_NAME_REG(r10d, r10),
+	SDT_NAME_REG(r11b, r11),
+	SDT_NAME_REG(r11w, r11),
+	SDT_NAME_REG(r11d, r11),
+	SDT_NAME_REG(r12b, r12),
+	SDT_NAME_REG(r12w, r12),
+	SDT_NAME_REG(r12d, r12),
+	SDT_NAME_REG(r13b, r13),
+	SDT_NAME_REG(r13w, r13),
+	SDT_NAME_REG(r13d, r13),
+	SDT_NAME_REG(r14b, r14),
+	SDT_NAME_REG(r14w, r14),
+	SDT_NAME_REG(r14d, r14),
+	SDT_NAME_REG(r15b, r15),
+	SDT_NAME_REG(r15w, r15),
+	SDT_NAME_REG(r15d, r15),
+	SDT_NAME_REG_END,
+};
+
+/*
+ * Perf only supports OP which is in  +/-NUM(REG)  form.
+ * Here plus-minus sign, NUM and parenthesis are optional,
+ * only REG is mandatory.
+ *
+ * SDT events also supports indirect addressing mode with a
+ * symbol as offset, scaled mode and constants in OP. But
+ * perf does not support them yet. Below are few examples.
+ *
+ * OP with scaled mode:
+ *     (%rax,%rsi,8)
+ *     10(%ras,%rsi,8)
+ *
+ * OP with indirect addressing mode:
+ *     check_action(%rip)
+ *     mp_+52(%rip)
+ *     44+mp_(%rip)
+ *
+ * OP with constant values:
+ *     $0
+ *     $123
+ *     $-1
+ */
+#define SDT_OP_REGEX  "^([+\\-]?)([0-9]*)(\\(?)(%[a-z][a-z0-9]+)(\\)?)$"
+
+static regex_t sdt_op_regex;
+
+static int sdt_init_op_regex(void)
+{
+	static int initialized;
+	int ret = 0;
+
+	if (initialized)
+		return 0;
+
+	ret = regcomp(&sdt_op_regex, SDT_OP_REGEX, REG_EXTENDED);
+	if (ret < 0) {
+		pr_debug4("Regex compilation error.\n");
+		return ret;
+	}
+
+	initialized = 1;
+	return 0;
+}
+
+/*
+ * Max x86 register name length is 5(ex: %r15d). So, 6th char
+ * should always contain NULL. This helps to find register name
+ * length using strlen, insted of maintaing one more variable.
+ */
+#define SDT_REG_NAME_SIZE  6
+
+/*
+ * The uprobe parser does not support all gas register names;
+ * so, we have to replace them (ex. for x86_64: %rax -> %ax).
+ * Note: If register does not require renaming, just copy
+ * paste as it is, but don't leave it empty.
+ */
+static void sdt_rename_register(char *sdt_reg, int sdt_len, char *uprobe_reg)
+{
+	int i = 0;
+
+	for (i = 0; sdt_reg_tbl[i].sdt_name != NULL; i++) {
+		if (!strncmp(sdt_reg_tbl[i].sdt_name, sdt_reg, sdt_len)) {
+			strcpy(uprobe_reg, sdt_reg_tbl[i].uprobe_name);
+			return;
+		}
+	}
+
+	strncpy(uprobe_reg, sdt_reg, sdt_len);
+}
+
+int arch_sdt_arg_parse_op(char *old_op, char **new_op)
+{
+	char new_reg[SDT_REG_NAME_SIZE] = {0};
+	int new_len = 0, ret;
+	/*
+	 * rm[0]:  +/-NUM(REG)
+	 * rm[1]:  +/-
+	 * rm[2]:  NUM
+	 * rm[3]:  (
+	 * rm[4]:  REG
+	 * rm[5]:  )
+	 */
+	regmatch_t rm[6];
+	/*
+	 * Max prefix length is 2 as it may contains sign(+/-)
+	 * and displacement 0 (Both sign and displacement 0 are
+	 * optional so it may be empty). Use one more character
+	 * to hold last NULL so that strlen can be used to find
+	 * prefix length, instead of maintaing one more variable.
+	 */
+	char prefix[3] = {0};
+
+	ret = sdt_init_op_regex();
+	if (ret < 0)
+		return ret;
+
+	/*
+	 * If unsupported OR does not match with regex OR
+	 * register name too long, skip it.
+	 */
+	if (strchr(old_op, ',') || strchr(old_op, '$') ||
+	    regexec(&sdt_op_regex, old_op, 6, rm, 0)   ||
+	    rm[4].rm_eo - rm[4].rm_so > SDT_REG_NAME_SIZE) {
+		pr_debug4("Skipping unsupported SDT argument: %s\n", old_op);
+		return SDT_ARG_SKIP;
+	}
+
+	/*
+	 * Prepare prefix.
+	 * If SDT OP has parenthesis but does not provide
+	 * displacement, add 0 for displacement.
+	 *     SDT         Uprobe     Prefix
+	 *     -----------------------------
+	 *     +24(%rdi)   +24(%di)   +
+	 *     24(%rdi)    +24(%di)   +
+	 *     %rdi        %di
+	 *     (%rdi)      +0(%di)    +0
+	 *     -80(%rbx)   -80(%bx)   -
+	 */
+	if (rm[3].rm_so != rm[3].rm_eo) {
+		if (rm[1].rm_so != rm[1].rm_eo)
+			prefix[0] = *(old_op + rm[1].rm_so);
+		else if (rm[2].rm_so != rm[2].rm_eo)
+			prefix[0] = '+';
+		else
+			strncpy(prefix, "+0", 2);
+	}
+
+	/* Rename register */
+	sdt_rename_register(old_op + rm[4].rm_so, rm[4].rm_eo - rm[4].rm_so,
+			    new_reg);
+
+	/* Prepare final OP which should be valid for uprobe_events */
+	new_len = strlen(prefix)              +
+		  (rm[2].rm_eo - rm[2].rm_so) +
+		  (rm[3].rm_eo - rm[3].rm_so) +
+		  strlen(new_reg)             +
+		  (rm[5].rm_eo - rm[5].rm_so) +
+		  1;					/* NULL */
+
+	*new_op = zalloc(new_len);
+	if (!*new_op)
+		return -ENOMEM;
+
+	scnprintf(*new_op, new_len, "%.*s%.*s%.*s%.*s%.*s",
+		  strlen(prefix), prefix,
+		  (int)(rm[2].rm_eo - rm[2].rm_so), old_op + rm[2].rm_so,
+		  (int)(rm[3].rm_eo - rm[3].rm_so), old_op + rm[3].rm_so,
+		  strlen(new_reg), new_reg,
+		  (int)(rm[5].rm_eo - rm[5].rm_so), old_op + rm[5].rm_so);
+
+	return SDT_ARG_VALID;
+}
diff --git a/tools/perf/bench/bench.h b/tools/perf/bench/bench.h
index 579a592990dd..842ab2781cdc 100644
--- a/tools/perf/bench/bench.h
+++ b/tools/perf/bench/bench.h
@@ -25,17 +25,17 @@
 # endif
 #endif
 
-int bench_numa(int argc, const char **argv, const char *prefix);
-int bench_sched_messaging(int argc, const char **argv, const char *prefix);
-int bench_sched_pipe(int argc, const char **argv, const char *prefix);
-int bench_mem_memcpy(int argc, const char **argv, const char *prefix);
-int bench_mem_memset(int argc, const char **argv, const char *prefix);
-int bench_futex_hash(int argc, const char **argv, const char *prefix);
-int bench_futex_wake(int argc, const char **argv, const char *prefix);
-int bench_futex_wake_parallel(int argc, const char **argv, const char *prefix);
-int bench_futex_requeue(int argc, const char **argv, const char *prefix);
+int bench_numa(int argc, const char **argv);
+int bench_sched_messaging(int argc, const char **argv);
+int bench_sched_pipe(int argc, const char **argv);
+int bench_mem_memcpy(int argc, const char **argv);
+int bench_mem_memset(int argc, const char **argv);
+int bench_futex_hash(int argc, const char **argv);
+int bench_futex_wake(int argc, const char **argv);
+int bench_futex_wake_parallel(int argc, const char **argv);
+int bench_futex_requeue(int argc, const char **argv);
 /* pi futexes */
-int bench_futex_lock_pi(int argc, const char **argv, const char *prefix);
+int bench_futex_lock_pi(int argc, const char **argv);
 
 #define BENCH_FORMAT_DEFAULT_STR	"default"
 #define BENCH_FORMAT_DEFAULT		0
diff --git a/tools/perf/bench/futex-hash.c b/tools/perf/bench/futex-hash.c
index da04b8c5568a..fe16b310097f 100644
--- a/tools/perf/bench/futex-hash.c
+++ b/tools/perf/bench/futex-hash.c
@@ -9,6 +9,7 @@
  */
 
 /* For the CLR_() macros */
+#include <string.h>
 #include <pthread.h>
 
 #include <errno.h>
@@ -113,8 +114,7 @@ static void print_summary(void)
 	       (int) runtime.tv_sec);
 }
 
-int bench_futex_hash(int argc, const char **argv,
-		     const char *prefix __maybe_unused)
+int bench_futex_hash(int argc, const char **argv)
 {
 	int ret = 0;
 	cpu_set_t cpu;
diff --git a/tools/perf/bench/futex-lock-pi.c b/tools/perf/bench/futex-lock-pi.c
index 91877777ec6e..73a1c44ea63c 100644
--- a/tools/perf/bench/futex-lock-pi.c
+++ b/tools/perf/bench/futex-lock-pi.c
@@ -3,6 +3,7 @@
  */
 
 /* For the CLR_() macros */
+#include <string.h>
 #include <pthread.h>
 
 #include <signal.h>
@@ -139,8 +140,7 @@ static void create_threads(struct worker *w, pthread_attr_t thread_attr)
 	}
 }
 
-int bench_futex_lock_pi(int argc, const char **argv,
-			const char *prefix __maybe_unused)
+int bench_futex_lock_pi(int argc, const char **argv)
 {
 	int ret = 0;
 	unsigned int i;
diff --git a/tools/perf/bench/futex-requeue.c b/tools/perf/bench/futex-requeue.c
index 2b9705a8734c..41786cbea24c 100644
--- a/tools/perf/bench/futex-requeue.c
+++ b/tools/perf/bench/futex-requeue.c
@@ -9,6 +9,7 @@
  */
 
 /* For the CLR_() macros */
+#include <string.h>
 #include <pthread.h>
 
 #include <signal.h>
@@ -108,8 +109,7 @@ static void toggle_done(int sig __maybe_unused,
 	done = true;
 }
 
-int bench_futex_requeue(int argc, const char **argv,
-			const char *prefix __maybe_unused)
+int bench_futex_requeue(int argc, const char **argv)
 {
 	int ret = 0;
 	unsigned int i, j;
diff --git a/tools/perf/bench/futex-wake-parallel.c b/tools/perf/bench/futex-wake-parallel.c
index 2c8fa67ad537..4ab12c8e016a 100644
--- a/tools/perf/bench/futex-wake-parallel.c
+++ b/tools/perf/bench/futex-wake-parallel.c
@@ -8,6 +8,7 @@
  */
 
 /* For the CLR_() macros */
+#include <string.h>
 #include <pthread.h>
 
 #include <signal.h>
@@ -196,8 +197,7 @@ static void toggle_done(int sig __maybe_unused,
 	done = true;
 }
 
-int bench_futex_wake_parallel(int argc, const char **argv,
-			      const char *prefix __maybe_unused)
+int bench_futex_wake_parallel(int argc, const char **argv)
 {
 	int ret = 0;
 	unsigned int i, j;
diff --git a/tools/perf/bench/futex-wake.c b/tools/perf/bench/futex-wake.c
index e246b1b8388a..2fa49222ef8d 100644
--- a/tools/perf/bench/futex-wake.c
+++ b/tools/perf/bench/futex-wake.c
@@ -9,6 +9,7 @@
  */
 
 /* For the CLR_() macros */
+#include <string.h>
 #include <pthread.h>
 
 #include <signal.h>
@@ -114,8 +115,7 @@ static void toggle_done(int sig __maybe_unused,
 	done = true;
 }
 
-int bench_futex_wake(int argc, const char **argv,
-		     const char *prefix __maybe_unused)
+int bench_futex_wake(int argc, const char **argv)
 {
 	int ret = 0;
 	unsigned int i, j;
diff --git a/tools/perf/bench/futex.h b/tools/perf/bench/futex.h
index b2e06d1190d0..e44fd3239530 100644
--- a/tools/perf/bench/futex.h
+++ b/tools/perf/bench/futex.h
@@ -88,13 +88,11 @@ futex_cmp_requeue(u_int32_t *uaddr, u_int32_t val, u_int32_t *uaddr2, int nr_wak
 
 #ifndef HAVE_PTHREAD_ATTR_SETAFFINITY_NP
 #include <pthread.h>
-static inline int pthread_attr_setaffinity_np(pthread_attr_t *attr,
-					      size_t cpusetsize,
-					      cpu_set_t *cpuset)
+#include <linux/compiler.h>
+static inline int pthread_attr_setaffinity_np(pthread_attr_t *attr __maybe_unused,
+					      size_t cpusetsize __maybe_unused,
+					      cpu_set_t *cpuset __maybe_unused)
 {
-	attr = attr;
-	cpusetsize = cpusetsize;
-	cpuset = cpuset;
 	return 0;
 }
 #endif
diff --git a/tools/perf/bench/mem-functions.c b/tools/perf/bench/mem-functions.c
index 52504a83b5a1..d1dea33dcfcf 100644
--- a/tools/perf/bench/mem-functions.c
+++ b/tools/perf/bench/mem-functions.c
@@ -284,7 +284,7 @@ static const char * const bench_mem_memcpy_usage[] = {
 	NULL
 };
 
-int bench_mem_memcpy(int argc, const char **argv, const char *prefix __maybe_unused)
+int bench_mem_memcpy(int argc, const char **argv)
 {
 	struct bench_mem_info info = {
 		.functions		= memcpy_functions,
@@ -358,7 +358,7 @@ static const struct function memset_functions[] = {
 	{ .name = NULL, }
 };
 
-int bench_mem_memset(int argc, const char **argv, const char *prefix __maybe_unused)
+int bench_mem_memset(int argc, const char **argv)
 {
 	struct bench_mem_info info = {
 		.functions		= memset_functions,
diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
index 3083fc36282b..1fe43bd5a012 100644
--- a/tools/perf/bench/numa.c
+++ b/tools/perf/bench/numa.c
@@ -187,7 +187,8 @@ static const struct option options[] = {
 	OPT_INCR   ('d', "show_details"	, &p0.show_details,	"Show details"),
 	OPT_INCR   ('a', "all"		, &p0.run_all,		"Run all tests in the suite"),
 	OPT_INTEGER('H', "thp"		, &p0.thp,		"MADV_NOHUGEPAGE < 0 < MADV_HUGEPAGE"),
-	OPT_BOOLEAN('c', "show_convergence", &p0.show_convergence, "show convergence details"),
+	OPT_BOOLEAN('c', "show_convergence", &p0.show_convergence, "show convergence details, "
+		    "convergence is reached when each process (all its threads) is running on a single NUMA node."),
 	OPT_BOOLEAN('m', "measure_convergence",	&p0.measure_convergence, "measure convergence latency"),
 	OPT_BOOLEAN('q', "quiet"	, &p0.show_quiet,	"quiet mode"),
 	OPT_BOOLEAN('S', "serialize-startup", &p0.serialize_startup,"serialize thread startup"),
@@ -1766,7 +1767,7 @@ static int bench_all(void)
 	return 0;
 }
 
-int bench_numa(int argc, const char **argv, const char *prefix __maybe_unused)
+int bench_numa(int argc, const char **argv)
 {
 	init_params(&p0, "main,", argc, argv);
 	argc = parse_options(argc, argv, options, bench_numa_usage, 0);
diff --git a/tools/perf/bench/sched-messaging.c b/tools/perf/bench/sched-messaging.c
index 6a111e775210..4f961e74535b 100644
--- a/tools/perf/bench/sched-messaging.c
+++ b/tools/perf/bench/sched-messaging.c
@@ -260,8 +260,7 @@ static const char * const bench_sched_message_usage[] = {
 	NULL
 };
 
-int bench_sched_messaging(int argc, const char **argv,
-		    const char *prefix __maybe_unused)
+int bench_sched_messaging(int argc, const char **argv)
 {
 	unsigned int i, total_children;
 	struct timeval start, stop, diff;
diff --git a/tools/perf/bench/sched-pipe.c b/tools/perf/bench/sched-pipe.c
index 2243f0150d76..a152737370c5 100644
--- a/tools/perf/bench/sched-pipe.c
+++ b/tools/perf/bench/sched-pipe.c
@@ -76,7 +76,7 @@ static void *worker_thread(void *__tdata)
 	return NULL;
 }
 
-int bench_sched_pipe(int argc, const char **argv, const char *prefix __maybe_unused)
+int bench_sched_pipe(int argc, const char **argv)
 {
 	struct thread_data threads[2], *td;
 	int pipe_1[2], pipe_2[2];
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 4f52d85f5ebc..56a7c8d210b9 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -383,7 +383,7 @@ static const char * const annotate_usage[] = {
 	NULL
 };
 
-int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_annotate(int argc, const char **argv)
 {
 	struct perf_annotate annotate = {
 		.tool = {
@@ -393,6 +393,7 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused)
 			.comm	= perf_event__process_comm,
 			.exit	= perf_event__process_exit,
 			.fork	= perf_event__process_fork,
+			.namespaces = perf_event__process_namespaces,
 			.ordered_events = true,
 			.ordering_requires_timestamps = true,
 		},
diff --git a/tools/perf/builtin-bench.c b/tools/perf/builtin-bench.c
index a1cddc6bbf0f..445e62881254 100644
--- a/tools/perf/builtin-bench.c
+++ b/tools/perf/builtin-bench.c
@@ -25,7 +25,7 @@
 #include <string.h>
 #include <sys/prctl.h>
 
-typedef int (*bench_fn_t)(int argc, const char **argv, const char *prefix);
+typedef int (*bench_fn_t)(int argc, const char **argv);
 
 struct bench {
 	const char	*name;
@@ -155,7 +155,7 @@ static int bench_str2int(const char *str)
  * to something meaningful:
  */
 static int run_bench(const char *coll_name, const char *bench_name, bench_fn_t fn,
-		     int argc, const char **argv, const char *prefix)
+		     int argc, const char **argv)
 {
 	int size;
 	char *name;
@@ -171,7 +171,7 @@ static int run_bench(const char *coll_name, const char *bench_name, bench_fn_t f
 	prctl(PR_SET_NAME, name);
 	argv[0] = name;
 
-	ret = fn(argc, argv, prefix);
+	ret = fn(argc, argv);
 
 	free(name);
 
@@ -198,7 +198,7 @@ static void run_collection(struct collection *coll)
 		fflush(stdout);
 
 		argv[1] = bench->name;
-		run_bench(coll->name, bench->name, bench->fn, 1, argv, NULL);
+		run_bench(coll->name, bench->name, bench->fn, 1, argv);
 		printf("\n");
 	}
 }
@@ -211,7 +211,7 @@ static void run_all_collections(void)
 		run_collection(coll);
 }
 
-int cmd_bench(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_bench(int argc, const char **argv)
 {
 	struct collection *coll;
 	int ret = 0;
@@ -270,7 +270,7 @@ int cmd_bench(int argc, const char **argv, const char *prefix __maybe_unused)
 			if (bench_format == BENCH_FORMAT_DEFAULT)
 				printf("# Running '%s/%s' benchmark:\n", coll->name, bench->name);
 			fflush(stdout);
-			ret = run_bench(coll->name, bench->name, bench->fn, argc-1, argv+1, prefix);
+			ret = run_bench(coll->name, bench->name, bench->fn, argc-1, argv+1);
 			goto end;
 		}
 
diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c
index 30e2b2cb2421..94b55eee0d9b 100644
--- a/tools/perf/builtin-buildid-cache.c
+++ b/tools/perf/builtin-buildid-cache.c
@@ -276,8 +276,7 @@ static int build_id_cache__update_file(const char *filename)
 	return err;
 }
 
-int cmd_buildid_cache(int argc, const char **argv,
-		      const char *prefix __maybe_unused)
+int cmd_buildid_cache(int argc, const char **argv)
 {
 	struct strlist *list;
 	struct str_node *pos;
diff --git a/tools/perf/builtin-buildid-list.c b/tools/perf/builtin-buildid-list.c
index 5e914ee79eb3..26f4e608207f 100644
--- a/tools/perf/builtin-buildid-list.c
+++ b/tools/perf/builtin-buildid-list.c
@@ -87,8 +87,7 @@ out:
 	return 0;
 }
 
-int cmd_buildid_list(int argc, const char **argv,
-		     const char *prefix __maybe_unused)
+int cmd_buildid_list(int argc, const char **argv)
 {
 	bool show_kernel = false;
 	bool with_hits = false;
diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c
index e2b21723bbf8..70c2c773a2b8 100644
--- a/tools/perf/builtin-c2c.c
+++ b/tools/perf/builtin-c2c.c
@@ -2334,7 +2334,7 @@ out:
 
 static void perf_c2c_display(struct perf_session *session)
 {
-	if (c2c.use_stdio)
+	if (use_browser == 0)
 		perf_c2c__hists_fprintf(stdout, session);
 	else
 		perf_c2c__hists_browse(&c2c.hists.hists);
@@ -2536,7 +2536,7 @@ static int perf_c2c__report(int argc, const char **argv)
 	OPT_BOOLEAN(0, "stdio", &c2c.use_stdio, "Use the stdio interface"),
 #endif
 	OPT_BOOLEAN(0, "stats", &c2c.stats_only,
-		    "Use the stdio interface"),
+		    "Display only statistic tables (implies --stdio)"),
 	OPT_BOOLEAN(0, "full-symbols", &c2c.symbol_full,
 		    "Display full length of symbols"),
 	OPT_BOOLEAN(0, "no-source", &no_source,
@@ -2755,12 +2755,12 @@ static int perf_c2c__record(int argc, const char **argv)
 		pr_debug("\n");
 	}
 
-	ret = cmd_record(i, rec_argv, NULL);
+	ret = cmd_record(i, rec_argv);
 	free(rec_argv);
 	return ret;
 }
 
-int cmd_c2c(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_c2c(int argc, const char **argv)
 {
 	argc = parse_options(argc, argv, c2c_options, c2c_usage,
 			     PARSE_OPT_STOP_AT_NON_OPTION);
diff --git a/tools/perf/builtin-config.c b/tools/perf/builtin-config.c
index 8c0d93b7c2f0..55f04f85b049 100644
--- a/tools/perf/builtin-config.c
+++ b/tools/perf/builtin-config.c
@@ -154,7 +154,7 @@ static int parse_config_arg(char *arg, char **var, char **value)
 	return 0;
 }
 
-int cmd_config(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_config(int argc, const char **argv)
 {
 	int i, ret = 0;
 	struct perf_config_set *set;
diff --git a/tools/perf/builtin-data.c b/tools/perf/builtin-data.c
index 7ad6e17ac6b3..0adb5f82335a 100644
--- a/tools/perf/builtin-data.c
+++ b/tools/perf/builtin-data.c
@@ -6,7 +6,7 @@
 #include "data-convert.h"
 #include "data-convert-bt.h"
 
-typedef int (*data_cmd_fn_t)(int argc, const char **argv, const char *prefix);
+typedef int (*data_cmd_fn_t)(int argc, const char **argv);
 
 struct data_cmd {
 	const char	*name;
@@ -50,8 +50,7 @@ static const char * const data_convert_usage[] = {
 	NULL
 };
 
-static int cmd_data_convert(int argc, const char **argv,
-			    const char *prefix __maybe_unused)
+static int cmd_data_convert(int argc, const char **argv)
 {
 	const char *to_ctf     = NULL;
 	struct perf_data_convert_opts opts = {
@@ -98,7 +97,7 @@ static struct data_cmd data_cmds[] = {
 	{ .name = NULL, },
 };
 
-int cmd_data(int argc, const char **argv, const char *prefix)
+int cmd_data(int argc, const char **argv)
 {
 	struct data_cmd *cmd;
 	const char *cmdstr;
@@ -118,7 +117,7 @@ int cmd_data(int argc, const char **argv, const char *prefix)
 		if (strcmp(cmd->name, cmdstr))
 			continue;
 
-		return cmd->fn(argc, argv, prefix);
+		return cmd->fn(argc, argv);
 	}
 
 	pr_err("Unknown command: %s\n", cmdstr);
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 1b96a3122228..cd2605d86984 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -364,6 +364,7 @@ static struct perf_tool tool = {
 	.exit	= perf_event__process_exit,
 	.fork	= perf_event__process_fork,
 	.lost	= perf_event__process_lost,
+	.namespaces = perf_event__process_namespaces,
 	.ordered_events = true,
 	.ordering_requires_timestamps = true,
 };
@@ -1320,7 +1321,7 @@ static int diff__config(const char *var, const char *value,
 	return 0;
 }
 
-int cmd_diff(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_diff(int argc, const char **argv)
 {
 	int ret = hists__init();
 
diff --git a/tools/perf/builtin-evlist.c b/tools/perf/builtin-evlist.c
index e09c4287fe87..6d210e40d611 100644
--- a/tools/perf/builtin-evlist.c
+++ b/tools/perf/builtin-evlist.c
@@ -46,7 +46,7 @@ static int __cmd_evlist(const char *file_name, struct perf_attr_details *details
 	return 0;
 }
 
-int cmd_evlist(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_evlist(int argc, const char **argv)
 {
 	struct perf_attr_details details = { .verbose = false, };
 	const struct option options[] = {
diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c
index c3e643666c72..f80fb60b00b0 100644
--- a/tools/perf/builtin-ftrace.c
+++ b/tools/perf/builtin-ftrace.c
@@ -11,11 +11,13 @@
 
 #include <unistd.h>
 #include <signal.h>
+#include <fcntl.h>
 
 #include "debug.h"
 #include <subcmd/parse-options.h>
 #include "evlist.h"
 #include "target.h"
+#include "cpumap.h"
 #include "thread_map.h"
 #include "util/config.h"
 
@@ -50,11 +52,12 @@ static void ftrace__workload_exec_failed_signal(int signo __maybe_unused,
 	done = true;
 }
 
-static int write_tracing_file(const char *name, const char *val)
+static int __write_tracing_file(const char *name, const char *val, bool append)
 {
 	char *file;
 	int fd, ret = -1;
 	ssize_t size = strlen(val);
+	int flags = O_WRONLY;
 
 	file = get_tracing_file(name);
 	if (!file) {
@@ -62,7 +65,12 @@ static int write_tracing_file(const char *name, const char *val)
 		return -1;
 	}
 
-	fd = open(file, O_WRONLY);
+	if (append)
+		flags |= O_APPEND;
+	else
+		flags |= O_TRUNC;
+
+	fd = open(file, flags);
 	if (fd < 0) {
 		pr_debug("cannot open tracing file: %s\n", name);
 		goto out;
@@ -79,6 +87,18 @@ out:
 	return ret;
 }
 
+static int write_tracing_file(const char *name, const char *val)
+{
+	return __write_tracing_file(name, val, false);
+}
+
+static int append_tracing_file(const char *name, const char *val)
+{
+	return __write_tracing_file(name, val, true);
+}
+
+static int reset_tracing_cpu(void);
+
 static int reset_tracing_files(struct perf_ftrace *ftrace __maybe_unused)
 {
 	if (write_tracing_file("tracing_on", "0") < 0)
@@ -90,14 +110,78 @@ static int reset_tracing_files(struct perf_ftrace *ftrace __maybe_unused)
 	if (write_tracing_file("set_ftrace_pid", " ") < 0)
 		return -1;
 
+	if (reset_tracing_cpu() < 0)
+		return -1;
+
+	return 0;
+}
+
+static int set_tracing_pid(struct perf_ftrace *ftrace)
+{
+	int i;
+	char buf[16];
+
+	if (target__has_cpu(&ftrace->target))
+		return 0;
+
+	for (i = 0; i < thread_map__nr(ftrace->evlist->threads); i++) {
+		scnprintf(buf, sizeof(buf), "%d",
+			  ftrace->evlist->threads->map[i]);
+		if (append_tracing_file("set_ftrace_pid", buf) < 0)
+			return -1;
+	}
 	return 0;
 }
 
+static int set_tracing_cpumask(struct cpu_map *cpumap)
+{
+	char *cpumask;
+	size_t mask_size;
+	int ret;
+	int last_cpu;
+
+	last_cpu = cpu_map__cpu(cpumap, cpumap->nr - 1);
+	mask_size = (last_cpu + 3) / 4 + 1;
+	mask_size += last_cpu / 32; /* ',' is needed for every 32th cpus */
+
+	cpumask = malloc(mask_size);
+	if (cpumask == NULL) {
+		pr_debug("failed to allocate cpu mask\n");
+		return -1;
+	}
+
+	cpu_map__snprint_mask(cpumap, cpumask, mask_size);
+
+	ret = write_tracing_file("tracing_cpumask", cpumask);
+
+	free(cpumask);
+	return ret;
+}
+
+static int set_tracing_cpu(struct perf_ftrace *ftrace)
+{
+	struct cpu_map *cpumap = ftrace->evlist->cpus;
+
+	if (!target__has_cpu(&ftrace->target))
+		return 0;
+
+	return set_tracing_cpumask(cpumap);
+}
+
+static int reset_tracing_cpu(void)
+{
+	struct cpu_map *cpumap = cpu_map__new(NULL);
+	int ret;
+
+	ret = set_tracing_cpumask(cpumap);
+	cpu_map__put(cpumap);
+	return ret;
+}
+
 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,
@@ -108,42 +192,43 @@ static int __cmd_ftrace(struct perf_ftrace *ftrace, int argc, const char **argv)
 		return -1;
 	}
 
-	if (argc < 1)
-		return -1;
-
 	signal(SIGINT, sig_handler);
 	signal(SIGUSR1, sig_handler);
 	signal(SIGCHLD, sig_handler);
+	signal(SIGPIPE, sig_handler);
 
-	reset_tracing_files(ftrace);
+	if (reset_tracing_files(ftrace) < 0)
+		goto out;
 
 	/* 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)
+	if (argc && 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 (set_tracing_pid(ftrace) < 0) {
+		pr_err("failed to set ftrace pid\n");
+		goto out_reset;
 	}
 
-	if (asprintf(&trace_pid, "%d", thread_map__pid(ftrace->evlist->threads, 0)) < 0) {
-		pr_err("failed to allocate pid string\n");
-		goto out;
+	if (set_tracing_cpu(ftrace) < 0) {
+		pr_err("failed to set tracing cpumask\n");
+		goto out_reset;
 	}
 
-	if (write_tracing_file("set_ftrace_pid", trace_pid) < 0) {
-		pr_err("failed to set pid: %s\n", trace_pid);
-		goto out_free_pid;
+	if (write_tracing_file("current_tracer", ftrace->tracer) < 0) {
+		pr_err("failed to set current_tracer to %s\n", ftrace->tracer);
+		goto out_reset;
 	}
 
 	trace_file = get_tracing_file("trace_pipe");
 	if (!trace_file) {
 		pr_err("failed to open trace_pipe\n");
-		goto out_free_pid;
+		goto out_reset;
 	}
 
 	trace_fd = open(trace_file, O_RDONLY);
@@ -152,7 +237,7 @@ static int __cmd_ftrace(struct perf_ftrace *ftrace, int argc, const char **argv)
 
 	if (trace_fd < 0) {
 		pr_err("failed to open trace_pipe\n");
-		goto out_free_pid;
+		goto out_reset;
 	}
 
 	fcntl(trace_fd, F_SETFL, O_NONBLOCK);
@@ -163,6 +248,8 @@ static int __cmd_ftrace(struct perf_ftrace *ftrace, int argc, const char **argv)
 		goto out_close_fd;
 	}
 
+	setup_pager();
+
 	perf_evlist__start_workload(ftrace->evlist);
 
 	while (!done) {
@@ -191,11 +278,9 @@ static int __cmd_ftrace(struct perf_ftrace *ftrace, int argc, const char **argv)
 
 out_close_fd:
 	close(trace_fd);
-out_free_pid:
-	free(trace_pid);
-out:
+out_reset:
 	reset_tracing_files(ftrace);
-
+out:
 	return done ? 0 : -1;
 }
 
@@ -219,7 +304,7 @@ static int perf_ftrace_config(const char *var, const char *value, void *cb)
 	return -1;
 }
 
-int cmd_ftrace(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_ftrace(int argc, const char **argv)
 {
 	int ret;
 	struct perf_ftrace ftrace = {
@@ -227,15 +312,21 @@ int cmd_ftrace(int argc, const char **argv, const char *prefix __maybe_unused)
 		.target = { .uid = UINT_MAX, },
 	};
 	const char * const ftrace_usage[] = {
-		"perf ftrace [<options>] <command>",
+		"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_STRING('p', "pid", &ftrace.target.pid, "pid",
+		   "trace on existing process id"),
 	OPT_INCR('v', "verbose", &verbose,
 		 "be more verbose"),
+	OPT_BOOLEAN('a', "all-cpus", &ftrace.target.system_wide,
+		    "system-wide collection from all CPUs"),
+	OPT_STRING('C', "cpu", &ftrace.target.cpu_list, "cpu",
+		    "list of cpus to monitor"),
 	OPT_END()
 	};
 
@@ -245,9 +336,18 @@ int cmd_ftrace(int argc, const char **argv, const char *prefix __maybe_unused)
 
 	argc = parse_options(argc, argv, ftrace_options, ftrace_usage,
 			    PARSE_OPT_STOP_AT_NON_OPTION);
-	if (!argc)
+	if (!argc && target__none(&ftrace.target))
 		usage_with_options(ftrace_usage, ftrace_options);
 
+	ret = target__validate(&ftrace.target);
+	if (ret) {
+		char errbuf[512];
+
+		target__strerror(&ftrace.target, ret, errbuf, 512);
+		pr_err("%s\n", errbuf);
+		return -EINVAL;
+	}
+
 	ftrace.evlist = perf_evlist__new();
 	if (ftrace.evlist == NULL)
 		return -ENOMEM;
diff --git a/tools/perf/builtin-help.c b/tools/perf/builtin-help.c
index aed0d844e8c2..1eec96a0fa67 100644
--- a/tools/perf/builtin-help.c
+++ b/tools/perf/builtin-help.c
@@ -301,12 +301,6 @@ void list_common_cmds_help(void)
 	}
 }
 
-static int is_perf_command(const char *s)
-{
-	return is_in_cmdlist(&main_cmds, s) ||
-		is_in_cmdlist(&other_cmds, s);
-}
-
 static const char *cmd_to_page(const char *perf_cmd)
 {
 	char *s;
@@ -418,7 +412,7 @@ static int show_html_page(const char *perf_cmd)
 	return 0;
 }
 
-int cmd_help(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_help(int argc, const char **argv)
 {
 	bool show_all = false;
 	enum help_format help_format = HELP_FORMAT_MAN;
@@ -446,7 +440,6 @@ int cmd_help(int argc, const char **argv, const char *prefix __maybe_unused)
 		"perf help [--all] [--man|--web|--info] [command]",
 		NULL
 	};
-	const char *alias;
 	int rc;
 
 	load_command_list("perf-", &main_cmds, &other_cmds);
@@ -472,12 +465,6 @@ int cmd_help(int argc, const char **argv, const char *prefix __maybe_unused)
 		return 0;
 	}
 
-	alias = alias_lookup(argv[0]);
-	if (alias && !is_perf_command(argv[0])) {
-		printf("`perf %s' is aliased to `%s'\n", argv[0], alias);
-		return 0;
-	}
-
 	switch (help_format) {
 	case HELP_FORMAT_MAN:
 		rc = show_man_page(argv[0]);
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index b9bc7e39833a..42dff0b1375a 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -333,6 +333,18 @@ static int perf_event__repipe_comm(struct perf_tool *tool,
 	return err;
 }
 
+static int perf_event__repipe_namespaces(struct perf_tool *tool,
+					 union perf_event *event,
+					 struct perf_sample *sample,
+					 struct machine *machine)
+{
+	int err = perf_event__process_namespaces(tool, event, sample, machine);
+
+	perf_event__repipe(tool, event, sample, machine);
+
+	return err;
+}
+
 static int perf_event__repipe_exit(struct perf_tool *tool,
 				   union perf_event *event,
 				   struct perf_sample *sample,
@@ -660,6 +672,7 @@ static int __cmd_inject(struct perf_inject *inject)
 		session->itrace_synth_opts = &inject->itrace_synth_opts;
 		inject->itrace_synth_opts.inject = true;
 		inject->tool.comm	    = perf_event__repipe_comm;
+		inject->tool.namespaces	    = perf_event__repipe_namespaces;
 		inject->tool.exit	    = perf_event__repipe_exit;
 		inject->tool.id_index	    = perf_event__repipe_id_index;
 		inject->tool.auxtrace_info  = perf_event__process_auxtrace_info;
@@ -725,7 +738,7 @@ static int __cmd_inject(struct perf_inject *inject)
 	return ret;
 }
 
-int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_inject(int argc, const char **argv)
 {
 	struct perf_inject inject = {
 		.tool = {
diff --git a/tools/perf/builtin-kallsyms.c b/tools/perf/builtin-kallsyms.c
index 224bfc454b4a..8ff38c4eb2c0 100644
--- a/tools/perf/builtin-kallsyms.c
+++ b/tools/perf/builtin-kallsyms.c
@@ -43,7 +43,7 @@ static int __cmd_kallsyms(int argc, const char **argv)
 	return 0;
 }
 
-int cmd_kallsyms(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_kallsyms(int argc, const char **argv)
 {
 	const struct option options[] = {
 	OPT_INCR('v', "verbose", &verbose, "be more verbose (show counter open errors, etc)"),
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index 6da8d083e4e5..515587825af4 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -964,6 +964,7 @@ static struct perf_tool perf_kmem = {
 	.comm		 = perf_event__process_comm,
 	.mmap		 = perf_event__process_mmap,
 	.mmap2		 = perf_event__process_mmap2,
+	.namespaces	 = perf_event__process_namespaces,
 	.ordered_events	 = true,
 };
 
@@ -1865,7 +1866,7 @@ static int __cmd_record(int argc, const char **argv)
 	for (j = 1; j < (unsigned int)argc; j++, i++)
 		rec_argv[i] = argv[j];
 
-	return cmd_record(i, rec_argv, NULL);
+	return cmd_record(i, rec_argv);
 }
 
 static int kmem_config(const char *var, const char *value, void *cb __maybe_unused)
@@ -1884,7 +1885,7 @@ static int kmem_config(const char *var, const char *value, void *cb __maybe_unus
 	return 0;
 }
 
-int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_kmem(int argc, const char **argv)
 {
 	const char * const default_slab_sort = "frag,hit,bytes";
 	const char * const default_page_sort = "bytes,hit";
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index 08fa88f62a24..38b409173693 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -1044,6 +1044,7 @@ static int read_events(struct perf_kvm_stat *kvm)
 	struct perf_tool eops = {
 		.sample			= process_sample_event,
 		.comm			= perf_event__process_comm,
+		.namespaces		= perf_event__process_namespaces,
 		.ordered_events		= true,
 	};
 	struct perf_data_file file = {
@@ -1208,7 +1209,7 @@ kvm_events_record(struct perf_kvm_stat *kvm, int argc, const char **argv)
 	set_option_flag(record_options, 0, "transaction", PARSE_OPT_DISABLED);
 
 	record_usage = kvm_stat_record_usage;
-	return cmd_record(i, rec_argv, NULL);
+	return cmd_record(i, rec_argv);
 }
 
 static int
@@ -1348,6 +1349,7 @@ static int kvm_events_live(struct perf_kvm_stat *kvm,
 	kvm->tool.exit   = perf_event__process_exit;
 	kvm->tool.fork   = perf_event__process_fork;
 	kvm->tool.lost   = process_lost_event;
+	kvm->tool.namespaces  = perf_event__process_namespaces;
 	kvm->tool.ordered_events = true;
 	perf_tool__fill_defaults(&kvm->tool);
 
@@ -1475,7 +1477,7 @@ static int kvm_cmd_stat(const char *file_name, int argc, const char **argv)
 #endif
 
 perf_stat:
-	return cmd_stat(argc, argv, NULL);
+	return cmd_stat(argc, argv);
 }
 #endif /* HAVE_KVM_STAT_SUPPORT */
 
@@ -1494,7 +1496,7 @@ static int __cmd_record(const char *file_name, int argc, const char **argv)
 
 	BUG_ON(i != rec_argc);
 
-	return cmd_record(i, rec_argv, NULL);
+	return cmd_record(i, rec_argv);
 }
 
 static int __cmd_report(const char *file_name, int argc, const char **argv)
@@ -1512,7 +1514,7 @@ static int __cmd_report(const char *file_name, int argc, const char **argv)
 
 	BUG_ON(i != rec_argc);
 
-	return cmd_report(i, rec_argv, NULL);
+	return cmd_report(i, rec_argv);
 }
 
 static int
@@ -1531,10 +1533,10 @@ __cmd_buildid_list(const char *file_name, int argc, const char **argv)
 
 	BUG_ON(i != rec_argc);
 
-	return cmd_buildid_list(i, rec_argv, NULL);
+	return cmd_buildid_list(i, rec_argv);
 }
 
-int cmd_kvm(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_kvm(int argc, const char **argv)
 {
 	const char *file_name = NULL;
 	const struct option kvm_options[] = {
@@ -1589,9 +1591,9 @@ int cmd_kvm(int argc, const char **argv, const char *prefix __maybe_unused)
 	else if (!strncmp(argv[0], "rep", 3))
 		return __cmd_report(file_name, argc, argv);
 	else if (!strncmp(argv[0], "diff", 4))
-		return cmd_diff(argc, argv, NULL);
+		return cmd_diff(argc, argv);
 	else if (!strncmp(argv[0], "top", 3))
-		return cmd_top(argc, argv, NULL);
+		return cmd_top(argc, argv);
 	else if (!strncmp(argv[0], "buildid-list", 12))
 		return __cmd_buildid_list(file_name, argc, argv);
 #ifdef HAVE_KVM_STAT_SUPPORT
diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c
index 3b9d98b5feef..4bf2cb4d25aa 100644
--- a/tools/perf/builtin-list.c
+++ b/tools/perf/builtin-list.c
@@ -18,8 +18,9 @@
 #include <subcmd/parse-options.h>
 
 static bool desc_flag = true;
+static bool details_flag;
 
-int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_list(int argc, const char **argv)
 {
 	int i;
 	bool raw_dump = false;
@@ -30,6 +31,8 @@ int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused)
 			    "Print extra event descriptions. --no-desc to not print."),
 		OPT_BOOLEAN('v', "long-desc", &long_desc_flag,
 			    "Print longer event descriptions."),
+		OPT_BOOLEAN(0, "details", &details_flag,
+			    "Print information on the perf event names and expressions used internally by events."),
 		OPT_INCR(0, "debug", &verbose,
 			     "Enable debugging output"),
 		OPT_END()
@@ -50,7 +53,8 @@ int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused)
 		printf("\nList of pre-defined events (to be used in -e):\n\n");
 
 	if (argc == 0) {
-		print_events(NULL, raw_dump, !desc_flag, long_desc_flag);
+		print_events(NULL, raw_dump, !desc_flag, long_desc_flag,
+				details_flag);
 		return 0;
 	}
 
@@ -72,7 +76,7 @@ int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused)
 			print_hwcache_events(NULL, raw_dump);
 		else if (strcmp(argv[i], "pmu") == 0)
 			print_pmu_events(NULL, raw_dump, !desc_flag,
-						long_desc_flag);
+						long_desc_flag, details_flag);
 		else if (strcmp(argv[i], "sdt") == 0)
 			print_sdt_events(NULL, NULL, raw_dump);
 		else if ((sep = strchr(argv[i], ':')) != NULL) {
@@ -80,7 +84,8 @@ int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused)
 
 			if (sep == NULL) {
 				print_events(argv[i], raw_dump, !desc_flag,
-							long_desc_flag);
+							long_desc_flag,
+							details_flag);
 				continue;
 			}
 			sep_idx = sep - argv[i];
@@ -103,7 +108,8 @@ int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused)
 					    event_symbols_sw, PERF_COUNT_SW_MAX, raw_dump);
 			print_hwcache_events(s, raw_dump);
 			print_pmu_events(s, raw_dump, !desc_flag,
-						long_desc_flag);
+						long_desc_flag,
+						details_flag);
 			print_tracepoint_events(NULL, s, raw_dump);
 			print_sdt_events(NULL, s, raw_dump);
 			free(s);
diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c
index ce3bfb48b26f..b686fb6759da 100644
--- a/tools/perf/builtin-lock.c
+++ b/tools/perf/builtin-lock.c
@@ -858,6 +858,7 @@ static int __cmd_report(bool display_info)
 	struct perf_tool eops = {
 		.sample		 = process_sample_event,
 		.comm		 = perf_event__process_comm,
+		.namespaces	 = perf_event__process_namespaces,
 		.ordered_events	 = true,
 	};
 	struct perf_data_file file = {
@@ -940,34 +941,36 @@ static int __cmd_record(int argc, const char **argv)
 
 	BUG_ON(i != rec_argc);
 
-	ret = cmd_record(i, rec_argv, NULL);
+	ret = cmd_record(i, rec_argv);
 	free(rec_argv);
 	return ret;
 }
 
-int cmd_lock(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_lock(int argc, const char **argv)
 {
-	const struct option info_options[] = {
-	OPT_BOOLEAN('t', "threads", &info_threads,
-		    "dump thread list in perf.data"),
-	OPT_BOOLEAN('m', "map", &info_map,
-		    "map of lock instances (address:name table)"),
-	OPT_BOOLEAN('f', "force", &force, "don't complain, do it"),
-	OPT_END()
-	};
 	const struct option lock_options[] = {
 	OPT_STRING('i', "input", &input_name, "file", "input file name"),
 	OPT_INCR('v', "verbose", &verbose, "be more verbose (show symbol address, etc)"),
 	OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace, "dump raw trace in ASCII"),
+	OPT_BOOLEAN('f', "force", &force, "don't complain, do it"),
 	OPT_END()
 	};
+
+	const struct option info_options[] = {
+	OPT_BOOLEAN('t', "threads", &info_threads,
+		    "dump thread list in perf.data"),
+	OPT_BOOLEAN('m', "map", &info_map,
+		    "map of lock instances (address:name table)"),
+	OPT_PARENT(lock_options)
+	};
+
 	const struct option report_options[] = {
 	OPT_STRING('k', "key", &sort_key, "acquired",
 		    "key for sorting (acquired / contended / avg_wait / wait_total / wait_max / wait_min)"),
-	OPT_BOOLEAN('f', "force", &force, "don't complain, do it"),
 	/* TODO: type */
-	OPT_END()
+	OPT_PARENT(lock_options)
 	};
+
 	const char * const info_usage[] = {
 		"perf lock info [<options>]",
 		NULL
@@ -1006,7 +1009,7 @@ int cmd_lock(int argc, const char **argv, const char *prefix __maybe_unused)
 		rc = __cmd_report(false);
 	} else if (!strcmp(argv[0], "script")) {
 		/* Aliased to 'perf script' */
-		return cmd_script(argc, argv, prefix);
+		return cmd_script(argc, argv);
 	} else if (!strcmp(argv[0], "info")) {
 		if (argc) {
 			argc = parse_options(argc, argv,
diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c
index 6114e07ca613..643f4faac0d0 100644
--- a/tools/perf/builtin-mem.c
+++ b/tools/perf/builtin-mem.c
@@ -129,7 +129,7 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem)
 		pr_debug("\n");
 	}
 
-	ret = cmd_record(i, rec_argv, NULL);
+	ret = cmd_record(i, rec_argv);
 	free(rec_argv);
 	return ret;
 }
@@ -256,7 +256,7 @@ static int report_events(int argc, const char **argv, struct perf_mem *mem)
 	for (j = 1; j < argc; j++, i++)
 		rep_argv[i] = argv[j];
 
-	ret = cmd_report(i, rep_argv, NULL);
+	ret = cmd_report(i, rep_argv);
 	free(rep_argv);
 	return ret;
 }
@@ -330,7 +330,7 @@ error:
 	return ret;
 }
 
-int cmd_mem(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_mem(int argc, const char **argv)
 {
 	struct stat st;
 	struct perf_mem mem = {
@@ -342,6 +342,7 @@ int cmd_mem(int argc, const char **argv, const char *prefix __maybe_unused)
 			.lost		= perf_event__process_lost,
 			.fork		= perf_event__process_fork,
 			.build_id	= perf_event__process_build_id,
+			.namespaces	= perf_event__process_namespaces,
 			.ordered_events	= true,
 		},
 		.input_name		 = "perf.data",
diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c
index aa7885b92696..cf9f9e9c2fc0 100644
--- a/tools/perf/builtin-probe.c
+++ b/tools/perf/builtin-probe.c
@@ -442,9 +442,9 @@ static int perf_del_probe_events(struct strfilter *filter)
 	}
 
 	if (ret == -ENOENT && ret2 == -ENOENT)
-		pr_debug("\"%s\" does not hit any event.\n", str);
-		/* Note that this is silently ignored */
-	ret = 0;
+		pr_warning("\"%s\" does not hit any event.\n", str);
+	else
+		ret = 0;
 
 error:
 	if (kfd >= 0)
@@ -468,7 +468,7 @@ out:
 
 
 static int
-__cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
+__cmd_probe(int argc, const char **argv)
 {
 	const char * const probe_usage[] = {
 		"perf probe [<options>] 'PROBEDEF' ['PROBEDEF' ...]",
@@ -687,13 +687,13 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
 	return 0;
 }
 
-int cmd_probe(int argc, const char **argv, const char *prefix)
+int cmd_probe(int argc, const char **argv)
 {
 	int ret;
 
 	ret = init_params();
 	if (!ret) {
-		ret = __cmd_probe(argc, argv, prefix);
+		ret = __cmd_probe(argc, argv);
 		cleanup_params();
 	}
 
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index bc84a375295d..3191ab063852 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -876,6 +876,9 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 	signal(SIGTERM, sig_handler);
 	signal(SIGSEGV, sigsegv_handler);
 
+	if (rec->opts.record_namespaces)
+		tool->namespace_events = true;
+
 	if (rec->opts.auxtrace_snapshot_mode || rec->switch_output.enabled) {
 		signal(SIGUSR2, snapshot_sig_handler);
 		if (rec->opts.auxtrace_snapshot_mode)
@@ -983,6 +986,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 	 */
 	if (forks) {
 		union perf_event *event;
+		pid_t tgid;
 
 		event = malloc(sizeof(event->comm) + machine->id_hdr_size);
 		if (event == NULL) {
@@ -996,10 +1000,30 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 		 * cannot see a correct process name for those events.
 		 * Synthesize COMM event to prevent it.
 		 */
-		perf_event__synthesize_comm(tool, event,
-					    rec->evlist->workload.pid,
-					    process_synthesized_event,
-					    machine);
+		tgid = perf_event__synthesize_comm(tool, event,
+						   rec->evlist->workload.pid,
+						   process_synthesized_event,
+						   machine);
+		free(event);
+
+		if (tgid == -1)
+			goto out_child;
+
+		event = malloc(sizeof(event->namespaces) +
+			       (NR_NAMESPACES * sizeof(struct perf_ns_link_info)) +
+			       machine->id_hdr_size);
+		if (event == NULL) {
+			err = -ENOMEM;
+			goto out_child;
+		}
+
+		/*
+		 * Synthesize NAMESPACES event for the command specified.
+		 */
+		perf_event__synthesize_namespaces(tool, event,
+						  rec->evlist->workload.pid,
+						  tgid, process_synthesized_event,
+						  machine);
 		free(event);
 
 		perf_evlist__start_workload(rec->evlist);
@@ -1497,6 +1521,7 @@ static struct record record = {
 		.fork		= perf_event__process_fork,
 		.exit		= perf_event__process_exit,
 		.comm		= perf_event__process_comm,
+		.namespaces	= perf_event__process_namespaces,
 		.mmap		= perf_event__process_mmap,
 		.mmap2		= perf_event__process_mmap2,
 		.ordered_events	= true,
@@ -1611,6 +1636,8 @@ static struct option __record_options[] = {
 			  "opts", "AUX area tracing Snapshot Mode", ""),
 	OPT_UINTEGER(0, "proc-map-timeout", &record.opts.proc_map_timeout,
 			"per thread proc mmap processing timeout in ms"),
+	OPT_BOOLEAN(0, "namespaces", &record.opts.record_namespaces,
+		    "Record namespaces events"),
 	OPT_BOOLEAN(0, "switch-events", &record.opts.record_switch_events,
 		    "Record context switch events"),
 	OPT_BOOLEAN_FLAG(0, "all-kernel", &record.opts.all_kernel,
@@ -1640,7 +1667,7 @@ static struct option __record_options[] = {
 
 struct option *record_options = __record_options;
 
-int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_record(int argc, const char **argv)
 {
 	int err;
 	struct record *rec = &record;
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 0a88670e56f3..c18158b83eb1 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -394,8 +394,7 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist,
 		fprintf(stdout, "\n\n");
 	}
 
-	if (sort_order == NULL &&
-	    parent_pattern == default_parent_pattern)
+	if (!quiet)
 		fprintf(stdout, "#\n# (%s)\n#\n", help);
 
 	if (rep->show_threads) {
@@ -682,7 +681,7 @@ const char report_callchain_help[] = "Display call graph (stack chain/backtrace)
 				     CALLCHAIN_REPORT_HELP
 				     "\n\t\t\t\tDefault: " CALLCHAIN_DEFAULT_OPT;
 
-int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_report(int argc, const char **argv)
 {
 	struct perf_session *session;
 	struct itrace_synth_opts itrace_synth_opts = { .set = 0, };
@@ -701,6 +700,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 			.mmap		 = perf_event__process_mmap,
 			.mmap2		 = perf_event__process_mmap2,
 			.comm		 = perf_event__process_comm,
+			.namespaces	 = perf_event__process_namespaces,
 			.exit		 = perf_event__process_exit,
 			.fork		 = perf_event__process_fork,
 			.lost		 = perf_event__process_lost,
@@ -845,6 +845,8 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 			     stdio__config_color, "always"),
 	OPT_STRING(0, "time", &report.time_str, "str",
 		   "Time span of interest (start,stop)"),
+	OPT_BOOLEAN(0, "inline", &symbol_conf.inline_name,
+		    "Show inline function"),
 	OPT_END()
 	};
 	struct perf_data_file file = {
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index b94cf0de715a..79833e226789 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -221,6 +221,7 @@ struct perf_sched {
 	unsigned int	max_stack;
 	bool		show_cpu_visual;
 	bool		show_wakeups;
+	bool		show_next;
 	bool		show_migrations;
 	bool		show_state;
 	u64		skipped_samples;
@@ -1897,14 +1898,18 @@ static char task_state_char(struct thread *thread, int state)
 }
 
 static void timehist_print_sample(struct perf_sched *sched,
+				  struct perf_evsel *evsel,
 				  struct perf_sample *sample,
 				  struct addr_location *al,
 				  struct thread *thread,
 				  u64 t, int state)
 {
 	struct thread_runtime *tr = thread__priv(thread);
+	const char *next_comm = perf_evsel__strval(evsel, sample, "next_comm");
+	const u32 next_pid = perf_evsel__intval(evsel, sample, "next_pid");
 	u32 max_cpus = sched->max_cpu + 1;
 	char tstr[64];
+	char nstr[30];
 	u64 wait_time;
 
 	timestamp__scnprintf_usec(t, tstr, sizeof(tstr));
@@ -1937,7 +1942,12 @@ static void timehist_print_sample(struct perf_sched *sched,
 	if (sched->show_state)
 		printf(" %5c ", task_state_char(thread, state));
 
-	if (sched->show_wakeups)
+	if (sched->show_next) {
+		snprintf(nstr, sizeof(nstr), "next: %s[%d]", next_comm, next_pid);
+		printf(" %-*s", comm_width, nstr);
+	}
+
+	if (sched->show_wakeups && !sched->show_next)
 		printf("  %-*s", comm_width, "");
 
 	if (thread->tid == 0)
@@ -2531,7 +2541,7 @@ static int timehist_sched_change_event(struct perf_tool *tool,
 	}
 
 	if (!sched->summary_only)
-		timehist_print_sample(sched, sample, &al, thread, t, state);
+		timehist_print_sample(sched, evsel, sample, &al, thread, t, state);
 
 out:
 	if (sched->hist_time.start == 0 && t >= ptime->start)
@@ -3262,16 +3272,17 @@ static int __cmd_record(int argc, const char **argv)
 
 	BUG_ON(i != rec_argc);
 
-	return cmd_record(i, rec_argv, NULL);
+	return cmd_record(i, rec_argv);
 }
 
-int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_sched(int argc, const char **argv)
 {
 	const char default_sort_order[] = "avg, max, switch, runtime";
 	struct perf_sched sched = {
 		.tool = {
 			.sample		 = perf_sched__process_tracepoint_sample,
 			.comm		 = perf_event__process_comm,
+			.namespaces	 = perf_event__process_namespaces,
 			.lost		 = perf_event__process_lost,
 			.fork		 = perf_sched__process_fork_event,
 			.ordered_events = true,
@@ -3340,6 +3351,7 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused)
 	OPT_BOOLEAN('S', "with-summary", &sched.summary,
 		    "Show all syscalls and summary with statistics"),
 	OPT_BOOLEAN('w', "wakeups", &sched.show_wakeups, "Show wakeup events"),
+	OPT_BOOLEAN('n', "next", &sched.show_next, "Show next task"),
 	OPT_BOOLEAN('M', "migrations", &sched.show_migrations, "Show migration events"),
 	OPT_BOOLEAN('V', "cpu-visual", &sched.show_cpu_visual, "Add CPU visual"),
 	OPT_BOOLEAN('I', "idle-hist", &sched.idle_hist, "Show idle events only"),
@@ -3400,7 +3412,7 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused)
 	 * Aliased to 'perf script' for now:
 	 */
 	if (!strcmp(argv[0], "script"))
-		return cmd_script(argc, argv, prefix);
+		return cmd_script(argc, argv);
 
 	if (!strncmp(argv[0], "rec", 3)) {
 		return __cmd_record(argc, argv);
@@ -3437,10 +3449,14 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused)
 			if (argc)
 				usage_with_options(timehist_usage, timehist_options);
 		}
-		if (sched.show_wakeups && sched.summary_only) {
-			pr_err(" Error: -s and -w are mutually exclusive.\n");
+		if ((sched.show_wakeups || sched.show_next) &&
+		    sched.summary_only) {
+			pr_err(" Error: -s and -[n|w] are mutually exclusive.\n");
 			parse_options_usage(timehist_usage, timehist_options, "s", true);
-			parse_options_usage(NULL, timehist_options, "w", true);
+			if (sched.show_wakeups)
+				parse_options_usage(NULL, timehist_options, "w", true);
+			if (sched.show_next)
+				parse_options_usage(NULL, timehist_options, "n", true);
 			return -EINVAL;
 		}
 
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index c0783b4f7b6c..46acc8ece41f 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -28,6 +28,7 @@
 #include <linux/time64.h>
 #include "asm/bug.h"
 #include "util/mem-events.h"
+#include "util/dump-insn.h"
 
 static char const		*script_name;
 static char const		*generate_script_lang;
@@ -42,6 +43,7 @@ static bool			nanosecs;
 static const char		*cpu_list;
 static DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
 static struct perf_stat_config	stat_config;
+static int			max_blocks;
 
 unsigned int scripting_max_stack = PERF_MAX_STACK_DEPTH;
 
@@ -69,6 +71,7 @@ enum perf_output_field {
 	PERF_OUTPUT_CALLINDENT	    = 1U << 20,
 	PERF_OUTPUT_INSN	    = 1U << 21,
 	PERF_OUTPUT_INSNLEN	    = 1U << 22,
+	PERF_OUTPUT_BRSTACKINSN	    = 1U << 23,
 };
 
 struct output_option {
@@ -98,6 +101,7 @@ struct output_option {
 	{.str = "callindent", .field = PERF_OUTPUT_CALLINDENT},
 	{.str = "insn", .field = PERF_OUTPUT_INSN},
 	{.str = "insnlen", .field = PERF_OUTPUT_INSNLEN},
+	{.str = "brstackinsn", .field = PERF_OUTPUT_BRSTACKINSN},
 };
 
 /* default set to maintain compatibility with current format */
@@ -292,7 +296,13 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel,
 		       "selected. Hence, no address to lookup the source line number.\n");
 		return -EINVAL;
 	}
-
+	if (PRINT_FIELD(BRSTACKINSN) &&
+	    !(perf_evlist__combined_branch_type(session->evlist) &
+	      PERF_SAMPLE_BRANCH_ANY)) {
+		pr_err("Display of branch stack assembler requested, but non all-branch filter set\n"
+		       "Hint: run 'perf record -b ...'\n");
+		return -EINVAL;
+	}
 	if ((PRINT_FIELD(PID) || PRINT_FIELD(TID)) &&
 		perf_evsel__check_stype(evsel, PERF_SAMPLE_TID, "TID",
 					PERF_OUTPUT_TID|PERF_OUTPUT_PID))
@@ -546,6 +556,233 @@ static void print_sample_brstacksym(struct perf_sample *sample,
 	}
 }
 
+#define MAXBB 16384UL
+
+static int grab_bb(u8 *buffer, u64 start, u64 end,
+		    struct machine *machine, struct thread *thread,
+		    bool *is64bit, u8 *cpumode, bool last)
+{
+	long offset, len;
+	struct addr_location al;
+	bool kernel;
+
+	if (!start || !end)
+		return 0;
+
+	kernel = machine__kernel_ip(machine, start);
+	if (kernel)
+		*cpumode = PERF_RECORD_MISC_KERNEL;
+	else
+		*cpumode = PERF_RECORD_MISC_USER;
+
+	/*
+	 * Block overlaps between kernel and user.
+	 * This can happen due to ring filtering
+	 * On Intel CPUs the entry into the kernel is filtered,
+	 * but the exit is not. Let the caller patch it up.
+	 */
+	if (kernel != machine__kernel_ip(machine, end)) {
+		printf("\tblock %" PRIx64 "-%" PRIx64 " transfers between kernel and user\n",
+				start, end);
+		return -ENXIO;
+	}
+
+	memset(&al, 0, sizeof(al));
+	if (end - start > MAXBB - MAXINSN) {
+		if (last)
+			printf("\tbrstack does not reach to final jump (%" PRIx64 "-%" PRIx64 ")\n", start, end);
+		else
+			printf("\tblock %" PRIx64 "-%" PRIx64 " (%" PRIu64 ") too long to dump\n", start, end, end - start);
+		return 0;
+	}
+
+	thread__find_addr_map(thread, *cpumode, MAP__FUNCTION, start, &al);
+	if (!al.map || !al.map->dso) {
+		printf("\tcannot resolve %" PRIx64 "-%" PRIx64 "\n", start, end);
+		return 0;
+	}
+	if (al.map->dso->data.status == DSO_DATA_STATUS_ERROR) {
+		printf("\tcannot resolve %" PRIx64 "-%" PRIx64 "\n", start, end);
+		return 0;
+	}
+
+	/* Load maps to ensure dso->is_64_bit has been updated */
+	map__load(al.map);
+
+	offset = al.map->map_ip(al.map, start);
+	len = dso__data_read_offset(al.map->dso, machine, offset, (u8 *)buffer,
+				    end - start + MAXINSN);
+
+	*is64bit = al.map->dso->is_64_bit;
+	if (len <= 0)
+		printf("\tcannot fetch code for block at %" PRIx64 "-%" PRIx64 "\n",
+			start, end);
+	return len;
+}
+
+static void print_jump(uint64_t ip, struct branch_entry *en,
+		       struct perf_insn *x, u8 *inbuf, int len,
+		       int insn)
+{
+	printf("\t%016" PRIx64 "\t%-30s\t#%s%s%s%s",
+	       ip,
+	       dump_insn(x, ip, inbuf, len, NULL),
+	       en->flags.predicted ? " PRED" : "",
+	       en->flags.mispred ? " MISPRED" : "",
+	       en->flags.in_tx ? " INTX" : "",
+	       en->flags.abort ? " ABORT" : "");
+	if (en->flags.cycles) {
+		printf(" %d cycles", en->flags.cycles);
+		if (insn)
+			printf(" %.2f IPC", (float)insn / en->flags.cycles);
+	}
+	putchar('\n');
+}
+
+static void print_ip_sym(struct thread *thread, u8 cpumode, int cpu,
+			 uint64_t addr, struct symbol **lastsym,
+			 struct perf_event_attr *attr)
+{
+	struct addr_location al;
+	int off;
+
+	memset(&al, 0, sizeof(al));
+
+	thread__find_addr_map(thread, cpumode, MAP__FUNCTION, addr, &al);
+	if (!al.map)
+		thread__find_addr_map(thread, cpumode, MAP__VARIABLE,
+				      addr, &al);
+	if ((*lastsym) && al.addr >= (*lastsym)->start && al.addr < (*lastsym)->end)
+		return;
+
+	al.cpu = cpu;
+	al.sym = NULL;
+	if (al.map)
+		al.sym = map__find_symbol(al.map, al.addr);
+
+	if (!al.sym)
+		return;
+
+	if (al.addr < al.sym->end)
+		off = al.addr - al.sym->start;
+	else
+		off = al.addr - al.map->start - al.sym->start;
+	printf("\t%s", al.sym->name);
+	if (off)
+		printf("%+d", off);
+	putchar(':');
+	if (PRINT_FIELD(SRCLINE))
+		map__fprintf_srcline(al.map, al.addr, "\t", stdout);
+	putchar('\n');
+	*lastsym = al.sym;
+}
+
+static void print_sample_brstackinsn(struct perf_sample *sample,
+				     struct thread *thread,
+				     struct perf_event_attr *attr,
+				     struct machine *machine)
+{
+	struct branch_stack *br = sample->branch_stack;
+	u64 start, end;
+	int i, insn, len, nr, ilen;
+	struct perf_insn x;
+	u8 buffer[MAXBB];
+	unsigned off;
+	struct symbol *lastsym = NULL;
+
+	if (!(br && br->nr))
+		return;
+	nr = br->nr;
+	if (max_blocks && nr > max_blocks + 1)
+		nr = max_blocks + 1;
+
+	x.thread = thread;
+	x.cpu = sample->cpu;
+
+	putchar('\n');
+
+	/* Handle first from jump, of which we don't know the entry. */
+	len = grab_bb(buffer, br->entries[nr-1].from,
+			br->entries[nr-1].from,
+			machine, thread, &x.is64bit, &x.cpumode, false);
+	if (len > 0) {
+		print_ip_sym(thread, x.cpumode, x.cpu,
+			     br->entries[nr - 1].from, &lastsym, attr);
+		print_jump(br->entries[nr - 1].from, &br->entries[nr - 1],
+			    &x, buffer, len, 0);
+	}
+
+	/* Print all blocks */
+	for (i = nr - 2; i >= 0; i--) {
+		if (br->entries[i].from || br->entries[i].to)
+			pr_debug("%d: %" PRIx64 "-%" PRIx64 "\n", i,
+				 br->entries[i].from,
+				 br->entries[i].to);
+		start = br->entries[i + 1].to;
+		end   = br->entries[i].from;
+
+		len = grab_bb(buffer, start, end, machine, thread, &x.is64bit, &x.cpumode, false);
+		/* Patch up missing kernel transfers due to ring filters */
+		if (len == -ENXIO && i > 0) {
+			end = br->entries[--i].from;
+			pr_debug("\tpatching up to %" PRIx64 "-%" PRIx64 "\n", start, end);
+			len = grab_bb(buffer, start, end, machine, thread, &x.is64bit, &x.cpumode, false);
+		}
+		if (len <= 0)
+			continue;
+
+		insn = 0;
+		for (off = 0;; off += ilen) {
+			uint64_t ip = start + off;
+
+			print_ip_sym(thread, x.cpumode, x.cpu, ip, &lastsym, attr);
+			if (ip == end) {
+				print_jump(ip, &br->entries[i], &x, buffer + off, len - off, insn);
+				break;
+			} else {
+				printf("\t%016" PRIx64 "\t%s\n", ip,
+					dump_insn(&x, ip, buffer + off, len - off, &ilen));
+				if (ilen == 0)
+					break;
+				insn++;
+			}
+		}
+	}
+
+	/*
+	 * Hit the branch? In this case we are already done, and the target
+	 * has not been executed yet.
+	 */
+	if (br->entries[0].from == sample->ip)
+		return;
+	if (br->entries[0].flags.abort)
+		return;
+
+	/*
+	 * Print final block upto sample
+	 */
+	start = br->entries[0].to;
+	end = sample->ip;
+	len = grab_bb(buffer, start, end, machine, thread, &x.is64bit, &x.cpumode, true);
+	print_ip_sym(thread, x.cpumode, x.cpu, start, &lastsym, attr);
+	if (len <= 0) {
+		/* Print at least last IP if basic block did not work */
+		len = grab_bb(buffer, sample->ip, sample->ip,
+			      machine, thread, &x.is64bit, &x.cpumode, false);
+		if (len <= 0)
+			return;
+
+		printf("\t%016" PRIx64 "\t%s\n", sample->ip,
+			dump_insn(&x, sample->ip, buffer, len, NULL));
+		return;
+	}
+	for (off = 0; off <= end - start; off += ilen) {
+		printf("\t%016" PRIx64 "\t%s\n", start + off,
+			dump_insn(&x, start + off, buffer + off, len - off, &ilen));
+		if (ilen == 0)
+			break;
+	}
+}
 
 static void print_sample_addr(struct perf_sample *sample,
 			  struct thread *thread,
@@ -632,7 +869,9 @@ static void print_sample_callindent(struct perf_sample *sample,
 }
 
 static void print_insn(struct perf_sample *sample,
-		       struct perf_event_attr *attr)
+		       struct perf_event_attr *attr,
+		       struct thread *thread,
+		       struct machine *machine)
 {
 	if (PRINT_FIELD(INSNLEN))
 		printf(" ilen: %d", sample->insn_len);
@@ -643,12 +882,15 @@ static void print_insn(struct perf_sample *sample,
 		for (i = 0; i < sample->insn_len; i++)
 			printf(" %02x", (unsigned char)sample->insn[i]);
 	}
+	if (PRINT_FIELD(BRSTACKINSN))
+		print_sample_brstackinsn(sample, thread, attr, machine);
 }
 
 static void print_sample_bts(struct perf_sample *sample,
 			     struct perf_evsel *evsel,
 			     struct thread *thread,
-			     struct addr_location *al)
+			     struct addr_location *al,
+			     struct machine *machine)
 {
 	struct perf_event_attr *attr = &evsel->attr;
 	bool print_srcline_last = false;
@@ -689,7 +931,7 @@ static void print_sample_bts(struct perf_sample *sample,
 	if (print_srcline_last)
 		map__fprintf_srcline(al->map, al->addr, "\n  ", stdout);
 
-	print_insn(sample, attr);
+	print_insn(sample, attr, thread, machine);
 
 	printf("\n");
 }
@@ -830,6 +1072,7 @@ struct perf_script {
 	bool			show_task_events;
 	bool			show_mmap_events;
 	bool			show_switch_events;
+	bool			show_namespace_events;
 	bool			allocated;
 	struct cpu_map		*cpus;
 	struct thread_map	*threads;
@@ -871,7 +1114,8 @@ static size_t data_src__printf(u64 data_src)
 
 static void process_event(struct perf_script *script,
 			  struct perf_sample *sample, struct perf_evsel *evsel,
-			  struct addr_location *al)
+			  struct addr_location *al,
+			  struct machine *machine)
 {
 	struct thread *thread = al->thread;
 	struct perf_event_attr *attr = &evsel->attr;
@@ -898,7 +1142,7 @@ static void process_event(struct perf_script *script,
 		print_sample_flags(sample->flags);
 
 	if (is_bts_event(attr)) {
-		print_sample_bts(sample, evsel, thread, al);
+		print_sample_bts(sample, evsel, thread, al, machine);
 		return;
 	}
 
@@ -936,7 +1180,7 @@ static void process_event(struct perf_script *script,
 
 	if (perf_evsel__is_bpf_output(evsel) && PRINT_FIELD(BPF_OUTPUT))
 		print_sample_bpf_output(sample);
-	print_insn(sample, attr);
+	print_insn(sample, attr, thread, machine);
 	printf("\n");
 }
 
@@ -1046,7 +1290,7 @@ static int process_sample_event(struct perf_tool *tool,
 	if (scripting_ops)
 		scripting_ops->process_event(event, sample, evsel, &al);
 	else
-		process_event(scr, sample, evsel, &al);
+		process_event(scr, sample, evsel, &al, machine);
 
 out_put:
 	addr_location__put(&al);
@@ -1118,6 +1362,41 @@ out:
 	return ret;
 }
 
+static int process_namespaces_event(struct perf_tool *tool,
+				    union perf_event *event,
+				    struct perf_sample *sample,
+				    struct machine *machine)
+{
+	struct thread *thread;
+	struct perf_script *script = container_of(tool, struct perf_script, tool);
+	struct perf_session *session = script->session;
+	struct perf_evsel *evsel = perf_evlist__id2evsel(session->evlist, sample->id);
+	int ret = -1;
+
+	thread = machine__findnew_thread(machine, event->namespaces.pid,
+					 event->namespaces.tid);
+	if (thread == NULL) {
+		pr_debug("problem processing NAMESPACES event, skipping it.\n");
+		return -1;
+	}
+
+	if (perf_event__process_namespaces(tool, event, sample, machine) < 0)
+		goto out;
+
+	if (!evsel->attr.sample_id_all) {
+		sample->cpu = 0;
+		sample->time = 0;
+		sample->tid = event->namespaces.tid;
+		sample->pid = event->namespaces.pid;
+	}
+	print_sample_start(sample, thread, evsel);
+	perf_event__fprintf(event, stdout);
+	ret = 0;
+out:
+	thread__put(thread);
+	return ret;
+}
+
 static int process_fork_event(struct perf_tool *tool,
 			      union perf_event *event,
 			      struct perf_sample *sample,
@@ -1293,6 +1572,8 @@ static int __cmd_script(struct perf_script *script)
 	}
 	if (script->show_switch_events)
 		script->tool.context_switch = process_switch_event;
+	if (script->show_namespace_events)
+		script->tool.namespaces = process_namespaces_event;
 
 	ret = perf_session__process_events(script->session);
 
@@ -2078,7 +2359,7 @@ int process_cpu_map_event(struct perf_tool *tool __maybe_unused,
 	return set_maps(script);
 }
 
-int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_script(int argc, const char **argv)
 {
 	bool show_full_info = false;
 	bool header = false;
@@ -2097,6 +2378,7 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 			.mmap		 = perf_event__process_mmap,
 			.mmap2		 = perf_event__process_mmap2,
 			.comm		 = perf_event__process_comm,
+			.namespaces	 = perf_event__process_namespaces,
 			.exit		 = perf_event__process_exit,
 			.fork		 = perf_event__process_fork,
 			.attr		 = process_attr,
@@ -2152,7 +2434,8 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 		     "Valid types: hw,sw,trace,raw. "
 		     "Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso,"
 		     "addr,symoff,period,iregs,brstack,brstacksym,flags,"
-		     "bpf-output,callindent,insn,insnlen", parse_output_fields),
+		     "bpf-output,callindent,insn,insnlen,brstackinsn",
+		     parse_output_fields),
 	OPT_BOOLEAN('a', "all-cpus", &system_wide,
 		    "system-wide collection from all CPUs"),
 	OPT_STRING('S', "symbols", &symbol_conf.sym_list_str, "symbol[,symbol...]",
@@ -2180,7 +2463,11 @@ 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('\0', "show-namespace-events", &script.show_namespace_events,
+		    "Show namespace events (if recorded)"),
 	OPT_BOOLEAN('f', "force", &symbol_conf.force, "don't complain, do it"),
+	OPT_INTEGER(0, "max-blocks", &max_blocks,
+		    "Maximum number of code blocks to dump with brstackinsn"),
 	OPT_BOOLEAN(0, "ns", &nanosecs,
 		    "Use 9 decimal places when displaying time"),
 	OPT_CALLBACK_OPTARG(0, "itrace", &itrace_synth_opts, NULL, "opts",
@@ -2217,7 +2504,7 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 	if (argc > 1 && !strncmp(argv[0], "rec", strlen("rec"))) {
 		rec_script_path = get_script_path(argv[1], RECORD_SUFFIX);
 		if (!rec_script_path)
-			return cmd_record(argc, argv, NULL);
+			return cmd_record(argc, argv);
 	}
 
 	if (argc > 1 && !strncmp(argv[0], "rep", strlen("rep"))) {
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 13b54999ad79..2158ea14da57 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -140,12 +140,14 @@ static unsigned int		unit_width			= 4; /* strlen("unit") */
 static bool			forever				= false;
 static bool			metric_only			= false;
 static bool			force_metric_only		= false;
+static bool			no_merge			= false;
 static struct timespec		ref_time;
 static struct cpu_map		*aggr_map;
 static aggr_get_id_t		aggr_get_id;
 static bool			append_file;
 static const char		*output_name;
 static int			output_fd;
+static int			print_free_counters_hint;
 
 struct perf_stat {
 	bool			 record;
@@ -1109,6 +1111,9 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval,
 			counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED,
 			csv_sep);
 
+		if (counter->supported)
+			print_free_counters_hint = 1;
+
 		fprintf(stat_config.output, "%-*s%s",
 			csv_output ? 0 : unit_width,
 			counter->unit, csv_sep);
@@ -1140,6 +1145,7 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval,
 	out.print_metric = pm;
 	out.new_line = nl;
 	out.ctx = &os;
+	out.force_header = false;
 
 	if (csv_output && !metric_only) {
 		print_noise(counter, noise);
@@ -1178,11 +1184,81 @@ static void aggr_update_shadow(void)
 	}
 }
 
+static void collect_all_aliases(struct perf_evsel *counter,
+			    void (*cb)(struct perf_evsel *counter, void *data,
+				       bool first),
+			    void *data)
+{
+	struct perf_evsel *alias;
+
+	alias = list_prepare_entry(counter, &(evsel_list->entries), node);
+	list_for_each_entry_continue (alias, &evsel_list->entries, node) {
+		if (strcmp(perf_evsel__name(alias), perf_evsel__name(counter)) ||
+		    alias->scale != counter->scale ||
+		    alias->cgrp != counter->cgrp ||
+		    strcmp(alias->unit, counter->unit) ||
+		    nsec_counter(alias) != nsec_counter(counter))
+			break;
+		alias->merged_stat = true;
+		cb(alias, data, false);
+	}
+}
+
+static bool collect_data(struct perf_evsel *counter,
+			    void (*cb)(struct perf_evsel *counter, void *data,
+				       bool first),
+			    void *data)
+{
+	if (counter->merged_stat)
+		return false;
+	cb(counter, data, true);
+	if (!no_merge)
+		collect_all_aliases(counter, cb, data);
+	return true;
+}
+
+struct aggr_data {
+	u64 ena, run, val;
+	int id;
+	int nr;
+	int cpu;
+};
+
+static void aggr_cb(struct perf_evsel *counter, void *data, bool first)
+{
+	struct aggr_data *ad = data;
+	int cpu, s2;
+
+	for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
+		struct perf_counts_values *counts;
+
+		s2 = aggr_get_id(perf_evsel__cpus(counter), cpu);
+		if (s2 != ad->id)
+			continue;
+		if (first)
+			ad->nr++;
+		counts = perf_counts(counter->counts, cpu, 0);
+		/*
+		 * When any result is bad, make them all to give
+		 * consistent output in interval mode.
+		 */
+		if (counts->ena == 0 || counts->run == 0 ||
+		    counter->counts->scaled == -1) {
+			ad->ena = 0;
+			ad->run = 0;
+			break;
+		}
+		ad->val += counts->val;
+		ad->ena += counts->ena;
+		ad->run += counts->run;
+	}
+}
+
 static void print_aggr(char *prefix)
 {
 	FILE *output = stat_config.output;
 	struct perf_evsel *counter;
-	int cpu, s, s2, id, nr;
+	int s, id, nr;
 	double uval;
 	u64 ena, run, val;
 	bool first;
@@ -1197,23 +1273,21 @@ static void print_aggr(char *prefix)
 	 * Without each counter has its own line.
 	 */
 	for (s = 0; s < aggr_map->nr; s++) {
+		struct aggr_data ad;
 		if (prefix && metric_only)
 			fprintf(output, "%s", prefix);
 
-		id = aggr_map->map[s];
+		ad.id = id = aggr_map->map[s];
 		first = true;
 		evlist__for_each_entry(evsel_list, counter) {
-			val = ena = run = 0;
-			nr = 0;
-			for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
-				s2 = aggr_get_id(perf_evsel__cpus(counter), cpu);
-				if (s2 != id)
-					continue;
-				val += perf_counts(counter->counts, cpu, 0)->val;
-				ena += perf_counts(counter->counts, cpu, 0)->ena;
-				run += perf_counts(counter->counts, cpu, 0)->run;
-				nr++;
-			}
+			ad.val = ad.ena = ad.run = 0;
+			ad.nr = 0;
+			if (!collect_data(counter, aggr_cb, &ad))
+				continue;
+			nr = ad.nr;
+			ena = ad.ena;
+			run = ad.run;
+			val = ad.val;
 			if (first && metric_only) {
 				first = false;
 				aggr_printout(counter, id, nr);
@@ -1257,6 +1331,21 @@ static void print_aggr_thread(struct perf_evsel *counter, char *prefix)
 	}
 }
 
+struct caggr_data {
+	double avg, avg_enabled, avg_running;
+};
+
+static void counter_aggr_cb(struct perf_evsel *counter, void *data,
+			    bool first __maybe_unused)
+{
+	struct caggr_data *cd = data;
+	struct perf_stat_evsel *ps = counter->priv;
+
+	cd->avg += avg_stats(&ps->res_stats[0]);
+	cd->avg_enabled += avg_stats(&ps->res_stats[1]);
+	cd->avg_running += avg_stats(&ps->res_stats[2]);
+}
+
 /*
  * Print out the results of a single counter:
  * aggregated counts in system-wide mode
@@ -1264,23 +1353,31 @@ static void print_aggr_thread(struct perf_evsel *counter, char *prefix)
 static void print_counter_aggr(struct perf_evsel *counter, char *prefix)
 {
 	FILE *output = stat_config.output;
-	struct perf_stat_evsel *ps = counter->priv;
-	double avg = avg_stats(&ps->res_stats[0]);
 	double uval;
-	double avg_enabled, avg_running;
+	struct caggr_data cd = { .avg = 0.0 };
 
-	avg_enabled = avg_stats(&ps->res_stats[1]);
-	avg_running = avg_stats(&ps->res_stats[2]);
+	if (!collect_data(counter, counter_aggr_cb, &cd))
+		return;
 
 	if (prefix && !metric_only)
 		fprintf(output, "%s", prefix);
 
-	uval = avg * counter->scale;
-	printout(-1, 0, counter, uval, prefix, avg_running, avg_enabled, avg);
+	uval = cd.avg * counter->scale;
+	printout(-1, 0, counter, uval, prefix, cd.avg_running, cd.avg_enabled, cd.avg);
 	if (!metric_only)
 		fprintf(output, "\n");
 }
 
+static void counter_cb(struct perf_evsel *counter, void *data,
+		       bool first __maybe_unused)
+{
+	struct aggr_data *ad = data;
+
+	ad->val += perf_counts(counter->counts, ad->cpu, 0)->val;
+	ad->ena += perf_counts(counter->counts, ad->cpu, 0)->ena;
+	ad->run += perf_counts(counter->counts, ad->cpu, 0)->run;
+}
+
 /*
  * Print out the results of a single counter:
  * does not use aggregated count in system-wide
@@ -1293,9 +1390,13 @@ static void print_counter(struct perf_evsel *counter, char *prefix)
 	int cpu;
 
 	for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
-		val = perf_counts(counter->counts, cpu, 0)->val;
-		ena = perf_counts(counter->counts, cpu, 0)->ena;
-		run = perf_counts(counter->counts, cpu, 0)->run;
+		struct aggr_data ad = { .cpu = cpu };
+
+		if (!collect_data(counter, counter_cb, &ad))
+			return;
+		val = ad.val;
+		ena = ad.ena;
+		run = ad.run;
 
 		if (prefix)
 			fprintf(output, "%s", prefix);
@@ -1380,6 +1481,7 @@ static void print_metric_headers(const char *prefix, bool no_indent)
 		out.ctx = &os;
 		out.print_metric = print_metric_header;
 		out.new_line = new_line_metric;
+		out.force_header = true;
 		os.evsel = counter;
 		perf_stat__print_shadow_stats(counter, 0,
 					      0,
@@ -1477,6 +1579,13 @@ static void print_footer(void)
 				avg_stats(&walltime_nsecs_stats));
 	}
 	fprintf(output, "\n\n");
+
+	if (print_free_counters_hint)
+		fprintf(output,
+"Some events weren't counted. Try disabling the NMI watchdog:\n"
+"	echo 0 > /proc/sys/kernel/nmi_watchdog\n"
+"	perf stat ...\n"
+"	echo 1 > /proc/sys/kernel/nmi_watchdog\n");
 }
 
 static void print_counters(struct timespec *ts, int argc, const char **argv)
@@ -1633,6 +1742,7 @@ static const struct option stat_options[] = {
 		    "list of cpus to monitor in system-wide"),
 	OPT_SET_UINT('A', "no-aggr", &stat_config.aggr_mode,
 		    "disable CPU count aggregation", AGGR_NONE),
+	OPT_BOOLEAN(0, "no-merge", &no_merge, "Do not merge identical named events"),
 	OPT_STRING('x', "field-separator", &csv_sep, "separator",
 		   "print counts with custom separator"),
 	OPT_CALLBACK('G', "cgroup", &evsel_list, "name",
@@ -2339,7 +2449,36 @@ static int __cmd_report(int argc, const char **argv)
 	return 0;
 }
 
-int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
+static void setup_system_wide(int forks)
+{
+	/*
+	 * Make system wide (-a) the default target if
+	 * no target was specified and one of following
+	 * conditions is met:
+	 *
+	 *   - there's no workload specified
+	 *   - there is workload specified but all requested
+	 *     events are system wide events
+	 */
+	if (!target__none(&target))
+		return;
+
+	if (!forks)
+		target.system_wide = true;
+	else {
+		struct perf_evsel *counter;
+
+		evlist__for_each_entry(evsel_list, counter) {
+			if (!counter->system_wide)
+				return;
+		}
+
+		if (evsel_list->nr_entries)
+			target.system_wide = true;
+	}
+}
+
+int cmd_stat(int argc, const char **argv)
 {
 	const char * const stat_usage[] = {
 		"perf stat [<options>] [<command>]",
@@ -2361,6 +2500,7 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 	argc = parse_options_subcommand(argc, argv, stat_options, stat_subcommands,
 					(const char **) stat_usage,
 					PARSE_OPT_STOP_AT_NON_OPTION);
+	perf_stat__collect_metric_expr(evsel_list);
 	perf_stat__init_shadow_stats();
 
 	if (csv_sep) {
@@ -2445,9 +2585,7 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 	} else if (big_num_opt == 0) /* User passed --no-big-num */
 		big_num = false;
 
-	/* Make system wide (-a) the default target. */
-	if (!argc && target__none(&target))
-		target.system_wide = true;
+	setup_system_wide(argc);
 
 	if (run_count < 0) {
 		pr_err("Run count must be a positive number\n");
diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index e7eaa298d34a..fafdb44b8bcb 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -1773,7 +1773,7 @@ static int timechart__io_record(int argc, const char **argv)
 	for (i = 0; i < (unsigned int)argc; i++)
 		*p++ = argv[i];
 
-	return cmd_record(rec_argc, rec_argv, NULL);
+	return cmd_record(rec_argc, rec_argv);
 }
 
 
@@ -1864,7 +1864,7 @@ static int timechart__record(struct timechart *tchart, int argc, const char **ar
 	for (j = 0; j < (unsigned int)argc; j++)
 		*p++ = argv[j];
 
-	return cmd_record(rec_argc, rec_argv, NULL);
+	return cmd_record(rec_argc, rec_argv);
 }
 
 static int
@@ -1917,8 +1917,7 @@ parse_time(const struct option *opt, const char *arg, int __maybe_unused unset)
 	return 0;
 }
 
-int cmd_timechart(int argc, const char **argv,
-		  const char *prefix __maybe_unused)
+int cmd_timechart(int argc, const char **argv)
 {
 	struct timechart tchart = {
 		.tool = {
@@ -1933,6 +1932,11 @@ int cmd_timechart(int argc, const char **argv,
 		.merge_dist = 1000,
 	};
 	const char *output_name = "output.svg";
+	const struct option timechart_common_options[] = {
+	OPT_BOOLEAN('P', "power-only", &tchart.power_only, "output power data only"),
+	OPT_BOOLEAN('T', "tasks-only", &tchart.tasks_only, "output processes data only"),
+	OPT_END()
+	};
 	const struct option timechart_options[] = {
 	OPT_STRING('i', "input", &input_name, "file", "input file name"),
 	OPT_STRING('o', "output", &output_name, "file", "output file name"),
@@ -1940,9 +1944,6 @@ int cmd_timechart(int argc, const char **argv,
 	OPT_CALLBACK(0, "highlight", NULL, "duration or task name",
 		      "highlight tasks. Pass duration in ns or process name.",
 		       parse_highlight),
-	OPT_BOOLEAN('P', "power-only", &tchart.power_only, "output power data only"),
-	OPT_BOOLEAN('T', "tasks-only", &tchart.tasks_only,
-		    "output processes data only"),
 	OPT_CALLBACK('p', "process", NULL, "process",
 		      "process selector. Pass a pid or process name.",
 		       parse_process),
@@ -1962,22 +1963,18 @@ int cmd_timechart(int argc, const char **argv,
 		     "merge events that are merge-dist us apart",
 		     parse_time),
 	OPT_BOOLEAN('f', "force", &tchart.force, "don't complain, do it"),
-	OPT_END()
+	OPT_PARENT(timechart_common_options),
 	};
 	const char * const timechart_subcommands[] = { "record", NULL };
 	const char *timechart_usage[] = {
 		"perf timechart [<options>] {record}",
 		NULL
 	};
-
 	const struct option timechart_record_options[] = {
-	OPT_BOOLEAN('P', "power-only", &tchart.power_only, "output power data only"),
-	OPT_BOOLEAN('T', "tasks-only", &tchart.tasks_only,
-		    "output processes data only"),
 	OPT_BOOLEAN('I', "io-only", &tchart.io_only,
 		    "record only IO data"),
 	OPT_BOOLEAN('g', "callchain", &tchart.with_backtrace, "record callchain"),
-	OPT_END()
+	OPT_PARENT(timechart_common_options),
 	};
 	const char * const timechart_record_usage[] = {
 		"perf timechart record [<options>]",
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index ab9077915763..a0c97c70ec81 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -1075,7 +1075,7 @@ parse_percent_limit(const struct option *opt, const char *arg,
 const char top_callchain_help[] = CALLCHAIN_RECORD_HELP CALLCHAIN_REPORT_HELP
 	"\n\t\t\t\tDefault: fp,graph,0.5,caller,function";
 
-int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_top(int argc, const char **argv)
 {
 	char errbuf[BUFSIZ];
 	struct perf_top top = {
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 256f1fac6f7e..fce278d5fada 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -31,6 +31,7 @@
 #include "util/intlist.h"
 #include "util/thread_map.h"
 #include "util/stat.h"
+#include "trace/beauty/beauty.h"
 #include "trace-event.h"
 #include "util/parse-events.h"
 #include "util/bpf-loader.h"
@@ -267,15 +268,6 @@ out_delete:
 	({ struct syscall_tp *fields = evsel->priv; \
 	   fields->name.pointer(&fields->name, sample); })
 
-struct syscall_arg {
-	unsigned long val;
-	struct thread *thread;
-	struct trace  *trace;
-	void	      *parm;
-	u8	      idx;
-	u8	      mask;
-};
-
 struct strarray {
 	int	    offset;
 	int	    nr_entries;
@@ -771,6 +763,10 @@ static struct syscall_fmt {
 	  .arg_parm	 = { [0] = &strarray__socket_families, /* family */ }, },
 	{ .name	    = "stat",	    .errmsg = true, .alias = "newstat", },
 	{ .name	    = "statfs",	    .errmsg = true, },
+	{ .name	    = "statx",	    .errmsg = true,
+	  .arg_scnprintf = { [0] = SCA_FDAT, /* flags */
+			     [2] = SCA_STATX_FLAGS, /* flags */
+			     [3] = SCA_STATX_MASK, /* mask */ }, },
 	{ .name	    = "swapoff",    .errmsg = true,
 	  .arg_scnprintf = { [0] = SCA_FILENAME, /* specialfile */ }, },
 	{ .name	    = "swapon",	    .errmsg = true,
@@ -821,12 +817,21 @@ struct syscall {
 	void		    **arg_parm;
 };
 
-static size_t fprintf_duration(unsigned long t, FILE *fp)
+/*
+ * We need to have this 'calculated' boolean because in some cases we really
+ * don't know what is the duration of a syscall, for instance, when we start
+ * a session and some threads are waiting for a syscall to finish, say 'poll',
+ * in which case all we can do is to print "( ? ) for duration and for the
+ * start timestamp.
+ */
+static size_t fprintf_duration(unsigned long t, bool calculated, FILE *fp)
 {
 	double duration = (double)t / NSEC_PER_MSEC;
 	size_t printed = fprintf(fp, "(");
 
-	if (duration >= 1.0)
+	if (!calculated)
+		printed += fprintf(fp, "     ?   ");
+	else if (duration >= 1.0)
 		printed += color_fprintf(fp, PERF_COLOR_RED, "%6.3f ms", duration);
 	else if (duration >= 0.01)
 		printed += color_fprintf(fp, PERF_COLOR_YELLOW, "%6.3f ms", duration);
@@ -1028,13 +1033,27 @@ static bool trace__filter_duration(struct trace *trace, double t)
 	return t < (trace->duration_filter * NSEC_PER_MSEC);
 }
 
-static size_t trace__fprintf_tstamp(struct trace *trace, u64 tstamp, FILE *fp)
+static size_t __trace__fprintf_tstamp(struct trace *trace, u64 tstamp, FILE *fp)
 {
 	double ts = (double)(tstamp - trace->base_time) / NSEC_PER_MSEC;
 
 	return fprintf(fp, "%10.3f ", ts);
 }
 
+/*
+ * We're handling tstamp=0 as an undefined tstamp, i.e. like when we are
+ * using ttrace->entry_time for a thread that receives a sys_exit without
+ * first having received a sys_enter ("poll" issued before tracing session
+ * starts, lost sys_enter exit due to ring buffer overflow).
+ */
+static size_t trace__fprintf_tstamp(struct trace *trace, u64 tstamp, FILE *fp)
+{
+	if (tstamp > 0)
+		return __trace__fprintf_tstamp(trace, tstamp, fp);
+
+	return fprintf(fp, "         ? ");
+}
+
 static bool done = false;
 static bool interrupted = false;
 
@@ -1045,10 +1064,10 @@ static void sig_handler(int sig)
 }
 
 static size_t trace__fprintf_entry_head(struct trace *trace, struct thread *thread,
-					u64 duration, u64 tstamp, FILE *fp)
+					u64 duration, bool duration_calculated, u64 tstamp, FILE *fp)
 {
 	size_t printed = trace__fprintf_tstamp(trace, tstamp, fp);
-	printed += fprintf_duration(duration, fp);
+	printed += fprintf_duration(duration, duration_calculated, fp);
 
 	if (trace->multiple_threads) {
 		if (trace->show_comm)
@@ -1450,7 +1469,7 @@ static int trace__printf_interrupted_entry(struct trace *trace, struct perf_samp
 
 	duration = sample->time - ttrace->entry_time;
 
-	printed  = trace__fprintf_entry_head(trace, trace->current, duration, ttrace->entry_time, trace->output);
+	printed  = trace__fprintf_entry_head(trace, trace->current, duration, true, ttrace->entry_time, trace->output);
 	printed += fprintf(trace->output, "%-70s) ...\n", ttrace->entry_str);
 	ttrace->entry_pending = false;
 
@@ -1497,7 +1516,7 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel,
 
 	if (sc->is_exit) {
 		if (!(trace->duration_filter || trace->summary_only || trace->min_stack)) {
-			trace__fprintf_entry_head(trace, thread, 1, ttrace->entry_time, trace->output);
+			trace__fprintf_entry_head(trace, thread, 0, false, ttrace->entry_time, trace->output);
 			fprintf(trace->output, "%-70s)\n", ttrace->entry_str);
 		}
 	} else {
@@ -1545,6 +1564,7 @@ static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel,
 {
 	long ret;
 	u64 duration = 0;
+	bool duration_calculated = false;
 	struct thread *thread;
 	int id = perf_evsel__sc_tp_uint(evsel, id, sample), err = -1, callchain_ret = 0;
 	struct syscall *sc = trace__syscall_info(trace, evsel, id);
@@ -1573,6 +1593,7 @@ static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel,
 		duration = sample->time - ttrace->entry_time;
 		if (trace__filter_duration(trace, duration))
 			goto out;
+		duration_calculated = true;
 	} else if (trace->duration_filter)
 		goto out;
 
@@ -1588,7 +1609,7 @@ static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel,
 	if (trace->summary_only)
 		goto out;
 
-	trace__fprintf_entry_head(trace, thread, duration, ttrace->entry_time, trace->output);
+	trace__fprintf_entry_head(trace, thread, duration, duration_calculated, ttrace->entry_time, trace->output);
 
 	if (ttrace->entry_pending) {
 		fprintf(trace->output, "%-70s", ttrace->entry_str);
@@ -1653,15 +1674,17 @@ static int trace__vfs_getname(struct trace *trace, struct perf_evsel *evsel,
 
 	ttrace = thread__priv(thread);
 	if (!ttrace)
-		goto out;
+		goto out_put;
 
 	filename_len = strlen(filename);
+	if (filename_len == 0)
+		goto out_put;
 
 	if (ttrace->filename.namelen < filename_len) {
 		char *f = realloc(ttrace->filename.name, filename_len + 1);
 
 		if (f == NULL)
-				goto out;
+			goto out_put;
 
 		ttrace->filename.namelen = filename_len;
 		ttrace->filename.name = f;
@@ -1671,12 +1694,12 @@ static int trace__vfs_getname(struct trace *trace, struct perf_evsel *evsel,
 	ttrace->filename.pending_open = true;
 
 	if (!ttrace->filename.ptr)
-		goto out;
+		goto out_put;
 
 	entry_str_len = strlen(ttrace->entry_str);
 	remaining_space = trace__entry_str_size - entry_str_len - 1; /* \0 */
 	if (remaining_space <= 0)
-		goto out;
+		goto out_put;
 
 	if (filename_len > (size_t)remaining_space) {
 		filename += filename_len - remaining_space;
@@ -1690,6 +1713,8 @@ static int trace__vfs_getname(struct trace *trace, struct perf_evsel *evsel,
 
 	ttrace->filename.ptr = 0;
 	ttrace->filename.entry_str_pos = 0;
+out_put:
+	thread__put(thread);
 out:
 	return 0;
 }
@@ -1710,6 +1735,7 @@ static int trace__sched_stat_runtime(struct trace *trace, struct perf_evsel *evs
 
 	ttrace->runtime_ms += runtime_ms;
 	trace->runtime_ms += runtime_ms;
+out_put:
 	thread__put(thread);
 	return 0;
 
@@ -1720,8 +1746,7 @@ out_dump:
 	       (pid_t)perf_evsel__intval(evsel, sample, "pid"),
 	       runtime,
 	       perf_evsel__intval(evsel, sample, "vruntime"));
-	thread__put(thread);
-	return 0;
+	goto out_put;
 }
 
 static void bpf_output__printer(enum binary_printer_ops op,
@@ -1851,7 +1876,7 @@ static int trace__pgfault(struct trace *trace,
 	thread__find_addr_location(thread, sample->cpumode, MAP__FUNCTION,
 			      sample->ip, &al);
 
-	trace__fprintf_entry_head(trace, thread, 0, sample->time, trace->output);
+	trace__fprintf_entry_head(trace, thread, 0, true, sample->time, trace->output);
 
 	fprintf(trace->output, "%sfault [",
 		evsel->attr.config == PERF_COUNT_SW_PAGE_FAULTS_MAJ ?
@@ -1920,7 +1945,7 @@ static int trace__process_sample(struct perf_tool *tool,
 
 	thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
 	if (thread && thread__is_filtered(thread))
-		return 0;
+		goto out;
 
 	trace__set_base_time(trace, evsel, sample);
 
@@ -1928,7 +1953,8 @@ static int trace__process_sample(struct perf_tool *tool,
 		++trace->nr_events;
 		handler(trace, evsel, event, sample);
 	}
-
+out:
+	thread__put(thread);
 	return err;
 }
 
@@ -1988,7 +2014,7 @@ static int trace__record(struct trace *trace, int argc, const char **argv)
 	for (i = 0; i < (unsigned int)argc; i++)
 		rec_argv[j++] = argv[i];
 
-	return cmd_record(j, rec_argv, NULL);
+	return cmd_record(j, rec_argv);
 }
 
 static size_t trace__fprintf_thread_summary(struct trace *trace, FILE *fp);
@@ -2415,8 +2441,9 @@ static int trace__replay(struct trace *trace)
 	trace->tool.exit	  = perf_event__process_exit;
 	trace->tool.fork	  = perf_event__process_fork;
 	trace->tool.attr	  = perf_event__process_attr;
-	trace->tool.tracing_data = perf_event__process_tracing_data;
+	trace->tool.tracing_data  = perf_event__process_tracing_data;
 	trace->tool.build_id	  = perf_event__process_build_id;
+	trace->tool.namespaces	  = perf_event__process_namespaces;
 
 	trace->tool.ordered_events = true;
 	trace->tool.ordering_requires_timestamps = true;
@@ -2785,7 +2812,7 @@ out:
 	return err;
 }
 
-int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_trace(int argc, const char **argv)
 {
 	const char *trace_usage[] = {
 		"perf trace [<options>] [<command>]",
diff --git a/tools/perf/builtin-version.c b/tools/perf/builtin-version.c
index 9b10cda6b6dc..b9a095b1db99 100644
--- a/tools/perf/builtin-version.c
+++ b/tools/perf/builtin-version.c
@@ -2,8 +2,7 @@
 #include "builtin.h"
 #include "perf.h"
 
-int cmd_version(int argc __maybe_unused, const char **argv __maybe_unused,
-		const char *prefix __maybe_unused)
+int cmd_version(int argc __maybe_unused, const char **argv __maybe_unused)
 {
 	printf("perf version %s\n", perf_version_string);
 	return 0;
diff --git a/tools/perf/builtin.h b/tools/perf/builtin.h
index 036e1e35b1a8..26669bf9129c 100644
--- a/tools/perf/builtin.h
+++ b/tools/perf/builtin.h
@@ -13,35 +13,35 @@ void prune_packed_objects(int);
 int read_line_with_nul(char *buf, int size, FILE *file);
 int check_pager_config(const char *cmd);
 
-int cmd_annotate(int argc, const char **argv, const char *prefix);
-int cmd_bench(int argc, const char **argv, const char *prefix);
-int cmd_buildid_cache(int argc, const char **argv, const char *prefix);
-int cmd_buildid_list(int argc, const char **argv, const char *prefix);
-int cmd_config(int argc, const char **argv, const char *prefix);
-int cmd_c2c(int argc, const char **argv, const char *prefix);
-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);
-int cmd_stat(int argc, const char **argv, const char *prefix);
-int cmd_timechart(int argc, const char **argv, const char *prefix);
-int cmd_top(int argc, const char **argv, const char *prefix);
-int cmd_script(int argc, const char **argv, const char *prefix);
-int cmd_version(int argc, const char **argv, const char *prefix);
-int cmd_probe(int argc, const char **argv, const char *prefix);
-int cmd_kmem(int argc, const char **argv, const char *prefix);
-int cmd_lock(int argc, const char **argv, const char *prefix);
-int cmd_kvm(int argc, const char **argv, const char *prefix);
-int cmd_test(int argc, const char **argv, const char *prefix);
-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 cmd_annotate(int argc, const char **argv);
+int cmd_bench(int argc, const char **argv);
+int cmd_buildid_cache(int argc, const char **argv);
+int cmd_buildid_list(int argc, const char **argv);
+int cmd_config(int argc, const char **argv);
+int cmd_c2c(int argc, const char **argv);
+int cmd_diff(int argc, const char **argv);
+int cmd_evlist(int argc, const char **argv);
+int cmd_help(int argc, const char **argv);
+int cmd_sched(int argc, const char **argv);
+int cmd_kallsyms(int argc, const char **argv);
+int cmd_list(int argc, const char **argv);
+int cmd_record(int argc, const char **argv);
+int cmd_report(int argc, const char **argv);
+int cmd_stat(int argc, const char **argv);
+int cmd_timechart(int argc, const char **argv);
+int cmd_top(int argc, const char **argv);
+int cmd_script(int argc, const char **argv);
+int cmd_version(int argc, const char **argv);
+int cmd_probe(int argc, const char **argv);
+int cmd_kmem(int argc, const char **argv);
+int cmd_lock(int argc, const char **argv);
+int cmd_kvm(int argc, const char **argv);
+int cmd_test(int argc, const char **argv);
+int cmd_trace(int argc, const char **argv);
+int cmd_inject(int argc, const char **argv);
+int cmd_mem(int argc, const char **argv);
+int cmd_data(int argc, const char **argv);
+int cmd_ftrace(int argc, const char **argv);
 
 int find_scripts(char **scripts_array, char **scripts_path_array);
 #endif
diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh
index c747bfd7f14d..83fe2202382e 100755
--- a/tools/perf/check-headers.sh
+++ b/tools/perf/check-headers.sh
@@ -1,7 +1,9 @@
 #!/bin/sh
 
 HEADERS='
+include/uapi/linux/fcntl.h
 include/uapi/linux/perf_event.h
+include/uapi/linux/stat.h
 include/linux/hash.h
 include/uapi/linux/hw_breakpoint.h
 arch/x86/include/asm/disabled-features.h
diff --git a/tools/perf/command-list.txt b/tools/perf/command-list.txt
index ac3efd396a72..2d0caf20ff3a 100644
--- a/tools/perf/command-list.txt
+++ b/tools/perf/command-list.txt
@@ -9,6 +9,7 @@ perf-buildid-cache		mainporcelain common
 perf-buildid-list		mainporcelain common
 perf-data			mainporcelain common
 perf-diff			mainporcelain common
+perf-c2c			mainporcelain common
 perf-config			mainporcelain common
 perf-evlist			mainporcelain common
 perf-ftrace			mainporcelain common
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index 6d5479e03e0d..9dc346f2b255 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -34,7 +34,7 @@ const char *input_name;
 
 struct cmd_struct {
 	const char *cmd;
-	int (*fn)(int, const char **, const char *);
+	int (*fn)(int, const char **);
 	int option;
 };
 
@@ -267,71 +267,6 @@ static int handle_options(const char ***argv, int *argc, int *envchanged)
 	return handled;
 }
 
-static int handle_alias(int *argcp, const char ***argv)
-{
-	int envchanged = 0, ret = 0, saved_errno = errno;
-	int count, option_count;
-	const char **new_argv;
-	const char *alias_command;
-	char *alias_string;
-
-	alias_command = (*argv)[0];
-	alias_string = alias_lookup(alias_command);
-	if (alias_string) {
-		if (alias_string[0] == '!') {
-			if (*argcp > 1) {
-				struct strbuf buf;
-
-				if (strbuf_init(&buf, PATH_MAX) < 0 ||
-				    strbuf_addstr(&buf, alias_string) < 0 ||
-				    sq_quote_argv(&buf, (*argv) + 1,
-						  PATH_MAX) < 0)
-					die("Failed to allocate memory.");
-				free(alias_string);
-				alias_string = buf.buf;
-			}
-			ret = system(alias_string + 1);
-			if (ret >= 0 && WIFEXITED(ret) &&
-			    WEXITSTATUS(ret) != 127)
-				exit(WEXITSTATUS(ret));
-			die("Failed to run '%s' when expanding alias '%s'",
-			    alias_string + 1, alias_command);
-		}
-		count = split_cmdline(alias_string, &new_argv);
-		if (count < 0)
-			die("Bad alias.%s string", alias_command);
-		option_count = handle_options(&new_argv, &count, &envchanged);
-		if (envchanged)
-			die("alias '%s' changes environment variables\n"
-				 "You can use '!perf' in the alias to do this.",
-				 alias_command);
-		memmove(new_argv - option_count, new_argv,
-				count * sizeof(char *));
-		new_argv -= option_count;
-
-		if (count < 1)
-			die("empty alias for %s", alias_command);
-
-		if (!strcmp(alias_command, new_argv[0]))
-			die("recursive alias: %s", alias_command);
-
-		new_argv = realloc(new_argv, sizeof(char *) *
-				    (count + *argcp + 1));
-		/* insert after command name */
-		memcpy(new_argv + count, *argv + 1, sizeof(char *) * *argcp);
-		new_argv[count + *argcp] = NULL;
-
-		*argv = new_argv;
-		*argcp += count - 1;
-
-		ret = 1;
-	}
-
-	errno = saved_errno;
-
-	return ret;
-}
-
 #define RUN_SETUP	(1<<0)
 #define USE_PAGER	(1<<1)
 
@@ -339,13 +274,8 @@ static int run_builtin(struct cmd_struct *p, int argc, const char **argv)
 {
 	int status;
 	struct stat st;
-	const char *prefix;
 	char sbuf[STRERR_BUFSIZE];
 
-	prefix = NULL;
-	if (p->option & RUN_SETUP)
-		prefix = NULL; /* setup_perf_directory(); */
-
 	if (use_browser == -1)
 		use_browser = check_browser_config(p->cmd);
 
@@ -356,7 +286,7 @@ static int run_builtin(struct cmd_struct *p, int argc, const char **argv)
 	commit_pager_choice();
 
 	perf_env__set_cmdline(&perf_env, argc, argv);
-	status = p->fn(argc, argv, prefix);
+	status = p->fn(argc, argv);
 	perf_config__exit();
 	exit_browser(status);
 	perf_env__exit(&perf_env);
@@ -448,7 +378,8 @@ static void execv_dashed_external(const char **argv)
 	if (status != -ERR_RUN_COMMAND_EXEC) {
 		if (IS_RUN_COMMAND_ERR(status)) {
 do_die:
-			die("unable to run '%s'", argv[0]);
+			pr_err("FATAL: unable to run '%s'", argv[0]);
+			status = -128;
 		}
 		exit(-status);
 	}
@@ -460,25 +391,12 @@ do_die:
 
 static int run_argv(int *argcp, const char ***argv)
 {
-	int done_alias = 0;
+	/* See if it's an internal command */
+	handle_internal_command(*argcp, *argv);
 
-	while (1) {
-		/* See if it's an internal command */
-		handle_internal_command(*argcp, *argv);
-
-		/* .. then try the external ones */
-		execv_dashed_external(*argv);
-
-		/* It could be an alias -- this works around the insanity
-		 * of overriding "perf log" with "perf show" by having
-		 * alias.log = show
-		 */
-		if (done_alias || !handle_alias(argcp, argv))
-			break;
-		done_alias = 1;
-	}
-
-	return done_alias;
+	/* .. then try the external ones */
+	execv_dashed_external(*argv);
+	return 0;
 }
 
 static void pthread__block_sigwinch(void)
@@ -566,7 +484,7 @@ int main(int argc, const char **argv)
 #ifdef HAVE_LIBAUDIT_SUPPORT
 		setup_path();
 		argv[0] = "trace";
-		return cmd_trace(argc, argv, NULL);
+		return cmd_trace(argc, argv);
 #else
 		fprintf(stderr,
 			"trace command not available: missing audit-libs devel package at build time.\n");
@@ -611,17 +529,12 @@ int main(int argc, const char **argv)
 
 	while (1) {
 		static int done_help;
-		int was_alias = run_argv(&argc, &argv);
+
+		run_argv(&argc, &argv);
 
 		if (errno != ENOENT)
 			break;
 
-		if (was_alias) {
-			fprintf(stderr, "Expansion of alias '%s' failed; "
-				"'%s' is not a perf-command\n",
-				cmd, argv[0]);
-			goto out;
-		}
 		if (!done_help) {
 			cmd = argv[0] = help_unknown_cmd(cmd);
 			done_help = 1;
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index 1c27d947c2fe..806c216a1078 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -50,6 +50,7 @@ struct record_opts {
 	bool	     running_time;
 	bool	     full_auxtrace;
 	bool	     auxtrace_snapshot_mode;
+	bool	     record_namespaces;
 	bool	     record_switch_events;
 	bool	     all_kernel;
 	bool	     all_user;
diff --git a/tools/perf/pmu-events/arch/x86/broadwell/uncore.json b/tools/perf/pmu-events/arch/x86/broadwell/uncore.json
new file mode 100644
index 000000000000..28e1e159a3cb
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/broadwell/uncore.json
@@ -0,0 +1,278 @@
+[
+  {
+    "Unit": "CBO",
+    "EventCode": "0x22",
+    "UMask": "0x41",
+    "EventName": "UNC_CBO_XSNP_RESPONSE.MISS_XCORE",
+    "BriefDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which misses in some processor core.",
+    "PublicDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which misses in some processor core.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x22",
+    "UMask": "0x81",
+    "EventName": "UNC_CBO_XSNP_RESPONSE.MISS_EVICTION",
+    "BriefDescription": "A cross-core snoop resulted from L3 Eviction which misses in some processor core.",
+    "PublicDescription": "A cross-core snoop resulted from L3 Eviction which misses in some processor core.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x22",
+    "UMask": "0x44",
+    "EventName": "UNC_CBO_XSNP_RESPONSE.HIT_XCORE",
+    "BriefDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a non-modified line in some processor core.",
+    "PublicDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a non-modified line in some processor core.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x22",
+    "UMask": "0x48",
+    "EventName": "UNC_CBO_XSNP_RESPONSE.HITM_XCORE",
+    "BriefDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a modified line in some processor core.",
+    "PublicDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a modified line in some processor core.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x11",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.READ_M",
+    "BriefDescription": "L3 Lookup read request that access cache and found line in M-state",
+    "PublicDescription": "L3 Lookup read request that access cache and found line in M-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x21",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_M",
+    "BriefDescription": "L3 Lookup write request that access cache and found line in M-state",
+    "PublicDescription": "L3 Lookup write request that access cache and found line in M-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x81",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_M",
+    "BriefDescription": "L3 Lookup any request that access cache and found line in M-state",
+    "PublicDescription": "L3 Lookup any request that access cache and found line in M-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x18",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.READ_I",
+    "BriefDescription": "L3 Lookup read request that access cache and found line in I-state",
+    "PublicDescription": "L3 Lookup read request that access cache and found line in I-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x88",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_I",
+    "BriefDescription": "L3 Lookup any request that access cache and found line in I-state",
+    "PublicDescription": "L3 Lookup any request that access cache and found line in I-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x1f",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.READ_MESI",
+    "BriefDescription": "L3 Lookup read request that access cache and found line in any MESI-state",
+    "PublicDescription": "L3 Lookup read request that access cache and found line in any MESI-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x2f",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_MESI",
+    "BriefDescription": "L3 Lookup write request that access cache and found line in MESI-state",
+    "PublicDescription": "L3 Lookup write request that access cache and found line in MESI-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x8f",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_MESI",
+    "BriefDescription": "L3 Lookup any request that access cache and found line in MESI-state",
+    "PublicDescription": "L3 Lookup any request that access cache and found line in MESI-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x86",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_ES",
+    "BriefDescription": "L3 Lookup any request that access cache and found line in E or S-state",
+    "PublicDescription": "L3 Lookup any request that access cache and found line in E or S-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x16",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.READ_ES",
+    "BriefDescription": "L3 Lookup read request that access cache and found line in E or S-state",
+    "PublicDescription": "L3 Lookup read request that access cache and found line in E or S-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x26",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_ES",
+    "BriefDescription": "L3 Lookup write request that access cache and found line in E or S-state",
+    "PublicDescription": "L3 Lookup write request that access cache and found line in E or S-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "iMPH-U",
+    "EventCode": "0x80",
+    "UMask": "0x01",
+    "EventName": "UNC_ARB_TRK_OCCUPANCY.ALL",
+    "BriefDescription": "Each cycle count number of all Core outgoing valid entries. Such entry is defined as valid from it's allocation till first of IDI0 or DRS0 messages is sent out. Accounts for Coherent and non-coherent traffic.",
+    "PublicDescription": "Each cycle count number of all Core outgoing valid entries. Such entry is defined as valid from it's allocation till first of IDI0 or DRS0 messages is sent out. Accounts for Coherent and non-coherent traffic.",
+    "Counter": "0,",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "iMPH-U",
+    "EventCode": "0x80",
+    "UMask": "0x02",
+    "EventName": "UNC_ARB_TRK_OCCUPANCY.DRD_DIRECT",
+    "BriefDescription": "Each cycle count number of 'valid' coherent Data Read entries that are in DirectData mode. Such entry is defined as valid when it is allocated till data sent to Core (first chunk, IDI0). Applicable for IA Cores' requests in normal case.",
+    "PublicDescription": "Each cycle count number of 'valid' coherent Data Read entries that are in DirectData mode. Such entry is defined as valid when it is allocated till data sent to Core (first chunk, IDI0). Applicable for IA Cores' requests in normal case.",
+    "Counter": "0,",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "iMPH-U",
+    "EventCode": "0x81",
+    "UMask": "0x01",
+    "EventName": "UNC_ARB_TRK_REQUESTS.ALL",
+    "BriefDescription": "Total number of Core outgoing entries allocated. Accounts for Coherent and non-coherent traffic.",
+    "PublicDescription": "Total number of Core outgoing entries allocated. Accounts for Coherent and non-coherent traffic.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "iMPH-U",
+    "EventCode": "0x81",
+    "UMask": "0x02",
+    "EventName": "UNC_ARB_TRK_REQUESTS.DRD_DIRECT",
+    "BriefDescription": "Number of Core coherent Data Read entries allocated in DirectData mode",
+    "PublicDescription": "Number of Core coherent Data Read entries allocated in DirectData mode.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "iMPH-U",
+    "EventCode": "0x81",
+    "UMask": "0x20",
+    "EventName": "UNC_ARB_TRK_REQUESTS.WRITES",
+    "BriefDescription": "Number of Writes allocated - any write transactions: full/partials writes and evictions.",
+    "PublicDescription": "Number of Writes allocated - any write transactions: full/partials writes and evictions.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "iMPH-U",
+    "EventCode": "0x84",
+    "UMask": "0x01",
+    "EventName": "UNC_ARB_COH_TRK_REQUESTS.ALL",
+    "BriefDescription": "Number of entries allocated. Account for Any type: e.g. Snoop, Core aperture, etc.",
+    "PublicDescription": "Number of entries allocated. Account for Any type: e.g. Snoop, Core aperture, etc.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "iMPH-U",
+    "EventCode": "0x80",
+    "UMask": "0x01",
+    "EventName": "UNC_ARB_TRK_OCCUPANCY.CYCLES_WITH_ANY_REQUEST",
+    "BriefDescription": "Cycles with at least one request outstanding is waiting for data return from memory controller. Account for coherent and non-coherent requests initiated by IA Cores, Processor Graphics Unit, or LLC.;",
+    "PublicDescription": "Cycles with at least one request outstanding is waiting for data return from memory controller. Account for coherent and non-coherent requests initiated by IA Cores, Processor Graphics Unit, or LLC.",
+    "Counter": "0,",
+    "CounterMask": "1",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "NCU",
+    "EventCode": "0x0",
+    "UMask": "0x01",
+    "EventName": "UNC_CLOCK.SOCKET",
+    "BriefDescription": "This 48-bit fixed counter counts the UCLK cycles",
+    "PublicDescription": "This 48-bit fixed counter counts the UCLK cycles.",
+    "Counter": "FIXED",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  }
+]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/uncore-cache.json b/tools/perf/pmu-events/arch/x86/broadwellde/uncore-cache.json
index 076459c51d4e..58ed6d33d1f4 100644
--- a/tools/perf/pmu-events/arch/x86/broadwellde/uncore-cache.json
+++ b/tools/perf/pmu-events/arch/x86/broadwellde/uncore-cache.json
@@ -1,13 +1,13 @@
 [
     {
-        "BriefDescription": "Uncore cache clock ticks. Derived from unc_c_clockticks",
+        "BriefDescription": "Uncore cache clock ticks",
         "Counter": "0,1,2,3",
         "EventName": "UNC_C_CLOCKTICKS",
         "PerPkg": "1",
         "Unit": "CBO"
     },
     {
-        "BriefDescription": "All LLC Misses (code+ data rd + data wr - including demand and prefetch). Derived from unc_c_llc_lookup.any",
+        "BriefDescription": "All LLC Misses (code+ data rd + data wr - including demand and prefetch)",
         "Counter": "0,1,2,3",
         "EventCode": "0x34",
         "EventName": "UNC_C_LLC_LOOKUP.ANY",
@@ -18,7 +18,7 @@
         "Unit": "CBO"
     },
     {
-        "BriefDescription": "M line evictions from LLC (writebacks to memory). Derived from unc_c_llc_victims.m_state",
+        "BriefDescription": "M line evictions from LLC (writebacks to memory)",
         "Counter": "0,1,2,3",
         "EventCode": "0x37",
         "EventName": "UNC_C_LLC_VICTIMS.M_STATE",
@@ -212,7 +212,7 @@
         "Unit": "CBO"
     },
     {
-        "BriefDescription": "read requests to home agent. Derived from unc_h_requests.reads",
+        "BriefDescription": "read requests to home agent",
         "Counter": "0,1,2,3",
         "EventCode": "0x1",
         "EventName": "UNC_H_REQUESTS.READS",
@@ -221,7 +221,7 @@
         "Unit": "HA"
     },
     {
-        "BriefDescription": "read requests to local home agent. Derived from unc_h_requests.reads_local",
+        "BriefDescription": "read requests to local home agent",
         "Counter": "0,1,2,3",
         "EventCode": "0x1",
         "EventName": "UNC_H_REQUESTS.READS_LOCAL",
@@ -230,7 +230,7 @@
         "Unit": "HA"
     },
     {
-        "BriefDescription": "read requests to remote home agent. Derived from unc_h_requests.reads_remote",
+        "BriefDescription": "read requests to remote home agent",
         "Counter": "0,1,2,3",
         "EventCode": "0x1",
         "EventName": "UNC_H_REQUESTS.READS_REMOTE",
@@ -239,7 +239,7 @@
         "Unit": "HA"
     },
     {
-        "BriefDescription": "write requests to home agent. Derived from unc_h_requests.writes",
+        "BriefDescription": "write requests to home agent",
         "Counter": "0,1,2,3",
         "EventCode": "0x1",
         "EventName": "UNC_H_REQUESTS.WRITES",
@@ -248,7 +248,7 @@
         "Unit": "HA"
     },
     {
-        "BriefDescription": "write requests to local home agent. Derived from unc_h_requests.writes_local",
+        "BriefDescription": "write requests to local home agent",
         "Counter": "0,1,2,3",
         "EventCode": "0x1",
         "EventName": "UNC_H_REQUESTS.WRITES_LOCAL",
@@ -257,7 +257,7 @@
         "Unit": "HA"
     },
     {
-        "BriefDescription": "write requests to remote home agent. Derived from unc_h_requests.writes_remote",
+        "BriefDescription": "write requests to remote home agent",
         "Counter": "0,1,2,3",
         "EventCode": "0x1",
         "EventName": "UNC_H_REQUESTS.WRITES_REMOTE",
@@ -266,7 +266,7 @@
         "Unit": "HA"
     },
     {
-        "BriefDescription": "Conflict requests (requests for same address from multiple agents simultaneously). Derived from unc_h_snoop_resp.rspcnflct",
+        "BriefDescription": "Conflict requests (requests for same address from multiple agents simultaneously)",
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "UNC_H_SNOOP_RESP.RSPCNFLCT",
@@ -275,7 +275,7 @@
         "Unit": "HA"
     },
     {
-        "BriefDescription": "M line forwarded from remote cache along with writeback to memory. Derived from unc_h_snoop_resp.rsp_fwd_wb",
+        "BriefDescription": "M line forwarded from remote cache along with writeback to memory",
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "UNC_H_SNOOP_RESP.RSP_FWD_WB",
@@ -285,7 +285,7 @@
         "Unit": "HA"
     },
     {
-        "BriefDescription": "M line forwarded from remote cache with no writeback to memory. Derived from unc_h_snoop_resp.rspifwd",
+        "BriefDescription": "M line forwarded from remote cache with no writeback to memory",
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "UNC_H_SNOOP_RESP.RSPIFWD",
@@ -295,7 +295,7 @@
         "Unit": "HA"
     },
     {
-        "BriefDescription": "Shared line response from remote cache. Derived from unc_h_snoop_resp.rsps",
+        "BriefDescription": "Shared line response from remote cache",
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "UNC_H_SNOOP_RESP.RSPS",
@@ -305,7 +305,7 @@
         "Unit": "HA"
     },
     {
-        "BriefDescription": "Shared line forwarded from remote cache. Derived from unc_h_snoop_resp.rspsfwd",
+        "BriefDescription": "Shared line forwarded from remote cache",
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "UNC_H_SNOOP_RESP.RSPSFWD",
diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/uncore-memory.json b/tools/perf/pmu-events/arch/x86/broadwellde/uncore-memory.json
index d17dc235f734..f4b0745cdbbf 100644
--- a/tools/perf/pmu-events/arch/x86/broadwellde/uncore-memory.json
+++ b/tools/perf/pmu-events/arch/x86/broadwellde/uncore-memory.json
@@ -3,7 +3,7 @@
         "BriefDescription": "read requests to memory controller. Derived from unc_m_cas_count.rd",
         "Counter": "0,1,2,3",
         "EventCode": "0x4",
-        "EventName": "UNC_M_CAS_COUNT.RD",
+        "EventName": "LLC_MISSES.MEM_READ",
         "PerPkg": "1",
         "ScaleUnit": "64Bytes",
         "UMask": "0x3",
@@ -13,48 +13,51 @@
         "BriefDescription": "write requests to memory controller. Derived from unc_m_cas_count.wr",
         "Counter": "0,1,2,3",
         "EventCode": "0x4",
-        "EventName": "UNC_M_CAS_COUNT.WR",
+        "EventName": "LLC_MISSES.MEM_WRITE",
         "PerPkg": "1",
         "ScaleUnit": "64Bytes",
         "UMask": "0xC",
         "Unit": "iMC"
     },
     {
-        "BriefDescription": "Memory controller clock ticks. Derived from unc_m_clockticks",
+        "BriefDescription": "Memory controller clock ticks",
         "Counter": "0,1,2,3",
-        "EventName": "UNC_M_CLOCKTICKS",
+        "EventName": "UNC_M_DCLOCKTICKS",
         "PerPkg": "1",
         "Unit": "iMC"
     },
     {
-        "BriefDescription": "Cycles where DRAM ranks are in power down (CKE) mode. Derived from unc_m_power_channel_ppd",
+        "BriefDescription": "Cycles where DRAM ranks are in power down (CKE) mode",
         "Counter": "0,1,2,3",
         "EventCode": "0x85",
         "EventName": "UNC_M_POWER_CHANNEL_PPD",
-        "MetricExpr": "(UNC_M_POWER_CHANNEL_PPD / UNC_M_CLOCKTICKS) * 100.",
+        "MetricExpr": "(UNC_M_POWER_CHANNEL_PPD / UNC_M_DCLOCKTICKS) * 100.",
+        "MetricName": "power_channel_ppd %",
         "PerPkg": "1",
         "Unit": "iMC"
     },
     {
-        "BriefDescription": "Cycles all ranks are in critical thermal throttle. Derived from unc_m_power_critical_throttle_cycles",
+        "BriefDescription": "Cycles all ranks are in critical thermal throttle",
         "Counter": "0,1,2,3",
         "EventCode": "0x86",
         "EventName": "UNC_M_POWER_CRITICAL_THROTTLE_CYCLES",
-        "MetricExpr": "(UNC_M_POWER_CRITICAL_THROTTLE_CYCLES / UNC_M_CLOCKTICKS) * 100.",
+        "MetricExpr": "(UNC_M_POWER_CRITICAL_THROTTLE_CYCLES / UNC_M_DCLOCKTICKS) * 100.",
+        "MetricName": "power_critical_throttle_cycles %",
         "PerPkg": "1",
         "Unit": "iMC"
     },
     {
-        "BriefDescription": "Cycles Memory is in self refresh power mode. Derived from unc_m_power_self_refresh",
+        "BriefDescription": "Cycles Memory is in self refresh power mode",
         "Counter": "0,1,2,3",
         "EventCode": "0x43",
         "EventName": "UNC_M_POWER_SELF_REFRESH",
-        "MetricExpr": "(UNC_M_POWER_SELF_REFRESH / UNC_M_CLOCKTICKS) * 100.",
+        "MetricExpr": "(UNC_M_POWER_SELF_REFRESH / UNC_M_DCLOCKTICKS) * 100.",
+        "MetricName": "power_self_refresh %",
         "PerPkg": "1",
         "Unit": "iMC"
     },
     {
-        "BriefDescription": "Pre-charges due to page misses. Derived from unc_m_pre_count.page_miss",
+        "BriefDescription": "Pre-charges due to page misses",
         "Counter": "0,1,2,3",
         "EventCode": "0x2",
         "EventName": "UNC_M_PRE_COUNT.PAGE_MISS",
@@ -63,7 +66,7 @@
         "Unit": "iMC"
     },
     {
-        "BriefDescription": "Pre-charge for reads. Derived from unc_m_pre_count.rd",
+        "BriefDescription": "Pre-charge for reads",
         "Counter": "0,1,2,3",
         "EventCode": "0x2",
         "EventName": "UNC_M_PRE_COUNT.RD",
@@ -72,7 +75,7 @@
         "Unit": "iMC"
     },
     {
-        "BriefDescription": "Pre-charge for writes. Derived from unc_m_pre_count.wr",
+        "BriefDescription": "Pre-charge for writes",
         "Counter": "0,1,2,3",
         "EventCode": "0x2",
         "EventName": "UNC_M_PRE_COUNT.WR",
diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/uncore-power.json b/tools/perf/pmu-events/arch/x86/broadwellde/uncore-power.json
index b44d43088bbb..dd1b95655d1d 100644
--- a/tools/perf/pmu-events/arch/x86/broadwellde/uncore-power.json
+++ b/tools/perf/pmu-events/arch/x86/broadwellde/uncore-power.json
@@ -1,83 +1,91 @@
 [
     {
-        "BriefDescription": "PCU clock ticks. Use to get percentages of PCU cycles events. Derived from unc_p_clockticks",
+        "BriefDescription": "PCU clock ticks. Use to get percentages of PCU cycles events",
         "Counter": "0,1,2,3",
         "EventName": "UNC_P_CLOCKTICKS",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "C0 and C1. Derived from unc_p_power_state_occupancy.cores_c0",
+        "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C0.  It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details",
         "Counter": "0,1,2,3",
         "EventCode": "0x80",
         "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C0",
         "Filter": "occ_sel=1",
         "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C0 / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "power_state_occupancy.cores_c0 %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "C3. Derived from unc_p_power_state_occupancy.cores_c3",
+        "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C3.  It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details",
         "Counter": "0,1,2,3",
         "EventCode": "0x80",
         "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C3",
         "Filter": "occ_sel=2",
         "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C3 / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "power_state_occupancy.cores_c3 %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "C6 and C7. Derived from unc_p_power_state_occupancy.cores_c6",
+        "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C6.  It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events ",
         "Counter": "0,1,2,3",
         "EventCode": "0x80",
         "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C6",
         "Filter": "occ_sel=3",
         "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C6 / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "power_state_occupancy.cores_c6 %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "External Prochot. Derived from unc_p_prochot_external_cycles",
+        "BriefDescription": "Counts the number of cycles that we are in external PROCHOT mode.  This mode is triggered when a sensor off the die determines that something off-die (like DRAM) is too hot and must throttle to avoid damaging the chip",
         "Counter": "0,1,2,3",
         "EventCode": "0xA",
         "EventName": "UNC_P_PROCHOT_EXTERNAL_CYCLES",
         "MetricExpr": "(UNC_P_PROCHOT_EXTERNAL_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "prochot_external_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "Thermal Strongest Upper Limit Cycles. Derived from unc_p_freq_max_limit_thermal_cycles",
+        "BriefDescription": "Counts the number of cycles when temperature is the upper limit on frequency",
         "Counter": "0,1,2,3",
         "EventCode": "0x4",
         "EventName": "UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES",
         "MetricExpr": "(UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_max_limit_thermal_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "OS Strongest Upper Limit Cycles. Derived from unc_p_freq_max_os_cycles",
+        "BriefDescription": "Counts the number of cycles when the OS is the upper limit on frequency",
         "Counter": "0,1,2,3",
         "EventCode": "0x6",
         "EventName": "UNC_P_FREQ_MAX_OS_CYCLES",
         "MetricExpr": "(UNC_P_FREQ_MAX_OS_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_max_os_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "Power Strongest Upper Limit Cycles. Derived from unc_p_freq_max_power_cycles",
+        "BriefDescription": "Counts the number of cycles when power is the upper limit on frequency",
         "Counter": "0,1,2,3",
         "EventCode": "0x5",
         "EventName": "UNC_P_FREQ_MAX_POWER_CYCLES",
         "MetricExpr": "(UNC_P_FREQ_MAX_POWER_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_max_power_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "Cycles spent changing Frequency. Derived from unc_p_freq_trans_cycles",
+        "BriefDescription": "Counts the number of cycles when current is the upper limit on frequency",
         "Counter": "0,1,2,3",
         "EventCode": "0x74",
         "EventName": "UNC_P_FREQ_TRANS_CYCLES",
         "MetricExpr": "(UNC_P_FREQ_TRANS_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_trans_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     }
diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/uncore-cache.json b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-cache.json
index 076459c51d4e..58ed6d33d1f4 100644
--- a/tools/perf/pmu-events/arch/x86/broadwellx/uncore-cache.json
+++ b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-cache.json
@@ -1,13 +1,13 @@
 [
     {
-        "BriefDescription": "Uncore cache clock ticks. Derived from unc_c_clockticks",
+        "BriefDescription": "Uncore cache clock ticks",
         "Counter": "0,1,2,3",
         "EventName": "UNC_C_CLOCKTICKS",
         "PerPkg": "1",
         "Unit": "CBO"
     },
     {
-        "BriefDescription": "All LLC Misses (code+ data rd + data wr - including demand and prefetch). Derived from unc_c_llc_lookup.any",
+        "BriefDescription": "All LLC Misses (code+ data rd + data wr - including demand and prefetch)",
         "Counter": "0,1,2,3",
         "EventCode": "0x34",
         "EventName": "UNC_C_LLC_LOOKUP.ANY",
@@ -18,7 +18,7 @@
         "Unit": "CBO"
     },
     {
-        "BriefDescription": "M line evictions from LLC (writebacks to memory). Derived from unc_c_llc_victims.m_state",
+        "BriefDescription": "M line evictions from LLC (writebacks to memory)",
         "Counter": "0,1,2,3",
         "EventCode": "0x37",
         "EventName": "UNC_C_LLC_VICTIMS.M_STATE",
@@ -212,7 +212,7 @@
         "Unit": "CBO"
     },
     {
-        "BriefDescription": "read requests to home agent. Derived from unc_h_requests.reads",
+        "BriefDescription": "read requests to home agent",
         "Counter": "0,1,2,3",
         "EventCode": "0x1",
         "EventName": "UNC_H_REQUESTS.READS",
@@ -221,7 +221,7 @@
         "Unit": "HA"
     },
     {
-        "BriefDescription": "read requests to local home agent. Derived from unc_h_requests.reads_local",
+        "BriefDescription": "read requests to local home agent",
         "Counter": "0,1,2,3",
         "EventCode": "0x1",
         "EventName": "UNC_H_REQUESTS.READS_LOCAL",
@@ -230,7 +230,7 @@
         "Unit": "HA"
     },
     {
-        "BriefDescription": "read requests to remote home agent. Derived from unc_h_requests.reads_remote",
+        "BriefDescription": "read requests to remote home agent",
         "Counter": "0,1,2,3",
         "EventCode": "0x1",
         "EventName": "UNC_H_REQUESTS.READS_REMOTE",
@@ -239,7 +239,7 @@
         "Unit": "HA"
     },
     {
-        "BriefDescription": "write requests to home agent. Derived from unc_h_requests.writes",
+        "BriefDescription": "write requests to home agent",
         "Counter": "0,1,2,3",
         "EventCode": "0x1",
         "EventName": "UNC_H_REQUESTS.WRITES",
@@ -248,7 +248,7 @@
         "Unit": "HA"
     },
     {
-        "BriefDescription": "write requests to local home agent. Derived from unc_h_requests.writes_local",
+        "BriefDescription": "write requests to local home agent",
         "Counter": "0,1,2,3",
         "EventCode": "0x1",
         "EventName": "UNC_H_REQUESTS.WRITES_LOCAL",
@@ -257,7 +257,7 @@
         "Unit": "HA"
     },
     {
-        "BriefDescription": "write requests to remote home agent. Derived from unc_h_requests.writes_remote",
+        "BriefDescription": "write requests to remote home agent",
         "Counter": "0,1,2,3",
         "EventCode": "0x1",
         "EventName": "UNC_H_REQUESTS.WRITES_REMOTE",
@@ -266,7 +266,7 @@
         "Unit": "HA"
     },
     {
-        "BriefDescription": "Conflict requests (requests for same address from multiple agents simultaneously). Derived from unc_h_snoop_resp.rspcnflct",
+        "BriefDescription": "Conflict requests (requests for same address from multiple agents simultaneously)",
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "UNC_H_SNOOP_RESP.RSPCNFLCT",
@@ -275,7 +275,7 @@
         "Unit": "HA"
     },
     {
-        "BriefDescription": "M line forwarded from remote cache along with writeback to memory. Derived from unc_h_snoop_resp.rsp_fwd_wb",
+        "BriefDescription": "M line forwarded from remote cache along with writeback to memory",
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "UNC_H_SNOOP_RESP.RSP_FWD_WB",
@@ -285,7 +285,7 @@
         "Unit": "HA"
     },
     {
-        "BriefDescription": "M line forwarded from remote cache with no writeback to memory. Derived from unc_h_snoop_resp.rspifwd",
+        "BriefDescription": "M line forwarded from remote cache with no writeback to memory",
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "UNC_H_SNOOP_RESP.RSPIFWD",
@@ -295,7 +295,7 @@
         "Unit": "HA"
     },
     {
-        "BriefDescription": "Shared line response from remote cache. Derived from unc_h_snoop_resp.rsps",
+        "BriefDescription": "Shared line response from remote cache",
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "UNC_H_SNOOP_RESP.RSPS",
@@ -305,7 +305,7 @@
         "Unit": "HA"
     },
     {
-        "BriefDescription": "Shared line forwarded from remote cache. Derived from unc_h_snoop_resp.rspsfwd",
+        "BriefDescription": "Shared line forwarded from remote cache",
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "UNC_H_SNOOP_RESP.RSPSFWD",
diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-interconnect.json
index 39387f7909b2..824961318c1e 100644
--- a/tools/perf/pmu-events/arch/x86/broadwellx/uncore-interconnect.json
+++ b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-interconnect.json
@@ -1,6 +1,6 @@
 [
     {
-        "BriefDescription": "QPI clock ticks. Derived from unc_q_clockticks",
+        "BriefDescription": "QPI clock ticks",
         "Counter": "0,1,2,3",
         "EventCode": "0x14",
         "EventName": "UNC_Q_CLOCKTICKS",
@@ -10,7 +10,7 @@
     {
         "BriefDescription": "Number of data flits transmitted . Derived from unc_q_txl_flits_g0.data",
         "Counter": "0,1,2,3",
-        "EventName": "UNC_Q_TxL_FLITS_G0.DATA",
+        "EventName": "QPI_DATA_BANDWIDTH_TX",
         "PerPkg": "1",
         "ScaleUnit": "8Bytes",
         "UMask": "0x2",
@@ -19,7 +19,7 @@
     {
         "BriefDescription": "Number of non data (control) flits transmitted . Derived from unc_q_txl_flits_g0.non_data",
         "Counter": "0,1,2,3",
-        "EventName": "UNC_Q_TxL_FLITS_G0.NON_DATA",
+        "EventName": "QPI_CTL_BANDWIDTH_TX",
         "PerPkg": "1",
         "ScaleUnit": "8Bytes",
         "UMask": "0x4",
diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/uncore-memory.json b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-memory.json
index d17dc235f734..66eed399724c 100644
--- a/tools/perf/pmu-events/arch/x86/broadwellx/uncore-memory.json
+++ b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-memory.json
@@ -3,7 +3,7 @@
         "BriefDescription": "read requests to memory controller. Derived from unc_m_cas_count.rd",
         "Counter": "0,1,2,3",
         "EventCode": "0x4",
-        "EventName": "UNC_M_CAS_COUNT.RD",
+        "EventName": "LLC_MISSES.MEM_READ",
         "PerPkg": "1",
         "ScaleUnit": "64Bytes",
         "UMask": "0x3",
@@ -13,48 +13,51 @@
         "BriefDescription": "write requests to memory controller. Derived from unc_m_cas_count.wr",
         "Counter": "0,1,2,3",
         "EventCode": "0x4",
-        "EventName": "UNC_M_CAS_COUNT.WR",
+        "EventName": "LLC_MISSES.MEM_WRITE",
         "PerPkg": "1",
         "ScaleUnit": "64Bytes",
         "UMask": "0xC",
         "Unit": "iMC"
     },
     {
-        "BriefDescription": "Memory controller clock ticks. Derived from unc_m_clockticks",
+        "BriefDescription": "Memory controller clock ticks",
         "Counter": "0,1,2,3",
         "EventName": "UNC_M_CLOCKTICKS",
         "PerPkg": "1",
         "Unit": "iMC"
     },
     {
-        "BriefDescription": "Cycles where DRAM ranks are in power down (CKE) mode. Derived from unc_m_power_channel_ppd",
+        "BriefDescription": "Cycles where DRAM ranks are in power down (CKE) mode",
         "Counter": "0,1,2,3",
         "EventCode": "0x85",
         "EventName": "UNC_M_POWER_CHANNEL_PPD",
         "MetricExpr": "(UNC_M_POWER_CHANNEL_PPD / UNC_M_CLOCKTICKS) * 100.",
+        "MetricName": "power_channel_ppd %",
         "PerPkg": "1",
         "Unit": "iMC"
     },
     {
-        "BriefDescription": "Cycles all ranks are in critical thermal throttle. Derived from unc_m_power_critical_throttle_cycles",
+        "BriefDescription": "Cycles all ranks are in critical thermal throttle",
         "Counter": "0,1,2,3",
         "EventCode": "0x86",
         "EventName": "UNC_M_POWER_CRITICAL_THROTTLE_CYCLES",
         "MetricExpr": "(UNC_M_POWER_CRITICAL_THROTTLE_CYCLES / UNC_M_CLOCKTICKS) * 100.",
+        "MetricName": "power_critical_throttle_cycles %",
         "PerPkg": "1",
         "Unit": "iMC"
     },
     {
-        "BriefDescription": "Cycles Memory is in self refresh power mode. Derived from unc_m_power_self_refresh",
+        "BriefDescription": "Cycles Memory is in self refresh power mode",
         "Counter": "0,1,2,3",
         "EventCode": "0x43",
         "EventName": "UNC_M_POWER_SELF_REFRESH",
         "MetricExpr": "(UNC_M_POWER_SELF_REFRESH / UNC_M_CLOCKTICKS) * 100.",
+        "MetricName": "power_self_refresh %",
         "PerPkg": "1",
         "Unit": "iMC"
     },
     {
-        "BriefDescription": "Pre-charges due to page misses. Derived from unc_m_pre_count.page_miss",
+        "BriefDescription": "Pre-charges due to page misses",
         "Counter": "0,1,2,3",
         "EventCode": "0x2",
         "EventName": "UNC_M_PRE_COUNT.PAGE_MISS",
@@ -63,7 +66,7 @@
         "Unit": "iMC"
     },
     {
-        "BriefDescription": "Pre-charge for reads. Derived from unc_m_pre_count.rd",
+        "BriefDescription": "Pre-charge for reads",
         "Counter": "0,1,2,3",
         "EventCode": "0x2",
         "EventName": "UNC_M_PRE_COUNT.RD",
@@ -72,7 +75,7 @@
         "Unit": "iMC"
     },
     {
-        "BriefDescription": "Pre-charge for writes. Derived from unc_m_pre_count.wr",
+        "BriefDescription": "Pre-charge for writes",
         "Counter": "0,1,2,3",
         "EventCode": "0x2",
         "EventName": "UNC_M_PRE_COUNT.WR",
diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/uncore-power.json b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-power.json
index b44d43088bbb..dd1b95655d1d 100644
--- a/tools/perf/pmu-events/arch/x86/broadwellx/uncore-power.json
+++ b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-power.json
@@ -1,83 +1,91 @@
 [
     {
-        "BriefDescription": "PCU clock ticks. Use to get percentages of PCU cycles events. Derived from unc_p_clockticks",
+        "BriefDescription": "PCU clock ticks. Use to get percentages of PCU cycles events",
         "Counter": "0,1,2,3",
         "EventName": "UNC_P_CLOCKTICKS",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "C0 and C1. Derived from unc_p_power_state_occupancy.cores_c0",
+        "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C0.  It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details",
         "Counter": "0,1,2,3",
         "EventCode": "0x80",
         "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C0",
         "Filter": "occ_sel=1",
         "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C0 / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "power_state_occupancy.cores_c0 %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "C3. Derived from unc_p_power_state_occupancy.cores_c3",
+        "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C3.  It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details",
         "Counter": "0,1,2,3",
         "EventCode": "0x80",
         "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C3",
         "Filter": "occ_sel=2",
         "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C3 / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "power_state_occupancy.cores_c3 %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "C6 and C7. Derived from unc_p_power_state_occupancy.cores_c6",
+        "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C6.  It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events ",
         "Counter": "0,1,2,3",
         "EventCode": "0x80",
         "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C6",
         "Filter": "occ_sel=3",
         "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C6 / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "power_state_occupancy.cores_c6 %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "External Prochot. Derived from unc_p_prochot_external_cycles",
+        "BriefDescription": "Counts the number of cycles that we are in external PROCHOT mode.  This mode is triggered when a sensor off the die determines that something off-die (like DRAM) is too hot and must throttle to avoid damaging the chip",
         "Counter": "0,1,2,3",
         "EventCode": "0xA",
         "EventName": "UNC_P_PROCHOT_EXTERNAL_CYCLES",
         "MetricExpr": "(UNC_P_PROCHOT_EXTERNAL_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "prochot_external_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "Thermal Strongest Upper Limit Cycles. Derived from unc_p_freq_max_limit_thermal_cycles",
+        "BriefDescription": "Counts the number of cycles when temperature is the upper limit on frequency",
         "Counter": "0,1,2,3",
         "EventCode": "0x4",
         "EventName": "UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES",
         "MetricExpr": "(UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_max_limit_thermal_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "OS Strongest Upper Limit Cycles. Derived from unc_p_freq_max_os_cycles",
+        "BriefDescription": "Counts the number of cycles when the OS is the upper limit on frequency",
         "Counter": "0,1,2,3",
         "EventCode": "0x6",
         "EventName": "UNC_P_FREQ_MAX_OS_CYCLES",
         "MetricExpr": "(UNC_P_FREQ_MAX_OS_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_max_os_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "Power Strongest Upper Limit Cycles. Derived from unc_p_freq_max_power_cycles",
+        "BriefDescription": "Counts the number of cycles when power is the upper limit on frequency",
         "Counter": "0,1,2,3",
         "EventCode": "0x5",
         "EventName": "UNC_P_FREQ_MAX_POWER_CYCLES",
         "MetricExpr": "(UNC_P_FREQ_MAX_POWER_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_max_power_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "Cycles spent changing Frequency. Derived from unc_p_freq_trans_cycles",
+        "BriefDescription": "Counts the number of cycles when current is the upper limit on frequency",
         "Counter": "0,1,2,3",
         "EventCode": "0x74",
         "EventName": "UNC_P_FREQ_TRANS_CYCLES",
         "MetricExpr": "(UNC_P_FREQ_TRANS_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_trans_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     }
diff --git a/tools/perf/pmu-events/arch/x86/haswell/uncore.json b/tools/perf/pmu-events/arch/x86/haswell/uncore.json
new file mode 100644
index 000000000000..3ef5c21fef56
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/haswell/uncore.json
@@ -0,0 +1,374 @@
+[
+  {
+    "Unit": "CBO",
+    "EventCode": "0x22",
+    "UMask": "0x21",
+    "EventName": "UNC_CBO_XSNP_RESPONSE.MISS_EXTERNAL",
+    "BriefDescription": "An external snoop misses in some processor core.",
+    "PublicDescription": "An external snoop misses in some processor core.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x22",
+    "UMask": "0x41",
+    "EventName": "UNC_CBO_XSNP_RESPONSE.MISS_XCORE",
+    "BriefDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which misses in some processor core.",
+    "PublicDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which misses in some processor core.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x22",
+    "UMask": "0x81",
+    "EventName": "UNC_CBO_XSNP_RESPONSE.MISS_EVICTION",
+    "BriefDescription": "A cross-core snoop resulted from L3 Eviction which misses in some processor core.",
+    "PublicDescription": "A cross-core snoop resulted from L3 Eviction which misses in some processor core.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x22",
+    "UMask": "0x24",
+    "EventName": "UNC_CBO_XSNP_RESPONSE.HIT_EXTERNAL",
+    "BriefDescription": "An external snoop hits a non-modified line in some processor core.",
+    "PublicDescription": "An external snoop hits a non-modified line in some processor core.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x22",
+    "UMask": "0x44",
+    "EventName": "UNC_CBO_XSNP_RESPONSE.HIT_XCORE",
+    "BriefDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a non-modified line in some processor core.",
+    "PublicDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a non-modified line in some processor core.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x22",
+    "UMask": "0x84",
+    "EventName": "UNC_CBO_XSNP_RESPONSE.HIT_EVICTION",
+    "BriefDescription": "A cross-core snoop resulted from L3 Eviction which hits a non-modified line in some processor core.",
+    "PublicDescription": "A cross-core snoop resulted from L3 Eviction which hits a non-modified line in some processor core.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x22",
+    "UMask": "0x28",
+    "EventName": "UNC_CBO_XSNP_RESPONSE.HITM_EXTERNAL",
+    "BriefDescription": "An external snoop hits a modified line in some processor core.",
+    "PublicDescription": "An external snoop hits a modified line in some processor core.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x22",
+    "UMask": "0x48",
+    "EventName": "UNC_CBO_XSNP_RESPONSE.HITM_XCORE",
+    "BriefDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a modified line in some processor core.",
+    "PublicDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a modified line in some processor core.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x22",
+    "UMask": "0x88",
+    "EventName": "UNC_CBO_XSNP_RESPONSE.HITM_EVICTION",
+    "BriefDescription": "A cross-core snoop resulted from L3 Eviction which hits a modified line in some processor core.",
+    "PublicDescription": "A cross-core snoop resulted from L3 Eviction which hits a modified line in some processor core.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x11",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.READ_M",
+    "BriefDescription": "L3 Lookup read request that access cache and found line in M-state.",
+    "PublicDescription": "L3 Lookup read request that access cache and found line in M-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x21",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_M",
+    "BriefDescription": "L3 Lookup write request that access cache and found line in M-state.",
+    "PublicDescription": "L3 Lookup write request that access cache and found line in M-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x41",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.EXTSNP_M",
+    "BriefDescription": "L3 Lookup external snoop request that access cache and found line in M-state.",
+    "PublicDescription": "L3 Lookup external snoop request that access cache and found line in M-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x81",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_M",
+    "BriefDescription": "L3 Lookup any request that access cache and found line in M-state.",
+    "PublicDescription": "L3 Lookup any request that access cache and found line in M-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x18",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.READ_I",
+    "BriefDescription": "L3 Lookup read request that access cache and found line in I-state.",
+    "PublicDescription": "L3 Lookup read request that access cache and found line in I-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x28",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_I",
+    "BriefDescription": "L3 Lookup write request that access cache and found line in I-state.",
+    "PublicDescription": "L3 Lookup write request that access cache and found line in I-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x48",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.EXTSNP_I",
+    "BriefDescription": "L3 Lookup external snoop request that access cache and found line in I-state.",
+    "PublicDescription": "L3 Lookup external snoop request that access cache and found line in I-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x88",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_I",
+    "BriefDescription": "L3 Lookup any request that access cache and found line in I-state.",
+    "PublicDescription": "L3 Lookup any request that access cache and found line in I-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x1f",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.READ_MESI",
+    "BriefDescription": "L3 Lookup read request that access cache and found line in any MESI-state.",
+    "PublicDescription": "L3 Lookup read request that access cache and found line in any MESI-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x2f",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_MESI",
+    "BriefDescription": "L3 Lookup write request that access cache and found line in MESI-state.",
+    "PublicDescription": "L3 Lookup write request that access cache and found line in MESI-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x4f",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.EXTSNP_MESI",
+    "BriefDescription": "L3 Lookup external snoop request that access cache and found line in MESI-state.",
+    "PublicDescription": "L3 Lookup external snoop request that access cache and found line in MESI-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x8f",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_MESI",
+    "BriefDescription": "L3 Lookup any request that access cache and found line in MESI-state.",
+    "PublicDescription": "L3 Lookup any request that access cache and found line in MESI-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x86",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_ES",
+    "BriefDescription": "L3 Lookup any request that access cache and found line in E or S-state.",
+    "PublicDescription": "L3 Lookup any request that access cache and found line in E or S-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x46",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.EXTSNP_ES",
+    "BriefDescription": "L3 Lookup external snoop request that access cache and found line in E or S-state.",
+    "PublicDescription": "L3 Lookup external snoop request that access cache and found line in E or S-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x16",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.READ_ES",
+    "BriefDescription": "L3 Lookup read request that access cache and found line in E or S-state.",
+    "PublicDescription": "L3 Lookup read request that access cache and found line in E or S-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x26",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_ES",
+    "BriefDescription": "L3 Lookup write request that access cache and found line in E or S-state.",
+    "PublicDescription": "L3 Lookup write request that access cache and found line in E or S-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "iMPH-U",
+    "EventCode": "0x80",
+    "UMask": "0x01",
+    "EventName": "UNC_ARB_TRK_OCCUPANCY.ALL",
+    "BriefDescription": "Each cycle count number of all Core outgoing valid entries. Such entry is defined as valid from it's allocation till first of IDI0 or DRS0 messages is sent out. Accounts for Coherent and non-coherent traffic.",
+    "PublicDescription": "Each cycle count number of all Core outgoing valid entries. Such entry is defined as valid from it's allocation till first of IDI0 or DRS0 messages is sent out. Accounts for Coherent and non-coherent traffic.",
+    "Counter": "0",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "iMPH-U",
+    "EventCode": "0x81",
+    "UMask": "0x01",
+    "EventName": "UNC_ARB_TRK_REQUESTS.ALL",
+    "BriefDescription": "Total number of Core outgoing entries allocated. Accounts for Coherent and non-coherent traffic.",
+    "PublicDescription": "Total number of Core outgoing entries allocated. Accounts for Coherent and non-coherent traffic.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "iMPH-U",
+    "EventCode": "0x81",
+    "UMask": "0x20",
+    "EventName": "UNC_ARB_TRK_REQUESTS.WRITES",
+    "BriefDescription": "Number of Writes allocated - any write transactions: full/partials writes and evictions.",
+    "PublicDescription": "Number of Writes allocated - any write transactions: full/partials writes and evictions.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "iMPH-U",
+    "EventCode": "0x83",
+    "UMask": "0x01",
+    "EventName": "UNC_ARB_COH_TRK_OCCUPANCY.All",
+    "BriefDescription": "Each cycle count number of valid entries in Coherency Tracker queue from allocation till deallocation. Aperture requests (snoops) appear as NC decoded internally and become coherent (snoop L3, access memory)",
+    "PublicDescription": "Each cycle count number of valid entries in Coherency Tracker queue from allocation till deallocation. Aperture requests (snoops) appear as NC decoded internally and become coherent (snoop L3, access memory).",
+    "Counter": "0",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "iMPH-U",
+    "EventCode": "0x84",
+    "UMask": "0x01",
+    "EventName": "UNC_ARB_COH_TRK_REQUESTS.ALL",
+    "BriefDescription": "Number of entries allocated. Account for Any type: e.g. Snoop, Core aperture, etc.",
+    "PublicDescription": "Number of entries allocated. Account for Any type: e.g. Snoop, Core aperture, etc.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "NCU",
+    "EventCode": "0x0",
+    "UMask": "0x01",
+    "EventName": "UNC_CLOCK.SOCKET",
+    "BriefDescription": "This 48-bit fixed counter counts the UCLK cycles.",
+    "PublicDescription": "This 48-bit fixed counter counts the UCLK cycles.",
+    "Counter": "FIXED",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  }
+]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/haswellx/uncore-cache.json b/tools/perf/pmu-events/arch/x86/haswellx/uncore-cache.json
index 076459c51d4e..58ed6d33d1f4 100644
--- a/tools/perf/pmu-events/arch/x86/haswellx/uncore-cache.json
+++ b/tools/perf/pmu-events/arch/x86/haswellx/uncore-cache.json
@@ -1,13 +1,13 @@
 [
     {
-        "BriefDescription": "Uncore cache clock ticks. Derived from unc_c_clockticks",
+        "BriefDescription": "Uncore cache clock ticks",
         "Counter": "0,1,2,3",
         "EventName": "UNC_C_CLOCKTICKS",
         "PerPkg": "1",
         "Unit": "CBO"
     },
     {
-        "BriefDescription": "All LLC Misses (code+ data rd + data wr - including demand and prefetch). Derived from unc_c_llc_lookup.any",
+        "BriefDescription": "All LLC Misses (code+ data rd + data wr - including demand and prefetch)",
         "Counter": "0,1,2,3",
         "EventCode": "0x34",
         "EventName": "UNC_C_LLC_LOOKUP.ANY",
@@ -18,7 +18,7 @@
         "Unit": "CBO"
     },
     {
-        "BriefDescription": "M line evictions from LLC (writebacks to memory). Derived from unc_c_llc_victims.m_state",
+        "BriefDescription": "M line evictions from LLC (writebacks to memory)",
         "Counter": "0,1,2,3",
         "EventCode": "0x37",
         "EventName": "UNC_C_LLC_VICTIMS.M_STATE",
@@ -212,7 +212,7 @@
         "Unit": "CBO"
     },
     {
-        "BriefDescription": "read requests to home agent. Derived from unc_h_requests.reads",
+        "BriefDescription": "read requests to home agent",
         "Counter": "0,1,2,3",
         "EventCode": "0x1",
         "EventName": "UNC_H_REQUESTS.READS",
@@ -221,7 +221,7 @@
         "Unit": "HA"
     },
     {
-        "BriefDescription": "read requests to local home agent. Derived from unc_h_requests.reads_local",
+        "BriefDescription": "read requests to local home agent",
         "Counter": "0,1,2,3",
         "EventCode": "0x1",
         "EventName": "UNC_H_REQUESTS.READS_LOCAL",
@@ -230,7 +230,7 @@
         "Unit": "HA"
     },
     {
-        "BriefDescription": "read requests to remote home agent. Derived from unc_h_requests.reads_remote",
+        "BriefDescription": "read requests to remote home agent",
         "Counter": "0,1,2,3",
         "EventCode": "0x1",
         "EventName": "UNC_H_REQUESTS.READS_REMOTE",
@@ -239,7 +239,7 @@
         "Unit": "HA"
     },
     {
-        "BriefDescription": "write requests to home agent. Derived from unc_h_requests.writes",
+        "BriefDescription": "write requests to home agent",
         "Counter": "0,1,2,3",
         "EventCode": "0x1",
         "EventName": "UNC_H_REQUESTS.WRITES",
@@ -248,7 +248,7 @@
         "Unit": "HA"
     },
     {
-        "BriefDescription": "write requests to local home agent. Derived from unc_h_requests.writes_local",
+        "BriefDescription": "write requests to local home agent",
         "Counter": "0,1,2,3",
         "EventCode": "0x1",
         "EventName": "UNC_H_REQUESTS.WRITES_LOCAL",
@@ -257,7 +257,7 @@
         "Unit": "HA"
     },
     {
-        "BriefDescription": "write requests to remote home agent. Derived from unc_h_requests.writes_remote",
+        "BriefDescription": "write requests to remote home agent",
         "Counter": "0,1,2,3",
         "EventCode": "0x1",
         "EventName": "UNC_H_REQUESTS.WRITES_REMOTE",
@@ -266,7 +266,7 @@
         "Unit": "HA"
     },
     {
-        "BriefDescription": "Conflict requests (requests for same address from multiple agents simultaneously). Derived from unc_h_snoop_resp.rspcnflct",
+        "BriefDescription": "Conflict requests (requests for same address from multiple agents simultaneously)",
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "UNC_H_SNOOP_RESP.RSPCNFLCT",
@@ -275,7 +275,7 @@
         "Unit": "HA"
     },
     {
-        "BriefDescription": "M line forwarded from remote cache along with writeback to memory. Derived from unc_h_snoop_resp.rsp_fwd_wb",
+        "BriefDescription": "M line forwarded from remote cache along with writeback to memory",
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "UNC_H_SNOOP_RESP.RSP_FWD_WB",
@@ -285,7 +285,7 @@
         "Unit": "HA"
     },
     {
-        "BriefDescription": "M line forwarded from remote cache with no writeback to memory. Derived from unc_h_snoop_resp.rspifwd",
+        "BriefDescription": "M line forwarded from remote cache with no writeback to memory",
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "UNC_H_SNOOP_RESP.RSPIFWD",
@@ -295,7 +295,7 @@
         "Unit": "HA"
     },
     {
-        "BriefDescription": "Shared line response from remote cache. Derived from unc_h_snoop_resp.rsps",
+        "BriefDescription": "Shared line response from remote cache",
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "UNC_H_SNOOP_RESP.RSPS",
@@ -305,7 +305,7 @@
         "Unit": "HA"
     },
     {
-        "BriefDescription": "Shared line forwarded from remote cache. Derived from unc_h_snoop_resp.rspsfwd",
+        "BriefDescription": "Shared line forwarded from remote cache",
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "UNC_H_SNOOP_RESP.RSPSFWD",
diff --git a/tools/perf/pmu-events/arch/x86/haswellx/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/haswellx/uncore-interconnect.json
index 39387f7909b2..824961318c1e 100644
--- a/tools/perf/pmu-events/arch/x86/haswellx/uncore-interconnect.json
+++ b/tools/perf/pmu-events/arch/x86/haswellx/uncore-interconnect.json
@@ -1,6 +1,6 @@
 [
     {
-        "BriefDescription": "QPI clock ticks. Derived from unc_q_clockticks",
+        "BriefDescription": "QPI clock ticks",
         "Counter": "0,1,2,3",
         "EventCode": "0x14",
         "EventName": "UNC_Q_CLOCKTICKS",
@@ -10,7 +10,7 @@
     {
         "BriefDescription": "Number of data flits transmitted . Derived from unc_q_txl_flits_g0.data",
         "Counter": "0,1,2,3",
-        "EventName": "UNC_Q_TxL_FLITS_G0.DATA",
+        "EventName": "QPI_DATA_BANDWIDTH_TX",
         "PerPkg": "1",
         "ScaleUnit": "8Bytes",
         "UMask": "0x2",
@@ -19,7 +19,7 @@
     {
         "BriefDescription": "Number of non data (control) flits transmitted . Derived from unc_q_txl_flits_g0.non_data",
         "Counter": "0,1,2,3",
-        "EventName": "UNC_Q_TxL_FLITS_G0.NON_DATA",
+        "EventName": "QPI_CTL_BANDWIDTH_TX",
         "PerPkg": "1",
         "ScaleUnit": "8Bytes",
         "UMask": "0x4",
diff --git a/tools/perf/pmu-events/arch/x86/haswellx/uncore-memory.json b/tools/perf/pmu-events/arch/x86/haswellx/uncore-memory.json
index d17dc235f734..66eed399724c 100644
--- a/tools/perf/pmu-events/arch/x86/haswellx/uncore-memory.json
+++ b/tools/perf/pmu-events/arch/x86/haswellx/uncore-memory.json
@@ -3,7 +3,7 @@
         "BriefDescription": "read requests to memory controller. Derived from unc_m_cas_count.rd",
         "Counter": "0,1,2,3",
         "EventCode": "0x4",
-        "EventName": "UNC_M_CAS_COUNT.RD",
+        "EventName": "LLC_MISSES.MEM_READ",
         "PerPkg": "1",
         "ScaleUnit": "64Bytes",
         "UMask": "0x3",
@@ -13,48 +13,51 @@
         "BriefDescription": "write requests to memory controller. Derived from unc_m_cas_count.wr",
         "Counter": "0,1,2,3",
         "EventCode": "0x4",
-        "EventName": "UNC_M_CAS_COUNT.WR",
+        "EventName": "LLC_MISSES.MEM_WRITE",
         "PerPkg": "1",
         "ScaleUnit": "64Bytes",
         "UMask": "0xC",
         "Unit": "iMC"
     },
     {
-        "BriefDescription": "Memory controller clock ticks. Derived from unc_m_clockticks",
+        "BriefDescription": "Memory controller clock ticks",
         "Counter": "0,1,2,3",
         "EventName": "UNC_M_CLOCKTICKS",
         "PerPkg": "1",
         "Unit": "iMC"
     },
     {
-        "BriefDescription": "Cycles where DRAM ranks are in power down (CKE) mode. Derived from unc_m_power_channel_ppd",
+        "BriefDescription": "Cycles where DRAM ranks are in power down (CKE) mode",
         "Counter": "0,1,2,3",
         "EventCode": "0x85",
         "EventName": "UNC_M_POWER_CHANNEL_PPD",
         "MetricExpr": "(UNC_M_POWER_CHANNEL_PPD / UNC_M_CLOCKTICKS) * 100.",
+        "MetricName": "power_channel_ppd %",
         "PerPkg": "1",
         "Unit": "iMC"
     },
     {
-        "BriefDescription": "Cycles all ranks are in critical thermal throttle. Derived from unc_m_power_critical_throttle_cycles",
+        "BriefDescription": "Cycles all ranks are in critical thermal throttle",
         "Counter": "0,1,2,3",
         "EventCode": "0x86",
         "EventName": "UNC_M_POWER_CRITICAL_THROTTLE_CYCLES",
         "MetricExpr": "(UNC_M_POWER_CRITICAL_THROTTLE_CYCLES / UNC_M_CLOCKTICKS) * 100.",
+        "MetricName": "power_critical_throttle_cycles %",
         "PerPkg": "1",
         "Unit": "iMC"
     },
     {
-        "BriefDescription": "Cycles Memory is in self refresh power mode. Derived from unc_m_power_self_refresh",
+        "BriefDescription": "Cycles Memory is in self refresh power mode",
         "Counter": "0,1,2,3",
         "EventCode": "0x43",
         "EventName": "UNC_M_POWER_SELF_REFRESH",
         "MetricExpr": "(UNC_M_POWER_SELF_REFRESH / UNC_M_CLOCKTICKS) * 100.",
+        "MetricName": "power_self_refresh %",
         "PerPkg": "1",
         "Unit": "iMC"
     },
     {
-        "BriefDescription": "Pre-charges due to page misses. Derived from unc_m_pre_count.page_miss",
+        "BriefDescription": "Pre-charges due to page misses",
         "Counter": "0,1,2,3",
         "EventCode": "0x2",
         "EventName": "UNC_M_PRE_COUNT.PAGE_MISS",
@@ -63,7 +66,7 @@
         "Unit": "iMC"
     },
     {
-        "BriefDescription": "Pre-charge for reads. Derived from unc_m_pre_count.rd",
+        "BriefDescription": "Pre-charge for reads",
         "Counter": "0,1,2,3",
         "EventCode": "0x2",
         "EventName": "UNC_M_PRE_COUNT.RD",
@@ -72,7 +75,7 @@
         "Unit": "iMC"
     },
     {
-        "BriefDescription": "Pre-charge for writes. Derived from unc_m_pre_count.wr",
+        "BriefDescription": "Pre-charge for writes",
         "Counter": "0,1,2,3",
         "EventCode": "0x2",
         "EventName": "UNC_M_PRE_COUNT.WR",
diff --git a/tools/perf/pmu-events/arch/x86/haswellx/uncore-power.json b/tools/perf/pmu-events/arch/x86/haswellx/uncore-power.json
index b44d43088bbb..dd1b95655d1d 100644
--- a/tools/perf/pmu-events/arch/x86/haswellx/uncore-power.json
+++ b/tools/perf/pmu-events/arch/x86/haswellx/uncore-power.json
@@ -1,83 +1,91 @@
 [
     {
-        "BriefDescription": "PCU clock ticks. Use to get percentages of PCU cycles events. Derived from unc_p_clockticks",
+        "BriefDescription": "PCU clock ticks. Use to get percentages of PCU cycles events",
         "Counter": "0,1,2,3",
         "EventName": "UNC_P_CLOCKTICKS",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "C0 and C1. Derived from unc_p_power_state_occupancy.cores_c0",
+        "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C0.  It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details",
         "Counter": "0,1,2,3",
         "EventCode": "0x80",
         "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C0",
         "Filter": "occ_sel=1",
         "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C0 / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "power_state_occupancy.cores_c0 %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "C3. Derived from unc_p_power_state_occupancy.cores_c3",
+        "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C3.  It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details",
         "Counter": "0,1,2,3",
         "EventCode": "0x80",
         "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C3",
         "Filter": "occ_sel=2",
         "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C3 / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "power_state_occupancy.cores_c3 %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "C6 and C7. Derived from unc_p_power_state_occupancy.cores_c6",
+        "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C6.  It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events ",
         "Counter": "0,1,2,3",
         "EventCode": "0x80",
         "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C6",
         "Filter": "occ_sel=3",
         "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C6 / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "power_state_occupancy.cores_c6 %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "External Prochot. Derived from unc_p_prochot_external_cycles",
+        "BriefDescription": "Counts the number of cycles that we are in external PROCHOT mode.  This mode is triggered when a sensor off the die determines that something off-die (like DRAM) is too hot and must throttle to avoid damaging the chip",
         "Counter": "0,1,2,3",
         "EventCode": "0xA",
         "EventName": "UNC_P_PROCHOT_EXTERNAL_CYCLES",
         "MetricExpr": "(UNC_P_PROCHOT_EXTERNAL_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "prochot_external_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "Thermal Strongest Upper Limit Cycles. Derived from unc_p_freq_max_limit_thermal_cycles",
+        "BriefDescription": "Counts the number of cycles when temperature is the upper limit on frequency",
         "Counter": "0,1,2,3",
         "EventCode": "0x4",
         "EventName": "UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES",
         "MetricExpr": "(UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_max_limit_thermal_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "OS Strongest Upper Limit Cycles. Derived from unc_p_freq_max_os_cycles",
+        "BriefDescription": "Counts the number of cycles when the OS is the upper limit on frequency",
         "Counter": "0,1,2,3",
         "EventCode": "0x6",
         "EventName": "UNC_P_FREQ_MAX_OS_CYCLES",
         "MetricExpr": "(UNC_P_FREQ_MAX_OS_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_max_os_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "Power Strongest Upper Limit Cycles. Derived from unc_p_freq_max_power_cycles",
+        "BriefDescription": "Counts the number of cycles when power is the upper limit on frequency",
         "Counter": "0,1,2,3",
         "EventCode": "0x5",
         "EventName": "UNC_P_FREQ_MAX_POWER_CYCLES",
         "MetricExpr": "(UNC_P_FREQ_MAX_POWER_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_max_power_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "Cycles spent changing Frequency. Derived from unc_p_freq_trans_cycles",
+        "BriefDescription": "Counts the number of cycles when current is the upper limit on frequency",
         "Counter": "0,1,2,3",
         "EventCode": "0x74",
         "EventName": "UNC_P_FREQ_TRANS_CYCLES",
         "MetricExpr": "(UNC_P_FREQ_TRANS_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_trans_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     }
diff --git a/tools/perf/pmu-events/arch/x86/ivybridge/uncore.json b/tools/perf/pmu-events/arch/x86/ivybridge/uncore.json
new file mode 100644
index 000000000000..42c70eed05a2
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/ivybridge/uncore.json
@@ -0,0 +1,314 @@
+[
+  {
+    "Unit": "CBO",
+    "EventCode": "0x22",
+    "UMask": "0x01",
+    "EventName": "UNC_CBO_XSNP_RESPONSE.MISS",
+    "BriefDescription": "A snoop misses in some processor core.",
+    "PublicDescription": "A snoop misses in some processor core.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x22",
+    "UMask": "0x02",
+    "EventName": "UNC_CBO_XSNP_RESPONSE.INVAL",
+    "BriefDescription": "A snoop invalidates a non-modified line in some processor core.",
+    "PublicDescription": "A snoop invalidates a non-modified line in some processor core.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x22",
+    "UMask": "0x04",
+    "EventName": "UNC_CBO_XSNP_RESPONSE.HIT",
+    "BriefDescription": "A snoop hits a non-modified line in some processor core.",
+    "PublicDescription": "A snoop hits a non-modified line in some processor core.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x22",
+    "UMask": "0x08",
+    "EventName": "UNC_CBO_XSNP_RESPONSE.HITM",
+    "BriefDescription": "A snoop hits a modified line in some processor core.",
+    "PublicDescription": "A snoop hits a modified line in some processor core.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x22",
+    "UMask": "0x10",
+    "EventName": "UNC_CBO_XSNP_RESPONSE.INVAL_M",
+    "BriefDescription": "A snoop invalidates a modified line in some processor core.",
+    "PublicDescription": "A snoop invalidates a modified line in some processor core.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x22",
+    "UMask": "0x20",
+    "EventName": "UNC_CBO_XSNP_RESPONSE.EXTERNAL_FILTER",
+    "BriefDescription": "Filter on cross-core snoops initiated by this Cbox due to external snoop request.",
+    "PublicDescription": "Filter on cross-core snoops initiated by this Cbox due to external snoop request.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x22",
+    "UMask": "0x40",
+    "EventName": "UNC_CBO_XSNP_RESPONSE.XCORE_FILTER",
+    "BriefDescription": "Filter on cross-core snoops initiated by this Cbox due to processor core memory request.",
+    "PublicDescription": "Filter on cross-core snoops initiated by this Cbox due to processor core memory request.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x22",
+    "UMask": "0x80",
+    "EventName": "UNC_CBO_XSNP_RESPONSE.EVICTION_FILTER",
+    "BriefDescription": "Filter on cross-core snoops initiated by this Cbox due to LLC eviction.",
+    "PublicDescription": "Filter on cross-core snoops initiated by this Cbox due to LLC eviction.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x01",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.M",
+    "BriefDescription": "LLC lookup request that access cache and found line in M-state.",
+    "PublicDescription": "LLC lookup request that access cache and found line in M-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x02",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.E",
+    "BriefDescription": "LLC lookup request that access cache and found line in E-state.",
+    "PublicDescription": "LLC lookup request that access cache and found line in E-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x04",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.S",
+    "BriefDescription": "LLC lookup request that access cache and found line in S-state.",
+    "PublicDescription": "LLC lookup request that access cache and found line in S-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x08",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.I",
+    "BriefDescription": "LLC lookup request that access cache and found line in I-state.",
+    "PublicDescription": "LLC lookup request that access cache and found line in I-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x10",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.READ_FILTER",
+    "BriefDescription": "Filter on processor core initiated cacheable read requests.",
+    "PublicDescription": "Filter on processor core initiated cacheable read requests.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x20",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_FILTER",
+    "BriefDescription": "Filter on processor core initiated cacheable write requests.",
+    "PublicDescription": "Filter on processor core initiated cacheable write requests.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x40",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.EXTSNP_FILTER",
+    "BriefDescription": "Filter on external snoop requests.",
+    "PublicDescription": "Filter on external snoop requests.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x80",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_REQUEST_FILTER",
+    "BriefDescription": "Filter on any IRQ or IPQ initiated requests including uncacheable, non-coherent requests.",
+    "PublicDescription": "Filter on any IRQ or IPQ initiated requests including uncacheable, non-coherent requests.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "ARB",
+    "EventCode": "0x80",
+    "UMask": "0x01",
+    "EventName": "UNC_ARB_TRK_OCCUPANCY.ALL",
+    "BriefDescription": "Counts cycles weighted by the number of requests waiting for data returning from the memory controller. Accounts for coherent and non-coherent requests initiated by IA cores, processor graphic units, or LLC.",
+    "PublicDescription": "Counts cycles weighted by the number of requests waiting for data returning from the memory controller. Accounts for coherent and non-coherent requests initiated by IA cores, processor graphic units, or LLC.",
+    "Counter": "0",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "ARB",
+    "EventCode": "0x81",
+    "UMask": "0x01",
+    "EventName": "UNC_ARB_TRK_REQUESTS.ALL",
+    "BriefDescription": "Counts the number of coherent and in-coherent requests initiated by IA cores, processor graphic units, or LLC.",
+    "PublicDescription": "Counts the number of coherent and in-coherent requests initiated by IA cores, processor graphic units, or LLC.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "ARB",
+    "EventCode": "0x81",
+    "UMask": "0x20",
+    "EventName": "UNC_ARB_TRK_REQUESTS.WRITES",
+    "BriefDescription": "Counts the number of allocated write entries, include full, partial, and LLC evictions.",
+    "PublicDescription": "Counts the number of allocated write entries, include full, partial, and LLC evictions.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "ARB",
+    "EventCode": "0x81",
+    "UMask": "0x80",
+    "EventName": "UNC_ARB_TRK_REQUESTS.EVICTIONS",
+    "BriefDescription": "Counts the number of LLC evictions allocated.",
+    "PublicDescription": "Counts the number of LLC evictions allocated.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "ARB",
+    "EventCode": "0x83",
+    "UMask": "0x01",
+    "EventName": "UNC_ARB_COH_TRK_OCCUPANCY.ALL",
+    "BriefDescription": "Cycles weighted by number of requests pending in Coherency Tracker.",
+    "PublicDescription": "Cycles weighted by number of requests pending in Coherency Tracker.",
+    "Counter": "0",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "ARB",
+    "EventCode": "0x84",
+    "UMask": "0x01",
+    "EventName": "UNC_ARB_COH_TRK_REQUESTS.ALL",
+    "BriefDescription": "Number of requests allocated in Coherency Tracker.",
+    "PublicDescription": "Number of requests allocated in Coherency Tracker.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "ARB",
+    "EventCode": "0x80",
+    "UMask": "0x01",
+    "EventName": "UNC_ARB_TRK_OCCUPANCY.CYCLES_WITH_ANY_REQUEST",
+    "BriefDescription": "Cycles with at least one request outstanding is waiting for data return from memory controller. Account for coherent and non-coherent requests initiated by IA Cores, Processor Graphics Unit, or LLC.",
+    "PublicDescription": "Cycles with at least one request outstanding is waiting for data return from memory controller. Account for coherent and non-coherent requests initiated by IA Cores, Processor Graphics Unit, or LLC.",
+    "Counter": "0,1",
+    "CounterMask": "1",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "ARB",
+    "EventCode": "0x80",
+    "UMask": "0x01",
+    "EventName": "UNC_ARB_TRK_OCCUPANCY.CYCLES_OVER_HALF_FULL",
+    "BriefDescription": "Cycles with at least half of the requests outstanding are waiting for data return from memory controller. Account for coherent and non-coherent requests initiated by IA Cores, Processor Graphics Unit, or LLC.",
+    "PublicDescription": "Cycles with at least half of the requests outstanding are waiting for data return from memory controller. Account for coherent and non-coherent requests initiated by IA Cores, Processor Graphics Unit, or LLC.",
+    "Counter": "0,1",
+    "CounterMask": "10",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "ARB",
+    "EventCode": "0x0",
+    "UMask": "0x01",
+    "EventName": "UNC_CLOCK.SOCKET",
+    "BriefDescription": "This 48-bit fixed counter counts the UCLK cycles.",
+    "PublicDescription": "This 48-bit fixed counter counts the UCLK cycles.",
+    "Counter": "Fixed",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x06",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.ES",
+    "BriefDescription": "LLC lookup request that access cache and found line in E-state or S-state.",
+    "PublicDescription": "LLC lookup request that access cache and found line in E-state or S-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  }
+]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/ivytown/uncore-cache.json b/tools/perf/pmu-events/arch/x86/ivytown/uncore-cache.json
index 2efdc6772e0b..267410594833 100644
--- a/tools/perf/pmu-events/arch/x86/ivytown/uncore-cache.json
+++ b/tools/perf/pmu-events/arch/x86/ivytown/uncore-cache.json
@@ -1,13 +1,13 @@
 [
     {
-        "BriefDescription": "Uncore cache clock ticks. Derived from unc_c_clockticks",
+        "BriefDescription": "Uncore cache clock ticks",
         "Counter": "0,1,2,3",
         "EventName": "UNC_C_CLOCKTICKS",
         "PerPkg": "1",
         "Unit": "CBO"
     },
     {
-        "BriefDescription": "All LLC Misses (code+ data rd + data wr - including demand and prefetch). Derived from unc_c_llc_lookup.any",
+        "BriefDescription": "All LLC Misses (code+ data rd + data wr - including demand and prefetch)",
         "Counter": "0,1",
         "EventCode": "0x34",
         "EventName": "UNC_C_LLC_LOOKUP.ANY",
@@ -18,7 +18,7 @@
         "Unit": "CBO"
     },
     {
-        "BriefDescription": "M line evictions from LLC (writebacks to memory). Derived from unc_c_llc_victims.m_state",
+        "BriefDescription": "M line evictions from LLC (writebacks to memory)",
         "Counter": "0,1",
         "EventCode": "0x37",
         "EventName": "UNC_C_LLC_VICTIMS.M_STATE",
@@ -237,7 +237,7 @@
         "Unit": "CBO"
     },
     {
-        "BriefDescription": "Occupancy for all LLC misses that are addressed to local memory. Derived from unc_c_tor_occupancy.miss_local",
+        "BriefDescription": "Occupancy for all LLC misses that are addressed to local memory",
         "EventCode": "0x36",
         "EventName": "UNC_C_TOR_OCCUPANCY.MISS_LOCAL",
         "PerPkg": "1",
@@ -254,7 +254,7 @@
         "Unit": "CBO"
     },
     {
-        "BriefDescription": "Occupancy for all LLC misses that are addressed to remote memory. Derived from unc_c_tor_occupancy.miss_remote",
+        "BriefDescription": "Occupancy for all LLC misses that are addressed to remote memory",
         "EventCode": "0x36",
         "EventName": "UNC_C_TOR_OCCUPANCY.MISS_REMOTE",
         "PerPkg": "1",
@@ -262,7 +262,7 @@
         "Unit": "CBO"
     },
     {
-        "BriefDescription": "Read requests to home agent. Derived from unc_h_requests.reads",
+        "BriefDescription": "Read requests to home agent",
         "Counter": "0,1,2,3",
         "EventCode": "0x1",
         "EventName": "UNC_H_REQUESTS.READS",
@@ -271,7 +271,7 @@
         "Unit": "HA"
     },
     {
-        "BriefDescription": "Write requests to home agent. Derived from unc_h_requests.writes",
+        "BriefDescription": "Write requests to home agent",
         "Counter": "0,1,2,3",
         "EventCode": "0x1",
         "EventName": "UNC_H_REQUESTS.WRITES",
@@ -280,7 +280,7 @@
         "Unit": "HA"
     },
     {
-        "BriefDescription": "M line forwarded from remote cache along with writeback to memory. Derived from unc_h_snoop_resp.rsp_fwd_wb",
+        "BriefDescription": "M line forwarded from remote cache along with writeback to memory",
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "UNC_H_SNOOP_RESP.RSP_FWD_WB",
@@ -290,7 +290,7 @@
         "Unit": "HA"
     },
     {
-        "BriefDescription": "M line forwarded from remote cache with no writeback to memory. Derived from unc_h_snoop_resp.rspifwd",
+        "BriefDescription": "M line forwarded from remote cache with no writeback to memory",
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "UNC_H_SNOOP_RESP.RSPIFWD",
@@ -300,7 +300,7 @@
         "Unit": "HA"
     },
     {
-        "BriefDescription": "Shared line response from remote cache. Derived from unc_h_snoop_resp.rsps",
+        "BriefDescription": "Shared line response from remote cache",
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "UNC_H_SNOOP_RESP.RSPS",
@@ -310,7 +310,7 @@
         "Unit": "HA"
     },
     {
-        "BriefDescription": "Shared line forwarded from remote cache. Derived from unc_h_snoop_resp.rspsfwd",
+        "BriefDescription": "Shared line forwarded from remote cache",
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "UNC_H_SNOOP_RESP.RSPSFWD",
diff --git a/tools/perf/pmu-events/arch/x86/ivytown/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/ivytown/uncore-interconnect.json
index d7e2fda1d695..b798a860bc81 100644
--- a/tools/perf/pmu-events/arch/x86/ivytown/uncore-interconnect.json
+++ b/tools/perf/pmu-events/arch/x86/ivytown/uncore-interconnect.json
@@ -1,6 +1,6 @@
 [
     {
-        "BriefDescription": "QPI clock ticks. Use to get percentages for QPI cycles events. Derived from unc_q_clockticks",
+        "BriefDescription": "QPI clock ticks. Use to get percentages for QPI cycles events",
         "Counter": "0,1,2,3",
         "EventCode": "0x14",
         "EventName": "UNC_Q_CLOCKTICKS",
@@ -8,25 +8,27 @@
         "Unit": "QPI LL"
     },
     {
-        "BriefDescription": "Cycles where receiving QPI link is in half-width mode. Derived from unc_q_rxl0p_power_cycles",
+        "BriefDescription": "Cycles where receiving QPI link is in half-width mode",
         "Counter": "0,1,2,3",
         "EventCode": "0x10",
         "EventName": "UNC_Q_RxL0P_POWER_CYCLES",
         "MetricExpr": "(UNC_Q_RxL0P_POWER_CYCLES / UNC_Q_CLOCKTICKS) * 100.",
+        "MetricName": "rxl0p_power_cycles %",
         "PerPkg": "1",
         "Unit": "QPI LL"
     },
     {
-        "BriefDescription": "Cycles where transmitting QPI link is in half-width mode. Derived from unc_q_txl0p_power_cycles",
+        "BriefDescription": "Cycles where transmitting QPI link is in half-width mode",
         "Counter": "0,1,2,3",
         "EventCode": "0xd",
         "EventName": "UNC_Q_TxL0P_POWER_CYCLES",
         "MetricExpr": "(UNC_Q_TxL0P_POWER_CYCLES / UNC_Q_CLOCKTICKS) * 100.",
+        "MetricName": "txl0p_power_cycles %",
         "PerPkg": "1",
         "Unit": "QPI LL"
     },
     {
-        "BriefDescription": "Number of data flits transmitted . Derived from unc_q_txl_flits_g0.data",
+        "BriefDescription": "Number of data flits transmitted ",
         "Counter": "0,1,2,3",
         "EventName": "UNC_Q_TxL_FLITS_G0.DATA",
         "PerPkg": "1",
@@ -35,7 +37,7 @@
         "Unit": "QPI LL"
     },
     {
-        "BriefDescription": "Number of non data (control) flits transmitted . Derived from unc_q_txl_flits_g0.non_data",
+        "BriefDescription": "Number of non data (control) flits transmitted ",
         "Counter": "0,1,2,3",
         "EventName": "UNC_Q_TxL_FLITS_G0.NON_DATA",
         "PerPkg": "1",
diff --git a/tools/perf/pmu-events/arch/x86/ivytown/uncore-memory.json b/tools/perf/pmu-events/arch/x86/ivytown/uncore-memory.json
index ac4ad4d6357b..df4b43294fa0 100644
--- a/tools/perf/pmu-events/arch/x86/ivytown/uncore-memory.json
+++ b/tools/perf/pmu-events/arch/x86/ivytown/uncore-memory.json
@@ -1,6 +1,6 @@
 [
     {
-        "BriefDescription": "Memory page activates for reads and writes. Derived from unc_m_act_count.rd",
+        "BriefDescription": "Memory page activates for reads and writes",
         "Counter": "0,1,2,3",
         "EventCode": "0x1",
         "EventName": "UNC_M_ACT_COUNT.RD",
@@ -13,7 +13,7 @@
         "BriefDescription": "Read requests to memory controller. Derived from unc_m_cas_count.rd",
         "Counter": "0,1,2,3",
         "EventCode": "0x4",
-        "EventName": "UNC_M_CAS_COUNT.RD",
+        "EventName": "LLC_MISSES.MEM_READ",
         "PerPkg": "1",
         "ScaleUnit": "64Bytes",
         "UMask": "0x3",
@@ -23,48 +23,51 @@
         "BriefDescription": "Write requests to memory controller. Derived from unc_m_cas_count.wr",
         "Counter": "0,1,2,3",
         "EventCode": "0x4",
-        "EventName": "UNC_M_CAS_COUNT.WR",
+        "EventName": "LLC_MISSES.MEM_WRITE",
         "PerPkg": "1",
         "ScaleUnit": "64Bytes",
         "UMask": "0xC",
         "Unit": "iMC"
     },
     {
-        "BriefDescription": "Memory controller clock ticks. Use to generate percentages for memory controller CYCLES events. Derived from unc_m_clockticks",
+        "BriefDescription": "Memory controller clock ticks. Use to generate percentages for memory controller CYCLES events",
         "Counter": "0,1,2,3",
         "EventName": "UNC_M_CLOCKTICKS",
         "PerPkg": "1",
         "Unit": "iMC"
     },
     {
-        "BriefDescription": "Cycles where DRAM ranks are in power down (CKE) mode. Derived from unc_m_power_channel_ppd",
+        "BriefDescription": "Cycles where DRAM ranks are in power down (CKE) mode",
         "Counter": "0,1,2,3",
         "EventCode": "0x85",
         "EventName": "UNC_M_POWER_CHANNEL_PPD",
         "MetricExpr": "(UNC_M_POWER_CHANNEL_PPD / UNC_M_CLOCKTICKS) * 100.",
+        "MetricName": "power_channel_ppd %",
         "PerPkg": "1",
         "Unit": "iMC"
     },
     {
-        "BriefDescription": "Cycles all ranks are in critical thermal throttle. Derived from unc_m_power_critical_throttle_cycles",
+        "BriefDescription": "Cycles all ranks are in critical thermal throttle",
         "Counter": "0,1,2,3",
         "EventCode": "0x86",
         "EventName": "UNC_M_POWER_CRITICAL_THROTTLE_CYCLES",
         "MetricExpr": "(UNC_M_POWER_CRITICAL_THROTTLE_CYCLES / UNC_M_CLOCKTICKS) * 100.",
+        "MetricName": "power_critical_throttle_cycles %",
         "PerPkg": "1",
         "Unit": "iMC"
     },
     {
-        "BriefDescription": "Cycles Memory is in self refresh power mode. Derived from unc_m_power_self_refresh",
+        "BriefDescription": "Cycles Memory is in self refresh power mode",
         "Counter": "0,1,2,3",
         "EventCode": "0x43",
         "EventName": "UNC_M_POWER_SELF_REFRESH",
         "MetricExpr": "(UNC_M_POWER_SELF_REFRESH / UNC_M_CLOCKTICKS) * 100.",
+        "MetricName": "power_self_refresh %",
         "PerPkg": "1",
         "Unit": "iMC"
     },
     {
-        "BriefDescription": "Memory page conflicts. Derived from unc_m_pre_count.page_miss",
+        "BriefDescription": "Memory page conflicts",
         "Counter": "0,1,2,3",
         "EventCode": "0x2",
         "EventName": "UNC_M_PRE_COUNT.PAGE_MISS",
diff --git a/tools/perf/pmu-events/arch/x86/ivytown/uncore-power.json b/tools/perf/pmu-events/arch/x86/ivytown/uncore-power.json
index dc2586db0dfc..d40498f2cb1e 100644
--- a/tools/perf/pmu-events/arch/x86/ivytown/uncore-power.json
+++ b/tools/perf/pmu-events/arch/x86/ivytown/uncore-power.json
@@ -1,44 +1,48 @@
 [
     {
-        "BriefDescription": "PCU clock ticks. Use to get percentages of PCU cycles events. Derived from unc_p_clockticks",
+        "BriefDescription": "PCU clock ticks. Use to get percentages of PCU cycles events",
         "Counter": "0,1,2,3",
         "EventName": "UNC_P_CLOCKTICKS",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter.  (filter_band0=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band0_cycles",
+        "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter.  (filter_band0=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency",
         "Counter": "0,1,2,3",
         "EventCode": "0xb",
         "EventName": "UNC_P_FREQ_BAND0_CYCLES",
         "MetricExpr": "(UNC_P_FREQ_BAND0_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_band0_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter.  (filter_band1=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band1_cycles",
+        "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter.  (filter_band1=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency",
         "Counter": "0,1,2,3",
         "EventCode": "0xc",
         "EventName": "UNC_P_FREQ_BAND1_CYCLES",
         "MetricExpr": "(UNC_P_FREQ_BAND1_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_band1_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter.  (filter_band2=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band2_cycles",
+        "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter.  (filter_band2=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency",
         "Counter": "0,1,2,3",
         "EventCode": "0xd",
         "EventName": "UNC_P_FREQ_BAND2_CYCLES",
         "MetricExpr": "(UNC_P_FREQ_BAND2_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_band2_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter.  (filter_band3=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band3_cycles",
+        "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter.  (filter_band3=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency",
         "Counter": "0,1,2,3",
         "EventCode": "0xe",
         "EventName": "UNC_P_FREQ_BAND3_CYCLES",
         "MetricExpr": "(UNC_P_FREQ_BAND3_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_band3_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
@@ -49,6 +53,7 @@
         "EventName": "UNC_P_FREQ_BAND0_TRANSITIONS",
         "Filter": "edge=1",
         "MetricExpr": "(UNC_P_FREQ_BAND0_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_band0_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
@@ -59,6 +64,7 @@
         "EventName": "UNC_P_FREQ_BAND1_TRANSITIONS",
         "Filter": "edge=1",
         "MetricExpr": "(UNC_P_FREQ_BAND1_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_band1_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
@@ -69,6 +75,7 @@
         "EventName": "UNC_P_FREQ_BAND2_TRANSITIONS",
         "Filter": "edge=1",
         "MetricExpr": "(UNC_P_FREQ_BAND2_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_band2_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
@@ -79,90 +86,100 @@
         "EventName": "UNC_P_FREQ_BAND3_TRANSITIONS",
         "Filter": "edge=1",
         "MetricExpr": "(UNC_P_FREQ_BAND3_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_band3_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "This is an occupancy event that tracks the number of cores that are in the chosen C-State.  It can be used by itself to get the average number of cores in that C-state with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details. Derived from unc_p_power_state_occupancy.cores_c0",
+        "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C0.  It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details",
         "Counter": "0,1,2,3",
         "EventCode": "0x80",
         "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C0",
         "Filter": "occ_sel=1",
         "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C0 / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "power_state_occupancy.cores_c0 %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "This is an occupancy event that tracks the number of cores that are in the chosen C-State.  It can be used by itself to get the average number of cores in that C-state with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details. Derived from unc_p_power_state_occupancy.cores_c3",
+        "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C3.  It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details",
         "Counter": "0,1,2,3",
         "EventCode": "0x80",
         "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C3",
         "Filter": "occ_sel=2",
         "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C3 / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "power_state_occupancy.cores_c3 %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "This is an occupancy event that tracks the number of cores that are in the chosen C-State.  It can be used by itself to get the average number of cores in that C-state with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details. Derived from unc_p_power_state_occupancy.cores_c6",
+        "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C6.  It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events ",
         "Counter": "0,1,2,3",
         "EventCode": "0x80",
         "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C6",
         "Filter": "occ_sel=3",
         "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C6 / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "power_state_occupancy.cores_c6 %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "Counts the number of cycles that we are in external PROCHOT mode.  This mode is triggered when a sensor off the die determines that something off-die (like DRAM) is too hot and must throttle to avoid damaging the chip. Derived from unc_p_prochot_external_cycles",
+        "BriefDescription": "Counts the number of cycles that we are in external PROCHOT mode.  This mode is triggered when a sensor off the die determines that something off-die (like DRAM) is too hot and must throttle to avoid damaging the chip",
         "Counter": "0,1,2,3",
         "EventCode": "0xa",
         "EventName": "UNC_P_PROCHOT_EXTERNAL_CYCLES",
         "MetricExpr": "(UNC_P_PROCHOT_EXTERNAL_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "prochot_external_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "Counts the number of cycles when thermal conditions are the upper limit on frequency.  This is related to the THERMAL_THROTTLE CYCLES_ABOVE_TEMP event, which always counts cycles when we are above the thermal temperature.  This event (STRONGEST_UPPER_LIMIT) is sampled at the output of the algorithm that determines the actual frequency, while THERMAL_THROTTLE looks at the input. Derived from unc_p_freq_max_limit_thermal_cycles",
+        "BriefDescription": "Counts the number of cycles when temperature is the upper limit on frequency",
         "Counter": "0,1,2,3",
         "EventCode": "0x4",
         "EventName": "UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES",
         "MetricExpr": "(UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_max_limit_thermal_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "Counts the number of cycles when the OS is the upper limit on frequency. Derived from unc_p_freq_max_os_cycles",
+        "BriefDescription": "Counts the number of cycles when the OS is the upper limit on frequency",
         "Counter": "0,1,2,3",
         "EventCode": "0x6",
         "EventName": "UNC_P_FREQ_MAX_OS_CYCLES",
         "MetricExpr": "(UNC_P_FREQ_MAX_OS_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_max_os_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "Counts the number of cycles when power is the upper limit on frequency. Derived from unc_p_freq_max_power_cycles",
+        "BriefDescription": "Counts the number of cycles when power is the upper limit on frequency",
         "Counter": "0,1,2,3",
         "EventCode": "0x5",
         "EventName": "UNC_P_FREQ_MAX_POWER_CYCLES",
         "MetricExpr": "(UNC_P_FREQ_MAX_POWER_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_max_power_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "Counts the number of cycles when current is the upper limit on frequency. Derived from unc_p_freq_max_current_cycles",
+        "BriefDescription": "Counts the number of cycles when current is the upper limit on frequency",
         "Counter": "0,1,2,3",
         "EventCode": "0x7",
         "EventName": "UNC_P_FREQ_MAX_CURRENT_CYCLES",
         "MetricExpr": "(UNC_P_FREQ_MAX_CURRENT_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_max_current_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "Counts the number of cycles when the system is changing frequency.  This can not be filtered by thread ID.  One can also use it with the occupancy counter that monitors number of threads in C0 to estimate the performance impact that frequency transitions had on the system. Derived from unc_p_freq_trans_cycles",
+        "BriefDescription": "Cycles spent changing Frequency",
         "Counter": "0,1,2,3",
         "EventCode": "0x60",
         "EventName": "UNC_P_FREQ_TRANS_CYCLES",
         "MetricExpr": "(UNC_P_FREQ_TRANS_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_trans_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
@@ -173,6 +190,7 @@
         "EventName": "UNC_P_FREQ_GE_1200MHZ_CYCLES",
         "Filter": "filter_band0=1200",
         "MetricExpr": "(UNC_P_FREQ_GE_1200MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_ge_1200mhz_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
@@ -183,6 +201,7 @@
         "EventName": "UNC_P_FREQ_GE_2000MHZ_CYCLES",
         "Filter": "filter_band1=2000",
         "MetricExpr": "(UNC_P_FREQ_GE_2000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_ge_2000mhz_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
@@ -193,6 +212,7 @@
         "EventName": "UNC_P_FREQ_GE_3000MHZ_CYCLES",
         "Filter": "filter_band2=3000",
         "MetricExpr": "(UNC_P_FREQ_GE_3000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_ge_3000mhz_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
@@ -203,6 +223,7 @@
         "EventName": "UNC_P_FREQ_GE_4000MHZ_CYCLES",
         "Filter": "filter_band3=4000",
         "MetricExpr": "(UNC_P_FREQ_GE_4000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_ge_4000mhz_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
@@ -213,6 +234,7 @@
         "EventName": "UNC_P_FREQ_GE_1200MHZ_TRANSITIONS",
         "Filter": "edge=1,filter_band0=1200",
         "MetricExpr": "(UNC_P_FREQ_GE_1200MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_ge_1200mhz_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
@@ -223,6 +245,7 @@
         "EventName": "UNC_P_FREQ_GE_2000MHZ_TRANSITIONS",
         "Filter": "edge=1,filter_band1=2000",
         "MetricExpr": "(UNC_P_FREQ_GE_2000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_ge_2000mhz_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
@@ -233,6 +256,7 @@
         "EventName": "UNC_P_FREQ_GE_3000MHZ_TRANSITIONS",
         "Filter": "edge=1,filter_band2=4000",
         "MetricExpr": "(UNC_P_FREQ_GE_3000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_ge_3000mhz_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
@@ -243,6 +267,7 @@
         "EventName": "UNC_P_FREQ_GE_4000MHZ_TRANSITIONS",
         "Filter": "edge=1,filter_band3=4000",
         "MetricExpr": "(UNC_P_FREQ_GE_4000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_ge_4000mhz_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     }
diff --git a/tools/perf/pmu-events/arch/x86/jaketown/uncore-cache.json b/tools/perf/pmu-events/arch/x86/jaketown/uncore-cache.json
index 2f23cf0129e7..3fa61d962607 100644
--- a/tools/perf/pmu-events/arch/x86/jaketown/uncore-cache.json
+++ b/tools/perf/pmu-events/arch/x86/jaketown/uncore-cache.json
@@ -1,13 +1,13 @@
 [
     {
-        "BriefDescription": "Uncore cache clock ticks. Derived from unc_c_clockticks",
+        "BriefDescription": "Uncore cache clock ticks",
         "Counter": "0,1,2,3",
         "EventName": "UNC_C_CLOCKTICKS",
         "PerPkg": "1",
         "Unit": "CBO"
     },
     {
-        "BriefDescription": "All LLC Misses (code+ data rd + data wr - including demand and prefetch). Derived from unc_c_llc_lookup.any",
+        "BriefDescription": "All LLC Misses (code+ data rd + data wr - including demand and prefetch)",
         "Counter": "0,1",
         "EventCode": "0x34",
         "EventName": "UNC_C_LLC_LOOKUP.ANY",
@@ -18,7 +18,7 @@
         "Unit": "CBO"
     },
     {
-        "BriefDescription": "M line evictions from LLC (writebacks to memory). Derived from unc_c_llc_victims.m_state",
+        "BriefDescription": "M line evictions from LLC (writebacks to memory)",
         "Counter": "0,1",
         "EventCode": "0x37",
         "EventName": "UNC_C_LLC_VICTIMS.M_STATE",
@@ -171,11 +171,12 @@
         "Unit": "CBO"
     },
     {
-        "BriefDescription": "Occupancy counter for all LLC misses; we divide this by UNC_C_CLOCKTICKS to get average Q depth. Derived from unc_c_tor_occupancy.miss_all",
+        "BriefDescription": "Occupancy counter for all LLC misses; we divide this by UNC_C_CLOCKTICKS to get average Q depth",
         "EventCode": "0x36",
         "EventName": "UNC_C_TOR_OCCUPANCY.MISS_ALL",
         "Filter": "filter_opc=0x182",
         "MetricExpr": "(UNC_C_TOR_OCCUPANCY.MISS_ALL / UNC_C_CLOCKTICKS) * 100.",
+        "MetricName": "tor_occupancy.miss_all %",
         "PerPkg": "1",
         "UMask": "0xa",
         "Unit": "CBO"
@@ -189,7 +190,7 @@
         "Unit": "CBO"
     },
     {
-        "BriefDescription": "read requests to home agent. Derived from unc_h_requests.reads",
+        "BriefDescription": "read requests to home agent",
         "Counter": "0,1,2,3",
         "EventCode": "0x1",
         "EventName": "UNC_H_REQUESTS.READS",
@@ -198,7 +199,7 @@
         "Unit": "HA"
     },
     {
-        "BriefDescription": "write requests to home agent. Derived from unc_h_requests.writes",
+        "BriefDescription": "write requests to home agent",
         "Counter": "0,1,2,3",
         "EventCode": "0x1",
         "EventName": "UNC_H_REQUESTS.WRITES",
diff --git a/tools/perf/pmu-events/arch/x86/jaketown/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/jaketown/uncore-interconnect.json
index 63351876eb57..1b53c0e609e3 100644
--- a/tools/perf/pmu-events/arch/x86/jaketown/uncore-interconnect.json
+++ b/tools/perf/pmu-events/arch/x86/jaketown/uncore-interconnect.json
@@ -1,6 +1,6 @@
 [
     {
-        "BriefDescription": "QPI clock ticks. Used to get percentages of QPI cycles events. Derived from unc_q_clockticks",
+        "BriefDescription": "QPI clock ticks. Used to get percentages of QPI cycles events",
         "Counter": "0,1,2,3",
         "EventCode": "0x14",
         "EventName": "UNC_Q_CLOCKTICKS",
@@ -8,25 +8,27 @@
         "Unit": "QPI LL"
     },
     {
-        "BriefDescription": "Cycles where receiving QPI link is in half-width mode. Derived from unc_q_rxl0p_power_cycles",
+        "BriefDescription": "Cycles where receiving QPI link is in half-width mode",
         "Counter": "0,1,2,3",
         "EventCode": "0x10",
         "EventName": "UNC_Q_RxL0P_POWER_CYCLES",
         "MetricExpr": "(UNC_Q_RxL0P_POWER_CYCLES / UNC_Q_CLOCKTICKS) * 100.",
+        "MetricName": "rxl0p_power_cycles %",
         "PerPkg": "1",
         "Unit": "QPI LL"
     },
     {
-        "BriefDescription": "Cycles where transmitting QPI link is in half-width mode. Derived from unc_q_txl0p_power_cycles",
+        "BriefDescription": "Cycles where transmitting QPI link is in half-width mode",
         "Counter": "0,1,2,3",
         "EventCode": "0xd",
         "EventName": "UNC_Q_TxL0P_POWER_CYCLES",
         "MetricExpr": "(UNC_Q_TxL0P_POWER_CYCLES / UNC_Q_CLOCKTICKS) * 100.",
+        "MetricName": "txl0p_power_cycles %",
         "PerPkg": "1",
         "Unit": "QPI LL"
     },
     {
-        "BriefDescription": "Number of data flits transmitted . Derived from unc_q_txl_flits_g0.data",
+        "BriefDescription": "Number of data flits transmitted ",
         "Counter": "0,1,2,3",
         "EventName": "UNC_Q_TxL_FLITS_G0.DATA",
         "PerPkg": "1",
@@ -35,7 +37,7 @@
         "Unit": "QPI LL"
     },
     {
-        "BriefDescription": "Number of non data (control) flits transmitted . Derived from unc_q_txl_flits_g0.non_data",
+        "BriefDescription": "Number of non data (control) flits transmitted ",
         "Counter": "0,1,2,3",
         "EventName": "UNC_Q_TxL_FLITS_G0.NON_DATA",
         "PerPkg": "1",
diff --git a/tools/perf/pmu-events/arch/x86/jaketown/uncore-memory.json b/tools/perf/pmu-events/arch/x86/jaketown/uncore-memory.json
index e2cf6daa7b37..8551cebeba23 100644
--- a/tools/perf/pmu-events/arch/x86/jaketown/uncore-memory.json
+++ b/tools/perf/pmu-events/arch/x86/jaketown/uncore-memory.json
@@ -1,6 +1,6 @@
 [
     {
-        "BriefDescription": "Memory page activates. Derived from unc_m_act_count",
+        "BriefDescription": "Memory page activates",
         "Counter": "0,1,2,3",
         "EventCode": "0x1",
         "EventName": "UNC_M_ACT_COUNT",
@@ -11,7 +11,7 @@
         "BriefDescription": "read requests to memory controller. Derived from unc_m_cas_count.rd",
         "Counter": "0,1,2,3",
         "EventCode": "0x4",
-        "EventName": "UNC_M_CAS_COUNT.RD",
+        "EventName": "LLC_MISSES.MEM_READ",
         "PerPkg": "1",
         "UMask": "0x3",
         "Unit": "iMC"
@@ -20,47 +20,50 @@
         "BriefDescription": "write requests to memory controller. Derived from unc_m_cas_count.wr",
         "Counter": "0,1,2,3",
         "EventCode": "0x4",
-        "EventName": "UNC_M_CAS_COUNT.WR",
+        "EventName": "LLC_MISSES.MEM_WRITE",
         "PerPkg": "1",
         "UMask": "0xc",
         "Unit": "iMC"
     },
     {
-        "BriefDescription": "Memory controller clock ticks. Used to get percentages of memory controller cycles events. Derived from unc_m_clockticks",
+        "BriefDescription": "Memory controller clock ticks. Used to get percentages of memory controller cycles events",
         "Counter": "0,1,2,3",
         "EventName": "UNC_M_CLOCKTICKS",
         "PerPkg": "1",
         "Unit": "iMC"
     },
     {
-        "BriefDescription": "Cycles where DRAM ranks are in power down (CKE) mode. Derived from unc_m_power_channel_ppd",
+        "BriefDescription": "Cycles where DRAM ranks are in power down (CKE) mode",
         "Counter": "0,1,2,3",
         "EventCode": "0x85",
         "EventName": "UNC_M_POWER_CHANNEL_PPD",
         "MetricExpr": "(UNC_M_POWER_CHANNEL_PPD / UNC_M_CLOCKTICKS) * 100.",
+        "MetricName": "power_channel_ppd %",
         "PerPkg": "1",
         "Unit": "iMC"
     },
     {
-        "BriefDescription": "Cycles all ranks are in critical thermal throttle. Derived from unc_m_power_critical_throttle_cycles",
+        "BriefDescription": "Cycles all ranks are in critical thermal throttle",
         "Counter": "0,1,2,3",
         "EventCode": "0x86",
         "EventName": "UNC_M_POWER_CRITICAL_THROTTLE_CYCLES",
         "MetricExpr": "(UNC_M_POWER_CRITICAL_THROTTLE_CYCLES / UNC_M_CLOCKTICKS) * 100.",
+        "MetricName": "power_critical_throttle_cycles %",
         "PerPkg": "1",
         "Unit": "iMC"
     },
     {
-        "BriefDescription": "Cycles Memory is in self refresh power mode. Derived from unc_m_power_self_refresh",
+        "BriefDescription": "Cycles Memory is in self refresh power mode",
         "Counter": "0,1,2,3",
         "EventCode": "0x43",
         "EventName": "UNC_M_POWER_SELF_REFRESH",
         "MetricExpr": "(UNC_M_POWER_SELF_REFRESH / UNC_M_CLOCKTICKS) * 100.",
+        "MetricName": "power_self_refresh %",
         "PerPkg": "1",
         "Unit": "iMC"
     },
     {
-        "BriefDescription": "Memory page conflicts. Derived from unc_m_pre_count.page_miss",
+        "BriefDescription": "Memory page conflicts",
         "Counter": "0,1,2,3",
         "EventCode": "0x2",
         "EventName": "UNC_M_PRE_COUNT.PAGE_MISS",
@@ -69,7 +72,7 @@
         "Unit": "iMC"
     },
     {
-        "BriefDescription": "Occupancy counter for memory read queue. Derived from unc_m_rpq_occupancy",
+        "BriefDescription": "Occupancy counter for memory read queue",
         "Counter": "0,1,2,3",
         "EventCode": "0x80",
         "EventName": "UNC_M_RPQ_OCCUPANCY",
diff --git a/tools/perf/pmu-events/arch/x86/jaketown/uncore-power.json b/tools/perf/pmu-events/arch/x86/jaketown/uncore-power.json
index bbe36d547386..16034bfd06dd 100644
--- a/tools/perf/pmu-events/arch/x86/jaketown/uncore-power.json
+++ b/tools/perf/pmu-events/arch/x86/jaketown/uncore-power.json
@@ -1,44 +1,48 @@
 [
     {
-        "BriefDescription": "PCU clock ticks. Use to get percentages of PCU cycles events. Derived from unc_p_clockticks",
+        "BriefDescription": "PCU clock ticks. Use to get percentages of PCU cycles events",
         "Counter": "0,1,2,3",
         "EventName": "UNC_P_CLOCKTICKS",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter.  (filter_band0=XXX with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band0_cycles",
+        "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter.  (filter_band0=XXX with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency",
         "Counter": "0,1,2,3",
         "EventCode": "0xb",
         "EventName": "UNC_P_FREQ_BAND0_CYCLES",
         "MetricExpr": "(UNC_P_FREQ_BAND0_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_band0_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter.  (filter_band1=XXX with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band1_cycles",
+        "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter.  (filter_band1=XXX with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency",
         "Counter": "0,1,2,3",
         "EventCode": "0xc",
         "EventName": "UNC_P_FREQ_BAND1_CYCLES",
         "MetricExpr": "(UNC_P_FREQ_BAND1_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_band1_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter.  (filter_band2=XXX with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band2_cycles",
+        "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter.  (filter_band2=XXX with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency",
         "Counter": "0,1,2,3",
         "EventCode": "0xd",
         "EventName": "UNC_P_FREQ_BAND2_CYCLES",
         "MetricExpr": "(UNC_P_FREQ_BAND2_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_band2_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter.  (filter_band3=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band3_cycles",
+        "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter.  (filter_band3=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency",
         "Counter": "0,1,2,3",
         "EventCode": "0xe",
         "EventName": "UNC_P_FREQ_BAND3_CYCLES",
         "MetricExpr": "(UNC_P_FREQ_BAND3_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_band3_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
@@ -49,6 +53,7 @@
         "EventName": "UNC_P_FREQ_BAND0_TRANSITIONS",
         "Filter": "edge=1",
         "MetricExpr": "(UNC_P_FREQ_BAND0_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_band0_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
@@ -59,6 +64,7 @@
         "EventName": "UNC_P_FREQ_BAND1_TRANSITIONS",
         "Filter": "edge=1",
         "MetricExpr": "(UNC_P_FREQ_BAND1_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_band1_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
@@ -69,6 +75,7 @@
         "EventName": "UNC_P_FREQ_BAND2_TRANSITIONS",
         "Filter": "edge=1",
         "MetricExpr": "(UNC_P_FREQ_BAND2_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_band2_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
@@ -79,89 +86,99 @@
         "EventName": "UNC_P_FREQ_BAND3_TRANSITIONS",
         "Filter": "edge=1",
         "MetricExpr": "(UNC_P_FREQ_BAND3_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_band3_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C0.  It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details. Derived from unc_p_power_state_occupancy.cores_c0",
+        "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C0.  It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details",
         "Counter": "0,1,2,3",
         "EventCode": "0x80",
         "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C0",
         "Filter": "occ_sel=1",
         "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C0 / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "power_state_occupancy.cores_c0 %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C3.  It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details. Derived from unc_p_power_state_occupancy.cores_c3",
+        "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C3.  It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details",
         "Counter": "0,1,2,3",
         "EventCode": "0x80",
         "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C3",
         "Filter": "occ_sel=2",
         "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C3 / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "power_state_occupancy.cores_c3 %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C6.  It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events . Derived from unc_p_power_state_occupancy.cores_c6",
+        "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C6.  It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events ",
         "Counter": "0,1,2,3",
         "EventCode": "0x80",
         "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C6",
         "Filter": "occ_sel=3",
         "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C6 / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "power_state_occupancy.cores_c6 %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "Counts the number of cycles that we are in external PROCHOT mode.  This mode is triggered when a sensor off the die determines that something off-die (like DRAM) is too hot and must throttle to avoid damaging the chip. Derived from unc_p_prochot_external_cycles",
+        "BriefDescription": "Counts the number of cycles that we are in external PROCHOT mode.  This mode is triggered when a sensor off the die determines that something off-die (like DRAM) is too hot and must throttle to avoid damaging the chip",
         "Counter": "0,1,2,3",
         "EventCode": "0xa",
         "EventName": "UNC_P_PROCHOT_EXTERNAL_CYCLES",
         "MetricExpr": "(UNC_P_PROCHOT_EXTERNAL_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "prochot_external_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "Counts the number of cycles when temperature is the upper limit on frequency. Derived from unc_p_freq_max_limit_thermal_cycles",
+        "BriefDescription": "Counts the number of cycles when temperature is the upper limit on frequency",
         "Counter": "0,1,2,3",
         "EventCode": "0x4",
         "EventName": "UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES",
         "MetricExpr": "(UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_max_limit_thermal_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "Counts the number of cycles when the OS is the upper limit on frequency. Derived from unc_p_freq_max_os_cycles",
+        "BriefDescription": "Counts the number of cycles when the OS is the upper limit on frequency",
         "Counter": "0,1,2,3",
         "EventCode": "0x6",
         "EventName": "UNC_P_FREQ_MAX_OS_CYCLES",
         "MetricExpr": "(UNC_P_FREQ_MAX_OS_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_max_os_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "Counts the number of cycles when power is the upper limit on frequency. Derived from unc_p_freq_max_power_cycles",
+        "BriefDescription": "Counts the number of cycles when power is the upper limit on frequency",
         "Counter": "0,1,2,3",
         "EventCode": "0x5",
         "EventName": "UNC_P_FREQ_MAX_POWER_CYCLES",
         "MetricExpr": "(UNC_P_FREQ_MAX_POWER_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_max_power_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "Counts the number of cycles when current is the upper limit on frequency. Derived from unc_p_freq_max_current_cycles",
+        "BriefDescription": "Counts the number of cycles when current is the upper limit on frequency",
         "Counter": "0,1,2,3",
         "EventCode": "0x7",
         "EventName": "UNC_P_FREQ_MAX_CURRENT_CYCLES",
         "MetricExpr": "(UNC_P_FREQ_MAX_CURRENT_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_max_current_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
     {
-        "BriefDescription": "Cycles spent changing Frequency. Derived from unc_p_freq_trans_cycles",
+        "BriefDescription": "Cycles spent changing Frequency",
         "Counter": "0,1,2,3",
         "EventName": "UNC_P_FREQ_TRANS_CYCLES",
         "MetricExpr": "(UNC_P_FREQ_TRANS_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_trans_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
@@ -172,6 +189,7 @@
         "EventName": "UNC_P_FREQ_GE_1200MHZ_CYCLES",
         "Filter": "filter_band0=1200",
         "MetricExpr": "(UNC_P_FREQ_GE_1200MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_ge_1200mhz_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
@@ -182,6 +200,7 @@
         "EventName": "UNC_P_FREQ_GE_2000MHZ_CYCLES",
         "Filter": "filter_band1=2000",
         "MetricExpr": "(UNC_P_FREQ_GE_2000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_ge_2000mhz_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
@@ -192,6 +211,7 @@
         "EventName": "UNC_P_FREQ_GE_3000MHZ_CYCLES",
         "Filter": "filter_band2=3000",
         "MetricExpr": "(UNC_P_FREQ_GE_3000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_ge_3000mhz_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
@@ -202,6 +222,7 @@
         "EventName": "UNC_P_FREQ_GE_4000MHZ_CYCLES",
         "Filter": "filter_band3=4000",
         "MetricExpr": "(UNC_P_FREQ_GE_4000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_ge_4000mhz_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
@@ -212,6 +233,7 @@
         "EventName": "UNC_P_FREQ_GE_1200MHZ_TRANSITIONS",
         "Filter": "edge=1,filter_band0=1200",
         "MetricExpr": "(UNC_P_FREQ_GE_1200MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_ge_1200mhz_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
@@ -222,6 +244,7 @@
         "EventName": "UNC_P_FREQ_GE_2000MHZ_TRANSITIONS",
         "Filter": "edge=1,filter_band1=2000",
         "MetricExpr": "(UNC_P_FREQ_GE_2000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_ge_2000mhz_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
@@ -232,6 +255,7 @@
         "EventName": "UNC_P_FREQ_GE_3000MHZ_TRANSITIONS",
         "Filter": "edge=1,filter_band2=4000",
         "MetricExpr": "(UNC_P_FREQ_GE_3000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_ge_3000mhz_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     },
@@ -242,6 +266,7 @@
         "EventName": "UNC_P_FREQ_GE_4000MHZ_TRANSITIONS",
         "Filter": "edge=1,filter_band3=4000",
         "MetricExpr": "(UNC_P_FREQ_GE_4000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "MetricName": "freq_ge_4000mhz_cycles %",
         "PerPkg": "1",
         "Unit": "PCU"
     }
diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv
index 12181bb1da2a..d1a12e584c1b 100644
--- a/tools/perf/pmu-events/arch/x86/mapfile.csv
+++ b/tools/perf/pmu-events/arch/x86/mapfile.csv
@@ -17,6 +17,7 @@ GenuineIntel-6-3A,v18,ivybridge,core
 GenuineIntel-6-3E,v19,ivytown,core
 GenuineIntel-6-2D,v20,jaketown,core
 GenuineIntel-6-57,v9,knightslanding,core
+GenuineIntel-6-85,v9,knightslanding,core
 GenuineIntel-6-1E,v2,nehalemep,core
 GenuineIntel-6-1F,v2,nehalemep,core
 GenuineIntel-6-1A,v2,nehalemep,core
diff --git a/tools/perf/pmu-events/arch/x86/sandybridge/uncore.json b/tools/perf/pmu-events/arch/x86/sandybridge/uncore.json
new file mode 100644
index 000000000000..42c70eed05a2
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/sandybridge/uncore.json
@@ -0,0 +1,314 @@
+[
+  {
+    "Unit": "CBO",
+    "EventCode": "0x22",
+    "UMask": "0x01",
+    "EventName": "UNC_CBO_XSNP_RESPONSE.MISS",
+    "BriefDescription": "A snoop misses in some processor core.",
+    "PublicDescription": "A snoop misses in some processor core.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x22",
+    "UMask": "0x02",
+    "EventName": "UNC_CBO_XSNP_RESPONSE.INVAL",
+    "BriefDescription": "A snoop invalidates a non-modified line in some processor core.",
+    "PublicDescription": "A snoop invalidates a non-modified line in some processor core.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x22",
+    "UMask": "0x04",
+    "EventName": "UNC_CBO_XSNP_RESPONSE.HIT",
+    "BriefDescription": "A snoop hits a non-modified line in some processor core.",
+    "PublicDescription": "A snoop hits a non-modified line in some processor core.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x22",
+    "UMask": "0x08",
+    "EventName": "UNC_CBO_XSNP_RESPONSE.HITM",
+    "BriefDescription": "A snoop hits a modified line in some processor core.",
+    "PublicDescription": "A snoop hits a modified line in some processor core.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x22",
+    "UMask": "0x10",
+    "EventName": "UNC_CBO_XSNP_RESPONSE.INVAL_M",
+    "BriefDescription": "A snoop invalidates a modified line in some processor core.",
+    "PublicDescription": "A snoop invalidates a modified line in some processor core.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x22",
+    "UMask": "0x20",
+    "EventName": "UNC_CBO_XSNP_RESPONSE.EXTERNAL_FILTER",
+    "BriefDescription": "Filter on cross-core snoops initiated by this Cbox due to external snoop request.",
+    "PublicDescription": "Filter on cross-core snoops initiated by this Cbox due to external snoop request.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x22",
+    "UMask": "0x40",
+    "EventName": "UNC_CBO_XSNP_RESPONSE.XCORE_FILTER",
+    "BriefDescription": "Filter on cross-core snoops initiated by this Cbox due to processor core memory request.",
+    "PublicDescription": "Filter on cross-core snoops initiated by this Cbox due to processor core memory request.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x22",
+    "UMask": "0x80",
+    "EventName": "UNC_CBO_XSNP_RESPONSE.EVICTION_FILTER",
+    "BriefDescription": "Filter on cross-core snoops initiated by this Cbox due to LLC eviction.",
+    "PublicDescription": "Filter on cross-core snoops initiated by this Cbox due to LLC eviction.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x01",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.M",
+    "BriefDescription": "LLC lookup request that access cache and found line in M-state.",
+    "PublicDescription": "LLC lookup request that access cache and found line in M-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x02",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.E",
+    "BriefDescription": "LLC lookup request that access cache and found line in E-state.",
+    "PublicDescription": "LLC lookup request that access cache and found line in E-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x04",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.S",
+    "BriefDescription": "LLC lookup request that access cache and found line in S-state.",
+    "PublicDescription": "LLC lookup request that access cache and found line in S-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x08",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.I",
+    "BriefDescription": "LLC lookup request that access cache and found line in I-state.",
+    "PublicDescription": "LLC lookup request that access cache and found line in I-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x10",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.READ_FILTER",
+    "BriefDescription": "Filter on processor core initiated cacheable read requests.",
+    "PublicDescription": "Filter on processor core initiated cacheable read requests.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x20",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_FILTER",
+    "BriefDescription": "Filter on processor core initiated cacheable write requests.",
+    "PublicDescription": "Filter on processor core initiated cacheable write requests.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x40",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.EXTSNP_FILTER",
+    "BriefDescription": "Filter on external snoop requests.",
+    "PublicDescription": "Filter on external snoop requests.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x80",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_REQUEST_FILTER",
+    "BriefDescription": "Filter on any IRQ or IPQ initiated requests including uncacheable, non-coherent requests.",
+    "PublicDescription": "Filter on any IRQ or IPQ initiated requests including uncacheable, non-coherent requests.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "ARB",
+    "EventCode": "0x80",
+    "UMask": "0x01",
+    "EventName": "UNC_ARB_TRK_OCCUPANCY.ALL",
+    "BriefDescription": "Counts cycles weighted by the number of requests waiting for data returning from the memory controller. Accounts for coherent and non-coherent requests initiated by IA cores, processor graphic units, or LLC.",
+    "PublicDescription": "Counts cycles weighted by the number of requests waiting for data returning from the memory controller. Accounts for coherent and non-coherent requests initiated by IA cores, processor graphic units, or LLC.",
+    "Counter": "0",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "ARB",
+    "EventCode": "0x81",
+    "UMask": "0x01",
+    "EventName": "UNC_ARB_TRK_REQUESTS.ALL",
+    "BriefDescription": "Counts the number of coherent and in-coherent requests initiated by IA cores, processor graphic units, or LLC.",
+    "PublicDescription": "Counts the number of coherent and in-coherent requests initiated by IA cores, processor graphic units, or LLC.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "ARB",
+    "EventCode": "0x81",
+    "UMask": "0x20",
+    "EventName": "UNC_ARB_TRK_REQUESTS.WRITES",
+    "BriefDescription": "Counts the number of allocated write entries, include full, partial, and LLC evictions.",
+    "PublicDescription": "Counts the number of allocated write entries, include full, partial, and LLC evictions.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "ARB",
+    "EventCode": "0x81",
+    "UMask": "0x80",
+    "EventName": "UNC_ARB_TRK_REQUESTS.EVICTIONS",
+    "BriefDescription": "Counts the number of LLC evictions allocated.",
+    "PublicDescription": "Counts the number of LLC evictions allocated.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "ARB",
+    "EventCode": "0x83",
+    "UMask": "0x01",
+    "EventName": "UNC_ARB_COH_TRK_OCCUPANCY.ALL",
+    "BriefDescription": "Cycles weighted by number of requests pending in Coherency Tracker.",
+    "PublicDescription": "Cycles weighted by number of requests pending in Coherency Tracker.",
+    "Counter": "0",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "ARB",
+    "EventCode": "0x84",
+    "UMask": "0x01",
+    "EventName": "UNC_ARB_COH_TRK_REQUESTS.ALL",
+    "BriefDescription": "Number of requests allocated in Coherency Tracker.",
+    "PublicDescription": "Number of requests allocated in Coherency Tracker.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "ARB",
+    "EventCode": "0x80",
+    "UMask": "0x01",
+    "EventName": "UNC_ARB_TRK_OCCUPANCY.CYCLES_WITH_ANY_REQUEST",
+    "BriefDescription": "Cycles with at least one request outstanding is waiting for data return from memory controller. Account for coherent and non-coherent requests initiated by IA Cores, Processor Graphics Unit, or LLC.",
+    "PublicDescription": "Cycles with at least one request outstanding is waiting for data return from memory controller. Account for coherent and non-coherent requests initiated by IA Cores, Processor Graphics Unit, or LLC.",
+    "Counter": "0,1",
+    "CounterMask": "1",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "ARB",
+    "EventCode": "0x80",
+    "UMask": "0x01",
+    "EventName": "UNC_ARB_TRK_OCCUPANCY.CYCLES_OVER_HALF_FULL",
+    "BriefDescription": "Cycles with at least half of the requests outstanding are waiting for data return from memory controller. Account for coherent and non-coherent requests initiated by IA Cores, Processor Graphics Unit, or LLC.",
+    "PublicDescription": "Cycles with at least half of the requests outstanding are waiting for data return from memory controller. Account for coherent and non-coherent requests initiated by IA Cores, Processor Graphics Unit, or LLC.",
+    "Counter": "0,1",
+    "CounterMask": "10",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "ARB",
+    "EventCode": "0x0",
+    "UMask": "0x01",
+    "EventName": "UNC_CLOCK.SOCKET",
+    "BriefDescription": "This 48-bit fixed counter counts the UCLK cycles.",
+    "PublicDescription": "This 48-bit fixed counter counts the UCLK cycles.",
+    "Counter": "Fixed",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x06",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.ES",
+    "BriefDescription": "LLC lookup request that access cache and found line in E-state or S-state.",
+    "PublicDescription": "LLC lookup request that access cache and found line in E-state or S-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  }
+]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/skylake/uncore.json b/tools/perf/pmu-events/arch/x86/skylake/uncore.json
new file mode 100644
index 000000000000..dbc193252fb3
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/skylake/uncore.json
@@ -0,0 +1,254 @@
+[
+  {
+    "Unit": "CBO",
+    "EventCode": "0x22",
+    "UMask": "0x41",
+    "EventName": "UNC_CBO_XSNP_RESPONSE.MISS_XCORE",
+    "BriefDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which misses in some processor core.",
+    "PublicDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which misses in some processor core.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x22",
+    "UMask": "0x81",
+    "EventName": "UNC_CBO_XSNP_RESPONSE.MISS_EVICTION",
+    "BriefDescription": "A cross-core snoop resulted from L3 Eviction which misses in some processor core.",
+    "PublicDescription": "A cross-core snoop resulted from L3 Eviction which misses in some processor core.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x22",
+    "UMask": "0x44",
+    "EventName": "UNC_CBO_XSNP_RESPONSE.HIT_XCORE",
+    "BriefDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a non-modified line in some processor core.",
+    "PublicDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a non-modified line in some processor core.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x22",
+    "UMask": "0x48",
+    "EventName": "UNC_CBO_XSNP_RESPONSE.HITM_XCORE",
+    "BriefDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a modified line in some processor core.",
+    "PublicDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a modified line in some processor core.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x21",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_M",
+    "BriefDescription": "L3 Lookup write request that access cache and found line in M-state",
+    "PublicDescription": "L3 Lookup write request that access cache and found line in M-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x81",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_M",
+    "BriefDescription": "L3 Lookup any request that access cache and found line in M-state",
+    "PublicDescription": "L3 Lookup any request that access cache and found line in M-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x18",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.READ_I",
+    "BriefDescription": "L3 Lookup read request that access cache and found line in I-state",
+    "PublicDescription": "L3 Lookup read request that access cache and found line in I-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x88",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_I",
+    "BriefDescription": "L3 Lookup any request that access cache and found line in I-state",
+    "PublicDescription": "L3 Lookup any request that access cache and found line in I-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x1f",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.READ_MESI",
+    "BriefDescription": "L3 Lookup read request that access cache and found line in any MESI-state",
+    "PublicDescription": "L3 Lookup read request that access cache and found line in any MESI-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x2f",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_MESI",
+    "BriefDescription": "L3 Lookup write request that access cache and found line in MESI-state",
+    "PublicDescription": "L3 Lookup write request that access cache and found line in MESI-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x8f",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_MESI",
+    "BriefDescription": "L3 Lookup any request that access cache and found line in MESI-state",
+    "PublicDescription": "L3 Lookup any request that access cache and found line in MESI-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x86",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_ES",
+    "BriefDescription": "L3 Lookup any request that access cache and found line in E or S-state",
+    "PublicDescription": "L3 Lookup any request that access cache and found line in E or S-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x16",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.READ_ES",
+    "BriefDescription": "L3 Lookup read request that access cache and found line in E or S-state",
+    "PublicDescription": "L3 Lookup read request that access cache and found line in E or S-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "CBO",
+    "EventCode": "0x34",
+    "UMask": "0x26",
+    "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_ES",
+    "BriefDescription": "L3 Lookup write request that access cache and found line in E or S-state",
+    "PublicDescription": "L3 Lookup write request that access cache and found line in E or S-state.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "iMPH-U",
+    "EventCode": "0x80",
+    "UMask": "0x01",
+    "EventName": "UNC_ARB_TRK_OCCUPANCY.ALL",
+    "BriefDescription": "Each cycle count number of all Core outgoing valid entries. Such entry is defined as valid from its allocation till first of IDI0 or DRS0 messages is sent out. Accounts for Coherent and non-coherent traffic.",
+    "PublicDescription": "Each cycle count number of all Core outgoing valid entries. Such entry is defined as valid from its allocation till first of IDI0 or DRS0 messages is sent out. Accounts for Coherent and non-coherent traffic.",
+    "Counter": "0",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "iMPH-U",
+    "EventCode": "0x81",
+    "UMask": "0x01",
+    "EventName": "UNC_ARB_TRK_REQUESTS.ALL",
+    "BriefDescription": "Total number of Core outgoing entries allocated. Accounts for Coherent and non-coherent traffic.",
+    "PublicDescription": "Total number of Core outgoing entries allocated. Accounts for Coherent and non-coherent traffic.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "iMPH-U",
+    "EventCode": "0x81",
+    "UMask": "0x02",
+    "EventName": "UNC_ARB_TRK_REQUESTS.DRD_DIRECT",
+    "BriefDescription": "Number of Core coherent Data Read entries allocated in DirectData mode",
+    "PublicDescription": "Number of Core coherent Data Read entries allocated in DirectData mode.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "iMPH-U",
+    "EventCode": "0x81",
+    "UMask": "0x20",
+    "EventName": "UNC_ARB_TRK_REQUESTS.WRITES",
+    "BriefDescription": "Number of Writes allocated - any write transactions: full/partials writes and evictions.",
+    "PublicDescription": "Number of Writes allocated - any write transactions: full/partials writes and evictions.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "iMPH-U",
+    "EventCode": "0x84",
+    "UMask": "0x01",
+    "EventName": "UNC_ARB_COH_TRK_REQUESTS.ALL",
+    "BriefDescription": "Number of entries allocated. Account for Any type: e.g. Snoop, Core aperture, etc.",
+    "PublicDescription": "Number of entries allocated. Account for Any type: e.g. Snoop, Core aperture, etc.",
+    "Counter": "0,1",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "iMPH-U",
+    "EventCode": "0x80",
+    "UMask": "0x01",
+    "EventName": "UNC_ARB_TRK_OCCUPANCY.CYCLES_WITH_ANY_REQUEST",
+    "BriefDescription": "Cycles with at least one request outstanding is waiting for data return from memory controller. Account for coherent and non-coherent requests initiated by IA Cores, Processor Graphics Unit, or LLC.;",
+    "PublicDescription": "Cycles with at least one request outstanding is waiting for data return from memory controller. Account for coherent and non-coherent requests initiated by IA Cores, Processor Graphics Unit, or LLC.",
+    "Counter": "0",
+    "CounterMask": "1",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  },
+  {
+    "Unit": "NCU",
+    "EventCode": "0x0",
+    "UMask": "0x01",
+    "EventName": "UNC_CLOCK.SOCKET",
+    "BriefDescription": "This 48-bit fixed counter counts the UCLK cycles",
+    "PublicDescription": "This 48-bit fixed counter counts the UCLK cycles.",
+    "Counter": "FIXED",
+    "CounterMask": "0",
+    "Invert": "0",
+    "EdgeDetect": "0"
+  }
+]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c
index eed09346a72a..baa073f38334 100644
--- a/tools/perf/pmu-events/jevents.c
+++ b/tools/perf/pmu-events/jevents.c
@@ -195,6 +195,7 @@ static struct map {
 	{ "CBO", "uncore_cbox" },
 	{ "QPI LL", "uncore_qpi" },
 	{ "SBO", "uncore_sbox" },
+	{ "iMPH-U", "uncore_arb" },
 	{}
 };
 
@@ -291,7 +292,9 @@ static void print_events_table_prefix(FILE *fp, const char *tblname)
 
 static int print_events_table_entry(void *data, char *name, char *event,
 				    char *desc, char *long_desc,
-				    char *pmu, char *unit, char *perpkg)
+				    char *pmu, char *unit, char *perpkg,
+				    char *metric_expr,
+				    char *metric_name)
 {
 	struct perf_entry_data *pd = data;
 	FILE *outfp = pd->outfp;
@@ -315,6 +318,10 @@ static int print_events_table_entry(void *data, char *name, char *event,
 		fprintf(outfp, "\t.unit = \"%s\",\n", unit);
 	if (perpkg)
 		fprintf(outfp, "\t.perpkg = \"%s\",\n", perpkg);
+	if (metric_expr)
+		fprintf(outfp, "\t.metric_expr = \"%s\",\n", metric_expr);
+	if (metric_name)
+		fprintf(outfp, "\t.metric_name = \"%s\",\n", metric_name);
 	fprintf(outfp, "},\n");
 
 	return 0;
@@ -362,7 +369,9 @@ static char *real_event(const char *name, char *event)
 int json_events(const char *fn,
 	  int (*func)(void *data, char *name, char *event, char *desc,
 		      char *long_desc,
-		      char *pmu, char *unit, char *perpkg),
+		      char *pmu, char *unit, char *perpkg,
+		      char *metric_expr,
+		      char *metric_name),
 	  void *data)
 {
 	int err = -EIO;
@@ -388,6 +397,8 @@ int json_events(const char *fn,
 		char *filter = NULL;
 		char *perpkg = NULL;
 		char *unit = NULL;
+		char *metric_expr = NULL;
+		char *metric_name = NULL;
 		unsigned long long eventcode = 0;
 		struct msrmap *msr = NULL;
 		jsmntok_t *msrval = NULL;
@@ -398,6 +409,7 @@ int json_events(const char *fn,
 		for (j = 0; j < obj->size; j += 2) {
 			jsmntok_t *field, *val;
 			int nz;
+			char *s;
 
 			field = tok + j;
 			EXPECT(field->type == JSMN_STRING, tok + j,
@@ -444,7 +456,6 @@ int json_events(const char *fn,
 					NULL);
 			} else if (json_streq(map, field, "Unit")) {
 				const char *ppmu;
-				char *s;
 
 				ppmu = field_to_perf(unit_to_pmu, map, val);
 				if (ppmu) {
@@ -458,12 +469,19 @@ int json_events(const char *fn,
 				}
 				addfield(map, &desc, ". ", "Unit: ", NULL);
 				addfield(map, &desc, "", pmu, NULL);
+				addfield(map, &desc, "", " ", NULL);
 			} else if (json_streq(map, field, "Filter")) {
 				addfield(map, &filter, "", "", val);
 			} else if (json_streq(map, field, "ScaleUnit")) {
 				addfield(map, &unit, "", "", val);
 			} else if (json_streq(map, field, "PerPkg")) {
 				addfield(map, &perpkg, "", "", val);
+			} else if (json_streq(map, field, "MetricName")) {
+				addfield(map, &metric_name, "", "", val);
+			} else if (json_streq(map, field, "MetricExpr")) {
+				addfield(map, &metric_expr, "", "", val);
+				for (s = metric_expr; *s; s++)
+					*s = tolower(*s);
 			}
 			/* ignore unknown fields */
 		}
@@ -488,7 +506,7 @@ int json_events(const char *fn,
 		fixname(name);
 
 		err = func(data, name, real_event(name, event), desc, long_desc,
-				pmu, unit, perpkg);
+				pmu, unit, perpkg, metric_expr, metric_name);
 		free(event);
 		free(desc);
 		free(name);
@@ -498,6 +516,8 @@ int json_events(const char *fn,
 		free(filter);
 		free(perpkg);
 		free(unit);
+		free(metric_expr);
+		free(metric_name);
 		if (err)
 			break;
 		tok += j;
diff --git a/tools/perf/pmu-events/jevents.h b/tools/perf/pmu-events/jevents.h
index 71e13de31092..611fac01913d 100644
--- a/tools/perf/pmu-events/jevents.h
+++ b/tools/perf/pmu-events/jevents.h
@@ -5,7 +5,8 @@ int json_events(const char *fn,
 		int (*func)(void *data, char *name, char *event, char *desc,
 				char *long_desc,
 				char *pmu,
-				char *unit, char *perpkg),
+				char *unit, char *perpkg, char *metric_expr,
+				char *metric_name),
 		void *data);
 char *get_cpu_str(void);
 
diff --git a/tools/perf/pmu-events/pmu-events.h b/tools/perf/pmu-events/pmu-events.h
index c669a3cdb9f0..569eab3688dd 100644
--- a/tools/perf/pmu-events/pmu-events.h
+++ b/tools/perf/pmu-events/pmu-events.h
@@ -13,6 +13,8 @@ struct pmu_event {
 	const char *pmu;
 	const char *unit;
 	const char *perpkg;
+	const char *metric_expr;
+	const char *metric_name;
 };
 
 /*
diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build
index 1cb3d9b540e9..af58ebc243ef 100644
--- a/tools/perf/tests/Build
+++ b/tools/perf/tests/Build
@@ -38,6 +38,7 @@ perf-y += cpumap.o
 perf-y += stat.o
 perf-y += event_update.o
 perf-y += event-times.o
+perf-y += expr.o
 perf-y += backward-ring-buffer.o
 perf-y += sdt.o
 perf-y += is_printable_array.o
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 83c4669cbc5b..e6d7876c94c2 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -44,6 +44,10 @@ static struct test generic_tests[] = {
 		.func = test__parse_events,
 	},
 	{
+		.desc = "Simple expression parser",
+		.func = test__expr,
+	},
+	{
 		.desc = "PERF_RECORD_* events & perf_sample fields",
 		.func = test__PERF_RECORD,
 	},
@@ -460,7 +464,7 @@ static int perf_test__list(int argc, const char **argv)
 	return 0;
 }
 
-int cmd_test(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_test(int argc, const char **argv)
 {
 	const char *test_usage[] = {
 	"perf test [<options>] [{list <test-name-fragment>|[<test-name-fragments>|<test-numbers>]}]",
diff --git a/tools/perf/tests/cpumap.c b/tools/perf/tests/cpumap.c
index f168a85992d0..4478773cdb97 100644
--- a/tools/perf/tests/cpumap.c
+++ b/tools/perf/tests/cpumap.c
@@ -66,7 +66,7 @@ static int process_event_cpus(struct perf_tool *tool __maybe_unused,
 	TEST_ASSERT_VAL("wrong nr",  map->nr == 2);
 	TEST_ASSERT_VAL("wrong cpu", map->map[0] == 1);
 	TEST_ASSERT_VAL("wrong cpu", map->map[1] == 256);
-	TEST_ASSERT_VAL("wrong refcnt", atomic_read(&map->refcnt) == 1);
+	TEST_ASSERT_VAL("wrong refcnt", refcount_read(&map->refcnt) == 1);
 	cpu_map__put(map);
 	return 0;
 }
diff --git a/tools/perf/tests/expr.c b/tools/perf/tests/expr.c
new file mode 100644
index 000000000000..6c6a3749aaf6
--- /dev/null
+++ b/tools/perf/tests/expr.c
@@ -0,0 +1,56 @@
+#include "util/debug.h"
+#include "util/expr.h"
+#include "tests.h"
+#include <stdlib.h>
+
+static int test(struct parse_ctx *ctx, const char *e, double val2)
+{
+	double val;
+
+	if (expr__parse(&val, ctx, &e))
+		TEST_ASSERT_VAL("parse test failed", 0);
+	TEST_ASSERT_VAL("unexpected value", val == val2);
+	return 0;
+}
+
+int test__expr(int subtest __maybe_unused)
+{
+	const char *p;
+	const char **other;
+	double val;
+	int ret;
+	struct parse_ctx ctx;
+	int num_other;
+
+	expr__ctx_init(&ctx);
+	expr__add_id(&ctx, "FOO", 1);
+	expr__add_id(&ctx, "BAR", 2);
+
+	ret = test(&ctx, "1+1", 2);
+	ret |= test(&ctx, "FOO+BAR", 3);
+	ret |= test(&ctx, "(BAR/2)%2", 1);
+	ret |= test(&ctx, "1 - -4",  5);
+	ret |= test(&ctx, "(FOO-1)*2 + (BAR/2)%2 - -4",  5);
+
+	if (ret)
+		return ret;
+
+	p = "FOO/0";
+	ret = expr__parse(&val, &ctx, &p);
+	TEST_ASSERT_VAL("division by zero", ret == 1);
+
+	p = "BAR/";
+	ret = expr__parse(&val, &ctx, &p);
+	TEST_ASSERT_VAL("missing operand", ret == 1);
+
+	TEST_ASSERT_VAL("find other",
+			expr__find_other("FOO + BAR + BAZ + BOZO", "FOO", &other, &num_other) == 0);
+	TEST_ASSERT_VAL("find other", num_other == 3);
+	TEST_ASSERT_VAL("find other", !strcmp(other[0], "BAR"));
+	TEST_ASSERT_VAL("find other", !strcmp(other[1], "BAZ"));
+	TEST_ASSERT_VAL("find other", !strcmp(other[2], "BOZO"));
+	TEST_ASSERT_VAL("find other", other[3] == NULL);
+	free((void *)other);
+
+	return 0;
+}
diff --git a/tools/perf/tests/sdt.c b/tools/perf/tests/sdt.c
index f59d210e1baf..26e5b7a0b839 100644
--- a/tools/perf/tests/sdt.c
+++ b/tools/perf/tests/sdt.c
@@ -43,7 +43,7 @@ static char *get_self_path(void)
 {
 	char *buf = calloc(PATH_MAX, sizeof(char));
 
-	if (buf && readlink("/proc/self/exe", buf, PATH_MAX) < 0) {
+	if (buf && readlink("/proc/self/exe", buf, PATH_MAX - 1) < 0) {
 		pr_debug("Failed to get correct path of perf\n");
 		free(buf);
 		return NULL;
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index 1fa9b9d83aa5..631859629403 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -62,6 +62,7 @@ int test__sample_parsing(int subtest);
 int test__keep_tracking(int subtest);
 int test__parse_no_sample_id_all(int subtest);
 int test__dwarf_unwind(int subtest);
+int test__expr(int subtest);
 int test__hists_filter(int subtest);
 int test__mmap_thread_lookup(int subtest);
 int test__thread_mg_share(int subtest);
diff --git a/tools/perf/tests/thread-map.c b/tools/perf/tests/thread-map.c
index f2d2e542d0ee..a63d6945807b 100644
--- a/tools/perf/tests/thread-map.c
+++ b/tools/perf/tests/thread-map.c
@@ -29,7 +29,7 @@ int test__thread_map(int subtest __maybe_unused)
 			thread_map__comm(map, 0) &&
 			!strcmp(thread_map__comm(map, 0), NAME));
 	TEST_ASSERT_VAL("wrong refcnt",
-			atomic_read(&map->refcnt) == 1);
+			refcount_read(&map->refcnt) == 1);
 	thread_map__put(map);
 
 	/* test dummy pid */
@@ -44,7 +44,7 @@ int test__thread_map(int subtest __maybe_unused)
 			thread_map__comm(map, 0) &&
 			!strcmp(thread_map__comm(map, 0), "dummy"));
 	TEST_ASSERT_VAL("wrong refcnt",
-			atomic_read(&map->refcnt) == 1);
+			refcount_read(&map->refcnt) == 1);
 	thread_map__put(map);
 	return 0;
 }
@@ -71,7 +71,7 @@ static int process_event(struct perf_tool *tool __maybe_unused,
 			thread_map__comm(threads, 0) &&
 			!strcmp(thread_map__comm(threads, 0), NAME));
 	TEST_ASSERT_VAL("wrong refcnt",
-			atomic_read(&threads->refcnt) == 1);
+			refcount_read(&threads->refcnt) == 1);
 	thread_map__put(threads);
 	return 0;
 }
diff --git a/tools/perf/tests/thread-mg-share.c b/tools/perf/tests/thread-mg-share.c
index 188b63140fc8..76686dd6f5ec 100644
--- a/tools/perf/tests/thread-mg-share.c
+++ b/tools/perf/tests/thread-mg-share.c
@@ -43,7 +43,7 @@ int test__thread_mg_share(int subtest __maybe_unused)
 			leader && t1 && t2 && t3 && other);
 
 	mg = leader->mg;
-	TEST_ASSERT_EQUAL("wrong refcnt", atomic_read(&mg->refcnt), 4);
+	TEST_ASSERT_EQUAL("wrong refcnt", refcount_read(&mg->refcnt), 4);
 
 	/* test the map groups pointer is shared */
 	TEST_ASSERT_VAL("map groups don't match", mg == t1->mg);
@@ -71,25 +71,25 @@ int test__thread_mg_share(int subtest __maybe_unused)
 	machine__remove_thread(machine, other_leader);
 
 	other_mg = other->mg;
-	TEST_ASSERT_EQUAL("wrong refcnt", atomic_read(&other_mg->refcnt), 2);
+	TEST_ASSERT_EQUAL("wrong refcnt", refcount_read(&other_mg->refcnt), 2);
 
 	TEST_ASSERT_VAL("map groups don't match", other_mg == other_leader->mg);
 
 	/* release thread group */
 	thread__put(leader);
-	TEST_ASSERT_EQUAL("wrong refcnt", atomic_read(&mg->refcnt), 3);
+	TEST_ASSERT_EQUAL("wrong refcnt", refcount_read(&mg->refcnt), 3);
 
 	thread__put(t1);
-	TEST_ASSERT_EQUAL("wrong refcnt", atomic_read(&mg->refcnt), 2);
+	TEST_ASSERT_EQUAL("wrong refcnt", refcount_read(&mg->refcnt), 2);
 
 	thread__put(t2);
-	TEST_ASSERT_EQUAL("wrong refcnt", atomic_read(&mg->refcnt), 1);
+	TEST_ASSERT_EQUAL("wrong refcnt", refcount_read(&mg->refcnt), 1);
 
 	thread__put(t3);
 
 	/* release other group  */
 	thread__put(other_leader);
-	TEST_ASSERT_EQUAL("wrong refcnt", atomic_read(&other_mg->refcnt), 1);
+	TEST_ASSERT_EQUAL("wrong refcnt", refcount_read(&other_mg->refcnt), 1);
 
 	thread__put(other);
 
diff --git a/tools/perf/trace/beauty/Build b/tools/perf/trace/beauty/Build
new file mode 100644
index 000000000000..be95ac6ce845
--- /dev/null
+++ b/tools/perf/trace/beauty/Build
@@ -0,0 +1 @@
+libperf-y += statx.o
diff --git a/tools/perf/trace/beauty/beauty.h b/tools/perf/trace/beauty/beauty.h
new file mode 100644
index 000000000000..cf50be3f17a4
--- /dev/null
+++ b/tools/perf/trace/beauty/beauty.h
@@ -0,0 +1,24 @@
+#ifndef _PERF_TRACE_BEAUTY_H
+#define _PERF_TRACE_BEAUTY_H
+
+#include <linux/types.h>
+
+struct trace;
+struct thread;
+
+struct syscall_arg {
+	unsigned long val;
+	struct thread *thread;
+	struct trace  *trace;
+	void	      *parm;
+	u8	      idx;
+	u8	      mask;
+};
+
+size_t syscall_arg__scnprintf_statx_flags(char *bf, size_t size, struct syscall_arg *arg);
+#define SCA_STATX_FLAGS syscall_arg__scnprintf_statx_flags
+
+size_t syscall_arg__scnprintf_statx_mask(char *bf, size_t size, struct syscall_arg *arg);
+#define SCA_STATX_MASK syscall_arg__scnprintf_statx_mask
+
+#endif /* _PERF_TRACE_BEAUTY_H */
diff --git a/tools/perf/trace/beauty/statx.c b/tools/perf/trace/beauty/statx.c
new file mode 100644
index 000000000000..5643b692af4c
--- /dev/null
+++ b/tools/perf/trace/beauty/statx.c
@@ -0,0 +1,72 @@
+/*
+ * trace/beauty/statx.c
+ *
+ *  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 "trace/beauty/beauty.h"
+#include <linux/kernel.h>
+#include <sys/types.h>
+#include <uapi/linux/fcntl.h>
+#include <uapi/linux/stat.h>
+
+size_t syscall_arg__scnprintf_statx_flags(char *bf, size_t size, struct syscall_arg *arg)
+{
+	int printed = 0, flags = arg->val;
+
+	if (flags == 0)
+		return scnprintf(bf, size, "SYNC_AS_STAT");
+#define	P_FLAG(n) \
+	if (flags & AT_##n) { \
+		printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \
+		flags &= ~AT_##n; \
+	}
+
+	P_FLAG(SYMLINK_NOFOLLOW);
+	P_FLAG(REMOVEDIR);
+	P_FLAG(SYMLINK_FOLLOW);
+	P_FLAG(NO_AUTOMOUNT);
+	P_FLAG(EMPTY_PATH);
+	P_FLAG(STATX_FORCE_SYNC);
+	P_FLAG(STATX_DONT_SYNC);
+
+#undef P_FLAG
+
+	if (flags)
+		printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags);
+
+	return printed;
+}
+
+size_t syscall_arg__scnprintf_statx_mask(char *bf, size_t size, struct syscall_arg *arg)
+{
+	int printed = 0, flags = arg->val;
+
+#define	P_FLAG(n) \
+	if (flags & STATX_##n) { \
+		printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \
+		flags &= ~STATX_##n; \
+	}
+
+	P_FLAG(TYPE);
+	P_FLAG(MODE);
+	P_FLAG(NLINK);
+	P_FLAG(UID);
+	P_FLAG(GID);
+	P_FLAG(ATIME);
+	P_FLAG(MTIME);
+	P_FLAG(CTIME);
+	P_FLAG(INO);
+	P_FLAG(SIZE);
+	P_FLAG(BLOCKS);
+	P_FLAG(BTIME);
+
+#undef P_FLAG
+
+	if (flags)
+		printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags);
+
+	return printed;
+}
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index fc4fb669ceee..da24072bb76e 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -144,9 +144,60 @@ static void callchain_list__set_folding(struct callchain_list *cl, bool unfold)
 	cl->unfolded = unfold ? cl->has_children : false;
 }
 
+static struct inline_node *inline_node__create(struct map *map, u64 ip)
+{
+	struct dso *dso;
+	struct inline_node *node;
+
+	if (map == NULL)
+		return NULL;
+
+	dso = map->dso;
+	if (dso == NULL)
+		return NULL;
+
+	if (dso->kernel != DSO_TYPE_USER)
+		return NULL;
+
+	node = dso__parse_addr_inlines(dso,
+				       map__rip_2objdump(map, ip));
+
+	return node;
+}
+
+static int inline__count_rows(struct inline_node *node)
+{
+	struct inline_list *ilist;
+	int i = 0;
+
+	if (node == NULL)
+		return 0;
+
+	list_for_each_entry(ilist, &node->val, list) {
+		if ((ilist->filename != NULL) || (ilist->funcname != NULL))
+			i++;
+	}
+
+	return i;
+}
+
+static int callchain_list__inline_rows(struct callchain_list *chain)
+{
+	struct inline_node *node;
+	int rows;
+
+	node = inline_node__create(chain->ms.map, chain->ip);
+	if (node == NULL)
+		return 0;
+
+	rows = inline__count_rows(node);
+	inline_node__delete(node);
+	return rows;
+}
+
 static int callchain_node__count_rows_rb_tree(struct callchain_node *node)
 {
-	int n = 0;
+	int n = 0, inline_rows;
 	struct rb_node *nd;
 
 	for (nd = rb_first(&node->rb_root); nd; nd = rb_next(nd)) {
@@ -156,6 +207,13 @@ static int callchain_node__count_rows_rb_tree(struct callchain_node *node)
 
 		list_for_each_entry(chain, &child->val, list) {
 			++n;
+
+			if (symbol_conf.inline_name) {
+				inline_rows =
+					callchain_list__inline_rows(chain);
+				n += inline_rows;
+			}
+
 			/* We need this because we may not have children */
 			folded_sign = callchain_list__folded(chain);
 			if (folded_sign == '+')
@@ -207,7 +265,7 @@ static int callchain_node__count_rows(struct callchain_node *node)
 {
 	struct callchain_list *chain;
 	bool unfolded = false;
-	int n = 0;
+	int n = 0, inline_rows;
 
 	if (callchain_param.mode == CHAIN_FLAT)
 		return callchain_node__count_flat_rows(node);
@@ -216,6 +274,11 @@ static int callchain_node__count_rows(struct callchain_node *node)
 
 	list_for_each_entry(chain, &node->val, list) {
 		++n;
+		if (symbol_conf.inline_name) {
+			inline_rows = callchain_list__inline_rows(chain);
+			n += inline_rows;
+		}
+
 		unfolded = chain->unfolded;
 	}
 
@@ -362,6 +425,19 @@ static void hist_entry__init_have_children(struct hist_entry *he)
 	he->init_have_children = true;
 }
 
+static void hist_entry_init_inline_node(struct hist_entry *he)
+{
+	if (he->inline_node)
+		return;
+
+	he->inline_node = inline_node__create(he->ms.map, he->ip);
+
+	if (he->inline_node == NULL)
+		return;
+
+	he->has_children = true;
+}
+
 static bool hist_browser__toggle_fold(struct hist_browser *browser)
 {
 	struct hist_entry *he = browser->he_selection;
@@ -393,7 +469,12 @@ static bool hist_browser__toggle_fold(struct hist_browser *browser)
 
 		if (he->unfolded) {
 			if (he->leaf)
-				he->nr_rows = callchain__count_rows(&he->sorted_chain);
+				if (he->inline_node)
+					he->nr_rows = inline__count_rows(
+							he->inline_node);
+				else
+					he->nr_rows = callchain__count_rows(
+							&he->sorted_chain);
 			else
 				he->nr_rows = hierarchy_count_rows(browser, he, false);
 
@@ -753,6 +834,71 @@ static bool hist_browser__check_dump_full(struct hist_browser *browser __maybe_u
 
 #define LEVEL_OFFSET_STEP 3
 
+static int hist_browser__show_inline(struct hist_browser *browser,
+				     struct inline_node *node,
+				     unsigned short row,
+				     int offset)
+{
+	struct inline_list *ilist;
+	char buf[1024];
+	int color, width, first_row;
+
+	first_row = row;
+	width = browser->b.width - (LEVEL_OFFSET_STEP + 2);
+	list_for_each_entry(ilist, &node->val, list) {
+		if ((ilist->filename != NULL) || (ilist->funcname != NULL)) {
+			color = HE_COLORSET_NORMAL;
+			if (ui_browser__is_current_entry(&browser->b, row))
+				color = HE_COLORSET_SELECTED;
+
+			if (callchain_param.key == CCKEY_ADDRESS ||
+			    callchain_param.key == CCKEY_SRCLINE) {
+				if (ilist->filename != NULL)
+					scnprintf(buf, sizeof(buf),
+						  "%s:%d (inline)",
+						  ilist->filename,
+						  ilist->line_nr);
+				else
+					scnprintf(buf, sizeof(buf), "??");
+			} else if (ilist->funcname != NULL)
+				scnprintf(buf, sizeof(buf), "%s (inline)",
+					  ilist->funcname);
+			else if (ilist->filename != NULL)
+				scnprintf(buf, sizeof(buf),
+					  "%s:%d (inline)",
+					  ilist->filename,
+					  ilist->line_nr);
+			else
+				scnprintf(buf, sizeof(buf), "??");
+
+			ui_browser__set_color(&browser->b, color);
+			hist_browser__gotorc(browser, row, 0);
+			ui_browser__write_nstring(&browser->b, " ",
+				LEVEL_OFFSET_STEP + offset);
+			ui_browser__write_nstring(&browser->b, buf, width);
+			row++;
+		}
+	}
+
+	return row - first_row;
+}
+
+static size_t show_inline_list(struct hist_browser *browser, struct map *map,
+			       u64 ip, int row, int offset)
+{
+	struct inline_node *node;
+	int ret;
+
+	node = inline_node__create(map, ip);
+	if (node == NULL)
+		return 0;
+
+	ret = hist_browser__show_inline(browser, node, row, offset);
+
+	inline_node__delete(node);
+	return ret;
+}
+
 static int hist_browser__show_callchain_list(struct hist_browser *browser,
 					     struct callchain_node *node,
 					     struct callchain_list *chain,
@@ -764,6 +910,7 @@ static int hist_browser__show_callchain_list(struct hist_browser *browser,
 	char bf[1024], *alloc_str;
 	char buf[64], *alloc_str2;
 	const char *str;
+	int inline_rows = 0, ret = 1;
 
 	if (arg->row_offset != 0) {
 		arg->row_offset--;
@@ -801,10 +948,15 @@ static int hist_browser__show_callchain_list(struct hist_browser *browser,
 	}
 
 	print(browser, chain, str, offset, row, arg);
-
 	free(alloc_str);
 	free(alloc_str2);
-	return 1;
+
+	if (symbol_conf.inline_name) {
+		inline_rows = show_inline_list(browser, chain->ms.map,
+					       chain->ip, row + 1, offset);
+	}
+
+	return ret + inline_rows;
 }
 
 static bool check_percent_display(struct rb_node *node, u64 parent_total)
@@ -1228,6 +1380,12 @@ static int hist_browser__show_entry(struct hist_browser *browser,
 		folded_sign = hist_entry__folded(entry);
 	}
 
+	if (symbol_conf.inline_name &&
+	    (!entry->has_children)) {
+		hist_entry_init_inline_node(entry);
+		folded_sign = hist_entry__folded(entry);
+	}
+
 	if (row_offset == 0) {
 		struct hpp_arg arg = {
 			.b		= &browser->b,
@@ -1259,7 +1417,8 @@ static int hist_browser__show_entry(struct hist_browser *browser,
 			}
 
 			if (first) {
-				if (symbol_conf.use_callchain) {
+				if (symbol_conf.use_callchain ||
+					symbol_conf.inline_name) {
 					ui_browser__printf(&browser->b, "%c ", folded_sign);
 					width -= 2;
 				}
@@ -1301,8 +1460,14 @@ static int hist_browser__show_entry(struct hist_browser *browser,
 			.is_current_entry = current_entry,
 		};
 
-		printed += hist_browser__show_callchain(browser, entry, 1, row,
-					hist_browser__show_callchain_entry, &arg,
+		if (entry->inline_node)
+			printed += hist_browser__show_inline(browser,
+					entry->inline_node, row, 0);
+		else
+			printed += hist_browser__show_callchain(browser,
+					entry, 1, row,
+					hist_browser__show_callchain_entry,
+					&arg,
 					hist_browser__check_output_full);
 	}
 
@@ -2308,7 +2473,7 @@ static int switch_data_file(void)
 		return ret;
 
 	memset(options, 0, sizeof(options));
-	memset(options, 0, sizeof(abs_path));
+	memset(abs_path, 0, sizeof(abs_path));
 
 	while ((dent = readdir(pwd_dir))) {
 		char path[PATH_MAX];
diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c
index 668f4aecf2e6..d52d5f64ea89 100644
--- a/tools/perf/ui/stdio/hist.c
+++ b/tools/perf/ui/stdio/hist.c
@@ -17,6 +17,67 @@ static size_t callchain__fprintf_left_margin(FILE *fp, int left_margin)
 	return ret;
 }
 
+static size_t inline__fprintf(struct map *map, u64 ip, int left_margin,
+			      int depth, int depth_mask, FILE *fp)
+{
+	struct dso *dso;
+	struct inline_node *node;
+	struct inline_list *ilist;
+	int ret = 0, i;
+
+	if (map == NULL)
+		return 0;
+
+	dso = map->dso;
+	if (dso == NULL)
+		return 0;
+
+	if (dso->kernel != DSO_TYPE_USER)
+		return 0;
+
+	node = dso__parse_addr_inlines(dso,
+				       map__rip_2objdump(map, ip));
+	if (node == NULL)
+		return 0;
+
+	list_for_each_entry(ilist, &node->val, list) {
+		if ((ilist->filename != NULL) || (ilist->funcname != NULL)) {
+			ret += callchain__fprintf_left_margin(fp, left_margin);
+
+			for (i = 0; i < depth; i++) {
+				if (depth_mask & (1 << i))
+					ret += fprintf(fp, "|");
+				else
+					ret += fprintf(fp, " ");
+				ret += fprintf(fp, "          ");
+			}
+
+			if (callchain_param.key == CCKEY_ADDRESS ||
+			    callchain_param.key == CCKEY_SRCLINE) {
+				if (ilist->filename != NULL)
+					ret += fprintf(fp, "%s:%d (inline)",
+						       ilist->filename,
+						       ilist->line_nr);
+				else
+					ret += fprintf(fp, "??");
+			} else if (ilist->funcname != NULL)
+				ret += fprintf(fp, "%s (inline)",
+					       ilist->funcname);
+			else if (ilist->filename != NULL)
+				ret += fprintf(fp, "%s:%d (inline)",
+					       ilist->filename,
+					       ilist->line_nr);
+			else
+				ret += fprintf(fp, "??");
+
+			ret += fprintf(fp, "\n");
+		}
+	}
+
+	inline_node__delete(node);
+	return ret;
+}
+
 static size_t ipchain__fprintf_graph_line(FILE *fp, int depth, int depth_mask,
 					  int left_margin)
 {
@@ -78,6 +139,10 @@ static size_t ipchain__fprintf_graph(FILE *fp, struct callchain_node *node,
 	fputs(str, fp);
 	fputc('\n', fp);
 	free(alloc_str);
+
+	if (symbol_conf.inline_name)
+		ret += inline__fprintf(chain->ms.map, chain->ip,
+				       left_margin, depth, depth_mask, fp);
 	return ret;
 }
 
@@ -229,6 +294,7 @@ static size_t callchain__fprintf_graph(FILE *fp, struct rb_root *root,
 			if (!i++ && field_order == NULL &&
 			    sort_order && !prefixcmp(sort_order, "sym"))
 				continue;
+
 			if (!printed) {
 				ret += callchain__fprintf_left_margin(fp, left_margin);
 				ret += fprintf(fp, "|\n");
@@ -251,6 +317,13 @@ static size_t callchain__fprintf_graph(FILE *fp, struct rb_root *root,
 
 			if (++entries_printed == callchain_param.print_limit)
 				break;
+
+			if (symbol_conf.inline_name)
+				ret += inline__fprintf(chain->ms.map,
+						       chain->ip,
+						       left_margin,
+						       0, 0,
+						       fp);
 		}
 		root = &cnode->rb_root;
 	}
@@ -529,6 +602,8 @@ static int hist_entry__fprintf(struct hist_entry *he, size_t size,
 			       bool use_callchain)
 {
 	int ret;
+	int callchain_ret = 0;
+	int inline_ret = 0;
 	struct perf_hpp hpp = {
 		.buf		= bf,
 		.size		= size,
@@ -547,7 +622,16 @@ static int hist_entry__fprintf(struct hist_entry *he, size_t size,
 	ret = fprintf(fp, "%s\n", bf);
 
 	if (use_callchain)
-		ret += hist_entry_callchain__fprintf(he, total_period, 0, fp);
+		callchain_ret = hist_entry_callchain__fprintf(he, total_period,
+							      0, fp);
+
+	if (callchain_ret == 0 && symbol_conf.inline_name) {
+		inline_ret = inline__fprintf(he->ms.map, he->ip, 0, 0, 0, fp);
+		ret += inline_ret;
+		if (inline_ret > 0)
+			ret += fprintf(fp, "\n");
+	} else
+		ret += callchain_ret;
 
 	return ret;
 }
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 5da376bc1afc..5c0ea11a8f0a 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -1,4 +1,3 @@
-libperf-y += alias.o
 libperf-y += annotate.o
 libperf-y += block-range.o
 libperf-y += build-id.o
@@ -42,6 +41,7 @@ libperf-y += pstack.o
 libperf-y += session.o
 libperf-$(CONFIG_AUDIT) += syscalltbl.o
 libperf-y += ordered-events.o
+libperf-y += namespaces.o
 libperf-y += comm.o
 libperf-y += thread.o
 libperf-y += thread_map.o
@@ -81,6 +81,7 @@ libperf-$(CONFIG_AUXTRACE) += intel-pt-decoder/
 libperf-$(CONFIG_AUXTRACE) += intel-pt.o
 libperf-$(CONFIG_AUXTRACE) += intel-bts.o
 libperf-y += parse-branch-options.o
+libperf-y += dump-insn.o
 libperf-y += parse-regs-options.o
 libperf-y += term.o
 libperf-y += help-unknown-cmd.o
@@ -88,6 +89,7 @@ libperf-y += mem-events.o
 libperf-y += vsprintf.o
 libperf-y += drv_configs.o
 libperf-y += time-utils.o
+libperf-y += expr-bison.o
 
 libperf-$(CONFIG_LIBBPF) += bpf-loader.o
 libperf-$(CONFIG_BPF_PROLOGUE) += bpf-prologue.o
@@ -140,6 +142,10 @@ $(OUTPUT)util/parse-events-bison.c: util/parse-events.y
 	$(call rule_mkdir)
 	$(Q)$(call echo-cmd,bison)$(BISON) -v util/parse-events.y -d $(PARSER_DEBUG_BISON) -o $@ -p parse_events_
 
+$(OUTPUT)util/expr-bison.c: util/expr.y
+	$(call rule_mkdir)
+	$(Q)$(call echo-cmd,bison)$(BISON) -v util/expr.y -d $(PARSER_DEBUG_BISON) -o $@ -p expr__
+
 $(OUTPUT)util/pmu-flex.c: util/pmu.l $(OUTPUT)util/pmu-bison.c
 	$(call rule_mkdir)
 	$(Q)$(call echo-cmd,flex)$(FLEX) -o $@ --header-file=$(OUTPUT)util/pmu-flex.h util/pmu.l
@@ -152,6 +158,7 @@ CFLAGS_parse-events-flex.o  += -w
 CFLAGS_pmu-flex.o           += -w
 CFLAGS_parse-events-bison.o += -DYYENABLE_NLS=0 -w
 CFLAGS_pmu-bison.o          += -DYYENABLE_NLS=0 -DYYLTYPE_IS_TRIVIAL=0 -w
+CFLAGS_expr-bison.o         += -DYYENABLE_NLS=0 -DYYLTYPE_IS_TRIVIAL=0 -w
 
 $(OUTPUT)util/parse-events.o: $(OUTPUT)util/parse-events-flex.c $(OUTPUT)util/parse-events-bison.c
 $(OUTPUT)util/pmu.o: $(OUTPUT)util/pmu-flex.c $(OUTPUT)util/pmu-bison.c
diff --git a/tools/perf/util/alias.c b/tools/perf/util/alias.c
deleted file mode 100644
index 6455471d9cd1..000000000000
--- a/tools/perf/util/alias.c
+++ /dev/null
@@ -1,78 +0,0 @@
-#include "cache.h"
-#include "util.h"
-#include "config.h"
-
-static const char *alias_key;
-static char *alias_val;
-
-static int alias_lookup_cb(const char *k, const char *v,
-			   void *cb __maybe_unused)
-{
-	if (!prefixcmp(k, "alias.") && !strcmp(k+6, alias_key)) {
-		if (!v)
-			return config_error_nonbool(k);
-		alias_val = strdup(v);
-		return 0;
-	}
-	return 0;
-}
-
-char *alias_lookup(const char *alias)
-{
-	alias_key = alias;
-	alias_val = NULL;
-	perf_config(alias_lookup_cb, NULL);
-	return alias_val;
-}
-
-int split_cmdline(char *cmdline, const char ***argv)
-{
-	int src, dst, count = 0, size = 16;
-	char quoted = 0;
-
-	*argv = malloc(sizeof(char*) * size);
-
-	/* split alias_string */
-	(*argv)[count++] = cmdline;
-	for (src = dst = 0; cmdline[src];) {
-		char c = cmdline[src];
-		if (!quoted && isspace(c)) {
-			cmdline[dst++] = 0;
-			while (cmdline[++src]
-					&& isspace(cmdline[src]))
-				; /* skip */
-			if (count >= size) {
-				size += 16;
-				*argv = realloc(*argv, sizeof(char*) * size);
-			}
-			(*argv)[count++] = cmdline + dst;
-		} else if (!quoted && (c == '\'' || c == '"')) {
-			quoted = c;
-			src++;
-		} else if (c == quoted) {
-			quoted = 0;
-			src++;
-		} else {
-			if (c == '\\' && quoted != '\'') {
-				src++;
-				c = cmdline[src];
-				if (!c) {
-					zfree(argv);
-					return error("cmdline ends with \\");
-				}
-			}
-			cmdline[dst++] = c;
-			src++;
-		}
-	}
-
-	cmdline[dst] = 0;
-
-	if (quoted) {
-		zfree(argv);
-		return error("unclosed quote");
-	}
-
-	return count;
-}
-
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 273f21fa32b5..a37032bd137d 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -1307,6 +1307,7 @@ static int dso__disassemble_filename(struct dso *dso, char *filename, size_t fil
 {
 	char linkname[PATH_MAX];
 	char *build_id_filename;
+	char *build_id_path = NULL;
 
 	if (dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS &&
 	    !dso__is_kcore(dso))
@@ -1322,8 +1323,14 @@ static int dso__disassemble_filename(struct dso *dso, char *filename, size_t fil
 		goto fallback;
 	}
 
+	build_id_path = strdup(filename);
+	if (!build_id_path)
+		return -1;
+
+	dirname(build_id_path);
+
 	if (dso__is_kcore(dso) ||
-	    readlink(filename, linkname, sizeof(linkname)) < 0 ||
+	    readlink(build_id_path, linkname, sizeof(linkname)) < 0 ||
 	    strstr(linkname, DSO__NAME_KALLSYMS) ||
 	    access(filename, R_OK)) {
 fallback:
@@ -1335,6 +1342,7 @@ fallback:
 		__symbol__join_symfs(filename, filename_size, dso->long_name);
 	}
 
+	free(build_id_path);
 	return 0;
 }
 
@@ -1435,7 +1443,7 @@ int symbol__disassemble(struct symbol *sym, struct map *map, const char *arch_na
 	snprintf(command, sizeof(command),
 		 "%s %s%s --start-address=0x%016" PRIx64
 		 " --stop-address=0x%016" PRIx64
-		 " -l -d %s %s -C %s 2>/dev/null|grep -v %s|expand",
+		 " -l -d %s %s -C %s 2>/dev/null|grep -v %s:|expand",
 		 objdump_path ? objdump_path : "objdump",
 		 disassembler_style ? "-M " : "",
 		 disassembler_style ? disassembler_style : "",
@@ -1482,6 +1490,12 @@ int symbol__disassemble(struct symbol *sym, struct map *map, const char *arch_na
 
 	nline = 0;
 	while (!feof(file)) {
+		/*
+		 * The source code line number (lineno) needs to be kept in
+		 * accross calls to symbol__parse_objdump_line(), so that it
+		 * can associate it with the instructions till the next one.
+		 * See disasm_line__new() and struct disasm_line::line_nr.
+		 */
 		if (symbol__parse_objdump_line(sym, map, arch, file, privsize,
 			    &lineno) < 0)
 			break;
@@ -1651,24 +1665,31 @@ static int symbol__get_source_line(struct symbol *sym, struct map *map,
 	start = map__rip_2objdump(map, sym->start);
 
 	for (i = 0; i < len; i++) {
-		u64 offset;
+		u64 offset, nr_samples;
 		double percent_max = 0.0;
 
 		src_line->nr_pcnt = nr_pcnt;
 
 		for (k = 0; k < nr_pcnt; k++) {
+			double percent = 0.0;
+
 			h = annotation__histogram(notes, evidx + k);
-			src_line->samples[k].percent = 100.0 * h->addr[i] / h->sum;
+			nr_samples = h->addr[i];
+			if (h->sum)
+				percent = 100.0 * nr_samples / h->sum;
 
-			if (src_line->samples[k].percent > percent_max)
-				percent_max = src_line->samples[k].percent;
+			if (percent > percent_max)
+				percent_max = percent;
+			src_line->samples[k].percent = percent;
+			src_line->samples[k].nr = nr_samples;
 		}
 
 		if (percent_max <= 0.5)
 			goto next;
 
 		offset = start + i;
-		src_line->path = get_srcline(map->dso, offset, NULL, false);
+		src_line->path = get_srcline(map->dso, offset, NULL,
+					     false, true);
 		insert_source_line(&tmp_root, src_line);
 
 	next:
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index 09776b5af991..948aa8e6fd39 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -98,7 +98,7 @@ struct cyc_hist {
 struct source_line_samples {
 	double		percent;
 	double		percent_sum;
-	double          nr;
+	u64		nr;
 };
 
 struct source_line {
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index c5a6e0b12452..78bd632f144d 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -1826,7 +1826,7 @@ static int addr_filter__resolve_kernel_syms(struct addr_filter *filt)
 		filt->addr = start;
 		if (filt->range && !filt->size && !filt->sym_to) {
 			filt->size = size;
-			no_size = !!size;
+			no_size = !size;
 		}
 	}
 
@@ -1840,7 +1840,7 @@ static int addr_filter__resolve_kernel_syms(struct addr_filter *filt)
 		if (err)
 			return err;
 		filt->size = start + size - filt->addr;
-		no_size = !!size;
+		no_size = !size;
 	}
 
 	/* The very last symbol in kallsyms does not imply a particular size */
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index e528c40739cc..33af67530d30 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -182,13 +182,17 @@ char *build_id_cache__origname(const char *sbuild_id)
 	char buf[PATH_MAX];
 	char *ret = NULL, *p;
 	size_t offs = 5;	/* == strlen("../..") */
+	ssize_t len;
 
 	linkname = build_id_cache__linkname(sbuild_id, NULL, 0);
 	if (!linkname)
 		return NULL;
 
-	if (readlink(linkname, buf, PATH_MAX) < 0)
+	len = readlink(linkname, buf, sizeof(buf) - 1);
+	if (len <= 0)
 		goto out;
+	buf[len] = '\0';
+
 	/* The link should be "../..<origpath>/<sbuild_id>" */
 	p = strrchr(buf, '/');	/* Cut off the "/<sbuild_id>" */
 	if (p && (p > buf + offs)) {
@@ -690,7 +694,7 @@ int build_id_cache__add_s(const char *sbuild_id, const char *name,
 		err = 0;
 
 	/* Update SDT cache : error is just warned */
-	if (build_id_cache__add_sdt_cache(sbuild_id, realname) < 0)
+	if (realname && build_id_cache__add_sdt_cache(sbuild_id, realname) < 0)
 		pr_debug4("Failed to update/scan SDT cache for %s\n", realname);
 
 out_free:
diff --git a/tools/perf/util/cache.h b/tools/perf/util/cache.h
index 512c0c83fbc6..0328f297a748 100644
--- a/tools/perf/util/cache.h
+++ b/tools/perf/util/cache.h
@@ -15,7 +15,6 @@
 #define PERF_TRACEFS_ENVIRONMENT "PERF_TRACEFS_DIR"
 #define PERF_PAGER_ENVIRONMENT "PERF_PAGER"
 
-char *alias_lookup(const char *alias);
 int split_cmdline(char *cmdline, const char ***argv);
 
 #define alloc_nr(x) (((x)+16)*3/2)
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index aba953421a03..3cea1fb5404b 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -80,6 +80,10 @@ static int parse_callchain_sort_key(const char *value)
 		callchain_param.key = CCKEY_ADDRESS;
 		return 0;
 	}
+	if (!strncmp(value, "srcline", strlen(value))) {
+		callchain_param.key = CCKEY_SRCLINE;
+		return 0;
+	}
 	if (!strncmp(value, "branch", strlen(value))) {
 		callchain_param.branch_callstack = 1;
 		return 0;
@@ -510,14 +514,51 @@ enum match_result {
 	MATCH_GT,
 };
 
+static enum match_result match_chain_srcline(struct callchain_cursor_node *node,
+					     struct callchain_list *cnode)
+{
+	char *left = get_srcline(cnode->ms.map->dso,
+				 map__rip_2objdump(cnode->ms.map, cnode->ip),
+				 cnode->ms.sym, true, false);
+	char *right = get_srcline(node->map->dso,
+				  map__rip_2objdump(node->map, node->ip),
+				  node->sym, true, false);
+	enum match_result ret = MATCH_EQ;
+	int cmp;
+
+	if (left && right)
+		cmp = strcmp(left, right);
+	else if (!left && right)
+		cmp = 1;
+	else if (left && !right)
+		cmp = -1;
+	else if (cnode->ip == node->ip)
+		cmp = 0;
+	else
+		cmp = (cnode->ip < node->ip) ? -1 : 1;
+
+	if (cmp != 0)
+		ret = cmp < 0 ? MATCH_LT : MATCH_GT;
+
+	free_srcline(left);
+	free_srcline(right);
+	return ret;
+}
+
 static enum match_result match_chain(struct callchain_cursor_node *node,
 				     struct callchain_list *cnode)
 {
 	struct symbol *sym = node->sym;
 	u64 left, right;
 
-	if (cnode->ms.sym && sym &&
-	    callchain_param.key == CCKEY_FUNCTION) {
+	if (callchain_param.key == CCKEY_SRCLINE) {
+		enum match_result match = match_chain_srcline(node, cnode);
+
+		if (match != MATCH_ERROR)
+			return match;
+	}
+
+	if (cnode->ms.sym && sym && callchain_param.key == CCKEY_FUNCTION) {
 		left = cnode->ms.sym->start;
 		right = sym->start;
 	} else {
@@ -911,15 +952,16 @@ out:
 char *callchain_list__sym_name(struct callchain_list *cl,
 			       char *bf, size_t bfsize, bool show_dso)
 {
+	bool show_addr = callchain_param.key == CCKEY_ADDRESS;
+	bool show_srcline = show_addr || callchain_param.key == CCKEY_SRCLINE;
 	int printed;
 
 	if (cl->ms.sym) {
-		if (callchain_param.key == CCKEY_ADDRESS &&
-		    cl->ms.map && !cl->srcline)
+		if (show_srcline && cl->ms.map && !cl->srcline)
 			cl->srcline = get_srcline(cl->ms.map->dso,
 						  map__rip_2objdump(cl->ms.map,
 								    cl->ip),
-						  cl->ms.sym, false);
+						  cl->ms.sym, false, show_addr);
 		if (cl->srcline)
 			printed = scnprintf(bf, bfsize, "%s %s",
 					cl->ms.sym->name, cl->srcline);
@@ -1063,63 +1105,100 @@ int callchain_branch_counts(struct callchain_root *root,
 						  cycles_count);
 }
 
-static int callchain_counts_printf(FILE *fp, char *bf, int bfsize,
-				   u64 branch_count, u64 predicted_count,
-				   u64 abort_count, u64 cycles_count,
-				   u64 iter_count, u64 samples_count)
+static int counts_str_build(char *bf, int bfsize,
+			     u64 branch_count, u64 predicted_count,
+			     u64 abort_count, u64 cycles_count,
+			     u64 iter_count, u64 samples_count)
 {
 	double predicted_percent = 0.0;
 	const char *null_str = "";
 	char iter_str[32];
-	char *str;
-	u64 cycles = 0;
-
-	if (branch_count == 0) {
-		if (fp)
-			return fprintf(fp, " (calltrace)");
+	char cycle_str[32];
+	char *istr, *cstr;
+	u64 cycles;
 
+	if (branch_count == 0)
 		return scnprintf(bf, bfsize, " (calltrace)");
-	}
+
+	cycles = cycles_count / branch_count;
 
 	if (iter_count && samples_count) {
-		scnprintf(iter_str, sizeof(iter_str),
-			 ", iterations:%" PRId64 "",
-			 iter_count / samples_count);
-		str = iter_str;
+		if (cycles > 0)
+			scnprintf(iter_str, sizeof(iter_str),
+				 " iterations:%" PRId64 "",
+				 iter_count / samples_count);
+		else
+			scnprintf(iter_str, sizeof(iter_str),
+				 "iterations:%" PRId64 "",
+				 iter_count / samples_count);
+		istr = iter_str;
 	} else
-		str = (char *)null_str;
+		istr = (char *)null_str;
+
+	if (cycles > 0) {
+		scnprintf(cycle_str, sizeof(cycle_str),
+			  "cycles:%" PRId64 "", cycles);
+		cstr = cycle_str;
+	} else
+		cstr = (char *)null_str;
 
 	predicted_percent = predicted_count * 100.0 / branch_count;
-	cycles = cycles_count / branch_count;
 
-	if ((predicted_percent >= 100.0) && (abort_count == 0)) {
-		if (fp)
-			return fprintf(fp, " (cycles:%" PRId64 "%s)",
-				       cycles, str);
+	if ((predicted_count == branch_count) && (abort_count == 0)) {
+		if ((cycles > 0) || (istr != (char *)null_str))
+			return scnprintf(bf, bfsize, " (%s%s)", cstr, istr);
+		else
+			return scnprintf(bf, bfsize, "%s", (char *)null_str);
+	}
 
-		return scnprintf(bf, bfsize, " (cycles:%" PRId64 "%s)",
-				 cycles, str);
+	if ((predicted_count < branch_count) && (abort_count == 0)) {
+		if ((cycles > 0) || (istr != (char *)null_str))
+			return scnprintf(bf, bfsize,
+				" (predicted:%.1f%% %s%s)",
+				predicted_percent, cstr, istr);
+		else {
+			return scnprintf(bf, bfsize,
+				" (predicted:%.1f%%)",
+				predicted_percent);
+		}
 	}
 
-	if ((predicted_percent < 100.0) && (abort_count == 0)) {
-		if (fp)
-			return fprintf(fp,
-				" (predicted:%.1f%%, cycles:%" PRId64 "%s)",
-				predicted_percent, cycles, str);
+	if ((predicted_count == branch_count) && (abort_count > 0)) {
+		if ((cycles > 0) || (istr != (char *)null_str))
+			return scnprintf(bf, bfsize,
+				" (abort:%" PRId64 " %s%s)",
+				abort_count, cstr, istr);
+		else
+			return scnprintf(bf, bfsize,
+				" (abort:%" PRId64 ")",
+				abort_count);
+	}
 
+	if ((cycles > 0) || (istr != (char *)null_str))
 		return scnprintf(bf, bfsize,
-			" (predicted:%.1f%%, cycles:%" PRId64 "%s)",
-			predicted_percent, cycles, str);
-	}
+			" (predicted:%.1f%% abort:%" PRId64 " %s%s)",
+			predicted_percent, abort_count, cstr, istr);
+
+	return scnprintf(bf, bfsize,
+			" (predicted:%.1f%% abort:%" PRId64 ")",
+			predicted_percent, abort_count);
+}
+
+static int callchain_counts_printf(FILE *fp, char *bf, int bfsize,
+				   u64 branch_count, u64 predicted_count,
+				   u64 abort_count, u64 cycles_count,
+				   u64 iter_count, u64 samples_count)
+{
+	char str[128];
+
+	counts_str_build(str, sizeof(str), branch_count,
+			 predicted_count, abort_count, cycles_count,
+			 iter_count, samples_count);
 
 	if (fp)
-		return fprintf(fp,
-		" (predicted:%.1f%%, abort:%" PRId64 ", cycles:%" PRId64 "%s)",
-			predicted_percent, abort_count, cycles, str);
+		return fprintf(fp, "%s", str);
 
-	return scnprintf(bf, bfsize,
-		" (predicted:%.1f%%, abort:%" PRId64 ", cycles:%" PRId64 "%s)",
-		predicted_percent, abort_count, cycles, str);
+	return scnprintf(bf, bfsize, "%s", str);
 }
 
 int callchain_list_counts__printf_value(struct callchain_node *node,
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index 4f4b60f1558a..c56c23dbbf72 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -77,7 +77,8 @@ typedef void (*sort_chain_func_t)(struct rb_root *, struct callchain_root *,
 
 enum chain_key {
 	CCKEY_FUNCTION,
-	CCKEY_ADDRESS
+	CCKEY_ADDRESS,
+	CCKEY_SRCLINE
 };
 
 enum chain_value {
diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c
index eafbf11442b2..86399eda3684 100644
--- a/tools/perf/util/cgroup.c
+++ b/tools/perf/util/cgroup.c
@@ -127,19 +127,19 @@ static int add_cgroup(struct perf_evlist *evlist, char *str)
 			goto found;
 		n++;
 	}
-	if (atomic_read(&cgrp->refcnt) == 0)
+	if (refcount_read(&cgrp->refcnt) == 0)
 		free(cgrp);
 
 	return -1;
 found:
-	atomic_inc(&cgrp->refcnt);
+	refcount_inc(&cgrp->refcnt);
 	counter->cgrp = cgrp;
 	return 0;
 }
 
 void close_cgroup(struct cgroup_sel *cgrp)
 {
-	if (cgrp && atomic_dec_and_test(&cgrp->refcnt)) {
+	if (cgrp && refcount_dec_and_test(&cgrp->refcnt)) {
 		close(cgrp->fd);
 		zfree(&cgrp->name);
 		free(cgrp);
diff --git a/tools/perf/util/cgroup.h b/tools/perf/util/cgroup.h
index 31f8dcdbd7ef..d91966b97cbd 100644
--- a/tools/perf/util/cgroup.h
+++ b/tools/perf/util/cgroup.h
@@ -1,14 +1,14 @@
 #ifndef __CGROUP_H__
 #define __CGROUP_H__
 
-#include <linux/atomic.h>
+#include <linux/refcount.h>
 
 struct option;
 
 struct cgroup_sel {
 	char *name;
 	int fd;
-	atomic_t refcnt;
+	refcount_t refcnt;
 };
 
 
diff --git a/tools/perf/util/cloexec.h b/tools/perf/util/cloexec.h
index d0d465953d36..94a5a7d829d5 100644
--- a/tools/perf/util/cloexec.h
+++ b/tools/perf/util/cloexec.h
@@ -3,10 +3,4 @@
 
 unsigned long perf_event_open_cloexec_flag(void);
 
-#ifdef __GLIBC_PREREQ
-#if !__GLIBC_PREREQ(2, 6) && !defined(__UCLIBC__)
-int sched_getcpu(void) __THROW;
-#endif
-#endif
-
 #endif /* __PERF_CLOEXEC_H */
diff --git a/tools/perf/util/comm.c b/tools/perf/util/comm.c
index 21b7ff382c3f..32837b6f7879 100644
--- a/tools/perf/util/comm.c
+++ b/tools/perf/util/comm.c
@@ -2,12 +2,12 @@
 #include "util.h"
 #include <stdlib.h>
 #include <stdio.h>
-#include <linux/atomic.h>
+#include <linux/refcount.h>
 
 struct comm_str {
 	char *str;
 	struct rb_node rb_node;
-	atomic_t refcnt;
+	refcount_t refcnt;
 };
 
 /* Should perhaps be moved to struct machine */
@@ -16,13 +16,13 @@ static struct rb_root comm_str_root;
 static struct comm_str *comm_str__get(struct comm_str *cs)
 {
 	if (cs)
-		atomic_inc(&cs->refcnt);
+		refcount_inc(&cs->refcnt);
 	return cs;
 }
 
 static void comm_str__put(struct comm_str *cs)
 {
-	if (cs && atomic_dec_and_test(&cs->refcnt)) {
+	if (cs && refcount_dec_and_test(&cs->refcnt)) {
 		rb_erase(&cs->rb_node, &comm_str_root);
 		zfree(&cs->str);
 		free(cs);
@@ -43,7 +43,7 @@ static struct comm_str *comm_str__alloc(const char *str)
 		return NULL;
 	}
 
-	atomic_set(&cs->refcnt, 0);
+	refcount_set(&cs->refcnt, 1);
 
 	return cs;
 }
@@ -61,7 +61,7 @@ static struct comm_str *comm_str__findnew(const char *str, struct rb_root *root)
 
 		cmp = strcmp(str, iter->str);
 		if (!cmp)
-			return iter;
+			return comm_str__get(iter);
 
 		if (cmp < 0)
 			p = &(*p)->rb_left;
@@ -95,8 +95,6 @@ struct comm *comm__new(const char *str, u64 timestamp, bool exec)
 		return NULL;
 	}
 
-	comm_str__get(comm->comm_str);
-
 	return comm;
 }
 
@@ -108,7 +106,6 @@ int comm__override(struct comm *comm, const char *str, u64 timestamp, bool exec)
 	if (!new)
 		return -ENOMEM;
 
-	comm_str__get(new);
 	comm_str__put(old);
 	comm->comm_str = new;
 	comm->start = timestamp;
diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c
index 0c7d5a4975cd..7b01d59076d3 100644
--- a/tools/perf/util/config.c
+++ b/tools/perf/util/config.c
@@ -627,6 +627,8 @@ static int perf_config_set__init(struct perf_config_set *set)
 {
 	int ret = -1;
 	const char *home = NULL;
+	char *user_config;
+	struct stat st;
 
 	/* Setting $PERF_CONFIG makes perf read _only_ the given config file. */
 	if (config_exclusive_filename)
@@ -637,35 +639,41 @@ static int perf_config_set__init(struct perf_config_set *set)
 	}
 
 	home = getenv("HOME");
-	if (perf_config_global() && home) {
-		char *user_config = strdup(mkpath("%s/.perfconfig", home));
-		struct stat st;
 
-		if (user_config == NULL) {
-			warning("Not enough memory to process %s/.perfconfig, "
-				"ignoring it.", home);
-			goto out;
-		}
+	/*
+	 * Skip reading user config if:
+	 *   - there is no place to read it from (HOME)
+	 *   - we are asked not to (PERF_CONFIG_NOGLOBAL=1)
+	 */
+	if (!home || !*home || !perf_config_global())
+		return 0;
 
-		if (stat(user_config, &st) < 0) {
-			if (errno == ENOENT)
-				ret = 0;
-			goto out_free;
-		}
+	user_config = strdup(mkpath("%s/.perfconfig", home));
+	if (user_config == NULL) {
+		warning("Not enough memory to process %s/.perfconfig, "
+			"ignoring it.", home);
+		goto out;
+	}
+
+	if (stat(user_config, &st) < 0) {
+		if (errno == ENOENT)
+			ret = 0;
+		goto out_free;
+	}
 
-		ret = 0;
+	ret = 0;
 
-		if (st.st_uid && (st.st_uid != geteuid())) {
-			warning("File %s not owned by current user or root, "
-				"ignoring it.", user_config);
-			goto out_free;
-		}
+	if (st.st_uid && (st.st_uid != geteuid())) {
+		warning("File %s not owned by current user or root, "
+			"ignoring it.", user_config);
+		goto out_free;
+	}
+
+	if (st.st_size)
+		ret = perf_config_from_file(collect_config, user_config, set);
 
-		if (st.st_size)
-			ret = perf_config_from_file(collect_config, user_config, set);
 out_free:
-		free(user_config);
-	}
+	free(user_config);
 out:
 	return ret;
 }
diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c
index 8c7504939113..061018b42393 100644
--- a/tools/perf/util/cpumap.c
+++ b/tools/perf/util/cpumap.c
@@ -29,7 +29,7 @@ static struct cpu_map *cpu_map__default_new(void)
 			cpus->map[i] = i;
 
 		cpus->nr = nr_cpus;
-		atomic_set(&cpus->refcnt, 1);
+		refcount_set(&cpus->refcnt, 1);
 	}
 
 	return cpus;
@@ -43,7 +43,7 @@ static struct cpu_map *cpu_map__trim_new(int nr_cpus, int *tmp_cpus)
 	if (cpus != NULL) {
 		cpus->nr = nr_cpus;
 		memcpy(cpus->map, tmp_cpus, payload_size);
-		atomic_set(&cpus->refcnt, 1);
+		refcount_set(&cpus->refcnt, 1);
 	}
 
 	return cpus;
@@ -252,7 +252,7 @@ struct cpu_map *cpu_map__dummy_new(void)
 	if (cpus != NULL) {
 		cpus->nr = 1;
 		cpus->map[0] = -1;
-		atomic_set(&cpus->refcnt, 1);
+		refcount_set(&cpus->refcnt, 1);
 	}
 
 	return cpus;
@@ -269,7 +269,7 @@ struct cpu_map *cpu_map__empty_new(int nr)
 		for (i = 0; i < nr; i++)
 			cpus->map[i] = -1;
 
-		atomic_set(&cpus->refcnt, 1);
+		refcount_set(&cpus->refcnt, 1);
 	}
 
 	return cpus;
@@ -278,7 +278,7 @@ struct cpu_map *cpu_map__empty_new(int nr)
 static void cpu_map__delete(struct cpu_map *map)
 {
 	if (map) {
-		WARN_ONCE(atomic_read(&map->refcnt) != 0,
+		WARN_ONCE(refcount_read(&map->refcnt) != 0,
 			  "cpu_map refcnt unbalanced\n");
 		free(map);
 	}
@@ -287,13 +287,13 @@ static void cpu_map__delete(struct cpu_map *map)
 struct cpu_map *cpu_map__get(struct cpu_map *map)
 {
 	if (map)
-		atomic_inc(&map->refcnt);
+		refcount_inc(&map->refcnt);
 	return map;
 }
 
 void cpu_map__put(struct cpu_map *map)
 {
-	if (map && atomic_dec_and_test(&map->refcnt))
+	if (map && refcount_dec_and_test(&map->refcnt))
 		cpu_map__delete(map);
 }
 
@@ -357,7 +357,7 @@ int cpu_map__build_map(struct cpu_map *cpus, struct cpu_map **res,
 	/* ensure we process id in increasing order */
 	qsort(c->map, c->nr, sizeof(int), cmp_ids);
 
-	atomic_set(&c->refcnt, 1);
+	refcount_set(&c->refcnt, 1);
 	*res = c;
 	return 0;
 }
@@ -673,3 +673,49 @@ size_t cpu_map__snprint(struct cpu_map *map, char *buf, size_t size)
 	pr_debug("cpumask list: %s\n", buf);
 	return ret;
 }
+
+static char hex_char(unsigned char val)
+{
+	if (val < 10)
+		return val + '0';
+	if (val < 16)
+		return val - 10 + 'a';
+	return '?';
+}
+
+size_t cpu_map__snprint_mask(struct cpu_map *map, char *buf, size_t size)
+{
+	int i, cpu;
+	char *ptr = buf;
+	unsigned char *bitmap;
+	int last_cpu = cpu_map__cpu(map, map->nr - 1);
+
+	bitmap = zalloc((last_cpu + 7) / 8);
+	if (bitmap == NULL) {
+		buf[0] = '\0';
+		return 0;
+	}
+
+	for (i = 0; i < map->nr; i++) {
+		cpu = cpu_map__cpu(map, i);
+		bitmap[cpu / 8] |= 1 << (cpu % 8);
+	}
+
+	for (cpu = last_cpu / 4 * 4; cpu >= 0; cpu -= 4) {
+		unsigned char bits = bitmap[cpu / 8];
+
+		if (cpu % 8)
+			bits >>= 4;
+		else
+			bits &= 0xf;
+
+		*ptr++ = hex_char(bits);
+		if ((cpu % 32) == 0 && cpu > 0)
+			*ptr++ = ',';
+	}
+	*ptr = '\0';
+	free(bitmap);
+
+	buf[size - 1] = '\0';
+	return ptr - buf;
+}
diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h
index 1a0549af8f5c..6b8bff87481d 100644
--- a/tools/perf/util/cpumap.h
+++ b/tools/perf/util/cpumap.h
@@ -3,13 +3,13 @@
 
 #include <stdio.h>
 #include <stdbool.h>
-#include <linux/atomic.h>
+#include <linux/refcount.h>
 
 #include "perf.h"
 #include "util/debug.h"
 
 struct cpu_map {
-	atomic_t refcnt;
+	refcount_t refcnt;
 	int nr;
 	int map[];
 };
@@ -20,6 +20,7 @@ struct cpu_map *cpu_map__dummy_new(void);
 struct cpu_map *cpu_map__new_data(struct cpu_map_data *data);
 struct cpu_map *cpu_map__read(FILE *file);
 size_t cpu_map__snprint(struct cpu_map *map, char *buf, size_t size);
+size_t cpu_map__snprint_mask(struct cpu_map *map, char *buf, size_t size);
 size_t cpu_map__fprintf(struct cpu_map *map, FILE *fp);
 int cpu_map__get_socket_id(int cpu);
 int cpu_map__get_socket(struct cpu_map *map, int idx, void *data);
diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c
index 4e6cbc99f08e..89ece2445713 100644
--- a/tools/perf/util/data-convert-bt.c
+++ b/tools/perf/util/data-convert-bt.c
@@ -1468,6 +1468,7 @@ int bt_convert__perf2ctf(const char *input, const char *path,
 			.lost            = perf_event__process_lost,
 			.tracing_data    = perf_event__process_tracing_data,
 			.build_id        = perf_event__process_build_id,
+			.namespaces      = perf_event__process_namespaces,
 			.ordered_events  = true,
 			.ordering_requires_timestamps = true,
 		},
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index d38b62a700ca..42db00d78573 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -1109,7 +1109,7 @@ struct dso *dso__new(const char *name)
 		INIT_LIST_HEAD(&dso->node);
 		INIT_LIST_HEAD(&dso->data.open_entry);
 		pthread_mutex_init(&dso->lock, NULL);
-		atomic_set(&dso->refcnt, 1);
+		refcount_set(&dso->refcnt, 1);
 	}
 
 	return dso;
@@ -1147,13 +1147,13 @@ void dso__delete(struct dso *dso)
 struct dso *dso__get(struct dso *dso)
 {
 	if (dso)
-		atomic_inc(&dso->refcnt);
+		refcount_inc(&dso->refcnt);
 	return dso;
 }
 
 void dso__put(struct dso *dso)
 {
-	if (dso && atomic_dec_and_test(&dso->refcnt))
+	if (dso && refcount_dec_and_test(&dso->refcnt))
 		dso__delete(dso);
 }
 
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index ecc4bbd3f82e..12350b171727 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -1,7 +1,7 @@
 #ifndef __PERF_DSO
 #define __PERF_DSO
 
-#include <linux/atomic.h>
+#include <linux/refcount.h>
 #include <linux/types.h>
 #include <linux/rbtree.h>
 #include <sys/types.h>
@@ -187,7 +187,7 @@ struct dso {
 		void	 *priv;
 		u64	 db_id;
 	};
-	atomic_t	 refcnt;
+	refcount_t	 refcnt;
 	char		 name[0];
 };
 
diff --git a/tools/perf/util/dump-insn.c b/tools/perf/util/dump-insn.c
new file mode 100644
index 000000000000..ffbdb19f05d0
--- /dev/null
+++ b/tools/perf/util/dump-insn.c
@@ -0,0 +1,14 @@
+#include <linux/compiler.h>
+#include "dump-insn.h"
+
+/* Fallback code */
+
+__weak
+const char *dump_insn(struct perf_insn *x __maybe_unused,
+		      u64 ip __maybe_unused, u8 *inbuf __maybe_unused,
+		      int inlen __maybe_unused, int *lenp)
+{
+	if (lenp)
+		*lenp = 0;
+	return "?";
+}
diff --git a/tools/perf/util/dump-insn.h b/tools/perf/util/dump-insn.h
new file mode 100644
index 000000000000..90fb115981cf
--- /dev/null
+++ b/tools/perf/util/dump-insn.h
@@ -0,0 +1,22 @@
+#ifndef __PERF_DUMP_INSN_H
+#define __PERF_DUMP_INSN_H 1
+
+#define MAXINSN 15
+
+#include <linux/types.h>
+
+struct thread;
+
+struct perf_insn {
+	/* Initialized by callers: */
+	struct thread *thread;
+	u8	      cpumode;
+	bool	      is64bit;
+	int	      cpu;
+	/* Temporary */
+	char	      out[256];
+};
+
+const char *dump_insn(struct perf_insn *x, u64 ip,
+		      u8 *inbuf, int inlen, int *lenp);
+#endif
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 4ea7ce72ed9c..76b9c6bc8369 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -31,6 +31,7 @@ static const char *perf_event__names[] = {
 	[PERF_RECORD_LOST_SAMPLES]		= "LOST_SAMPLES",
 	[PERF_RECORD_SWITCH]			= "SWITCH",
 	[PERF_RECORD_SWITCH_CPU_WIDE]		= "SWITCH_CPU_WIDE",
+	[PERF_RECORD_NAMESPACES]		= "NAMESPACES",
 	[PERF_RECORD_HEADER_ATTR]		= "ATTR",
 	[PERF_RECORD_HEADER_EVENT_TYPE]		= "EVENT_TYPE",
 	[PERF_RECORD_HEADER_TRACING_DATA]	= "TRACING_DATA",
@@ -49,6 +50,16 @@ static const char *perf_event__names[] = {
 	[PERF_RECORD_TIME_CONV]			= "TIME_CONV",
 };
 
+static const char *perf_ns__names[] = {
+	[NET_NS_INDEX]		= "net",
+	[UTS_NS_INDEX]		= "uts",
+	[IPC_NS_INDEX]		= "ipc",
+	[PID_NS_INDEX]		= "pid",
+	[USER_NS_INDEX]		= "user",
+	[MNT_NS_INDEX]		= "mnt",
+	[CGROUP_NS_INDEX]	= "cgroup",
+};
+
 const char *perf_event__name(unsigned int id)
 {
 	if (id >= ARRAY_SIZE(perf_event__names))
@@ -58,6 +69,13 @@ const char *perf_event__name(unsigned int id)
 	return perf_event__names[id];
 }
 
+static const char *perf_ns__name(unsigned int id)
+{
+	if (id >= ARRAY_SIZE(perf_ns__names))
+		return "UNKNOWN";
+	return perf_ns__names[id];
+}
+
 static int perf_tool__process_synth_event(struct perf_tool *tool,
 					  union perf_event *event,
 					  struct machine *machine,
@@ -203,6 +221,58 @@ pid_t perf_event__synthesize_comm(struct perf_tool *tool,
 	return tgid;
 }
 
+static void perf_event__get_ns_link_info(pid_t pid, const char *ns,
+					 struct perf_ns_link_info *ns_link_info)
+{
+	struct stat64 st;
+	char proc_ns[128];
+
+	sprintf(proc_ns, "/proc/%u/ns/%s", pid, ns);
+	if (stat64(proc_ns, &st) == 0) {
+		ns_link_info->dev = st.st_dev;
+		ns_link_info->ino = st.st_ino;
+	}
+}
+
+int perf_event__synthesize_namespaces(struct perf_tool *tool,
+				      union perf_event *event,
+				      pid_t pid, pid_t tgid,
+				      perf_event__handler_t process,
+				      struct machine *machine)
+{
+	u32 idx;
+	struct perf_ns_link_info *ns_link_info;
+
+	if (!tool || !tool->namespace_events)
+		return 0;
+
+	memset(&event->namespaces, 0, (sizeof(event->namespaces) +
+	       (NR_NAMESPACES * sizeof(struct perf_ns_link_info)) +
+	       machine->id_hdr_size));
+
+	event->namespaces.pid = tgid;
+	event->namespaces.tid = pid;
+
+	event->namespaces.nr_namespaces = NR_NAMESPACES;
+
+	ns_link_info = event->namespaces.link_info;
+
+	for (idx = 0; idx < event->namespaces.nr_namespaces; idx++)
+		perf_event__get_ns_link_info(pid, perf_ns__name(idx),
+					     &ns_link_info[idx]);
+
+	event->namespaces.header.type = PERF_RECORD_NAMESPACES;
+
+	event->namespaces.header.size = (sizeof(event->namespaces) +
+			(NR_NAMESPACES * sizeof(struct perf_ns_link_info)) +
+			machine->id_hdr_size);
+
+	if (perf_tool__process_synth_event(tool, event, machine, process) != 0)
+		return -1;
+
+	return 0;
+}
+
 static int perf_event__synthesize_fork(struct perf_tool *tool,
 				       union perf_event *event,
 				       pid_t pid, pid_t tgid, pid_t ppid,
@@ -255,8 +325,8 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 	if (machine__is_default_guest(machine))
 		return 0;
 
-	snprintf(filename, sizeof(filename), "%s/proc/%d/maps",
-		 machine->root_dir, pid);
+	snprintf(filename, sizeof(filename), "%s/proc/%d/task/%d/maps",
+		 machine->root_dir, pid, pid);
 
 	fp = fopen(filename, "r");
 	if (fp == NULL) {
@@ -434,8 +504,9 @@ int perf_event__synthesize_modules(struct perf_tool *tool,
 static int __event__synthesize_thread(union perf_event *comm_event,
 				      union perf_event *mmap_event,
 				      union perf_event *fork_event,
+				      union perf_event *namespaces_event,
 				      pid_t pid, int full,
-					  perf_event__handler_t process,
+				      perf_event__handler_t process,
 				      struct perf_tool *tool,
 				      struct machine *machine,
 				      bool mmap_data,
@@ -455,6 +526,11 @@ static int __event__synthesize_thread(union perf_event *comm_event,
 		if (tgid == -1)
 			return -1;
 
+		if (perf_event__synthesize_namespaces(tool, namespaces_event, pid,
+						      tgid, process, machine) < 0)
+			return -1;
+
+
 		return perf_event__synthesize_mmap_events(tool, mmap_event, pid, tgid,
 							  process, machine, mmap_data,
 							  proc_map_timeout);
@@ -488,6 +564,11 @@ static int __event__synthesize_thread(union perf_event *comm_event,
 		if (perf_event__synthesize_fork(tool, fork_event, _pid, tgid,
 						ppid, process, machine) < 0)
 			break;
+
+		if (perf_event__synthesize_namespaces(tool, namespaces_event, _pid,
+						      tgid, process, machine) < 0)
+			break;
+
 		/*
 		 * Send the prepared comm event
 		 */
@@ -516,6 +597,7 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool,
 				      unsigned int proc_map_timeout)
 {
 	union perf_event *comm_event, *mmap_event, *fork_event;
+	union perf_event *namespaces_event;
 	int err = -1, thread, j;
 
 	comm_event = malloc(sizeof(comm_event->comm) + machine->id_hdr_size);
@@ -530,10 +612,16 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool,
 	if (fork_event == NULL)
 		goto out_free_mmap;
 
+	namespaces_event = malloc(sizeof(namespaces_event->namespaces) +
+				  (NR_NAMESPACES * sizeof(struct perf_ns_link_info)) +
+				  machine->id_hdr_size);
+	if (namespaces_event == NULL)
+		goto out_free_fork;
+
 	err = 0;
 	for (thread = 0; thread < threads->nr; ++thread) {
 		if (__event__synthesize_thread(comm_event, mmap_event,
-					       fork_event,
+					       fork_event, namespaces_event,
 					       thread_map__pid(threads, thread), 0,
 					       process, tool, machine,
 					       mmap_data, proc_map_timeout)) {
@@ -559,7 +647,7 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool,
 			/* if not, generate events for it */
 			if (need_leader &&
 			    __event__synthesize_thread(comm_event, mmap_event,
-						       fork_event,
+						       fork_event, namespaces_event,
 						       comm_event->comm.pid, 0,
 						       process, tool, machine,
 						       mmap_data, proc_map_timeout)) {
@@ -568,6 +656,8 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool,
 			}
 		}
 	}
+	free(namespaces_event);
+out_free_fork:
 	free(fork_event);
 out_free_mmap:
 	free(mmap_event);
@@ -587,6 +677,7 @@ int perf_event__synthesize_threads(struct perf_tool *tool,
 	char proc_path[PATH_MAX];
 	struct dirent *dirent;
 	union perf_event *comm_event, *mmap_event, *fork_event;
+	union perf_event *namespaces_event;
 	int err = -1;
 
 	if (machine__is_default_guest(machine))
@@ -604,11 +695,17 @@ int perf_event__synthesize_threads(struct perf_tool *tool,
 	if (fork_event == NULL)
 		goto out_free_mmap;
 
+	namespaces_event = malloc(sizeof(namespaces_event->namespaces) +
+				  (NR_NAMESPACES * sizeof(struct perf_ns_link_info)) +
+				  machine->id_hdr_size);
+	if (namespaces_event == NULL)
+		goto out_free_fork;
+
 	snprintf(proc_path, sizeof(proc_path), "%s/proc", machine->root_dir);
 	proc = opendir(proc_path);
 
 	if (proc == NULL)
-		goto out_free_fork;
+		goto out_free_namespaces;
 
 	while ((dirent = readdir(proc)) != NULL) {
 		char *end;
@@ -620,13 +717,16 @@ int perf_event__synthesize_threads(struct perf_tool *tool,
  		 * We may race with exiting thread, so don't stop just because
  		 * one thread couldn't be synthesized.
  		 */
-		__event__synthesize_thread(comm_event, mmap_event, fork_event, pid,
-					   1, process, tool, machine, mmap_data,
+		__event__synthesize_thread(comm_event, mmap_event, fork_event,
+					   namespaces_event, pid, 1, process,
+					   tool, machine, mmap_data,
 					   proc_map_timeout);
 	}
 
 	err = 0;
 	closedir(proc);
+out_free_namespaces:
+	free(namespaces_event);
 out_free_fork:
 	free(fork_event);
 out_free_mmap:
@@ -1008,6 +1108,33 @@ size_t perf_event__fprintf_comm(union perf_event *event, FILE *fp)
 	return fprintf(fp, "%s: %s:%d/%d\n", s, event->comm.comm, event->comm.pid, event->comm.tid);
 }
 
+size_t perf_event__fprintf_namespaces(union perf_event *event, FILE *fp)
+{
+	size_t ret = 0;
+	struct perf_ns_link_info *ns_link_info;
+	u32 nr_namespaces, idx;
+
+	ns_link_info = event->namespaces.link_info;
+	nr_namespaces = event->namespaces.nr_namespaces;
+
+	ret += fprintf(fp, " %d/%d - nr_namespaces: %u\n\t\t[",
+		       event->namespaces.pid,
+		       event->namespaces.tid,
+		       nr_namespaces);
+
+	for (idx = 0; idx < nr_namespaces; idx++) {
+		if (idx && (idx % 4 == 0))
+			ret += fprintf(fp, "\n\t\t ");
+
+		ret  += fprintf(fp, "%u/%s: %" PRIu64 "/%#" PRIx64 "%s", idx,
+				perf_ns__name(idx), (u64)ns_link_info[idx].dev,
+				(u64)ns_link_info[idx].ino,
+				((idx + 1) != nr_namespaces) ? ", " : "]\n");
+	}
+
+	return ret;
+}
+
 int perf_event__process_comm(struct perf_tool *tool __maybe_unused,
 			     union perf_event *event,
 			     struct perf_sample *sample,
@@ -1016,6 +1143,14 @@ int perf_event__process_comm(struct perf_tool *tool __maybe_unused,
 	return machine__process_comm_event(machine, event, sample);
 }
 
+int perf_event__process_namespaces(struct perf_tool *tool __maybe_unused,
+				   union perf_event *event,
+				   struct perf_sample *sample,
+				   struct machine *machine)
+{
+	return machine__process_namespaces_event(machine, event, sample);
+}
+
 int perf_event__process_lost(struct perf_tool *tool __maybe_unused,
 			     union perf_event *event,
 			     struct perf_sample *sample,
@@ -1153,11 +1288,12 @@ int perf_event__process_exit(struct perf_tool *tool __maybe_unused,
 
 size_t perf_event__fprintf_aux(union perf_event *event, FILE *fp)
 {
-	return fprintf(fp, " offset: %#"PRIx64" size: %#"PRIx64" flags: %#"PRIx64" [%s%s]\n",
+	return fprintf(fp, " offset: %#"PRIx64" size: %#"PRIx64" flags: %#"PRIx64" [%s%s%s]\n",
 		       event->aux.aux_offset, event->aux.aux_size,
 		       event->aux.flags,
 		       event->aux.flags & PERF_AUX_FLAG_TRUNCATED ? "T" : "",
-		       event->aux.flags & PERF_AUX_FLAG_OVERWRITE ? "O" : "");
+		       event->aux.flags & PERF_AUX_FLAG_OVERWRITE ? "O" : "",
+		       event->aux.flags & PERF_AUX_FLAG_PARTIAL   ? "P" : "");
 }
 
 size_t perf_event__fprintf_itrace_start(union perf_event *event, FILE *fp)
@@ -1196,6 +1332,9 @@ size_t perf_event__fprintf(union perf_event *event, FILE *fp)
 	case PERF_RECORD_MMAP:
 		ret += perf_event__fprintf_mmap(event, fp);
 		break;
+	case PERF_RECORD_NAMESPACES:
+		ret += perf_event__fprintf_namespaces(event, fp);
+		break;
 	case PERF_RECORD_MMAP2:
 		ret += perf_event__fprintf_mmap2(event, fp);
 		break;
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index c735c53a26f8..eb7a7b200737 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -39,6 +39,13 @@ struct comm_event {
 	char comm[16];
 };
 
+struct namespaces_event {
+	struct perf_event_header header;
+	u32 pid, tid;
+	u64 nr_namespaces;
+	struct perf_ns_link_info link_info[];
+};
+
 struct fork_event {
 	struct perf_event_header header;
 	u32 pid, ppid;
@@ -269,6 +276,7 @@ struct events_stats {
 	u64 total_lost;
 	u64 total_lost_samples;
 	u64 total_aux_lost;
+	u64 total_aux_partial;
 	u64 total_invalid_chains;
 	u32 nr_events[PERF_RECORD_HEADER_MAX];
 	u32 nr_non_filtered_samples;
@@ -485,6 +493,7 @@ union perf_event {
 	struct mmap_event		mmap;
 	struct mmap2_event		mmap2;
 	struct comm_event		comm;
+	struct namespaces_event		namespaces;
 	struct fork_event		fork;
 	struct lost_event		lost;
 	struct lost_samples_event	lost_samples;
@@ -587,6 +596,10 @@ int perf_event__process_switch(struct perf_tool *tool,
 			       union perf_event *event,
 			       struct perf_sample *sample,
 			       struct machine *machine);
+int perf_event__process_namespaces(struct perf_tool *tool,
+				   union perf_event *event,
+				   struct perf_sample *sample,
+				   struct machine *machine);
 int perf_event__process_mmap(struct perf_tool *tool,
 			     union perf_event *event,
 			     struct perf_sample *sample,
@@ -636,6 +649,12 @@ pid_t perf_event__synthesize_comm(struct perf_tool *tool,
 				  perf_event__handler_t process,
 				  struct machine *machine);
 
+int perf_event__synthesize_namespaces(struct perf_tool *tool,
+				      union perf_event *event,
+				      pid_t pid, pid_t tgid,
+				      perf_event__handler_t process,
+				      struct machine *machine);
+
 int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 				       union perf_event *event,
 				       pid_t pid, pid_t tgid,
@@ -653,6 +672,7 @@ size_t perf_event__fprintf_itrace_start(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_switch(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_thread_map(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_cpu_map(union perf_event *event, FILE *fp);
+size_t perf_event__fprintf_namespaces(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf(union perf_event *event, FILE *fp);
 
 u64 kallsyms__get_function_start(const char *kallsyms_filename,
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index b601f2814a30..50420cd35446 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -777,7 +777,7 @@ union perf_event *perf_mmap__read_forward(struct perf_mmap *md, bool check_messu
 	/*
 	 * Check if event was unmapped due to a POLLHUP/POLLERR.
 	 */
-	if (!atomic_read(&md->refcnt))
+	if (!refcount_read(&md->refcnt))
 		return NULL;
 
 	head = perf_mmap__read_head(md);
@@ -794,7 +794,7 @@ perf_mmap__read_backward(struct perf_mmap *md)
 	/*
 	 * Check if event was unmapped due to a POLLHUP/POLLERR.
 	 */
-	if (!atomic_read(&md->refcnt))
+	if (!refcount_read(&md->refcnt))
 		return NULL;
 
 	head = perf_mmap__read_head(md);
@@ -856,7 +856,7 @@ void perf_mmap__read_catchup(struct perf_mmap *md)
 {
 	u64 head;
 
-	if (!atomic_read(&md->refcnt))
+	if (!refcount_read(&md->refcnt))
 		return;
 
 	head = perf_mmap__read_head(md);
@@ -875,14 +875,14 @@ static bool perf_mmap__empty(struct perf_mmap *md)
 
 static void perf_mmap__get(struct perf_mmap *map)
 {
-	atomic_inc(&map->refcnt);
+	refcount_inc(&map->refcnt);
 }
 
 static void perf_mmap__put(struct perf_mmap *md)
 {
-	BUG_ON(md->base && atomic_read(&md->refcnt) == 0);
+	BUG_ON(md->base && refcount_read(&md->refcnt) == 0);
 
-	if (atomic_dec_and_test(&md->refcnt))
+	if (refcount_dec_and_test(&md->refcnt))
 		perf_mmap__munmap(md);
 }
 
@@ -894,7 +894,7 @@ void perf_mmap__consume(struct perf_mmap *md, bool overwrite)
 		perf_mmap__write_tail(md, old);
 	}
 
-	if (atomic_read(&md->refcnt) == 1 && perf_mmap__empty(md))
+	if (refcount_read(&md->refcnt) == 1 && perf_mmap__empty(md))
 		perf_mmap__put(md);
 }
 
@@ -937,7 +937,7 @@ static void perf_mmap__munmap(struct perf_mmap *map)
 		munmap(map->base, perf_mmap__mmap_len(map));
 		map->base = NULL;
 		map->fd = -1;
-		atomic_set(&map->refcnt, 0);
+		refcount_set(&map->refcnt, 0);
 	}
 	auxtrace_mmap__munmap(&map->auxtrace_mmap);
 }
@@ -974,8 +974,19 @@ static struct perf_mmap *perf_evlist__alloc_mmap(struct perf_evlist *evlist)
 	if (!map)
 		return NULL;
 
-	for (i = 0; i < evlist->nr_mmaps; i++)
+	for (i = 0; i < evlist->nr_mmaps; i++) {
 		map[i].fd = -1;
+		/*
+		 * When the perf_mmap() call is made we grab one refcount, plus
+		 * one extra to let perf_evlist__mmap_consume() get the last
+		 * events after all real references (perf_mmap__get()) are
+		 * dropped.
+		 *
+		 * Each PERF_EVENT_IOC_SET_OUTPUT points to this mmap and
+		 * thus does perf_mmap__get() on it.
+		 */
+		refcount_set(&map[i].refcnt, 0);
+	}
 	return map;
 }
 
@@ -1001,7 +1012,7 @@ static int perf_mmap__mmap(struct perf_mmap *map,
 	 * evlist layer can't just drop it when filtering events in
 	 * perf_evlist__filter_pollfd().
 	 */
-	atomic_set(&map->refcnt, 2);
+	refcount_set(&map->refcnt, 2);
 	map->prev = 0;
 	map->mask = mp->mask;
 	map->base = mmap(NULL, perf_mmap__mmap_len(map), mp->prot,
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 389b9ccdf8c7..39942995f537 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -1,7 +1,7 @@
 #ifndef __PERF_EVLIST_H
 #define __PERF_EVLIST_H 1
 
-#include <linux/atomic.h>
+#include <linux/refcount.h>
 #include <linux/list.h>
 #include <api/fd/array.h>
 #include <stdio.h>
@@ -29,7 +29,7 @@ struct perf_mmap {
 	void		 *base;
 	int		 mask;
 	int		 fd;
-	atomic_t	 refcnt;
+	refcount_t	 refcnt;
 	u64		 prev;
 	struct auxtrace_mmap auxtrace_mmap;
 	char		 event_copy[PERF_SAMPLE_MAX_SIZE] __attribute__((aligned(8)));
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index ac59710b79e0..9dc7e2d6e48a 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -236,6 +236,10 @@ void perf_evsel__init(struct perf_evsel *evsel,
 	evsel->sample_size = __perf_evsel__sample_size(attr->sample_type);
 	perf_evsel__calc_id_pos(evsel);
 	evsel->cmdline_group_boundary = false;
+	evsel->metric_expr   = NULL;
+	evsel->metric_name   = NULL;
+	evsel->metric_events = NULL;
+	evsel->collect_stat  = false;
 }
 
 struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx)
@@ -932,6 +936,9 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts,
 	attr->mmap2 = track && !perf_missing_features.mmap2;
 	attr->comm  = track;
 
+	if (opts->record_namespaces)
+		attr->namespaces  = track;
+
 	if (opts->record_switch_events)
 		attr->context_switch = track;
 
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 06ef6f29efa1..d101695c482c 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -131,6 +131,11 @@ struct perf_evsel {
 	bool			cmdline_group_boundary;
 	struct list_head	config_terms;
 	int			bpf_fd;
+	bool			merged_stat;
+	const char *		metric_expr;
+	const char *		metric_name;
+	struct perf_evsel	**metric_events;
+	bool			collect_stat;
 };
 
 union u64_swap {
diff --git a/tools/perf/util/expr.h b/tools/perf/util/expr.h
new file mode 100644
index 000000000000..9c2760a1a96e
--- /dev/null
+++ b/tools/perf/util/expr.h
@@ -0,0 +1,25 @@
+#ifndef PARSE_CTX_H
+#define PARSE_CTX_H 1
+
+#define EXPR_MAX_OTHER 8
+#define MAX_PARSE_ID EXPR_MAX_OTHER
+
+struct parse_id {
+	const char *name;
+	double val;
+};
+
+struct parse_ctx {
+	int num_ids;
+	struct parse_id ids[MAX_PARSE_ID];
+};
+
+void expr__ctx_init(struct parse_ctx *ctx);
+void expr__add_id(struct parse_ctx *ctx, const char *id, double val);
+#ifndef IN_EXPR_Y
+int expr__parse(double *final_val, struct parse_ctx *ctx, const char **pp);
+#endif
+int expr__find_other(const char *p, const char *one, const char ***other,
+		int *num_other);
+
+#endif
diff --git a/tools/perf/util/expr.y b/tools/perf/util/expr.y
new file mode 100644
index 000000000000..954556bea36e
--- /dev/null
+++ b/tools/perf/util/expr.y
@@ -0,0 +1,173 @@
+/* Simple expression parser */
+%{
+#include "util.h"
+#include "util/debug.h"
+#define IN_EXPR_Y 1
+#include "expr.h"
+#include <string.h>
+
+#define MAXIDLEN 256
+%}
+
+%pure-parser
+%parse-param { double *final_val }
+%parse-param { struct parse_ctx *ctx }
+%parse-param { const char **pp }
+%lex-param { const char **pp }
+
+%union {
+	double num;
+	char id[MAXIDLEN+1];
+}
+
+%token <num> NUMBER
+%token <id> ID
+%left '|'
+%left '^'
+%left '&'
+%left '-' '+'
+%left '*' '/' '%'
+%left NEG NOT
+%type <num> expr
+
+%{
+static int expr__lex(YYSTYPE *res, const char **pp);
+
+static void expr__error(double *final_val __maybe_unused,
+		       struct parse_ctx *ctx __maybe_unused,
+		       const char **pp __maybe_unused,
+		       const char *s)
+{
+	pr_debug("%s\n", s);
+}
+
+static int lookup_id(struct parse_ctx *ctx, char *id, double *val)
+{
+	int i;
+
+	for (i = 0; i < ctx->num_ids; i++) {
+		if (!strcasecmp(ctx->ids[i].name, id)) {
+			*val = ctx->ids[i].val;
+			return 0;
+		}
+	}
+	return -1;
+}
+
+%}
+%%
+
+all_expr: expr			{ *final_val = $1; }
+	;
+
+expr:	  NUMBER
+	| ID			{ if (lookup_id(ctx, $1, &$$) < 0) {
+					pr_debug("%s not found", $1);
+					YYABORT;
+				  }
+				}
+	| expr '+' expr		{ $$ = $1 + $3; }
+	| expr '-' expr		{ $$ = $1 - $3; }
+	| expr '*' expr		{ $$ = $1 * $3; }
+	| expr '/' expr		{ if ($3 == 0) YYABORT; $$ = $1 / $3; }
+	| expr '%' expr		{ if ((long)$3 == 0) YYABORT; $$ = (long)$1 % (long)$3; }
+	| '-' expr %prec NEG	{ $$ = -$2; }
+	| '(' expr ')'		{ $$ = $2; }
+	;
+
+%%
+
+static int expr__symbol(YYSTYPE *res, const char *p, const char **pp)
+{
+	char *dst = res->id;
+	const char *s = p;
+
+	while (isalnum(*p) || *p == '_' || *p == '.') {
+		if (p - s >= MAXIDLEN)
+			return -1;
+		*dst++ = *p++;
+	}
+	*dst = 0;
+	*pp = p;
+	return ID;
+}
+
+static int expr__lex(YYSTYPE *res, const char **pp)
+{
+	int tok;
+	const char *s;
+	const char *p = *pp;
+
+	while (isspace(*p))
+		p++;
+	s = p;
+	switch (*p++) {
+	case 'a' ... 'z':
+	case 'A' ... 'Z':
+		return expr__symbol(res, p - 1, pp);
+	case '0' ... '9': case '.':
+		res->num = strtod(s, (char **)&p);
+		tok = NUMBER;
+		break;
+	default:
+		tok = *s;
+		break;
+	}
+	*pp = p;
+	return tok;
+}
+
+/* Caller must make sure id is allocated */
+void expr__add_id(struct parse_ctx *ctx, const char *name, double val)
+{
+	int idx;
+	assert(ctx->num_ids < MAX_PARSE_ID);
+	idx = ctx->num_ids++;
+	ctx->ids[idx].name = name;
+	ctx->ids[idx].val = val;
+}
+
+void expr__ctx_init(struct parse_ctx *ctx)
+{
+	ctx->num_ids = 0;
+}
+
+int expr__find_other(const char *p, const char *one, const char ***other,
+		     int *num_otherp)
+{
+	const char *orig = p;
+	int err = -1;
+	int num_other;
+
+	*other = malloc((EXPR_MAX_OTHER + 1) * sizeof(char *));
+	if (!*other)
+		return -1;
+
+	num_other = 0;
+	for (;;) {
+		YYSTYPE val;
+		int tok = expr__lex(&val, &p);
+		if (tok == 0) {
+			err = 0;
+			break;
+		}
+		if (tok == ID && strcasecmp(one, val.id)) {
+			if (num_other >= EXPR_MAX_OTHER - 1) {
+				pr_debug("Too many extra events in %s\n", orig);
+				break;
+			}
+			(*other)[num_other] = strdup(val.id);
+			if (!(*other)[num_other])
+				return -1;
+			num_other++;
+		}
+	}
+	(*other)[num_other] = NULL;
+	*num_otherp = num_other;
+	if (err) {
+		*num_otherp = 0;
+		free(*other);
+		*other = NULL;
+	}
+	return err;
+}
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 05714d548584..ef09f26e67da 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -370,15 +370,11 @@ static int write_cmdline(int fd, struct perf_header *h __maybe_unused,
 			 struct perf_evlist *evlist __maybe_unused)
 {
 	char buf[MAXPATHLEN];
-	char proc[32];
 	u32 n;
 	int i, ret;
 
-	/*
-	 * actual atual path to perf binary
-	 */
-	sprintf(proc, "/proc/%d/exe", getpid());
-	ret = readlink(proc, buf, sizeof(buf));
+	/* actual path to perf binary */
+	ret = readlink("/proc/self/exe", buf, sizeof(buf) - 1);
 	if (ret <= 0)
 		return -1;
 
diff --git a/tools/perf/util/help-unknown-cmd.c b/tools/perf/util/help-unknown-cmd.c
index 2821f8d77e52..34201440ac03 100644
--- a/tools/perf/util/help-unknown-cmd.c
+++ b/tools/perf/util/help-unknown-cmd.c
@@ -6,16 +6,12 @@
 #include "levenshtein.h"
 
 static int autocorrect;
-static struct cmdnames aliases;
 
 static int perf_unknown_cmd_config(const char *var, const char *value,
 				   void *cb __maybe_unused)
 {
 	if (!strcmp(var, "help.autocorrect"))
 		autocorrect = perf_config_int(var,value);
-	/* Also use aliases for command lookup */
-	if (!prefixcmp(var, "alias."))
-		add_cmdname(&aliases, var + 6, strlen(var + 6));
 
 	return 0;
 }
@@ -59,14 +55,12 @@ const char *help_unknown_cmd(const char *cmd)
 
 	memset(&main_cmds, 0, sizeof(main_cmds));
 	memset(&other_cmds, 0, sizeof(main_cmds));
-	memset(&aliases, 0, sizeof(aliases));
 
 	perf_config(perf_unknown_cmd_config, NULL);
 
 	load_command_list("perf-", &main_cmds, &other_cmds);
 
-	if (add_cmd_list(&main_cmds, &aliases) < 0 ||
-	    add_cmd_list(&main_cmds, &other_cmds) < 0) {
+	if (add_cmd_list(&main_cmds, &other_cmds) < 0) {
 		fprintf(stderr, "ERROR: Failed to allocate command list for unknown command.\n");
 		goto end;
 	}
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index eaf72a938fb4..61bf304206fd 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -3,6 +3,7 @@
 #include "hist.h"
 #include "map.h"
 #include "session.h"
+#include "namespaces.h"
 #include "sort.h"
 #include "evlist.h"
 #include "evsel.h"
@@ -169,6 +170,7 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
 		hists__set_unres_dso_col_len(hists, HISTC_MEM_DADDR_DSO);
 	}
 
+	hists__new_col_len(hists, HISTC_CGROUP_ID, 20);
 	hists__new_col_len(hists, HISTC_CPU, 3);
 	hists__new_col_len(hists, HISTC_SOCKET, 6);
 	hists__new_col_len(hists, HISTC_MEM_LOCKED, 6);
@@ -574,9 +576,14 @@ __hists__add_entry(struct hists *hists,
 		   bool sample_self,
 		   struct hist_entry_ops *ops)
 {
+	struct namespaces *ns = thread__namespaces(al->thread);
 	struct hist_entry entry = {
 		.thread	= al->thread,
 		.comm = thread__comm(al->thread),
+		.cgroup_id = {
+			.dev = ns ? ns->link_info[CGROUP_NS_INDEX].dev : 0,
+			.ino = ns ? ns->link_info[CGROUP_NS_INDEX].ino : 0,
+		},
 		.ms = {
 			.map	= al->map,
 			.sym	= al->sym,
@@ -1129,6 +1136,11 @@ void hist_entry__delete(struct hist_entry *he)
 		zfree(&he->mem_info);
 	}
 
+	if (he->inline_node) {
+		inline_node__delete(he->inline_node);
+		he->inline_node = NULL;
+	}
+
 	zfree(&he->stat_acc);
 	free_srcline(he->srcline);
 	if (he->srcfile && he->srcfile[0])
@@ -2447,7 +2459,7 @@ int parse_filter_percentage(const struct option *opt __maybe_unused,
 	else if (!strcmp(arg, "absolute"))
 		symbol_conf.filter_relative = false;
 	else {
-		pr_debug("Invalud percentage: %s\n", arg);
+		pr_debug("Invalid percentage: %s\n", arg);
 		return -1;
 	}
 
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 28c216e3d5b7..ee3670a388df 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -30,6 +30,7 @@ enum hist_column {
 	HISTC_DSO,
 	HISTC_THREAD,
 	HISTC_COMM,
+	HISTC_CGROUP_ID,
 	HISTC_PARENT,
 	HISTC_CPU,
 	HISTC_SOCKET,
@@ -57,6 +58,7 @@ enum hist_column {
 	HISTC_SRCLINE_FROM,
 	HISTC_SRCLINE_TO,
 	HISTC_TRACE,
+	HISTC_SYM_SIZE,
 	HISTC_NR_COLS, /* Last entry */
 };
 
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c
index 4f3c758d875d..54818828023b 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c
@@ -26,6 +26,7 @@
 #include "insn.c"
 
 #include "intel-pt-insn-decoder.h"
+#include "dump-insn.h"
 
 #if INTEL_PT_INSN_BUF_SZ < MAX_INSN_SIZE || INTEL_PT_INSN_BUF_SZ > MAX_INSN
 #error Instruction buffer size too small
@@ -39,6 +40,8 @@ static void intel_pt_insn_decoder(struct insn *insn,
 	enum intel_pt_insn_branch branch = INTEL_PT_BR_NO_BRANCH;
 	int ext;
 
+	intel_pt_insn->rel = 0;
+
 	if (insn_is_avx(insn)) {
 		intel_pt_insn->op = INTEL_PT_OP_OTHER;
 		intel_pt_insn->branch = INTEL_PT_BR_NO_BRANCH;
@@ -177,6 +180,29 @@ int intel_pt_get_insn(const unsigned char *buf, size_t len, int x86_64,
 	return 0;
 }
 
+const char *dump_insn(struct perf_insn *x, uint64_t ip __maybe_unused,
+		      u8 *inbuf, int inlen, int *lenp)
+{
+	struct insn insn;
+	int n, i;
+	int left;
+
+	insn_init(&insn, inbuf, inlen, x->is64bit);
+	insn_get_length(&insn);
+	if (!insn_complete(&insn) || insn.length > inlen)
+		return "<bad>";
+	if (lenp)
+		*lenp = insn.length;
+	left = sizeof(x->out);
+	n = snprintf(x->out, left, "insn: ");
+	left -= n;
+	for (i = 0; i < insn.length; i++) {
+		n += snprintf(x->out + n, left, "%02x ", inbuf[i]);
+		left -= n;
+	}
+	return x->out;
+}
+
 const char *branch_name[] = {
 	[INTEL_PT_OP_OTHER]	= "Other",
 	[INTEL_PT_OP_CALL]	= "Call",
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 71c9720d4973..dfc600446586 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -13,6 +13,7 @@
 #include <symbol/kallsyms.h>
 #include "unwind.h"
 #include "linux/hash.h"
+#include "asm/bug.h"
 
 static void __machine__remove_thread(struct machine *machine, struct thread *th, bool lock);
 
@@ -501,6 +502,37 @@ int machine__process_comm_event(struct machine *machine, union perf_event *event
 	return err;
 }
 
+int machine__process_namespaces_event(struct machine *machine __maybe_unused,
+				      union perf_event *event,
+				      struct perf_sample *sample __maybe_unused)
+{
+	struct thread *thread = machine__findnew_thread(machine,
+							event->namespaces.pid,
+							event->namespaces.tid);
+	int err = 0;
+
+	WARN_ONCE(event->namespaces.nr_namespaces > NR_NAMESPACES,
+		  "\nWARNING: kernel seems to support more namespaces than perf"
+		  " tool.\nTry updating the perf tool..\n\n");
+
+	WARN_ONCE(event->namespaces.nr_namespaces < NR_NAMESPACES,
+		  "\nWARNING: perf tool seems to support more namespaces than"
+		  " the kernel.\nTry updating the kernel..\n\n");
+
+	if (dump_trace)
+		perf_event__fprintf_namespaces(event, stdout);
+
+	if (thread == NULL ||
+	    thread__set_namespaces(thread, sample->time, &event->namespaces)) {
+		dump_printf("problem processing PERF_RECORD_NAMESPACES, skipping event.\n");
+		err = -1;
+	}
+
+	thread__put(thread);
+
+	return err;
+}
+
 int machine__process_lost_event(struct machine *machine __maybe_unused,
 				union perf_event *event, struct perf_sample *sample __maybe_unused)
 {
@@ -1439,7 +1471,7 @@ static void __machine__remove_thread(struct machine *machine, struct thread *th,
 	if (machine->last_match == th)
 		machine->last_match = NULL;
 
-	BUG_ON(atomic_read(&th->refcnt) == 0);
+	BUG_ON(refcount_read(&th->refcnt) == 0);
 	if (lock)
 		pthread_rwlock_wrlock(&machine->threads_lock);
 	rb_erase_init(&th->rb_node, &machine->threads);
@@ -1538,6 +1570,8 @@ int machine__process_event(struct machine *machine, union perf_event *event,
 		ret = machine__process_comm_event(machine, event, sample); break;
 	case PERF_RECORD_MMAP:
 		ret = machine__process_mmap_event(machine, event, sample); break;
+	case PERF_RECORD_NAMESPACES:
+		ret = machine__process_namespaces_event(machine, event, sample); break;
 	case PERF_RECORD_MMAP2:
 		ret = machine__process_mmap2_event(machine, event, sample); break;
 	case PERF_RECORD_FORK:
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index a28305029711..3cdb1340f917 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -97,6 +97,9 @@ int machine__process_itrace_start_event(struct machine *machine,
 					union perf_event *event);
 int machine__process_switch_event(struct machine *machine,
 				  union perf_event *event);
+int machine__process_namespaces_event(struct machine *machine,
+				      union perf_event *event,
+				      struct perf_sample *sample);
 int machine__process_mmap_event(struct machine *machine, union perf_event *event,
 				struct perf_sample *sample);
 int machine__process_mmap2_event(struct machine *machine, union perf_event *event,
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 0a943e7b1ea7..c1870ac365a3 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -141,7 +141,7 @@ void map__init(struct map *map, enum map_type type,
 	RB_CLEAR_NODE(&map->rb_node);
 	map->groups   = NULL;
 	map->erange_warned = false;
-	atomic_set(&map->refcnt, 1);
+	refcount_set(&map->refcnt, 1);
 }
 
 struct map *map__new(struct machine *machine, u64 start, u64 len,
@@ -255,7 +255,7 @@ void map__delete(struct map *map)
 
 void map__put(struct map *map)
 {
-	if (map && atomic_dec_and_test(&map->refcnt))
+	if (map && refcount_dec_and_test(&map->refcnt))
 		map__delete(map);
 }
 
@@ -354,7 +354,7 @@ struct map *map__clone(struct map *from)
 	struct map *map = memdup(from, sizeof(*map));
 
 	if (map != NULL) {
-		atomic_set(&map->refcnt, 1);
+		refcount_set(&map->refcnt, 1);
 		RB_CLEAR_NODE(&map->rb_node);
 		dso__get(map->dso);
 		map->groups = NULL;
@@ -405,7 +405,8 @@ int map__fprintf_srcline(struct map *map, u64 addr, const char *prefix,
 
 	if (map && map->dso) {
 		srcline = get_srcline(map->dso,
-				      map__rip_2objdump(map, addr), NULL, true);
+				      map__rip_2objdump(map, addr), NULL,
+				      true, true);
 		if (srcline != SRCLINE_UNKNOWN)
 			ret = fprintf(fp, "%s%s", prefix, srcline);
 		free_srcline(srcline);
@@ -485,7 +486,7 @@ void map_groups__init(struct map_groups *mg, struct machine *machine)
 		maps__init(&mg->maps[i]);
 	}
 	mg->machine = machine;
-	atomic_set(&mg->refcnt, 1);
+	refcount_set(&mg->refcnt, 1);
 }
 
 static void __maps__purge(struct maps *maps)
@@ -547,7 +548,7 @@ void map_groups__delete(struct map_groups *mg)
 
 void map_groups__put(struct map_groups *mg)
 {
-	if (mg && atomic_dec_and_test(&mg->refcnt))
+	if (mg && refcount_dec_and_test(&mg->refcnt))
 		map_groups__delete(mg);
 }
 
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index abdacf800c98..c8a5a644c0a9 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -1,7 +1,7 @@
 #ifndef __PERF_MAP_H
 #define __PERF_MAP_H
 
-#include <linux/atomic.h>
+#include <linux/refcount.h>
 #include <linux/compiler.h>
 #include <linux/list.h>
 #include <linux/rbtree.h>
@@ -51,7 +51,7 @@ struct map {
 
 	struct dso		*dso;
 	struct map_groups	*groups;
-	atomic_t		refcnt;
+	refcount_t		refcnt;
 };
 
 struct kmap {
@@ -67,7 +67,7 @@ struct maps {
 struct map_groups {
 	struct maps	 maps[MAP__NR_TYPES];
 	struct machine	 *machine;
-	atomic_t	 refcnt;
+	refcount_t	 refcnt;
 };
 
 struct map_groups *map_groups__new(struct machine *machine);
@@ -77,7 +77,7 @@ bool map_groups__empty(struct map_groups *mg);
 static inline struct map_groups *map_groups__get(struct map_groups *mg)
 {
 	if (mg)
-		atomic_inc(&mg->refcnt);
+		refcount_inc(&mg->refcnt);
 	return mg;
 }
 
@@ -150,7 +150,7 @@ struct map *map__clone(struct map *map);
 static inline struct map *map__get(struct map *map)
 {
 	if (map)
-		atomic_inc(&map->refcnt);
+		refcount_inc(&map->refcnt);
 	return map;
 }
 
diff --git a/tools/perf/util/namespaces.c b/tools/perf/util/namespaces.c
new file mode 100644
index 000000000000..2de8da64d90c
--- /dev/null
+++ b/tools/perf/util/namespaces.c
@@ -0,0 +1,36 @@
+/*
+ * 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.
+ *
+ * Copyright (C) 2017 Hari Bathini, IBM Corporation
+ */
+
+#include "namespaces.h"
+#include "util.h"
+#include "event.h"
+#include <stdlib.h>
+#include <stdio.h>
+
+struct namespaces *namespaces__new(struct namespaces_event *event)
+{
+	struct namespaces *namespaces;
+	u64 link_info_size = ((event ? event->nr_namespaces : NR_NAMESPACES) *
+			      sizeof(struct perf_ns_link_info));
+
+	namespaces = zalloc(sizeof(struct namespaces) + link_info_size);
+	if (!namespaces)
+		return NULL;
+
+	namespaces->end_time = -1;
+
+	if (event)
+		memcpy(namespaces->link_info, event->link_info, link_info_size);
+
+	return namespaces;
+}
+
+void namespaces__free(struct namespaces *namespaces)
+{
+	free(namespaces);
+}
diff --git a/tools/perf/util/namespaces.h b/tools/perf/util/namespaces.h
new file mode 100644
index 000000000000..468f1e9a1484
--- /dev/null
+++ b/tools/perf/util/namespaces.h
@@ -0,0 +1,26 @@
+/*
+ * 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.
+ *
+ * Copyright (C) 2017 Hari Bathini, IBM Corporation
+ */
+
+#ifndef __PERF_NAMESPACES_H
+#define __PERF_NAMESPACES_H
+
+#include "../perf.h"
+#include <linux/list.h>
+
+struct namespaces_event;
+
+struct namespaces {
+	struct list_head list;
+	u64 end_time;
+	struct perf_ns_link_info link_info[];
+};
+
+struct namespaces *namespaces__new(struct namespaces_event *event);
+void namespaces__free(struct namespaces *namespaces);
+
+#endif  /* __PERF_NAMESPACES_H */
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 67a8aebc67ab..6b498aea9fde 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -316,8 +316,9 @@ __add_event(struct list_head *list, int *idx,
 		return NULL;
 
 	(*idx)++;
-	evsel->cpus     = cpu_map__get(cpus);
-	evsel->own_cpus = cpu_map__get(cpus);
+	evsel->cpus        = cpu_map__get(cpus);
+	evsel->own_cpus    = cpu_map__get(cpus);
+	evsel->system_wide = !!cpus;
 
 	if (name)
 		evsel->name = strdup(name);
@@ -1254,11 +1255,59 @@ int parse_events_add_pmu(struct parse_events_evlist *data,
 		evsel->scale = info.scale;
 		evsel->per_pkg = info.per_pkg;
 		evsel->snapshot = info.snapshot;
+		evsel->metric_expr = info.metric_expr;
+		evsel->metric_name = info.metric_name;
 	}
 
 	return evsel ? 0 : -ENOMEM;
 }
 
+int parse_events_multi_pmu_add(struct parse_events_evlist *data,
+			       char *str, struct list_head **listp)
+{
+	struct list_head *head;
+	struct parse_events_term *term;
+	struct list_head *list;
+	struct perf_pmu *pmu = NULL;
+	int ok = 0;
+
+	*listp = NULL;
+	/* Add it for all PMUs that support the alias */
+	list = malloc(sizeof(struct list_head));
+	if (!list)
+		return -1;
+	INIT_LIST_HEAD(list);
+	while ((pmu = perf_pmu__scan(pmu)) != NULL) {
+		struct perf_pmu_alias *alias;
+
+		list_for_each_entry(alias, &pmu->aliases, list) {
+			if (!strcasecmp(alias->name, str)) {
+				head = malloc(sizeof(struct list_head));
+				if (!head)
+					return -1;
+				INIT_LIST_HEAD(head);
+				if (parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
+							   str, 1, false, &str, NULL) < 0)
+					return -1;
+				list_add_tail(&term->list, head);
+
+				if (!parse_events_add_pmu(data, list,
+						  pmu->name, head)) {
+					pr_debug("%s -> %s/%s/\n", str,
+						 pmu->name, alias->str);
+					ok++;
+				}
+
+				parse_events_terms__delete(head);
+			}
+		}
+	}
+	if (!ok)
+		return -1;
+	*listp = list;
+	return 0;
+}
+
 int parse_events__modifier_group(struct list_head *list,
 				 char *event_mod)
 {
@@ -2276,7 +2325,7 @@ out_enomem:
  * Print the help text for the event symbols:
  */
 void print_events(const char *event_glob, bool name_only, bool quiet_flag,
-			bool long_desc)
+			bool long_desc, bool details_flag)
 {
 	print_symbol_events(event_glob, PERF_TYPE_HARDWARE,
 			    event_symbols_hw, PERF_COUNT_HW_MAX, name_only);
@@ -2286,7 +2335,8 @@ void print_events(const char *event_glob, bool name_only, bool quiet_flag,
 
 	print_hwcache_events(event_glob, name_only);
 
-	print_pmu_events(event_glob, name_only, quiet_flag, long_desc);
+	print_pmu_events(event_glob, name_only, quiet_flag, long_desc,
+			details_flag);
 
 	if (event_glob != NULL)
 		return;
@@ -2415,6 +2465,31 @@ int parse_events_term__clone(struct parse_events_term **new,
 	return new_term(new, &temp, term->val.str, term->val.num);
 }
 
+int parse_events_copy_term_list(struct list_head *old,
+				 struct list_head **new)
+{
+	struct parse_events_term *term, *n;
+	int ret;
+
+	if (!old) {
+		*new = NULL;
+		return 0;
+	}
+
+	*new = malloc(sizeof(struct list_head));
+	if (!*new)
+		return -ENOMEM;
+	INIT_LIST_HEAD(*new);
+
+	list_for_each_entry (term, old, list) {
+		ret = parse_events_term__clone(&n, term);
+		if (ret)
+			return ret;
+		list_add_tail(&n->list, *new);
+	}
+	return 0;
+}
+
 void parse_events_terms__purge(struct list_head *terms)
 {
 	struct parse_events_term *term, *h;
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index 1af6a267c21b..a235f4d6d5e5 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -8,6 +8,7 @@
 #include <stdbool.h>
 #include <linux/types.h>
 #include <linux/perf_event.h>
+#include <string.h>
 
 struct list_head;
 struct perf_evsel;
@@ -166,6 +167,14 @@ int parse_events_add_breakpoint(struct list_head *list, int *idx,
 int parse_events_add_pmu(struct parse_events_evlist *data,
 			 struct list_head *list, char *name,
 			 struct list_head *head_config);
+
+int parse_events_multi_pmu_add(struct parse_events_evlist *data,
+			       char *str,
+			       struct list_head **listp);
+
+int parse_events_copy_term_list(struct list_head *old,
+				 struct list_head **new);
+
 enum perf_pmu_event_symbol_type
 perf_pmu__parse_check(const char *name);
 void parse_events__set_leader(char *name, struct list_head *list);
@@ -175,7 +184,7 @@ void parse_events_evlist_error(struct parse_events_evlist *data,
 			       int idx, const char *str);
 
 void print_events(const char *event_glob, bool name_only, bool quiet,
-		  bool long_desc);
+		  bool long_desc, bool details_flag);
 
 struct event_symbol {
 	const char	*symbol;
@@ -196,4 +205,23 @@ int is_valid_tracepoint(const char *event_string);
 int valid_event_mount(const char *eventfs);
 char *parse_events_formats_error_string(char *additional_terms);
 
+#ifdef HAVE_LIBELF_SUPPORT
+/*
+ * If the probe point starts with '%',
+ * or starts with "sdt_" and has a ':' but no '=',
+ * then it should be a SDT/cached probe point.
+ */
+static inline bool is_sdt_event(char *str)
+{
+	return (str[0] == '%' ||
+		(!strncmp(str, "sdt_", 4) &&
+		 !!strchr(str, ':') && !strchr(str, '=')));
+}
+#else
+static inline bool is_sdt_event(char *str __maybe_unused)
+{
+	return false;
+}
+#endif /* HAVE_LIBELF_SUPPORT */
+
 #endif /* __PERF_PARSE_EVENTS_H */
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index 30f018ea1370..04fd8c9af9f9 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -226,68 +226,55 @@ event_pmu:
 PE_NAME opt_event_config
 {
 	struct parse_events_evlist *data = _data;
-	struct list_head *list;
+	struct list_head *list, *orig_terms, *terms;
+
+	if (parse_events_copy_term_list($2, &orig_terms))
+		YYABORT;
 
 	ALLOC_LIST(list);
-	ABORT_ON(parse_events_add_pmu(data, list, $1, $2));
+	if (parse_events_add_pmu(data, list, $1, $2)) {
+		struct perf_pmu *pmu = NULL;
+		int ok = 0;
+
+		while ((pmu = perf_pmu__scan(pmu)) != NULL) {
+			char *name = pmu->name;
+
+			if (!strncmp(name, "uncore_", 7) &&
+			    strncmp($1, "uncore_", 7))
+				name += 7;
+			if (!strncmp($1, name, strlen($1))) {
+				if (parse_events_copy_term_list(orig_terms, &terms))
+					YYABORT;
+				if (!parse_events_add_pmu(data, list, pmu->name, terms))
+					ok++;
+				parse_events_terms__delete(terms);
+			}
+		}
+		if (!ok)
+			YYABORT;
+	}
 	parse_events_terms__delete($2);
+	parse_events_terms__delete(orig_terms);
 	$$ = list;
 }
 |
 PE_KERNEL_PMU_EVENT sep_dc
 {
-	struct parse_events_evlist *data = _data;
-	struct list_head *head;
-	struct parse_events_term *term;
 	struct list_head *list;
-	struct perf_pmu *pmu = NULL;
-	int ok = 0;
-
-	/* Add it for all PMUs that support the alias */
-	ALLOC_LIST(list);
-	while ((pmu = perf_pmu__scan(pmu)) != NULL) {
-		struct perf_pmu_alias *alias;
-
-		list_for_each_entry(alias, &pmu->aliases, list) {
-			if (!strcasecmp(alias->name, $1)) {
-				ALLOC_LIST(head);
-				ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
-					$1, 1, false, &@1, NULL));
-				list_add_tail(&term->list, head);
-
-				if (!parse_events_add_pmu(data, list,
-						  pmu->name, head)) {
-					pr_debug("%s -> %s/%s/\n", $1,
-						 pmu->name, alias->str);
-					ok++;
-				}
 
-				parse_events_terms__delete(head);
-			}
-		}
-	}
-	if (!ok)
+	if (parse_events_multi_pmu_add(_data, $1, &list) < 0)
 		YYABORT;
 	$$ = list;
 }
 |
 PE_PMU_EVENT_PRE '-' PE_PMU_EVENT_SUF sep_dc
 {
-	struct parse_events_evlist *data = _data;
-	struct list_head *head;
-	struct parse_events_term *term;
 	struct list_head *list;
 	char pmu_name[128];
-	snprintf(&pmu_name, 128, "%s-%s", $1, $3);
 
-	ALLOC_LIST(head);
-	ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
-					&pmu_name, 1, false, &@1, NULL));
-	list_add_tail(&term->list, head);
-
-	ALLOC_LIST(list);
-	ABORT_ON(parse_events_add_pmu(data, list, "cpu", head));
-	parse_events_terms__delete(head);
+	snprintf(&pmu_name, 128, "%s-%s", $1, $3);
+	if (parse_events_multi_pmu_add(_data, pmu_name, &list) < 0)
+		YYABORT;
 	$$ = list;
 }
 
diff --git a/tools/perf/util/perf_regs.c b/tools/perf/util/perf_regs.c
index c4023f22f287..b2ae039eff85 100644
--- a/tools/perf/util/perf_regs.c
+++ b/tools/perf/util/perf_regs.c
@@ -6,6 +6,12 @@ const struct sample_reg __weak sample_reg_masks[] = {
 	SMPL_REG_END
 };
 
+int __weak arch_sdt_arg_parse_op(char *old_op __maybe_unused,
+				 char **new_op __maybe_unused)
+{
+	return SDT_ARG_SKIP;
+}
+
 #ifdef HAVE_PERF_REGS_SUPPORT
 int perf_reg_value(u64 *valp, struct regs_dump *regs, int id)
 {
diff --git a/tools/perf/util/perf_regs.h b/tools/perf/util/perf_regs.h
index 679d6e493962..32b37d19dcc3 100644
--- a/tools/perf/util/perf_regs.h
+++ b/tools/perf/util/perf_regs.h
@@ -15,6 +15,13 @@ struct sample_reg {
 
 extern const struct sample_reg sample_reg_masks[];
 
+enum {
+	SDT_ARG_VALID = 0,
+	SDT_ARG_SKIP,
+};
+
+int arch_sdt_arg_parse_op(char *old_op, char **new_op);
+
 #ifdef HAVE_PERF_REGS_SUPPORT
 #include <perf_regs.h>
 
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 12f84dd2ac5d..362051ea7f3d 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -231,7 +231,9 @@ static int perf_pmu__parse_snapshot(struct perf_pmu_alias *alias,
 static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name,
 				 char *desc, char *val,
 				 char *long_desc, char *topic,
-				 char *unit, char *perpkg)
+				 char *unit, char *perpkg,
+				 char *metric_expr,
+				 char *metric_name)
 {
 	struct perf_pmu_alias *alias;
 	int ret;
@@ -265,6 +267,8 @@ static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name,
 		perf_pmu__parse_snapshot(alias, dir, name);
 	}
 
+	alias->metric_expr = metric_expr ? strdup(metric_expr) : NULL;
+	alias->metric_name = metric_name ? strdup(metric_name): NULL;
 	alias->desc = desc ? strdup(desc) : NULL;
 	alias->long_desc = long_desc ? strdup(long_desc) :
 				desc ? strdup(desc) : NULL;
@@ -294,7 +298,7 @@ static int perf_pmu__new_alias(struct list_head *list, char *dir, char *name, FI
 	buf[ret] = 0;
 
 	return __perf_pmu__new_alias(list, dir, name, NULL, buf, NULL, NULL, NULL,
-				     NULL);
+				     NULL, NULL, NULL);
 }
 
 static inline bool pmu_alias_info_file(char *name)
@@ -564,7 +568,9 @@ static void pmu_add_cpu_aliases(struct list_head *head, const char *name)
 		__perf_pmu__new_alias(head, NULL, (char *)pe->name,
 				(char *)pe->desc, (char *)pe->event,
 				(char *)pe->long_desc, (char *)pe->topic,
-				(char *)pe->unit, (char *)pe->perpkg);
+				(char *)pe->unit, (char *)pe->perpkg,
+				(char *)pe->metric_expr,
+				(char *)pe->metric_name);
 	}
 
 out:
@@ -991,6 +997,8 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms,
 	info->unit     = NULL;
 	info->scale    = 0.0;
 	info->snapshot = false;
+	info->metric_expr = NULL;
+	info->metric_name = NULL;
 
 	list_for_each_entry_safe(term, h, head_terms, list) {
 		alias = pmu_find_alias(pmu, term);
@@ -1006,6 +1014,8 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms,
 
 		if (alias->per_pkg)
 			info->per_pkg = true;
+		info->metric_expr = alias->metric_expr;
+		info->metric_name = alias->metric_name;
 
 		list_del(&term->list);
 		free(term);
@@ -1100,6 +1110,8 @@ struct sevent {
 	char *topic;
 	char *str;
 	char *pmu;
+	char *metric_expr;
+	char *metric_name;
 };
 
 static int cmp_sevent(const void *a, const void *b)
@@ -1142,7 +1154,7 @@ static void wordwrap(char *s, int start, int max, int corr)
 }
 
 void print_pmu_events(const char *event_glob, bool name_only, bool quiet_flag,
-			bool long_desc)
+			bool long_desc, bool details_flag)
 {
 	struct perf_pmu *pmu;
 	struct perf_pmu_alias *alias;
@@ -1198,6 +1210,8 @@ void print_pmu_events(const char *event_glob, bool name_only, bool quiet_flag,
 			aliases[j].topic = alias->topic;
 			aliases[j].str = alias->str;
 			aliases[j].pmu = pmu->name;
+			aliases[j].metric_expr = alias->metric_expr;
+			aliases[j].metric_name = alias->metric_name;
 			j++;
 		}
 		if (pmu->selectable &&
@@ -1232,8 +1246,14 @@ void print_pmu_events(const char *event_glob, bool name_only, bool quiet_flag,
 			printf("%*s", 8, "[");
 			wordwrap(aliases[j].desc, 8, columns, 0);
 			printf("]\n");
-			if (verbose > 0)
-				printf("%*s%s/%s/\n", 8, "", aliases[j].pmu, aliases[j].str);
+			if (details_flag) {
+				printf("%*s%s/%s/ ", 8, "", aliases[j].pmu, aliases[j].str);
+				if (aliases[j].metric_name)
+					printf(" MetricName: %s", aliases[j].metric_name);
+				if (aliases[j].metric_expr)
+					printf(" MetricExpr: %s", aliases[j].metric_expr);
+				putchar('\n');
+			}
 		} else
 			printf("  %-50s [Kernel PMU event]\n", aliases[j].name);
 		printed++;
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index 00852ddc7741..ea7f450dc609 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -31,6 +31,8 @@ struct perf_pmu {
 
 struct perf_pmu_info {
 	const char *unit;
+	const char *metric_expr;
+	const char *metric_name;
 	double scale;
 	bool per_pkg;
 	bool snapshot;
@@ -50,6 +52,8 @@ struct perf_pmu_alias {
 	double scale;
 	bool per_pkg;
 	bool snapshot;
+	char *metric_expr;
+	char *metric_name;
 };
 
 struct perf_pmu *perf_pmu__find(const char *name);
@@ -76,7 +80,7 @@ int perf_pmu__format_parse(char *dir, struct list_head *head);
 struct perf_pmu *perf_pmu__scan(struct perf_pmu *pmu);
 
 void print_pmu_events(const char *event_glob, bool name_only, bool quiet,
-		      bool long_desc);
+		      bool long_desc, bool details_flag);
 bool pmu_have_event(const char *pname, const char *name);
 
 int perf_pmu__scan_file(struct perf_pmu *pmu, const char *name, const char *fmt,
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 28fb62c32678..e4b889444447 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -47,7 +47,6 @@
 #include "probe-file.h"
 #include "session.h"
 
-#define MAX_CMDLEN 256
 #define PERFPROBE_GROUP "probe"
 
 bool probe_event_dry_run;	/* Dry run flag */
@@ -757,7 +756,9 @@ post_process_kernel_probe_trace_events(struct probe_trace_event *tevs,
 	}
 
 	for (i = 0; i < ntevs; i++) {
-		if (!tevs[i].point.address || tevs[i].point.retprobe)
+		if (!tevs[i].point.address)
+			continue;
+		if (tevs[i].point.retprobe && !kretprobe_offset_is_supported())
 			continue;
 		/* If we found a wrong one, mark it by NULL symbol */
 		if (kprobe_warn_out_range(tevs[i].point.symbol,
@@ -1339,14 +1340,7 @@ static int parse_perf_probe_point(char *arg, struct perf_probe_event *pev)
 	if (!arg)
 		return -EINVAL;
 
-	/*
-	 * If the probe point starts with '%',
-	 * or starts with "sdt_" and has a ':' but no '=',
-	 * then it should be a SDT/cached probe point.
-	 */
-	if (arg[0] == '%' ||
-	    (!strncmp(arg, "sdt_", 4) &&
-	     !!strchr(arg, ':') && !strchr(arg, '='))) {
+	if (is_sdt_event(arg)) {
 		pev->sdt = true;
 		if (arg[0] == '%')
 			arg++;
@@ -1528,11 +1522,6 @@ static int parse_perf_probe_point(char *arg, struct perf_probe_event *pev)
 		return -EINVAL;
 	}
 
-	if (pp->retprobe && !pp->function) {
-		semantic_error("Return probe requires an entry function.\n");
-		return -EINVAL;
-	}
-
 	if ((pp->offset || pp->line || pp->lazy_line) && pp->retprobe) {
 		semantic_error("Offset/Line/Lazy pattern can't be used with "
 			       "return probe.\n");
@@ -2841,7 +2830,8 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev,
 	}
 
 	/* Note that the symbols in the kmodule are not relocated */
-	if (!pev->uprobes && !pp->retprobe && !pev->target) {
+	if (!pev->uprobes && !pev->target &&
+			(!pp->retprobe || kretprobe_offset_is_supported())) {
 		reloc_sym = kernel_get_ref_reloc_sym();
 		if (!reloc_sym) {
 			pr_warning("Relocated base symbol is not found!\n");
@@ -3057,7 +3047,7 @@ concat_probe_trace_events(struct probe_trace_event **tevs, int *ntevs,
 	struct probe_trace_event *new_tevs;
 	int ret = 0;
 
-	if (ntevs == 0) {
+	if (*ntevs == 0) {
 		*tevs = *tevs2;
 		*ntevs = ntevs2;
 		*tevs2 = NULL;
diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c
index 436b64731f65..88714dec8912 100644
--- a/tools/perf/util/probe-file.c
+++ b/tools/perf/util/probe-file.c
@@ -27,8 +27,10 @@
 #include "probe-event.h"
 #include "probe-file.h"
 #include "session.h"
+#include "perf_regs.h"
 
-#define MAX_CMDLEN 256
+/* 4096 - 2 ('\n' + '\0') */
+#define MAX_CMDLEN 4094
 
 static void print_open_warning(int err, bool uprobe)
 {
@@ -70,7 +72,7 @@ static void print_both_open_warning(int kerr, int uerr)
 	}
 }
 
-static int open_probe_events(const char *trace_file, bool readwrite)
+int open_trace_file(const char *trace_file, bool readwrite)
 {
 	char buf[PATH_MAX];
 	int ret;
@@ -92,12 +94,12 @@ static int open_probe_events(const char *trace_file, bool readwrite)
 
 static int open_kprobe_events(bool readwrite)
 {
-	return open_probe_events("kprobe_events", readwrite);
+	return open_trace_file("kprobe_events", readwrite);
 }
 
 static int open_uprobe_events(bool readwrite)
 {
-	return open_probe_events("uprobe_events", readwrite);
+	return open_trace_file("uprobe_events", readwrite);
 }
 
 int probe_file__open(int flag)
@@ -687,6 +689,110 @@ static unsigned long long sdt_note__get_addr(struct sdt_note *note)
 		 : (unsigned long long)note->addr.a64[0];
 }
 
+static const char * const type_to_suffix[] = {
+	":s64", "", "", "", ":s32", "", ":s16", ":s8",
+	"", ":u8", ":u16", "", ":u32", "", "", "", ":u64"
+};
+
+/*
+ * Isolate the string number and convert it into a decimal value;
+ * this will be an index to get suffix of the uprobe name (defining
+ * the type)
+ */
+static int sdt_arg_parse_size(char *n_ptr, const char **suffix)
+{
+	long type_idx;
+
+	type_idx = strtol(n_ptr, NULL, 10);
+	if (type_idx < -8 || type_idx > 8) {
+		pr_debug4("Failed to get a valid sdt type\n");
+		return -1;
+	}
+
+	*suffix = type_to_suffix[type_idx + 8];
+	return 0;
+}
+
+static int synthesize_sdt_probe_arg(struct strbuf *buf, int i, const char *arg)
+{
+	char *op, *desc = strdup(arg), *new_op = NULL;
+	const char *suffix = "";
+	int ret = -1;
+
+	if (desc == NULL) {
+		pr_debug4("Allocation error\n");
+		return ret;
+	}
+
+	/*
+	 * Argument is in N@OP format. N is size of the argument and OP is
+	 * the actual assembly operand. N can be omitted; in that case
+	 * argument is just OP(without @).
+	 */
+	op = strchr(desc, '@');
+	if (op) {
+		op[0] = '\0';
+		op++;
+
+		if (sdt_arg_parse_size(desc, &suffix))
+			goto error;
+	} else {
+		op = desc;
+	}
+
+	ret = arch_sdt_arg_parse_op(op, &new_op);
+
+	if (ret < 0)
+		goto error;
+
+	if (ret == SDT_ARG_VALID) {
+		ret = strbuf_addf(buf, " arg%d=%s%s", i + 1, new_op, suffix);
+		if (ret < 0)
+			goto error;
+	}
+
+	ret = 0;
+error:
+	free(desc);
+	free(new_op);
+	return ret;
+}
+
+static char *synthesize_sdt_probe_command(struct sdt_note *note,
+					const char *pathname,
+					const char *sdtgrp)
+{
+	struct strbuf buf;
+	char *ret = NULL, **args;
+	int i, args_count;
+
+	if (strbuf_init(&buf, 32) < 0)
+		return NULL;
+
+	if (strbuf_addf(&buf, "p:%s/%s %s:0x%llx",
+				sdtgrp, note->name, pathname,
+				sdt_note__get_addr(note)) < 0)
+		goto error;
+
+	if (!note->args)
+		goto out;
+
+	if (note->args) {
+		args = argv_split(note->args, &args_count);
+
+		for (i = 0; i < args_count; ++i) {
+			if (synthesize_sdt_probe_arg(&buf, i, args[i]) < 0)
+				goto error;
+		}
+	}
+
+out:
+	ret = strbuf_detach(&buf, NULL);
+error:
+	strbuf_release(&buf);
+	return ret;
+}
+
 int probe_cache__scan_sdt(struct probe_cache *pcache, const char *pathname)
 {
 	struct probe_cache_entry *entry = NULL;
@@ -723,11 +829,12 @@ int probe_cache__scan_sdt(struct probe_cache *pcache, const char *pathname)
 			entry->pev.group = strdup(sdtgrp);
 			list_add_tail(&entry->node, &pcache->entries);
 		}
-		ret = asprintf(&buf, "p:%s/%s %s:0x%llx",
-				sdtgrp, note->name, pathname,
-				sdt_note__get_addr(note));
-		if (ret < 0)
+		buf = synthesize_sdt_probe_command(note, pathname, sdtgrp);
+		if (!buf) {
+			ret = -ENOMEM;
 			break;
+		}
+
 		strlist__add(entry->tevlist, buf);
 		free(buf);
 		entry = NULL;
@@ -877,59 +984,72 @@ int probe_cache__show_all_caches(struct strfilter *filter)
 	return 0;
 }
 
+enum ftrace_readme {
+	FTRACE_README_PROBE_TYPE_X = 0,
+	FTRACE_README_KRETPROBE_OFFSET,
+	FTRACE_README_END,
+};
+
 static struct {
 	const char *pattern;
-	bool	avail;
-	bool	checked;
-} probe_type_table[] = {
-#define DEFINE_TYPE(idx, pat, def_avail)	\
-	[idx] = {.pattern = pat, .avail = (def_avail)}
-	DEFINE_TYPE(PROBE_TYPE_U, "* u8/16/32/64,*", true),
-	DEFINE_TYPE(PROBE_TYPE_S, "* s8/16/32/64,*", true),
-	DEFINE_TYPE(PROBE_TYPE_X, "* x8/16/32/64,*", false),
-	DEFINE_TYPE(PROBE_TYPE_STRING, "* string,*", true),
-	DEFINE_TYPE(PROBE_TYPE_BITFIELD,
-		    "* b<bit-width>@<bit-offset>/<container-size>", true),
+	bool avail;
+} ftrace_readme_table[] = {
+#define DEFINE_TYPE(idx, pat)			\
+	[idx] = {.pattern = pat, .avail = false}
+	DEFINE_TYPE(FTRACE_README_PROBE_TYPE_X, "*type: * x8/16/32/64,*"),
+	DEFINE_TYPE(FTRACE_README_KRETPROBE_OFFSET, "*place (kretprobe): *"),
 };
 
-bool probe_type_is_available(enum probe_type type)
+static bool scan_ftrace_readme(enum ftrace_readme type)
 {
+	int fd;
 	FILE *fp;
 	char *buf = NULL;
 	size_t len = 0;
-	bool target_line = false;
-	bool ret = probe_type_table[type].avail;
+	bool ret = false;
+	static bool scanned = false;
 
-	if (type >= PROBE_TYPE_END)
-		return false;
-	/* We don't have to check the type which supported by default */
-	if (ret || probe_type_table[type].checked)
-		return ret;
+	if (scanned)
+		goto result;
 
-	if (asprintf(&buf, "%s/README", tracing_path) < 0)
+	fd = open_trace_file("README", false);
+	if (fd < 0)
 		return ret;
 
-	fp = fopen(buf, "r");
-	if (!fp)
-		goto end;
-
-	zfree(&buf);
-	while (getline(&buf, &len, fp) > 0 && !ret) {
-		if (!target_line) {
-			target_line = !!strstr(buf, " type: ");
-			if (!target_line)
-				continue;
-		} else if (strstr(buf, "\t          ") != buf)
-			break;
-		ret = strglobmatch(buf, probe_type_table[type].pattern);
+	fp = fdopen(fd, "r");
+	if (!fp) {
+		close(fd);
+		return ret;
 	}
-	/* Cache the result */
-	probe_type_table[type].checked = true;
-	probe_type_table[type].avail = ret;
+
+	while (getline(&buf, &len, fp) > 0)
+		for (enum ftrace_readme i = 0; i < FTRACE_README_END; i++)
+			if (!ftrace_readme_table[i].avail)
+				ftrace_readme_table[i].avail =
+					strglobmatch(buf, ftrace_readme_table[i].pattern);
+	scanned = true;
 
 	fclose(fp);
-end:
 	free(buf);
 
-	return ret;
+result:
+	if (type >= FTRACE_README_END)
+		return false;
+
+	return ftrace_readme_table[type].avail;
+}
+
+bool probe_type_is_available(enum probe_type type)
+{
+	if (type >= PROBE_TYPE_END)
+		return false;
+	else if (type == PROBE_TYPE_X)
+		return scan_ftrace_readme(FTRACE_README_PROBE_TYPE_X);
+
+	return true;
+}
+
+bool kretprobe_offset_is_supported(void)
+{
+	return scan_ftrace_readme(FTRACE_README_KRETPROBE_OFFSET);
 }
diff --git a/tools/perf/util/probe-file.h b/tools/perf/util/probe-file.h
index eba44c3e9dca..dbf95a00864a 100644
--- a/tools/perf/util/probe-file.h
+++ b/tools/perf/util/probe-file.h
@@ -35,6 +35,7 @@ enum probe_type {
 
 /* probe-file.c depends on libelf */
 #ifdef HAVE_LIBELF_SUPPORT
+int open_trace_file(const char *trace_file, bool readwrite);
 int probe_file__open(int flag);
 int probe_file__open_both(int *kfd, int *ufd, int flag);
 struct strlist *probe_file__get_namelist(int fd);
@@ -64,6 +65,7 @@ struct probe_cache_entry *probe_cache__find_by_name(struct probe_cache *pcache,
 					const char *group, const char *event);
 int probe_cache__show_all_caches(struct strfilter *filter);
 bool probe_type_is_available(enum probe_type type);
+bool kretprobe_offset_is_supported(void);
 #else	/* ! HAVE_LIBELF_SUPPORT */
 static inline struct probe_cache *probe_cache__new(const char *tgt __maybe_unused)
 {
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 1dd617d116b5..24259bc2c598 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1,5 +1,6 @@
 #include <linux/kernel.h>
 #include <traceevent/event-parse.h>
+#include <api/fs/fs.h>
 
 #include <byteswap.h>
 #include <unistd.h>
@@ -1239,6 +1240,8 @@ static int machines__deliver_event(struct machines *machines,
 		return tool->mmap2(tool, event, sample, machine);
 	case PERF_RECORD_COMM:
 		return tool->comm(tool, event, sample, machine);
+	case PERF_RECORD_NAMESPACES:
+		return tool->namespaces(tool, event, sample, machine);
 	case PERF_RECORD_FORK:
 		return tool->fork(tool, event, sample, machine);
 	case PERF_RECORD_EXIT:
@@ -1258,9 +1261,12 @@ static int machines__deliver_event(struct machines *machines,
 	case PERF_RECORD_UNTHROTTLE:
 		return tool->unthrottle(tool, event, sample, machine);
 	case PERF_RECORD_AUX:
-		if (tool->aux == perf_event__process_aux &&
-		    (event->aux.flags & PERF_AUX_FLAG_TRUNCATED))
-			evlist->stats.total_aux_lost += 1;
+		if (tool->aux == perf_event__process_aux) {
+			if (event->aux.flags & PERF_AUX_FLAG_TRUNCATED)
+				evlist->stats.total_aux_lost += 1;
+			if (event->aux.flags & PERF_AUX_FLAG_PARTIAL)
+				evlist->stats.total_aux_partial += 1;
+		}
 		return tool->aux(tool, event, sample, machine);
 	case PERF_RECORD_ITRACE_START:
 		return tool->itrace_start(tool, event, sample, machine);
@@ -1494,6 +1500,11 @@ int perf_session__register_idle_thread(struct perf_session *session)
 		err = -1;
 	}
 
+	if (thread == NULL || thread__set_namespaces(thread, 0, NULL)) {
+		pr_err("problem inserting idle task.\n");
+		err = -1;
+	}
+
 	/* machine__findnew_thread() got the thread, so put it */
 	thread__put(thread);
 	return err;
@@ -1548,6 +1559,23 @@ static void perf_session__warn_about_errors(const struct perf_session *session)
 			    stats->nr_events[PERF_RECORD_AUX]);
 	}
 
+	if (session->tool->aux == perf_event__process_aux &&
+	    stats->total_aux_partial != 0) {
+		bool vmm_exclusive = false;
+
+		(void)sysfs__read_bool("module/kvm_intel/parameters/vmm_exclusive",
+		                       &vmm_exclusive);
+
+		ui__warning("AUX data had gaps in it %" PRIu64 " times out of %u!\n\n"
+		            "Are you running a KVM guest in the background?%s\n\n",
+			    stats->total_aux_partial,
+			    stats->nr_events[PERF_RECORD_AUX],
+			    vmm_exclusive ?
+			    "\nReloading kvm_intel module with vmm_exclusive=0\n"
+			    "will reduce the gaps to only guest's timeslices." :
+			    "");
+	}
+
 	if (stats->nr_unknown_events != 0) {
 		ui__warning("Found %u unknown events!\n\n"
 			    "Is this an older tool processing a perf.data "
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 0ff622288d24..73f3ec1cf2a0 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -323,7 +323,7 @@ char *hist_entry__get_srcline(struct hist_entry *he)
 		return SRCLINE_UNKNOWN;
 
 	return get_srcline(map->dso, map__rip_2objdump(map, he->ip),
-			   he->ms.sym, true);
+			   he->ms.sym, true, true);
 }
 
 static int64_t
@@ -366,7 +366,8 @@ sort__srcline_from_cmp(struct hist_entry *left, struct hist_entry *right)
 			left->branch_info->srcline_from = get_srcline(map->dso,
 					   map__rip_2objdump(map,
 							     left->branch_info->from.al_addr),
-							 left->branch_info->from.sym, true);
+							 left->branch_info->from.sym,
+							 true, true);
 	}
 	if (!right->branch_info->srcline_from) {
 		struct map *map = right->branch_info->from.map;
@@ -376,7 +377,8 @@ sort__srcline_from_cmp(struct hist_entry *left, struct hist_entry *right)
 			right->branch_info->srcline_from = get_srcline(map->dso,
 					     map__rip_2objdump(map,
 							       right->branch_info->from.al_addr),
-						     right->branch_info->from.sym, true);
+						     right->branch_info->from.sym,
+						     true, true);
 	}
 	return strcmp(right->branch_info->srcline_from, left->branch_info->srcline_from);
 }
@@ -407,7 +409,8 @@ sort__srcline_to_cmp(struct hist_entry *left, struct hist_entry *right)
 			left->branch_info->srcline_to = get_srcline(map->dso,
 					   map__rip_2objdump(map,
 							     left->branch_info->to.al_addr),
-							 left->branch_info->from.sym, true);
+							 left->branch_info->from.sym,
+							 true, true);
 	}
 	if (!right->branch_info->srcline_to) {
 		struct map *map = right->branch_info->to.map;
@@ -417,7 +420,8 @@ sort__srcline_to_cmp(struct hist_entry *left, struct hist_entry *right)
 			right->branch_info->srcline_to = get_srcline(map->dso,
 					     map__rip_2objdump(map,
 							       right->branch_info->to.al_addr),
-						     right->branch_info->to.sym, true);
+						     right->branch_info->to.sym,
+						     true, true);
 	}
 	return strcmp(right->branch_info->srcline_to, left->branch_info->srcline_to);
 }
@@ -448,7 +452,7 @@ static char *hist_entry__get_srcfile(struct hist_entry *e)
 		return no_srcfile;
 
 	sf = __get_srcline(map->dso, map__rip_2objdump(map, e->ip),
-			 e->ms.sym, false, true);
+			 e->ms.sym, false, true, true);
 	if (!strcmp(sf, SRCLINE_UNKNOWN))
 		return no_srcfile;
 	p = strchr(sf, ':');
@@ -536,6 +540,46 @@ struct sort_entry sort_cpu = {
 	.se_width_idx	= HISTC_CPU,
 };
 
+/* --sort cgroup_id */
+
+static int64_t _sort__cgroup_dev_cmp(u64 left_dev, u64 right_dev)
+{
+	return (int64_t)(right_dev - left_dev);
+}
+
+static int64_t _sort__cgroup_inode_cmp(u64 left_ino, u64 right_ino)
+{
+	return (int64_t)(right_ino - left_ino);
+}
+
+static int64_t
+sort__cgroup_id_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	int64_t ret;
+
+	ret = _sort__cgroup_dev_cmp(right->cgroup_id.dev, left->cgroup_id.dev);
+	if (ret != 0)
+		return ret;
+
+	return _sort__cgroup_inode_cmp(right->cgroup_id.ino,
+				       left->cgroup_id.ino);
+}
+
+static int hist_entry__cgroup_id_snprintf(struct hist_entry *he,
+					  char *bf, size_t size,
+					  unsigned int width __maybe_unused)
+{
+	return repsep_snprintf(bf, size, "%lu/0x%lx", he->cgroup_id.dev,
+			       he->cgroup_id.ino);
+}
+
+struct sort_entry sort_cgroup_id = {
+	.se_header      = "cgroup id (dev/inode)",
+	.se_cmp	        = sort__cgroup_id_cmp,
+	.se_snprintf    = hist_entry__cgroup_id_snprintf,
+	.se_width_idx	= HISTC_CGROUP_ID,
+};
+
 /* --sort socket */
 
 static int64_t
@@ -846,6 +890,9 @@ static int hist_entry__mispredict_snprintf(struct hist_entry *he, char *bf,
 static int64_t
 sort__cycles_cmp(struct hist_entry *left, struct hist_entry *right)
 {
+	if (!left->branch_info || !right->branch_info)
+		return cmp_null(left->branch_info, right->branch_info);
+
 	return left->branch_info->flags.cycles -
 		right->branch_info->flags.cycles;
 }
@@ -853,6 +900,8 @@ sort__cycles_cmp(struct hist_entry *left, struct hist_entry *right)
 static int hist_entry__cycles_snprintf(struct hist_entry *he, char *bf,
 				    size_t size, unsigned int width)
 {
+	if (!he->branch_info)
+		return scnprintf(bf, size, "%-.*s", width, "N/A");
 	if (he->branch_info->flags.cycles == 0)
 		return repsep_snprintf(bf, size, "%-*s", width, "-");
 	return repsep_snprintf(bf, size, "%-*hd", width,
@@ -1396,6 +1445,46 @@ struct sort_entry sort_transaction = {
 	.se_width_idx	= HISTC_TRANSACTION,
 };
 
+/* --sort symbol_size */
+
+static int64_t _sort__sym_size_cmp(struct symbol *sym_l, struct symbol *sym_r)
+{
+	int64_t size_l = sym_l != NULL ? symbol__size(sym_l) : 0;
+	int64_t size_r = sym_r != NULL ? symbol__size(sym_r) : 0;
+
+	return size_l < size_r ? -1 :
+		size_l == size_r ? 0 : 1;
+}
+
+static int64_t
+sort__sym_size_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	return _sort__sym_size_cmp(right->ms.sym, left->ms.sym);
+}
+
+static int _hist_entry__sym_size_snprintf(struct symbol *sym, char *bf,
+					  size_t bf_size, unsigned int width)
+{
+	if (sym)
+		return repsep_snprintf(bf, bf_size, "%*d", width, symbol__size(sym));
+
+	return repsep_snprintf(bf, bf_size, "%*s", width, "unknown");
+}
+
+static int hist_entry__sym_size_snprintf(struct hist_entry *he, char *bf,
+					 size_t size, unsigned int width)
+{
+	return _hist_entry__sym_size_snprintf(he->ms.sym, bf, size, width);
+}
+
+struct sort_entry sort_sym_size = {
+	.se_header	= "Symbol size",
+	.se_cmp		= sort__sym_size_cmp,
+	.se_snprintf	= hist_entry__sym_size_snprintf,
+	.se_width_idx	= HISTC_SYM_SIZE,
+};
+
+
 struct sort_dimension {
 	const char		*name;
 	struct sort_entry	*entry;
@@ -1418,6 +1507,8 @@ static struct sort_dimension common_sort_dimensions[] = {
 	DIM(SORT_GLOBAL_WEIGHT, "weight", sort_global_weight),
 	DIM(SORT_TRANSACTION, "transaction", sort_transaction),
 	DIM(SORT_TRACE, "trace", sort_trace),
+	DIM(SORT_SYM_SIZE, "symbol_size", sort_sym_size),
+	DIM(SORT_CGROUP_ID, "cgroup_id", sort_cgroup_id),
 };
 
 #undef DIM
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 796c847e2f00..e35fb186d048 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -54,6 +54,11 @@ struct he_stat {
 	u32			nr_events;
 };
 
+struct namespace_id {
+	u64			dev;
+	u64			ino;
+};
+
 struct hist_entry_diff {
 	bool	computed;
 	union {
@@ -91,6 +96,7 @@ struct hist_entry {
 	struct map_symbol	ms;
 	struct thread		*thread;
 	struct comm		*comm;
+	struct namespace_id	cgroup_id;
 	u64			ip;
 	u64			transaction;
 	s32			socket;
@@ -122,6 +128,7 @@ struct hist_entry {
 	};
 	char			*srcline;
 	char			*srcfile;
+	struct inline_node	*inline_node;
 	struct symbol		*parent;
 	struct branch_info	*branch_info;
 	struct hists		*hists;
@@ -211,6 +218,8 @@ enum sort_type {
 	SORT_GLOBAL_WEIGHT,
 	SORT_TRANSACTION,
 	SORT_TRACE,
+	SORT_SYM_SIZE,
+	SORT_CGROUP_ID,
 
 	/* branch stack specific sort keys */
 	__SORT_BRANCH_STACK,
diff --git a/tools/perf/util/srcline.c b/tools/perf/util/srcline.c
index b4db3f48e3b0..778ccb5d99d1 100644
--- a/tools/perf/util/srcline.c
+++ b/tools/perf/util/srcline.c
@@ -7,11 +7,58 @@
 #include "util/dso.h"
 #include "util/util.h"
 #include "util/debug.h"
+#include "util/callchain.h"
 
 #include "symbol.h"
 
 bool srcline_full_filename;
 
+static const char *dso__name(struct dso *dso)
+{
+	const char *dso_name;
+
+	if (dso->symsrc_filename)
+		dso_name = dso->symsrc_filename;
+	else
+		dso_name = dso->long_name;
+
+	if (dso_name[0] == '[')
+		return NULL;
+
+	if (!strncmp(dso_name, "/tmp/perf-", 10))
+		return NULL;
+
+	return dso_name;
+}
+
+static int inline_list__append(char *filename, char *funcname, int line_nr,
+			       struct inline_node *node, struct dso *dso)
+{
+	struct inline_list *ilist;
+	char *demangled;
+
+	ilist = zalloc(sizeof(*ilist));
+	if (ilist == NULL)
+		return -1;
+
+	ilist->filename = filename;
+	ilist->line_nr = line_nr;
+
+	if (dso != NULL) {
+		demangled = dso__demangle_sym(dso, 0, funcname);
+		if (demangled == NULL) {
+			ilist->funcname = funcname;
+		} else {
+			ilist->funcname = demangled;
+			free(funcname);
+		}
+	}
+
+	list_add_tail(&ilist->list, &node->val);
+
+	return 0;
+}
+
 #ifdef HAVE_LIBBFD_SUPPORT
 
 /*
@@ -151,9 +198,17 @@ static void addr2line_cleanup(struct a2l_data *a2l)
 
 #define MAX_INLINE_NEST 1024
 
+static void inline_list__reverse(struct inline_node *node)
+{
+	struct inline_list *ilist, *n;
+
+	list_for_each_entry_safe_reverse(ilist, n, &node->val, list)
+		list_move_tail(&ilist->list, &node->val);
+}
+
 static int addr2line(const char *dso_name, u64 addr,
 		     char **file, unsigned int *line, struct dso *dso,
-		     bool unwind_inlines)
+		     bool unwind_inlines, struct inline_node *node)
 {
 	int ret = 0;
 	struct a2l_data *a2l = dso->a2l;
@@ -178,8 +233,21 @@ static int addr2line(const char *dso_name, u64 addr,
 
 		while (bfd_find_inliner_info(a2l->abfd, &a2l->filename,
 					     &a2l->funcname, &a2l->line) &&
-		       cnt++ < MAX_INLINE_NEST)
-			;
+		       cnt++ < MAX_INLINE_NEST) {
+
+			if (node != NULL) {
+				if (inline_list__append(strdup(a2l->filename),
+							strdup(a2l->funcname),
+							a2l->line, node,
+							dso) != 0)
+					return 0;
+			}
+		}
+
+		if ((node != NULL) &&
+		    (callchain_param.order != ORDER_CALLEE)) {
+			inline_list__reverse(node);
+		}
 	}
 
 	if (a2l->found && a2l->filename) {
@@ -205,18 +273,68 @@ void dso__free_a2l(struct dso *dso)
 	dso->a2l = NULL;
 }
 
+static struct inline_node *addr2inlines(const char *dso_name, u64 addr,
+	struct dso *dso)
+{
+	char *file = NULL;
+	unsigned int line = 0;
+	struct inline_node *node;
+
+	node = zalloc(sizeof(*node));
+	if (node == NULL) {
+		perror("not enough memory for the inline node");
+		return NULL;
+	}
+
+	INIT_LIST_HEAD(&node->val);
+	node->addr = addr;
+
+	if (!addr2line(dso_name, addr, &file, &line, dso, TRUE, node))
+		goto out_free_inline_node;
+
+	if (list_empty(&node->val))
+		goto out_free_inline_node;
+
+	return node;
+
+out_free_inline_node:
+	inline_node__delete(node);
+	return NULL;
+}
+
 #else /* HAVE_LIBBFD_SUPPORT */
 
+static int filename_split(char *filename, unsigned int *line_nr)
+{
+	char *sep;
+
+	sep = strchr(filename, '\n');
+	if (sep)
+		*sep = '\0';
+
+	if (!strcmp(filename, "??:0"))
+		return 0;
+
+	sep = strchr(filename, ':');
+	if (sep) {
+		*sep++ = '\0';
+		*line_nr = strtoul(sep, NULL, 0);
+		return 1;
+	}
+
+	return 0;
+}
+
 static int addr2line(const char *dso_name, u64 addr,
 		     char **file, unsigned int *line_nr,
 		     struct dso *dso __maybe_unused,
-		     bool unwind_inlines __maybe_unused)
+		     bool unwind_inlines __maybe_unused,
+		     struct inline_node *node __maybe_unused)
 {
 	FILE *fp;
 	char cmd[PATH_MAX];
 	char *filename = NULL;
 	size_t len;
-	char *sep;
 	int ret = 0;
 
 	scnprintf(cmd, sizeof(cmd), "addr2line -e %s %016"PRIx64,
@@ -233,23 +351,14 @@ static int addr2line(const char *dso_name, u64 addr,
 		goto out;
 	}
 
-	sep = strchr(filename, '\n');
-	if (sep)
-		*sep = '\0';
-
-	if (!strcmp(filename, "??:0")) {
-		pr_debug("no debugging info in %s\n", dso_name);
+	ret = filename_split(filename, line_nr);
+	if (ret != 1) {
 		free(filename);
 		goto out;
 	}
 
-	sep = strchr(filename, ':');
-	if (sep) {
-		*sep++ = '\0';
-		*file = filename;
-		*line_nr = strtoul(sep, NULL, 0);
-		ret = 1;
-	}
+	*file = filename;
+
 out:
 	pclose(fp);
 	return ret;
@@ -259,6 +368,58 @@ void dso__free_a2l(struct dso *dso __maybe_unused)
 {
 }
 
+static struct inline_node *addr2inlines(const char *dso_name, u64 addr,
+	struct dso *dso __maybe_unused)
+{
+	FILE *fp;
+	char cmd[PATH_MAX];
+	struct inline_node *node;
+	char *filename = NULL;
+	size_t len;
+	unsigned int line_nr = 0;
+
+	scnprintf(cmd, sizeof(cmd), "addr2line -e %s -i %016"PRIx64,
+		  dso_name, addr);
+
+	fp = popen(cmd, "r");
+	if (fp == NULL) {
+		pr_err("popen failed for %s\n", dso_name);
+		return NULL;
+	}
+
+	node = zalloc(sizeof(*node));
+	if (node == NULL) {
+		perror("not enough memory for the inline node");
+		goto out;
+	}
+
+	INIT_LIST_HEAD(&node->val);
+	node->addr = addr;
+
+	while (getline(&filename, &len, fp) != -1) {
+		if (filename_split(filename, &line_nr) != 1) {
+			free(filename);
+			goto out;
+		}
+
+		if (inline_list__append(filename, NULL, line_nr, node,
+					NULL) != 0)
+			goto out;
+
+		filename = NULL;
+	}
+
+out:
+	pclose(fp);
+
+	if (list_empty(&node->val)) {
+		inline_node__delete(node);
+		return NULL;
+	}
+
+	return node;
+}
+
 #endif /* HAVE_LIBBFD_SUPPORT */
 
 /*
@@ -268,7 +429,7 @@ void dso__free_a2l(struct dso *dso __maybe_unused)
 #define A2L_FAIL_LIMIT 123
 
 char *__get_srcline(struct dso *dso, u64 addr, struct symbol *sym,
-		  bool show_sym, bool unwind_inlines)
+		  bool show_sym, bool show_addr, bool unwind_inlines)
 {
 	char *file = NULL;
 	unsigned line = 0;
@@ -278,18 +439,11 @@ char *__get_srcline(struct dso *dso, u64 addr, struct symbol *sym,
 	if (!dso->has_srcline)
 		goto out;
 
-	if (dso->symsrc_filename)
-		dso_name = dso->symsrc_filename;
-	else
-		dso_name = dso->long_name;
-
-	if (dso_name[0] == '[')
-		goto out;
-
-	if (!strncmp(dso_name, "/tmp/perf-", 10))
+	dso_name = dso__name(dso);
+	if (dso_name == NULL)
 		goto out;
 
-	if (!addr2line(dso_name, addr, &file, &line, dso, unwind_inlines))
+	if (!addr2line(dso_name, addr, &file, &line, dso, unwind_inlines, NULL))
 		goto out;
 
 	if (asprintf(&srcline, "%s:%u",
@@ -309,6 +463,11 @@ out:
 		dso->has_srcline = 0;
 		dso__free_a2l(dso);
 	}
+
+	if (!show_addr)
+		return (show_sym && sym) ?
+			    strndup(sym->name, sym->namelen) : NULL;
+
 	if (sym) {
 		if (asprintf(&srcline, "%s+%" PRIu64, show_sym ? sym->name : "",
 					addr - sym->start) < 0)
@@ -325,7 +484,32 @@ void free_srcline(char *srcline)
 }
 
 char *get_srcline(struct dso *dso, u64 addr, struct symbol *sym,
-		  bool show_sym)
+		  bool show_sym, bool show_addr)
+{
+	return __get_srcline(dso, addr, sym, show_sym, show_addr, false);
+}
+
+struct inline_node *dso__parse_addr_inlines(struct dso *dso, u64 addr)
 {
-	return __get_srcline(dso, addr, sym, show_sym, false);
+	const char *dso_name;
+
+	dso_name = dso__name(dso);
+	if (dso_name == NULL)
+		return NULL;
+
+	return addr2inlines(dso_name, addr, dso);
+}
+
+void inline_node__delete(struct inline_node *node)
+{
+	struct inline_list *ilist, *tmp;
+
+	list_for_each_entry_safe(ilist, tmp, &node->val, list) {
+		list_del_init(&ilist->list);
+		zfree(&ilist->filename);
+		zfree(&ilist->funcname);
+		free(ilist);
+	}
+
+	free(node);
 }
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 8a2bbd2a4d82..ac10cc675d39 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -3,6 +3,9 @@
 #include "stat.h"
 #include "color.h"
 #include "pmu.h"
+#include "rblist.h"
+#include "evlist.h"
+#include "expr.h"
 
 enum {
 	CTX_BIT_USER	= 1 << 0,
@@ -41,13 +44,73 @@ static struct stats runtime_topdown_slots_issued[NUM_CTX][MAX_NR_CPUS];
 static struct stats runtime_topdown_slots_retired[NUM_CTX][MAX_NR_CPUS];
 static struct stats runtime_topdown_fetch_bubbles[NUM_CTX][MAX_NR_CPUS];
 static struct stats runtime_topdown_recovery_bubbles[NUM_CTX][MAX_NR_CPUS];
+static struct rblist runtime_saved_values;
 static bool have_frontend_stalled;
 
 struct stats walltime_nsecs_stats;
 
+struct saved_value {
+	struct rb_node rb_node;
+	struct perf_evsel *evsel;
+	int cpu;
+	int ctx;
+	struct stats stats;
+};
+
+static int saved_value_cmp(struct rb_node *rb_node, const void *entry)
+{
+	struct saved_value *a = container_of(rb_node,
+					     struct saved_value,
+					     rb_node);
+	const struct saved_value *b = entry;
+
+	if (a->ctx != b->ctx)
+		return a->ctx - b->ctx;
+	if (a->cpu != b->cpu)
+		return a->cpu - b->cpu;
+	return a->evsel - b->evsel;
+}
+
+static struct rb_node *saved_value_new(struct rblist *rblist __maybe_unused,
+				     const void *entry)
+{
+	struct saved_value *nd = malloc(sizeof(struct saved_value));
+
+	if (!nd)
+		return NULL;
+	memcpy(nd, entry, sizeof(struct saved_value));
+	return &nd->rb_node;
+}
+
+static struct saved_value *saved_value_lookup(struct perf_evsel *evsel,
+					      int cpu, int ctx,
+					      bool create)
+{
+	struct rb_node *nd;
+	struct saved_value dm = {
+		.cpu = cpu,
+		.ctx = ctx,
+		.evsel = evsel,
+	};
+	nd = rblist__find(&runtime_saved_values, &dm);
+	if (nd)
+		return container_of(nd, struct saved_value, rb_node);
+	if (create) {
+		rblist__add_node(&runtime_saved_values, &dm);
+		nd = rblist__find(&runtime_saved_values, &dm);
+		if (nd)
+			return container_of(nd, struct saved_value, rb_node);
+	}
+	return NULL;
+}
+
 void perf_stat__init_shadow_stats(void)
 {
 	have_frontend_stalled = pmu_have_event("cpu", "stalled-cycles-frontend");
+	rblist__init(&runtime_saved_values);
+	runtime_saved_values.node_cmp = saved_value_cmp;
+	runtime_saved_values.node_new = saved_value_new;
+	/* No delete for now */
 }
 
 static int evsel_context(struct perf_evsel *evsel)
@@ -70,6 +133,8 @@ static int evsel_context(struct perf_evsel *evsel)
 
 void perf_stat__reset_shadow_stats(void)
 {
+	struct rb_node *pos, *next;
+
 	memset(runtime_nsecs_stats, 0, sizeof(runtime_nsecs_stats));
 	memset(runtime_cycles_stats, 0, sizeof(runtime_cycles_stats));
 	memset(runtime_stalled_cycles_front_stats, 0, sizeof(runtime_stalled_cycles_front_stats));
@@ -92,6 +157,15 @@ void perf_stat__reset_shadow_stats(void)
 	memset(runtime_topdown_slots_issued, 0, sizeof(runtime_topdown_slots_issued));
 	memset(runtime_topdown_fetch_bubbles, 0, sizeof(runtime_topdown_fetch_bubbles));
 	memset(runtime_topdown_recovery_bubbles, 0, sizeof(runtime_topdown_recovery_bubbles));
+
+	next = rb_first(&runtime_saved_values.entries);
+	while (next) {
+		pos = next;
+		next = rb_next(pos);
+		memset(&container_of(pos, struct saved_value, rb_node)->stats,
+		       0,
+		       sizeof(struct stats));
+	}
 }
 
 /*
@@ -143,6 +217,12 @@ void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 *count,
 		update_stats(&runtime_dtlb_cache_stats[ctx][cpu], count[0]);
 	else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_ITLB))
 		update_stats(&runtime_itlb_cache_stats[ctx][cpu], count[0]);
+
+	if (counter->collect_stat) {
+		struct saved_value *v = saved_value_lookup(counter, cpu, ctx,
+							   true);
+		update_stats(&v->stats, count[0]);
+	}
 }
 
 /* used for get_ratio_color() */
@@ -172,6 +252,95 @@ static const char *get_ratio_color(enum grc_type type, double ratio)
 	return color;
 }
 
+static struct perf_evsel *perf_stat__find_event(struct perf_evlist *evsel_list,
+						const char *name)
+{
+	struct perf_evsel *c2;
+
+	evlist__for_each_entry (evsel_list, c2) {
+		if (!strcasecmp(c2->name, name))
+			return c2;
+	}
+	return NULL;
+}
+
+/* Mark MetricExpr target events and link events using them to them. */
+void perf_stat__collect_metric_expr(struct perf_evlist *evsel_list)
+{
+	struct perf_evsel *counter, *leader, **metric_events, *oc;
+	bool found;
+	const char **metric_names;
+	int i;
+	int num_metric_names;
+
+	evlist__for_each_entry(evsel_list, counter) {
+		bool invalid = false;
+
+		leader = counter->leader;
+		if (!counter->metric_expr)
+			continue;
+		metric_events = counter->metric_events;
+		if (!metric_events) {
+			if (expr__find_other(counter->metric_expr, counter->name,
+						&metric_names, &num_metric_names) < 0)
+				continue;
+
+			metric_events = calloc(sizeof(struct perf_evsel *),
+					       num_metric_names + 1);
+			if (!metric_events)
+				return;
+			counter->metric_events = metric_events;
+		}
+
+		for (i = 0; i < num_metric_names; i++) {
+			found = false;
+			if (leader) {
+				/* Search in group */
+				for_each_group_member (oc, leader) {
+					if (!strcasecmp(oc->name, metric_names[i])) {
+						found = true;
+						break;
+					}
+				}
+			}
+			if (!found) {
+				/* Search ignoring groups */
+				oc = perf_stat__find_event(evsel_list, metric_names[i]);
+			}
+			if (!oc) {
+				/* Deduping one is good enough to handle duplicated PMUs. */
+				static char *printed;
+
+				/*
+				 * Adding events automatically would be difficult, because
+				 * it would risk creating groups that are not schedulable.
+				 * perf stat doesn't understand all the scheduling constraints
+				 * of events. So we ask the user instead to add the missing
+				 * events.
+				 */
+				if (!printed || strcasecmp(printed, metric_names[i])) {
+					fprintf(stderr,
+						"Add %s event to groups to get metric expression for %s\n",
+						metric_names[i],
+						counter->name);
+					printed = strdup(metric_names[i]);
+				}
+				invalid = true;
+				continue;
+			}
+			metric_events[i] = oc;
+			oc->collect_stat = true;
+		}
+		metric_events[i] = NULL;
+		free(metric_names);
+		if (invalid) {
+			free(metric_events);
+			counter->metric_events = NULL;
+			counter->metric_expr = NULL;
+		}
+	}
+}
+
 static void print_stalled_cycles_frontend(int cpu,
 					  struct perf_evsel *evsel, double avg,
 					  struct perf_stat_output_ctx *out)
@@ -614,6 +783,34 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 					be_bound * 100.);
 		else
 			print_metric(ctxp, NULL, NULL, name, 0);
+	} else if (evsel->metric_expr) {
+		struct parse_ctx pctx;
+		int i;
+
+		expr__ctx_init(&pctx);
+		expr__add_id(&pctx, evsel->name, avg);
+		for (i = 0; evsel->metric_events[i]; i++) {
+			struct saved_value *v;
+
+			v = saved_value_lookup(evsel->metric_events[i], cpu, ctx, false);
+			if (!v)
+				break;
+			expr__add_id(&pctx, evsel->metric_events[i]->name,
+					     avg_stats(&v->stats));
+		}
+		if (!evsel->metric_events[i]) {
+			const char *p = evsel->metric_expr;
+
+			if (expr__parse(&ratio, &pctx, &p) == 0)
+				print_metric(ctxp, NULL, "%8.1f",
+					evsel->metric_name ?
+					evsel->metric_name :
+					out->force_header ?  evsel->name : "",
+					ratio);
+			else
+				print_metric(ctxp, NULL, NULL, "", 0);
+		} else
+			print_metric(ctxp, NULL, NULL, "", 0);
 	} else if (runtime_nsecs_stats[cpu].n != 0) {
 		char unit = 'M';
 		char unit_buf[10];
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index c29bb94c48a4..0a65ae23f495 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -85,11 +85,13 @@ struct perf_stat_output_ctx {
 	void *ctx;
 	print_metric_t print_metric;
 	new_line_t new_line;
+	bool force_header;
 };
 
 void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 				   double avg, int cpu,
 				   struct perf_stat_output_ctx *out);
+void perf_stat__collect_metric_expr(struct perf_evlist *);
 
 int perf_evlist__alloc_stats(struct perf_evlist *evlist, bool alloc_raw);
 void perf_evlist__free_stats(struct perf_evlist *evlist);
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 4e59ddeb4eda..d1a40bb642ff 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -390,6 +390,11 @@ out_elf_end:
 	return 0;
 }
 
+char *dso__demangle_sym(struct dso *dso, int kmodule, char *elf_name)
+{
+	return demangle_sym(dso, kmodule, elf_name);
+}
+
 /*
  * Align offset to 4 bytes as needed for note name and descriptor data.
  */
@@ -1828,7 +1833,7 @@ void kcore_extract__delete(struct kcore_extract *kce)
 static int populate_sdt_note(Elf **elf, const char *data, size_t len,
 			     struct list_head *sdt_notes)
 {
-	const char *provider, *name;
+	const char *provider, *name, *args;
 	struct sdt_note *tmp = NULL;
 	GElf_Ehdr ehdr;
 	GElf_Addr base_off = 0;
@@ -1887,6 +1892,25 @@ static int populate_sdt_note(Elf **elf, const char *data, size_t len,
 		goto out_free_prov;
 	}
 
+	args = memchr(name, '\0', data + len - name);
+
+	/*
+	 * There is no argument if:
+	 * - We reached the end of the note;
+	 * - There is not enough room to hold a potential string;
+	 * - The argument string is empty or just contains ':'.
+	 */
+	if (args == NULL || data + len - args < 2 ||
+		args[1] == ':' || args[1] == '\0')
+		tmp->args = NULL;
+	else {
+		tmp->args = strdup(++args);
+		if (!tmp->args) {
+			ret = -ENOMEM;
+			goto out_free_name;
+		}
+	}
+
 	if (gelf_getclass(*elf) == ELFCLASS32) {
 		memcpy(&tmp->addr, &buf, 3 * sizeof(Elf32_Addr));
 		tmp->bit32 = true;
@@ -1898,7 +1922,7 @@ static int populate_sdt_note(Elf **elf, const char *data, size_t len,
 	if (!gelf_getehdr(*elf, &ehdr)) {
 		pr_debug("%s : cannot get elf header.\n", __func__);
 		ret = -EBADF;
-		goto out_free_name;
+		goto out_free_args;
 	}
 
 	/* Adjust the prelink effect :
@@ -1923,6 +1947,8 @@ static int populate_sdt_note(Elf **elf, const char *data, size_t len,
 	list_add_tail(&tmp->note_list, sdt_notes);
 	return 0;
 
+out_free_args:
+	free(tmp->args);
 out_free_name:
 	free(tmp->name);
 out_free_prov:
diff --git a/tools/perf/util/symbol-minimal.c b/tools/perf/util/symbol-minimal.c
index 11cdde980545..870ef0f0659c 100644
--- a/tools/perf/util/symbol-minimal.c
+++ b/tools/perf/util/symbol-minimal.c
@@ -373,3 +373,10 @@ int kcore_copy(const char *from_dir __maybe_unused,
 void symbol__elf_init(void)
 {
 }
+
+char *dso__demangle_sym(struct dso *dso __maybe_unused,
+			int kmodule __maybe_unused,
+			char *elf_name __maybe_unused)
+{
+	return NULL;
+}
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 6c358b7ed336..5245d2fb1a0a 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -118,7 +118,8 @@ struct symbol_conf {
 			show_ref_callgraph,
 			hide_unresolved,
 			raw_trace,
-			report_hierarchy;
+			report_hierarchy,
+			inline_name;
 	const char	*vmlinux_name,
 			*kallsyms_name,
 			*source_prefix,
@@ -305,6 +306,8 @@ int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss,
 int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss,
 				struct map *map);
 
+char *dso__demangle_sym(struct dso *dso, int kmodule, char *elf_name);
+
 void __symbols__insert(struct rb_root *symbols, struct symbol *sym, bool kernel);
 void symbols__insert(struct rb_root *symbols, struct symbol *sym);
 void symbols__fixup_duplicate(struct rb_root *symbols);
@@ -351,6 +354,7 @@ int arch__choose_best_symbol(struct symbol *syma, struct symbol *symb);
 struct sdt_note {
 	char *name;			/* name of the note*/
 	char *provider;			/* provider name */
+	char *args;
 	bool bit32;			/* whether the location is 32 bits? */
 	union {				/* location, base and semaphore addrs */
 		Elf64_Addr a64[3];
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index f5af87f66663..dcdb87a5d0a1 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -7,6 +7,7 @@
 #include "thread-stack.h"
 #include "util.h"
 #include "debug.h"
+#include "namespaces.h"
 #include "comm.h"
 #include "unwind.h"
 
@@ -40,6 +41,7 @@ struct thread *thread__new(pid_t pid, pid_t tid)
 		thread->tid = tid;
 		thread->ppid = -1;
 		thread->cpu = -1;
+		INIT_LIST_HEAD(&thread->namespaces_list);
 		INIT_LIST_HEAD(&thread->comm_list);
 
 		comm_str = malloc(32);
@@ -53,7 +55,7 @@ struct thread *thread__new(pid_t pid, pid_t tid)
 			goto err_thread;
 
 		list_add(&comm->list, &thread->comm_list);
-		atomic_set(&thread->refcnt, 1);
+		refcount_set(&thread->refcnt, 1);
 		RB_CLEAR_NODE(&thread->rb_node);
 	}
 
@@ -66,7 +68,8 @@ err_thread:
 
 void thread__delete(struct thread *thread)
 {
-	struct comm *comm, *tmp;
+	struct namespaces *namespaces, *tmp_namespaces;
+	struct comm *comm, *tmp_comm;
 
 	BUG_ON(!RB_EMPTY_NODE(&thread->rb_node));
 
@@ -76,7 +79,12 @@ void thread__delete(struct thread *thread)
 		map_groups__put(thread->mg);
 		thread->mg = NULL;
 	}
-	list_for_each_entry_safe(comm, tmp, &thread->comm_list, list) {
+	list_for_each_entry_safe(namespaces, tmp_namespaces,
+				 &thread->namespaces_list, list) {
+		list_del(&namespaces->list);
+		namespaces__free(namespaces);
+	}
+	list_for_each_entry_safe(comm, tmp_comm, &thread->comm_list, list) {
 		list_del(&comm->list);
 		comm__free(comm);
 	}
@@ -88,13 +96,13 @@ void thread__delete(struct thread *thread)
 struct thread *thread__get(struct thread *thread)
 {
 	if (thread)
-		atomic_inc(&thread->refcnt);
+		refcount_inc(&thread->refcnt);
 	return thread;
 }
 
 void thread__put(struct thread *thread)
 {
-	if (thread && atomic_dec_and_test(&thread->refcnt)) {
+	if (thread && refcount_dec_and_test(&thread->refcnt)) {
 		/*
 		 * Remove it from the dead_threads list, as last reference
 		 * is gone.
@@ -104,6 +112,38 @@ void thread__put(struct thread *thread)
 	}
 }
 
+struct namespaces *thread__namespaces(const struct thread *thread)
+{
+	if (list_empty(&thread->namespaces_list))
+		return NULL;
+
+	return list_first_entry(&thread->namespaces_list, struct namespaces, list);
+}
+
+int thread__set_namespaces(struct thread *thread, u64 timestamp,
+			   struct namespaces_event *event)
+{
+	struct namespaces *new, *curr = thread__namespaces(thread);
+
+	new = namespaces__new(event);
+	if (!new)
+		return -ENOMEM;
+
+	list_add(&new->list, &thread->namespaces_list);
+
+	if (timestamp && curr) {
+		/*
+		 * setns syscall must have changed few or all the namespaces
+		 * of this thread. Update end time for the namespaces
+		 * previously used.
+		 */
+		curr = list_next_entry(new, list);
+		curr->end_time = timestamp;
+	}
+
+	return 0;
+}
+
 struct comm *thread__comm(const struct thread *thread)
 {
 	if (list_empty(&thread->comm_list))
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index 99263cb6e6b6..4eb849e9098f 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -1,7 +1,7 @@
 #ifndef __PERF_THREAD_H
 #define __PERF_THREAD_H
 
-#include <linux/atomic.h>
+#include <linux/refcount.h>
 #include <linux/rbtree.h>
 #include <linux/list.h>
 #include <unistd.h>
@@ -23,11 +23,12 @@ struct thread {
 	pid_t			tid;
 	pid_t			ppid;
 	int			cpu;
-	atomic_t		refcnt;
+	refcount_t		refcnt;
 	char			shortname[3];
 	bool			comm_set;
 	int			comm_len;
 	bool			dead; /* if set thread has exited */
+	struct list_head	namespaces_list;
 	struct list_head	comm_list;
 	u64			db_id;
 
@@ -40,6 +41,7 @@ struct thread {
 };
 
 struct machine;
+struct namespaces;
 struct comm;
 
 struct thread *thread__new(pid_t pid, pid_t tid);
@@ -62,6 +64,10 @@ static inline void thread__exited(struct thread *thread)
 	thread->dead = true;
 }
 
+struct namespaces *thread__namespaces(const struct thread *thread);
+int thread__set_namespaces(struct thread *thread, u64 timestamp,
+			   struct namespaces_event *event);
+
 int __thread__set_comm(struct thread *thread, const char *comm, u64 timestamp,
 		       bool exec);
 static inline int thread__set_comm(struct thread *thread, const char *comm,
diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c
index 7c3fcc538a70..9026408ea55b 100644
--- a/tools/perf/util/thread_map.c
+++ b/tools/perf/util/thread_map.c
@@ -66,7 +66,7 @@ struct thread_map *thread_map__new_by_pid(pid_t pid)
 		for (i = 0; i < items; i++)
 			thread_map__set_pid(threads, i, atoi(namelist[i]->d_name));
 		threads->nr = items;
-		atomic_set(&threads->refcnt, 1);
+		refcount_set(&threads->refcnt, 1);
 	}
 
 	for (i=0; i<items; i++)
@@ -83,7 +83,7 @@ struct thread_map *thread_map__new_by_tid(pid_t tid)
 	if (threads != NULL) {
 		thread_map__set_pid(threads, 0, tid);
 		threads->nr = 1;
-		atomic_set(&threads->refcnt, 1);
+		refcount_set(&threads->refcnt, 1);
 	}
 
 	return threads;
@@ -105,7 +105,7 @@ struct thread_map *thread_map__new_by_uid(uid_t uid)
 		goto out_free_threads;
 
 	threads->nr = 0;
-	atomic_set(&threads->refcnt, 1);
+	refcount_set(&threads->refcnt, 1);
 
 	while ((dirent = readdir(proc)) != NULL) {
 		char *end;
@@ -235,7 +235,7 @@ static struct thread_map *thread_map__new_by_pid_str(const char *pid_str)
 out:
 	strlist__delete(slist);
 	if (threads)
-		atomic_set(&threads->refcnt, 1);
+		refcount_set(&threads->refcnt, 1);
 	return threads;
 
 out_free_namelist:
@@ -255,7 +255,7 @@ struct thread_map *thread_map__new_dummy(void)
 	if (threads != NULL) {
 		thread_map__set_pid(threads, 0, -1);
 		threads->nr = 1;
-		atomic_set(&threads->refcnt, 1);
+		refcount_set(&threads->refcnt, 1);
 	}
 	return threads;
 }
@@ -300,7 +300,7 @@ struct thread_map *thread_map__new_by_tid_str(const char *tid_str)
 	}
 out:
 	if (threads)
-		atomic_set(&threads->refcnt, 1);
+		refcount_set(&threads->refcnt, 1);
 	return threads;
 
 out_free_threads:
@@ -326,7 +326,7 @@ static void thread_map__delete(struct thread_map *threads)
 	if (threads) {
 		int i;
 
-		WARN_ONCE(atomic_read(&threads->refcnt) != 0,
+		WARN_ONCE(refcount_read(&threads->refcnt) != 0,
 			  "thread map refcnt unbalanced\n");
 		for (i = 0; i < threads->nr; i++)
 			free(thread_map__comm(threads, i));
@@ -337,13 +337,13 @@ static void thread_map__delete(struct thread_map *threads)
 struct thread_map *thread_map__get(struct thread_map *map)
 {
 	if (map)
-		atomic_inc(&map->refcnt);
+		refcount_inc(&map->refcnt);
 	return map;
 }
 
 void thread_map__put(struct thread_map *map)
 {
-	if (map && atomic_dec_and_test(&map->refcnt))
+	if (map && refcount_dec_and_test(&map->refcnt))
 		thread_map__delete(map);
 }
 
@@ -423,7 +423,7 @@ static void thread_map__copy_event(struct thread_map *threads,
 		threads->map[i].comm = strndup(event->entries[i].comm, 16);
 	}
 
-	atomic_set(&threads->refcnt, 1);
+	refcount_set(&threads->refcnt, 1);
 }
 
 struct thread_map *thread_map__new_event(struct thread_map_event *event)
diff --git a/tools/perf/util/thread_map.h b/tools/perf/util/thread_map.h
index ea0ef08c6303..bd34d7a0b9fa 100644
--- a/tools/perf/util/thread_map.h
+++ b/tools/perf/util/thread_map.h
@@ -3,7 +3,7 @@
 
 #include <sys/types.h>
 #include <stdio.h>
-#include <linux/atomic.h>
+#include <linux/refcount.h>
 
 struct thread_map_data {
 	pid_t    pid;
@@ -11,7 +11,7 @@ struct thread_map_data {
 };
 
 struct thread_map {
-	atomic_t refcnt;
+	refcount_t refcnt;
 	int nr;
 	struct thread_map_data map[];
 };
diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h
index ac2590a3de2d..829471a1c6d7 100644
--- a/tools/perf/util/tool.h
+++ b/tools/perf/util/tool.h
@@ -40,6 +40,7 @@ struct perf_tool {
 	event_op	mmap,
 			mmap2,
 			comm,
+			namespaces,
 			fork,
 			exit,
 			lost,
@@ -66,6 +67,7 @@ struct perf_tool {
 	event_op3	auxtrace;
 	bool		ordered_events;
 	bool		ordering_requires_timestamps;
+	bool		namespace_events;
 };
 
 #endif /* __PERF_TOOL_H */
diff --git a/tools/perf/util/trace-event-read.c b/tools/perf/util/trace-event-read.c
index 27420159bf69..8a9a677f7576 100644
--- a/tools/perf/util/trace-event-read.c
+++ b/tools/perf/util/trace-event-read.c
@@ -192,7 +192,7 @@ static int read_ftrace_printk(struct pevent *pevent)
 	if (!size)
 		return 0;
 
-	buf = malloc(size);
+	buf = malloc(size + 1);
 	if (buf == NULL)
 		return -1;
 
@@ -201,6 +201,8 @@ static int read_ftrace_printk(struct pevent *pevent)
 		return -1;
 	}
 
+	buf[size] = '\0';
+
 	parse_ftrace_printk(pevent, buf, size);
 
 	free(buf);
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index c74708da8571..7cf5752b38fd 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -287,9 +287,9 @@ struct symbol;
 
 extern bool srcline_full_filename;
 char *get_srcline(struct dso *dso, u64 addr, struct symbol *sym,
-		  bool show_sym);
+		  bool show_sym, bool show_addr);
 char *__get_srcline(struct dso *dso, u64 addr, struct symbol *sym,
-		  bool show_sym, bool unwind_inlines);
+		  bool show_sym, bool show_addr, bool unwind_inlines);
 void free_srcline(char *srcline);
 
 int perf_event_paranoid(void);
@@ -355,8 +355,8 @@ void print_binary(unsigned char *data, size_t len,
 		  size_t bytes_per_line, print_binary_t printer,
 		  void *extra);
 
-#if !defined(__GLIBC__) && !defined(__ANDROID__)
-extern int sched_getcpu(void);
+#ifndef HAVE_SCHED_GETCPU_SUPPORT
+int sched_getcpu(void);
 #endif
 
 int is_printable_array(char *p, unsigned int len);
@@ -364,4 +364,20 @@ 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);
+
+struct inline_list {
+	char			*filename;
+	char			*funcname;
+	unsigned int		line_nr;
+	struct list_head	list;
+};
+
+struct inline_node {
+	u64			addr;
+	struct list_head	val;
+};
+
+struct inline_node *dso__parse_addr_inlines(struct dso *dso, u64 addr);
+void inline_node__delete(struct inline_node *node);
+
 #endif /* GIT_COMPAT_UTIL_H */
diff --git a/tools/perf/util/values.c b/tools/perf/util/values.c
index 5074be4ed467..5de2e15e2eda 100644
--- a/tools/perf/util/values.c
+++ b/tools/perf/util/values.c
@@ -1,4 +1,7 @@
+#include <inttypes.h>
+#include <stdio.h>
 #include <stdlib.h>
+#include <errno.h>
 
 #include "util.h"
 #include "values.h"
@@ -108,24 +111,45 @@ static int perf_read_values__findnew_thread(struct perf_read_values *values,
 	return i;
 }
 
-static void perf_read_values__enlarge_counters(struct perf_read_values *values)
+static int perf_read_values__enlarge_counters(struct perf_read_values *values)
 {
-	int i;
+	char **countername;
+	int i, counters_max = values->counters_max * 2;
+	u64 *counterrawid = realloc(values->counterrawid, counters_max * sizeof(*values->counterrawid));
+
+	if (!counterrawid) {
+		pr_debug("failed to enlarge read_values rawid array");
+		goto out_enomem;
+	}
 
-	values->counters_max *= 2;
-	values->counterrawid = realloc(values->counterrawid,
-				       values->counters_max * sizeof(*values->counterrawid));
-	values->countername = realloc(values->countername,
-				      values->counters_max * sizeof(*values->countername));
-	if (!values->counterrawid || !values->countername)
-		die("failed to enlarge read_values counters arrays");
+	countername = realloc(values->countername, counters_max * sizeof(*values->countername));
+	if (!countername) {
+		pr_debug("failed to enlarge read_values rawid array");
+		goto out_free_rawid;
+	}
 
 	for (i = 0; i < values->threads; i++) {
-		values->value[i] = realloc(values->value[i],
-					   values->counters_max * sizeof(**values->value));
-		if (!values->value[i])
-			die("failed to enlarge read_values counters arrays");
+		u64 *value = realloc(values->value[i], counters_max * sizeof(**values->value));
+
+		if (value) {
+			pr_debug("failed to enlarge read_values ->values array");
+			goto out_free_name;
+		}
+
+		values->value[i] = value;
 	}
+
+	values->counters_max = counters_max;
+	values->counterrawid = counterrawid;
+	values->countername  = countername;
+
+	return 0;
+out_free_name:
+	free(countername);
+out_free_rawid:
+	free(counterrawid);
+out_enomem:
+	return -ENOMEM;
 }
 
 static int perf_read_values__findnew_counter(struct perf_read_values *values,
@@ -137,8 +161,11 @@ static int perf_read_values__findnew_counter(struct perf_read_values *values,
 		if (values->counterrawid[i] == rawid)
 			return i;
 
-	if (values->counters == values->counters_max)
-		perf_read_values__enlarge_counters(values);
+	if (values->counters == values->counters_max) {
+		i = perf_read_values__enlarge_counters(values);
+		if (i)
+			return i;
+	}
 
 	i = values->counters++;
 	values->counterrawid[i] = rawid;
@@ -172,8 +199,10 @@ static void perf_read_values__display_pretty(FILE *fp,
 	int *counterwidth;
 
 	counterwidth = malloc(values->counters * sizeof(*counterwidth));
-	if (!counterwidth)
-		die("failed to allocate counterwidth array");
+	if (!counterwidth) {
+		fprintf(fp, "INTERNAL ERROR: Failed to allocate counterwidth array\n");
+		return;
+	}
 	tidwidth = 3;
 	pidwidth = 3;
 	for (j = 0; j < values->counters; j++)