perf updates all over the place:

core:
 
    - Support for cgroup tracking in samples to allow cgroup based
      analysis
 
  tools:
 
    - Support for cgroup analysis
 
    - Commandline option and hotkey for perf top to change the sort order
 
    - A set of fixes all over the place
 
    - Various build system related improvements
 
    - Updates of the X86 pmu event JSON data
 
    - Documentation updates
 -----BEGIN PGP SIGNATURE-----
 
 iQJHBAABCgAxFiEEQp8+kY+LLUocC4bMphj1TA10mKEFAl6J2iATHHRnbHhAbGlu
 dXRyb25peC5kZQAKCRCmGPVMDXSYoXMEEACy6WaNabX7EzkLUnX0WCgxnZVSryNR
 4EnxLJSg5lChEe4q2mOS3mRMpzlXHQieWcFxlwda7kjIbFlgQvjJQUiYlAvxRRO/
 giY/GwCtTi/Flcb+7wKxTgMYmtAUOZDWeQbBZUlFLi9vyeCHVkjget9EyVsgbe/W
 EmRsrPuKOVMUTeEwm3zpIE051DObpiWLNge++My70q5W/yNsS94PbNydgKO7osqk
 pX37YVyBFpI2IQxMGzaE3yK7OxXRjYljZaz1tONFDMEYOX9gmxpDsCCflsP1ZOzL
 4/P4faRvAOElwxtYBelKmRl8eboqhRpTEK0Et0TI0LYbUZrE2nisDi0LTKPWQb0k
 Om2Qi6AfZs67PVzx9htlx6rfee72+sUluz5BDKOGH0pNJ8CFy70ns8InLsZqbBZ7
 SgFVNjx6bHxB58VuVE9WEzr/KVs6zI/SuJlH7WG7FLXbm5j0cETfCjg40JlDpSNh
 CZs+Epky1zyytrVJ9Gc7KnRlw8VB2eWEQ2cQ0sqj5w7WxhfrnsCmQf1zk4sofhOF
 iz3Dvb9Llz/pYWGZbEiQAuI+8bo0psJptidzpmpbIXs/woKDhW49w1FxqowJQMWe
 +lGWcauSfo3gjgEnTkOWAx3yiH4i9rvRChX8Jh0Z07d6Kwf19YYfxcuhlkx0Wutj
 eKaaErWDtWAxpA==
 =2UUD
 -----END PGP SIGNATURE-----

Merge tag 'perf-urgent-2020-04-05' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull more perf updates from Thomas Gleixner:
 "Perf updates all over the place:

  core:

   - Support for cgroup tracking in samples to allow cgroup based
     analysis

  tools:

   - Support for cgroup analysis

   - Commandline option and hotkey for perf top to change the sort order

   - A set of fixes all over the place

   - Various build system related improvements

   - Updates of the X86 pmu event JSON data

   - Documentation updates"

* tag 'perf-urgent-2020-04-05' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (55 commits)
  perf python: Fix clang detection to strip out options passed in $CC
  perf tools: Support Python 3.8+ in Makefile
  perf script: Fix invalid read of directory entry after closedir()
  perf script report: Fix SEGFAULT when using DWARF mode
  perf script: add -S/--symbols documentation
  perf pmu-events x86: Use CPU_CLK_UNHALTED.THREAD in Kernel_Utilization metric
  perf events parser: Add missing Intel CPU events to parser
  perf script: Allow --symbol to accept hexadecimal addresses
  perf report/top TUI: Fix title line formatting
  perf top: Support hotkey to change sort order
  perf top: Support --group-sort-idx to change the sort order
  perf symbols: Fix arm64 gap between kernel start and module end
  perf build-test: Honour JOBS to override detection of number of cores
  perf script: Add --show-cgroup-events option
  perf top: Add --all-cgroups option
  perf record: Add --all-cgroups option
  perf record: Support synthesizing cgroup events
  perf report: Add 'cgroup' sort key
  perf cgroup: Maintain cgroup hierarchy
  perf tools: Basic support for CGROUP event
  ...

include/linux/perf_event.h

@@ -1020,6 +1020,7 @@ struct perf_sample_data {
 	u64				stack_user_size;
 
 	u64				phys_addr;
+	u64				cgroup;
 } ____cacheline_aligned;
 
 /* default value for data source */

include/uapi/linux/perf_event.h

@@ -142,8 +142,9 @@ enum perf_event_sample_format {
 	PERF_SAMPLE_REGS_INTR			= 1U << 18,
 	PERF_SAMPLE_PHYS_ADDR			= 1U << 19,
 	PERF_SAMPLE_AUX				= 1U << 20,
+	PERF_SAMPLE_CGROUP			= 1U << 21,
 
-	PERF_SAMPLE_MAX = 1U << 21,		/* non-ABI */
+	PERF_SAMPLE_MAX = 1U << 22,		/* non-ABI */
 
 	__PERF_SAMPLE_CALLCHAIN_EARLY		= 1ULL << 63, /* non-ABI; internal use */
 };
@@ -381,7 +382,8 @@ struct perf_event_attr {
 				ksymbol        :  1, /* include ksymbol events */
 				bpf_event      :  1, /* include bpf events */
 				aux_output     :  1, /* generate AUX records instead of events */
-				__reserved_1   : 32;
+				cgroup         :  1, /* include cgroup events */
+				__reserved_1   : 31;
 
 	union {
 		__u32		wakeup_events;	  /* wakeup every n events */
@@ -1012,6 +1014,16 @@ enum perf_event_type {
 	 */
 	PERF_RECORD_BPF_EVENT			= 18,
 
+	/*
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *	u64				id;
+	 *	char				path[];
+	 *	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_CGROUP			= 19,
+
 	PERF_RECORD_MAX,			/* non-ABI */
 };
 

init/Kconfig

@@ -1029,7 +1029,8 @@ config CGROUP_PERF
 	help
 	  This option extends the perf per-cpu mode to restrict monitoring
 	  to threads which belong to the cgroup specified and run on the
-	  designated cpu.
+	  designated cpu.  Or this can be used to have cgroup ID in samples
+	  so that it can monitor performance events among cgroups.
 
 	  Say N if unsure.
 

kernel/events/core.c

@@ -387,6 +387,7 @@ static atomic_t nr_freq_events __read_mostly;
 static atomic_t nr_switch_events __read_mostly;
 static atomic_t nr_ksymbol_events __read_mostly;
 static atomic_t nr_bpf_events __read_mostly;
+static atomic_t nr_cgroup_events __read_mostly;
 
 static LIST_HEAD(pmus);
 static DEFINE_MUTEX(pmus_lock);
@@ -1861,6 +1862,9 @@ static void __perf_event_header_size(struct perf_event *event, u64 sample_type)
 	if (sample_type & PERF_SAMPLE_PHYS_ADDR)
 		size += sizeof(data->phys_addr);
 
+	if (sample_type & PERF_SAMPLE_CGROUP)
+		size += sizeof(data->cgroup);
+
 	event->header_size = size;
 }
 
@@ -4608,6 +4612,8 @@ static void unaccount_event(struct perf_event *event)
 		atomic_dec(&nr_comm_events);
 	if (event->attr.namespaces)
 		atomic_dec(&nr_namespaces_events);
+	if (event->attr.cgroup)
+		atomic_dec(&nr_cgroup_events);
 	if (event->attr.task)
 		atomic_dec(&nr_task_events);
 	if (event->attr.freq)
@@ -6864,6 +6870,9 @@ void perf_output_sample(struct perf_output_handle *handle,
 	if (sample_type & PERF_SAMPLE_PHYS_ADDR)
 		perf_output_put(handle, data->phys_addr);
 
+	if (sample_type & PERF_SAMPLE_CGROUP)
+		perf_output_put(handle, data->cgroup);
+
 	if (sample_type & PERF_SAMPLE_AUX) {
 		perf_output_put(handle, data->aux_size);
 
@@ -7063,6 +7072,16 @@ void perf_prepare_sample(struct perf_event_header *header,
 	if (sample_type & PERF_SAMPLE_PHYS_ADDR)
 		data->phys_addr = perf_virt_to_phys(data->addr);
 
+#ifdef CONFIG_CGROUP_PERF
+	if (sample_type & PERF_SAMPLE_CGROUP) {
+		struct cgroup *cgrp;
+
+		/* protected by RCU */
+		cgrp = task_css_check(current, perf_event_cgrp_id, 1)->cgroup;
+		data->cgroup = cgroup_id(cgrp);
+	}
+#endif
+
 	if (sample_type & PERF_SAMPLE_AUX) {
 		u64 size;
 
@@ -7735,6 +7754,105 @@ void perf_event_namespaces(struct task_struct *task)
 			NULL);
 }
 
+/*
+ * cgroup tracking
+ */
+#ifdef CONFIG_CGROUP_PERF
+
+struct perf_cgroup_event {
+	char				*path;
+	int				path_size;
+	struct {
+		struct perf_event_header	header;
+		u64				id;
+		char				path[];
+	} event_id;
+};
+
+static int perf_event_cgroup_match(struct perf_event *event)
+{
+	return event->attr.cgroup;
+}
+
+static void perf_event_cgroup_output(struct perf_event *event, void *data)
+{
+	struct perf_cgroup_event *cgroup_event = data;
+	struct perf_output_handle handle;
+	struct perf_sample_data sample;
+	u16 header_size = cgroup_event->event_id.header.size;
+	int ret;
+
+	if (!perf_event_cgroup_match(event))
+		return;
+
+	perf_event_header__init_id(&cgroup_event->event_id.header,
+				   &sample, event);
+	ret = perf_output_begin(&handle, event,
+				cgroup_event->event_id.header.size);
+	if (ret)
+		goto out;
+
+	perf_output_put(&handle, cgroup_event->event_id);
+	__output_copy(&handle, cgroup_event->path, cgroup_event->path_size);
+
+	perf_event__output_id_sample(event, &handle, &sample);
+
+	perf_output_end(&handle);
+out:
+	cgroup_event->event_id.header.size = header_size;
+}
+
+static void perf_event_cgroup(struct cgroup *cgrp)
+{
+	struct perf_cgroup_event cgroup_event;
+	char path_enomem[16] = "//enomem";
+	char *pathname;
+	size_t size;
+
+	if (!atomic_read(&nr_cgroup_events))
+		return;
+
+	cgroup_event = (struct perf_cgroup_event){
+		.event_id  = {
+			.header = {
+				.type = PERF_RECORD_CGROUP,
+				.misc = 0,
+				.size = sizeof(cgroup_event.event_id),
+			},
+			.id = cgroup_id(cgrp),
+		},
+	};
+
+	pathname = kmalloc(PATH_MAX, GFP_KERNEL);
+	if (pathname == NULL) {
+		cgroup_event.path = path_enomem;
+	} else {
+		/* just to be sure to have enough space for alignment */
+		cgroup_path(cgrp, pathname, PATH_MAX - sizeof(u64));
+		cgroup_event.path = pathname;
+	}
+
+	/*
+	 * Since our buffer works in 8 byte units we need to align our string
+	 * size to a multiple of 8. However, we must guarantee the tail end is
+	 * zero'd out to avoid leaking random bits to userspace.
+	 */
+	size = strlen(cgroup_event.path) + 1;
+	while (!IS_ALIGNED(size, sizeof(u64)))
+		cgroup_event.path[size++] = '\0';
+
+	cgroup_event.event_id.header.size += size;
+	cgroup_event.path_size = size;
+
+	perf_iterate_sb(perf_event_cgroup_output,
+			&cgroup_event,
+			NULL);
+
+	kfree(pathname);
+}
+
+#endif
+
 /*
  * mmap tracking
  */
@@ -10778,6 +10896,8 @@ static void account_event(struct perf_event *event)
 		atomic_inc(&nr_comm_events);
 	if (event->attr.namespaces)
 		atomic_inc(&nr_namespaces_events);
+	if (event->attr.cgroup)
+		atomic_inc(&nr_cgroup_events);
 	if (event->attr.task)
 		atomic_inc(&nr_task_events);
 	if (event->attr.freq)
@@ -11157,6 +11277,12 @@ static int perf_copy_attr(struct perf_event_attr __user *uattr,
 
 	if (attr->sample_type & PERF_SAMPLE_REGS_INTR)
 		ret = perf_reg_validate(attr->sample_regs_intr);
+
+#ifndef CONFIG_CGROUP_PERF
+	if (attr->sample_type & PERF_SAMPLE_CGROUP)
+		return -EINVAL;
+#endif
+
 out:
 	return ret;
 
@@ -12754,6 +12880,12 @@ static void perf_cgroup_css_free(struct cgroup_subsys_state *css)
 	kfree(jc);
 }
 
+static int perf_cgroup_css_online(struct cgroup_subsys_state *css)
+{
+	perf_event_cgroup(css->cgroup);
+	return 0;
+}
+
 static int __perf_cgroup_move(void *info)
 {
 	struct task_struct *task = info;
@@ -12775,6 +12907,7 @@ static void perf_cgroup_attach(struct cgroup_taskset *tset)
 struct cgroup_subsys perf_event_cgrp_subsys = {
 	.css_alloc	= perf_cgroup_css_alloc,
 	.css_free	= perf_cgroup_css_free,
+	.css_online	= perf_cgroup_css_online,
 	.attach		= perf_cgroup_attach,
 	/*
 	 * Implicitly enable on dfl hierarchy so that perf events can

tools/build/Makefile.feature

@@ -72,7 +72,8 @@ FEATURE_TESTS_BASIC :=                  \
         setns				\
         libaio				\
         libzstd				\
-        disassembler-four-args
+        disassembler-four-args		\
+        file-handle
 
 # FEATURE_TESTS_BASIC + FEATURE_TESTS_EXTRA is the complete list
 # of all feature tests

tools/build/feature/Makefile

@@ -68,7 +68,8 @@ FILES=                                          \
          test-llvm-version.bin			\
          test-libaio.bin			\
          test-libzstd.bin			\
-         test-clang-bpf-global-var.bin
+         test-clang-bpf-global-var.bin		\
+         test-file-handle.bin
 
 FILES := $(addprefix $(OUTPUT),$(FILES))
 
@@ -327,6 +328,8 @@ $(OUTPUT)test-clang-bpf-global-var.bin:
 	$(CLANG) -S -g -target bpf -o - $(patsubst %.bin,%.c,$(@F)) |	\
 		grep BTF_KIND_VAR
 
+$(OUTPUT)test-file-handle.bin:
+	$(BUILD)
 
 ###############################
 

tools/build/feature/test-file-handle.c

@@ -0,0 +1,17 @@
+#define _GNU_SOURCE
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <inttypes.h>
+
+int main(void)
+{
+	struct {
+		struct file_handle fh;
+		uint64_t cgroup_id;
+	} handle;
+	int mount_id;
+
+	name_to_handle_at(AT_FDCWD, "/", &handle.fh, &mount_id, 0);
+	return 0;
+}

tools/include/uapi/linux/perf_event.h

@@ -142,8 +142,9 @@ enum perf_event_sample_format {
 	PERF_SAMPLE_REGS_INTR			= 1U << 18,
 	PERF_SAMPLE_PHYS_ADDR			= 1U << 19,
 	PERF_SAMPLE_AUX				= 1U << 20,
+	PERF_SAMPLE_CGROUP			= 1U << 21,
 
-	PERF_SAMPLE_MAX = 1U << 21,		/* non-ABI */
+	PERF_SAMPLE_MAX = 1U << 22,		/* non-ABI */
 
 	__PERF_SAMPLE_CALLCHAIN_EARLY		= 1ULL << 63, /* non-ABI; internal use */
 };
@@ -381,7 +382,8 @@ struct perf_event_attr {
 				ksymbol        :  1, /* include ksymbol events */
 				bpf_event      :  1, /* include bpf events */
 				aux_output     :  1, /* generate AUX records instead of events */
-				__reserved_1   : 32;
+				cgroup         :  1, /* include cgroup events */
+				__reserved_1   : 31;
 
 	union {
 		__u32		wakeup_events;	  /* wakeup every n events */
@@ -1012,6 +1014,16 @@ enum perf_event_type {
 	 */
 	PERF_RECORD_BPF_EVENT			= 18,
 
+	/*
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *	u64				id;
+	 *	char				path[];
+	 *	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_CGROUP			= 19,
+
 	PERF_RECORD_MAX,			/* non-ABI */
 };
 

tools/lib/perf/include/perf/event.h

@@ -105,6 +105,12 @@ struct perf_record_bpf_event {
 	__u8			 tag[BPF_TAG_SIZE];  // prog tag
 };
 
+struct perf_record_cgroup {
+	struct perf_event_header header;
+	__u64			 id;
+	char			 path[PATH_MAX];
+};
+
 struct perf_record_sample {
 	struct perf_event_header header;
 	__u64			 array[];
@@ -352,6 +358,7 @@ union perf_event {
 	struct perf_record_mmap2		mmap2;
 	struct perf_record_comm			comm;
 	struct perf_record_namespaces		namespaces;
+	struct perf_record_cgroup		cgroup;
 	struct perf_record_fork			fork;
 	struct perf_record_lost			lost;
 	struct perf_record_lost_samples		lost_samples;

tools/perf/Documentation/perf-config.txt

@@ -405,14 +405,16 @@ ui.*::
 		This option is only applied to TUI.
 
 call-graph.*::
-	When sub-commands 'top' and 'report' work with -g/—-children
-	there're options in control of call-graph.
+	The following controls the handling of call-graphs (obtained via the
+	-g/--call-graph options).
 
 	call-graph.record-mode::
-		The record-mode can be 'fp' (frame pointer), 'dwarf' and 'lbr'.
-		The value of 'dwarf' is effective only if perf detect needed library
-		(libunwind or a recent version of libdw).
-		'lbr' only work for cpus that support it.
+		The mode for user space can be 'fp' (frame pointer), 'dwarf'
+		and 'lbr'.  The value 'dwarf' is effective only if libunwind
+		(or a recent version of libdw) is present on the system;
+		the value 'lbr' only works for certain cpus. The method for
+		kernel space is controlled not by this option but by the
+		kernel config (CONFIG_UNWINDER_*).
 
 	call-graph.dump-size::
 		The size of stack to dump in order to do post-unwinding. Default is 8192 (byte).

tools/perf/Documentation/perf-record.txt

@@ -237,16 +237,22 @@ OPTIONS
 	option and remains only for backward compatibility.  See --event.
 
 -g::
-	Enables call-graph (stack chain/backtrace) recording.
+	Enables call-graph (stack chain/backtrace) recording for both
+	kernel space and user space.
 
 --call-graph::
 	Setup and enable call-graph (stack chain/backtrace) recording,
-	implies -g.  Default is "fp".
+	implies -g.  Default is "fp" (for user space).
 
-	Allows specifying "fp" (frame pointer) or "dwarf"
-	(DWARF's CFI - Call Frame Information) or "lbr"
-	(Hardware Last Branch Record facility) as the method to collect
-	the information used to show the call graphs.
+	The unwinding method used for kernel space is dependent on the
+	unwinder used by the active kernel configuration, i.e
+	CONFIG_UNWINDER_FRAME_POINTER (fp) or CONFIG_UNWINDER_ORC (orc)
+
+	Any option specified here controls the method used for user space.
+
+	Valid options are "fp" (frame pointer), "dwarf" (DWARF's CFI -
+	Call Frame Information) or "lbr" (Hardware Last Branch Record
+	facility).
 
 	In some systems, where binaries are build with gcc
 	--fomit-frame-pointer, using the "fp" method will produce bogus
@@ -385,7 +391,10 @@ displayed with the weight and local_weight sort keys.  This currently works for
 abort events and some memory events in precise mode on modern Intel CPUs.
 
 --namespaces::
-Record events of type PERF_RECORD_NAMESPACES.
+Record events of type PERF_RECORD_NAMESPACES.  This enables 'cgroup_id' sort key.
+
+--all-cgroups::
+Record events of type PERF_RECORD_CGROUP.  This enables 'cgroup' sort key.
 
 --transaction::
 Record transaction flags for transaction related events.

tools/perf/Documentation/perf-report.txt

@@ -95,6 +95,7 @@ OPTIONS
 	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.
+	- cgroup: cgroup pathname in the cgroupfs.
 	- transaction: Transaction abort flags.
 	- overhead: Overhead percentage of sample
 	- overhead_sys: Overhead percentage of sample running in system mode
@@ -377,6 +378,11 @@ OPTIONS
 	Show event group information together. It forces group output also
 	if there are no groups defined in data file.
 
+--group-sort-idx::
+	Sort the output by the event at the index n in group. If n is invalid,
+	sort by the first event. It can support multiple groups with different
+	amount of events. WARNING: This should be used on grouped events.
+
 --demangle::
 	Demangle symbol names to human readable form. It's enabled by default,
 	disable with --no-demangle.

tools/perf/Documentation/perf-script.txt

@@ -319,6 +319,9 @@ OPTIONS
 --show-bpf-events
 	Display bpf events i.e. events of type PERF_RECORD_KSYMBOL and PERF_RECORD_BPF_EVENT.
 
+--show-cgroup-events
+	Display cgroup events i.e. events of type PERF_RECORD_CGROUP.
+
 --demangle::
 	Demangle symbol names to human readable form. It's enabled by default,
 	disable with --no-demangle.
@@ -390,6 +393,9 @@ include::itrace.txt[]
 --reltime::
 	Print time stamps relative to trace start.
 
+--deltatime::
+	Print time stamps relative to previous event.
+
 --per-event-dump::
 	Create per event files with a "perf.data.EVENT.dump" name instead of
         printing to stdout, useful, for instance, for generating flamegraphs.
@@ -406,6 +412,14 @@ include::itrace.txt[]
 --xed::
 	Run xed disassembler on output. Requires installing the xed disassembler.
 
+-S::
+--symbols=symbol[,symbol...]::
+	Only consider the listed symbols. Symbols are typically a name
+	but they may also be hexadecimal address.
+
+	For example, to select the symbol noploop or the address 0x4007a0:
+	perf script --symbols=noploop,0x4007a0
+
 --call-trace::
 	Show call stream for intel_pt traces. The CPUs are interleaved, but
 	can be filtered with -C.

tools/perf/Documentation/perf-top.txt

@@ -53,6 +53,11 @@ Default is to monitor all CPUS.
 --group::
         Put the counters into a counter group.
 
+--group-sort-idx::
+	Sort the output by the event at the index n in group. If n is invalid,
+	sort by the first event. It can support multiple groups with different
+	amount of events. WARNING: This should be used on grouped events.
+
 -F <freq>::
 --freq=<freq>::
 	Profile at this frequency. Use 'max' to use the currently maximum
@@ -272,6 +277,10 @@ Default is to monitor all CPUS.
 	Record events of type PERF_RECORD_NAMESPACES and display it with the
 	'cgroup_id' sort key.
 
+--all-cgroups::
+	Record events of type PERF_RECORD_CGROUP and display it with the
+	'cgroup' sort key.
+
 --switch-on EVENT_NAME::
 	Only consider events after this event is found.
 

tools/perf/Makefile.config

@@ -228,8 +228,17 @@ strip-libs  = $(filter-out -l%,$(1))
 
 PYTHON_CONFIG_SQ := $(call shell-sq,$(PYTHON_CONFIG))
 
+# Python 3.8 changed the output of `python-config --ldflags` to not include the
+# '-lpythonX.Y' flag unless '--embed' is also passed. The feature check for
+# libpython fails if that flag is not included in LDFLAGS
+ifeq ($(shell $(PYTHON_CONFIG_SQ) --ldflags --embed 2>&1 1>/dev/null; echo $$?), 0)
+  PYTHON_CONFIG_LDFLAGS := --ldflags --embed
+else
+  PYTHON_CONFIG_LDFLAGS := --ldflags
+endif
+
 ifdef PYTHON_CONFIG
-  PYTHON_EMBED_LDOPTS := $(shell $(PYTHON_CONFIG_SQ) --ldflags 2>/dev/null)
+  PYTHON_EMBED_LDOPTS := $(shell $(PYTHON_CONFIG_SQ) $(PYTHON_CONFIG_LDFLAGS) 2>/dev/null)
   PYTHON_EMBED_LDFLAGS := $(call strip-libs,$(PYTHON_EMBED_LDOPTS))
   PYTHON_EMBED_LIBADD := $(call grep-libs,$(PYTHON_EMBED_LDOPTS)) -lutil
   PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --includes 2>/dev/null)
@@ -348,6 +357,10 @@ ifeq ($(feature-gettid), 1)
   CFLAGS += -DHAVE_GETTID
 endif
 
+ifeq ($(feature-file-handle), 1)
+  CFLAGS += -DHAVE_FILE_HANDLE
+endif
+
 ifdef NO_LIBELF
   NO_DWARF := 1
   NO_DEMANGLE := 1

tools/perf/Makefile.perf

@@ -231,6 +231,7 @@ TRACE_EVENT_DIR = $(srctree)/tools/lib/traceevent/
 BPF_DIR         = $(srctree)/tools/lib/bpf/
 SUBCMD_DIR      = $(srctree)/tools/lib/subcmd/
 LIBPERF_DIR     = $(srctree)/tools/lib/perf/
+DOC_DIR         = $(srctree)/tools/perf/Documentation/
 
 # Set FEATURE_TESTS to 'all' so all possible feature checkers are executed.
 # Without this setting the output feature dump file misses some features, for
@@ -573,7 +574,7 @@ arch_errno_hdr_dir := $(srctree)/tools
 arch_errno_tbl := $(srctree)/tools/perf/trace/beauty/arch_errno_names.sh
 
 $(arch_errno_name_array): $(arch_errno_tbl)
-	$(Q)$(SHELL) '$(arch_errno_tbl)' $(CC) $(arch_errno_hdr_dir) > $@
+	$(Q)$(SHELL) '$(arch_errno_tbl)' $(firstword $(CC)) $(arch_errno_hdr_dir) > $@
 
 sync_file_range_arrays := $(beauty_outdir)/sync_file_range_arrays.c
 sync_file_range_tbls := $(srctree)/tools/perf/trace/beauty/sync_file_range.sh
@@ -792,7 +793,6 @@ $(LIBSUBCMD): FORCE
 	$(Q)$(MAKE) -C $(SUBCMD_DIR) O=$(OUTPUT) $(OUTPUT)libsubcmd.a
 
 $(LIBSUBCMD)-clean:
-	$(call QUIET_CLEAN, libsubcmd)
 	$(Q)$(MAKE) -C $(SUBCMD_DIR) O=$(OUTPUT) clean
 
 help:
@@ -832,7 +832,7 @@ INSTALL_DOC_TARGETS += quick-install-doc quick-install-man quick-install-html
 
 # 'make doc' should call 'make -C Documentation all'
 $(DOC_TARGETS):
-	$(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) $(@:doc=all)
+	$(Q)$(MAKE) -C $(DOC_DIR) O=$(OUTPUT) $(@:doc=all)
 
 TAG_FOLDERS= . ../lib ../include
 TAG_FILES= ../../include/uapi/linux/perf_event.h
@@ -959,7 +959,7 @@ install-python_ext:
 
 # 'make install-doc' should call 'make -C Documentation install'
 $(INSTALL_DOC_TARGETS):
-	$(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) $(@:-doc=)
+	$(Q)$(MAKE) -C $(DOC_DIR) O=$(OUTPUT) $(@:-doc=)
 
 ### Cleaning rules
 
@@ -1008,7 +1008,8 @@ clean:: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clea
 		$(OUTPUT)$(rename_flags_array) \
 		$(OUTPUT)$(arch_errno_name_array) \
 		$(OUTPUT)$(sync_file_range_arrays)
-	$(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) clean
+	$(call QUIET_CLEAN, Documentation) \
+	$(MAKE) -C $(DOC_DIR) O=$(OUTPUT) clean >/dev/null
 
 #
 # To provide FEATURE-DUMP into $(FEATURE_DUMP_COPY)

tools/perf/arch/arm64/util/Build

@@ -1,6 +1,6 @@
 perf-y += header.o
+perf-y += machine.o
 perf-y += perf_regs.o
-perf-y += sym-handling.o
 perf-$(CONFIG_DWARF)     += dwarf-regs.o
 perf-$(CONFIG_LOCAL_LIBUNWIND) += unwind-libunwind.o
 perf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o

tools/perf/arch/arm64/util/machine.c

@@ -0,0 +1,27 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <stdio.h>
+#include <string.h>
+#include "debug.h"
+#include "symbol.h"
+
+/* On arm64, kernel text segment start at high memory address,
+ * for example 0xffff 0000 8xxx xxxx. Modules start at a low memory
+ * address, like 0xffff 0000 00ax xxxx. When only samll amount of
+ * memory is used by modules, gap between end of module's text segment
+ * and start of kernel text segment may be reach 2G.
+ * Therefore do not fill this gap and do not assign it to the kernel dso map.
+ */
+
+#define SYMBOL_LIMIT (1 << 12) /* 4K */
+
+void arch__symbols__fixup_end(struct symbol *p, struct symbol *c)
+{
+	if ((strchr(p->name, '[') && strchr(c->name, '[') == NULL) ||
+			(strchr(p->name, '[') == NULL && strchr(c->name, '[')))
+		/* Limit range of last symbol in module and kernel */
+		p->end += SYMBOL_LIMIT;
+	else
+		p->end = c->start;
+	pr_debug4("%s sym:%s end:%#lx\n", __func__, p->name, p->end);
+}

tools/perf/arch/arm64/util/sym-handling.c

@@ -1,19 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- *
- * Copyright (C) 2015 Naveen N. Rao, IBM Corporation
- */
-
-#include "symbol.h" // for the elf__needs_adjust_symbols() prototype
-#include <stdbool.h>
-
-#ifdef HAVE_LIBELF_SUPPORT
-#include <gelf.h>
-
-bool elf__needs_adjust_symbols(GElf_Ehdr ehdr)
-{
-	return ehdr.e_type == ET_EXEC ||
-	       ehdr.e_type == ET_REL ||
-	       ehdr.e_type == ET_DYN;
-}
-#endif

tools/perf/arch/powerpc/util/Build

@@ -1,5 +1,4 @@
 perf-y += header.o
-perf-y += sym-handling.o
 perf-y += kvm-stat.o
 perf-y += perf_regs.o
 perf-y += mem-events.o

tools/perf/arch/powerpc/util/sym-handling.c

@@ -10,16 +10,6 @@
 #include "probe-event.h"
 #include "probe-file.h"
 
-#ifdef HAVE_LIBELF_SUPPORT
-bool elf__needs_adjust_symbols(GElf_Ehdr ehdr)
-{
-	return ehdr.e_type == ET_EXEC ||
-	       ehdr.e_type == ET_REL ||
-	       ehdr.e_type == ET_DYN;
-}
-
-#endif
-
 int arch__choose_best_symbol(struct symbol *syma,
 			     struct symbol *symb __maybe_unused)
 {

tools/perf/builtin-diff.c

@@ -455,6 +455,7 @@ static struct perf_diff pdiff = {
 		.fork	= perf_event__process_fork,
 		.lost	= perf_event__process_lost,
 		.namespaces = perf_event__process_namespaces,
+		.cgroup = perf_event__process_cgroup,
 		.ordered_events = true,
 		.ordering_requires_timestamps = true,
 	},

tools/perf/builtin-record.c

@@ -1397,6 +1397,11 @@ static int record__synthesize(struct record *rec, bool tail)
 	if (err < 0)
 		pr_warning("Couldn't synthesize bpf events.\n");
 
+	err = perf_event__synthesize_cgroups(tool, process_synthesized_event,
+					     machine);
+	if (err < 0)
+		pr_warning("Couldn't synthesize cgroup events.\n");
+
 	err = __machine__synthesize_threads(machine, tool, &opts->target, rec->evlist->core.threads,
 					    process_synthesized_event, opts->sample_address,
 					    1);
@@ -1428,6 +1433,15 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 	if (rec->opts.record_namespaces)
 		tool->namespace_events = true;
 
+	if (rec->opts.record_cgroup) {
+#ifdef HAVE_FILE_HANDLE
+		tool->cgroup_events = true;
+#else
+		pr_err("cgroup tracking is not supported\n");
+		return -1;
+#endif
+	}
+
 	if (rec->opts.auxtrace_snapshot_mode || rec->switch_output.enabled) {
 		signal(SIGUSR2, snapshot_sig_handler);
 		if (rec->opts.auxtrace_snapshot_mode)
@@ -2358,6 +2372,8 @@ static struct option __record_options[] = {
 			"per thread proc mmap processing timeout in ms"),
 	OPT_BOOLEAN(0, "namespaces", &record.opts.record_namespaces,
 		    "Record namespaces events"),
+	OPT_BOOLEAN(0, "all-cgroups", &record.opts.record_cgroup,
+		    "Record cgroup 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,

tools/perf/builtin-report.c

@@ -635,7 +635,7 @@ static int report__browse_hists(struct report *rep)
 		 * Usually "ret" is the last pressed key, and we only
 		 * care if the key notifies us to switch data file.
 		 */
-		if (ret != K_SWITCH_INPUT_DATA)
+		if (ret != K_SWITCH_INPUT_DATA && ret != K_RELOAD)
 			ret = 0;
 		break;
 	case 2:
@@ -1105,6 +1105,7 @@ int cmd_report(int argc, const char **argv)
 			.mmap2		 = perf_event__process_mmap2,
 			.comm		 = perf_event__process_comm,
 			.namespaces	 = perf_event__process_namespaces,
+			.cgroup		 = perf_event__process_cgroup,
 			.exit		 = perf_event__process_exit,
 			.fork		 = perf_event__process_fork,
 			.lost		 = perf_event__process_lost,
@@ -1227,6 +1228,10 @@ int cmd_report(int argc, const char **argv)
 		    "Show a column with the sum of periods"),
 	OPT_BOOLEAN_SET(0, "group", &symbol_conf.event_group, &report.group_set,
 		    "Show event group information together"),
+	OPT_INTEGER(0, "group-sort-idx", &symbol_conf.group_sort_idx,
+		    "Sort the output by the event at the index n in group. "
+		    "If n is invalid, sort by the first event. "
+		    "WARNING: should be used on grouped events."),
 	OPT_CALLBACK_NOOPT('b', "branch-stack", &branch_mode, "",
 		    "use branch records for per branch histogram filling",
 		    parse_branch_mode),
@@ -1369,6 +1374,12 @@ repeat:
 
 	setup_forced_leader(&report, session->evlist);
 
+	if (symbol_conf.group_sort_idx && !session->evlist->nr_groups) {
+		parse_options_usage(NULL, options, "group-sort-idx", 0);
+		ret = -EINVAL;
+		goto error;
+	}
+
 	if (itrace_synth_opts.last_branch)
 		has_br_stack = true;
 
@@ -1470,7 +1481,7 @@ repeat:
 		sort_order = sort_tmp;
 	}
 
-	if ((last_key != K_SWITCH_INPUT_DATA) &&
+	if ((last_key != K_SWITCH_INPUT_DATA && last_key != K_RELOAD) &&
 	    (setup_sorting(session->evlist) < 0)) {
 		if (sort_order)
 			parse_options_usage(report_usage, options, "s", 1);
@@ -1549,7 +1560,7 @@ repeat:
 	sort__setup_elide(stdout);
 
 	ret = __cmd_report(&report);
-	if (ret == K_SWITCH_INPUT_DATA) {
+	if (ret == K_SWITCH_INPUT_DATA || ret == K_RELOAD) {
 		perf_session__delete(session);
 		last_key = K_SWITCH_INPUT_DATA;
 		goto repeat;

tools/perf/builtin-script.c

@@ -63,7 +63,9 @@
 static char const		*script_name;
 static char const		*generate_script_lang;
 static bool			reltime;
+static bool			deltatime;
 static u64			initial_time;
+static u64			previous_time;
 static bool			debug_mode;
 static u64			last_timestamp;
 static u64			nr_unordered;
@@ -704,6 +706,13 @@ static int perf_sample__fprintf_start(struct perf_sample *sample,
 			if (!initial_time)
 				initial_time = sample->time;
 			t = sample->time - initial_time;
+		} else if (deltatime) {
+			if (previous_time)
+				t = sample->time - previous_time;
+			else {
+				t = 0;
+			}
+			previous_time = sample->time;
 		}
 		nsecs = t;
 		secs = nsecs / NSEC_PER_SEC;
@@ -1685,6 +1694,7 @@ struct perf_script {
 	bool			show_lost_events;
 	bool			show_round_events;
 	bool			show_bpf_events;
+	bool			show_cgroup_events;
 	bool			allocated;
 	bool			per_event_dump;
 	struct evswitch		evswitch;
@@ -2203,6 +2213,41 @@ out:
 	return ret;
 }
 
+static int process_cgroup_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 evsel *evsel = perf_evlist__id2evsel(session->evlist, sample->id);
+	int ret = -1;
+
+	thread = machine__findnew_thread(machine, sample->pid, sample->tid);
+	if (thread == NULL) {
+		pr_debug("problem processing CGROUP event, skipping it.\n");
+		return -1;
+	}
+
+	if (perf_event__process_cgroup(tool, event, sample, machine) < 0)
+		goto out;
+
+	if (!evsel->core.attr.sample_id_all) {
+		sample->cpu = 0;
+		sample->time = 0;
+	}
+	if (!filter_cpu(sample)) {
+		perf_sample__fprintf_start(sample, thread, evsel,
+					   PERF_RECORD_CGROUP, stdout);
+		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,
@@ -2542,6 +2587,8 @@ static int __cmd_script(struct perf_script *script)
 		script->tool.context_switch = process_switch_event;
 	if (script->show_namespace_events)
 		script->tool.namespaces = process_namespaces_event;
+	if (script->show_cgroup_events)
+		script->tool.cgroup = process_cgroup_event;
 	if (script->show_lost_events)
 		script->tool.lost = process_lost_event;
 	if (script->show_round_events) {
@@ -3218,10 +3265,10 @@ static char *get_script_path(const char *script_root, const char *suffix)
 			__script_root = get_script_root(script_dirent, suffix);
 			if (__script_root && !strcmp(script_root, __script_root)) {
 				free(__script_root);
-				closedir(lang_dir);
 				closedir(scripts_dir);
 				scnprintf(script_path, MAXPATHLEN, "%s/%s",
 					  lang_path, script_dirent->d_name);
+				closedir(lang_dir);
 				return strdup(script_path);
 			}
 			free(__script_root);
@@ -3467,6 +3514,7 @@ int cmd_script(int argc, const char **argv)
 			.mmap2		 = perf_event__process_mmap2,
 			.comm		 = perf_event__process_comm,
 			.namespaces	 = perf_event__process_namespaces,
+			.cgroup		 = perf_event__process_cgroup,
 			.exit		 = perf_event__process_exit,
 			.fork		 = perf_event__process_fork,
 			.attr		 = process_attr,
@@ -3555,6 +3603,7 @@ int cmd_script(int argc, const char **argv)
 		     "anything beyond the specified depth will be ignored. "
 		     "Default: kernel.perf_event_max_stack or " __stringify(PERF_MAX_STACK_DEPTH)),
 	OPT_BOOLEAN(0, "reltime", &reltime, "Show time stamps relative to start"),
+	OPT_BOOLEAN(0, "deltatime", &deltatime, "Show time stamps relative to previous event"),
 	OPT_BOOLEAN('I', "show-info", &show_full_info,
 		    "display extended information from perf.data file"),
 	OPT_BOOLEAN('\0', "show-kernel-path", &symbol_conf.show_kernel_path,
@@ -3567,6 +3616,8 @@ int cmd_script(int argc, const char **argv)
 		    "Show context switch events (if recorded)"),
 	OPT_BOOLEAN('\0', "show-namespace-events", &script.show_namespace_events,
 		    "Show namespace events (if recorded)"),
+	OPT_BOOLEAN('\0', "show-cgroup-events", &script.show_cgroup_events,
+		    "Show cgroup events (if recorded)"),
 	OPT_BOOLEAN('\0', "show-lost-events", &script.show_lost_events,
 		    "Show lost events (if recorded)"),
 	OPT_BOOLEAN('\0', "show-round-events", &script.show_round_events,
@@ -3651,6 +3702,13 @@ int cmd_script(int argc, const char **argv)
 		}
 	}
 
+	if (reltime && deltatime) {
+		fprintf(stderr,
+			"reltime and deltatime - the two don't get along well. "
+			"Please limit to --reltime or --deltatime.\n");
+		return -1;
+	}
+
 	if (itrace_synth_opts.callchain &&
 	    itrace_synth_opts.callchain_sz > scripting_max_stack)
 		scripting_max_stack = itrace_synth_opts.callchain_sz;

tools/perf/builtin-top.c

@@ -616,6 +616,7 @@ static void *display_thread_tui(void *arg)
 		.arg		= top,
 		.refresh	= top->delay_secs,
 	};
+	int ret;
 
 	/* In order to read symbols from other namespaces perf to  needs to call
 	 * setns(2).  This isn't permitted if the struct_fs has multiple users.
@@ -626,6 +627,7 @@ static void *display_thread_tui(void *arg)
 
 	prctl(PR_SET_NAME, "perf-top-UI", 0, 0, 0);
 
+repeat:
 	perf_top__sort_new_samples(top);
 
 	/*
@@ -638,13 +640,18 @@ static void *display_thread_tui(void *arg)
 		hists->uid_filter_str = top->record_opts.target.uid_str;
 	}
 
-	perf_evlist__tui_browse_hists(top->evlist, help, &hbt,
+	ret = perf_evlist__tui_browse_hists(top->evlist, help, &hbt,
 				      top->min_percent,
 				      &top->session->header.env,
 				      !top->record_opts.overwrite,
 				      &top->annotation_opts);
 
-	stop_top();
+	if (ret == K_RELOAD) {
+		top->zero = true;
+		goto repeat;
+	} else
+		stop_top();
+
 	return NULL;
 }
 
@@ -1246,6 +1253,14 @@ static int __cmd_top(struct perf_top *top)
 
 	if (opts->record_namespaces)
 		top->tool.namespace_events = true;
+	if (opts->record_cgroup) {
+#ifdef HAVE_FILE_HANDLE
+		top->tool.cgroup_events = true;
+#else
+		pr_err("cgroup tracking is not supported.\n");
+		return -1;
+#endif
+	}
 
 	ret = perf_event__synthesize_bpf_events(top->session, perf_event__process,
 						&top->session->machines.host,
@@ -1253,6 +1268,11 @@ static int __cmd_top(struct perf_top *top)
 	if (ret < 0)
 		pr_debug("Couldn't synthesize BPF events: Pre-existing BPF programs won't have symbols resolved.\n");
 
+	ret = perf_event__synthesize_cgroups(&top->tool, perf_event__process,
+					     &top->session->machines.host);
+	if (ret < 0)
+		pr_debug("Couldn't synthesize cgroup events.\n");
+
 	machine__synthesize_threads(&top->session->machines.host, &opts->target,
 				    top->evlist->core.threads, false,
 				    top->nr_threads_synthesize);
@@ -1545,6 +1565,12 @@ int cmd_top(int argc, const char **argv)
 			"number of thread to run event synthesize"),
 	OPT_BOOLEAN(0, "namespaces", &opts->record_namespaces,
 		    "Record namespaces events"),
+	OPT_BOOLEAN(0, "all-cgroups", &opts->record_cgroup,
+		    "Record cgroup events"),
+	OPT_INTEGER(0, "group-sort-idx", &symbol_conf.group_sort_idx,
+		    "Sort the output by the event at the index n in group. "
+		    "If n is invalid, sort by the first event. "
+		    "WARNING: should be used on grouped events."),
 	OPTS_EVSWITCH(&top.evswitch),
 	OPT_END()
 	};

tools/perf/pmu-events/arch/test/test_cpu/other.json

@@ -0,0 +1,26 @@
+[
+    {
+        "EventCode": "0x6",
+        "Counter": "0,1",
+        "UMask": "0x80",
+        "EventName": "SEGMENT_REG_LOADS.ANY",
+        "SampleAfterValue": "200000",
+        "BriefDescription": "Number of segment register loads."
+    },
+    {
+        "EventCode": "0x9",
+        "Counter": "0,1",
+        "UMask": "0x20",
+        "EventName": "DISPATCH_BLOCKED.ANY",
+        "SampleAfterValue": "200000",
+        "BriefDescription": "Memory cluster signals to block micro-op dispatch for any reason"
+    },
+    {
+        "EventCode": "0x3A",
+        "Counter": "0,1",
+        "UMask": "0x0",
+        "EventName": "EIST_TRANS",
+        "SampleAfterValue": "200000",
+        "BriefDescription": "Number of Enhanced Intel SpeedStep(R) Technology (EIST) transitions"
+    }
+]

tools/perf/pmu-events/arch/test/test_cpu/uncore.json

@@ -0,0 +1,21 @@
+[
+ {
+	    "EventCode": "0x02",
+	    "EventName": "uncore_hisi_ddrc.flux_wcmd",
+	    "BriefDescription": "DDRC write commands",
+	    "PublicDescription": "DDRC write commands",
+	    "Unit": "hisi_sccl,ddrc"
+   },
+   {
+	    "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"
+  }
+]

tools/perf/pmu-events/arch/x86/amdfam17h/cache.json

@@ -1,329 +0,0 @@
-[
-  {
-    "EventName": "ic_fw32",
-    "EventCode": "0x80",
-    "BriefDescription": "The number of 32B fetch windows transferred from IC pipe to DE instruction decoder (includes non-cacheable and cacheable fill responses)."
-  },
-  {
-    "EventName": "ic_fw32_miss",
-    "EventCode": "0x81",
-    "BriefDescription": "The number of 32B fetch windows tried to read the L1 IC and missed in the full tag."
-  },
-  {
-    "EventName": "ic_cache_fill_l2",
-    "EventCode": "0x82",
-    "BriefDescription": "The number of 64 byte instruction cache line was fulfilled from the L2 cache."
-  },
-  {
-    "EventName": "ic_cache_fill_sys",
-    "EventCode": "0x83",
-    "BriefDescription": "The number of 64 byte instruction cache line fulfilled from system memory or another cache."
-  },
-  {
-    "EventName": "bp_l1_tlb_miss_l2_hit",
-    "EventCode": "0x84",
-    "BriefDescription": "The number of instruction fetches that miss in the L1 ITLB but hit in the L2 ITLB."
-  },
-  {
-    "EventName": "bp_l1_tlb_miss_l2_miss",
-    "EventCode": "0x85",
-    "BriefDescription": "The number of instruction fetches that miss in both the L1 and L2 TLBs."
-  },
-  {
-    "EventName": "bp_snp_re_sync",
-    "EventCode": "0x86",
-    "BriefDescription": "The number of pipeline restarts caused by invalidating probes that hit on the instruction stream currently being executed. This would happen if the active instruction stream was being modified by another processor in an MP system - typically a highly unlikely event."
-  },
-  {
-    "EventName": "ic_fetch_stall.ic_stall_any",
-    "EventCode": "0x87",
-    "BriefDescription": "IC pipe was stalled during this clock cycle for any reason (nothing valid in pipe ICM1).",
-    "PublicDescription": "Instruction Pipe Stall. IC pipe was stalled during this clock cycle for any reason (nothing valid in pipe ICM1).",
-    "UMask": "0x4"
-  },
-  {
-    "EventName": "ic_fetch_stall.ic_stall_dq_empty",
-    "EventCode": "0x87",
-    "BriefDescription": "IC pipe was stalled during this clock cycle (including IC to OC fetches) due to DQ empty.",
-    "PublicDescription": "Instruction Pipe Stall. IC pipe was stalled during this clock cycle (including IC to OC fetches) due to DQ empty.",
-    "UMask": "0x2"
-  },
-  {
-    "EventName": "ic_fetch_stall.ic_stall_back_pressure",
-    "EventCode": "0x87",
-    "BriefDescription": "IC pipe was stalled during this clock cycle (including IC to OC fetches) due to back-pressure.",
-    "PublicDescription": "Instruction Pipe Stall. IC pipe was stalled during this clock cycle (including IC to OC fetches) due to back-pressure.",
-    "UMask": "0x1"
-  },
-  {
-    "EventName": "ic_cache_inval.l2_invalidating_probe",
-    "EventCode": "0x8c",
-    "BriefDescription": "IC line invalidated due to L2 invalidating probe (external or LS).",
-    "PublicDescription": "The number of instruction cache lines invalidated. A non-SMC event is CMC (cross modifying code), either from the other thread of the core or another core. IC line invalidated due to L2 invalidating probe (external or LS).",
-    "UMask": "0x2"
-  },
-  {
-    "EventName": "ic_cache_inval.fill_invalidated",
-    "EventCode": "0x8c",
-    "BriefDescription": "IC line invalidated due to overwriting fill response.",
-    "PublicDescription": "The number of instruction cache lines invalidated. A non-SMC event is CMC (cross modifying code), either from the other thread of the core or another core. IC line invalidated due to overwriting fill response.",
-    "UMask": "0x1"
-  },
-  {
-    "EventName": "bp_tlb_rel",
-    "EventCode": "0x99",
-    "BriefDescription": "The number of ITLB reload requests."
-  },
-  {
-    "EventName": "l2_request_g1.rd_blk_l",
-    "EventCode": "0x60",
-    "BriefDescription": "Requests to L2 Group1.",
-    "PublicDescription": "Requests to L2 Group1.",
-    "UMask": "0x80"
-  },
-  {
-    "EventName": "l2_request_g1.rd_blk_x",
-    "EventCode": "0x60",
-    "BriefDescription": "Requests to L2 Group1.",
-    "PublicDescription": "Requests to L2 Group1.",
-    "UMask": "0x40"
-  },
-  {
-    "EventName": "l2_request_g1.ls_rd_blk_c_s",
-    "EventCode": "0x60",
-    "BriefDescription": "Requests to L2 Group1.",
-    "PublicDescription": "Requests to L2 Group1.",
-    "UMask": "0x20"
-  },
-  {
-    "EventName": "l2_request_g1.cacheable_ic_read",
-    "EventCode": "0x60",
-    "BriefDescription": "Requests to L2 Group1.",
-    "PublicDescription": "Requests to L2 Group1.",
-    "UMask": "0x10"
-  },
-  {
-    "EventName": "l2_request_g1.change_to_x",
-    "EventCode": "0x60",
-    "BriefDescription": "Requests to L2 Group1.",
-    "PublicDescription": "Requests to L2 Group1.",
-    "UMask": "0x8"
-  },
-  {
-    "EventName": "l2_request_g1.prefetch_l2",
-    "EventCode": "0x60",
-    "BriefDescription": "Requests to L2 Group1.",
-    "PublicDescription": "Requests to L2 Group1.",
-    "UMask": "0x4"
-  },
-  {
-    "EventName": "l2_request_g1.l2_hw_pf",
-    "EventCode": "0x60",
-    "BriefDescription": "Requests to L2 Group1.",
-    "PublicDescription": "Requests to L2 Group1.",
-    "UMask": "0x2"
-  },
-  {
-    "EventName": "l2_request_g1.other_requests",
-    "EventCode": "0x60",
-    "BriefDescription": "Events covered by l2_request_g2.",
-    "PublicDescription": "Requests to L2 Group1. Events covered by l2_request_g2.",
-    "UMask": "0x1"
-  },
-  {
-    "EventName": "l2_request_g2.group1",
-    "EventCode": "0x61",
-    "BriefDescription": "All Group 1 commands not in unit0.",
-    "PublicDescription": "Multi-events in that LS and IF requests can be received simultaneous. All Group 1 commands not in unit0.",
-    "UMask": "0x80"
-  },
-  {
-    "EventName": "l2_request_g2.ls_rd_sized",
-    "EventCode": "0x61",
-    "BriefDescription": "RdSized, RdSized32, RdSized64.",
-    "PublicDescription": "Multi-events in that LS and IF requests can be received simultaneous. RdSized, RdSized32, RdSized64.",
-    "UMask": "0x40"
-  },
-  {
-    "EventName": "l2_request_g2.ls_rd_sized_nc",
-    "EventCode": "0x61",
-    "BriefDescription": "RdSizedNC, RdSized32NC, RdSized64NC.",
-    "PublicDescription": "Multi-events in that LS and IF requests can be received simultaneous. RdSizedNC, RdSized32NC, RdSized64NC.",
-    "UMask": "0x20"
-  },
-  {
-    "EventName": "l2_request_g2.ic_rd_sized",
-    "EventCode": "0x61",
-    "BriefDescription": "Multi-events in that LS and IF requests can be received simultaneous.",
-    "PublicDescription": "Multi-events in that LS and IF requests can be received simultaneous.",
-    "UMask": "0x10"
-  },
-  {
-    "EventName": "l2_request_g2.ic_rd_sized_nc",
-    "EventCode": "0x61",
-    "BriefDescription": "Multi-events in that LS and IF requests can be received simultaneous.",
-    "PublicDescription": "Multi-events in that LS and IF requests can be received simultaneous.",
-    "UMask": "0x8"
-  },
-  {
-    "EventName": "l2_request_g2.smc_inval",
-    "EventCode": "0x61",
-    "BriefDescription": "Multi-events in that LS and IF requests can be received simultaneous.",
-    "PublicDescription": "Multi-events in that LS and IF requests can be received simultaneous.",
-    "UMask": "0x4"
-  },
-  {
-    "EventName": "l2_request_g2.bus_locks_originator",
-    "EventCode": "0x61",
-    "BriefDescription": "Multi-events in that LS and IF requests can be received simultaneous.",
-    "PublicDescription": "Multi-events in that LS and IF requests can be received simultaneous.",
-    "UMask": "0x2"
-  },
-  {
-    "EventName": "l2_request_g2.bus_locks_responses",
-    "EventCode": "0x61",
-    "BriefDescription": "Multi-events in that LS and IF requests can be received simultaneous.",
-    "PublicDescription": "Multi-events in that LS and IF requests can be received simultaneous.",
-    "UMask": "0x1"
-  },
-  {
-    "EventName": "l2_latency.l2_cycles_waiting_on_fills",
-    "EventCode": "0x62",
-    "BriefDescription": "Total cycles spent waiting for L2 fills to complete from L3 or memory, divided by four. Event counts are for both threads. To calculate average latency, the number of fills from both threads must be used.",
-    "PublicDescription": "Total cycles spent waiting for L2 fills to complete from L3 or memory, divided by four. Event counts are for both threads. To calculate average latency, the number of fills from both threads must be used.",
-    "UMask": "0x1"
-  },
-  {
-    "EventName": "l2_wcb_req.wcb_write",
-    "EventCode": "0x63",
-    "PublicDescription": "LS (Load/Store unit) to L2 WCB (Write Combining Buffer) write requests.",
-    "BriefDescription": "LS to L2 WCB write requests.",
-    "UMask": "0x40"
-  },
-  {
-    "EventName": "l2_wcb_req.wcb_close",
-    "EventCode": "0x63",
-    "BriefDescription": "LS to L2 WCB close requests.",
-    "PublicDescription": "LS (Load/Store unit) to L2 WCB (Write Combining Buffer) close requests.",
-    "UMask": "0x20"
-  },
-  {
-    "EventName": "l2_wcb_req.zero_byte_store",
-    "EventCode": "0x63",
-    "BriefDescription": "LS to L2 WCB zero byte store requests.",
-    "PublicDescription": "LS (Load/Store unit) to L2 WCB (Write Combining Buffer) zero byte store requests.",
-    "UMask": "0x4"
-  },
-  {
-    "EventName": "l2_wcb_req.cl_zero",
-    "EventCode": "0x63",
-    "PublicDescription": "LS to L2 WCB cache line zeroing requests.",
-    "BriefDescription": "LS (Load/Store unit) to L2 WCB (Write Combining Buffer) cache line zeroing requests.",
-    "UMask": "0x1"
-  },
-  {
-    "EventName": "l2_cache_req_stat.ls_rd_blk_cs",
-    "EventCode": "0x64",
-    "BriefDescription": "LS ReadBlock C/S Hit.",
-    "PublicDescription": "This event does not count accesses to the L2 cache by the L2 prefetcher, but it does count accesses by the L1 prefetcher. LS ReadBlock C/S Hit.",
-    "UMask": "0x80"
-  },
-  {
-    "EventName": "l2_cache_req_stat.ls_rd_blk_l_hit_x",
-    "EventCode": "0x64",
-    "BriefDescription": "LS Read Block L Hit X.",
-    "PublicDescription": "This event does not count accesses to the L2 cache by the L2 prefetcher, but it does count accesses by the L1 prefetcher. LS Read Block L Hit X.",
-    "UMask": "0x40"
-  },
-  {
-    "EventName": "l2_cache_req_stat.ls_rd_blk_l_hit_s",
-    "EventCode": "0x64",
-    "BriefDescription": "LsRdBlkL Hit Shared.",
-    "PublicDescription": "This event does not count accesses to the L2 cache by the L2 prefetcher, but it does count accesses by the L1 prefetcher. LsRdBlkL Hit Shared.",
-    "UMask": "0x20"
-  },
-  {
-    "EventName": "l2_cache_req_stat.ls_rd_blk_x",
-    "EventCode": "0x64",
-    "BriefDescription": "LsRdBlkX/ChgToX Hit X.  Count RdBlkX finding Shared as a Miss.",
-    "PublicDescription": "This event does not count accesses to the L2 cache by the L2 prefetcher, but it does count accesses by the L1 prefetcher. LsRdBlkX/ChgToX Hit X.  Count RdBlkX finding Shared as a Miss.",
-    "UMask": "0x10"
-  },
-  {
-    "EventName": "l2_cache_req_stat.ls_rd_blk_c",
-    "EventCode": "0x64",
-    "BriefDescription": "LS Read Block C S L X Change to X Miss.",
-    "PublicDescription": "This event does not count accesses to the L2 cache by the L2 prefetcher, but it does count accesses by the L1 prefetcher. LS Read Block C S L X Change to X Miss.",
-    "UMask": "0x8"
-  },
-  {
-    "EventName": "l2_cache_req_stat.ic_fill_hit_x",
-    "EventCode": "0x64",
-    "BriefDescription": "IC Fill Hit Exclusive Stale.",
-    "PublicDescription": "This event does not count accesses to the L2 cache by the L2 prefetcher, but it does count accesses by the L1 prefetcher. IC Fill Hit Exclusive Stale.",
-    "UMask": "0x4"
-  },
-  {
-    "EventName": "l2_cache_req_stat.ic_fill_hit_s",
-    "EventCode": "0x64",
-    "BriefDescription": "IC Fill Hit Shared.",
-    "PublicDescription": "This event does not count accesses to the L2 cache by the L2 prefetcher, but it does count accesses by the L1 prefetcher. IC Fill Hit Shared.",
-    "UMask": "0x2"
-  },
-  {
-    "EventName": "l2_cache_req_stat.ic_fill_miss",
-    "EventCode": "0x64",
-    "BriefDescription": "IC Fill Miss.",
-    "PublicDescription": "This event does not count accesses to the L2 cache by the L2 prefetcher, but it does count accesses by the L1 prefetcher. IC Fill Miss.",
-    "UMask": "0x1"
-  },
-  {
-    "EventName": "l2_fill_pending.l2_fill_busy",
-    "EventCode": "0x6d",
-    "BriefDescription": "Total cycles spent with one or more fill requests in flight from L2.",
-    "PublicDescription": "Total cycles spent with one or more fill requests in flight from L2.",
-    "UMask": "0x1"
-  },
-  {
-    "EventName": "l3_request_g1.caching_l3_cache_accesses",
-    "EventCode": "0x01",
-    "BriefDescription": "Caching: L3 cache accesses",
-    "UMask": "0x80",
-    "Unit": "L3PMC"
-  },
-  {
-    "EventName": "l3_lookup_state.all_l3_req_typs",
-    "EventCode": "0x04",
-    "BriefDescription": "All L3 Request Types",
-    "UMask": "0xff",
-    "Unit": "L3PMC"
-  },
-  {
-    "EventName": "l3_comb_clstr_state.other_l3_miss_typs",
-    "EventCode": "0x06",
-    "BriefDescription": "Other L3 Miss Request Types",
-    "UMask": "0xfe",
-    "Unit": "L3PMC"
-  },
-  {
-    "EventName": "l3_comb_clstr_state.request_miss",
-    "EventCode": "0x06",
-    "BriefDescription": "L3 cache misses",
-    "UMask": "0x01",
-    "Unit": "L3PMC"
-  },
-  {
-    "EventName": "xi_sys_fill_latency",
-    "EventCode": "0x90",
-    "BriefDescription": "L3 Cache Miss Latency. Total cycles for all transactions divided by 16. Ignores SliceMask and ThreadMask.",
-    "UMask": "0x00",
-    "Unit": "L3PMC"
-  },
-  {
-    "EventName": "xi_ccx_sdp_req1.all_l3_miss_req_typs",
-    "EventCode": "0x9a",
-    "BriefDescription": "All L3 Miss Request Types. Ignores SliceMask and ThreadMask.",
-    "UMask": "0x3f",
-    "Unit": "L3PMC"
-  }
-]

tools/perf/pmu-events/arch/x86/amdfam17h/other.json

@@ -1,65 +0,0 @@
-[
-  {
-    "EventName": "ic_oc_mode_switch.oc_ic_mode_switch",
-    "EventCode": "0x28a",
-    "BriefDescription": "OC to IC mode switch.",
-    "PublicDescription": "OC Mode Switch. OC to IC mode switch.",
-    "UMask": "0x2"
-  },
-  {
-    "EventName": "ic_oc_mode_switch.ic_oc_mode_switch",
-    "EventCode": "0x28a",
-    "BriefDescription": "IC to OC mode switch.",
-    "PublicDescription": "OC Mode Switch. IC to OC mode switch.",
-    "UMask": "0x1"
-  },
-  {
-    "EventName": "de_dis_dispatch_token_stalls0.retire_token_stall",
-    "EventCode": "0xaf",
-    "BriefDescription": "RETIRE Tokens unavailable.",
-    "PublicDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall. RETIRE Tokens unavailable.",
-    "UMask": "0x40"
-  },
-  {
-    "EventName": "de_dis_dispatch_token_stalls0.agsq_token_stall",
-    "EventCode": "0xaf",
-    "BriefDescription": "AGSQ Tokens unavailable.",
-    "PublicDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall. AGSQ Tokens unavailable.",
-    "UMask": "0x20"
-  },
-  {
-    "EventName": "de_dis_dispatch_token_stalls0.alu_token_stall",
-    "EventCode": "0xaf",
-    "BriefDescription": "ALU tokens total unavailable.",
-    "PublicDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall. ALU tokens total unavailable.",
-    "UMask": "0x10"
-  },
-  {
-    "EventName": "de_dis_dispatch_token_stalls0.alsq3_0_token_stall",
-    "EventCode": "0xaf",
-    "BriefDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall.",
-    "PublicDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall.",
-    "UMask": "0x8"
-  },
-  {
-    "EventName": "de_dis_dispatch_token_stalls0.alsq3_token_stall",
-    "EventCode": "0xaf",
-    "BriefDescription": "ALSQ 3 Tokens unavailable.",
-    "PublicDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall. ALSQ 3 Tokens unavailable.",
-    "UMask": "0x4"
-  },
-  {
-    "EventName": "de_dis_dispatch_token_stalls0.alsq2_token_stall",
-    "EventCode": "0xaf",
-    "BriefDescription": "ALSQ 2 Tokens unavailable.",
-    "PublicDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall. ALSQ 2 Tokens unavailable.",
-    "UMask": "0x2"
-  },
-  {
-    "EventName": "de_dis_dispatch_token_stalls0.alsq1_token_stall",
-    "EventCode": "0xaf",
-    "BriefDescription": "ALSQ 1 Tokens unavailable.",
-    "PublicDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall. ALSQ 1 Tokens unavailable.",
-    "UMask": "0x1"
-  }
-]

tools/perf/pmu-events/arch/x86/amdzen1/branch.json

@@ -0,0 +1,23 @@
+[
+  {
+    "EventName": "bp_l1_btb_correct",
+    "EventCode": "0x8a",
+    "BriefDescription": "L1 BTB Correction."
+  },
+  {
+    "EventName": "bp_l2_btb_correct",
+    "EventCode": "0x8b",
+    "BriefDescription": "L2 BTB Correction."
+  },
+  {
+    "EventName": "bp_dyn_ind_pred",
+    "EventCode": "0x8e",
+    "BriefDescription": "Dynamic Indirect Predictions.",
+    "PublicDescription": "Indirect Branch Prediction for potential multi-target branch (speculative)."
+  },
+  {
+    "EventName": "bp_de_redirect",
+    "EventCode": "0x91",
+    "BriefDescription": "Decoder Overrides Existing Branch Prediction (speculative)."
+  }
+]

tools/perf/pmu-events/arch/x86/amdzen1/cache.json

@@ -0,0 +1,294 @@
+[
+  {
+    "EventName": "ic_fw32",
+    "EventCode": "0x80",
+    "BriefDescription": "The number of 32B fetch windows transferred from IC pipe to DE instruction decoder (includes non-cacheable and cacheable fill responses)."
+  },
+  {
+    "EventName": "ic_fw32_miss",
+    "EventCode": "0x81",
+    "BriefDescription": "The number of 32B fetch windows tried to read the L1 IC and missed in the full tag."
+  },
+  {
+    "EventName": "ic_cache_fill_l2",
+    "EventCode": "0x82",
+    "BriefDescription": "The number of 64 byte instruction cache line was fulfilled from the L2 cache."
+  },
+  {
+    "EventName": "ic_cache_fill_sys",
+    "EventCode": "0x83",
+    "BriefDescription": "The number of 64 byte instruction cache line fulfilled from system memory or another cache."
+  },
+  {
+    "EventName": "bp_l1_tlb_miss_l2_hit",
+    "EventCode": "0x84",
+    "BriefDescription": "The number of instruction fetches that miss in the L1 ITLB but hit in the L2 ITLB."
+  },
+  {
+    "EventName": "bp_l1_tlb_miss_l2_miss",
+    "EventCode": "0x85",
+    "BriefDescription": "The number of instruction fetches that miss in both the L1 and L2 TLBs."
+  },
+  {
+    "EventName": "bp_snp_re_sync",
+    "EventCode": "0x86",
+    "BriefDescription": "The number of pipeline restarts caused by invalidating probes that hit on the instruction stream currently being executed. This would happen if the active instruction stream was being modified by another processor in an MP system - typically a highly unlikely event."
+  },
+  {
+    "EventName": "ic_fetch_stall.ic_stall_any",
+    "EventCode": "0x87",
+    "BriefDescription": "Instruction Pipe Stall. IC pipe was stalled during this clock cycle for any reason (nothing valid in pipe ICM1).",
+    "UMask": "0x4"
+  },
+  {
+    "EventName": "ic_fetch_stall.ic_stall_dq_empty",
+    "EventCode": "0x87",
+    "BriefDescription": "Instruction Pipe Stall. IC pipe was stalled during this clock cycle (including IC to OC fetches) due to DQ empty.",
+    "UMask": "0x2"
+  },
+  {
+    "EventName": "ic_fetch_stall.ic_stall_back_pressure",
+    "EventCode": "0x87",
+    "BriefDescription": "Instruction Pipe Stall. IC pipe was stalled during this clock cycle (including IC to OC fetches) due to back-pressure.",
+    "UMask": "0x1"
+  },
+  {
+    "EventName": "ic_cache_inval.l2_invalidating_probe",
+    "EventCode": "0x8c",
+    "BriefDescription": "IC line invalidated due to L2 invalidating probe (external or LS). The number of instruction cache lines invalidated. A non-SMC event is CMC (cross modifying code), either from the other thread of the core or another core.",
+    "UMask": "0x2"
+  },
+  {
+    "EventName": "ic_cache_inval.fill_invalidated",
+    "EventCode": "0x8c",
+    "BriefDescription": "IC line invalidated due to overwriting fill response. The number of instruction cache lines invalidated. A non-SMC event is CMC (cross modifying code), either from the other thread of the core or another core.",
+    "UMask": "0x1"
+  },
+  {
+    "EventName": "bp_tlb_rel",
+    "EventCode": "0x99",
+    "BriefDescription": "The number of ITLB reload requests."
+  },
+  {
+    "EventName": "l2_request_g1.rd_blk_l",
+    "EventCode": "0x60",
+    "BriefDescription": "All L2 Cache Requests (Breakdown 1 - Common). Data cache reads (including hardware and software prefetch).",
+    "UMask": "0x80"
+  },
+  {
+    "EventName": "l2_request_g1.rd_blk_x",
+    "EventCode": "0x60",
+    "BriefDescription": "All L2 Cache Requests (Breakdown 1 - Common). Data cache stores.",
+    "UMask": "0x40"
+  },
+  {
+    "EventName": "l2_request_g1.ls_rd_blk_c_s",
+    "EventCode": "0x60",
+    "BriefDescription": "All L2 Cache Requests (Breakdown 1 - Common). Data cache shared reads.",
+    "UMask": "0x20"
+  },
+  {
+    "EventName": "l2_request_g1.cacheable_ic_read",
+    "EventCode": "0x60",
+    "BriefDescription": "All L2 Cache Requests (Breakdown 1 - Common). Instruction cache reads.",
+    "UMask": "0x10"
+  },
+  {
+    "EventName": "l2_request_g1.change_to_x",
+    "EventCode": "0x60",
+    "BriefDescription": "All L2 Cache Requests (Breakdown 1 - Common). Data cache state change requests. Request change to writable, check L2 for current state.",
+    "UMask": "0x8"
+  },
+  {
+    "EventName": "l2_request_g1.prefetch_l2_cmd",
+    "EventCode": "0x60",
+    "BriefDescription": "All L2 Cache Requests (Breakdown 1 - Common). PrefetchL2Cmd.",
+    "UMask": "0x4"
+  },
+  {
+    "EventName": "l2_request_g1.l2_hw_pf",
+    "EventCode": "0x60",
+    "BriefDescription": "All L2 Cache Requests (Breakdown 1 - Common). L2 Prefetcher. All prefetches accepted by L2 pipeline, hit or miss. Types of PF and L2 hit/miss broken out in a separate perfmon event.",
+    "UMask": "0x2"
+  },
+  {
+    "EventName": "l2_request_g1.group2",
+    "EventCode": "0x60",
+    "BriefDescription": "Miscellaneous events covered in more detail by l2_request_g2 (PMCx061).",
+    "UMask": "0x1"
+  },
+  {
+    "EventName": "l2_request_g2.group1",
+    "EventCode": "0x61",
+    "BriefDescription": "Miscellaneous events covered in more detail by l2_request_g1 (PMCx060).",
+    "UMask": "0x80"
+  },
+  {
+    "EventName": "l2_request_g2.ls_rd_sized",
+    "EventCode": "0x61",
+    "BriefDescription": "All L2 Cache Requests (Breakdown 2 - Rare). Data cache read sized.",
+    "UMask": "0x40"
+  },
+  {
+    "EventName": "l2_request_g2.ls_rd_sized_nc",
+    "EventCode": "0x61",
+    "BriefDescription": "All L2 Cache Requests (Breakdown 2 - Rare). Data cache read sized non-cacheable.",
+    "UMask": "0x20"
+  },
+  {
+    "EventName": "l2_request_g2.ic_rd_sized",
+    "EventCode": "0x61",
+    "BriefDescription": "All L2 Cache Requests (Breakdown 2 - Rare). Instruction cache read sized.",
+    "UMask": "0x10"
+  },
+  {
+    "EventName": "l2_request_g2.ic_rd_sized_nc",
+    "EventCode": "0x61",
+    "BriefDescription": "All L2 Cache Requests (Breakdown 2 - Rare). Instruction cache read sized non-cacheable.",
+    "UMask": "0x8"
+  },
+  {
+    "EventName": "l2_request_g2.smc_inval",
+    "EventCode": "0x61",
+    "BriefDescription": "All L2 Cache Requests (Breakdown 2 - Rare). Self-modifying code invalidates.",
+    "UMask": "0x4"
+  },
+  {
+    "EventName": "l2_request_g2.bus_locks_originator",
+    "EventCode": "0x61",
+    "BriefDescription": "All L2 Cache Requests (Breakdown 2 - Rare). Bus locks.",
+    "UMask": "0x2"
+  },
+  {
+    "EventName": "l2_request_g2.bus_locks_responses",
+    "EventCode": "0x61",
+    "BriefDescription": "All L2 Cache Requests (Breakdown 2 - Rare). Bus lock response.",
+    "UMask": "0x1"
+  },
+  {
+    "EventName": "l2_latency.l2_cycles_waiting_on_fills",
+    "EventCode": "0x62",
+    "BriefDescription": "Total cycles spent waiting for L2 fills to complete from L3 or memory, divided by four. Event counts are for both threads. To calculate average latency, the number of fills from both threads must be used.",
+    "UMask": "0x1"
+  },
+  {
+    "EventName": "l2_wcb_req.wcb_write",
+    "EventCode": "0x63",
+    "BriefDescription": "LS to L2 WCB write requests. LS (Load/Store unit) to L2 WCB (Write Combining Buffer) write requests.",
+    "UMask": "0x40"
+  },
+  {
+    "EventName": "l2_wcb_req.wcb_close",
+    "EventCode": "0x63",
+    "BriefDescription": "LS to L2 WCB close requests. LS (Load/Store unit) to L2 WCB (Write Combining Buffer) close requests.",
+    "UMask": "0x20"
+  },
+  {
+    "EventName": "l2_wcb_req.zero_byte_store",
+    "EventCode": "0x63",
+    "BriefDescription": "LS to L2 WCB zero byte store requests. LS (Load/Store unit) to L2 WCB (Write Combining Buffer) zero byte store requests.",
+    "UMask": "0x4"
+  },
+  {
+    "EventName": "l2_wcb_req.cl_zero",
+    "EventCode": "0x63",
+    "BriefDescription": "LS to L2 WCB cache line zeroing requests. LS (Load/Store unit) to L2 WCB (Write Combining Buffer) cache line zeroing requests.",
+    "UMask": "0x1"
+  },
+  {
+    "EventName": "l2_cache_req_stat.ls_rd_blk_cs",
+    "EventCode": "0x64",
+    "BriefDescription": "Core to L2 cacheable request access status (not including L2 Prefetch). Data cache shared read hit in L2",
+    "UMask": "0x80"
+  },
+  {
+    "EventName": "l2_cache_req_stat.ls_rd_blk_l_hit_x",
+    "EventCode": "0x64",
+    "BriefDescription": "Core to L2 cacheable request access status (not including L2 Prefetch). Data cache read hit in L2.",
+    "UMask": "0x40"
+  },
+  {
+    "EventName": "l2_cache_req_stat.ls_rd_blk_l_hit_s",
+    "EventCode": "0x64",
+    "BriefDescription": "Core to L2 cacheable request access status (not including L2 Prefetch). Data cache read hit on shared line in L2.",
+    "UMask": "0x20"
+  },
+  {
+    "EventName": "l2_cache_req_stat.ls_rd_blk_x",
+    "EventCode": "0x64",
+    "BriefDescription": "Core to L2 cacheable request access status (not including L2 Prefetch). Data cache store or state change hit in L2.",
+    "UMask": "0x10"
+  },
+  {
+    "EventName": "l2_cache_req_stat.ls_rd_blk_c",
+    "EventCode": "0x64",
+    "BriefDescription": "Core to L2 cacheable request access status (not including L2 Prefetch). Data cache request miss in L2 (all types).",
+    "UMask": "0x8"
+  },
+  {
+    "EventName": "l2_cache_req_stat.ic_fill_hit_x",
+    "EventCode": "0x64",
+    "BriefDescription": "Core to L2 cacheable request access status (not including L2 Prefetch). Instruction cache hit modifiable line in L2.",
+    "UMask": "0x4"
+  },
+  {
+    "EventName": "l2_cache_req_stat.ic_fill_hit_s",
+    "EventCode": "0x64",
+    "BriefDescription": "Core to L2 cacheable request access status (not including L2 Prefetch). Instruction cache hit clean line in L2.",
+    "UMask": "0x2"
+  },
+  {
+    "EventName": "l2_cache_req_stat.ic_fill_miss",
+    "EventCode": "0x64",
+    "BriefDescription": "Core to L2 cacheable request access status (not including L2 Prefetch). Instruction cache request miss in L2.",
+    "UMask": "0x1"
+  },
+  {
+    "EventName": "l2_fill_pending.l2_fill_busy",
+    "EventCode": "0x6d",
+    "BriefDescription": "Cycles with fill pending from L2. Total cycles spent with one or more fill requests in flight from L2.",
+    "UMask": "0x1"
+  },
+  {
+    "EventName": "l3_request_g1.caching_l3_cache_accesses",
+    "EventCode": "0x01",
+    "BriefDescription": "Caching: L3 cache accesses",
+    "UMask": "0x80",
+    "Unit": "L3PMC"
+  },
+  {
+    "EventName": "l3_lookup_state.all_l3_req_typs",
+    "EventCode": "0x04",
+    "BriefDescription": "All L3 Request Types",
+    "UMask": "0xff",
+    "Unit": "L3PMC"
+  },
+  {
+    "EventName": "l3_comb_clstr_state.other_l3_miss_typs",
+    "EventCode": "0x06",
+    "BriefDescription": "Other L3 Miss Request Types",
+    "UMask": "0xfe",
+    "Unit": "L3PMC"
+  },
+  {
+    "EventName": "l3_comb_clstr_state.request_miss",
+    "EventCode": "0x06",
+    "BriefDescription": "L3 cache misses",
+    "UMask": "0x01",
+    "Unit": "L3PMC"
+  },
+  {
+    "EventName": "xi_sys_fill_latency",
+    "EventCode": "0x90",
+    "BriefDescription": "L3 Cache Miss Latency. Total cycles for all transactions divided by 16. Ignores SliceMask and ThreadMask.",
+    "UMask": "0x00",
+    "Unit": "L3PMC"
+  },
+  {
+    "EventName": "xi_ccx_sdp_req1.all_l3_miss_req_typs",
+    "EventCode": "0x9a",
+    "BriefDescription": "All L3 Miss Request Types. Ignores SliceMask and ThreadMask.",
+    "UMask": "0x3f",
+    "Unit": "L3PMC"
+  }
+]

tools/perf/pmu-events/arch/x86/amdzen1/core.json

@@ -62,7 +62,6 @@
     "EventName": "ex_ret_brn_ind_misp",
     "EventCode": "0xca",
     "BriefDescription": "Retired Indirect Branch Instructions Mispredicted.",
-    "PublicDescription": "Retired Indirect Branch Instructions Mispredicted."
   },
   {
     "EventName": "ex_ret_mmx_fp_instr.sse_instr",
@@ -90,11 +89,6 @@
     "EventCode": "0xd1",
     "BriefDescription": "Retired Conditional Branch Instructions."
   },
-  {
-    "EventName": "ex_ret_cond_misp",
-    "EventCode": "0xd2",
-    "BriefDescription": "Retired Conditional Branch Instructions Mispredicted."
-  },
   {
     "EventName": "ex_div_busy",
     "EventCode": "0xd3",
@@ -108,22 +102,19 @@
   {
     "EventName": "ex_tagged_ibs_ops.ibs_count_rollover",
     "EventCode": "0x1cf",
-    "BriefDescription": "Number of times an op could not be tagged by IBS because of a previous tagged op that has not retired.",
-    "PublicDescription": "Tagged IBS Ops. Number of times an op could not be tagged by IBS because of a previous tagged op that has not retired.",
+    "BriefDescription": "Tagged IBS Ops. Number of times an op could not be tagged by IBS because of a previous tagged op that has not retired.",
     "UMask": "0x4"
   },
   {
     "EventName": "ex_tagged_ibs_ops.ibs_tagged_ops_ret",
     "EventCode": "0x1cf",
-    "BriefDescription": "Number of Ops tagged by IBS that retired.",
-    "PublicDescription": "Tagged IBS Ops. Number of Ops tagged by IBS that retired.",
+    "BriefDescription": "Tagged IBS Ops. Number of Ops tagged by IBS that retired.",
     "UMask": "0x2"
   },
   {
     "EventName": "ex_tagged_ibs_ops.ibs_tagged_ops",
     "EventCode": "0x1cf",
-    "BriefDescription": "Number of Ops tagged by IBS.",
-    "PublicDescription": "Tagged IBS Ops. Number of Ops tagged by IBS.",
+    "BriefDescription": "Tagged IBS Ops. Number of Ops tagged by IBS.",
     "UMask": "0x1"
   },
   {

tools/perf/pmu-events/arch/x86/amdzen1/floating-point.json

@@ -2,17 +2,73 @@
   {
     "EventName": "fpu_pipe_assignment.dual",
     "EventCode": "0x00",
-    "BriefDescription": "Total number multi-pipe uOps.",
-    "PublicDescription": "The number of operations (uOps) and dual-pipe uOps dispatched to each of the 4 FPU execution pipelines. This event reflects how busy the FPU pipelines are and may be used for workload characterization. This includes all operations performed by x87, MMX, and SSE instructions, including moves. Each increment represents a one- cycle dispatch event. This event is a speculative event. Since this event includes non-numeric operations it is not suitable for measuring MFLOPS. Total number multi-pipe uOps assigned to Pipe 3.",
+    "BriefDescription": "Total number multi-pipe uOps assigned to all pipes.",
+    "PublicDescription": "The number of operations (uOps) and dual-pipe uOps dispatched to each of the 4 FPU execution pipelines. This event reflects how busy the FPU pipelines are and may be used for workload characterization. This includes all operations performed by x87, MMX, and SSE instructions, including moves. Each increment represents a one- cycle dispatch event. This event is a speculative event. Since this event includes non-numeric operations it is not suitable for measuring MFLOPS. Total number multi-pipe uOps assigned to all pipes.",
     "UMask": "0xf0"
   },
+  {
+    "EventName": "fpu_pipe_assignment.dual3",
+    "EventCode": "0x00",
+    "BriefDescription": "Total number multi-pipe uOps assigned to pipe 3.",
+    "PublicDescription": "The number of operations (uOps) and dual-pipe uOps dispatched to each of the 4 FPU execution pipelines. This event reflects how busy the FPU pipelines are and may be used for workload characterization. This includes all operations performed by x87, MMX, and SSE instructions, including moves. Each increment represents a one- cycle dispatch event. This event is a speculative event. Since this event includes non-numeric operations it is not suitable for measuring MFLOPS. Total number multi-pipe uOps assigned to pipe 3.",
+    "UMask": "0x80"
+  },
+  {
+    "EventName": "fpu_pipe_assignment.dual2",
+    "EventCode": "0x00",
+    "BriefDescription": "Total number multi-pipe uOps assigned to pipe 2.",
+    "PublicDescription": "The number of operations (uOps) and dual-pipe uOps dispatched to each of the 4 FPU execution pipelines. This event reflects how busy the FPU pipelines are and may be used for workload characterization. This includes all operations performed by x87, MMX, and SSE instructions, including moves. Each increment represents a one- cycle dispatch event. This event is a speculative event. Since this event includes non-numeric operations it is not suitable for measuring MFLOPS. Total number multi-pipe uOps assigned to pipe 2.",
+    "UMask": "0x40"
+  },
+  {
+    "EventName": "fpu_pipe_assignment.dual1",
+    "EventCode": "0x00",
+    "BriefDescription": "Total number multi-pipe uOps assigned to pipe 1.",
+    "PublicDescription": "The number of operations (uOps) and dual-pipe uOps dispatched to each of the 4 FPU execution pipelines. This event reflects how busy the FPU pipelines are and may be used for workload characterization. This includes all operations performed by x87, MMX, and SSE instructions, including moves. Each increment represents a one- cycle dispatch event. This event is a speculative event. Since this event includes non-numeric operations it is not suitable for measuring MFLOPS. Total number multi-pipe uOps assigned to pipe 1.",
+    "UMask": "0x20"
+  },
+  {
+    "EventName": "fpu_pipe_assignment.dual0",
+    "EventCode": "0x00",
+    "BriefDescription": "Total number multi-pipe uOps assigned to pipe 0.",
+    "PublicDescription": "The number of operations (uOps) and dual-pipe uOps dispatched to each of the 4 FPU execution pipelines. This event reflects how busy the FPU pipelines are and may be used for workload characterization. This includes all operations performed by x87, MMX, and SSE instructions, including moves. Each increment represents a one- cycle dispatch event. This event is a speculative event. Since this event includes non-numeric operations it is not suitable for measuring MFLOPS. Total number multi-pipe uOps assigned to pipe 0.",
+    "UMask": "0x10"
+  },
   {
     "EventName": "fpu_pipe_assignment.total",
     "EventCode": "0x00",
-    "BriefDescription": "Total number uOps.",
-    "PublicDescription": "The number of operations (uOps) and dual-pipe uOps dispatched to each of the 4 FPU execution pipelines. This event reflects how busy the FPU pipelines are and may be used for workload characterization. This includes all operations performed by x87, MMX, and SSE instructions, including moves. Each increment represents a one- cycle dispatch event. This event is a speculative event. Since this event includes non-numeric operations it is not suitable for measuring MFLOPS. Total number uOps assigned to Pipe 3.",
+    "BriefDescription": "Total number uOps assigned to all fpu pipes.",
+    "PublicDescription": "The number of operations (uOps) and dual-pipe uOps dispatched to each of the 4 FPU execution pipelines. This event reflects how busy the FPU pipelines are and may be used for workload characterization. This includes all operations performed by x87, MMX, and SSE instructions, including moves. Each increment represents a one- cycle dispatch event. This event is a speculative event. Since this event includes non-numeric operations it is not suitable for measuring MFLOPS. Total number uOps assigned to all pipes.",
     "UMask": "0xf"
   },
+  {
+    "EventName": "fpu_pipe_assignment.total3",
+    "EventCode": "0x00",
+    "BriefDescription": "Total number of fp uOps on pipe 3.",
+    "PublicDescription": "The number of operations (uOps) dispatched to each of the 4 FPU execution pipelines. This event reflects how busy the FPU pipelines are and may be used for workload characterization. This includes all operations performed by x87, MMX, and SSE instructions, including moves. Each increment represents a one-cycle dispatch event. This event is a speculative event. Since this event includes non-numeric operations it is not suitable for measuring MFLOPS. Total number uOps assigned to pipe 3.",
+    "UMask": "0x8"
+  },
+  {
+    "EventName": "fpu_pipe_assignment.total2",
+    "EventCode": "0x00",
+    "BriefDescription": "Total number of fp uOps on pipe 2.",
+    "PublicDescription": "The number of operations (uOps) dispatched to each of the 4 FPU execution pipelines. This event reflects how busy the FPU pipelines are and may be used for workload characterization. This includes all operations performed by x87, MMX, and SSE instructions, including moves. Each increment represents a one- cycle dispatch event. This event is a speculative event. Since this event includes non-numeric operations it is not suitable for measuring MFLOPS. Total number uOps assigned to pipe 2.",
+    "UMask": "0x4"
+  },
+  {
+    "EventName": "fpu_pipe_assignment.total1",
+    "EventCode": "0x00",
+    "BriefDescription": "Total number of fp uOps on pipe 1.",
+    "PublicDescription": "The number of operations (uOps) dispatched to each of the 4 FPU execution pipelines. This event reflects how busy the FPU pipelines are and may be used for workload characterization. This includes all operations performed by x87, MMX, and SSE instructions, including moves. Each increment represents a one- cycle dispatch event. This event is a speculative event. Since this event includes non-numeric operations it is not suitable for measuring MFLOPS. Total number uOps assigned to pipe 1.",
+    "UMask": "0x2"
+  },
+  {
+    "EventName": "fpu_pipe_assignment.total0",
+    "EventCode": "0x00",
+    "BriefDescription": "Total number of fp uOps  on pipe 0.",
+    "PublicDescription": "The number of operations (uOps) dispatched to each of the 4 FPU execution pipelines. This event reflects how busy the FPU pipelines are and may be used for workload characterization. This includes all operations performed by x87, MMX, and SSE instructions, including moves. Each increment represents a one- cycle dispatch event. This event is a speculative event. Since this event includes non-numeric operations it is not suitable for measuring MFLOPS. Total number uOps assigned to pipe 0.",
+    "UMask": "0x1"
+  },
   {
     "EventName": "fp_sched_empty",
     "EventCode": "0x01",

tools/perf/pmu-events/arch/x86/amdzen1/memory.json

@@ -3,28 +3,24 @@
     "EventName": "ls_locks.bus_lock",
     "EventCode": "0x25",
     "BriefDescription": "Bus lock when a locked operations crosses a cache boundary or is done on an uncacheable memory type.",
-    "PublicDescription": "Bus lock when a locked operations crosses a cache boundary or is done on an uncacheable memory type.",
     "UMask": "0x1"
   },
   {
     "EventName": "ls_dispatch.ld_st_dispatch",
     "EventCode": "0x29",
-    "BriefDescription": "Load-op-Stores.",
-    "PublicDescription": "Counts the number of operations dispatched to the LS unit. Unit Masks ADDed. Load-op-Stores.",
+    "BriefDescription": "Counts the number of operations dispatched to the LS unit. Unit Masks ADDed. Load-op-Stores.",
     "UMask": "0x4"
   },
   {
     "EventName": "ls_dispatch.store_dispatch",
     "EventCode": "0x29",
-    "BriefDescription": "Counts the number of operations dispatched to the LS unit. Unit Masks ADDed.",
-    "PublicDescription": "Counts the number of operations dispatched to the LS unit. Unit Masks ADDed.",
+    "BriefDescription": "Counts the number of stores dispatched to the LS unit. Unit Masks ADDed.",
     "UMask": "0x2"
   },
   {
     "EventName": "ls_dispatch.ld_dispatch",
     "EventCode": "0x29",
-    "BriefDescription": "Counts the number of operations dispatched to the LS unit. Unit Masks ADDed.",
-    "PublicDescription": "Counts the number of operations dispatched to the LS unit. Unit Masks ADDed.",
+    "BriefDescription": "Counts the number of loads dispatched to the LS unit. Unit Masks ADDed.",
     "UMask": "0x1"
   },
   {
@@ -37,83 +33,114 @@
     "EventCode": "0x40",
     "BriefDescription": "The number of accesses to the data cache for load and store references. This may include certain microcode scratchpad accesses, although these are generally rare. Each increment represents an eight-byte access, although the instruction may only be accessing a portion of that. This event is a speculative event."
   },
+  {
+    "EventName": "ls_mab_alloc.dc_prefetcher",
+    "EventCode": "0x41",
+    "BriefDescription": "LS MAB allocates by type - DC prefetcher.",
+    "UMask": "0x8"
+  },
+  {
+    "EventName": "ls_mab_alloc.stores",
+    "EventCode": "0x41",
+    "BriefDescription": "LS MAB allocates by type - stores.",
+    "UMask": "0x2"
+  },
+  {
+    "EventName": "ls_mab_alloc.loads",
+    "EventCode": "0x41",
+    "BriefDescription": "LS MAB allocates by type - loads.",
+    "UMask": "0x01"
+  },
   {
     "EventName": "ls_l1_d_tlb_miss.all",
     "EventCode": "0x45",
     "BriefDescription": "L1 DTLB Miss or Reload off all sizes.",
-    "PublicDescription": "L1 DTLB Miss or Reload off all sizes.",
     "UMask": "0xff"
   },
   {
     "EventName": "ls_l1_d_tlb_miss.tlb_reload_1g_l2_miss",
     "EventCode": "0x45",
     "BriefDescription": "L1 DTLB Miss of a page of 1G size.",
-    "PublicDescription": "L1 DTLB Miss of a page of 1G size.",
     "UMask": "0x80"
   },
   {
     "EventName": "ls_l1_d_tlb_miss.tlb_reload_2m_l2_miss",
     "EventCode": "0x45",
     "BriefDescription": "L1 DTLB Miss of a page of 2M size.",
-    "PublicDescription": "L1 DTLB Miss of a page of 2M size.",
     "UMask": "0x40"
   },
   {
     "EventName": "ls_l1_d_tlb_miss.tlb_reload_32k_l2_miss",
     "EventCode": "0x45",
     "BriefDescription": "L1 DTLB Miss of a page of 32K size.",
-    "PublicDescription": "L1 DTLB Miss of a page of 32K size.",
     "UMask": "0x20"
   },
   {
     "EventName": "ls_l1_d_tlb_miss.tlb_reload_4k_l2_miss",
     "EventCode": "0x45",
     "BriefDescription": "L1 DTLB Miss of a page of 4K size.",
-    "PublicDescription": "L1 DTLB Miss of a page of 4K size.",
     "UMask": "0x10"
   },
   {
     "EventName": "ls_l1_d_tlb_miss.tlb_reload_1g_l2_hit",
     "EventCode": "0x45",
     "BriefDescription": "L1 DTLB Reload of a page of 1G size.",
-    "PublicDescription": "L1 DTLB Reload of a page of 1G size.",
     "UMask": "0x8"
   },
   {
     "EventName": "ls_l1_d_tlb_miss.tlb_reload_2m_l2_hit",
     "EventCode": "0x45",
     "BriefDescription": "L1 DTLB Reload of a page of 2M size.",
-    "PublicDescription": "L1 DTLB Reload of a page of 2M size.",
     "UMask": "0x4"
   },
   {
     "EventName": "ls_l1_d_tlb_miss.tlb_reload_32k_l2_hit",
     "EventCode": "0x45",
     "BriefDescription": "L1 DTLB Reload of a page of 32K size.",
-    "PublicDescription": "L1 DTLB Reload of a page of 32K size.",
     "UMask": "0x2"
   },
   {
     "EventName": "ls_l1_d_tlb_miss.tlb_reload_4k_l2_hit",
     "EventCode": "0x45",
     "BriefDescription": "L1 DTLB Reload of a page of 4K size.",
-    "PublicDescription": "L1 DTLB Reload of a page of 4K size.",
     "UMask": "0x1"
   },
   {
-    "EventName": "ls_tablewalker.perf_mon_tablewalk_alloc_iside",
+    "EventName": "ls_tablewalker.iside",
     "EventCode": "0x46",
-    "BriefDescription": "Tablewalker allocation.",
-    "PublicDescription": "Tablewalker allocation.",
+    "BriefDescription": "Total Page Table Walks on I-side.",
     "UMask": "0xc"
   },
   {
-    "EventName": "ls_tablewalker.perf_mon_tablewalk_alloc_dside",
+    "EventName": "ls_tablewalker.ic_type1",
     "EventCode": "0x46",
-    "BriefDescription": "Tablewalker allocation.",
-    "PublicDescription": "Tablewalker allocation.",
+    "BriefDescription": "Total Page Table Walks IC Type 1.",
+    "UMask": "0x8"
+  },
+  {
+    "EventName": "ls_tablewalker.ic_type0",
+    "EventCode": "0x46",
+    "BriefDescription": "Total Page Table Walks IC Type 0.",
+    "UMask": "0x4"
+  },
+  {
+    "EventName": "ls_tablewalker.dside",
+    "EventCode": "0x46",
+    "BriefDescription": "Total Page Table Walks on D-side.",
     "UMask": "0x3"
   },
+  {
+    "EventName": "ls_tablewalker.dc_type1",
+    "EventCode": "0x46",
+    "BriefDescription": "Total Page Table Walks DC Type 1.",
+    "UMask": "0x2"
+  },
+  {
+    "EventName": "ls_tablewalker.dc_type0",
+    "EventCode": "0x46",
+    "BriefDescription": "Total Page Table Walks DC Type 0.",
+    "UMask": "0x1"
+  },
   {
     "EventName": "ls_misal_accesses",
     "EventCode": "0x47",
@@ -123,35 +150,30 @@
     "EventName": "ls_pref_instr_disp.prefetch_nta",
     "EventCode": "0x4b",
     "BriefDescription": "Software Prefetch Instructions (PREFETCHNTA instruction) Dispatched.",
-    "PublicDescription": "Software Prefetch Instructions (PREFETCHNTA instruction) Dispatched.",
     "UMask": "0x4"
   },
   {
     "EventName": "ls_pref_instr_disp.store_prefetch_w",
     "EventCode": "0x4b",
     "BriefDescription": "Software Prefetch Instructions (3DNow PREFETCHW instruction) Dispatched.",
-    "PublicDescription": "Software Prefetch Instructions (3DNow PREFETCHW instruction) Dispatched.",
     "UMask": "0x2"
   },
   {
     "EventName": "ls_pref_instr_disp.load_prefetch_w",
     "EventCode": "0x4b",
-    "BriefDescription": "Prefetch, Prefetch_T0_T1_T2.",
-    "PublicDescription": "Software Prefetch Instructions Dispatched. Prefetch, Prefetch_T0_T1_T2.",
+    "BriefDescription": "Software Prefetch Instructions Dispatched. Prefetch, Prefetch_T0_T1_T2.",
     "UMask": "0x1"
   },
   {
     "EventName": "ls_inef_sw_pref.mab_mch_cnt",
     "EventCode": "0x52",
-    "BriefDescription": "The number of software prefetches that did not fetch data outside of the processor core.",
-    "PublicDescription": "The number of software prefetches that did not fetch data outside of the processor core.",
+    "BriefDescription": "The number of software prefetches that did not fetch data outside of the processor core. Software PREFETCH instruction saw a match on an already-allocated miss request buffer.",
     "UMask": "0x2"
   },
   {
     "EventName": "ls_inef_sw_pref.data_pipe_sw_pf_dc_hit",
     "EventCode": "0x52",
-    "BriefDescription": "The number of software prefetches that did not fetch data outside of the processor core.",
-    "PublicDescription": "The number of software prefetches that did not fetch data outside of the processor core.",
+    "BriefDescription": "The number of software prefetches that did not fetch data outside of the processor core. Software PREFETCH instruction saw a DC hit.",
     "UMask": "0x1"
   },
   {

tools/perf/pmu-events/arch/x86/amdzen1/other.json

@@ -0,0 +1,56 @@
+[
+  {
+    "EventName": "ic_oc_mode_switch.oc_ic_mode_switch",
+    "EventCode": "0x28a",
+    "BriefDescription": "OC Mode Switch. OC to IC mode switch.",
+    "UMask": "0x2"
+  },
+  {
+    "EventName": "ic_oc_mode_switch.ic_oc_mode_switch",
+    "EventCode": "0x28a",
+    "BriefDescription": "OC Mode Switch. IC to OC mode switch.",
+    "UMask": "0x1"
+  },
+  {
+    "EventName": "de_dis_dispatch_token_stalls0.retire_token_stall",
+    "EventCode": "0xaf",
+    "BriefDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall. RETIRE Tokens unavailable.",
+    "UMask": "0x40"
+  },
+  {
+    "EventName": "de_dis_dispatch_token_stalls0.agsq_token_stall",
+    "EventCode": "0xaf",
+    "BriefDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall. AGSQ Tokens unavailable.",
+    "UMask": "0x20"
+  },
+  {
+    "EventName": "de_dis_dispatch_token_stalls0.alu_token_stall",
+    "EventCode": "0xaf",
+    "BriefDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall. ALU tokens total unavailable.",
+    "UMask": "0x10"
+  },
+  {
+    "EventName": "de_dis_dispatch_token_stalls0.alsq3_0_token_stall",
+    "EventCode": "0xaf",
+    "BriefDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall. ALSQ 3_0 Tokens unavailable.",
+    "UMask": "0x8"
+  },
+  {
+    "EventName": "de_dis_dispatch_token_stalls0.alsq3_token_stall",
+    "EventCode": "0xaf",
+    "BriefDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall. ALSQ 3 Tokens unavailable.",
+    "UMask": "0x4"
+  },
+  {
+    "EventName": "de_dis_dispatch_token_stalls0.alsq2_token_stall",
+    "EventCode": "0xaf",
+    "BriefDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall. ALSQ 2 Tokens unavailable.",
+    "UMask": "0x2"
+  },
+  {
+    "EventName": "de_dis_dispatch_token_stalls0.alsq1_token_stall",
+    "EventCode": "0xaf",
+    "BriefDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall. ALSQ 1 Tokens unavailable.",
+    "UMask": "0x1"
+  }
+]

tools/perf/pmu-events/arch/x86/amdzen2/branch.json

@@ -0,0 +1,52 @@
+[
+  {
+    "EventName": "bp_l1_btb_correct",
+    "EventCode": "0x8a",
+    "BriefDescription": "L1 Branch Prediction Overrides Existing Prediction (speculative)."
+  },
+  {
+    "EventName": "bp_l2_btb_correct",
+    "EventCode": "0x8b",
+    "BriefDescription": "L2 Branch Prediction Overrides Existing Prediction (speculative)."
+  },
+  {
+    "EventName": "bp_dyn_ind_pred",
+    "EventCode": "0x8e",
+    "BriefDescription": "Dynamic Indirect Predictions.",
+    "PublicDescription": "Indirect Branch Prediction for potential multi-target branch (speculative)."
+  },
+  {
+    "EventName": "bp_de_redirect",
+    "EventCode": "0x91",
+    "BriefDescription": "Decoder Overrides Existing Branch Prediction (speculative)."
+  },
+  {
+    "EventName": "bp_l1_tlb_fetch_hit",
+    "EventCode": "0x94",
+    "BriefDescription": "The number of instruction fetches that hit in the L1 ITLB.",
+    "UMask": "0xFF"
+  },
+  {
+    "EventName": "bp_l1_tlb_fetch_hit.if1g",
+    "EventCode": "0x94",
+    "BriefDescription": "The number of instruction fetches that hit in the L1 ITLB. Instruction fetches to a 1GB page.",
+    "UMask": "0x4"
+  },
+  {
+    "EventName": "bp_l1_tlb_fetch_hit.if2m",
+    "EventCode": "0x94",
+    "BriefDescription": "The number of instruction fetches that hit in the L1 ITLB. Instruction fetches to a 2MB page.",
+    "UMask": "0x2"
+  },
+  {
+    "EventName": "bp_l1_tlb_fetch_hit.if4k",
+    "EventCode": "0x94",
+    "BriefDescription": "The number of instruction fetches that hit in the L1 ITLB. Instruction fetches to a 4KB page.",
+    "UMask": "0x1"
+  },
+  {
+    "EventName": "bp_tlb_rel",
+    "EventCode": "0x99",
+    "BriefDescription": "The number of ITLB reload requests."
+  }
+]

tools/perf/pmu-events/arch/x86/amdzen2/cache.json

@@ -0,0 +1,338 @@
+[
+  {
+    "EventName": "l2_request_g1.rd_blk_l",
+    "EventCode": "0x60",
+    "BriefDescription": "All L2 Cache Requests (Breakdown 1 - Common). Data cache reads (including hardware and software prefetch).",
+    "UMask": "0x80"
+  },
+  {
+    "EventName": "l2_request_g1.rd_blk_x",
+    "EventCode": "0x60",
+    "BriefDescription": "All L2 Cache Requests (Breakdown 1 - Common). Data cache stores.",
+    "UMask": "0x40"
+  },
+  {
+    "EventName": "l2_request_g1.ls_rd_blk_c_s",
+    "EventCode": "0x60",
+    "BriefDescription": "All L2 Cache Requests (Breakdown 1 - Common). Data cache shared reads.",
+    "UMask": "0x20"
+  },
+  {
+    "EventName": "l2_request_g1.cacheable_ic_read",
+    "EventCode": "0x60",
+    "BriefDescription": "All L2 Cache Requests (Breakdown 1 - Common). Instruction cache reads.",
+    "UMask": "0x10"
+  },
+  {
+    "EventName": "l2_request_g1.change_to_x",
+    "EventCode": "0x60",
+    "BriefDescription": "All L2 Cache Requests (Breakdown 1 - Common). Data cache state change requests. Request change to writable, check L2 for current state.",
+    "UMask": "0x8"
+  },
+  {
+    "EventName": "l2_request_g1.prefetch_l2_cmd",
+    "EventCode": "0x60",
+    "BriefDescription": "All L2 Cache Requests (Breakdown 1 - Common). PrefetchL2Cmd.",
+    "UMask": "0x4"
+  },
+  {
+    "EventName": "l2_request_g1.l2_hw_pf",
+    "EventCode": "0x60",
+    "BriefDescription": "All L2 Cache Requests (Breakdown 1 - Common). L2 Prefetcher. All prefetches accepted by L2 pipeline, hit or miss. Types of PF and L2 hit/miss broken out in a separate perfmon event.",
+    "UMask": "0x2"
+  },
+  {
+    "EventName": "l2_request_g1.group2",
+    "EventCode": "0x60",
+    "BriefDescription": "Miscellaneous events covered in more detail by l2_request_g2 (PMCx061).",
+    "UMask": "0x1"
+  },
+  {
+    "EventName": "l2_request_g2.group1",
+    "EventCode": "0x61",
+    "BriefDescription": "Miscellaneous events covered in more detail by l2_request_g1 (PMCx060).",
+    "UMask": "0x80"
+  },
+  {
+    "EventName": "l2_request_g2.ls_rd_sized",
+    "EventCode": "0x61",
+    "BriefDescription": "All L2 Cache Requests (Breakdown 2 - Rare). Data cache read sized.",
+    "UMask": "0x40"
+  },
+  {
+    "EventName": "l2_request_g2.ls_rd_sized_nc",
+    "EventCode": "0x61",
+    "BriefDescription": "All L2 Cache Requests (Breakdown 2 - Rare). Data cache read sized non-cacheable.",
+    "UMask": "0x20"
+  },
+  {
+    "EventName": "l2_request_g2.ic_rd_sized",
+    "EventCode": "0x61",
+    "BriefDescription": "All L2 Cache Requests (Breakdown 2 - Rare). Instruction cache read sized.",
+    "UMask": "0x10"
+  },
+  {
+    "EventName": "l2_request_g2.ic_rd_sized_nc",
+    "EventCode": "0x61",
+    "BriefDescription": "All L2 Cache Requests (Breakdown 2 - Rare). Instruction cache read sized non-cacheable.",
+    "UMask": "0x8"
+  },
+  {
+    "EventName": "l2_request_g2.smc_inval",
+    "EventCode": "0x61",
+    "BriefDescription": "All L2 Cache Requests (Breakdown 2 - Rare). Self-modifying code invalidates.",
+    "UMask": "0x4"
+  },
+  {
+    "EventName": "l2_request_g2.bus_locks_originator",
+    "EventCode": "0x61",
+    "BriefDescription": "All L2 Cache Requests (Breakdown 2 - Rare). Bus locks.",
+    "UMask": "0x2"
+  },
+  {
+    "EventName": "l2_request_g2.bus_locks_responses",
+    "EventCode": "0x61",
+    "BriefDescription": "All L2 Cache Requests (Breakdown 2 - Rare). Bus lock response.",
+    "UMask": "0x1"
+  },
+  {
+    "EventName": "l2_latency.l2_cycles_waiting_on_fills",
+    "EventCode": "0x62",
+    "BriefDescription": "Total cycles spent waiting for L2 fills to complete from L3 or memory, divided by four. Event counts are for both threads. To calculate average latency, the number of fills from both threads must be used.",
+    "UMask": "0x1"
+  },
+  {
+    "EventName": "l2_wcb_req.wcb_write",
+    "EventCode": "0x63",
+    "BriefDescription": "LS to L2 WCB write requests. LS (Load/Store unit) to L2 WCB (Write Combining Buffer) write requests.",
+    "UMask": "0x40"
+  },
+  {
+    "EventName": "l2_wcb_req.wcb_close",
+    "EventCode": "0x63",
+    "BriefDescription": "LS to L2 WCB close requests. LS (Load/Store unit) to L2 WCB (Write Combining Buffer) close requests.",
+    "UMask": "0x20"
+  },
+  {
+    "EventName": "l2_wcb_req.zero_byte_store",
+    "EventCode": "0x63",
+    "BriefDescription": "LS to L2 WCB zero byte store requests. LS (Load/Store unit) to L2 WCB (Write Combining Buffer) zero byte store requests.",
+    "UMask": "0x4"
+  },
+  {
+    "EventName": "l2_wcb_req.cl_zero",
+    "EventCode": "0x63",
+    "BriefDescription": "LS to L2 WCB cache line zeroing requests. LS (Load/Store unit) to L2 WCB (Write Combining Buffer) cache line zeroing requests.",
+    "UMask": "0x1"
+  },
+  {
+    "EventName": "l2_cache_req_stat.ls_rd_blk_cs",
+    "EventCode": "0x64",
+    "BriefDescription": "Core to L2 cacheable request access status (not including L2 Prefetch). Data cache shared read hit in L2",
+    "UMask": "0x80"
+  },
+  {
+    "EventName": "l2_cache_req_stat.ls_rd_blk_l_hit_x",
+    "EventCode": "0x64",
+    "BriefDescription": "Core to L2 cacheable request access status (not including L2 Prefetch). Data cache read hit in L2.",
+    "UMask": "0x40"
+  },
+  {
+    "EventName": "l2_cache_req_stat.ls_rd_blk_l_hit_s",
+    "EventCode": "0x64",
+    "BriefDescription": "Core to L2 cacheable request access status (not including L2 Prefetch). Data cache read hit on shared line in L2.",
+    "UMask": "0x20"
+  },
+  {
+    "EventName": "l2_cache_req_stat.ls_rd_blk_x",
+    "EventCode": "0x64",
+    "BriefDescription": "Core to L2 cacheable request access status (not including L2 Prefetch). Data cache store or state change hit in L2.",
+    "UMask": "0x10"
+  },
+  {
+    "EventName": "l2_cache_req_stat.ls_rd_blk_c",
+    "EventCode": "0x64",
+    "BriefDescription": "Core to L2 cacheable request access status (not including L2 Prefetch). Data cache request miss in L2 (all types).",
+    "UMask": "0x8"
+  },
+  {
+    "EventName": "l2_cache_req_stat.ic_fill_hit_x",
+    "EventCode": "0x64",
+    "BriefDescription": "Core to L2 cacheable request access status (not including L2 Prefetch). Instruction cache hit modifiable line in L2.",
+    "UMask": "0x4"
+  },
+  {
+    "EventName": "l2_cache_req_stat.ic_fill_hit_s",
+    "EventCode": "0x64",
+    "BriefDescription": "Core to L2 cacheable request access status (not including L2 Prefetch). Instruction cache hit clean line in L2.",
+    "UMask": "0x2"
+  },
+  {
+    "EventName": "l2_cache_req_stat.ic_fill_miss",
+    "EventCode": "0x64",
+    "BriefDescription": "Core to L2 cacheable request access status (not including L2 Prefetch). Instruction cache request miss in L2.",
+    "UMask": "0x1"
+  },
+  {
+    "EventName": "l2_fill_pending.l2_fill_busy",
+    "EventCode": "0x6d",
+    "BriefDescription": "Cycles with fill pending from L2. Total cycles spent with one or more fill requests in flight from L2.",
+    "UMask": "0x1"
+  },
+  {
+    "EventName": "l2_pf_hit_l2",
+    "EventCode": "0x70",
+    "BriefDescription": "L2 prefetch hit in L2.",
+    "UMask": "0xff"
+  },
+  {
+    "EventName": "l2_pf_miss_l2_hit_l3",
+    "EventCode": "0x71",
+    "BriefDescription": "L2 prefetcher hits in L3. Counts all L2 prefetches accepted by the L2 pipeline which miss the L2 cache and hit the L3.",
+    "UMask": "0xff"
+  },
+  {
+    "EventName": "l2_pf_miss_l2_l3",
+    "EventCode": "0x72",
+    "BriefDescription": "L2 prefetcher misses in L3. All L2 prefetches accepted by the L2 pipeline which miss the L2 and the L3 caches.",
+    "UMask": "0xff"
+  },
+  {
+    "EventName": "ic_fw32",
+    "EventCode": "0x80",
+    "BriefDescription": "The number of 32B fetch windows transferred from IC pipe to DE instruction decoder (includes non-cacheable and cacheable fill responses)."
+  },
+  {
+    "EventName": "ic_fw32_miss",
+    "EventCode": "0x81",
+    "BriefDescription": "The number of 32B fetch windows tried to read the L1 IC and missed in the full tag."
+  },
+  {
+    "EventName": "ic_cache_fill_l2",
+    "EventCode": "0x82",
+    "BriefDescription": "The number of 64 byte instruction cache line was fulfilled from the L2 cache."
+  },
+  {
+    "EventName": "ic_cache_fill_sys",
+    "EventCode": "0x83",
+    "BriefDescription": "The number of 64 byte instruction cache line fulfilled from system memory or another cache."
+  },
+  {
+    "EventName": "bp_l1_tlb_miss_l2_hit",
+    "EventCode": "0x84",
+    "BriefDescription": "The number of instruction fetches that miss in the L1 ITLB but hit in the L2 ITLB."
+  },
+  {
+    "EventName": "bp_l1_tlb_miss_l2_tlb_miss",
+    "EventCode": "0x85",
+    "BriefDescription": "The number of instruction fetches that miss in both the L1 and L2 TLBs.",
+    "UMask": "0xff"
+  },
+  {
+    "EventName": "bp_l1_tlb_miss_l2_tlb_miss.if1g",
+    "EventCode": "0x85",
+    "BriefDescription": "The number of instruction fetches that miss in both the L1 and L2 TLBs. Instruction fetches to a 1GB page.",
+    "UMask": "0x4"
+  },
+  {
+    "EventName": "bp_l1_tlb_miss_l2_tlb_miss.if2m",
+    "EventCode": "0x85",
+    "BriefDescription": "The number of instruction fetches that miss in both the L1 and L2 TLBs. Instruction fetches to a 2MB page.",
+    "UMask": "0x2"
+  },
+  {
+    "EventName": "bp_l1_tlb_miss_l2_tlb_miss.if4k",
+    "EventCode": "0x85",
+    "BriefDescription": "The number of instruction fetches that miss in both the L1 and L2 TLBs. Instruction fetches to a 4KB page.",
+    "UMask": "0x1"
+  },
+  {
+    "EventName": "bp_snp_re_sync",
+    "EventCode": "0x86",
+    "BriefDescription": "The number of pipeline restarts caused by invalidating probes that hit on the instruction stream currently being executed. This would happen if the active instruction stream was being modified by another processor in an MP system - typically a highly unlikely event."
+  },
+  {
+    "EventName": "ic_fetch_stall.ic_stall_any",
+    "EventCode": "0x87",
+    "BriefDescription": "Instruction Pipe Stall. IC pipe was stalled during this clock cycle for any reason (nothing valid in pipe ICM1).",
+    "UMask": "0x4"
+  },
+  {
+    "EventName": "ic_fetch_stall.ic_stall_dq_empty",
+    "EventCode": "0x87",
+    "BriefDescription": "Instruction Pipe Stall. IC pipe was stalled during this clock cycle (including IC to OC fetches) due to DQ empty.",
+    "UMask": "0x2"
+  },
+  {
+    "EventName": "ic_fetch_stall.ic_stall_back_pressure",
+    "EventCode": "0x87",
+    "BriefDescription": "Instruction Pipe Stall. IC pipe was stalled during this clock cycle (including IC to OC fetches) due to back-pressure.",
+    "UMask": "0x1"
+  },
+  {
+    "EventName": "ic_cache_inval.l2_invalidating_probe",
+    "EventCode": "0x8c",
+    "BriefDescription": "IC line invalidated due to L2 invalidating probe (external or LS). The number of instruction cache lines invalidated. A non-SMC event is CMC (cross modifying code), either from the other thread of the core or another core.",
+    "UMask": "0x2"
+  },
+  {
+    "EventName": "ic_cache_inval.fill_invalidated",
+    "EventCode": "0x8c",
+    "BriefDescription": "IC line invalidated due to overwriting fill response. The number of instruction cache lines invalidated. A non-SMC event is CMC (cross modifying code), either from the other thread of the core or another core.",
+    "UMask": "0x1"
+  },
+  {
+    "EventName": "ic_oc_mode_switch.oc_ic_mode_switch",
+    "EventCode": "0x28a",
+    "BriefDescription": "OC Mode Switch. OC to IC mode switch.",
+    "UMask": "0x2"
+  },
+  {
+    "EventName": "ic_oc_mode_switch.ic_oc_mode_switch",
+    "EventCode": "0x28a",
+    "BriefDescription": "OC Mode Switch. IC to OC mode switch.",
+    "UMask": "0x1"
+  },
+  {
+    "EventName": "l3_request_g1.caching_l3_cache_accesses",
+    "EventCode": "0x01",
+    "BriefDescription": "Caching: L3 cache accesses",
+    "UMask": "0x80",
+    "Unit": "L3PMC"
+  },
+  {
+    "EventName": "l3_lookup_state.all_l3_req_typs",
+    "EventCode": "0x04",
+    "BriefDescription": "All L3 Request Types",
+    "UMask": "0xff",
+    "Unit": "L3PMC"
+  },
+  {
+    "EventName": "l3_comb_clstr_state.other_l3_miss_typs",
+    "EventCode": "0x06",
+    "BriefDescription": "Other L3 Miss Request Types",
+    "UMask": "0xfe",
+    "Unit": "L3PMC"
+  },
+  {
+    "EventName": "l3_comb_clstr_state.request_miss",
+    "EventCode": "0x06",
+    "BriefDescription": "L3 cache misses",
+    "UMask": "0x01",
+    "Unit": "L3PMC"
+  },
+  {
+    "EventName": "xi_sys_fill_latency",
+    "EventCode": "0x90",
+    "BriefDescription": "L3 Cache Miss Latency. Total cycles for all transactions divided by 16. Ignores SliceMask and ThreadMask.",
+    "UMask": "0x00",
+    "Unit": "L3PMC"
+  },
+  {
+    "EventName": "xi_ccx_sdp_req1.all_l3_miss_req_typs",
+    "EventCode": "0x9A",
+    "BriefDescription": "All L3 Miss Request Types. Ignores SliceMask and ThreadMask.",
+    "UMask": "0x3f",
+    "Unit": "L3PMC"
+  }
+]

tools/perf/pmu-events/arch/x86/amdzen2/core.json

@@ -0,0 +1,130 @@
+[
+  {
+    "EventName": "ex_ret_instr",
+    "EventCode": "0xc0",
+    "BriefDescription": "Retired Instructions."
+  },
+  {
+    "EventName": "ex_ret_cops",
+    "EventCode": "0xc1",
+    "BriefDescription": "Retired Uops.",
+    "PublicDescription": "The number of micro-ops retired. This count includes all processor activity (instructions, exceptions, interrupts, microcode assists, etc.). The number of events logged per cycle can vary from 0 to 8."
+  },
+  {
+    "EventName": "ex_ret_brn",
+    "EventCode": "0xc2",
+    "BriefDescription": "Retired Branch Instructions.",
+    "PublicDescription": "The number of branch instructions retired. This includes all types of architectural control flow changes, including exceptions and interrupts."
+  },
+  {
+    "EventName": "ex_ret_brn_misp",
+    "EventCode": "0xc3",
+    "BriefDescription": "Retired Branch Instructions Mispredicted.",
+    "PublicDescription": "The number of branch instructions retired, of any type, that were not correctly predicted. This includes those for which prediction is not attempted (far control transfers, exceptions and interrupts)."
+  },
+  {
+    "EventName": "ex_ret_brn_tkn",
+    "EventCode": "0xc4",
+    "BriefDescription": "Retired Taken Branch Instructions.",
+    "PublicDescription": "The number of taken branches that were retired. This includes all types of architectural control flow changes, including exceptions and interrupts."
+  },
+  {
+    "EventName": "ex_ret_brn_tkn_misp",
+    "EventCode": "0xc5",
+    "BriefDescription": "Retired Taken Branch Instructions Mispredicted.",
+    "PublicDescription": "The number of retired taken branch instructions that were mispredicted."
+  },
+  {
+    "EventName": "ex_ret_brn_far",
+    "EventCode": "0xc6",
+    "BriefDescription": "Retired Far Control Transfers.",
+    "PublicDescription": "The number of far control transfers retired including far call/jump/return, IRET, SYSCALL and SYSRET, plus exceptions and interrupts. Far control transfers are not subject to branch prediction."
+  },
+  {
+    "EventName": "ex_ret_brn_resync",
+    "EventCode": "0xc7",
+    "BriefDescription": "Retired Branch Resyncs.",
+    "PublicDescription": "The number of resync branches. These reflect pipeline restarts due to certain microcode assists and events such as writes to the active instruction stream, among other things. Each occurrence reflects a restart penalty similar to a branch mispredict. This is relatively rare."
+  },
+  {
+    "EventName": "ex_ret_near_ret",
+    "EventCode": "0xc8",
+    "BriefDescription": "Retired Near Returns.",
+    "PublicDescription": "The number of near return instructions (RET or RET Iw) retired."
+  },
+  {
+    "EventName": "ex_ret_near_ret_mispred",
+    "EventCode": "0xc9",
+    "BriefDescription": "Retired Near Returns Mispredicted.",
+    "PublicDescription": "The number of near returns retired that were not correctly predicted by the return address predictor. Each such mispredict incurs the same penalty as a mispredicted conditional branch instruction."
+  },
+  {
+    "EventName": "ex_ret_brn_ind_misp",
+    "EventCode": "0xca",
+    "BriefDescription": "Retired Indirect Branch Instructions Mispredicted."
+  },
+  {
+    "EventName": "ex_ret_mmx_fp_instr.sse_instr",
+    "EventCode": "0xcb",
+    "BriefDescription": "SSE instructions (SSE, SSE2, SSE3, SSSE3, SSE4A, SSE41, SSE42, AVX).",
+    "PublicDescription": "The number of MMX, SSE or x87 instructions retired. The UnitMask allows the selection of the individual classes of instructions as given in the table. Each increment represents one complete instruction. Since this event includes non-numeric instructions it is not suitable for measuring MFLOPS. SSE instructions (SSE, SSE2, SSE3, SSSE3, SSE4A, SSE41, SSE42, AVX).",
+    "UMask": "0x4"
+  },
+  {
+    "EventName": "ex_ret_mmx_fp_instr.mmx_instr",
+    "EventCode": "0xcb",
+    "BriefDescription": "MMX instructions.",
+    "PublicDescription": "The number of MMX, SSE or x87 instructions retired. The UnitMask allows the selection of the individual classes of instructions as given in the table. Each increment represents one complete instruction. Since this event includes non-numeric instructions it is not suitable for measuring MFLOPS. MMX instructions.",
+    "UMask": "0x2"
+  },
+  {
+    "EventName": "ex_ret_mmx_fp_instr.x87_instr",
+    "EventCode": "0xcb",
+    "BriefDescription": "x87 instructions.",
+    "PublicDescription": "The number of MMX, SSE or x87 instructions retired. The UnitMask allows the selection of the individual classes of instructions as given in the table. Each increment represents one complete instruction. Since this event includes non-numeric instructions it is not suitable for measuring MFLOPS. x87 instructions.",
+    "UMask": "0x1"
+  },
+  {
+    "EventName": "ex_ret_cond",
+    "EventCode": "0xd1",
+    "BriefDescription": "Retired Conditional Branch Instructions."
+  },
+  {
+    "EventName": "ex_ret_cond_misp",
+    "EventCode": "0xd2",
+    "BriefDescription": "Retired Conditional Branch Instructions Mispredicted."
+  },
+  {
+    "EventName": "ex_div_busy",
+    "EventCode": "0xd3",
+    "BriefDescription": "Div Cycles Busy count."
+  },
+  {
+    "EventName": "ex_div_count",
+    "EventCode": "0xd4",
+    "BriefDescription": "Div Op Count."
+  },
+  {
+    "EventName": "ex_tagged_ibs_ops.ibs_count_rollover",
+    "EventCode": "0x1cf",
+    "BriefDescription": "Tagged IBS Ops. Number of times an op could not be tagged by IBS because of a previous tagged op that has not retired.",
+    "UMask": "0x4"
+  },
+  {
+    "EventName": "ex_tagged_ibs_ops.ibs_tagged_ops_ret",
+    "EventCode": "0x1cf",
+    "BriefDescription": "Tagged IBS Ops. Number of Ops tagged by IBS that retired.",
+    "UMask": "0x2"
+  },
+  {
+    "EventName": "ex_tagged_ibs_ops.ibs_tagged_ops",
+    "EventCode": "0x1cf",
+    "BriefDescription": "Tagged IBS Ops. Number of Ops tagged by IBS.",
+    "UMask": "0x1"
+  },
+  {
+    "EventName": "ex_ret_fus_brnch_inst",
+    "EventCode": "0x1d0",
+    "BriefDescription": "Retired Fused Instructions. The number of fuse-branch instructions retired per cycle. The number of events logged per cycle can vary from 0-8.",
+  }
+]

tools/perf/pmu-events/arch/x86/amdzen2/floating-point.json

@@ -0,0 +1,140 @@
+[
+  {
+    "EventName": "fpu_pipe_assignment.total",
+    "EventCode": "0x00",
+    "BriefDescription": "Total number of fp uOps.",
+    "PublicDescription": "Total number of fp uOps. The number of operations (uOps) dispatched to each of the 4 FPU execution pipelines. This event reflects how busy the FPU pipelines are and may be used for workload characterization. This includes all operations performed by x87, MMX, and SSE instructions, including moves. Each increment represents a one- cycle dispatch event. This event is a speculative event. Since this event includes non-numeric operations it is not suitable for measuring MFLOPS.",
+    "UMask": "0xf"
+  },
+  {
+    "EventName": "fpu_pipe_assignment.total3",
+    "EventCode": "0x00",
+    "BriefDescription": "Total number uOps assigned to pipe 3.",
+    "PublicDescription": "The number of operations (uOps) dispatched to each of the 4 FPU execution pipelines. This event reflects how busy the FPU pipelines are and may be used for workload characterization. This includes all operations performed by x87, MMX, and SSE instructions, including moves. Each increment represents a one-cycle dispatch event. This event is a speculative event. Since this event includes non-numeric operations it is not suitable for measuring MFLOPS. Total number uOps assigned to pipe 3.",
+    "UMask": "0x8"
+  },
+  {
+    "EventName": "fpu_pipe_assignment.total2",
+    "EventCode": "0x00",
+    "BriefDescription": "Total number uOps assigned to pipe 2.",
+    "PublicDescription": "The number of operations (uOps) dispatched to each of the 4 FPU execution pipelines. This event reflects how busy the FPU pipelines are and may be used for workload characterization. This includes all operations performed by x87, MMX, and SSE instructions, including moves. Each increment represents a one- cycle dispatch event. This event is a speculative event. Since this event includes non-numeric operations it is not suitable for measuring MFLOPS. Total number uOps assigned to pipe 2.",
+    "UMask": "0x4"
+  },
+  {
+    "EventName": "fpu_pipe_assignment.total1",
+    "EventCode": "0x00",
+    "BriefDescription": "Total number uOps assigned to pipe 1.",
+    "PublicDescription": "The number of operations (uOps) dispatched to each of the 4 FPU execution pipelines. This event reflects how busy the FPU pipelines are and may be used for workload characterization. This includes all operations performed by x87, MMX, and SSE instructions, including moves. Each increment represents a one- cycle dispatch event. This event is a speculative event. Since this event includes non-numeric operations it is not suitable for measuring MFLOPS. Total number uOps assigned to pipe 1.",
+    "UMask": "0x2"
+  },
+  {
+    "EventName": "fpu_pipe_assignment.total0",
+    "EventCode": "0x00",
+    "BriefDescription": "Total number of fp uOps  on pipe 0.",
+    "PublicDescription": "The number of operations (uOps) dispatched to each of the 4 FPU execution pipelines. This event reflects how busy the FPU pipelines are and may be used for workload characterization. This includes all operations performed by x87, MMX, and SSE instructions, including moves. Each increment represents a one- cycle dispatch event. This event is a speculative event. Since this event includes non-numeric operations it is not suitable for measuring MFLOPS. Total number uOps assigned to pipe 0.",
+    "UMask": "0x1"
+  },
+  {
+    "EventName": "fp_ret_sse_avx_ops.all",
+    "EventCode": "0x03",
+    "BriefDescription": "All FLOPS. This is a retire-based event. The number of retired SSE/AVX FLOPS. The number of events logged per cycle can vary from 0 to 64. This event can count above 15.",
+    "UMask": "0xff"
+  },
+  {
+    "EventName": "fp_ret_sse_avx_ops.mac_flops",
+    "EventCode": "0x03",
+    "BriefDescription": "Multiply-add FLOPS. Multiply-add counts as 2 FLOPS. This is a retire-based event. The number of retired SSE/AVX FLOPS. The number of events logged per cycle can vary from 0 to 64. This event can count above 15.",
+    "PublicDescription": "",
+    "UMask": "0x8"
+  },
+  {
+    "EventName": "fp_ret_sse_avx_ops.div_flops",
+    "EventCode": "0x03",
+    "BriefDescription": "Divide/square root FLOPS. This is a retire-based event. The number of retired SSE/AVX FLOPS. The number of events logged per cycle can vary from 0 to 64. This event can count above 15.",
+    "UMask": "0x4"
+  },
+  {
+    "EventName": "fp_ret_sse_avx_ops.mult_flops",
+    "EventCode": "0x03",
+    "BriefDescription": "Multiply FLOPS. This is a retire-based event. The number of retired SSE/AVX FLOPS. The number of events logged per cycle can vary from 0 to 64. This event can count above 15.",
+    "UMask": "0x2"
+  },
+  {
+    "EventName": "fp_ret_sse_avx_ops.add_sub_flops",
+    "EventCode": "0x03",
+    "BriefDescription": "Add/subtract FLOPS. This is a retire-based event. The number of retired SSE/AVX FLOPS. The number of events logged per cycle can vary from 0 to 64. This event can count above 15.",
+    "UMask": "0x1"
+  },
+  {
+    "EventName": "fp_num_mov_elim_scal_op.optimized",
+    "EventCode": "0x04",
+    "BriefDescription": "Number of Scalar Ops optimized. This is a dispatch based speculative event, and is useful for measuring the effectiveness of the Move elimination and Scalar code optimization schemes.",
+    "UMask": "0x8"
+  },
+  {
+    "EventName": "fp_num_mov_elim_scal_op.opt_potential",
+    "EventCode": "0x04",
+    "BriefDescription": "Number of Ops that are candidates for optimization (have Z-bit either set or pass). This is a dispatch based speculative event, and is useful for measuring the effectiveness of the Move elimination and Scalar code optimization schemes.",
+    "UMask": "0x4"
+  },
+  {
+    "EventName": "fp_num_mov_elim_scal_op.sse_mov_ops_elim",
+    "EventCode": "0x04",
+    "BriefDescription": "Number of SSE Move Ops eliminated. This is a dispatch based speculative event, and is useful for measuring the effectiveness of the Move elimination and Scalar code optimization schemes.",
+    "UMask": "0x2"
+  },
+  {
+    "EventName": "fp_num_mov_elim_scal_op.sse_mov_ops",
+    "EventCode": "0x04",
+    "BriefDescription": "Number of SSE Move Ops. This is a dispatch based speculative event, and is useful for measuring the effectiveness of the Move elimination and Scalar code optimization schemes.",
+    "UMask": "0x1"
+  },
+  {
+    "EventName": "fp_retired_ser_ops.sse_bot_ret",
+    "EventCode": "0x05",
+    "BriefDescription": "SSE bottom-executing uOps retired. The number of serializing Ops retired.",
+    "UMask": "0x8"
+  },
+  {
+    "EventName": "fp_retired_ser_ops.sse_ctrl_ret",
+    "EventCode": "0x05",
+    "BriefDescription": "The number of serializing Ops retired. SSE control word mispredict traps due to mispredictions in RC, FTZ or DAZ, or changes in mask bits.",
+    "UMask": "0x4"
+  },
+  {
+    "EventName": "fp_retired_ser_ops.x87_bot_ret",
+    "EventCode": "0x05",
+    "BriefDescription": "x87 bottom-executing uOps retired. The number of serializing Ops retired.",
+    "UMask": "0x2"
+  },
+  {
+    "EventName": "fp_retired_ser_ops.x87_ctrl_ret",
+    "EventCode": "0x05",
+    "BriefDescription": "x87 control word mispredict traps due to mispredictions in RC or PC, or changes in mask bits. The number of serializing Ops retired.",
+    "UMask": "0x1"
+  },
+  {
+    "EventName": "fp_disp_faults.ymm_spill_fault",
+    "EventCode": "0x0e",
+    "BriefDescription": "Floating Point Dispatch Faults. YMM spill fault.",
+    "UMask": "0x8"
+  },
+  {
+    "EventName": "fp_disp_faults.ymm_fill_fault",
+    "EventCode": "0x0e",
+    "BriefDescription": "Floating Point Dispatch Faults. YMM fill fault.",
+    "UMask": "0x4"
+  },
+  {
+    "EventName": "fp_disp_faults.xmm_fill_fault",
+    "EventCode": "0x0e",
+    "BriefDescription": "Floating Point Dispatch Faults. XMM fill fault.",
+    "UMask": "0x2"
+  },
+  {
+    "EventName": "fp_disp_faults.x87_fill_fault",
+    "EventCode": "0x0e",
+    "BriefDescription": "Floating Point Dispatch Faults. x87 fill fault.",
+    "UMask": "0x1"
+  }
+]

tools/perf/pmu-events/arch/x86/amdzen2/memory.json

@@ -0,0 +1,341 @@
+[
+  {
+    "EventName": "ls_bad_status2.stli_other",
+    "EventCode": "0x24",
+    "BriefDescription": "Non-forwardable conflict; used to reduce STLI's via software. All reasons. Store To Load Interlock (STLI) are loads that were unable to complete because of a possible match with an older store, and the older store could not do STLF for some reason.",
+    "PublicDescription" : "Store-to-load conflicts: A load was unable to complete due to a non-forwardable conflict with an older store. Most commonly, a load's address range partially but not completely overlaps with an uncompleted older store. Software can avoid this problem by using same-size and same-alignment loads and stores when accessing the same data. Vector/SIMD code is particularly susceptible to this problem; software should construct wide vector stores by manipulating vector elements in registers using shuffle/blend/swap instructions prior to storing to memory, instead of using narrow element-by-element stores.",
+    "UMask": "0x2"
+  },
+  {
+    "EventName": "ls_locks.spec_lock_hi_spec",
+    "EventCode": "0x25",
+    "BriefDescription": "Retired lock instructions. High speculative cacheable lock speculation succeeded.",
+    "UMask": "0x8"
+  },
+  {
+    "EventName": "ls_locks.spec_lock_lo_spec",
+    "EventCode": "0x25",
+    "BriefDescription": "Retired lock instructions. Low speculative cacheable lock speculation succeeded.",
+    "UMask": "0x4"
+  },
+  {
+    "EventName": "ls_locks.non_spec_lock",
+    "EventCode": "0x25",
+    "BriefDescription": "Retired lock instructions. Non-speculative lock succeeded.",
+    "UMask": "0x2"
+  },
+  {
+    "EventName": "ls_locks.bus_lock",
+    "EventCode": "0x25",
+    "BriefDescription": "Retired lock instructions. Bus lock when a locked operations crosses a cache boundary or is done on an uncacheable memory type. Comparable to legacy bus lock.",
+    "UMask": "0x1"
+  },
+  {
+    "EventName": "ls_ret_cl_flush",
+    "EventCode": "0x26",
+    "BriefDescription": "Number of retired CLFLUSH instructions."
+  },
+  {
+    "EventName": "ls_ret_cpuid",
+    "EventCode": "0x27",
+    "BriefDescription": "Number of retired CPUID instructions."
+  },
+  {
+    "EventName": "ls_dispatch.ld_st_dispatch",
+    "EventCode": "0x29",
+    "BriefDescription": "Dispatch of a single op that performs a load from and store to the same memory address. Number of single ops that do load/store to an address.",
+    "UMask": "0x4"
+  },
+  {
+    "EventName": "ls_dispatch.store_dispatch",
+    "EventCode": "0x29",
+    "BriefDescription": "Number of stores dispatched. Counts the number of operations dispatched to the LS unit. Unit Masks ADDed.",
+    "UMask": "0x2"
+  },
+  {
+    "EventName": "ls_dispatch.ld_dispatch",
+    "EventCode": "0x29",
+    "BriefDescription": "Number of loads dispatched. Counts the number of operations dispatched to the LS unit. Unit Masks ADDed.",
+    "UMask": "0x1"
+  },
+  {
+    "EventName": "ls_smi_rx",
+    "EventCode": "0x2B",
+    "BriefDescription": "Number of SMIs received."
+  },
+  {
+    "EventName": "ls_int_taken",
+    "EventCode": "0x2C",
+    "BriefDescription": "Number of interrupts taken."
+  },
+  {
+    "EventName": "ls_rdtsc",
+    "EventCode": "0x2D",
+    "BriefDescription": "Number of reads of the TSC (RDTSC instructions). The count is speculative."
+  },
+  {
+    "EventName": "ls_stlf",
+    "EventCode": "0x35",
+    "BriefDescription": "Number of STLF hits."
+  },
+  {
+    "EventName": "ls_st_commit_cancel2.st_commit_cancel_wcb_full",
+    "EventCode": "0x37",
+    "BriefDescription": "A non-cacheable store and the non-cacheable commit buffer is full."
+  },
+  {
+    "EventName": "ls_dc_accesses",
+    "EventCode": "0x40",
+    "BriefDescription": "Number of accesses to the dcache for load/store references.",
+    "PublicDescription": "The number of accesses to the data cache for load and store references. This may include certain microcode scratchpad accesses, although these are generally rare. Each increment represents an eight-byte access, although the instruction may only be accessing a portion of that. This event is a speculative event."
+  },
+  {
+    "EventName": "ls_mab_alloc.dc_prefetcher",
+    "EventCode": "0x41",
+    "BriefDescription": "LS MAB Allocates by Type. DC prefetcher.",
+    "UMask": "0x8"
+  },
+  {
+    "EventName": "ls_mab_alloc.stores",
+    "EventCode": "0x41",
+    "BriefDescription": "LS MAB Allocates by Type. Stores.",
+    "UMask": "0x2"
+  },
+  {
+    "EventName": "ls_mab_alloc.loads",
+    "EventCode": "0x41",
+    "BriefDescription": "LS MAB Allocates by Type. Loads.",
+    "UMask": "0x1"
+  },
+  {
+    "EventName": "ls_refills_from_sys.ls_mabresp_rmt_dram",
+    "EventCode": "0x43",
+    "BriefDescription": "Demand Data Cache Fills by Data Source. DRAM or IO from different die.",
+    "UMask": "0x40"
+  },
+  {
+    "EventName": "ls_refills_from_sys.ls_mabresp_rmt_cache",
+    "EventCode": "0x43",
+    "BriefDescription": "Demand Data Cache Fills by Data Source. Hit in cache; Remote CCX and the address's Home Node is on a different die.",
+    "UMask": "0x10"
+  },
+  {
+    "EventName": "ls_refills_from_sys.ls_mabresp_lcl_dram",
+    "EventCode": "0x43",
+    "BriefDescription": "Demand Data Cache Fills by Data Source. DRAM or IO from this thread's die.",
+    "UMask": "0x8"
+  },
+  {
+    "EventName": "ls_refills_from_sys.ls_mabresp_lcl_cache",
+    "EventCode": "0x43",
+    "BriefDescription": "Demand Data Cache Fills by Data Source. Hit in cache; local CCX (not Local L2), or Remote CCX and the address's Home Node is on this thread's die.",
+    "UMask": "0x2"
+  },
+  {
+    "EventName": "ls_refills_from_sys.ls_mabresp_lcl_l2",
+    "EventCode": "0x43",
+    "BriefDescription": "Demand Data Cache Fills by Data Source. Local L2 hit.",
+    "UMask": "0x1"
+  },
+  {
+    "EventName": "ls_l1_d_tlb_miss.all",
+    "EventCode": "0x45",
+    "BriefDescription": "All L1 DTLB Misses or Reloads.",
+    "UMask": "0xff"
+  },
+  {
+    "EventName": "ls_l1_d_tlb_miss.tlb_reload_1g_l2_miss",
+    "EventCode": "0x45",
+    "BriefDescription": "L1 DTLB Miss. DTLB reload to a 1G page that miss in the L2 TLB.",
+    "UMask": "0x80"
+  },
+  {
+    "EventName": "ls_l1_d_tlb_miss.tlb_reload_2m_l2_miss",
+    "EventCode": "0x45",
+    "BriefDescription": "L1 DTLB Miss. DTLB reload to a 2M page that miss in the L2 TLB.",
+    "UMask": "0x40"
+  },
+  {
+    "EventName": "ls_l1_d_tlb_miss.tlb_reload_coalesced_page_miss",
+    "EventCode": "0x45",
+    "BriefDescription": "L1 DTLB Miss. DTLB reload coalesced page miss.",
+    "UMask": "0x20"
+  },
+  {
+    "EventName": "ls_l1_d_tlb_miss.tlb_reload_4k_l2_miss",
+    "EventCode": "0x45",
+    "BriefDescription": "L1 DTLB Miss. DTLB reload to a 4K page that miss the L2 TLB.",
+    "UMask": "0x10"
+  },
+  {
+    "EventName": "ls_l1_d_tlb_miss.tlb_reload_1g_l2_hit",
+    "EventCode": "0x45",
+    "BriefDescription": "L1 DTLB Miss. DTLB reload to a 1G page that hit in the L2 TLB.",
+    "UMask": "0x8"
+  },
+  {
+    "EventName": "ls_l1_d_tlb_miss.tlb_reload_2m_l2_hit",
+    "EventCode": "0x45",
+    "BriefDescription": "L1 DTLB Miss. DTLB reload to a 2M page that hit in the L2 TLB.",
+    "UMask": "0x4"
+  },
+  {
+    "EventName": "ls_l1_d_tlb_miss.tlb_reload_coalesced_page_hit",
+    "EventCode": "0x45",
+    "BriefDescription": "L1 DTLB Miss. DTLB reload hit a coalesced page.",
+    "UMask": "0x2"
+  },
+  {
+    "EventName": "ls_l1_d_tlb_miss.tlb_reload_4k_l2_hit",
+    "EventCode": "0x45",
+    "BriefDescription": "L1 DTLB Miss. DTLB reload to a 4K page that hit in the L2 TLB.",
+    "UMask": "0x1"
+  },
+  {
+    "EventName": "ls_tablewalker.iside",
+    "EventCode": "0x46",
+    "BriefDescription": "Total Page Table Walks on I-side.",
+    "UMask": "0xc"
+  },
+  {
+    "EventName": "ls_tablewalker.ic_type1",
+    "EventCode": "0x46",
+    "BriefDescription": "Total Page Table Walks IC Type 1.",
+    "UMask": "0x8"
+  },
+  {
+    "EventName": "ls_tablewalker.ic_type0",
+    "EventCode": "0x46",
+    "BriefDescription": "Total Page Table Walks IC Type 0.",
+    "UMask": "0x4"
+  },
+  {
+    "EventName": "ls_tablewalker.dside",
+    "EventCode": "0x46",
+    "BriefDescription": "Total Page Table Walks on D-side.",
+    "UMask": "0x3"
+  },
+  {
+    "EventName": "ls_tablewalker.dc_type1",
+    "EventCode": "0x46",
+    "BriefDescription": "Total Page Table Walks DC Type 1.",
+    "UMask": "0x2"
+  },
+  {
+    "EventName": "ls_tablewalker.dc_type0",
+    "EventCode": "0x46",
+    "BriefDescription": "Total Page Table Walks DC Type 0.",
+    "UMask": "0x1"
+  },
+  {
+    "EventName": "ls_misal_accesses",
+    "EventCode": "0x47",
+    "BriefDescription": "Misaligned loads."
+  },
+  {
+    "EventName": "ls_pref_instr_disp",
+    "EventCode": "0x4b",
+    "BriefDescription": "Software Prefetch Instructions Dispatched (Speculative).",
+    "UMask": "0xff"
+  },
+  {
+    "EventName": "ls_pref_instr_disp.prefetch_nta",
+    "EventCode": "0x4b",
+    "BriefDescription": "Software Prefetch Instructions Dispatched (Speculative). PrefetchNTA instruction. See docAPM3 PREFETCHlevel.",
+    "UMask": "0x4"
+  },
+  {
+    "EventName": "ls_pref_instr_disp.prefetch_w",
+    "EventCode": "0x4b",
+    "BriefDescription": "Software Prefetch Instructions Dispatched (Speculative). See docAPM3 PREFETCHW.",
+    "UMask": "0x2"
+  },
+  {
+    "EventName": "ls_pref_instr_disp.prefetch",
+    "EventCode": "0x4b",
+    "BriefDescription": "Software Prefetch Instructions Dispatched (Speculative). Prefetch_T0_T1_T2. PrefetchT0, T1 and T2 instructions. See docAPM3 PREFETCHlevel.",
+    "UMask": "0x1"
+  },
+  {
+    "EventName": "ls_inef_sw_pref.mab_mch_cnt",
+    "EventCode": "0x52",
+    "BriefDescription": "The number of software prefetches that did not fetch data outside of the processor core. Software PREFETCH instruction saw a match on an already-allocated miss request buffer.",
+    "UMask": "0x2"
+  },
+  {
+    "EventName": "ls_inef_sw_pref.data_pipe_sw_pf_dc_hit",
+    "EventCode": "0x52",
+    "BriefDescription": "The number of software prefetches that did not fetch data outside of the processor core. Software PREFETCH instruction saw a DC hit.",
+    "UMask": "0x1"
+  },
+  {
+    "EventName": "ls_sw_pf_dc_fill.ls_mabresp_rmt_dram",
+    "EventCode": "0x59",
+    "BriefDescription": "Software Prefetch Data Cache Fills by Data Source. From DRAM (home node remote).",
+    "UMask": "0x40"
+  },
+  {
+    "EventName": "ls_sw_pf_dc_fill.ls_mabresp_rmt_cache",
+    "EventCode": "0x59",
+    "BriefDescription": "Software Prefetch Data Cache Fills by Data Source. From another cache (home node remote).",
+    "UMask": "0x10"
+  },
+  {
+    "EventName": "ls_sw_pf_dc_fill.ls_mabresp_lcl_dram",
+    "EventCode": "0x59",
+    "BriefDescription": "Software Prefetch Data Cache Fills by Data Source. DRAM or IO from this thread's die.  From DRAM (home node local).",
+    "UMask": "0x8"
+  },
+  {
+    "EventName": "ls_sw_pf_dc_fill.ls_mabresp_lcl_cache",
+    "EventCode": "0x59",
+    "BriefDescription": "Software Prefetch Data Cache Fills by Data Source. From another cache (home node local).",
+    "UMask": "0x2"
+  },
+  {
+    "EventName": "ls_sw_pf_dc_fill.ls_mabresp_lcl_l2",
+    "EventCode": "0x59",
+    "BriefDescription": "Software Prefetch Data Cache Fills by Data Source. Local L2 hit.",
+    "UMask": "0x1"
+  },
+  {
+    "EventName": "ls_hw_pf_dc_fill.ls_mabresp_rmt_dram",
+    "EventCode": "0x5A",
+    "BriefDescription": "Hardware Prefetch Data Cache Fills by Data Source. From DRAM (home node remote).",
+    "UMask": "0x40"
+  },
+  {
+    "EventName": "ls_hw_pf_dc_fill.ls_mabresp_rmt_cache",
+    "EventCode": "0x5A",
+    "BriefDescription": "Hardware Prefetch Data Cache Fills by Data Source. From another cache (home node remote).",
+    "UMask": "0x10"
+  },
+  {
+    "EventName": "ls_hw_pf_dc_fill.ls_mabresp_lcl_dram",
+    "EventCode": "0x5A",
+    "BriefDescription": "Hardware Prefetch Data Cache Fills by Data Source. From DRAM (home node local).",
+    "UMask": "0x8"
+  },
+  {
+    "EventName": "ls_hw_pf_dc_fill.ls_mabresp_lcl_cache",
+    "EventCode": "0x5A",
+    "BriefDescription": "Hardware Prefetch Data Cache Fills by Data Source. From another cache (home node local).",
+    "UMask": "0x2"
+  },
+  {
+    "EventName": "ls_hw_pf_dc_fill.ls_mabresp_lcl_l2",
+    "EventCode": "0x5A",
+    "BriefDescription": "Hardware Prefetch Data Cache Fills by Data Source. Local L2 hit.",
+    "UMask": "0x1"
+  },
+  {
+    "EventName": "ls_not_halted_cyc",
+    "EventCode": "0x76",
+    "BriefDescription": "Cycles not in Halt."
+  },
+  {
+    "EventName": "ls_tlb_flush",
+    "EventCode": "0x78",
+    "BriefDescription": "All TLB Flushes"
+  }
+]

tools/perf/pmu-events/arch/x86/amdzen2/other.json

@@ -0,0 +1,115 @@
+[
+  {
+    "EventName": "de_dis_uop_queue_empty_di0",
+    "EventCode": "0xa9",
+    "BriefDescription": "Cycles where the Micro-Op Queue is empty."
+  },
+  {
+    "EventName": "de_dis_uops_from_decoder",
+    "EventCode": "0xaa",
+    "BriefDescription": "Ops dispatched from either the decoders, OpCache or both.",
+    "UMask": "0xff"
+  },
+  {
+    "EventName": "de_dis_uops_from_decoder.opcache_dispatched",
+    "EventCode": "0xaa",
+    "BriefDescription": "Count of dispatched Ops from OpCache.",
+    "UMask": "0x2"
+  },
+  {
+    "EventName": "de_dis_uops_from_decoder.decoder_dispatched",
+    "EventCode": "0xaa",
+    "BriefDescription": "Count of dispatched Ops from Decoder.",
+    "UMask": "0x1"
+  },
+  {
+    "EventName": "de_dis_dispatch_token_stalls1.fp_misc_rsrc_stall",
+    "EventCode": "0xae",
+    "BriefDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall. FP Miscellaneous resource unavailable. Applies to the recovery of mispredicts with FP ops.",
+    "UMask": "0x80"
+  },
+  {
+    "EventName": "de_dis_dispatch_token_stalls1.fp_sch_rsrc_stall",
+    "EventCode": "0xae",
+    "BriefDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall. FP scheduler resource stall. Applies to ops that use the FP scheduler.",
+    "UMask": "0x40"
+  },
+  {
+    "EventName": "de_dis_dispatch_token_stalls1.fp_reg_file_rsrc_stall",
+    "EventCode": "0xae",
+    "BriefDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall. Floating point register file resource stall. Applies to all FP ops that have a destination register.",
+    "UMask": "0x20"
+  },
+  {
+    "EventName": "de_dis_dispatch_token_stalls1.taken_branch_buffer_rsrc_stall",
+    "EventCode": "0xae",
+    "BriefDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall. Taken branch buffer resource stall.",
+    "UMask": "0x10"
+  },
+  {
+    "EventName": "de_dis_dispatch_token_stalls1.int_sched_misc_token_stall",
+    "EventCode": "0xae",
+    "BriefDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall. Integer Scheduler miscellaneous resource stall.",
+    "UMask": "0x8"
+  },
+  {
+    "EventName": "de_dis_dispatch_token_stalls1.store_queue_token_stall",
+    "EventCode": "0xae",
+    "BriefDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall. Store queue resource stall. Applies to all ops with store semantics.",
+    "UMask": "0x4"
+  },
+  {
+    "EventName": "de_dis_dispatch_token_stalls1.load_queue_token_stall",
+    "EventCode": "0xae",
+    "BriefDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall. Load queue resource stall. Applies to all ops with load semantics.",
+    "UMask": "0x2"
+  },
+  {
+    "EventName": "de_dis_dispatch_token_stalls1.int_phy_reg_file_token_stall",
+    "EventCode": "0xae",
+    "BriefDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall. Integer Physical Register File resource stall. Applies to all ops that have an integer destination register.",
+    "UMask": "0x1"
+  },
+  {
+    "EventName": "de_dis_dispatch_token_stalls0.sc_agu_dispatch_stall",
+    "EventCode": "0xaf",
+    "BriefDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall. SC AGU dispatch stall.",
+    "UMask": "0x40"
+  },
+  {
+    "EventName": "de_dis_dispatch_token_stalls0.retire_token_stall",
+    "EventCode": "0xaf",
+    "BriefDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall. RETIRE Tokens unavailable.",
+    "UMask": "0x20"
+  },
+  {
+    "EventName": "de_dis_dispatch_token_stalls0.agsq_token_stall",
+    "EventCode": "0xaf",
+    "BriefDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall. AGSQ Tokens unavailable.",
+    "UMask": "0x10"
+  },
+  {
+    "EventName": "de_dis_dispatch_token_stalls0.alu_token_stall",
+    "EventCode": "0xaf",
+    "BriefDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall. ALU tokens total unavailable.",
+    "UMask": "0x8"
+  },
+  {
+    "EventName": "de_dis_dispatch_token_stalls0.alsq3_0_token_stall",
+    "EventCode": "0xaf",
+    "BriefDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall. ALSQ3_0_TokenStall.",
+    "UMask": "0x4"
+  },
+  {
+    "EventName": "de_dis_dispatch_token_stalls0.alsq2_token_stall",
+    "EventCode": "0xaf",
+    "BriefDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall. ALSQ 2 Tokens unavailable.",
+    "UMask": "0x2"
+  },
+  {
+    "EventName": "de_dis_dispatch_token_stalls0.alsq1_token_stall",
+    "EventCode": "0xaf",
+    "BriefDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall. ALSQ 1 Tokens unavailable.",
+    "UMask": "0x1"
+  }
+]

tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json

@@ -297,7 +297,7 @@
     },
     {
         "BriefDescription": "Fraction of cycles spent in Kernel mode",
-        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:k / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricExpr": "CPU_CLK_UNHALTED.THREAD:k / CPU_CLK_UNHALTED.THREAD",
         "MetricGroup": "Summary",
         "MetricName": "Kernel_Utilization"
     },

tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json

@@ -115,7 +115,7 @@
     },
     {
         "BriefDescription": "Fraction of cycles spent in Kernel mode",
-        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:k / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricExpr": "CPU_CLK_UNHALTED.THREAD:k / CPU_CLK_UNHALTED.THREAD",
         "MetricGroup": "Summary",
         "MetricName": "Kernel_Utilization"
     },

tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json

@@ -297,7 +297,7 @@
     },
     {
         "BriefDescription": "Fraction of cycles spent in Kernel mode",
-        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:k / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricExpr": "CPU_CLK_UNHALTED.THREAD:k / CPU_CLK_UNHALTED.THREAD",
         "MetricGroup": "Summary",
         "MetricName": "Kernel_Utilization"
     },

tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json

@@ -316,7 +316,7 @@
     },
     {
         "BriefDescription": "Fraction of cycles spent in Kernel mode",
-        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:k / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricExpr": "CPU_CLK_UNHALTED.THREAD:k / CPU_CLK_UNHALTED.THREAD",
         "MetricGroup": "Summary",
         "MetricName": "Kernel_Utilization"
     },

tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json

@@ -267,7 +267,7 @@
     },
     {
         "BriefDescription": "Fraction of cycles spent in Kernel mode",
-        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:k / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricExpr": "CPU_CLK_UNHALTED.THREAD:k / CPU_CLK_UNHALTED.THREAD",
         "MetricGroup": "Summary",
         "MetricName": "Kernel_Utilization"
     },

tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json

@@ -267,7 +267,7 @@
     },
     {
         "BriefDescription": "Fraction of cycles spent in Kernel mode",
-        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:k / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricExpr": "CPU_CLK_UNHALTED.THREAD:k / CPU_CLK_UNHALTED.THREAD",
         "MetricGroup": "Summary",
         "MetricName": "Kernel_Utilization"
     },

tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json

@@ -285,7 +285,7 @@
     },
     {
         "BriefDescription": "Fraction of cycles spent in Kernel mode",
-        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:k / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricExpr": "CPU_CLK_UNHALTED.THREAD:k / CPU_CLK_UNHALTED.THREAD",
         "MetricGroup": "Summary",
         "MetricName": "Kernel_Utilization"
     },

tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json

@@ -285,7 +285,7 @@
     },
     {
         "BriefDescription": "Fraction of cycles spent in Kernel mode",
-        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:k / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricExpr": "CPU_CLK_UNHALTED.THREAD:k / CPU_CLK_UNHALTED.THREAD",
         "MetricGroup": "Summary",
         "MetricName": "Kernel_Utilization"
     },

tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json

@@ -171,7 +171,7 @@
     },
     {
         "BriefDescription": "Fraction of cycles spent in Kernel mode",
-        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:k / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricExpr": "CPU_CLK_UNHALTED.THREAD:k / CPU_CLK_UNHALTED.THREAD",
         "MetricGroup": "Summary",
         "MetricName": "Kernel_Utilization"
     },

tools/perf/pmu-events/arch/x86/mapfile.csv

@@ -36,4 +36,5 @@ GenuineIntel-6-55-[56789ABCDEF],v1,cascadelakex,core
 GenuineIntel-6-7D,v1,icelake,core
 GenuineIntel-6-7E,v1,icelake,core
 GenuineIntel-6-86,v1,tremontx,core
-AuthenticAMD-23-[[:xdigit:]]+,v1,amdfam17h,core
+AuthenticAMD-23-([12][0-9A-F]|[0-9A-F]),v2,amdzen1,core
+AuthenticAMD-23-[[:xdigit:]]+,v1,amdzen2,core

tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json

@@ -171,7 +171,7 @@
     },
     {
         "BriefDescription": "Fraction of cycles spent in Kernel mode",
-        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:k / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricExpr": "CPU_CLK_UNHALTED.THREAD:k / CPU_CLK_UNHALTED.THREAD",
         "MetricGroup": "Summary",
         "MetricName": "Kernel_Utilization"
     },

tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json

@@ -304,7 +304,7 @@
     },
     {
         "BriefDescription": "Fraction of cycles spent in Kernel mode",
-        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:k / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricExpr": "CPU_CLK_UNHALTED.THREAD:k / CPU_CLK_UNHALTED.THREAD",
         "MetricGroup": "Summary",
         "MetricName": "Kernel_Utilization"
     },

tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json

@@ -316,7 +316,7 @@
     },
     {
         "BriefDescription": "Fraction of cycles spent in Kernel mode",
-        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:k / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricExpr": "CPU_CLK_UNHALTED.THREAD:k / CPU_CLK_UNHALTED.THREAD",
         "MetricGroup": "Summary",
         "MetricName": "Kernel_Utilization"
     },

tools/perf/pmu-events/jevents.c

@@ -771,6 +771,19 @@ static void print_mapping_table_suffix(FILE *outfp)
 	fprintf(outfp, "};\n");
 }
 
+static void print_mapping_test_table(FILE *outfp)
+{
+	/*
+	 * Print the terminating, NULL entry.
+	 */
+	fprintf(outfp, "{\n");
+	fprintf(outfp, "\t.cpuid = \"testcpu\",\n");
+	fprintf(outfp, "\t.version = \"v1\",\n");
+	fprintf(outfp, "\t.type = \"core\",\n");
+	fprintf(outfp, "\t.table = pme_test_cpu,\n");
+	fprintf(outfp, "},\n");
+}
+
 static int process_mapfile(FILE *outfp, char *fpath)
 {
 	int n = 16384;
@@ -848,6 +861,7 @@ static int process_mapfile(FILE *outfp, char *fpath)
 	}
 
 out:
+	print_mapping_test_table(outfp);
 	print_mapping_table_suffix(outfp);
 	fclose(mapfp);
 	free(line);
@@ -1168,6 +1182,22 @@ int main(int argc, char *argv[])
 		goto empty_map;
 	}
 
+	sprintf(ldirname, "%s/test", start_dirname);
+
+	rc = nftw(ldirname, process_one_file, maxfds, 0);
+	if (rc && verbose) {
+		pr_info("%s: Error walking file tree %s rc=%d for test\n",
+			prog, ldirname, rc);
+		goto empty_map;
+	} else if (rc < 0) {
+		/* Make build fail */
+		free_arch_std_events();
+		ret = 1;
+		goto out_free_mapfile;
+	} else if (rc) {
+		goto empty_map;
+	}
+
 	if (close_table)
 		print_events_table_suffix(eventsfp);
 

tools/perf/tests/Build

@@ -14,6 +14,7 @@ perf-y += evsel-roundtrip-name.o
 perf-y += evsel-tp-sched.o
 perf-y += fdarray.o
 perf-y += pmu.o
+perf-y += pmu-events.o
 perf-y += hists_common.o
 perf-y += hists_link.o
 perf-y += hists_filter.o

tools/perf/tests/builtin-test.c

@@ -72,6 +72,10 @@ static struct test generic_tests[] = {
 		.desc = "Parse perf pmu format",
 		.func = test__pmu,
 	},
+	{
+		.desc = "PMU events",
+		.func = test__pmu_events,
+	},
 	{
 		.desc = "DSO data read",
 		.func = test__dso_data,

tools/perf/tests/make

@@ -28,9 +28,13 @@ endif
 
 PARALLEL_OPT=
 ifeq ($(SET_PARALLEL),1)
-  cores := $(shell (getconf _NPROCESSORS_ONLN || egrep -c '^processor|^CPU[0-9]' /proc/cpuinfo) 2>/dev/null)
-  ifeq ($(cores),0)
-    cores := 1
+  ifeq ($(JOBS),)
+    cores := $(shell (getconf _NPROCESSORS_ONLN || egrep -c '^processor|^CPU[0-9]' /proc/cpuinfo) 2>/dev/null)
+    ifeq ($(cores),0)
+      cores := 1
+    endif
+  else
+    cores=$(JOBS)
   endif
   PARALLEL_OPT="-j$(cores)"
 endif

tools/perf/tests/pmu-events.c

@@ -0,0 +1,379 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "parse-events.h"
+#include "pmu.h"
+#include "tests.h"
+#include <errno.h>
+#include <stdio.h>
+#include <linux/kernel.h>
+#include <linux/zalloc.h>
+#include "debug.h"
+#include "../pmu-events/pmu-events.h"
+
+struct perf_pmu_test_event {
+	struct pmu_event event;
+
+	/* extra events for aliases */
+	const char *alias_str;
+
+	/*
+	 * Note: For when PublicDescription does not exist in the JSON, we
+	 * will have no long_desc in pmu_event.long_desc, but long_desc may
+	 * be set in the alias.
+	 */
+	const char *alias_long_desc;
+};
+
+static struct perf_pmu_test_event test_cpu_events[] = {
+	{
+		.event = {
+			.name = "bp_l1_btb_correct",
+			.event = "event=0x8a",
+			.desc = "L1 BTB Correction",
+			.topic = "branch",
+		},
+		.alias_str = "event=0x8a",
+		.alias_long_desc = "L1 BTB Correction",
+	},
+	{
+		.event = {
+			.name = "bp_l2_btb_correct",
+			.event = "event=0x8b",
+			.desc = "L2 BTB Correction",
+			.topic = "branch",
+		},
+		.alias_str = "event=0x8b",
+		.alias_long_desc = "L2 BTB Correction",
+	},
+	{
+		.event = {
+			.name = "segment_reg_loads.any",
+			.event = "umask=0x80,period=200000,event=0x6",
+			.desc = "Number of segment register loads",
+			.topic = "other",
+		},
+		.alias_str = "umask=0x80,(null)=0x30d40,event=0x6",
+		.alias_long_desc = "Number of segment register loads",
+	},
+	{
+		.event = {
+			.name = "dispatch_blocked.any",
+			.event = "umask=0x20,period=200000,event=0x9",
+			.desc = "Memory cluster signals to block micro-op dispatch for any reason",
+			.topic = "other",
+		},
+		.alias_str = "umask=0x20,(null)=0x30d40,event=0x9",
+		.alias_long_desc = "Memory cluster signals to block micro-op dispatch for any reason",
+	},
+	{
+		.event = {
+			.name = "eist_trans",
+			.event = "umask=0x0,period=200000,event=0x3a",
+			.desc = "Number of Enhanced Intel SpeedStep(R) Technology (EIST) transitions",
+			.topic = "other",
+		},
+		.alias_str = "umask=0,(null)=0x30d40,event=0x3a",
+		.alias_long_desc = "Number of Enhanced Intel SpeedStep(R) Technology (EIST) transitions",
+	},
+	{ /* sentinel */
+		.event = {
+			.name = NULL,
+		},
+	},
+};
+
+static struct perf_pmu_test_event test_uncore_events[] = {
+	{
+		.event = {
+			.name = "uncore_hisi_ddrc.flux_wcmd",
+			.event = "event=0x2",
+			.desc = "DDRC write commands. Unit: hisi_sccl,ddrc ",
+			.topic = "uncore",
+			.long_desc = "DDRC write commands",
+			.pmu = "hisi_sccl,ddrc",
+		},
+		.alias_str = "event=0x2",
+		.alias_long_desc = "DDRC write commands",
+	},
+	{
+		.event = {
+			.name = "unc_cbo_xsnp_response.miss_eviction",
+			.event = "umask=0x81,event=0x22",
+			.desc = "Unit: uncore_cbox A cross-core snoop resulted from L3 Eviction which misses in some processor core",
+			.topic = "uncore",
+			.long_desc = "A cross-core snoop resulted from L3 Eviction which misses in some processor core",
+			.pmu = "uncore_cbox",
+		},
+		.alias_str = "umask=0x81,event=0x22",
+		.alias_long_desc = "A cross-core snoop resulted from L3 Eviction which misses in some processor core",
+	},
+	{ /* sentinel */
+		.event = {
+			.name = NULL,
+		},
+	}
+};
+
+const int total_test_events_size = ARRAY_SIZE(test_uncore_events);
+
+static bool is_same(const char *reference, const char *test)
+{
+	if (!reference && !test)
+		return true;
+
+	if (reference && !test)
+		return false;
+
+	if (!reference && test)
+		return false;
+
+	return !strcmp(reference, test);
+}
+
+static struct pmu_events_map *__test_pmu_get_events_map(void)
+{
+	struct pmu_events_map *map;
+
+	for (map = &pmu_events_map[0]; map->cpuid; map++) {
+		if (!strcmp(map->cpuid, "testcpu"))
+			return map;
+	}
+
+	pr_err("could not find test events map\n");
+
+	return NULL;
+}
+
+/* Verify generated events from pmu-events.c is as expected */
+static int __test_pmu_event_table(void)
+{
+	struct pmu_events_map *map = __test_pmu_get_events_map();
+	struct pmu_event *table;
+	int map_events = 0, expected_events;
+
+	/* ignore 2x sentinels */
+	expected_events = ARRAY_SIZE(test_cpu_events) +
+			  ARRAY_SIZE(test_uncore_events) - 2;
+
+	if (!map)
+		return -1;
+
+	for (table = map->table; table->name; table++) {
+		struct perf_pmu_test_event *test;
+		struct pmu_event *te;
+		bool found = false;
+
+		if (table->pmu)
+			test = &test_uncore_events[0];
+		else
+			test = &test_cpu_events[0];
+
+		te = &test->event;
+
+		for (; te->name; test++, te = &test->event) {
+			if (strcmp(table->name, te->name))
+				continue;
+			found = true;
+			map_events++;
+
+			if (!is_same(table->desc, te->desc)) {
+				pr_debug2("testing event table %s: mismatched desc, %s vs %s\n",
+					  table->name, table->desc, te->desc);
+				return -1;
+			}
+
+			if (!is_same(table->topic, te->topic)) {
+				pr_debug2("testing event table %s: mismatched topic, %s vs %s\n",
+					  table->name, table->topic,
+					  te->topic);
+				return -1;
+			}
+
+			if (!is_same(table->long_desc, te->long_desc)) {
+				pr_debug2("testing event table %s: mismatched long_desc, %s vs %s\n",
+					  table->name, table->long_desc,
+					  te->long_desc);
+				return -1;
+			}
+
+			if (!is_same(table->unit, te->unit)) {
+				pr_debug2("testing event table %s: mismatched unit, %s vs %s\n",
+					  table->name, table->unit,
+					  te->unit);
+				return -1;
+			}
+
+			if (!is_same(table->perpkg, te->perpkg)) {
+				pr_debug2("testing event table %s: mismatched perpkg, %s vs %s\n",
+					  table->name, table->perpkg,
+					  te->perpkg);
+				return -1;
+			}
+
+			if (!is_same(table->metric_expr, te->metric_expr)) {
+				pr_debug2("testing event table %s: mismatched metric_expr, %s vs %s\n",
+					  table->name, table->metric_expr,
+					  te->metric_expr);
+				return -1;
+			}
+
+			if (!is_same(table->metric_name, te->metric_name)) {
+				pr_debug2("testing event table %s: mismatched metric_name, %s vs %s\n",
+					  table->name,  table->metric_name,
+					  te->metric_name);
+				return -1;
+			}
+
+			if (!is_same(table->deprecated, te->deprecated)) {
+				pr_debug2("testing event table %s: mismatched deprecated, %s vs %s\n",
+					  table->name, table->deprecated,
+					  te->deprecated);
+				return -1;
+			}
+
+			pr_debug("testing event table %s: pass\n", table->name);
+		}
+
+		if (!found) {
+			pr_err("testing event table: could not find event %s\n",
+			       table->name);
+			return -1;
+		}
+	}
+
+	if (map_events != expected_events) {
+		pr_err("testing event table: found %d, but expected %d\n",
+		       map_events, expected_events);
+		return -1;
+	}
+
+	return 0;
+}
+
+static struct perf_pmu_alias *find_alias(const char *test_event, struct list_head *aliases)
+{
+	struct perf_pmu_alias *alias;
+
+	list_for_each_entry(alias, aliases, list)
+		if (!strcmp(test_event, alias->name))
+			return alias;
+
+	return NULL;
+}
+
+/* Verify aliases are as expected */
+static int __test__pmu_event_aliases(char *pmu_name, int *count)
+{
+	struct perf_pmu_test_event *test;
+	struct pmu_event *te;
+	struct perf_pmu *pmu;
+	LIST_HEAD(aliases);
+	int res = 0;
+	bool use_uncore_table;
+	struct pmu_events_map *map = __test_pmu_get_events_map();
+
+	if (!map)
+		return -1;
+
+	if (is_pmu_core(pmu_name)) {
+		test = &test_cpu_events[0];
+		use_uncore_table = false;
+	} else {
+		test = &test_uncore_events[0];
+		use_uncore_table = true;
+	}
+
+	pmu = zalloc(sizeof(*pmu));
+	if (!pmu)
+		return -1;
+
+	pmu->name = pmu_name;
+
+	pmu_add_cpu_aliases_map(&aliases, pmu, map);
+
+	for (te = &test->event; te->name; test++, te = &test->event) {
+		struct perf_pmu_alias *alias = find_alias(te->name, &aliases);
+
+		if (!alias) {
+			bool uncore_match = pmu_uncore_alias_match(pmu_name,
+								   te->pmu);
+
+			if (use_uncore_table && !uncore_match) {
+				pr_debug3("testing aliases PMU %s: skip matching alias %s\n",
+					  pmu_name, te->name);
+				continue;
+			}
+
+			pr_debug2("testing aliases PMU %s: no alias, alias_table->name=%s\n",
+				  pmu_name, te->name);
+			res = -1;
+			break;
+		}
+
+		if (!is_same(alias->desc, te->desc)) {
+			pr_debug2("testing aliases PMU %s: mismatched desc, %s vs %s\n",
+				  pmu_name, alias->desc, te->desc);
+			res = -1;
+			break;
+		}
+
+		if (!is_same(alias->long_desc, test->alias_long_desc)) {
+			pr_debug2("testing aliases PMU %s: mismatched long_desc, %s vs %s\n",
+				  pmu_name, alias->long_desc,
+				  test->alias_long_desc);
+			res = -1;
+			break;
+		}
+
+		if (!is_same(alias->str, test->alias_str)) {
+			pr_debug2("testing aliases PMU %s: mismatched str, %s vs %s\n",
+				  pmu_name, alias->str, test->alias_str);
+			res = -1;
+			break;
+		}
+
+		if (!is_same(alias->topic, te->topic)) {
+			pr_debug2("testing aliases PMU %s: mismatched topic, %s vs %s\n",
+				  pmu_name, alias->topic, te->topic);
+			res = -1;
+			break;
+		}
+
+		(*count)++;
+		pr_debug2("testing aliases PMU %s: matched event %s\n",
+			  pmu_name, alias->name);
+	}
+
+	free(pmu);
+	return res;
+}
+
+int test__pmu_events(struct test *test __maybe_unused,
+		     int subtest __maybe_unused)
+{
+	struct perf_pmu *pmu = NULL;
+
+	if (__test_pmu_event_table())
+		return -1;
+
+	while ((pmu = perf_pmu__scan(pmu)) != NULL) {
+		int count = 0;
+
+		if (list_empty(&pmu->format)) {
+			pr_debug2("skipping testing PMU %s\n", pmu->name);
+			continue;
+		}
+
+		if (__test__pmu_event_aliases(pmu->name, &count)) {
+			pr_debug("testing PMU %s aliases: failed\n", pmu->name);
+			return -1;
+		}
+
+		if (count == 0)
+			pr_debug3("testing PMU %s aliases: no events to match\n",
+				  pmu->name);
+		else
+			pr_debug("testing PMU %s aliases: pass\n", pmu->name);
+	}
+
+	return 0;
+}

tools/perf/tests/sample-parsing.c

@@ -151,6 +151,9 @@ static bool samples_same(const struct perf_sample *s1,
 	if (type & PERF_SAMPLE_PHYS_ADDR)
 		COMP(phys_addr);
 
+	if (type & PERF_SAMPLE_CGROUP)
+		COMP(cgroup);
+
 	if (type & PERF_SAMPLE_AUX) {
 		COMP(aux_sample.size);
 		if (memcmp(s1->aux_sample.data, s2->aux_sample.data,
@@ -230,6 +233,7 @@ static int do_test(u64 sample_type, u64 sample_regs, u64 read_format)
 			.regs	= regs,
 		},
 		.phys_addr	= 113,
+		.cgroup		= 114,
 		.aux_sample	= {
 			.size	= sizeof(aux_data),
 			.data	= (void *)aux_data,
@@ -336,7 +340,7 @@ int test__sample_parsing(struct test *test __maybe_unused, int subtest __maybe_u
 	 * were added.  Please actually update the test rather than just change
 	 * the condition below.
 	 */
-	if (PERF_SAMPLE_MAX > PERF_SAMPLE_AUX << 1) {
+	if (PERF_SAMPLE_MAX > PERF_SAMPLE_CGROUP << 1) {
 		pr_debug("sample format has changed, some new PERF_SAMPLE_ bit was introduced - test needs updating\n");
 		return -1;
 	}

tools/perf/tests/tests.h

@@ -49,6 +49,7 @@ int test__perf_evsel__roundtrip_name_test(struct test *test, int subtest);
 int test__perf_evsel__tp_sched_test(struct test *test, int subtest);
 int test__syscall_openat_tp_fields(struct test *test, int subtest);
 int test__pmu(struct test *test, int subtest);
+int test__pmu_events(struct test *test, int subtest);
 int test__attr(struct test *test, int subtest);
 int test__dso_data(struct test *test, int subtest);
 int test__dso_data_cache(struct test *test, int subtest);

tools/perf/ui/browsers/hists.c

@@ -677,7 +677,7 @@ static int hist_browser__title(struct hist_browser *browser, char *bf, size_t si
 	return browser->title ? browser->title(browser, bf, size) : 0;
 }
 
-static int hist_browser__handle_hotkey(struct hist_browser *browser, bool warn_lost_event, char *title, int key)
+static int hist_browser__handle_hotkey(struct hist_browser *browser, bool warn_lost_event, char *title, size_t size, int key)
 {
 	switch (key) {
 	case K_TIMER: {
@@ -703,7 +703,7 @@ static int hist_browser__handle_hotkey(struct hist_browser *browser, bool warn_l
 			ui_browser__warn_lost_events(&browser->b);
 		}
 
-		hist_browser__title(browser, title, sizeof(title));
+		hist_browser__title(browser, title, size);
 		ui_browser__show_title(&browser->b, title);
 		break;
 	}
@@ -764,13 +764,13 @@ int hist_browser__run(struct hist_browser *browser, const char *help,
 	if (ui_browser__show(&browser->b, title, "%s", help) < 0)
 		return -1;
 
-	if (key && hist_browser__handle_hotkey(browser, warn_lost_event, title, key))
+	if (key && hist_browser__handle_hotkey(browser, warn_lost_event, title, sizeof(title), key))
 		goto out;
 
 	while (1) {
 		key = ui_browser__run(&browser->b, delay_secs);
 
-		if (hist_browser__handle_hotkey(browser, warn_lost_event, title, key))
+		if (hist_browser__handle_hotkey(browser, warn_lost_event, title, sizeof(title), key))
 			break;
 	}
 out:
@@ -2465,13 +2465,41 @@ do_annotate(struct hist_browser *browser, struct popup_action *act)
 	return 0;
 }
 
+static struct symbol *symbol__new_unresolved(u64 addr, struct map *map)
+{
+	struct annotated_source *src;
+	struct symbol *sym;
+	char name[64];
+
+	snprintf(name, sizeof(name), "%.*" PRIx64, BITS_PER_LONG / 4, addr);
+
+	sym = symbol__new(addr, ANNOTATION_DUMMY_LEN, 0, 0, name);
+	if (sym) {
+		src = symbol__hists(sym, 1);
+		if (!src) {
+			symbol__delete(sym);
+			return NULL;
+		}
+
+		dso__insert_symbol(map->dso, sym);
+	}
+
+	return sym;
+}
+
 static int
 add_annotate_opt(struct hist_browser *browser __maybe_unused,
 		 struct popup_action *act, char **optstr,
-		 struct map_symbol *ms)
+		 struct map_symbol *ms,
+		 u64 addr)
 {
-	if (ms->sym == NULL || ms->map->dso->annotate_warned ||
-	    symbol__annotation(ms->sym)->src == NULL)
+	if (!ms->map || !ms->map->dso || ms->map->dso->annotate_warned)
+		return 0;
+
+	if (!ms->sym)
+		ms->sym = symbol__new_unresolved(addr, ms->map);
+
+	if (ms->sym == NULL || symbol__annotation(ms->sym)->src == NULL)
 		return 0;
 
 	if (asprintf(optstr, "Annotate %s", ms->sym->name) < 0)
@@ -2964,7 +2992,8 @@ static int perf_evsel__hists_browse(struct evsel *evsel, int nr_events,
 	"s             Switch to another data file in PWD\n"
 	"t             Zoom into current Thread\n"
 	"V             Verbose (DSO names in callchains, etc)\n"
-	"/             Filter symbol by name";
+	"/             Filter symbol by name\n"
+	"0-9           Sort by event n in group";
 	static const char top_help[] = HIST_BROWSER_HELP_COMMON
 	"P             Print histograms to perf.hist.N\n"
 	"t             Zoom into current Thread\n"
@@ -3025,6 +3054,31 @@ do_hotkey:		 // key came straight from options ui__popup_menu()
 			 * go to the next or previous
 			 */
 			goto out_free_stack;
+		case '0' ... '9':
+			if (!symbol_conf.event_group ||
+			    evsel->core.nr_members < 2) {
+				snprintf(buf, sizeof(buf),
+					 "Sort by index only available with group events!");
+				helpline = buf;
+				continue;
+			}
+
+			if (key - '0' == symbol_conf.group_sort_idx)
+				continue;
+
+			symbol_conf.group_sort_idx = key - '0';
+
+			if (symbol_conf.group_sort_idx >= evsel->core.nr_members) {
+				snprintf(buf, sizeof(buf),
+					 "Max event group index to sort is %d (index from 0 to %d)",
+					 evsel->core.nr_members - 1,
+					 evsel->core.nr_members - 1);
+				helpline = buf;
+				continue;
+			}
+
+			key = K_RELOAD;
+			goto out_free_stack;
 		case 'a':
 			if (!hists__has(hists, sym)) {
 				ui_browser__warning(&browser->b, delay_secs * 2,
@@ -3033,21 +3087,45 @@ do_hotkey:		 // key came straight from options ui__popup_menu()
 				continue;
 			}
 
-			if (browser->selection == NULL ||
-			    browser->selection->sym == NULL ||
-			    browser->selection->map->dso->annotate_warned)
-				continue;
-
-			if (symbol__annotation(browser->selection->sym)->src == NULL) {
-				ui_browser__warning(&browser->b, delay_secs * 2,
-						    "No samples for the \"%s\" symbol.\n\n"
-						    "Probably appeared just in a callchain",
-						    browser->selection->sym->name);
+			if (!browser->selection ||
+			    !browser->selection->map ||
+			    !browser->selection->map->dso ||
+			    browser->selection->map->dso->annotate_warned) {
 				continue;
 			}
 
-			actions->ms.map = browser->selection->map;
-			actions->ms.sym = browser->selection->sym;
+			if (!browser->selection->sym) {
+				if (!browser->he_selection)
+					continue;
+
+				if (sort__mode == SORT_MODE__BRANCH) {
+					bi = browser->he_selection->branch_info;
+					if (!bi || !bi->to.ms.map)
+						continue;
+
+					actions->ms.sym = symbol__new_unresolved(bi->to.al_addr, bi->to.ms.map);
+					actions->ms.map = bi->to.ms.map;
+				} else {
+					actions->ms.sym = symbol__new_unresolved(browser->he_selection->ip,
+										 browser->selection->map);
+					actions->ms.map = browser->selection->map;
+				}
+
+				if (!actions->ms.sym)
+					continue;
+			} else {
+				if (symbol__annotation(browser->selection->sym)->src == NULL) {
+					ui_browser__warning(&browser->b, delay_secs * 2,
+						"No samples for the \"%s\" symbol.\n\n"
+						"Probably appeared just in a callchain",
+						browser->selection->sym->name);
+					continue;
+				}
+
+				actions->ms.map = browser->selection->map;
+				actions->ms.sym = browser->selection->sym;
+			}
+
 			do_annotate(browser, actions);
 			continue;
 		case 'P':
@@ -3219,17 +3297,20 @@ do_hotkey:		 // key came straight from options ui__popup_menu()
 			nr_options += add_annotate_opt(browser,
 						       &actions[nr_options],
 						       &options[nr_options],
-						       &bi->from.ms);
+						       &bi->from.ms,
+						       bi->from.al_addr);
 			if (bi->to.ms.sym != bi->from.ms.sym)
 				nr_options += add_annotate_opt(browser,
 							&actions[nr_options],
 							&options[nr_options],
-							&bi->to.ms);
+							&bi->to.ms,
+							bi->to.al_addr);
 		} else {
 			nr_options += add_annotate_opt(browser,
 						       &actions[nr_options],
 						       &options[nr_options],
-						       browser->selection);
+						       browser->selection,
+						       browser->he_selection->ip);
 		}
 skip_annotation:
 		nr_options += add_thread_opt(browser, &actions[nr_options],
@@ -3440,6 +3521,7 @@ browse_hists:
 					pos = perf_evsel__prev(pos);
 				goto browse_hists;
 			case K_SWITCH_INPUT_DATA:
+			case K_RELOAD:
 			case 'q':
 			case CTRL('c'):
 				goto out;

tools/perf/ui/hist.c

@@ -151,15 +151,90 @@ static int field_cmp(u64 field_a, u64 field_b)
 	return 0;
 }
 
+static int hist_entry__new_pair(struct hist_entry *a, struct hist_entry *b,
+				hpp_field_fn get_field, int nr_members,
+				u64 **fields_a, u64 **fields_b)
+{
+	u64 *fa = calloc(nr_members, sizeof(*fa)),
+	    *fb = calloc(nr_members, sizeof(*fb));
+	struct hist_entry *pair;
+
+	if (!fa || !fb)
+		goto out_free;
+
+	list_for_each_entry(pair, &a->pairs.head, pairs.node) {
+		struct evsel *evsel = hists_to_evsel(pair->hists);
+		fa[perf_evsel__group_idx(evsel)] = get_field(pair);
+	}
+
+	list_for_each_entry(pair, &b->pairs.head, pairs.node) {
+		struct evsel *evsel = hists_to_evsel(pair->hists);
+		fb[perf_evsel__group_idx(evsel)] = get_field(pair);
+	}
+
+	*fields_a = fa;
+	*fields_b = fb;
+	return 0;
+out_free:
+	free(fa);
+	free(fb);
+	*fields_a = *fields_b = NULL;
+	return -1;
+}
+
+static int __hpp__group_sort_idx(struct hist_entry *a, struct hist_entry *b,
+				 hpp_field_fn get_field, int idx)
+{
+	struct evsel *evsel = hists_to_evsel(a->hists);
+	u64 *fields_a, *fields_b;
+	int cmp, nr_members, ret, i;
+
+	cmp = field_cmp(get_field(a), get_field(b));
+	if (!perf_evsel__is_group_event(evsel))
+		return cmp;
+
+	nr_members = evsel->core.nr_members;
+	if (idx < 1 || idx >= nr_members)
+		return cmp;
+
+	ret = hist_entry__new_pair(a, b, get_field, nr_members, &fields_a, &fields_b);
+	if (ret) {
+		ret = cmp;
+		goto out;
+	}
+
+	ret = field_cmp(fields_a[idx], fields_b[idx]);
+	if (ret)
+		goto out;
+
+	for (i = 1; i < nr_members; i++) {
+		if (i != idx) {
+			ret = field_cmp(fields_a[i], fields_b[i]);
+			if (ret)
+				goto out;
+		}
+	}
+
+out:
+	free(fields_a);
+	free(fields_b);
+
+	return ret;
+}
+
 static int __hpp__sort(struct hist_entry *a, struct hist_entry *b,
 		       hpp_field_fn get_field)
 {
 	s64 ret;
 	int i, nr_members;
 	struct evsel *evsel;
-	struct hist_entry *pair;
 	u64 *fields_a, *fields_b;
 
+	if (symbol_conf.group_sort_idx && symbol_conf.event_group) {
+		return __hpp__group_sort_idx(a, b, get_field,
+					     symbol_conf.group_sort_idx);
+	}
+
 	ret = field_cmp(get_field(a), get_field(b));
 	if (ret || !symbol_conf.event_group)
 		return ret;
@@ -169,22 +244,10 @@ static int __hpp__sort(struct hist_entry *a, struct hist_entry *b,
 		return ret;
 
 	nr_members = evsel->core.nr_members;
-	fields_a = calloc(nr_members, sizeof(*fields_a));
-	fields_b = calloc(nr_members, sizeof(*fields_b));
-
-	if (!fields_a || !fields_b)
+	i = hist_entry__new_pair(a, b, get_field, nr_members, &fields_a, &fields_b);
+	if (i)
 		goto out;
 
-	list_for_each_entry(pair, &a->pairs.head, pairs.node) {
-		evsel = hists_to_evsel(pair->hists);
-		fields_a[perf_evsel__group_idx(evsel)] = get_field(pair);
-	}
-
-	list_for_each_entry(pair, &b->pairs.head, pairs.node) {
-		evsel = hists_to_evsel(pair->hists);
-		fields_b[perf_evsel__group_idx(evsel)] = get_field(pair);
-	}
-
 	for (i = 1; i < nr_members; i++) {
 		ret = field_cmp(fields_a[i], fields_b[i]);
 		if (ret)

tools/perf/ui/keysyms.h

@@ -25,5 +25,6 @@
 #define K_ERROR	 -2
 #define K_RESIZE -3
 #define K_SWITCH_INPUT_DATA -4
+#define K_RELOAD -5
 
 #endif /* _PERF_KEYSYMS_H_ */

tools/perf/util/annotate.h

@@ -74,6 +74,7 @@ bool ins__is_fused(struct arch *arch, const char *ins1, const char *ins2);
 #define ANNOTATION__CYCLES_WIDTH 6
 #define ANNOTATION__MINMAX_CYCLES_WIDTH 19
 #define ANNOTATION__AVG_IPC_WIDTH 36
+#define ANNOTATION_DUMMY_LEN	256
 
 struct annotation_options {
 	bool hide_src_code,

tools/perf/util/cgroup.c

@@ -191,3 +191,83 @@ int parse_cgroups(const struct option *opt, const char *str,
 	}
 	return 0;
 }
+
+static struct cgroup *__cgroup__findnew(struct rb_root *root, uint64_t id,
+					bool create, const char *path)
+{
+	struct rb_node **p = &root->rb_node;
+	struct rb_node *parent = NULL;
+	struct cgroup *cgrp;
+
+	while (*p != NULL) {
+		parent = *p;
+		cgrp = rb_entry(parent, struct cgroup, node);
+
+		if (cgrp->id == id)
+			return cgrp;
+
+		if (cgrp->id < id)
+			p = &(*p)->rb_left;
+		else
+			p = &(*p)->rb_right;
+	}
+
+	if (!create)
+		return NULL;
+
+	cgrp = malloc(sizeof(*cgrp));
+	if (cgrp == NULL)
+		return NULL;
+
+	cgrp->name = strdup(path);
+	if (cgrp->name == NULL) {
+		free(cgrp);
+		return NULL;
+	}
+
+	cgrp->fd = -1;
+	cgrp->id = id;
+	refcount_set(&cgrp->refcnt, 1);
+
+	rb_link_node(&cgrp->node, parent, p);
+	rb_insert_color(&cgrp->node, root);
+
+	return cgrp;
+}
+
+struct cgroup *cgroup__findnew(struct perf_env *env, uint64_t id,
+			       const char *path)
+{
+	struct cgroup *cgrp;
+
+	down_write(&env->cgroups.lock);
+	cgrp = __cgroup__findnew(&env->cgroups.tree, id, true, path);
+	up_write(&env->cgroups.lock);
+	return cgrp;
+}
+
+struct cgroup *cgroup__find(struct perf_env *env, uint64_t id)
+{
+	struct cgroup *cgrp;
+
+	down_read(&env->cgroups.lock);
+	cgrp = __cgroup__findnew(&env->cgroups.tree, id, false, NULL);
+	up_read(&env->cgroups.lock);
+	return cgrp;
+}
+
+void perf_env__purge_cgroups(struct perf_env *env)
+{
+	struct rb_node *node;
+	struct cgroup *cgrp;
+
+	down_write(&env->cgroups.lock);
+	while (!RB_EMPTY_ROOT(&env->cgroups.tree)) {
+		node = rb_first(&env->cgroups.tree);
+		cgrp = rb_entry(node, struct cgroup, node);
+
+		rb_erase(node, &env->cgroups.tree);
+		cgroup__put(cgrp);
+	}
+	up_write(&env->cgroups.lock);
+}

tools/perf/util/cgroup.h

@@ -3,16 +3,19 @@
 #define __CGROUP_H__
 
 #include <linux/refcount.h>
+#include <linux/rbtree.h>
+#include "util/env.h"
 
 struct option;
 
 struct cgroup {
-	char *name;
-	int fd;
-	refcount_t refcnt;
+	struct rb_node		node;
+	u64			id;
+	char			*name;
+	int			fd;
+	refcount_t		refcnt;
 };
 
-
 extern int nr_cgroups; /* number of explicit cgroups defined */
 
 struct cgroup *cgroup__get(struct cgroup *cgroup);
@@ -26,4 +29,10 @@ void evlist__set_default_cgroup(struct evlist *evlist, struct cgroup *cgroup);
 
 int parse_cgroups(const struct option *opt, const char *str, int unset);
 
+struct cgroup *cgroup__findnew(struct perf_env *env, uint64_t id,
+			       const char *path);
+struct cgroup *cgroup__find(struct perf_env *env, uint64_t id);
+
+void perf_env__purge_cgroups(struct perf_env *env);
+
 #endif /* __CGROUP_H__ */

tools/perf/util/cpumap.c

@@ -317,7 +317,7 @@ static void set_max_cpu_num(void)
 
 	/* get the highest possible cpu number for a sparse allocation */
 	ret = snprintf(path, PATH_MAX, "%s/devices/system/cpu/possible", mnt);
-	if (ret == PATH_MAX) {
+	if (ret >= PATH_MAX) {
 		pr_err("sysfs path crossed PATH_MAX(%d) size\n", PATH_MAX);
 		goto out;
 	}
@@ -328,7 +328,7 @@ static void set_max_cpu_num(void)
 
 	/* get the highest present cpu number for a sparse allocation */
 	ret = snprintf(path, PATH_MAX, "%s/devices/system/cpu/present", mnt);
-	if (ret == PATH_MAX) {
+	if (ret >= PATH_MAX) {
 		pr_err("sysfs path crossed PATH_MAX(%d) size\n", PATH_MAX);
 		goto out;
 	}
@@ -356,7 +356,7 @@ static void set_max_node_num(void)
 
 	/* get the highest possible cpu number for a sparse allocation */
 	ret = snprintf(path, PATH_MAX, "%s/devices/system/node/possible", mnt);
-	if (ret == PATH_MAX) {
+	if (ret >= PATH_MAX) {
 		pr_err("sysfs path crossed PATH_MAX(%d) size\n", PATH_MAX);
 		goto out;
 	}
@@ -441,7 +441,7 @@ int cpu__setup_cpunode_map(void)
 		return 0;
 
 	n = snprintf(path, PATH_MAX, "%s/devices/system/node", mnt);
-	if (n == PATH_MAX) {
+	if (n >= PATH_MAX) {
 		pr_err("sysfs path crossed PATH_MAX(%d) size\n", PATH_MAX);
 		return -1;
 	}
@@ -456,7 +456,7 @@ int cpu__setup_cpunode_map(void)
 			continue;
 
 		n = snprintf(buf, PATH_MAX, "%s/%s", path, dent1->d_name);
-		if (n == PATH_MAX) {
+		if (n >= PATH_MAX) {
 			pr_err("sysfs path crossed PATH_MAX(%d) size\n", PATH_MAX);
 			continue;
 		}

tools/perf/util/dsos.c

@@ -26,13 +26,29 @@ static int __dso_id__cmp(struct dso_id *a, struct dso_id *b)
 	return 0;
 }
 
+static bool dso_id__empty(struct dso_id *id)
+{
+	if (!id)
+		return true;
+
+	return !id->maj && !id->min && !id->ino && !id->ino_generation;
+}
+
+static void dso__inject_id(struct dso *dso, struct dso_id *id)
+{
+	dso->id.maj = id->maj;
+	dso->id.min = id->min;
+	dso->id.ino = id->ino;
+	dso->id.ino_generation = id->ino_generation;
+}
+
 static int dso_id__cmp(struct dso_id *a, struct dso_id *b)
 {
 	/*
 	 * The second is always dso->id, so zeroes if not set, assume passing
 	 * NULL for a means a zeroed id
 	 */
-	if (a == NULL)
+	if (dso_id__empty(a) || dso_id__empty(b))
 		return 0;
 
 	return __dso_id__cmp(a, b);
@@ -249,6 +265,10 @@ struct dso *__dsos__addnew(struct dsos *dsos, const char *name)
 static struct dso *__dsos__findnew_id(struct dsos *dsos, const char *name, struct dso_id *id)
 {
 	struct dso *dso = __dsos__find_id(dsos, name, id, false);
+
+	if (dso && dso_id__empty(&dso->id) && !dso_id__empty(id))
+		dso__inject_id(dso, id);
+
 	return dso ? dso : __dsos__addnew_id(dsos, name, id);
 }
 

tools/perf/util/env.c

@@ -6,6 +6,7 @@
 #include <linux/ctype.h>
 #include <linux/zalloc.h>
 #include "bpf-event.h"
+#include "cgroup.h"
 #include <errno.h>
 #include <sys/utsname.h>
 #include <bpf/libbpf.h>
@@ -168,6 +169,7 @@ void perf_env__exit(struct perf_env *env)
 	int i;
 
 	perf_env__purge_bpf(env);
+	perf_env__purge_cgroups(env);
 	zfree(&env->hostname);
 	zfree(&env->os_release);
 	zfree(&env->version);

tools/perf/util/env.h

@@ -88,6 +88,12 @@ struct perf_env {
 		u32			btfs_cnt;
 	} bpf_progs;
 
+	/* same reason as above (for perf-top) */
+	struct {
+		struct rw_semaphore	lock;
+		struct rb_root		tree;
+	} cgroups;
+
 	/* For fast cpu to numa node lookup via perf_env__numa_node */
 	int			*numa_map;
 	int			 nr_numa_map;

tools/perf/util/event.c

@@ -54,6 +54,7 @@ static const char *perf_event__names[] = {
 	[PERF_RECORD_NAMESPACES]		= "NAMESPACES",
 	[PERF_RECORD_KSYMBOL]			= "KSYMBOL",
 	[PERF_RECORD_BPF_EVENT]			= "BPF_EVENT",
+	[PERF_RECORD_CGROUP]			= "CGROUP",
 	[PERF_RECORD_HEADER_ATTR]		= "ATTR",
 	[PERF_RECORD_HEADER_EVENT_TYPE]		= "EVENT_TYPE",
 	[PERF_RECORD_HEADER_TRACING_DATA]	= "TRACING_DATA",
@@ -180,6 +181,12 @@ size_t perf_event__fprintf_namespaces(union perf_event *event, FILE *fp)
 	return ret;
 }
 
+size_t perf_event__fprintf_cgroup(union perf_event *event, FILE *fp)
+{
+	return fprintf(fp, " cgroup: %" PRI_lu64 " %s\n",
+		       event->cgroup.id, event->cgroup.path);
+}
+
 int perf_event__process_comm(struct perf_tool *tool __maybe_unused,
 			     union perf_event *event,
 			     struct perf_sample *sample,
@@ -196,6 +203,14 @@ int perf_event__process_namespaces(struct perf_tool *tool __maybe_unused,
 	return machine__process_namespaces_event(machine, event, sample);
 }
 
+int perf_event__process_cgroup(struct perf_tool *tool __maybe_unused,
+			       union perf_event *event,
+			       struct perf_sample *sample,
+			       struct machine *machine)
+{
+	return machine__process_cgroup_event(machine, event, sample);
+}
+
 int perf_event__process_lost(struct perf_tool *tool __maybe_unused,
 			     union perf_event *event,
 			     struct perf_sample *sample,
@@ -417,6 +432,9 @@ size_t perf_event__fprintf(union perf_event *event, FILE *fp)
 	case PERF_RECORD_NAMESPACES:
 		ret += perf_event__fprintf_namespaces(event, fp);
 		break;
+	case PERF_RECORD_CGROUP:
+		ret += perf_event__fprintf_cgroup(event, fp);
+		break;
 	case PERF_RECORD_MMAP2:
 		ret += perf_event__fprintf_mmap2(event, fp);
 		break;
@@ -599,10 +617,23 @@ int machine__resolve(struct machine *machine, struct addr_location *al,
 		al->sym = map__find_symbol(al->map, al->addr);
 	}
 
-	if (symbol_conf.sym_list &&
-		(!al->sym || !strlist__has_entry(symbol_conf.sym_list,
-						al->sym->name))) {
-		al->filtered |= (1 << HIST_FILTER__SYMBOL);
+	if (symbol_conf.sym_list) {
+		int ret = 0;
+		char al_addr_str[32];
+		size_t sz = sizeof(al_addr_str);
+
+		if (al->sym) {
+			ret = strlist__has_entry(symbol_conf.sym_list,
+						al->sym->name);
+		}
+		if (!(ret && al->sym)) {
+			snprintf(al_addr_str, sz, "0x%"PRIx64,
+				al->map->unmap_ip(al->map, al->sym->start));
+			ret = strlist__has_entry(symbol_conf.sym_list,
+						al_addr_str);
+		}
+		if (!ret)
+			al->filtered |= (1 << HIST_FILTER__SYMBOL);
 	}
 
 	return 0;

tools/perf/util/event.h

@@ -135,6 +135,7 @@ struct perf_sample {
 	u32 raw_size;
 	u64 data_src;
 	u64 phys_addr;
+	u64 cgroup;
 	u32 flags;
 	u16 insn_len;
 	u8  cpumode;
@@ -322,6 +323,10 @@ int perf_event__process_namespaces(struct perf_tool *tool,
 				   union perf_event *event,
 				   struct perf_sample *sample,
 				   struct machine *machine);
+int perf_event__process_cgroup(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,
@@ -377,6 +382,7 @@ 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_cgroup(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_ksymbol(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_bpf(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf(union perf_event *event, FILE *fp);

tools/perf/util/evsel.c

@@ -1104,6 +1104,11 @@ void perf_evsel__config(struct evsel *evsel, struct record_opts *opts,
 	if (opts->record_namespaces)
 		attr->namespaces  = track;
 
+	if (opts->record_cgroup) {
+		attr->cgroup = track && !perf_missing_features.cgroup;
+		perf_evsel__set_sample_bit(evsel, CGROUP);
+	}
+
 	if (opts->record_switch_events)
 		attr->context_switch = track;
 
@@ -1287,6 +1292,7 @@ void perf_evsel__exit(struct evsel *evsel)
 	perf_thread_map__put(evsel->core.threads);
 	zfree(&evsel->group_name);
 	zfree(&evsel->name);
+	zfree(&evsel->pmu_name);
 	perf_evsel__object.fini(evsel);
 }
 
@@ -1788,7 +1794,11 @@ try_fallback:
 	 * Must probe features in the order they were added to the
 	 * perf_event_attr interface.
 	 */
-	if (!perf_missing_features.branch_hw_idx &&
+        if (!perf_missing_features.cgroup && evsel->core.attr.cgroup) {
+		perf_missing_features.cgroup = true;
+		pr_debug2_peo("Kernel has no cgroup sampling support, bailing out\n");
+		goto out_close;
+        } else if (!perf_missing_features.branch_hw_idx &&
 	    (evsel->core.attr.branch_sample_type & PERF_SAMPLE_BRANCH_HW_INDEX)) {
 		perf_missing_features.branch_hw_idx = true;
 		pr_debug2("switching off branch HW index support\n");
@@ -2266,6 +2276,12 @@ int perf_evsel__parse_sample(struct evsel *evsel, union perf_event *event,
 		array++;
 	}
 
+	data->cgroup = 0;
+	if (type & PERF_SAMPLE_CGROUP) {
+		data->cgroup = *array;
+		array++;
+	}
+
 	if (type & PERF_SAMPLE_AUX) {
 		OVERFLOW_CHECK_u64(array);
 		sz = *array++;

tools/perf/util/evsel.h

@@ -120,6 +120,7 @@ struct perf_missing_features {
 	bool bpf;
 	bool aux_output;
 	bool branch_hw_idx;
+	bool cgroup;
 };
 
 extern struct perf_missing_features perf_missing_features;

tools/perf/util/hist.c

@@ -10,6 +10,7 @@
 #include "mem-events.h"
 #include "session.h"
 #include "namespaces.h"
+#include "cgroup.h"
 #include "sort.h"
 #include "units.h"
 #include "evlist.h"
@@ -194,6 +195,7 @@ 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, 6);
 	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);
@@ -222,6 +224,16 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
 
 	if (h->trace_output)
 		hists__new_col_len(hists, HISTC_TRACE, strlen(h->trace_output));
+
+	if (h->cgroup) {
+		const char *cgrp_name = "unknown";
+		struct cgroup *cgrp = cgroup__find(h->ms.maps->machine->env,
+						   h->cgroup);
+		if (cgrp != NULL)
+			cgrp_name = cgrp->name;
+
+		hists__new_col_len(hists, HISTC_CGROUP, strlen(cgrp_name));
+	}
 }
 
 void hists__output_recalc_col_len(struct hists *hists, int max_rows)
@@ -691,6 +703,7 @@ __hists__add_entry(struct hists *hists,
 			.dev = ns ? ns->link_info[CGROUP_NS_INDEX].dev : 0,
 			.ino = ns ? ns->link_info[CGROUP_NS_INDEX].ino : 0,
 		},
+		.cgroup = sample->cgroup,
 		.ms = {
 			.maps	= al->maps,
 			.map	= al->map,

tools/perf/util/hist.h

@@ -38,6 +38,7 @@ enum hist_column {
 	HISTC_THREAD,
 	HISTC_COMM,
 	HISTC_CGROUP_ID,
+	HISTC_CGROUP,
 	HISTC_PARENT,
 	HISTC_CPU,
 	HISTC_SOCKET,
@@ -536,6 +537,7 @@ static inline int block_hists_tui_browse(struct block_hist *bh __maybe_unused,
 #define K_LEFT  -1000
 #define K_RIGHT -2000
 #define K_SWITCH_INPUT_DATA -3000
+#define K_RELOAD -4000
 #endif
 
 unsigned int hists__sort_list_width(struct hists *hists);

tools/perf/util/machine.c

@@ -33,6 +33,7 @@
 #include "asm/bug.h"
 #include "bpf-event.h"
 #include <internal/lib.h> // page_size
+#include "cgroup.h"
 
 #include <linux/ctype.h>
 #include <symbol/kallsyms.h>
@@ -654,6 +655,22 @@ int machine__process_namespaces_event(struct machine *machine __maybe_unused,
 	return err;
 }
 
+int machine__process_cgroup_event(struct machine *machine,
+				  union perf_event *event,
+				  struct perf_sample *sample __maybe_unused)
+{
+	struct cgroup *cgrp;
+
+	if (dump_trace)
+		perf_event__fprintf_cgroup(event, stdout);
+
+	cgrp = cgroup__findnew(machine->env, event->cgroup.id, event->cgroup.path);
+	if (cgrp == NULL)
+		return -ENOMEM;
+
+	return 0;
+}
+
 int machine__process_lost_event(struct machine *machine __maybe_unused,
 				union perf_event *event, struct perf_sample *sample __maybe_unused)
 {
@@ -1878,6 +1895,8 @@ int machine__process_event(struct machine *machine, union perf_event *event,
 		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_CGROUP:
+		ret = machine__process_cgroup_event(machine, event, sample); break;
 	case PERF_RECORD_MMAP2:
 		ret = machine__process_mmap2_event(machine, event, sample); break;
 	case PERF_RECORD_FORK:

tools/perf/util/machine.h

@@ -128,6 +128,9 @@ int machine__process_switch_event(struct machine *machine,
 int machine__process_namespaces_event(struct machine *machine,
 				      union perf_event *event,
 				      struct perf_sample *sample);
+int machine__process_cgroup_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,

tools/perf/util/metricgroup.c

@@ -95,13 +95,16 @@ struct egroup {
 static struct evsel *find_evsel_group(struct evlist *perf_evlist,
 				      const char **ids,
 				      int idnum,
-				      struct evsel **metric_events)
+				      struct evsel **metric_events,
+				      bool *evlist_used)
 {
 	struct evsel *ev;
-	int i = 0;
+	int i = 0, j = 0;
 	bool leader_found;
 
 	evlist__for_each_entry (perf_evlist, ev) {
+		if (evlist_used[j++])
+			continue;
 		if (!strcmp(ev->name, ids[i])) {
 			if (!metric_events[i])
 				metric_events[i] = ev;
@@ -109,22 +112,17 @@ static struct evsel *find_evsel_group(struct evlist *perf_evlist,
 			if (i == idnum)
 				break;
 		} else {
-			if (i + 1 == idnum) {
-				/* Discard the whole match and start again */
-				i = 0;
-				memset(metric_events, 0,
-				       sizeof(struct evsel *) * idnum);
-				continue;
-			}
+			/* Discard the whole match and start again */
+			i = 0;
+			memset(metric_events, 0,
+				sizeof(struct evsel *) * idnum);
 
-			if (!strcmp(ev->name, ids[i]))
-				metric_events[i] = ev;
-			else {
-				/* Discard the whole match and start again */
-				i = 0;
-				memset(metric_events, 0,
-				       sizeof(struct evsel *) * idnum);
-				continue;
+			if (!strcmp(ev->name, ids[i])) {
+				if (!metric_events[i])
+					metric_events[i] = ev;
+				i++;
+				if (i == idnum)
+					break;
 			}
 		}
 	}
@@ -146,7 +144,10 @@ static struct evsel *find_evsel_group(struct evlist *perf_evlist,
 			    !strcmp(ev->name, metric_events[i]->name)) {
 				ev->metric_leader = metric_events[i];
 			}
+			j++;
 		}
+		ev = metric_events[i];
+		evlist_used[ev->idx] = true;
 	}
 
 	return metric_events[0];
@@ -162,6 +163,13 @@ static int metricgroup__setup_events(struct list_head *groups,
 	int ret = 0;
 	struct egroup *eg;
 	struct evsel *evsel;
+	bool *evlist_used;
+
+	evlist_used = calloc(perf_evlist->core.nr_entries, sizeof(bool));
+	if (!evlist_used) {
+		ret = -ENOMEM;
+		return ret;
+	}
 
 	list_for_each_entry (eg, groups, nd) {
 		struct evsel **metric_events;
@@ -172,7 +180,7 @@ static int metricgroup__setup_events(struct list_head *groups,
 			break;
 		}
 		evsel = find_evsel_group(perf_evlist, eg->ids, eg->idnum,
-					 metric_events);
+					 metric_events, evlist_used);
 		if (!evsel) {
 			pr_debug("Cannot resolve %s: %s\n",
 					eg->metric_name, eg->metric_expr);
@@ -196,6 +204,9 @@ static int metricgroup__setup_events(struct list_head *groups,
 		expr->metric_events = metric_events;
 		list_add(&expr->nd, &me->head);
 	}
+
+	free(evlist_used);
+
 	return ret;
 }
 

tools/perf/util/parse-events.c

@@ -1449,7 +1449,7 @@ int parse_events_add_pmu(struct parse_events_state *parse_state,
 		evsel = __add_event(list, &parse_state->idx, &attr, NULL, pmu, NULL,
 				    auto_merge_stats, NULL);
 		if (evsel) {
-			evsel->pmu_name = name;
+			evsel->pmu_name = name ? strdup(name) : NULL;
 			evsel->use_uncore_alias = use_uncore_alias;
 			return 0;
 		} else {
@@ -1497,7 +1497,7 @@ int parse_events_add_pmu(struct parse_events_state *parse_state,
 		evsel->snapshot = info.snapshot;
 		evsel->metric_expr = info.metric_expr;
 		evsel->metric_name = info.metric_name;
-		evsel->pmu_name = name;
+		evsel->pmu_name = name ? strdup(name) : NULL;
 		evsel->use_uncore_alias = use_uncore_alias;
 		evsel->percore = config_term_percore(&evsel->config_terms);
 	}
@@ -1547,7 +1547,7 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state,
 				if (!parse_events_add_pmu(parse_state, list,
 							  pmu->name, head,
 							  true, true)) {
-					pr_debug("%s -> %s/%s/\n", config,
+					pr_debug("%s -> %s/%s/\n", str,
 						 pmu->name, alias->str);
 					ok++;
 				}

tools/perf/util/parse-events.l

@@ -342,11 +342,13 @@ bpf-output					{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_BPF_OUT
 	 * Because the prefix cycles is mixed up with cpu-cycles.
 	 * loads and stores are mixed up with cache event
 	 */
-cycles-ct					{ return str(yyscanner, PE_KERNEL_PMU_EVENT); }
-cycles-t					{ return str(yyscanner, PE_KERNEL_PMU_EVENT); }
-mem-loads					{ return str(yyscanner, PE_KERNEL_PMU_EVENT); }
-mem-stores					{ return str(yyscanner, PE_KERNEL_PMU_EVENT); }
-topdown-[a-z-]+					{ return str(yyscanner, PE_KERNEL_PMU_EVENT); }
+cycles-ct				|
+cycles-t				|
+mem-loads				|
+mem-stores				|
+topdown-[a-z-]+				|
+tx-capacity-[a-z-]+			|
+el-capacity-[a-z-]+			{ return str(yyscanner, PE_KERNEL_PMU_EVENT); }
 
 L1-dcache|l1-d|l1d|L1-data		|
 L1-icache|l1-i|l1i|L1-instruction	|

tools/perf/util/perf_event_attr_fprintf.c

@@ -35,6 +35,7 @@ static void __p_sample_type(char *buf, size_t size, u64 value)
 		bit_name(BRANCH_STACK), bit_name(REGS_USER), bit_name(STACK_USER),
 		bit_name(IDENTIFIER), bit_name(REGS_INTR), bit_name(DATA_SRC),
 		bit_name(WEIGHT), bit_name(PHYS_ADDR), bit_name(AUX),
+		bit_name(CGROUP),
 		{ .name = NULL, }
 	};
 #undef bit_name
@@ -132,6 +133,7 @@ int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr,
 	PRINT_ATTRf(ksymbol, p_unsigned);
 	PRINT_ATTRf(bpf_event, p_unsigned);
 	PRINT_ATTRf(aux_output, p_unsigned);
+	PRINT_ATTRf(cgroup, p_unsigned);
 
 	PRINT_ATTRn("{ wakeup_events, wakeup_watermark }", wakeup_events, p_unsigned);
 	PRINT_ATTRf(bp_type, p_unsigned);

tools/perf/util/pmu.c

@@ -21,7 +21,6 @@
 #include "pmu.h"
 #include "parse-events.h"
 #include "header.h"
-#include "pmu-events/pmu-events.h"
 #include "string2.h"
 #include "strbuf.h"
 #include "fncache.h"
@@ -699,7 +698,7 @@ struct pmu_events_map *perf_pmu__find_map(struct perf_pmu *pmu)
 	return map;
 }
 
-static bool pmu_uncore_alias_match(const char *pmu_name, const char *name)
+bool pmu_uncore_alias_match(const char *pmu_name, const char *name)
 {
 	char *tmp = NULL, *tok, *str;
 	bool res;
@@ -744,16 +743,11 @@ out:
  * to the current running CPU. Then, add all PMU events from that table
  * as aliases.
  */
-static void pmu_add_cpu_aliases(struct list_head *head, struct perf_pmu *pmu)
+void pmu_add_cpu_aliases_map(struct list_head *head, struct perf_pmu *pmu,
+			     struct pmu_events_map *map)
 {
 	int i;
-	struct pmu_events_map *map;
 	const char *name = pmu->name;
-
-	map = perf_pmu__find_map(pmu);
-	if (!map)
-		return;
-
 	/*
 	 * Found a matching PMU events table. Create aliases
 	 */
@@ -788,6 +782,17 @@ new_alias:
 	}
 }
 
+static void pmu_add_cpu_aliases(struct list_head *head, struct perf_pmu *pmu)
+{
+	struct pmu_events_map *map;
+
+	map = perf_pmu__find_map(pmu);
+	if (!map)
+		return;
+
+	pmu_add_cpu_aliases_map(head, pmu, map);
+}
+
 struct perf_event_attr * __weak
 perf_pmu__get_default_config(struct perf_pmu *pmu __maybe_unused)
 {
@@ -979,12 +984,11 @@ static int pmu_resolve_param_term(struct parse_events_term *term,
 	struct parse_events_term *t;
 
 	list_for_each_entry(t, head_terms, list) {
-		if (t->type_val == PARSE_EVENTS__TERM_TYPE_NUM) {
-			if (!strcmp(t->config, term->config)) {
-				t->used = true;
-				*value = t->val.num;
-				return 0;
-			}
+		if (t->type_val == PARSE_EVENTS__TERM_TYPE_NUM &&
+		    t->config && !strcmp(t->config, term->config)) {
+			t->used = true;
+			*value = t->val.num;
+			return 0;
 		}
 	}
 
@@ -1395,6 +1399,11 @@ static void wordwrap(char *s, int start, int max, int corr)
 	}
 }
 
+bool is_pmu_core(const char *name)
+{
+	return !strcmp(name, "cpu") || is_arm_pmu_core(name);
+}
+
 void print_pmu_events(const char *event_glob, bool name_only, bool quiet_flag,
 			bool long_desc, bool details_flag, bool deprecated)
 {

tools/perf/util/pmu.h

@@ -7,6 +7,7 @@
 #include <linux/perf_event.h>
 #include <stdbool.h>
 #include "parse-events.h"
+#include "pmu-events/pmu-events.h"
 
 struct perf_evsel_config_term;
 
@@ -87,6 +88,7 @@ int perf_pmu__format_parse(char *dir, struct list_head *head);
 
 struct perf_pmu *perf_pmu__scan(struct perf_pmu *pmu);
 
+bool is_pmu_core(const char *name);
 void print_pmu_events(const char *event_glob, bool name_only, bool quiet,
 		      bool long_desc, bool details_flag,
 		      bool deprecated);
@@ -97,8 +99,11 @@ int perf_pmu__scan_file(struct perf_pmu *pmu, const char *name, const char *fmt,
 int perf_pmu__test(void);
 
 struct perf_event_attr *perf_pmu__get_default_config(struct perf_pmu *pmu);
+void pmu_add_cpu_aliases_map(struct list_head *head, struct perf_pmu *pmu,
+			     struct pmu_events_map *map);
 
 struct pmu_events_map *perf_pmu__find_map(struct perf_pmu *pmu);
+bool pmu_uncore_alias_match(const char *pmu_name, const char *name);
 
 int perf_pmu__convert_scale(const char *scale, char **end, double *sval);
 

tools/perf/util/python-ext-sources

@@ -34,3 +34,4 @@ util/string.c
 util/symbol_fprintf.c
 util/units.c
 util/affinity.c
+util/rwsem.c

tools/perf/util/record.h

@@ -34,6 +34,7 @@ struct record_opts {
 	bool	      auxtrace_snapshot_on_exit;
 	bool	      auxtrace_sample_mode;
 	bool	      record_namespaces;
+	bool	      record_cgroup;
 	bool	      record_switch_events;
 	bool	      all_kernel;
 	bool	      all_user;

tools/perf/util/scripting-engines/trace-event-python.c

@@ -694,6 +694,9 @@ static int regs_map(struct regs_dump *regs, uint64_t mask, char *bf, int size)
 
 	bf[0] = 0;
 
+	if (!regs || !regs->regs)
+		return 0;
+
 	for_each_set_bit(r, (unsigned long *) &mask, sizeof(mask) * 8) {
 		u64 val = regs->regs[i++];
 

tools/perf/util/session.c

@@ -471,6 +471,8 @@ void perf_tool__fill_defaults(struct perf_tool *tool)
 		tool->comm = process_event_stub;
 	if (tool->namespaces == NULL)
 		tool->namespaces = process_event_stub;
+	if (tool->cgroup == NULL)
+		tool->cgroup = process_event_stub;
 	if (tool->fork == NULL)
 		tool->fork = process_event_stub;
 	if (tool->exit == NULL)
@@ -1436,6 +1438,8 @@ static int machines__deliver_event(struct machines *machines,
 		return tool->comm(tool, event, sample, machine);
 	case PERF_RECORD_NAMESPACES:
 		return tool->namespaces(tool, event, sample, machine);
+	case PERF_RECORD_CGROUP:
+		return tool->cgroup(tool, event, sample, machine);
 	case PERF_RECORD_FORK:
 		return tool->fork(tool, event, sample, machine);
 	case PERF_RECORD_EXIT:

tools/perf/util/setup.py

@@ -3,7 +3,7 @@ from subprocess import Popen, PIPE
 from re import sub
 
 cc = getenv("CC")
-cc_is_clang = b"clang version" in Popen([cc, "-v"], stderr=PIPE).stderr.readline()
+cc_is_clang = b"clang version" in Popen([cc.split()[0], "-v"], stderr=PIPE).stderr.readline()
 
 def clang_has_option(option):
     return [o for o in Popen([cc, option], stderr=PIPE).stderr.readlines() if b"unknown argument" in o] == [ ]

tools/perf/util/sort.c

@@ -12,6 +12,7 @@
 #include "cacheline.h"
 #include "comm.h"
 #include "map.h"
+#include "maps.h"
 #include "symbol.h"
 #include "map_symbol.h"
 #include "branch.h"
@@ -25,6 +26,8 @@
 #include "mem-events.h"
 #include "annotate.h"
 #include "time-utils.h"
+#include "cgroup.h"
+#include "machine.h"
 #include <linux/kernel.h>
 #include <linux/string.h>
 
@@ -634,6 +637,39 @@ struct sort_entry sort_cgroup_id = {
 	.se_width_idx	= HISTC_CGROUP_ID,
 };
 
+/* --sort cgroup */
+
+static int64_t
+sort__cgroup_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	return right->cgroup - left->cgroup;
+}
+
+static int hist_entry__cgroup_snprintf(struct hist_entry *he,
+				       char *bf, size_t size,
+				       unsigned int width __maybe_unused)
+{
+	const char *cgrp_name = "N/A";
+
+	if (he->cgroup) {
+		struct cgroup *cgrp = cgroup__find(he->ms.maps->machine->env,
+						   he->cgroup);
+		if (cgrp != NULL)
+			cgrp_name = cgrp->name;
+		else
+			cgrp_name = "unknown";
+	}
+
+	return repsep_snprintf(bf, size, "%s", cgrp_name);
+}
+
+struct sort_entry sort_cgroup = {
+	.se_header      = "Cgroup",
+	.se_cmp	        = sort__cgroup_cmp,
+	.se_snprintf    = hist_entry__cgroup_snprintf,
+	.se_width_idx	= HISTC_CGROUP,
+};
+
 /* --sort socket */
 
 static int64_t
@@ -869,7 +905,8 @@ static int hist_entry__sym_from_snprintf(struct hist_entry *he, char *bf,
 	if (he->branch_info) {
 		struct addr_map_symbol *from = &he->branch_info->from;
 
-		return _hist_entry__sym_snprintf(&from->ms, from->addr, he->level, bf, size, width);
+		return _hist_entry__sym_snprintf(&from->ms, from->al_addr,
+						 he->level, bf, size, width);
 	}
 
 	return repsep_snprintf(bf, size, "%-*.*s", width, width, "N/A");
@@ -881,7 +918,8 @@ static int hist_entry__sym_to_snprintf(struct hist_entry *he, char *bf,
 	if (he->branch_info) {
 		struct addr_map_symbol *to = &he->branch_info->to;
 
-		return _hist_entry__sym_snprintf(&to->ms, to->addr, he->level, bf, size, width);
+		return _hist_entry__sym_snprintf(&to->ms, to->al_addr,
+						 he->level, bf, size, width);
 	}
 
 	return repsep_snprintf(bf, size, "%-*.*s", width, width, "N/A");
@@ -1658,6 +1696,7 @@ static struct sort_dimension common_sort_dimensions[] = {
 	DIM(SORT_TRACE, "trace", sort_trace),
 	DIM(SORT_SYM_SIZE, "symbol_size", sort_sym_size),
 	DIM(SORT_DSO_SIZE, "dso_size", sort_dso_size),
+	DIM(SORT_CGROUP, "cgroup", sort_cgroup),
 	DIM(SORT_CGROUP_ID, "cgroup_id", sort_cgroup_id),
 	DIM(SORT_SYM_IPC_NULL, "ipc_null", sort_sym_ipc_null),
 	DIM(SORT_TIME, "time", sort_time),

tools/perf/util/sort.h

@@ -101,6 +101,7 @@ struct hist_entry {
 	struct thread		*thread;
 	struct comm		*comm;
 	struct namespace_id	cgroup_id;
+	u64			cgroup;
 	u64			ip;
 	u64			transaction;
 	s32			socket;
@@ -224,6 +225,7 @@ enum sort_type {
 	SORT_TRACE,
 	SORT_SYM_SIZE,
 	SORT_DSO_SIZE,
+	SORT_CGROUP,
 	SORT_CGROUP_ID,
 	SORT_SYM_IPC_NULL,
 	SORT_TIME,

tools/perf/util/stat-display.c

@@ -115,11 +115,11 @@ static void aggr_printout(struct perf_stat_config *config,
 			fprintf(config->output, "S%d-D%d-C%*d%s",
 				cpu_map__id_to_socket(id),
 				cpu_map__id_to_die(id),
-				config->csv_output ? 0 : -5,
+				config->csv_output ? 0 : -3,
 				cpu_map__id_to_cpu(id), config->csv_sep);
 		} else {
-			fprintf(config->output, "CPU%*d%s ",
-				config->csv_output ? 0 : -5,
+			fprintf(config->output, "CPU%*d%s",
+				config->csv_output ? 0 : -7,
 				evsel__cpus(evsel)->map[id],
 				config->csv_sep);
 		}

tools/perf/util/symbol-elf.c

@@ -704,9 +704,15 @@ void symsrc__destroy(struct symsrc *ss)
 	close(ss->fd);
 }
 
-bool __weak elf__needs_adjust_symbols(GElf_Ehdr ehdr)
+bool elf__needs_adjust_symbols(GElf_Ehdr ehdr)
 {
-	return ehdr.e_type == ET_EXEC || ehdr.e_type == ET_REL;
+	/*
+	 * Usually vmlinux is an ELF file with type ET_EXEC for most
+	 * architectures; except Arm64 kernel is linked with option
+	 * '-share', so need to check type ET_DYN.
+	 */
+	return ehdr.e_type == ET_EXEC || ehdr.e_type == ET_REL ||
+	       ehdr.e_type == ET_DYN;
 }
 
 int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name,

tools/perf/util/symbol_conf.h

@@ -73,6 +73,7 @@ struct symbol_conf {
 	const char	*symfs;
 	int		res_sample;
 	int		pad_output_len_dso;
+	int		group_sort_idx;
 };
 
 extern struct symbol_conf symbol_conf;

tools/perf/util/synthetic-events.c

@@ -16,6 +16,7 @@
 #include "util/synthetic-events.h"
 #include "util/target.h"
 #include "util/time-utils.h"
+#include "util/cgroup.h"
 #include <linux/bitops.h>
 #include <linux/kernel.h>
 #include <linux/string.h>
@@ -414,6 +415,127 @@ out:
 	return rc;
 }
 
+#ifdef HAVE_FILE_HANDLE
+static int perf_event__synthesize_cgroup(struct perf_tool *tool,
+					 union perf_event *event,
+					 char *path, size_t mount_len,
+					 perf_event__handler_t process,
+					 struct machine *machine)
+{
+	size_t event_size = sizeof(event->cgroup) - sizeof(event->cgroup.path);
+	size_t path_len = strlen(path) - mount_len + 1;
+	struct {
+		struct file_handle fh;
+		uint64_t cgroup_id;
+	} handle;
+	int mount_id;
+
+	while (path_len % sizeof(u64))
+		path[mount_len + path_len++] = '\0';
+
+	memset(&event->cgroup, 0, event_size);
+
+	event->cgroup.header.type = PERF_RECORD_CGROUP;
+	event->cgroup.header.size = event_size + path_len + machine->id_hdr_size;
+
+	handle.fh.handle_bytes = sizeof(handle.cgroup_id);
+	if (name_to_handle_at(AT_FDCWD, path, &handle.fh, &mount_id, 0) < 0) {
+		pr_debug("stat failed: %s\n", path);
+		return -1;
+	}
+
+	event->cgroup.id = handle.cgroup_id;
+	strncpy(event->cgroup.path, path + mount_len, path_len);
+	memset(event->cgroup.path + path_len, 0, machine->id_hdr_size);
+
+	if (perf_tool__process_synth_event(tool, event, machine, process) < 0) {
+		pr_debug("process synth event failed\n");
+		return -1;
+	}
+
+	return 0;
+}
+
+static int perf_event__walk_cgroup_tree(struct perf_tool *tool,
+					union perf_event *event,
+					char *path, size_t mount_len,
+					perf_event__handler_t process,
+					struct machine *machine)
+{
+	size_t pos = strlen(path);
+	DIR *d;
+	struct dirent *dent;
+	int ret = 0;
+
+	if (perf_event__synthesize_cgroup(tool, event, path, mount_len,
+					  process, machine) < 0)
+		return -1;
+
+	d = opendir(path);
+	if (d == NULL) {
+		pr_debug("failed to open directory: %s\n", path);
+		return -1;
+	}
+
+	while ((dent = readdir(d)) != NULL) {
+		if (dent->d_type != DT_DIR)
+			continue;
+		if (!strcmp(dent->d_name, ".") ||
+		    !strcmp(dent->d_name, ".."))
+			continue;
+
+		/* any sane path should be less than PATH_MAX */
+		if (strlen(path) + strlen(dent->d_name) + 1 >= PATH_MAX)
+			continue;
+
+		if (path[pos - 1] != '/')
+			strcat(path, "/");
+		strcat(path, dent->d_name);
+
+		ret = perf_event__walk_cgroup_tree(tool, event, path,
+						   mount_len, process, machine);
+		if (ret < 0)
+			break;
+
+		path[pos] = '\0';
+	}
+
+	closedir(d);
+	return ret;
+}
+
+int perf_event__synthesize_cgroups(struct perf_tool *tool,
+				   perf_event__handler_t process,
+				   struct machine *machine)
+{
+	union perf_event event;
+	char cgrp_root[PATH_MAX];
+	size_t mount_len;  /* length of mount point in the path */
+
+	if (cgroupfs_find_mountpoint(cgrp_root, PATH_MAX, "perf_event") < 0) {
+		pr_debug("cannot find cgroup mount point\n");
+		return -1;
+	}
+
+	mount_len = strlen(cgrp_root);
+	/* make sure the path starts with a slash (after mount point) */
+	strcat(cgrp_root, "/");
+
+	if (perf_event__walk_cgroup_tree(tool, &event, cgrp_root, mount_len,
+					 process, machine) < 0)
+		return -1;
+
+	return 0;
+}
+#else
+int perf_event__synthesize_cgroups(struct perf_tool *tool __maybe_unused,
+				   perf_event__handler_t process __maybe_unused,
+				   struct machine *machine __maybe_unused)
+{
+	return -1;
+}
+#endif
+
 int perf_event__synthesize_modules(struct perf_tool *tool, perf_event__handler_t process,
 				   struct machine *machine)
 {
@@ -1230,6 +1352,9 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type,
 	if (type & PERF_SAMPLE_PHYS_ADDR)
 		result += sizeof(u64);
 
+	if (type & PERF_SAMPLE_CGROUP)
+		result += sizeof(u64);
+
 	if (type & PERF_SAMPLE_AUX) {
 		result += sizeof(u64);
 		result += sample->aux_sample.size;
@@ -1404,6 +1529,11 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type, u64 read_fo
 		array++;
 	}
 
+	if (type & PERF_SAMPLE_CGROUP) {
+		*array = sample->cgroup;
+		array++;
+	}
+
 	if (type & PERF_SAMPLE_AUX) {
 		sz = sample->aux_sample.size;
 		*array++ = sz;

tools/perf/util/synthetic-events.h

@@ -45,6 +45,7 @@ int perf_event__synthesize_kernel_mmap(struct perf_tool *tool, perf_event__handl
 int perf_event__synthesize_mmap_events(struct perf_tool *tool, union perf_event *event, pid_t pid, pid_t tgid, perf_event__handler_t process, struct machine *machine, bool mmap_data);
 int perf_event__synthesize_modules(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_cgroups(struct perf_tool *tool, perf_event__handler_t process, struct machine *machine);
 int perf_event__synthesize_sample(union perf_event *event, u64 type, u64 read_format, const struct perf_sample *sample);
 int perf_event__synthesize_stat_config(struct perf_tool *tool, struct perf_stat_config *config, perf_event__handler_t process, struct machine *machine);
 int perf_event__synthesize_stat_events(struct perf_stat_config *config, struct perf_tool *tool, struct evlist *evlist, perf_event__handler_t process, bool attrs);

tools/perf/util/tool.h

@@ -46,6 +46,7 @@ struct perf_tool {
 			mmap2,
 			comm,
 			namespaces,
+			cgroup,
 			fork,
 			exit,
 			lost,
@@ -78,6 +79,7 @@ struct perf_tool {
 	bool		ordered_events;
 	bool		ordering_requires_timestamps;
 	bool		namespace_events;
+	bool		cgroup_events;
 	bool		no_warn;
 	enum show_feature_header show_feat_hdr;
 };