Merge tag 'perf-core-for-mingo-20161024' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core

Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo:

New features:

- Dynamicly change verbosity level by pressing 'V' in the 'perf top/report'
hists TUI browser (Alexis Berlemont)

- Implement 'perf trace --delay' in the same fashion as in 'perf record --delay',
to skip sampling workload initialization events (Alexis Berlemont)

- Make vendor named events case insensitive in 'perf list', i.e.
'perf list LONGEST_LAT' works just the same as 'perf list longest_lat' (Andi Kleen)

- Show instruction bytes and lenght in 'perf script' for Intel PT and BTS (Andi Kleen, Adrian Hunter)

E.g:

% perf record -e intel_pt// foo
% perf script --itrace=i0ns -F ip,insn,insnlen
ffffffff8101232f ilen: 5 insn: 0f 1f 44 00 00
ffffffff81012334 ilen: 1 insn: 5b
ffffffff81012335 ilen: 1 insn: 5d
ffffffff81012336 ilen: 1 insn: c3
ffffffff810123e3 ilen: 1 insn: 5b
ffffffff810123e4 ilen: 2 insn: 41 5c
ffffffff810123e6 ilen: 1 insn: 5d
ffffffff810123e7 ilen: 1 insn: c3
ffffffff810124a6 ilen: 2 insn: 31 c0
ffffffff810124a8 ilen: 9 insn: 41 83 bc 24 a8 01 00 00 01
ffffffff810124b1 ilen: 2 insn: 75 87

- Allow enabling the perf_event_attr.branch_type attribute member: (Andi Kleen)

perf record -e sched:sched_switch,cpu/cpu-cycles,branch_type=any/ ...

- Add unwinding support for jitdump (Stefano Sanfilippo)

Fixes:

- Use raw_syscall:sys_enter timestamp in 'perf trace' (Arnaldo Carvalho de Melo)

Infrastructure:

- Allow jitdump to be built without libdwarf (Maciej Debski)

- Sync x86's syscall table tools/ copy (Arnaldo Carvalho de Melo)

- Fixes to avoid calling die() in library fuctions already propagating other
errors (Arnaldo Carvalho de Melo)

- Improvements to allow libtraceevent to be properly installed in distro
packages (Jiri Olsa)

- Removing coresight miscellaneous debug output (Mathieu Poirier)

- Cache align the 'perf bench futex' worker struct (Sebastian Andrzej Siewior)

Documentation:

- Minor improvements on the documentation of event parameters (Andi Kleen)

- Add jitdump format specification document (Stephane Eranian)

Spelling fixes:

- Fix typo "No enough" to "Not enough" (Alexander Alemayhu)

Signed-off-by: Arnaldo Carvalho de Melo <[e-mail]>
Signed-off-by: Ingo Molnar <[e-mail]>

tools/include/asm-generic/bitops.h

···
  */
 
 #include <asm-generic/bitops/__ffs.h>
+#include <asm-generic/bitops/__ffz.h>
 #include <asm-generic/bitops/fls.h>
 #include <asm-generic/bitops/__fls.h>
 #include <asm-generic/bitops/fls64.h>

tools/include/asm-generic/bitops/__ffz.h

···
+#ifndef _ASM_GENERIC_BITOPS_FFZ_H_
+#define _ASM_GENERIC_BITOPS_FFZ_H_
+
+/*
+ * ffz - find first zero in word.
+ * @word: The word to search
+ *
+ * Undefined if no zero exists, so code should check against ~0UL first.
+ */
+#define ffz(x)  __ffs(~(x))
+
+#endif /* _ASM_GENERIC_BITOPS_FFZ_H_ */

tools/include/asm-generic/bitops/find.h

···
 		size, unsigned long offset);
 #endif
 
+#ifndef find_next_zero_bit
+
+/**
+ * find_next_zero_bit - find the next cleared bit in a memory region
+ * @addr: The address to base the search on
+ * @offset: The bitnumber to start searching at
+ * @size: The bitmap size in bits
+ *
+ * Returns the bit number of the next zero bit
+ * If no bits are zero, returns @size.
+ */
+unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size,
+				 unsigned long offset);
+#endif
+
 #ifndef find_first_bit
 
 /**
···
 				    unsigned long size);
 
 #endif /* find_first_bit */
+
+#ifndef find_first_zero_bit
+
+/**
+ * find_first_zero_bit - find the first cleared bit in a memory region
+ * @addr: The address to start the search at
+ * @size: The maximum number of bits to search
+ *
+ * Returns the bit number of the first cleared bit.
+ * If no bits are zero, returns @size.
+ */
+unsigned long find_first_zero_bit(const unsigned long *addr, unsigned long size);
+#endif
 
 #endif /*_TOOLS_LINUX_ASM_GENERIC_BITOPS_FIND_H_ */

tools/include/linux/bitops.h

···
 	     (bit) < (size);					\
 	     (bit) = find_next_bit((addr), (size), (bit) + 1))
 
+#define for_each_clear_bit(bit, addr, size) \
+	for ((bit) = find_first_zero_bit((addr), (size));       \
+	     (bit) < (size);                                    \
+	     (bit) = find_next_zero_bit((addr), (size), (bit) + 1))
+
 /* same as for_each_set_bit() but use bit as value to start with */
 #define for_each_set_bit_from(bit, addr, size) \
 	for ((bit) = find_next_bit((addr), (size), (bit));	\

tools/lib/find_bit.c

···
 	return size;
 }
 #endif
+
+#ifndef find_first_zero_bit
+/*
+ * Find the first cleared bit in a memory region.
+ */
+unsigned long find_first_zero_bit(const unsigned long *addr, unsigned long size)
+{
+	unsigned long idx;
+
+	for (idx = 0; idx * BITS_PER_LONG < size; idx++) {
+		if (addr[idx] != ~0UL)
+			return min(idx * BITS_PER_LONG + ffz(addr[idx]), size);
+	}
+
+	return size;
+}
+#endif
+
+#ifndef find_next_zero_bit
+unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size,
+				 unsigned long offset)
+{
+	return _find_next_bit(addr, size, offset, ~0UL);
+}
+#endif

tools/lib/traceevent/Makefile

···
 libdir_relative_SQ = $(subst ','\'',$(libdir_relative))
 plugin_dir_SQ = $(subst ','\'',$(plugin_dir))
 
-LIB_FILE = libtraceevent.a libtraceevent.so
-
 CONFIG_INCLUDES = 
 CONFIG_LIBS	=
 CONFIG_FLAGS	=
···
 N		=
 
 EVENT_PARSE_VERSION = $(EP_VERSION).$(EP_PATCHLEVEL).$(EP_EXTRAVERSION)
+
+LIB_TARGET  = libtraceevent.a libtraceevent.so.$(EVENT_PARSE_VERSION)
+LIB_INSTALL = libtraceevent.a libtraceevent.so*
 
 INCLUDES = -I. -I $(srctree)/tools/include $(CONFIG_INCLUDES)
 
···
 PLUGINS    := $(addprefix $(OUTPUT),$(PLUGINS))
 PLUGINS_IN := $(PLUGINS:.so=-in.o)
 
-TE_IN    := $(OUTPUT)libtraceevent-in.o
-LIB_FILE := $(addprefix $(OUTPUT),$(LIB_FILE))
+TE_IN      := $(OUTPUT)libtraceevent-in.o
+LIB_TARGET := $(addprefix $(OUTPUT),$(LIB_TARGET))
 DYNAMIC_LIST_FILE := $(OUTPUT)libtraceevent-dynamic-list
 
-CMD_TARGETS = $(LIB_FILE) $(PLUGINS) $(DYNAMIC_LIST_FILE)
+CMD_TARGETS = $(LIB_TARGET) $(PLUGINS) $(DYNAMIC_LIST_FILE)
 
 TARGETS = $(CMD_TARGETS)
 
···
 $(TE_IN): force
 	$(Q)$(MAKE) $(build)=libtraceevent
 
-$(OUTPUT)libtraceevent.so: $(TE_IN)
-	$(QUIET_LINK)$(CC) --shared $^ -o $@
+$(OUTPUT)libtraceevent.so.$(EVENT_PARSE_VERSION): $(TE_IN)
+	$(QUIET_LINK)$(CC) --shared $^ -Wl,-soname,libtraceevent.so.$(EP_VERSION) -o $@
+	@ln -sf $(@F) $(OUTPUT)libtraceevent.so
+	@ln -sf $(@F) $(OUTPUT)libtraceevent.so.$(EP_VERSION)
 
 $(OUTPUT)libtraceevent.a: $(TE_IN)
 	$(QUIET_LINK)$(RM) $@; $(AR) rcs $@ $^
···
 	find . -name '*.[ch]' | xargs etags \
 	--regex='/_PE(\([^,)]*\).*/PEVENT_ERRNO__\1/'
 
+define do_install_mkdir
+	if [ ! -d '$(DESTDIR_SQ)$1' ]; then		\
+		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$1';	\
+	fi
+endef
+
 define do_install
-	if [ ! -d '$(DESTDIR_SQ)$2' ]; then		\
-		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$2';	\
-	fi;						\
-	$(INSTALL) $1 '$(DESTDIR_SQ)$2'
+	$(call do_install_mkdir,$2);			\
+	$(INSTALL) $(if $3,-m $3,) $1 '$(DESTDIR_SQ)$2'
 endef
 
 define do_install_plugins
···
 endef
 
 install_lib: all_cmd install_plugins
-	$(call QUIET_INSTALL, $(LIB_FILE)) \
-		$(call do_install,$(LIB_FILE),$(libdir_SQ))
+	$(call QUIET_INSTALL, $(LIB_TARGET)) \
+		$(call do_install_mkdir,$(libdir_SQ)); \
+		cp -fpR $(LIB_INSTALL) $(DESTDIR)$(libdir_SQ)
 
 install_plugins: $(PLUGINS)
 	$(call QUIET_INSTALL, trace_plugins) \
 		$(call do_install_plugins, $(PLUGINS))
+
+install_headers:
+	$(call QUIET_INSTALL, headers) \
+		$(call do_install,event-parse.h,$(prefix)/include/traceevent,644); \
+		$(call do_install,event-utils.h,$(prefix)/include/traceevent,644); \
+		$(call do_install,kbuffer.h,$(prefix)/include/traceevent,644)
 
 install: install_lib
 

tools/perf/Documentation/jitdump-specification.txt

···
+JITDUMP specification version 2
+Last Revised: 09/15/2016
+Author: Stephane Eranian <[e-mail]>
+
+--------------------------------------------------------
+| Revision  |    Date    | Description                 |
+--------------------------------------------------------
+|   1       | 09/07/2016 | Initial revision            |
+--------------------------------------------------------
+|   2       | 09/15/2016 | Add JIT_CODE_UNWINDING_INFO |
+--------------------------------------------------------
+
+
+I/ Introduction
+
+
+This document describes the jitdump file format. The file is generated by Just-In-time compiler runtimes to save meta-data information about the generated code, such as address, size, and name of generated functions, the native code generated, the source line information. The data may then be used by performance tools, such as Linux perf to generate function and assembly level profiles.
+
+The format is not specific to any particular programming language. It can be extended as need be.
+
+The format of the file is binary. It is self-describing in terms of endianness and is portable across multiple processor architectures.
+
+
+II/ Overview of the format
+
+
+The format requires only sequential accesses, i.e., append only mode. The file starts with a fixed size file header describing the version of the specification, the endianness.
+
+The header is followed by a series of records, each starting with a fixed size header describing the type of record and its size. It is, itself, followed by the payload for the record. Records can have a variable size even for a given type.
+
+Each entry in the file is timestamped. All timestamps must use the same clock source. The CLOCK_MONOTONIC clock source is recommended.
+
+
+III/ Jitdump file header format
+
+Each jitdump file starts with a fixed size header containing the following fields in order:
+
+
+* uint32_t magic     : a magic number tagging the file type. The value is 4-byte long and represents the string "JiTD" in ASCII form. It is 0x4A695444 or 0x4454694a depending on the endianness. The field can be used to detect the endianness of the file
+* uint32_t version   : a 4-byte value representing the format version. It is currently set to 2
+* uint32_t total_size: size in bytes of file header
+* uint32_t elf_mach  : ELF architecture encoding (ELF e_machine value as specified in /usr/include/elf.h)
+* uint32_t pad1      : padding. Reserved for future use
+* uint32_t pid       : JIT runtime process identification (OS specific)
+* uint64_t timestamp : timestamp of when the file was created
+* uint64_t flags     : a bitmask of flags
+
+The flags currently defined are as follows:
+ * bit 0: JITDUMP_FLAGS_ARCH_TIMESTAMP : set if the jitdump file is using an architecture-specific timestamp clock source. For instance, on x86, one could use TSC directly
+
+IV/ Record header
+
+The file header is immediately followed by records. Each record starts with a fixed size header describing the record that follows.
+
+The record header is specified in order as follows:
+* uint32_t id        : a value identifying the record type (see below)
+* uint32_t total_size: the size in bytes of the record including the header.
+* uint64_t timestamp : a timestamp of when the record was created.
+
+The following record types are defined:
+ * Value 0 : JIT_CODE_LOAD      : record describing a jitted function
+ * Value 1 : JIT_CODE_MOVE      : record describing an already jitted function which is moved
+ * Value 2 : JIT_CODE_DEBUG_INFO: record describing the debug information for a jitted function
+ * Value 3 : JIT_CODE_CLOSE     : record marking the end of the jit runtime (optional)
+ * Value 4 : JIT_CODE_UNWINDING_INFO: record describing a function unwinding information
+
+ The payload of the record must immediately follow the record header without padding.
+
+V/ JIT_CODE_LOAD record
+
+
+  The record has the following fields following the fixed-size record header in order:
+  * uint32_t pid: OS process id of the runtime generating the jitted code
+  * uint32_t tid: OS thread identification of the runtime thread generating the jitted code
+  * uint64_t vma: virtual address of jitted code start
+  * uint64_t code_addr: code start address for the jitted code. By default vma = code_addr
+  * uint64_t code_size: size in bytes of the generated jitted code
+  * uint64_t code_index: unique identifier for the jitted code (see below)
+  * char[n]: function name in ASCII including the null termination
+  * native code: raw byte encoding of the jitted code
+
+  The record header total_size field is inclusive of all components:
+  * record header
+  * fixed-sized fields
+  * function name string, including termination
+  * native code length
+  * record specific variable data (e.g., array of data entries)
+
+The code_index is used to uniquely identify each jitted function. The index can be a monotonically increasing 64-bit value. Each time a function is jitted it gets a new number. This value is used in case the code for a function is moved and avoids having to issue another JIT_CODE_LOAD record.
+
+The format supports empty functions with no native code.
+
+
+VI/ JIT_CODE_MOVE record
+
+  The record type is optional.
+
+  The record has the following fields following the fixed-size record header in order:
+  * uint32_t pid          : OS process id of the runtime generating the jitted code
+  * uint32_t tid          : OS thread identification of the runtime thread generating the jitted code
+  * uint64_t vma          : new virtual address of jitted code start
+  * uint64_t old_code_addr: previous code address for the same function
+  * uint64_t new_code_addr: alternate new code started address for the jitted code. By default it should be equal to the vma address.
+  * uint64_t code_size    : size in bytes of the jitted code
+  * uint64_t code_index   : index referring to the JIT_CODE_LOAD code_index record of when the function was initially jitted
+
+
+The MOVE record can be used in case an already jitted function is simply moved by the runtime inside the code cache.
+
+The JIT_CODE_MOVE record cannot come before the JIT_CODE_LOAD record for the same function name. The function cannot have changed name, otherwise a new JIT_CODE_LOAD record must be emitted.
+
+The code size of the function cannot change.
+
+
+VII/ JIT_DEBUG_INFO record
+
+The record type is optional.
+
+The record contains source lines debug information, i.e., a way to map a code address back to a source line. This information may be used by the performance tool.
+
+The record has the following fields following the fixed-size record header in order:
+  * uint64_t code_addr: address of function for which the debug information is generated
+  * uint64_t nr_entry : number of debug entries for the function
+  * debug_entry[n]: array of nr_entry debug entries for the function
+
+The debug_entry describes the source line information. It is defined as follows in order:
+* uint64_t code_addr: address of function for which the debug information is generated
+* uint32_t line     : source file line number (starting at 1)
+* uint32_t discrim  : column discriminator, 0 is default
+* char name[n]      : source file name in ASCII, including null termination
+
+The debug_entry entries are saved in sequence but given that they have variable sizes due to the file name string, they cannot be indexed directly.
+They need to be walked sequentially. The next debug_entry is found at sizeof(debug_entry) + strlen(name) + 1.
+
+IMPORTANT:
+  The JIT_CODE_DEBUG for a given function must always be generated BEFORE the JIT_CODE_LOAD for the function. This facilitates greatly the parser for the jitdump file.
+
+
+VIII/ JIT_CODE_CLOSE record
+
+
+The record type is optional.
+
+The record is used as a marker for the end of the jitted runtime. It can be replaced by the end of the file.
+
+The JIT_CODE_CLOSE record does not have any specific fields, the record header contains all the information needed.
+
+
+IX/ JIT_CODE_UNWINDING_INFO
+
+
+The record type is optional.
+
+The record is used to describe the unwinding information for a jitted function.
+
+The record has the following fields following the fixed-size record header in order:
+
+uint64_t unwind_data_size   : the size in bytes of the unwinding data table at the end of the record
+uint64_t eh_frame_hdr_size  : the size in bytes of the DWARF EH Frame Header at the start of the unwinding data table at the end of the record
+uint64_t mapped_size        : the size of the unwinding data mapped in memory
+const char unwinding_data[n]: an array of unwinding data, consisting of the EH Frame Header, followed by the actual EH Frame
+
+
+The EH Frame header follows the Linux Standard Base (LSB) specification as described in the document at https://refspecs.linuxfoundation.org/LSB_1.3.0/gLSB/gLSB/ehframehdr.html
+
+
+The EH Frame follows the LSB specicfication as described in the document at https://refspecs.linuxbase.org/LSB_3.0.0/LSB-PDA/LSB-PDA/ehframechpt.html
+
+
+NOTE: The mapped_size is generally either the same as unwind_data_size (if the unwinding data was mapped in memory by the running process) or zero (if the unwinding data is not mapped by the process). If the unwinding data was not mapped, then only the EH Frame Header will be read, which can be used to specify FP based unwinding for a function which does not have unwinding information.

tools/perf/Documentation/perf-record.txt

···
           param1 and param2 are defined as formats for the PMU in:
           /sys/bus/event_source/devices/<pmu>/format/*
 
-	  There are also some params which are not defined in .../<pmu>/format/*.
+	  There are also some parameters which are not defined in .../<pmu>/format/*.
 	  These params can be used to overload default config values per event.
-	  Here is a list of the params.
+	  Here are some common parameters:
 	  - 'period': Set event sampling period
 	  - 'freq': Set event sampling frequency
 	  - 'time': Disable/enable time stamping. Acceptable values are 1 for
···
 			 FP mode, "dwarf" for DWARF mode, "lbr" for LBR mode and
 			 "no" for disable callgraph.
 	  - 'stack-size': user stack size for dwarf mode
+
+          See the linkperf:perf-list[1] man page for more parameters.
+
 	  Note: If user explicitly sets options which conflict with the params,
-	  the value set by the params will be overridden.
+	  the value set by the parameters will be overridden.
 
 	  Also not defined in .../<pmu>/format/* are PMU driver specific
 	  configuration parameters.  Any configuration parameter preceded by

tools/perf/Documentation/perf-script.txt

···
         Comma separated list of fields to print. Options are:
         comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff,
         srcline, period, iregs, brstack, brstacksym, flags, bpf-output,
-        callindent. Field list can be prepended with the type, trace, sw or hw,
+        callindent, insn, insnlen. Field list can be prepended with the type, trace, sw or hw,
         to indicate to which event type the field list applies.
         e.g., -F sw:comm,tid,time,ip,sym  and -F trace:time,cpu,trace
 
···
 	The callindent field is synthesized and may have a value when
 	Instruction Trace decoding. For calls and returns, it will display the
 	name of the symbol indented with spaces to reflect the stack depth.
+
+	When doing instruction trace decoding insn and insnlen give the
+	instruction bytes and the instruction length of the current
+	instruction.
 
 	Finally, a user may not set fields to none for all event types.
 	i.e., -F "" is not allowed.

tools/perf/Documentation/perf-trace.txt

···
 	Prefixing with ! shows all syscalls but the ones specified.  You may
 	need to escape it.
 
+-D msecs::
+--delay msecs::
+After starting the program, wait msecs before measuring. This is useful to
+filter out the startup phase of the program, which is often very different.
+
 -o::
 --output=::
 	Output file name.

tools/perf/MANIFEST

···
 tools/include/asm-generic/bitops/atomic.h
 tools/include/asm-generic/bitops/const_hweight.h
 tools/include/asm-generic/bitops/__ffs.h
+tools/include/asm-generic/bitops/__ffz.h
 tools/include/asm-generic/bitops/__fls.h
 tools/include/asm-generic/bitops/find.h
 tools/include/asm-generic/bitops/fls64.h

tools/perf/Makefile.config

···
 endif
 
 ifdef PERF_HAVE_JITDUMP
-  ifndef NO_DWARF
+  ifndef NO_LIBELF
     $(call detected,CONFIG_JITDUMP)
     CFLAGS += -DHAVE_JITDUMP
   endif

tools/perf/arch/arm/util/cs-etm.c

···
 	snprintf(path, PATH_MAX,
 		 "%s" CS_BUS_DEVICE_PATH "%s", sysfs, name);
 
-	printf("path: %s\n", path);
-
 	if (stat(path, &st) < 0)
 		return NULL;
 

tools/perf/arch/x86/entry/syscalls/syscall_64.tbl

···
 543	x32	io_setup		compat_sys_io_setup
 544	x32	io_submit		compat_sys_io_submit
 545	x32	execveat		compat_sys_execveat/ptregs
-534	x32	preadv2			compat_sys_preadv2
-535	x32	pwritev2		compat_sys_pwritev2
+546	x32	preadv2			compat_sys_preadv64v2
+547	x32	pwritev2		compat_sys_pwritev64v2

tools/perf/bench/futex-hash.c

···
 static struct stats throughput_stats;
 static pthread_cond_t thread_parent, thread_worker;
 
+#define SMP_CACHE_BYTES 256
+#define __cacheline_aligned __attribute__ ((aligned (SMP_CACHE_BYTES)))
+
 struct worker {
 	int tid;
 	u_int32_t *futex;
 	pthread_t thread;
 	unsigned long ops;
-};
+} __cacheline_aligned;
 
 static const struct option options[] = {
 	OPT_UINTEGER('t', "threads", &nthreads, "Specify amount of threads"),

tools/perf/bench/mem-functions.c

···
 
 struct bench_mem_info {
 	const struct function *functions;
-	u64 (*do_cycles)(const struct function *r, size_t size);
-	double (*do_gettimeofday)(const struct function *r, size_t size);
+	u64 (*do_cycles)(const struct function *r, size_t size, void *src, void *dst);
+	double (*do_gettimeofday)(const struct function *r, size_t size, void *src, void *dst);
 	const char *const *usage;
+	bool alloc_src;
 };
 
 static void __bench_mem_function(struct bench_mem_info *info, int r_idx, size_t size, double size_total)
···
 	const struct function *r = &info->functions[r_idx];
 	double result_bps = 0.0;
 	u64 result_cycles = 0;
+	void *src = NULL, *dst = zalloc(size);
 
 	printf("# function '%s' (%s)\n", r->name, r->desc);
+
+	if (dst == NULL)
+		goto out_alloc_failed;
+
+	if (info->alloc_src) {
+		src = zalloc(size);
+		if (src == NULL)
+			goto out_alloc_failed;
+	}
 
 	if (bench_format == BENCH_FORMAT_DEFAULT)
 		printf("# Copying %s bytes ...\n\n", size_str);
 
 	if (use_cycles) {
-		result_cycles = info->do_cycles(r, size);
+		result_cycles = info->do_cycles(r, size, src, dst);
 	} else {
-		result_bps = info->do_gettimeofday(r, size);
+		result_bps = info->do_gettimeofday(r, size, src, dst);
 	}
 
 	switch (bench_format) {
···
 		BUG_ON(1);
 		break;
 	}
+
+out_free:
+	free(src);
+	free(dst);
+	return;
+out_alloc_failed:
+	printf("# Memory allocation failed - maybe size (%s) is too large?\n", size_str);
+	goto out_free;
 }
 
 static int bench_mem_common(int argc, const char **argv, struct bench_mem_info *info)
···
 	return 0;
 }
 
-static void memcpy_alloc_mem(void **dst, void **src, size_t size)
-{
-	*dst = zalloc(size);
-	if (!*dst)
-		die("memory allocation failed - maybe size is too large?\n");
-
-	*src = zalloc(size);
-	if (!*src)
-		die("memory allocation failed - maybe size is too large?\n");
-
-	/* Make sure to always prefault zero pages even if MMAP_THRESH is crossed: */
-	memset(*src, 0, size);
-}
-
-static u64 do_memcpy_cycles(const struct function *r, size_t size)
+static u64 do_memcpy_cycles(const struct function *r, size_t size, void *src, void *dst)
 {
 	u64 cycle_start = 0ULL, cycle_end = 0ULL;
-	void *src = NULL, *dst = NULL;
 	memcpy_t fn = r->fn.memcpy;
 	int i;
 
-	memcpy_alloc_mem(&dst, &src, size);
+	/* Make sure to always prefault zero pages even if MMAP_THRESH is crossed: */
+	memset(src, 0, size);
 
 	/*
 	 * We prefault the freshly allocated memory range here,
···
 		fn(dst, src, size);
 	cycle_end = get_cycles();
 
-	free(src);
-	free(dst);
 	return cycle_end - cycle_start;
 }
 
-static double do_memcpy_gettimeofday(const struct function *r, size_t size)
+static double do_memcpy_gettimeofday(const struct function *r, size_t size, void *src, void *dst)
 {
 	struct timeval tv_start, tv_end, tv_diff;
 	memcpy_t fn = r->fn.memcpy;
-	void *src = NULL, *dst = NULL;
 	int i;
-
-	memcpy_alloc_mem(&dst, &src, size);
 
 	/*
 	 * We prefault the freshly allocated memory range here,
···
 	BUG_ON(gettimeofday(&tv_end, NULL));
 
 	timersub(&tv_end, &tv_start, &tv_diff);
-
-	free(src);
-	free(dst);
 
 	return (double)(((double)size * nr_loops) / timeval2double(&tv_diff));
 }
···
 		.do_cycles		= do_memcpy_cycles,
 		.do_gettimeofday	= do_memcpy_gettimeofday,
 		.usage			= bench_mem_memcpy_usage,
+		.alloc_src              = true,
 	};
 
 	return bench_mem_common(argc, argv, &info);
 }
 
-static void memset_alloc_mem(void **dst, size_t size)
-{
-	*dst = zalloc(size);
-	if (!*dst)
-		die("memory allocation failed - maybe size is too large?\n");
-}
-
-static u64 do_memset_cycles(const struct function *r, size_t size)
+static u64 do_memset_cycles(const struct function *r, size_t size, void *src __maybe_unused, void *dst)
 {
 	u64 cycle_start = 0ULL, cycle_end = 0ULL;
 	memset_t fn = r->fn.memset;
-	void *dst = NULL;
 	int i;
-
-	memset_alloc_mem(&dst, size);
 
 	/*
 	 * We prefault the freshly allocated memory range here,
···
 		fn(dst, i, size);
 	cycle_end = get_cycles();
 
-	free(dst);
 	return cycle_end - cycle_start;
 }
 
-static double do_memset_gettimeofday(const struct function *r, size_t size)
+static double do_memset_gettimeofday(const struct function *r, size_t size, void *src __maybe_unused, void *dst)
 {
 	struct timeval tv_start, tv_end, tv_diff;
 	memset_t fn = r->fn.memset;
-	void *dst = NULL;
 	int i;
-
-	memset_alloc_mem(&dst, size);
 
 	/*
 	 * We prefault the freshly allocated memory range here,
···
 
 	timersub(&tv_end, &tv_start, &tv_diff);
 
-	free(dst);
 	return (double)(((double)size * nr_loops) / timeval2double(&tv_diff));
 }
 

tools/perf/builtin-report.c

···
 
 	if (rep->show_threads) {
 		const char *name = evsel ? perf_evsel__name(evsel) : "unknown";
-		perf_read_values_add_value(&rep->show_threads_values,
+		int err = perf_read_values_add_value(&rep->show_threads_values,
 					   event->read.pid, event->read.tid,
 					   event->read.id,
 					   name,
 					   event->read.value);
+
+		if (err)
+			return err;
 	}
 
 	dump_printf(": %d %d %s %" PRIu64 "\n", event->read.pid, event->read.tid,
···
 		}
 	}
 
-	if (rep->show_threads)
-		perf_read_values_init(&rep->show_threads_values);
+	if (rep->show_threads) {
+		ret = perf_read_values_init(&rep->show_threads_values);
+		if (ret)
+			return ret;
+	}
 
 	ret = report__setup_sample_type(rep);
 	if (ret) {

tools/perf/builtin-script.c

···
 	PERF_OUTPUT_WEIGHT	    = 1U << 18,
 	PERF_OUTPUT_BPF_OUTPUT	    = 1U << 19,
 	PERF_OUTPUT_CALLINDENT	    = 1U << 20,
+	PERF_OUTPUT_INSN	    = 1U << 21,
+	PERF_OUTPUT_INSNLEN	    = 1U << 22,
 };
 
 struct output_option {
···
 	{.str = "weight",   .field = PERF_OUTPUT_WEIGHT},
 	{.str = "bpf-output",   .field = PERF_OUTPUT_BPF_OUTPUT},
 	{.str = "callindent", .field = PERF_OUTPUT_CALLINDENT},
+	{.str = "insn", .field = PERF_OUTPUT_INSN},
+	{.str = "insnlen", .field = PERF_OUTPUT_INSNLEN},
 };
 
 /* default set to maintain compatibility with current format */
···
 		printf("%*s", spacing - len, "");
 }
 
+static void print_insn(struct perf_sample *sample,
+		       struct perf_event_attr *attr)
+{
+	if (PRINT_FIELD(INSNLEN))
+		printf(" ilen: %d", sample->insn_len);
+	if (PRINT_FIELD(INSN)) {
+		int i;
+
+		printf(" insn:");
+		for (i = 0; i < sample->insn_len; i++)
+			printf(" %02x", (unsigned char)sample->insn[i]);
+	}
+}
+
 static void print_sample_bts(struct perf_sample *sample,
 			     struct perf_evsel *evsel,
 			     struct thread *thread,
···
 
 	if (print_srcline_last)
 		map__fprintf_srcline(al->map, al->addr, "\n  ", stdout);
+
+	print_insn(sample, attr);
 
 	printf("\n");
 }
···
 
 	if (perf_evsel__is_bpf_output(evsel) && PRINT_FIELD(BPF_OUTPUT))
 		print_sample_bpf_output(sample);
-
+	print_insn(sample, attr);
 	printf("\n");
 }
 
···
 		     "Valid types: hw,sw,trace,raw. "
 		     "Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso,"
 		     "addr,symoff,period,iregs,brstack,brstacksym,flags,"
-		     "bpf-output,callindent", parse_output_fields),
+		     "bpf-output,callindent,insn,insnlen", parse_output_fields),
 	OPT_BOOLEAN('a', "all-cpus", &system_wide,
 		    "system-wide collection from all CPUs"),
 	OPT_STRING('S', "symbols", &symbol_conf.sym_list_str, "symbol[,symbol...]",

tools/perf/builtin-trace.c

···
  */
 struct thread_trace {
 	u64		  entry_time;
-	u64		  exit_time;
 	bool		  entry_pending;
 	unsigned long	  nr_events;
 	unsigned long	  pfmaj, pfmin;
···
 
 	duration = sample->time - ttrace->entry_time;
 
-	printed  = trace__fprintf_entry_head(trace, trace->current, duration, sample->time, trace->output);
+	printed  = trace__fprintf_entry_head(trace, trace->current, duration, ttrace->entry_time, trace->output);
 	printed += fprintf(trace->output, "%-70s) ...\n", ttrace->entry_str);
 	ttrace->entry_pending = false;
 
···
 
 	if (sc->is_exit) {
 		if (!(trace->duration_filter || trace->summary_only || trace->min_stack)) {
-			trace__fprintf_entry_head(trace, thread, 1, sample->time, trace->output);
+			trace__fprintf_entry_head(trace, thread, 1, ttrace->entry_time, trace->output);
 			fprintf(trace->output, "%-70s)\n", ttrace->entry_str);
 		}
 	} else {
···
 		++trace->stats.vfs_getname;
 	}
 
-	ttrace->exit_time = sample->time;
-
 	if (ttrace->entry_time) {
 		duration = sample->time - ttrace->entry_time;
 		if (trace__filter_duration(trace, duration))
···
 	if (trace->summary_only)
 		goto out;
 
-	trace__fprintf_entry_head(trace, thread, duration, sample->time, trace->output);
+	trace__fprintf_entry_head(trace, thread, duration, ttrace->entry_time, trace->output);
 
 	if (ttrace->entry_pending) {
 		fprintf(trace->output, "%-70s", ttrace->entry_str);
···
 	if (err < 0)
 		goto out_error_mmap;
 
-	if (!target__none(&trace->opts.target))
+	if (!target__none(&trace->opts.target) && !trace->opts.initial_delay)
 		perf_evlist__enable(evlist);
 
 	if (forks)
 		perf_evlist__start_workload(evlist);
+
+	if (trace->opts.initial_delay) {
+		usleep(trace->opts.initial_delay * 1000);
+		perf_evlist__enable(evlist);
+	}
 
 	trace->multiple_threads = thread_map__pid(evlist->threads, 0) == -1 ||
 				  evlist->threads->nr > 1 ||
···
 		     "Default: kernel.perf_event_max_stack or " __stringify(PERF_MAX_STACK_DEPTH)),
 	OPT_UINTEGER(0, "proc-map-timeout", &trace.opts.proc_map_timeout,
 			"per thread proc mmap processing timeout in ms"),
+	OPT_UINTEGER('D', "delay", &trace.opts.initial_delay,
+		     "ms to wait before starting measurement after program "
+		     "start"),
 	OPT_END()
 	};
 	bool __maybe_unused max_stack_user_set = true;

tools/perf/jvmti/jvmti_agent.c

···
 static char jit_path[PATH_MAX];
 static void *marker_addr;
 
-/*
- * padding buffer
- */
-static const char pad_bytes[7];
-
 static inline pid_t gettid(void)
 {
 	return (pid_t)syscall(__NR_gettid);
···
 
 void *jvmti_open(void)
 {
-	int pad_cnt;
 	char dump_path[PATH_MAX];
 	struct jitheader header;
 	int fd;
···
 	header.total_size = sizeof(header);
 	header.pid        = getpid();
 
-	/* calculate amount of padding '\0' */
-	pad_cnt = PADDING_8ALIGNED(header.total_size);
-	header.total_size += pad_cnt;
-
 	header.timestamp = perf_get_timestamp();
 
 	if (use_arch_timestamp)
···
 		warn("jvmti: cannot write dumpfile header");
 		goto error;
 	}
-
-	/* write padding '\0' if necessary */
-	if (pad_cnt && !fwrite(pad_bytes, pad_cnt, 1, fp)) {
-		warn("jvmti: cannot write dumpfile header padding");
-		goto error;
-	}
-
 	return fp;
 error:
 	fclose(fp);
···
 	static int code_generation = 1;
 	struct jr_code_load rec;
 	size_t sym_len;
-	size_t padding_count;
 	FILE *fp = agent;
 	int ret = -1;
 
···
 
 	rec.p.id           = JIT_CODE_LOAD;
 	rec.p.total_size   = sizeof(rec) + sym_len;
-	padding_count      = PADDING_8ALIGNED(rec.p.total_size);
-	rec.p. total_size += padding_count;
 	rec.p.timestamp    = perf_get_timestamp();
 
 	rec.code_size  = size;
···
 	ret = fwrite_unlocked(&rec, sizeof(rec), 1, fp);
 	fwrite_unlocked(sym, sym_len, 1, fp);
 
-	if (padding_count)
-		fwrite_unlocked(pad_bytes, padding_count, 1, fp);
-
 	if (code)
 		fwrite_unlocked(code, size, 1, fp);
 
···
 {
 	struct jr_code_debug_info rec;
 	size_t sret, len, size, flen;
-	size_t padding_count;
 	uint64_t addr;
 	const char *fn = file;
 	FILE *fp = agent;
···
 	 * int      : line number
 	 * int      : column discriminator
 	 * file[]   : source file name
-	 * padding  : pad to multiple of 8 bytes
 	 */
 	size += nr_lines * sizeof(struct debug_entry);
 	size += flen * nr_lines;
-	/*
-	 * pad to 8 bytes
-	 */
-	padding_count = PADDING_8ALIGNED(size);
-
-	rec.p.total_size = size + padding_count;
+	rec.p.total_size = size;
 
 	/*
 	 * If JVM is multi-threaded, nultiple concurrent calls to agent
···
 		if (sret != 1)
 			goto error;
 	}
-	if (padding_count) {
-		sret = fwrite_unlocked(pad_bytes, padding_count, 1, fp);
-		if (sret != 1)
-			goto error;
-	}
-
 	funlockfile(fp);
 	return 0;
 error:

tools/perf/jvmti/libjvmti.c

···
 static int has_line_numbers;
 void *jvmti_agent;
 
+static void print_error(jvmtiEnv *jvmti, const char *msg, jvmtiError ret)
+{
+	char *err_msg = NULL;
+	jvmtiError err;
+	err = (*jvmti)->GetErrorName(jvmti, ret, &err_msg);
+	if (err == JVMTI_ERROR_NONE) {
+		warnx("%s failed with %s", msg, err_msg);
+		(*jvmti)->Deallocate(jvmti, (unsigned char *)err_msg);
+	} else {
+		warnx("%s failed with an unknown error %d", msg, ret);
+	}
+}
+
 static jvmtiError
 do_get_line_numbers(jvmtiEnv *jvmti, void *pc, jmethodID m, jint bci,
 		    jvmti_line_info_t *tab, jint *nr)
···
 	jvmtiError ret;
 
 	ret = (*jvmti)->GetLineNumberTable(jvmti, m, &nr_lines, &loc_tab);
-	if (ret != JVMTI_ERROR_NONE)
+	if (ret != JVMTI_ERROR_NONE) {
+		print_error(jvmti, "GetLineNumberTable", ret);
 		return ret;
+	}
 
 	for (i = 0; i < nr_lines; i++) {
 		if (loc_tab[i].start_location < bci) {
···
 					/* free what was allocated for nothing */
 					(*jvmti)->Deallocate(jvmti, (unsigned char *)lne);
 					nr_total += (int)nr;
+				} else {
+					print_error(jvmti, "GetLineNumberTable", ret);
 				}
 			}
 		}
···
 	ret = (*jvmti)->GetMethodDeclaringClass(jvmti, method,
 						&decl_class);
 	if (ret != JVMTI_ERROR_NONE) {
-		warnx("jvmti: cannot get declaring class");
+		print_error(jvmti, "GetMethodDeclaringClass", ret);
 		return;
 	}
 
···
 
 	ret = (*jvmti)->GetSourceFileName(jvmti, decl_class, &file_name);
 	if (ret != JVMTI_ERROR_NONE) {
-		warnx("jvmti: cannot get source filename ret=%d", ret);
+		print_error(jvmti, "GetSourceFileName", ret);
 		goto error;
 	}
 
 	ret = (*jvmti)->GetClassSignature(jvmti, decl_class,
 					  &class_sign, NULL);
 	if (ret != JVMTI_ERROR_NONE) {
-		warnx("jvmti: getclassignature failed");
+		print_error(jvmti, "GetClassSignature", ret);
 		goto error;
 	}
 
 	ret = (*jvmti)->GetMethodName(jvmti, method, &func_name,
 				      &func_sign, NULL);
 	if (ret != JVMTI_ERROR_NONE) {
-		warnx("jvmti: failed getmethodname");
+		print_error(jvmti, "GetMethodName", ret);
 		goto error;
 	}
 
···
 
 	ret = (*jvmti)->AddCapabilities(jvmti, &caps1);
 	if (ret != JVMTI_ERROR_NONE) {
-		warnx("jvmti: acquire compiled_method capability failed");
+		print_error(jvmti, "AddCapabilities", ret);
 		return -1;
 	}
 	ret = (*jvmti)->GetJLocationFormat(jvmti, &format);
···
 		ret = (*jvmti)->AddCapabilities(jvmti, &caps1);
                 if (ret == JVMTI_ERROR_NONE)
                         has_line_numbers = 1;
-        }
+        } else if (ret != JVMTI_ERROR_NONE)
+		print_error(jvmti, "GetJLocationFormat", ret);
+
 
 	memset(&cb, 0, sizeof(cb));
 
···
 
 	ret = (*jvmti)->SetEventCallbacks(jvmti, &cb, sizeof(cb));
 	if (ret != JVMTI_ERROR_NONE) {
-		warnx("jvmti: cannot set event callbacks");
+		print_error(jvmti, "SetEventCallbacks", ret);
 		return -1;
 	}
 
 	ret = (*jvmti)->SetEventNotificationMode(jvmti, JVMTI_ENABLE,
 			JVMTI_EVENT_COMPILED_METHOD_LOAD, NULL);
 	if (ret != JVMTI_ERROR_NONE) {
-		warnx("jvmti: setnotification failed for method_load");
+		print_error(jvmti, "SetEventNotificationMode(METHOD_LOAD)", ret);
 		return -1;
 	}
 
 	ret = (*jvmti)->SetEventNotificationMode(jvmti, JVMTI_ENABLE,
 			JVMTI_EVENT_DYNAMIC_CODE_GENERATED, NULL);
 	if (ret != JVMTI_ERROR_NONE) {
-		warnx("jvmti: setnotification failed on code_generated");
+		print_error(jvmti, "SetEventNotificationMode(CODE_GENERATED)", ret);
 		return -1;
 	}
 	return 0;

tools/perf/tests/backward-ring-buffer.c

···
 
 	evlist = perf_evlist__new();
 	if (!evlist) {
-		pr_debug("No enough memory to create evlist\n");
+		pr_debug("Not enough memory to create evlist\n");
 		return TEST_FAIL;
 	}
 

tools/perf/tests/bpf.c

···
 	/* Instead of perf_evlist__new_default, don't add default events */
 	evlist = perf_evlist__new();
 	if (!evlist) {
-		pr_debug("No enough memory to create evlist\n");
+		pr_debug("Not enough memory to create evlist\n");
 		return TEST_FAIL;
 	}
 

tools/perf/ui/browsers/hists.c

···
 			do_zoom_dso(browser, actions);
 			continue;
 		case 'V':
-			browser->show_dso = !browser->show_dso;
+			verbose = (verbose + 1) % 4;
+			browser->show_dso = verbose > 0;
+			ui_helpline__fpush("Verbosity level set to %d\n",
+					   verbose);
 			continue;
 		case 't':
 			actions->thread = thread;

tools/perf/util/Build

···
 ifdef CONFIG_JITDUMP
 libperf-$(CONFIG_LIBELF) += jitdump.o
 libperf-$(CONFIG_LIBELF) += genelf.o
-libperf-$(CONFIG_LIBELF) += genelf_debug.o
+libperf-$(CONFIG_DWARF) += genelf_debug.o
 endif
 
 CFLAGS_config.o   += -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"

tools/perf/util/bpf-loader.c

···
 	int err = 0;
 
 	if (!text) {
-		pr_debug("No enough memory: dup config_str failed\n");
+		pr_debug("Not enough memory: dup config_str failed\n");
 		return ERR_PTR(-ENOMEM);
 	}
 
···
 
 	ptevs = malloc(array_sz);
 	if (!ptevs) {
-		pr_debug("No enough memory: alloc ptevs failed\n");
+		pr_debug("Not enough memory: alloc ptevs failed\n");
 		return -ENOMEM;
 	}
 
···
 	priv->need_prologue = true;
 	priv->insns_buf = malloc(sizeof(struct bpf_insn) * BPF_MAXINSNS);
 	if (!priv->insns_buf) {
-		pr_debug("No enough memory: alloc insns_buf failed\n");
+		pr_debug("Not enough memory: alloc insns_buf failed\n");
 		return -ENOMEM;
 	}
 
 	priv->type_mapping = malloc(sizeof(int) * pev->ntevs);
 	if (!priv->type_mapping) {
-		pr_debug("No enough memory: alloc type_mapping failed\n");
+		pr_debug("Not enough memory: alloc type_mapping failed\n");
 		return -ENOMEM;
 	}
 	memset(priv->type_mapping, -1,
···
 
 		op->k.array.ranges = memdup(term->array.ranges, memsz);
 		if (!op->k.array.ranges) {
-			pr_debug("No enough memory to alloc indices for map\n");
+			pr_debug("Not enough memory to alloc indices for map\n");
 			return -ENOMEM;
 		}
 		op->key_type = BPF_MAP_KEY_RANGES;
···
 
 	newpriv = zalloc(sizeof(*newpriv));
 	if (!newpriv) {
-		pr_debug("No enough memory to alloc map private\n");
+		pr_debug("Not enough memory to alloc map private\n");
 		return NULL;
 	}
 	INIT_LIST_HEAD(&newpriv->ops_list);
···
 	if (!priv) {
 		priv = zalloc(sizeof(*priv));
 		if (!priv) {
-			pr_debug("No enough memory to alloc map private\n");
+			pr_debug("Not enough memory to alloc map private\n");
 			return -ENOMEM;
 		}
 		INIT_LIST_HEAD(&priv->ops_list);

tools/perf/util/event.h

···
 	PERF_IP_FLAG_TRACE_BEGIN	|\
 	PERF_IP_FLAG_TRACE_END)
 
+#define MAX_INSN 16
+
 struct perf_sample {
 	u64 ip;
 	u32 pid, tid;
···
 	u32 flags;
 	u16 insn_len;
 	u8  cpumode;
+	char insn[MAX_INSN];
 	void *raw_data;
 	struct ip_callchain *callchain;
 	struct branch_stack *branch_stack;

tools/perf/util/evsel.c

···
 #include "debug.h"
 #include "trace-event.h"
 #include "stat.h"
+#include "util/parse-branch-options.h"
 
 static struct {
 	bool sample_id_all;
···
 			break;
 		case PERF_EVSEL__CONFIG_TERM_CALLGRAPH:
 			callgraph_buf = term->val.callgraph;
+			break;
+		case PERF_EVSEL__CONFIG_TERM_BRANCH:
+			if (term->val.branch && strcmp(term->val.branch, "no")) {
+				perf_evsel__set_sample_bit(evsel, BRANCH_STACK);
+				parse_branch_str(term->val.branch,
+						 &attr->branch_sample_type);
+			} else
+				perf_evsel__reset_sample_bit(evsel, BRANCH_STACK);
 			break;
 		case PERF_EVSEL__CONFIG_TERM_STACK_USER:
 			dump_size = term->val.stack_user;

tools/perf/util/evsel.h

···
 	PERF_EVSEL__CONFIG_TERM_MAX_STACK,
 	PERF_EVSEL__CONFIG_TERM_OVERWRITE,
 	PERF_EVSEL__CONFIG_TERM_DRV_CFG,
+	PERF_EVSEL__CONFIG_TERM_BRANCH,
 	PERF_EVSEL__CONFIG_TERM_MAX,
 };
 
···
 		int	max_stack;
 		bool	inherit;
 		bool	overwrite;
+		char	*branch;
 	} val;
 };
 

tools/perf/util/genelf.c

···
 #include <limits.h>
 #include <fcntl.h>
 #include <err.h>
+#ifdef HAVE_DWARF_SUPPORT
 #include <dwarf.h>
+#endif
 
 #include "perf.h"
 #include "genelf.h"
 #include "../util/jitdump.h"
+
+#ifndef NT_GNU_BUILD_ID
+#define NT_GNU_BUILD_ID 3
+#endif
 
 #define JVMTI
 
···
 	'.', 'd', 'e', 'b', 'u', 'g', '_', 'l', 'i', 'n', 'e', 0, /* 52 */
 	'.', 'd', 'e', 'b', 'u', 'g', '_', 'i', 'n', 'f', 'o', 0, /* 64 */
 	'.', 'd', 'e', 'b', 'u', 'g', '_', 'a', 'b', 'b', 'r', 'e', 'v', 0, /* 76 */
+	'.', 'e', 'h', '_', 'f', 'r', 'a', 'm', 'e', '_', 'h', 'd', 'r', 0, /* 90 */
+	'.', 'e', 'h', '_', 'f', 'r', 'a', 'm', 'e', 0, /* 104 */
 };
 
 static struct buildid_note {
···
 }
 #endif
 
+static int
+jit_add_eh_frame_info(Elf *e, void* unwinding, uint64_t unwinding_header_size,
+		      uint64_t unwinding_size, uint64_t base_offset)
+{
+	Elf_Data *d;
+	Elf_Scn *scn;
+	Elf_Shdr *shdr;
+	uint64_t unwinding_table_size = unwinding_size - unwinding_header_size;
+
+	/*
+	 * setup eh_frame section
+	 */
+	scn = elf_newscn(e);
+	if (!scn) {
+		warnx("cannot create section");
+		return -1;
+	}
+
+	d = elf_newdata(scn);
+	if (!d) {
+		warnx("cannot get new data");
+		return -1;
+	}
+
+	d->d_align = 8;
+	d->d_off = 0LL;
+	d->d_buf = unwinding;
+	d->d_type = ELF_T_BYTE;
+	d->d_size = unwinding_table_size;
+	d->d_version = EV_CURRENT;
+
+	shdr = elf_getshdr(scn);
+	if (!shdr) {
+		warnx("cannot get section header");
+		return -1;
+	}
+
+	shdr->sh_name = 104;
+	shdr->sh_type = SHT_PROGBITS;
+	shdr->sh_addr = base_offset;
+	shdr->sh_flags = SHF_ALLOC;
+	shdr->sh_entsize = 0;
+
+	/*
+	 * setup eh_frame_hdr section
+	 */
+	scn = elf_newscn(e);
+	if (!scn) {
+		warnx("cannot create section");
+		return -1;
+	}
+
+	d = elf_newdata(scn);
+	if (!d) {
+		warnx("cannot get new data");
+		return -1;
+	}
+
+	d->d_align = 4;
+	d->d_off = 0LL;
+	d->d_buf = unwinding + unwinding_table_size;
+	d->d_type = ELF_T_BYTE;
+	d->d_size = unwinding_header_size;
+	d->d_version = EV_CURRENT;
+
+	shdr = elf_getshdr(scn);
+	if (!shdr) {
+		warnx("cannot get section header");
+		return -1;
+	}
+
+	shdr->sh_name = 90;
+	shdr->sh_type = SHT_PROGBITS;
+	shdr->sh_addr = base_offset + unwinding_table_size;
+	shdr->sh_flags = SHF_ALLOC;
+	shdr->sh_entsize = 0;
+
+	return 0;
+}
+
 /*
  * fd: file descriptor open for writing for the output file
  * load_addr: code load address (could be zero, just used for buildid)
···
 int
 jit_write_elf(int fd, uint64_t load_addr, const char *sym,
 	      const void *code, int csize,
-	      void *debug, int nr_debug_entries)
+	      void *debug __maybe_unused, int nr_debug_entries __maybe_unused,
+	      void *unwinding, uint64_t unwinding_header_size, uint64_t unwinding_size)
 {
 	Elf *e;
 	Elf_Data *d;
 	Elf_Scn *scn;
 	Elf_Ehdr *ehdr;
 	Elf_Shdr *shdr;
+	uint64_t eh_frame_base_offset;
 	char *strsym = NULL;
 	int symlen;
 	int retval = -1;
···
 	ehdr->e_type = ET_DYN;
 	ehdr->e_entry = GEN_ELF_TEXT_OFFSET;
 	ehdr->e_version = EV_CURRENT;
-	ehdr->e_shstrndx= 2; /* shdr index for section name */
+	ehdr->e_shstrndx= unwinding ? 4 : 2; /* shdr index for section name */
 
 	/*
 	 * setup text section
···
 	shdr->sh_addr = GEN_ELF_TEXT_OFFSET;
 	shdr->sh_flags = SHF_EXECINSTR | SHF_ALLOC;
 	shdr->sh_entsize = 0;
+
+	/*
+	 * Setup .eh_frame_hdr and .eh_frame
+	 */
+	if (unwinding) {
+		eh_frame_base_offset = ALIGN_8(GEN_ELF_TEXT_OFFSET + csize);
+		retval = jit_add_eh_frame_info(e, unwinding,
+					       unwinding_header_size, unwinding_size,
+					       eh_frame_base_offset);
+		if (retval)
+			goto error;
+	}
 
 	/*
 	 * setup section headers string table
···
 	shdr->sh_type = SHT_SYMTAB;
 	shdr->sh_flags = 0;
 	shdr->sh_entsize = sizeof(Elf_Sym);
-	shdr->sh_link = 4; /* index of .strtab section */
+	shdr->sh_link = unwinding ? 6 : 4; /* index of .strtab section */
 
 	/*
 	 * setup symbols string table
···
 	shdr->sh_size = sizeof(bnote);
 	shdr->sh_entsize = 0;
 
+#ifdef HAVE_DWARF_SUPPORT
 	if (debug && nr_debug_entries) {
 		retval = jit_add_debug_info(e, load_addr, debug, nr_debug_entries);
 		if (retval)
 			goto error;
-	} else {
+	} else
+#endif
+	{
 		if (elf_update(e, ELF_C_WRITE) < 0) {
 			warnx("elf_update 4 failed");
 			goto error;

tools/perf/util/genelf.h

···
 
 /* genelf.c */
 int jit_write_elf(int fd, uint64_t code_addr, const char *sym,
-		  const void *code, int csize, void *debug, int nr_debug_entries);
+		  const void *code, int csize, void *debug, int nr_debug_entries,
+		  void *unwinding, uint64_t unwinding_header_size, uint64_t unwinding_size);
+#ifdef HAVE_DWARF_SUPPORT
 /* genelf_debug.c */
 int jit_add_debug_info(Elf *e, uint64_t code_addr, void *debug, int nr_debug_entries);
+#endif
 
 #if   defined(__arm__)
 #define GEN_ELF_ARCH	EM_ARM

tools/perf/util/header.c

···
 	struct header_print_data hd;
 	struct perf_header *header = &session->header;
 	int fd = perf_data_file__fd(session->file);
+	struct stat st;
+	int ret, bit;
+
 	hd.fp = fp;
 	hd.full = full;
 
+	ret = fstat(fd, &st);
+	if (ret == -1)
+		return -1;
+
+	fprintf(fp, "# captured on: %s", ctime(&st.st_ctime));
+
 	perf_header__process_sections(header, fd, &hd,
 				      perf_file_section__fprintf_info);
+
+	fprintf(fp, "# missing features: ");
+	for_each_clear_bit(bit, header->adds_features, HEADER_LAST_FEATURE) {
+		if (bit)
+			fprintf(fp, "%s ", feat_ops[bit].name);
+	}
+
+	fprintf(fp, "\n");
 	return 0;
 }
 
···
 
 		err = feat_ops[type].write(fd, h, evlist);
 		if (err < 0) {
-			pr_debug("failed to write feature %d\n", type);
+			pr_debug("failed to write feature %s\n", feat_ops[type].name);
 
 			/* undo anything written */
 			lseek(fd, (*p)->offset, SEEK_SET);

tools/perf/util/intel-bts.c

···
 	sample.cpu = btsq->cpu;
 	sample.flags = btsq->sample_flags;
 	sample.insn_len = btsq->intel_pt_insn.length;
+	memcpy(sample.insn, btsq->intel_pt_insn.buf, INTEL_PT_INSN_BUF_SZ);
 
 	if (bts->synth_opts.inject) {
 		event.sample.header.size = bts->branches_event_size;
···
 	struct machine *machine = btsq->bts->machine;
 	struct thread *thread;
 	struct addr_location al;
-	unsigned char buf[1024];
-	size_t bufsz;
+	unsigned char buf[INTEL_PT_INSN_BUF_SZ];
 	ssize_t len;
 	int x86_64;
 	uint8_t cpumode;
 	int err = -1;
-
-	bufsz = intel_pt_insn_max_size();
 
 	if (machine__kernel_ip(machine, ip))
 		cpumode = PERF_RECORD_MISC_KERNEL;
···
 	if (!al.map || !al.map->dso)
 		goto out_put;
 
-	len = dso__data_read_addr(al.map->dso, al.map, machine, ip, buf, bufsz);
+	len = dso__data_read_addr(al.map->dso, al.map, machine, ip, buf,
+				  INTEL_PT_INSN_BUF_SZ);
 	if (len <= 0)
 		goto out_put;
 

tools/perf/util/intel-pt-decoder/intel-pt-decoder.c

···
 out_no_progress:
 	decoder->state.insn_op = intel_pt_insn->op;
 	decoder->state.insn_len = intel_pt_insn->length;
+	memcpy(decoder->state.insn, intel_pt_insn->buf,
+	       INTEL_PT_INSN_BUF_SZ);
 
 	if (decoder->tx_flags & INTEL_PT_IN_TX)
 		decoder->state.flags |= INTEL_PT_IN_TX;

tools/perf/util/intel-pt-decoder/intel-pt-decoder.h

···
 	uint32_t flags;
 	enum intel_pt_insn_op insn_op;
 	int insn_len;
+	char insn[INTEL_PT_INSN_BUF_SZ];
 };
 
 struct intel_pt_insn;

tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c

···
 
 #include "intel-pt-insn-decoder.h"
 
+#if INTEL_PT_INSN_BUF_SZ < MAX_INSN_SIZE || INTEL_PT_INSN_BUF_SZ > MAX_INSN
+#error Instruction buffer size too small
+#endif
+
 /* Based on branch_type() from perf_event_intel_lbr.c */
 static void intel_pt_insn_decoder(struct insn *insn,
 				  struct intel_pt_insn *intel_pt_insn)
···
 	if (!insn_complete(&insn) || insn.length > len)
 		return -1;
 	intel_pt_insn_decoder(&insn, intel_pt_insn);
-	if (insn.length < INTEL_PT_INSN_DBG_BUF_SZ)
+	if (insn.length < INTEL_PT_INSN_BUF_SZ)
 		memcpy(intel_pt_insn->buf, buf, insn.length);
 	else
-		memcpy(intel_pt_insn->buf, buf, INTEL_PT_INSN_DBG_BUF_SZ);
+		memcpy(intel_pt_insn->buf, buf, INTEL_PT_INSN_BUF_SZ);
 	return 0;
 }
 
···
 		break;
 	}
 	return 0;
-}
-
-size_t intel_pt_insn_max_size(void)
-{
-	return MAX_INSN_SIZE;
 }
 
 int intel_pt_insn_type(enum intel_pt_insn_op op)

tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.h

···
 #include <stdint.h>
 
 #define INTEL_PT_INSN_DESC_MAX		32
-#define INTEL_PT_INSN_DBG_BUF_SZ	16
+#define INTEL_PT_INSN_BUF_SZ		16
 
 enum intel_pt_insn_op {
 	INTEL_PT_OP_OTHER,
···
 	enum intel_pt_insn_branch	branch;
 	int				length;
 	int32_t				rel;
-	unsigned char			buf[INTEL_PT_INSN_DBG_BUF_SZ];
+	unsigned char			buf[INTEL_PT_INSN_BUF_SZ];
 };
 
 int intel_pt_get_insn(const unsigned char *buf, size_t len, int x86_64,
···
 
 int intel_pt_insn_desc(const struct intel_pt_insn *intel_pt_insn, char *buf,
 		       size_t buf_len);
-
-size_t intel_pt_insn_max_size(void);
 
 int intel_pt_insn_type(enum intel_pt_insn_op op);
 

tools/perf/util/intel-pt-decoder/intel-pt-log.c

···
 	if (intel_pt_log_open())
 		return;
 
-	if (len > INTEL_PT_INSN_DBG_BUF_SZ)
-		len = INTEL_PT_INSN_DBG_BUF_SZ;
+	if (len > INTEL_PT_INSN_BUF_SZ)
+		len = INTEL_PT_INSN_BUF_SZ;
 	intel_pt_print_data(intel_pt_insn->buf, len, ip, 8);
 	if (intel_pt_insn_desc(intel_pt_insn, desc, INTEL_PT_INSN_DESC_MAX) > 0)
 		fprintf(f, "%s\n", desc);

tools/perf/util/intel-pt.c

···
 	u32 flags;
 	u16 insn_len;
 	u64 last_insn_cnt;
+	char insn[INTEL_PT_INSN_BUF_SZ];
 };
 
 static void intel_pt_dump(struct intel_pt *pt __maybe_unused,
···
 	enum intel_pt_insn_branch	branch;
 	int				length;
 	int32_t				rel;
+	char				insn[INTEL_PT_INSN_BUF_SZ];
 };
 
 static int intel_pt_config_div(const char *var, const char *value, void *data)
···
 	e->branch = intel_pt_insn->branch;
 	e->length = intel_pt_insn->length;
 	e->rel = intel_pt_insn->rel;
+	memcpy(e->insn, intel_pt_insn->buf, INTEL_PT_INSN_BUF_SZ);
 
 	err = auxtrace_cache__add(c, offset, &e->entry);
 	if (err)
···
 	struct machine *machine = ptq->pt->machine;
 	struct thread *thread;
 	struct addr_location al;
-	unsigned char buf[1024];
-	size_t bufsz;
+	unsigned char buf[INTEL_PT_INSN_BUF_SZ];
 	ssize_t len;
 	int x86_64;
 	u8 cpumode;
···
 	u64 insn_cnt = 0;
 	bool one_map = true;
 
+	intel_pt_insn->length = 0;
+
 	if (to_ip && *ip == to_ip)
 		goto out_no_cache;
-
-	bufsz = intel_pt_insn_max_size();
 
 	if (*ip >= ptq->pt->kernel_start)
 		cpumode = PERF_RECORD_MISC_KERNEL;
···
 				intel_pt_insn->branch = e->branch;
 				intel_pt_insn->length = e->length;
 				intel_pt_insn->rel = e->rel;
+				memcpy(intel_pt_insn->buf, e->insn,
+				       INTEL_PT_INSN_BUF_SZ);
 				intel_pt_log_insn_no_data(intel_pt_insn, *ip);
 				return 0;
 			}
···
 
 		while (1) {
 			len = dso__data_read_offset(al.map->dso, machine,
-						    offset, buf, bufsz);
+						    offset, buf,
+						    INTEL_PT_INSN_BUF_SZ);
 			if (len <= 0)
 				return -EINVAL;
 
···
 		if (ptq->state->flags & INTEL_PT_IN_TX)
 			ptq->flags |= PERF_IP_FLAG_IN_TX;
 		ptq->insn_len = ptq->state->insn_len;
+		memcpy(ptq->insn, ptq->state->insn, INTEL_PT_INSN_BUF_SZ);
 	}
 }
 
···
 	sample.cpu = ptq->cpu;
 	sample.flags = ptq->flags;
 	sample.insn_len = ptq->insn_len;
+	memcpy(sample.insn, ptq->insn, INTEL_PT_INSN_BUF_SZ);
 
 	/*
 	 * perf report cannot handle events without a branch stack when using
···
 	sample.cpu = ptq->cpu;
 	sample.flags = ptq->flags;
 	sample.insn_len = ptq->insn_len;
+	memcpy(sample.insn, ptq->insn, INTEL_PT_INSN_BUF_SZ);
 
 	ptq->last_insn_cnt = ptq->state->tot_insn_cnt;
 
···
 	sample.cpu = ptq->cpu;
 	sample.flags = ptq->flags;
 	sample.insn_len = ptq->insn_len;
+	memcpy(sample.insn, ptq->insn, INTEL_PT_INSN_BUF_SZ);
 
 	if (pt->synth_opts.callchain) {
 		thread_stack__sample(ptq->thread, ptq->chain,

tools/perf/util/jitdump.c

···
 	bool		 needs_bswap; /* handles cross-endianess */
 	bool		 use_arch_timestamp;
 	void		 *debug_data;
+	void		 *unwinding_data;
+	uint64_t	 unwinding_size;
+	uint64_t	 unwinding_mapped_size;
+	uint64_t         eh_frame_hdr_size;
 	size_t		 nr_debug_entries;
 	uint32_t         code_load_count;
 	u64		 bytes_written;
···
 	     const void *code,
 	     int csize,
 	     void *debug,
-	     int nr_debug_entries)
+	     int nr_debug_entries,
+	     void *unwinding,
+	     uint32_t unwinding_header_size,
+	     uint32_t unwinding_size)
 {
 	int ret, fd;
 
···
 		return -1;
 	}
 
-        ret = jit_write_elf(fd, code_addr, sym, (const void *)code, csize, debug, nr_debug_entries);
+	ret = jit_write_elf(fd, code_addr, sym, (const void *)code, csize, debug, nr_debug_entries,
+			    unwinding, unwinding_header_size, unwinding_size);
 
         close(fd);
 
···
 			header.pid,
 			header.elf_mach,
 			jd->use_arch_timestamp);
+
+	if (header.version > JITHEADER_VERSION) {
+		pr_err("wrong jitdump version %u, expected " STR(JITHEADER_VERSION),
+			header.version);
+		goto error;
+	}
 
 	if (header.flags & JITDUMP_FLAGS_RESERVED) {
 		pr_err("jitdump file contains invalid or unsupported flags 0x%llx\n",
···
 		return NULL;
 
 	if (id >= JIT_CODE_MAX) {
-		pr_warning("next_entry: unknown prefix %d, skipping\n", id);
-		return NULL;
+		pr_warning("next_entry: unknown record type %d, skipping\n", id);
 	}
 	if (bs > jd->bufsize) {
 		void *n;
···
 			}
 		}
 		break;
+	case JIT_CODE_UNWINDING_INFO:
+		if (jd->needs_bswap) {
+			jr->unwinding.unwinding_size = bswap_64(jr->unwinding.unwinding_size);
+			jr->unwinding.eh_frame_hdr_size = bswap_64(jr->unwinding.eh_frame_hdr_size);
+			jr->unwinding.mapped_size = bswap_64(jr->unwinding.mapped_size);
+		}
+		break;
 	case JIT_CODE_CLOSE:
 		break;
 	case JIT_CODE_LOAD:
···
 		break;
 	case JIT_CODE_MAX:
 	default:
-		return NULL;
+		/* skip unknown record (we have read them) */
+		break;
 	}
 	return jr;
 }
···
 	u16 idr_size;
 	const char *sym;
 	uint32_t count;
-	int ret, csize;
+	int ret, csize, usize;
 	pid_t pid, tid;
 	struct {
 		u32 pid, tid;
···
 	pid   = jr->load.pid;
 	tid   = jr->load.tid;
 	csize = jr->load.code_size;
+	usize = jd->unwinding_mapped_size;
 	addr  = jr->load.code_addr;
 	sym   = (void *)((unsigned long)jr + sizeof(jr->load));
 	code  = (unsigned long)jr + jr->load.p.total_size - csize;
···
 
 	size = PERF_ALIGN(size, sizeof(u64));
 	uaddr = (uintptr_t)code;
-	ret = jit_emit_elf(filename, sym, addr, (const void *)uaddr, csize, jd->debug_data, jd->nr_debug_entries);
+	ret = jit_emit_elf(filename, sym, addr, (const void *)uaddr, csize, jd->debug_data, jd->nr_debug_entries,
+			   jd->unwinding_data, jd->eh_frame_hdr_size, jd->unwinding_size);
 
 	if (jd->debug_data && jd->nr_debug_entries) {
 		free(jd->debug_data);
 		jd->debug_data = NULL;
 		jd->nr_debug_entries = 0;
+	}
+
+	if (jd->unwinding_data && jd->eh_frame_hdr_size) {
+		free(jd->unwinding_data);
+		jd->unwinding_data = NULL;
+		jd->eh_frame_hdr_size = 0;
+		jd->unwinding_mapped_size = 0;
+		jd->unwinding_size = 0;
 	}
 
 	if (ret) {
···
 
 	event->mmap2.pgoff = GEN_ELF_TEXT_OFFSET;
 	event->mmap2.start = addr;
-	event->mmap2.len   = csize;
+	event->mmap2.len   = usize ? ALIGN_8(csize) + usize : csize;
 	event->mmap2.pid   = pid;
 	event->mmap2.tid   = tid;
 	event->mmap2.ino   = st.st_ino;
···
 	char *filename;
 	size_t size;
 	struct stat st;
+	int usize;
 	u16 idr_size;
 	int ret;
 	pid_t pid, tid;
···
 
 	pid = jr->move.pid;
 	tid =  jr->move.tid;
+	usize = jd->unwinding_mapped_size;
 	idr_size = jd->machine->id_hdr_size;
 
 	/*
···
 			(sizeof(event->mmap2.filename) - size) + idr_size);
 	event->mmap2.pgoff = GEN_ELF_TEXT_OFFSET;
 	event->mmap2.start = jr->move.new_code_addr;
-	event->mmap2.len   = jr->move.code_size;
+	event->mmap2.len   = usize ? ALIGN_8(jr->move.code_size) + usize
+				   : jr->move.code_size;
 	event->mmap2.pid   = pid;
 	event->mmap2.tid   = tid;
 	event->mmap2.ino   = st.st_ino;
···
 }
 
 static int
+jit_repipe_unwinding_info(struct jit_buf_desc *jd, union jr_entry *jr)
+{
+	void *unwinding_data;
+	uint32_t unwinding_data_size;
+
+	if (!(jd && jr))
+		return -1;
+
+	unwinding_data_size  = jr->prefix.total_size - sizeof(jr->unwinding);
+	unwinding_data = malloc(unwinding_data_size);
+	if (!unwinding_data)
+		return -1;
+
+	memcpy(unwinding_data, &jr->unwinding.unwinding_data,
+	       unwinding_data_size);
+
+	jd->eh_frame_hdr_size = jr->unwinding.eh_frame_hdr_size;
+	jd->unwinding_size = jr->unwinding.unwinding_size;
+	jd->unwinding_mapped_size = jr->unwinding.mapped_size;
+	jd->unwinding_data = unwinding_data;
+
+	return 0;
+}
+
+static int
 jit_process_dump(struct jit_buf_desc *jd)
 {
 	union jr_entry *jr;
-	int ret;
+	int ret = 0;
 
 	while ((jr = jit_get_next_entry(jd))) {
 		switch(jr->prefix.id) {
···
 			break;
 		case JIT_CODE_DEBUG_INFO:
 			ret = jit_repipe_debug_info(jd, jr);
+			break;
+		case JIT_CODE_UNWINDING_INFO:
+			ret = jit_repipe_unwinding_info(jd, jr);
 			break;
 		default:
 			ret = 0;

tools/perf/util/jitdump.h

···
 #define JITHEADER_MAGIC_SW	0x4454694A
 
 #define PADDING_8ALIGNED(x) ((((x) + 7) & 7) ^ 7)
+#define ALIGN_8(x) (((x) + 7) & (~7))
 
 #define JITHEADER_VERSION 1
 
···
         JIT_CODE_MOVE           = 1,
 	JIT_CODE_DEBUG_INFO	= 2,
 	JIT_CODE_CLOSE		= 3,
+	JIT_CODE_UNWINDING_INFO	= 4,
 
 	JIT_CODE_MAX,
 };
···
 	struct debug_entry entries[0];
 };
 
+struct jr_code_unwinding_info {
+	struct jr_prefix p;
+
+	uint64_t unwinding_size;
+	uint64_t eh_frame_hdr_size;
+	uint64_t mapped_size;
+	const char unwinding_data[0];
+};
+
 union jr_entry {
         struct jr_code_debug_info info;
         struct jr_code_close close;
         struct jr_code_load load;
         struct jr_code_move move;
         struct jr_prefix prefix;
+        struct jr_code_unwinding_info unwinding;
 };
 
 static inline struct debug_entry *

tools/perf/util/llvm-utils.c

···
 	char *p;
 
 	if (!obj_path) {
-		pr_warning("WARNING: No enough memory, skip object dumping\n");
+		pr_warning("WARNING: Not enough memory, skip object dumping\n");
 		return;
 	}
 

tools/perf/util/map.c

···
 			continue;
 
 		if (verbose >= 2) {
-			fputs("overlapping maps:\n", fp);
-			map__fprintf(map, fp);
-			map__fprintf(pos, fp);
+
+			if (use_browser) {
+				pr_warning("overlapping maps in %s "
+					   "(disable tui for more info)\n",
+					   map->dso->name);
+			} else {
+				fputs("overlapping maps:\n", fp);
+				map__fprintf(map, fp);
+				map__fprintf(pos, fp);
+			}
 		}
 
 		rb_erase_init(&pos->rb_node, root);
···
 
 			before->end = map->start;
 			__map_groups__insert(pos->groups, before);
-			if (verbose >= 2)
+			if (verbose >= 2 && !use_browser)
 				map__fprintf(before, fp);
 			map__put(before);
 		}
···
 
 			after->start = map->end;
 			__map_groups__insert(pos->groups, after);
-			if (verbose >= 2)
+			if (verbose >= 2 && !use_browser)
 				map__fprintf(after, fp);
 			map__put(after);
 		}

tools/perf/util/parse-branch-options.c

···
 	BRANCH_END
 };
 
-int
-parse_branch_stack(const struct option *opt, const char *str, int unset)
+int parse_branch_str(const char *str, __u64 *mode)
 {
 #define ONLY_PLM \
 	(PERF_SAMPLE_BRANCH_USER	|\
 	 PERF_SAMPLE_BRANCH_KERNEL	|\
 	 PERF_SAMPLE_BRANCH_HV)
 
-	uint64_t *mode = (uint64_t *)opt->value;
+	int ret = 0;
+	char *p, *s;
+	char *os = NULL;
 	const struct branch_mode *br;
-	char *s, *os = NULL, *p;
-	int ret = -1;
+
+	if (str == NULL) {
+		*mode = PERF_SAMPLE_BRANCH_ANY;
+		return 0;
+	}
+
+	/* because str is read-only */
+	s = os = strdup(str);
+	if (!s)
+		return -1;
+
+	for (;;) {
+		p = strchr(s, ',');
+		if (p)
+			*p = '\0';
+
+		for (br = branch_modes; br->name; br++) {
+			if (!strcasecmp(s, br->name))
+				break;
+		}
+		if (!br->name) {
+			ret = -1;
+			ui__warning("unknown branch filter %s,"
+				    " check man page\n", s);
+			goto error;
+		}
+
+		*mode |= br->mode;
+
+		if (!p)
+			break;
+
+		s = p + 1;
+	}
+
+	/* default to any branch */
+	if ((*mode & ~ONLY_PLM) == 0) {
+		*mode = PERF_SAMPLE_BRANCH_ANY;
+	}
+error:
+	free(os);
+	return ret;
+}
+
+int
+parse_branch_stack(const struct option *opt, const char *str, int unset)
+{
+	__u64 *mode = (__u64 *)opt->value;
 
 	if (unset)
 		return 0;
···
 	if (*mode)
 		return -1;
 
-	/* str may be NULL in case no arg is passed to -b */
-	if (str) {
-		/* because str is read-only */
-		s = os = strdup(str);
-		if (!s)
-			return -1;
-
-		for (;;) {
-			p = strchr(s, ',');
-			if (p)
-				*p = '\0';
-
-			for (br = branch_modes; br->name; br++) {
-				if (!strcasecmp(s, br->name))
-					break;
-			}
-			if (!br->name) {
-				ui__warning("unknown branch filter %s,"
-					    " check man page\n", s);
-				goto error;
-			}
-
-			*mode |= br->mode;
-
-			if (!p)
-				break;
-
-			s = p + 1;
-		}
-	}
-	ret = 0;
-
-	/* default to any branch */
-	if ((*mode & ~ONLY_PLM) == 0) {
-		*mode = PERF_SAMPLE_BRANCH_ANY;
-	}
-error:
-	free(os);
-	return ret;
+	return parse_branch_str(str, mode);
 }

tools/perf/util/parse-branch-options.h

···
 #ifndef _PERF_PARSE_BRANCH_OPTIONS_H
 #define _PERF_PARSE_BRANCH_OPTIONS_H 1
-struct option;
+#include <stdint.h>
 int parse_branch_stack(const struct option *opt, const char *str, int unset);
+int parse_branch_str(const char *str, __u64 *mode);
 #endif /* _PERF_PARSE_BRANCH_OPTIONS_H */

tools/perf/util/parse-events.c

···
 #include "cpumap.h"
 #include "probe-file.h"
 #include "asm/bug.h"
+#include "util/parse-branch-options.h"
 
 #define MAX_NAME_LEN 100
 
···
 		CHECK_TYPE_VAL(NUM);
 		break;
 	case PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE:
-		/*
-		 * TODO uncomment when the field is available
-		 * attr->branch_sample_type = term->val.num;
-		 */
+		CHECK_TYPE_VAL(STR);
+		if (strcmp(term->val.str, "no") &&
+		    parse_branch_str(term->val.str, &attr->branch_sample_type)) {
+			err->str = strdup("invalid branch sample type");
+			err->idx = term->err_val;
+			return -EINVAL;
+		}
 		break;
 	case PARSE_EVENTS__TERM_TYPE_TIME:
 		CHECK_TYPE_VAL(NUM);
···
 			break;
 		case PARSE_EVENTS__TERM_TYPE_CALLGRAPH:
 			ADD_CONFIG_TERM(CALLGRAPH, callgraph, term->val.str);
+			break;
+		case PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE:
+			ADD_CONFIG_TERM(BRANCH, branch, term->val.str);
 			break;
 		case PARSE_EVENTS__TERM_TYPE_STACKSIZE:
 			ADD_CONFIG_TERM(STACK_USER, stack_user, term->val.num);

tools/perf/util/pmu.c

···
 	struct pmu_events_map *map;
 	struct pmu_event *pe;
 	char *cpuid;
+	static bool printed;
 
 	cpuid = getenv("PERF_CPUID");
 	if (cpuid)
···
 	if (!cpuid)
 		return;
 
-	pr_debug("Using CPUID %s\n", cpuid);
+	if (!printed) {
+		pr_debug("Using CPUID %s\n", cpuid);
+		printed = true;
+	}
 
 	i = 0;
 	while (1) {
···
 			bool is_cpu = !strcmp(pmu->name, "cpu");
 
 			if (event_glob != NULL &&
-			    !(strglobmatch(name, event_glob) ||
-			      (!is_cpu && strglobmatch(alias->name,
+			    !(strglobmatch_nocase(name, event_glob) ||
+			      (!is_cpu && strglobmatch_nocase(alias->name,
 						       event_glob))))
 				continue;
 

tools/perf/util/quote.c

···
 			break;
 		ret = sq_quote_buf(dst, argv[i]);
 		if (maxlen && dst->len > maxlen)
-			die("Too many or long arguments");
+			return -ENOSPC;
 	}
 	return ret;
 }

tools/perf/util/session.c

···
 void perf_session__fprintf_info(struct perf_session *session, FILE *fp,
 				bool full)
 {
-	struct stat st;
-	int fd, ret;
-
 	if (session == NULL || fp == NULL)
 		return;
 
-	fd = perf_data_file__fd(session->file);
-
-	ret = fstat(fd, &st);
-	if (ret == -1)
-		return;
-
 	fprintf(fp, "# ========\n");
-	fprintf(fp, "# captured on: %s", ctime(&st.st_ctime));
 	perf_header__fprintf_info(session, fp, full);
 	fprintf(fp, "# ========\n#\n");
 }

tools/perf/util/string.c

···
 }
 
 /* Glob/lazy pattern matching */
-static bool __match_glob(const char *str, const char *pat, bool ignore_space)
+static bool __match_glob(const char *str, const char *pat, bool ignore_space,
+			bool case_ins)
 {
 	while (*str && *pat && *pat != '*') {
 		if (ignore_space) {
···
 				return false;
 		else if (*pat == '\\') /* Escaped char match as normal char */
 			pat++;
-		if (*str++ != *pat++)
+		if (case_ins) {
+			if (tolower(*str) != tolower(*pat))
+				return false;
+		} else if (*str != *pat)
 			return false;
+		str++;
+		pat++;
 	}
 	/* Check wild card */
 	if (*pat == '*') {
···
 		if (!*pat)	/* Tail wild card matches all */
 			return true;
 		while (*str)
-			if (__match_glob(str++, pat, ignore_space))
+			if (__match_glob(str++, pat, ignore_space, case_ins))
 				return true;
 	}
 	return !*str && !*pat;
···
  */
 bool strglobmatch(const char *str, const char *pat)
 {
-	return __match_glob(str, pat, false);
+	return __match_glob(str, pat, false, false);
+}
+
+bool strglobmatch_nocase(const char *str, const char *pat)
+{
+	return __match_glob(str, pat, false, true);
 }
 
 /**
···
  */
 bool strlazymatch(const char *str, const char *pat)
 {
-	return __match_glob(str, pat, true);
+	return __match_glob(str, pat, true, false);
 }
 
 /**

tools/perf/util/unwind-libunwind-local.c

···
 		di.format   = UNW_INFO_FORMAT_REMOTE_TABLE;
 		di.start_ip = map->start;
 		di.end_ip   = map->end;
-		di.u.rti.segbase    = map->start + segbase;
-		di.u.rti.table_data = map->start + table_data;
+		di.u.rti.segbase    = map->start + segbase - map->pgoff;
+		di.u.rti.table_data = map->start + table_data - map->pgoff;
 		di.u.rti.table_len  = fde_count * sizeof(struct table_entry)
 				      / sizeof(unw_word_t);
 		ret = dwarf_search_unwind_table(as, ip, &di, pi,

tools/perf/util/util.h

···
 char **argv_split(const char *str, int *argcp);
 void argv_free(char **argv);
 bool strglobmatch(const char *str, const char *pat);
+bool strglobmatch_nocase(const char *str, const char *pat);
 bool strlazymatch(const char *str, const char *pat);
 static inline bool strisglob(const char *str)
 {

tools/perf/util/values.c

···
 
 #include "util.h"
 #include "values.h"
+#include "debug.h"
 
-void perf_read_values_init(struct perf_read_values *values)
+int perf_read_values_init(struct perf_read_values *values)
 {
 	values->threads_max = 16;
 	values->pid = malloc(values->threads_max * sizeof(*values->pid));
 	values->tid = malloc(values->threads_max * sizeof(*values->tid));
 	values->value = malloc(values->threads_max * sizeof(*values->value));
-	if (!values->pid || !values->tid || !values->value)
-		die("failed to allocate read_values threads arrays");
+	if (!values->pid || !values->tid || !values->value) {
+		pr_debug("failed to allocate read_values threads arrays");
+		goto out_free_pid;
+	}
 	values->threads = 0;
 
 	values->counters_max = 16;
···
 				      * sizeof(*values->counterrawid));
 	values->countername = malloc(values->counters_max
 				     * sizeof(*values->countername));
-	if (!values->counterrawid || !values->countername)
-		die("failed to allocate read_values counters arrays");
+	if (!values->counterrawid || !values->countername) {
+		pr_debug("failed to allocate read_values counters arrays");
+		goto out_free_counter;
+	}
 	values->counters = 0;
+
+	return 0;
+
+out_free_counter:
+	zfree(&values->counterrawid);
+	zfree(&values->countername);
+out_free_pid:
+	zfree(&values->pid);
+	zfree(&values->tid);
+	zfree(&values->value);
+	return -ENOMEM;
 }
 
 void perf_read_values_destroy(struct perf_read_values *values)
···
 	zfree(&values->countername);
 }
 
-static void perf_read_values__enlarge_threads(struct perf_read_values *values)
+static int perf_read_values__enlarge_threads(struct perf_read_values *values)
 {
-	values->threads_max *= 2;
-	values->pid = realloc(values->pid,
-			      values->threads_max * sizeof(*values->pid));
-	values->tid = realloc(values->tid,
-			      values->threads_max * sizeof(*values->tid));
-	values->value = realloc(values->value,
-				values->threads_max * sizeof(*values->value));
-	if (!values->pid || !values->tid || !values->value)
-		die("failed to enlarge read_values threads arrays");
+	int nthreads_max = values->threads_max * 2;
+	void *npid = realloc(values->pid, nthreads_max * sizeof(*values->pid)),
+	     *ntid = realloc(values->tid, nthreads_max * sizeof(*values->tid)),
+	     *nvalue = realloc(values->value, nthreads_max * sizeof(*values->value));
+
+	if (!npid || !ntid || !nvalue)
+		goto out_err;
+
+	values->threads_max = nthreads_max;
+	values->pid = npid;
+	values->tid = ntid;
+	values->value = nvalue;
+	return 0;
+out_err:
+	free(npid);
+	free(ntid);
+	free(nvalue);
+	pr_debug("failed to enlarge read_values threads arrays");
+	return -ENOMEM;
 }
 
 static int perf_read_values__findnew_thread(struct perf_read_values *values,
···
 		if (values->pid[i] == pid && values->tid[i] == tid)
 			return i;
 
-	if (values->threads == values->threads_max)
-		perf_read_values__enlarge_threads(values);
+	if (values->threads == values->threads_max) {
+		i = perf_read_values__enlarge_threads(values);
+		if (i < 0)
+			return i;
+	}
 
-	i = values->threads++;
+	i = values->threads + 1;
+	values->value[i] = malloc(values->counters_max * sizeof(**values->value));
+	if (!values->value[i]) {
+		pr_debug("failed to allocate read_values counters array");
+		return -ENOMEM;
+	}
 	values->pid[i] = pid;
 	values->tid[i] = tid;
-	values->value[i] = malloc(values->counters_max * sizeof(**values->value));
-	if (!values->value[i])
-		die("failed to allocate read_values counters array");
+	values->threads = i;
 
 	return i;
 }
···
 	return i;
 }
 
-void perf_read_values_add_value(struct perf_read_values *values,
+int perf_read_values_add_value(struct perf_read_values *values,
 				u32 pid, u32 tid,
 				u64 rawid, const char *name, u64 value)
 {
 	int tindex, cindex;
 
 	tindex = perf_read_values__findnew_thread(values, pid, tid);
+	if (tindex < 0)
+		return tindex;
 	cindex = perf_read_values__findnew_counter(values, rawid, name);
+	if (cindex < 0)
+		return cindex;
 
 	values->value[tindex][cindex] = value;
+	return 0;
 }
 
 static void perf_read_values__display_pretty(FILE *fp,

tools/perf/util/values.h

···
 	u64 **value;
 };
 
-void perf_read_values_init(struct perf_read_values *values);
+int perf_read_values_init(struct perf_read_values *values);
 void perf_read_values_destroy(struct perf_read_values *values);
 
-void perf_read_values_add_value(struct perf_read_values *values,
+int perf_read_values_add_value(struct perf_read_values *values,
 				u32 pid, u32 tid,
 				u64 rawid, const char *name, u64 value);