perf tools: Introduce an abstraction for AUX Area and Instruction Tracing

index 6966d07..a5b3672 100644
@@ -75,6 +75,7 @@ libperf-$(CONFIG_X86) += tsc.o
 libperf-y += cloexec.o
 libperf-y += thread-stack.o
 libperf-$(CONFIG_AUXTRACE) += auxtrace.o
+libperf-$(CONFIG_AUXTRACE) += intel-pt-decoder/
 
 libperf-$(CONFIG_LIBELF) += symbol-elf.o
 libperf-$(CONFIG_LIBELF) += probe-event.o

new file mode 100644
index 0000000..9d67381
@@ -0,0 +1 @@
+libperf-$(CONFIG_AUXTRACE) += intel-pt-pkt-decoder.o

index 10df572..7ad74e4 100644
@@ -57,6 +57,8 @@ quiet_cmd_cc_i_c = CPP      $@
 quiet_cmd_cc_s_c = AS       $@
       cmd_cc_s_c = $(CC) $(c_flags) -S -o $@ $<
 
+quiet_cmd_gen = GEN      $@
+
 # Link agregate command
 # If there's nothing to link, create empty $@ object.
 quiet_cmd_ld_multi = LD       $@

index 812f904..c88d5c5 100644
@@ -28,3 +28,5 @@ config.mak.autogen
 *-flex.*
 *.pyc
 *.pyo
+util/intel-pt-decoder/inat-tables.c
+util/intel-pt-decoder/inat.c

index 5816a3b..3ae3a8e 100644
@@ -76,6 +76,12 @@ include config/utilities.mak
 #
 # Define NO_AUXTRACE if you do not want AUX area tracing support
 
+# As per kernel Makefile, avoid funny character set dependencies
+unexport LC_ALL
+LC_COLLATE=C
+LC_NUMERIC=C
+export LC_COLLATE LC_NUMERIC
+
 ifeq ($(srctree),)
 srctree := $(patsubst %/,%,$(dir $(shell pwd)))
 srctree := $(patsubst %/,%,$(dir $(srctree)))

@@ -122,6 +128,7 @@ INSTALL = install
 FLEX    = flex
 BISON   = bison
 STRIP   = strip
+AWK     = awk
 
 LIB_DIR          = $(srctree)/tools/lib/api/
 TRACE_EVENT_DIR = $(srctree)/tools/lib/traceevent/

@@ -272,7 +279,7 @@ strip: $(PROGRAMS) $(OUTPUT)perf
 
 PERF_IN := $(OUTPUT)perf-in.o
 
-export srctree OUTPUT RM CC LD AR CFLAGS V BISON FLEX
+export srctree OUTPUT RM CC LD AR CFLAGS V BISON FLEX AWK
 build := -f $(srctree)/tools/build/Makefile.build dir=. obj
 
 $(PERF_IN): $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h FORCE

@@ -536,7 +543,8 @@ clean: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean config-clean
 	$(Q)find . -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete
 	$(Q)$(RM) .config-detected
 	$(call QUIET_CLEAN, core-progs) $(RM) $(ALL_PROGRAMS) perf perf-read-vdso32 perf-read-vdsox32
-	$(call QUIET_CLEAN, core-gen)   $(RM)  *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope* $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)FEATURE-DUMP $(OUTPUT)util/*-bison* $(OUTPUT)util/*-flex*
+	$(call QUIET_CLEAN, core-gen)   $(RM)  *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope* $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)FEATURE-DUMP $(OUTPUT)util/*-bison* $(OUTPUT)util/*-flex* \
+		$(OUTPUT)util/intel-pt-decoder/inat.c $(OUTPUT)util/intel-pt-decoder/inat-tables.c
 	$(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) clean
 	$(python-clean)
 

index 9d67381..f5f7f87 100644
@@ -1 +1,14 @@
-libperf-$(CONFIG_AUXTRACE) += intel-pt-pkt-decoder.o
+libperf-$(CONFIG_AUXTRACE) += intel-pt-pkt-decoder.o intel-pt-insn-decoder.o
+
+inat_tables_script = ../../arch/x86/tools/gen-insn-attr-x86.awk
+inat_tables_maps = ../../arch/x86/lib/x86-opcode-map.txt
+
+$(OUTPUT)util/intel-pt-decoder/inat-tables.c: $(inat_tables_script) $(inat_tables_maps)
+	@$(call echo-cmd,gen)$(AWK) -f $(inat_tables_script) $(inat_tables_maps) > $@ || rm -f $@
+
+$(OUTPUT)util/intel-pt-decoder/inat.c:
+	@$(call echo-cmd,gen)cp ../../arch/x86/lib/inat.c $(OUTPUT)util/intel-pt-decoder/inat.c
+
+$(OUTPUT)util/intel-pt-decoder/intel-pt-insn-decoder.o: $(OUTPUT)util/intel-pt-decoder/inat.c $(OUTPUT)util/intel-pt-decoder/inat-tables.c
+
+CFLAGS_intel-pt-insn-decoder.o += -I../../arch/x86/include -I$(OUTPUT)util/intel-pt-decoder -I../../arch/x86/lib -Wno-override-init

index f5f7f87..587321a 100644
@@ -1,4 +1,4 @@
-libperf-$(CONFIG_AUXTRACE) += intel-pt-pkt-decoder.o intel-pt-insn-decoder.o
+libperf-$(CONFIG_AUXTRACE) += intel-pt-pkt-decoder.o intel-pt-insn-decoder.o intel-pt-log.o
 
 inat_tables_script = ../../arch/x86/tools/gen-insn-attr-x86.awk
 inat_tables_maps = ../../arch/x86/lib/x86-opcode-map.txt

index 587321a..fa12eac 100644
@@ -1,4 +1,4 @@
-libperf-$(CONFIG_AUXTRACE) += intel-pt-pkt-decoder.o intel-pt-insn-decoder.o intel-pt-log.o
+libperf-$(CONFIG_AUXTRACE) += intel-pt-pkt-decoder.o intel-pt-insn-decoder.o intel-pt-log.o intel-pt-decoder.o
 
 inat_tables_script = ../../arch/x86/tools/gen-insn-attr-x86.awk
 inat_tables_maps = ../../arch/x86/lib/x86-opcode-map.txt

index cfbccc4..1396088 100644
@@ -6,3 +6,5 @@ libperf-$(CONFIG_DWARF) += dwarf-regs.o
 
 libperf-$(CONFIG_LIBUNWIND)          += unwind-libunwind.o
 libperf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o
+
+libperf-$(CONFIG_AUXTRACE) += intel-pt.o

index a5b3672..321f34b 100644
@@ -76,6 +76,7 @@ libperf-y += cloexec.o
 libperf-y += thread-stack.o
 libperf-$(CONFIG_AUXTRACE) += auxtrace.o
 libperf-$(CONFIG_AUXTRACE) += intel-pt-decoder/
+libperf-$(CONFIG_AUXTRACE) += intel-pt.o
 
 libperf-$(CONFIG_LIBELF) += symbol-elf.o
 libperf-$(CONFIG_LIBELF) += probe-event.o

new file mode 100644
index 0000000..f47ef16
@@ -0,0 +1,467 @@
+Intel Processor Trace
+=====================
+
+perf record
+===========
+
+new event
+---------
+
+The Intel PT kernel driver creates a new PMU for Intel PT.  PMU events are
+selected by providing the PMU name followed by the "config" separated by slashes.
+An enhancement has been made to allow default "config" e.g. the option
+
+	-e intel_pt//
+
+will use a default config value.  Currently that is the same as
+
+	-e intel_pt/tsc,noretcomp=0/
+
+which is the same as
+
+	-e intel_pt/tsc=1,noretcomp=0/
+
+The config terms are listed in /sys/devices/intel_pt/format.  They are bit
+fields within the config member of the struct perf_event_attr which is
+passed to the kernel by the perf_event_open system call.  They correspond to bit
+fields in the IA32_RTIT_CTL MSR.  Here is a list of them and their definitions:
+
+	$ for f in `ls /sys/devices/intel_pt/format`;do
+	> echo $f
+	> cat /sys/devices/intel_pt/format/$f
+	> done
+	noretcomp
+	config:11
+	tsc
+	config:10
+
+Note that the default config must be overridden for each term i.e.
+
+	-e intel_pt/noretcomp=0/
+
+is the same as:
+
+	-e intel_pt/tsc=1,noretcomp=0/
+
+So, to disable TSC packets use:
+
+	-e intel_pt/tsc=0/
+
+It is also possible to specify the config value explicitly:
+
+	-e intel_pt/config=0x400/
+
+Note that, as with all events, the event is suffixed with event modifiers:
+
+	u	userspace
+	k	kernel
+	h	hypervisor
+	G	guest
+	H	host
+	p	precise ip
+
+'h', 'G' and 'H' are for virtualization which is not supported by Intel PT.
+'p' is also not relevant to Intel PT.  So only options 'u' and 'k' are
+meaningful for Intel PT.
+
+perf_event_attr is displayed if the -vv option is used e.g.
+
+	------------------------------------------------------------
+	perf_event_attr:
+	type                             6
+	size                             112
+	config                           0x400
+	{ sample_period, sample_freq }   1
+	sample_type                      IP|TID|TIME|CPU|IDENTIFIER
+	read_format                      ID
+	disabled                         1
+	inherit                          1
+	exclude_kernel                   1
+	exclude_hv                       1
+	enable_on_exec                   1
+	sample_id_all                    1
+	------------------------------------------------------------
+	sys_perf_event_open: pid 31104  cpu 0  group_fd -1  flags 0x8
+	sys_perf_event_open: pid 31104  cpu 1  group_fd -1  flags 0x8
+	sys_perf_event_open: pid 31104  cpu 2  group_fd -1  flags 0x8
+	sys_perf_event_open: pid 31104  cpu 3  group_fd -1  flags 0x8
+	------------------------------------------------------------
+
+
+new snapshot option
+-------------------
+
+To select snapshot mode a new option has been added:
+
+	-S
+
+Optionally it can be followed by the snapshot size e.g.
+
+	-S0x100000
+
+The default snapshot size is the auxtrace mmap size.  If neither auxtrace mmap size
+nor snapshot size is specified, then the default is 4MiB for privileged users
+(or if /proc/sys/kernel/perf_event_paranoid < 0), 128KiB for unprivileged users.
+If an unprivileged user does not specify mmap pages, the mmap pages will be
+reduced as described in the 'new auxtrace mmap size option' section below.
+
+The snapshot size is displayed if the option -vv is used e.g.
+
+	Intel PT snapshot size: %zu
+
+
+new auxtrace mmap size option
+---------------------------
+
+Intel PT buffer size is specified by an addition to the -m option e.g.
+
+	-m,16
+
+selects a buffer size of 16 pages i.e. 64KiB.
+
+Note that the existing functionality of -m is unchanged.  The auxtrace mmap size
+is specified by the optional addition of a comma and the value.
+
+The default auxtrace mmap size for Intel PT is 4MiB/page_size for privileged users
+(or if /proc/sys/kernel/perf_event_paranoid < 0), 128KiB for unprivileged users.
+If an unprivileged user does not specify mmap pages, the mmap pages will be
+reduced from the default 512KiB/page_size to 256KiB/page_size, otherwise the
+user is likely to get an error as they exceed their mlock limit (Max locked
+memory as shown in /proc/self/limits).  Note that perf does not count the first
+512KiB (actually /proc/sys/kernel/perf_event_mlock_kb minus 1 page) per cpu
+against the mlock limit so an unprivileged user is allowed 512KiB per cpu plus
+their mlock limit (which defaults to 64KiB but is not multiplied by the number
+of cpus).
+
+In full-trace mode, powers of two are allowed for buffer size, with a minimum
+size of 2 pages.  In snapshot mode, it is the same but the minimum size is
+1 page.
+
+The mmap size and auxtrace mmap size are displayed if the -vv option is used e.g.
+
+	mmap length 528384
+	auxtrace mmap length 4198400
+
+
+Intel PT modes of operation
+---------------------------
+
+Intel PT can be used in 2 modes:
+	full-trace mode
+	snapshot mode
+
+Full-trace mode traces continuously e.g.
+
+	perf record -e intel_pt//u uname
+
+Snapshot mode captures the available data when a signal is sent e.g.
+
+	perf record -v -e intel_pt//u -S ./loopy 1000000000 &
+	[1] 11435
+	kill -USR2 11435
+	Recording AUX area tracing snapshot
+
+Note that the signal sent is SIGUSR2.
+Note that "Recording AUX area tracing snapshot" is displayed because the -v
+option is used.
+
+None of the 3 modes can be used together.
+
+
+Buffer handling
+---------------
+
+There may be buffer limitations (i.e. single ToPa entry) which means that actual
+buffer sizes are limited to powers of 2 up to 4MiB (MAX_ORDER).  In order to
+provide other sizes, and in particular an arbitrarily large size, multiple
+buffers are logically concatenated.  However an interrupt must be used to switch
+between buffers.  That has two potential problems:
+	a) the interrupt may not be handled in time so that the current buffer
+	becomes full and some trace data is lost.
+	b) the interrupts may slow the system and affect the performance
+	results.
+
+If trace data is lost, the driver sets 'truncated' in the PERF_RECORD_AUX event
+which the tools report as an error.
+
+In full-trace mode, the driver waits for data to be copied out before allowing
+the (logical) buffer to wrap-around.  If data is not copied out quickly enough,
+again 'truncated' is set in the PERF_RECORD_AUX event.  If the driver has to
+wait, the intel_pt event gets disabled.  Because it is difficult to know when
+that happens, perf tools always re-enable the intel_pt event after copying out
+data.
+
+
+Intel PT and build ids
+----------------------
+
+By default "perf record" post-processes the event stream to find all build ids
+for executables for all addresses sampled.  Deliberately, Intel PT is not
+decoded for that purpose (it would take too long).  Instead the build ids for
+all executables encountered (due to mmap, comm or task events) are included
+in the perf.data file.
+
+To see buildids included in the perf.data file use the command:
+
+	perf buildid-list
+
+If the perf.data file contains Intel PT data, that is the same as:
+
+	perf buildid-list --with-hits
+
+
+Snapshot mode and event disabling
+---------------------------------
+
+In order to make a snapshot, the intel_pt event is disabled using an IOCTL,
+namely PERF_EVENT_IOC_DISABLE.  However doing that can also disable the
+collection of side-band information.  In order to prevent that,  a dummy
+software event has been introduced that permits tracking events (like mmaps) to
+continue to be recorded while intel_pt is disabled.  That is important to ensure
+there is complete side-band information to allow the decoding of subsequent
+snapshots.
+
+A test has been created for that.  To find the test:
+
+	perf test list
+	...
+	23: Test using a dummy software event to keep tracking
+
+To run the test:
+
+	perf test 23
+	23: Test using a dummy software event to keep tracking     : Ok
+
+
+perf record modes (nothing new here)
+------------------------------------
+
+perf record essentially operates in one of three modes:
+	per thread
+	per cpu
+	workload only
+
+"per thread" mode is selected by -t or by --per-thread (with -p or -u or just a
+workload).
+"per cpu" is selected by -C or -a.
+"workload only" mode is selected by not using the other options but providing a
+command to run (i.e. the workload).
+
+In per-thread mode an exact list of threads is traced.  There is no inheritance.
+Each thread has its own event buffer.
+
+In per-cpu mode all processes (or processes from the selected cgroup i.e. -G
+option, or processes selected with -p or -u) are traced.  Each cpu has its own
+buffer. Inheritance is allowed.
+
+In workload-only mode, the workload is traced but with per-cpu buffers.
+Inheritance is allowed.  Note that you can now trace a workload in per-thread
+mode by using the --per-thread option.
+
+
+Privileged vs non-privileged users
+----------------------------------
+
+Unless /proc/sys/kernel/perf_event_paranoid is set to -1, unprivileged users
+have memory limits imposed upon them.  That affects what buffer sizes they can
+have as outlined above.
+
+Unless /proc/sys/kernel/perf_event_paranoid is set to -1, unprivileged users are
+not permitted to use tracepoints which means there is insufficient side-band
+information to decode Intel PT in per-cpu mode, and potentially workload-only
+mode too if the workload creates new processes.
+
+Note also, that to use tracepoints, read-access to debugfs is required.  So if
+debugfs is not mounted or the user does not have read-access, it will again not
+be possible to decode Intel PT in per-cpu mode.
+
+
+sched_switch tracepoint
+-----------------------
+
+The sched_switch tracepoint is used to provide side-band data for Intel PT
+decoding.  sched_switch events are automatically added. e.g. the second event
+shown below
+
+	$ perf record -vv -e intel_pt//u uname
+	------------------------------------------------------------
+	perf_event_attr:
+	type                             6
+	size                             112
+	config                           0x400
+	{ sample_period, sample_freq }   1
+	sample_type                      IP|TID|TIME|CPU|IDENTIFIER
+	read_format                      ID
+	disabled                         1
+	inherit                          1
+	exclude_kernel                   1
+	exclude_hv                       1
+	enable_on_exec                   1
+	sample_id_all                    1
+	------------------------------------------------------------
+	sys_perf_event_open: pid 31104  cpu 0  group_fd -1  flags 0x8
+	sys_perf_event_open: pid 31104  cpu 1  group_fd -1  flags 0x8
+	sys_perf_event_open: pid 31104  cpu 2  group_fd -1  flags 0x8
+	sys_perf_event_open: pid 31104  cpu 3  group_fd -1  flags 0x8
+	------------------------------------------------------------
+	perf_event_attr:
+	type                             2
+	size                             112
+	config                           0x108
+	{ sample_period, sample_freq }   1
+	sample_type                      IP|TID|TIME|CPU|PERIOD|RAW|IDENTIFIER
+	read_format                      ID
+	inherit                          1
+	sample_id_all                    1
+	exclude_guest                    1
+	------------------------------------------------------------
+	sys_perf_event_open: pid -1  cpu 0  group_fd -1  flags 0x8
+	sys_perf_event_open: pid -1  cpu 1  group_fd -1  flags 0x8
+	sys_perf_event_open: pid -1  cpu 2  group_fd -1  flags 0x8
+	sys_perf_event_open: pid -1  cpu 3  group_fd -1  flags 0x8
+	------------------------------------------------------------
+	perf_event_attr:
+	type                             1
+	size                             112
+	config                           0x9
+	{ sample_period, sample_freq }   1
+	sample_type                      IP|TID|TIME|IDENTIFIER
+	read_format                      ID
+	disabled                         1
+	inherit                          1
+	exclude_kernel                   1
+	exclude_hv                       1
+	mmap                             1
+	comm                             1
+	enable_on_exec                   1
+	task                             1
+	sample_id_all                    1
+	mmap2                            1
+	comm_exec                        1
+	------------------------------------------------------------
+	sys_perf_event_open: pid 31104  cpu 0  group_fd -1  flags 0x8
+	sys_perf_event_open: pid 31104  cpu 1  group_fd -1  flags 0x8
+	sys_perf_event_open: pid 31104  cpu 2  group_fd -1  flags 0x8
+	sys_perf_event_open: pid 31104  cpu 3  group_fd -1  flags 0x8
+	mmap size 528384B
+	AUX area mmap length 4194304
+	perf event ring buffer mmapped per cpu
+	Synthesizing auxtrace information
+	Linux
+	[ perf record: Woken up 1 times to write data ]
+	[ perf record: Captured and wrote 0.042 MB perf.data ]
+
+Note, the sched_switch event is only added if the user is permitted to use it
+and only in per-cpu mode.
+
+Note also, the sched_switch event is only added if TSC packets are requested.
+That is because, in the absence of timing information, the sched_switch events
+cannot be matched against the Intel PT trace.
+
+
+perf script
+===========
+
+By default, perf script will decode trace data found in the perf.data file.
+This can be further controlled by new option --itrace.
+
+
+New AUX area option
+----------------------------
+
+Having no option is the same as
+
+	--itrace
+
+which, in turn, is the same as
+
+	--itrace=ibxe
+
+The letters are:
+
+	i	synthesize "instructions" events
+	b	synthesize "branches" events
+	x	synthesize "transactions" events
+	c	synthesize branches events (calls only)
+	r	synthesize branches events (returns only)
+	e	synthesize tracing error events
+	d	create a debug log
+	g	synthesize a call chain (use with i or x)
+
+"Instructions" events look like they were recorded by "perf record -e
+instructions".
+
+"Branches" events look like they were recorded by "perf record -e branches". "c"
+and "r" can be combined to get calls and returns.
+
+"Transactions" events correspond to the start or end of transactions. The
+'flags' field can be used in perf script to determine whether the event is a
+tranasaction start, commit or abort.
+
+Error events are new.  They show where the decoder lost the trace.  Error events
+are quite important.  Users must know if what they are seeing is a complete
+picture or not.
+
+The "d" option will cause the creation of a file "intel_pt.log" containing all
+decoded packets and instructions.  Note that this option slows down the decoder
+and that the resulting file may be very large.
+
+In addition, the period of the "instructions" event can be specified. e.g.
+
+	--itrace=i10us
+
+sets the period to 10us i.e. one  instruction sample is synthesized for each 10
+microseconds of trace.  Alternatives to "us" are "ms" (milliseconds),
+"ns" (nanoseconds), "t" (TSC ticks) or "i" (instructions).
+
+"ms", "us" and "ns" are converted to TSC ticks.
+
+The timing information included with Intel PT does not give the time of every
+instruction.  Consequently, for the purpose of sampling, the decoder estimates
+the time since the last timing packet based on 1 tick per instruction.  The time
+on the sample is *not* adjusted and reflects the last known value of TSC.
+
+For Intel PT, the default period is 100us.
+
+Also the call chain size (default 16, max. 1024) for instructions or
+transactions events can be specified. e.g.
+
+	--itrace=ig32
+	--itrace=xg32
+
+To disable trace decoding entirely, use the option --no-itrace.
+
+
+dump option
+-----------
+
+perf script has an option (-D) to "dump" the events i.e. display the binary
+data.
+
+When -D is used, Intel PT packets are displayed.  The packet decoder does not
+pay attention to PSB packets, but just decodes the bytes - so the packets seen
+by the actual decoder may not be identical in places where the data is corrupt.
+One example of that would be when the buffer-switching interrupt has been too
+slow, and the buffer has been filled completely.  In that case, the last packet
+in the buffer might be truncated and immediately followed by a PSB as the trace
+continues in the next buffer.
+
+To disable the display of Intel PT packets, combine the -D option with
+--no-itrace.
+
+
+perf report
+===========
+
+By default, perf report will decode trace data found in the perf.data file.
+This can be further controlled by new option --itrace exactly the same as
+perf script, with the exception that the default is --itrace=ge.
+
+
+perf inject
+===========
+
+perf inject also accepts the --itrace option in which case tracing data is
+removed and replaced with the synthesized events. e.g.
+
+	perf inject --itrace -i perf.data -o perf.data.new

index 1396088..a8be9f9 100644
@@ -1,5 +1,6 @@
 libperf-y += header.o
 libperf-y += tsc.o
+libperf-y += pmu.o
 libperf-y += kvm-stat.o
 
 libperf-$(CONFIG_DWARF) += dwarf-regs.o

@@ -7,4 +8,5 @@ libperf-$(CONFIG_DWARF) += dwarf-regs.o
 libperf-$(CONFIG_LIBUNWIND)          += unwind-libunwind.o
 libperf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o
 
+libperf-$(CONFIG_AUXTRACE) += auxtrace.o
 libperf-$(CONFIG_AUXTRACE) += intel-pt.o

new file mode 100644
index 0000000..7a79d36
@@ -0,0 +1,69 @@
+Intel Branch Trace Store
+========================
+
+perf record
+===========
+
+new event
+---------
+
+The Intel BTS kernel driver creates a new PMU for Intel BTS.  The perf record
+option is:
+
+	-e intel_bts//
+
+Currently Intel BTS is limited to per-thread tracing so the --per-thread option
+is also needed.
+
+
+snapshot option
+---------------
+
+The snapshot option is the same as Intel PT (refer Intel PT documentation).
+
+
+auxtrace mmap size option
+-----------------------
+
+The mmap size option is the same as Intel PT (refer Intel PT documentation).
+
+
+perf script
+===========
+
+By default, perf script will decode trace data found in the perf.data file.
+This can be further controlled by option --itrace.  The --itrace option is
+the same as Intel PT (refer Intel PT documentation) except that neither
+"instructions" events nor "transactions" events (and consequently call
+chains) are supported.
+
+To disable trace decoding entirely, use the option --no-itrace.
+
+
+dump option
+-----------
+
+perf script has an option (-D) to "dump" the events i.e. display the binary
+data.
+
+When -D is used, Intel BTS packets are displayed.
+
+To disable the display of Intel BTS packets, combine the -D option with
+--no-itrace.
+
+
+perf report
+===========
+
+By default, perf report will decode trace data found in the perf.data file.
+This can be further controlled by new option --itrace exactly the same as
+perf script.
+
+
+perf inject
+===========
+
+perf inject also accepts the --itrace option in which case tracing data is
+removed and replaced with the synthesized events. e.g.
+
+	perf inject --itrace -i perf.data -o perf.data.new

index a8be9f9..2c55e1b 100644
@@ -10,3 +10,4 @@ libperf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o
 
 libperf-$(CONFIG_AUXTRACE) += auxtrace.o
 libperf-$(CONFIG_AUXTRACE) += intel-pt.o
+libperf-$(CONFIG_AUXTRACE) += intel-bts.o

index 321f34b..2c261dc 100644
@@ -77,6 +77,7 @@ libperf-y += thread-stack.o
 libperf-$(CONFIG_AUXTRACE) += auxtrace.o
 libperf-$(CONFIG_AUXTRACE) += intel-pt-decoder/
 libperf-$(CONFIG_AUXTRACE) += intel-pt.o
+libperf-$(CONFIG_AUXTRACE) += intel-bts.o
 
 libperf-$(CONFIG_LIBELF) += symbol-elf.o
 libperf-$(CONFIG_LIBELF) += probe-event.o

new file mode 100644
index 0000000..5e8cfdf
@@ -0,0 +1,285 @@
+#!/usr/bin/python2
+# call-graph-from-postgresql.py: create call-graph from postgresql database
+# Copyright (c) 2014, Intel Corporation.
+#
+# This program is free software; you can redistribute it and/or modify it
+# under the terms and conditions of the GNU General Public License,
+# version 2, as published by the Free Software Foundation.
+#
+# This program is distributed in the hope it will be useful, but WITHOUT
+# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+# FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+# more details.
+
+import sys
+from PySide.QtCore import *
+from PySide.QtGui import *
+from PySide.QtSql import *
+from decimal import *
+
+class TreeItem():
+
+	def __init__(self, db, row, parent_item):
+		self.db = db
+		self.row = row
+		self.parent_item = parent_item
+		self.query_done = False;
+		self.child_count = 0
+		self.child_items = []
+		self.data = ["", "", "", "", "", "", ""]
+		self.comm_id = 0
+		self.thread_id = 0
+		self.call_path_id = 1
+		self.branch_count = 0
+		self.time = 0
+		if not parent_item:
+			self.setUpRoot()
+
+	def setUpRoot(self):
+		self.query_done = True
+		query = QSqlQuery(self.db)
+		ret = query.exec_('SELECT id, comm FROM comms')
+		if not ret:
+			raise Exception("Query failed: " + query.lastError().text())
+		while query.next():
+			if not query.value(0):
+				continue
+			child_item = TreeItem(self.db, self.child_count, self)
+			self.child_items.append(child_item)
+			self.child_count += 1
+			child_item.setUpLevel1(query.value(0), query.value(1))
+
+	def setUpLevel1(self, comm_id, comm):
+		self.query_done = True;
+		self.comm_id = comm_id
+		self.data[0] = comm
+		self.child_items = []
+		self.child_count = 0
+		query = QSqlQuery(self.db)
+		ret = query.exec_('SELECT thread_id, ( SELECT pid FROM threads WHERE id = thread_id ), ( SELECT tid FROM threads WHERE id = thread_id ) FROM comm_threads WHERE comm_id = ' + str(comm_id))
+		if not ret:
+			raise Exception("Query failed: " + query.lastError().text())
+		while query.next():
+			child_item = TreeItem(self.db, self.child_count, self)
+			self.child_items.append(child_item)
+			self.child_count += 1
+			child_item.setUpLevel2(comm_id, query.value(0), query.value(1), query.value(2))
+
+	def setUpLevel2(self, comm_id, thread_id, pid, tid):
+		self.comm_id = comm_id
+		self.thread_id = thread_id
+		self.data[0] = str(pid) + ":" + str(tid)
+
+	def getChildItem(self, row):
+		return self.child_items[row]
+
+	def getParentItem(self):
+		return self.parent_item
+
+	def getRow(self):
+		return self.row
+
+	def timePercent(self, b):
+		if not self.time:
+			return "0.0"
+		x = (b * Decimal(100)) / self.time
+		return str(x.quantize(Decimal('.1'), rounding=ROUND_HALF_UP))
+
+	def branchPercent(self, b):
+		if not self.branch_count:
+			return "0.0"
+		x = (b * Decimal(100)) / self.branch_count
+		return str(x.quantize(Decimal('.1'), rounding=ROUND_HALF_UP))
+
+	def addChild(self, call_path_id, name, dso, count, time, branch_count):
+		child_item = TreeItem(self.db, self.child_count, self)
+		child_item.comm_id = self.comm_id
+		child_item.thread_id = self.thread_id
+		child_item.call_path_id = call_path_id
+		child_item.branch_count = branch_count
+		child_item.time = time
+		child_item.data[0] = name
+		if dso == "[kernel.kallsyms]":
+			dso = "[kernel]"
+		child_item.data[1] = dso
+		child_item.data[2] = str(count)
+		child_item.data[3] = str(time)
+		child_item.data[4] = self.timePercent(time)
+		child_item.data[5] = str(branch_count)
+		child_item.data[6] = self.branchPercent(branch_count)
+		self.child_items.append(child_item)
+		self.child_count += 1
+
+	def selectCalls(self):
+		self.query_done = True;
+		query = QSqlQuery(self.db)
+		ret = query.exec_('SELECT id, call_path_id, branch_count, call_time, return_time, '
+				  '( SELECT name FROM symbols WHERE id = ( SELECT symbol_id FROM call_paths WHERE id = call_path_id ) ), '
+				  '( SELECT short_name FROM dsos WHERE id = ( SELECT dso_id FROM symbols WHERE id = ( SELECT symbol_id FROM call_paths WHERE id = call_path_id ) ) ), '
+				  '( SELECT ip FROM call_paths where id = call_path_id ) '
+				  'FROM calls WHERE parent_call_path_id = ' + str(self.call_path_id) + ' AND comm_id = ' + str(self.comm_id) + ' AND thread_id = ' + str(self.thread_id) +
+				  'ORDER BY call_path_id')
+		if not ret:
+			raise Exception("Query failed: " + query.lastError().text())
+		last_call_path_id = 0
+		name = ""
+		dso = ""
+		count = 0
+		branch_count = 0
+		total_branch_count = 0
+		time = 0
+		total_time = 0
+		while query.next():
+			if query.value(1) == last_call_path_id:
+				count += 1
+				branch_count += query.value(2)
+				time += query.value(4) - query.value(3)
+			else:
+				if count:
+					self.addChild(last_call_path_id, name, dso, count, time, branch_count)
+				last_call_path_id = query.value(1)
+				name = query.value(5)
+				dso = query.value(6)
+				count = 1
+				total_branch_count += branch_count
+				total_time += time
+				branch_count = query.value(2)
+				time = query.value(4) - query.value(3)
+		if count:
+			self.addChild(last_call_path_id, name, dso, count, time, branch_count)
+		total_branch_count += branch_count
+		total_time += time
+		# Top level does not have time or branch count, so fix that here
+		if total_branch_count > self.branch_count:
+			self.branch_count = total_branch_count
+			if self.branch_count:
+				for child_item in self.child_items:
+					child_item.data[6] = self.branchPercent(child_item.branch_count)
+		if total_time > self.time:
+			self.time = total_time
+			if self.time:
+				for child_item in self.child_items:
+					child_item.data[4] = self.timePercent(child_item.time)
+
+	def childCount(self):
+		if not self.query_done:
+			self.selectCalls()
+		return self.child_count
+
+	def columnCount(self):
+		return 7
+
+	def columnHeader(self, column):
+		headers = ["Call Path", "Object", "Count ", "Time (ns) ", "Time (%) ", "Branch Count ", "Branch Count (%) "]
+		return headers[column]
+
+	def getData(self, column):
+		return self.data[column]
+
+class TreeModel(QAbstractItemModel):
+
+	def __init__(self, db, parent=None):
+		super(TreeModel, self).__init__(parent)
+		self.db = db
+		self.root = TreeItem(db, 0, None)
+
+	def columnCount(self, parent):
+		return self.root.columnCount()
+
+	def rowCount(self, parent):
+		if parent.isValid():
+			parent_item = parent.internalPointer()
+		else:
+			parent_item = self.root
+		return parent_item.childCount()
+
+	def headerData(self, section, orientation, role):
+		if role == Qt.TextAlignmentRole:
+			if section > 1:
+				return Qt.AlignRight
+		if role != Qt.DisplayRole:
+			return None
+		if orientation != Qt.Horizontal:
+			return None
+		return self.root.columnHeader(section)
+
+	def parent(self, child):
+		child_item = child.internalPointer()
+		if child_item is self.root:
+			return QModelIndex()
+		parent_item = child_item.getParentItem()
+		return self.createIndex(parent_item.getRow(), 0, parent_item)
+
+	def index(self, row, column, parent):
+		if parent.isValid():
+			parent_item = parent.internalPointer()
+		else:
+			parent_item = self.root
+		child_item = parent_item.getChildItem(row)
+		return self.createIndex(row, column, child_item)
+
+	def data(self, index, role):
+		if role == Qt.TextAlignmentRole:
+			if index.column() > 1:
+				return Qt.AlignRight
+		if role != Qt.DisplayRole:
+			return None
+		index_item = index.internalPointer()
+		return index_item.getData(index.column())
+
+class MainWindow(QMainWindow):
+
+	def __init__(self, db, dbname, parent=None):
+		super(MainWindow, self).__init__(parent)
+
+		self.setObjectName("MainWindow")
+		self.setWindowTitle("Call Graph: " + dbname)
+		self.move(100, 100)
+		self.resize(800, 600)
+		style = self.style()
+		icon = style.standardIcon(QStyle.SP_MessageBoxInformation)
+		self.setWindowIcon(icon);
+
+		self.model = TreeModel(db)
+
+		self.view = QTreeView()
+		self.view.setModel(self.model)
+
+		self.setCentralWidget(self.view)
+
+if __name__ == '__main__':
+	if (len(sys.argv) < 2):
+		print >> sys.stderr, "Usage is: call-graph-from-postgresql.py <database name>"
+		raise Exception("Too few arguments")
+
+	dbname = sys.argv[1]
+
+	db = QSqlDatabase.addDatabase('QPSQL')
+
+	opts = dbname.split()
+	for opt in opts:
+		if '=' in opt:
+			opt = opt.split('=')
+			if opt[0] == 'hostname':
+				db.setHostName(opt[1])
+			elif opt[0] == 'port':
+				db.setPort(int(opt[1]))
+			elif opt[0] == 'username':
+				db.setUserName(opt[1])
+			elif opt[0] == 'password':
+				db.setPassword(opt[1])
+			elif opt[0] == 'dbname':
+				dbname = opt[1]
+		else:
+			dbname = opt
+
+	db.setDatabaseName(dbname)
+	if not db.open():
+		raise Exception("Failed to open database " + dbname + " error: " + db.lastError().text())
+
+	app = QApplication(sys.argv)
+	window = MainWindow(db, dbname)
+	window.show()
+	err = app.exec_()
+	db.close()
+	sys.exit(err)

new file mode 100644
index 0000000..2ff9466
@@ -0,0 +1,22 @@
+		i	synthesize instructions events
+		b	synthesize branches events
+		c	synthesize branches events (calls only)
+		r	synthesize branches events (returns only)
+		x	synthesize transactions events
+		e	synthesize error events
+		d	create a debug log
+		g	synthesize a call chain (use with i or x)
+
+	The default is all events i.e. the same as --itrace=ibxe
+
+	In addition, the period (default 100000) for instructions events
+	can be specified in units of:
+
+		i	instructions
+		t	ticks
+		ms	milliseconds
+		us	microseconds
+		ns	nanoseconds (default)
+
+	Also the call chain size (default 16, max. 1024) for instructions or
+	transactions events can be specified.

index b876ae3..0c721c3 100644
@@ -48,28 +48,7 @@ OPTIONS
 	Decode Instruction Tracing data, replacing it with synthesized events.
 	Options are:
 
-		i	synthesize instructions events
-		b	synthesize branches events
-		c	synthesize branches events (calls only)
-		r	synthesize branches events (returns only)
-		x	synthesize transactions events
-		e	synthesize error events
-		d	create a debug log
-		g	synthesize a call chain (use with i or x)
-
-	The default is all events i.e. the same as --itrace=ibxe
-
-	In addition, the period (default 100000) for instructions events
-	can be specified in units of:
-
-		i	instructions
-		t	ticks
-		ms	milliseconds
-		us	microseconds
-		ns	nanoseconds (default)
-
-	Also the call chain size (default 16, max. 1024) for instructions or
-	transactions events can be specified.
+include::itrace.txt[]
 
 SEE ALSO
 --------

index c33b69f..6c44928 100644
@@ -328,28 +328,7 @@ OPTIONS
 --itrace::
 	Options for decoding instruction tracing data. The options are:
 
-		i	synthesize instructions events
-		b	synthesize branches events
-		c	synthesize branches events (calls only)
-		r	synthesize branches events (returns only)
-		x	synthesize transactions events
-		e	synthesize error events
-		d	create a debug log
-		g	synthesize a call chain (use with i or x)
-
-	The default is all events i.e. the same as --itrace=ibxe
-
-	In addition, the period (default 100000) for instructions events
-	can be specified in units of:
-
-		i	instructions
-		t	ticks
-		ms	milliseconds
-		us	microseconds
-		ns	nanoseconds (default)
-
-	Also the call chain size (default 16, max. 1024) for instructions or
-	transactions events can be specified.
+include::itrace.txt[]
 
 	To disable decoding entirely, use --no-itrace.
 

index c82df57..ac9e99a 100644
@@ -231,28 +231,7 @@ OPTIONS
 --itrace::
 	Options for decoding instruction tracing data. The options are:
 
-		i	synthesize instructions events
-		b	synthesize branches events
-		c	synthesize branches events (calls only)
-		r	synthesize branches events (returns only)
-		x	synthesize transactions events
-		e	synthesize error events
-		d	create a debug log
-		g	synthesize a call chain (use with i or x)
-
-	The default is all events i.e. the same as --itrace=ibxe
-
-	In addition, the period (default 100000) for instructions events
-	can be specified in units of:
-
-		i	instructions
-		t	ticks
-		ms	milliseconds
-		us	microseconds
-		ns	nanoseconds (default)
-
-	Also the call chain size (default 16, max. 1024) for instructions or
-	transactions events can be specified.
+include::itrace.txt[]
 
 	To disable decoding entirely, use --no-itrace.