Merge tag 'perf-core-for-mingo-5.5-20191021' 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:

perf trace:

- Add syscall failure stats to -s/--summary and -S/--with-summary, works in
  combination with specifying just a set of syscalls, see below first with
  -s/--summary, then with -S/--with-summary just for the syscalls we saw failing
  with -s:

    # perf trace -s sleep 1

     Summary of events:

     sleep (16218), 80 events, 93.0%

       syscall     calls  errors  total      min      avg      max   stddev
                                  (msec)   (msec)   (msec)   (msec)    (%)
       ----------- -----  ------ -------- -------- -------- -------- ------
       nanosleep       1      0  1000.091 1000.091 1000.091 1000.091  0.00%
       mmap            8      0     0.045    0.005    0.006    0.008  7.09%
       mprotect        4      0     0.028    0.005    0.007    0.009 11.38%
       openat          3      0     0.021    0.005    0.007    0.009 14.07%
       munmap          1      0     0.017    0.017    0.017    0.017  0.00%
       brk             4      0     0.010    0.001    0.002    0.004 23.15%
       read            4      0     0.009    0.002    0.002    0.003  8.13%
       close           5      0     0.008    0.001    0.002    0.002 10.83%
       fstat           3      0     0.006    0.002    0.002    0.002  6.97%
       access          1      1     0.006    0.006    0.006    0.006  0.00%
       lseek           3      0     0.005    0.001    0.002    0.002  7.37%
       arch_prctl      2      1     0.004    0.001    0.002    0.002 17.64%
       execve          1      0     0.000    0.000    0.000    0.000  0.00%

    # perf trace -e access,arch_prctl -S sleep 1
         0.000 ( 0.006 ms): sleep/19503 arch_prctl(option: 0x3001, arg2: 0x7fff165996b0) = -1 EINVAL (Invalid argument)
         0.024 ( 0.006 ms): sleep/19503 access(filename: 0x2177e510, mode: R)            = -1 ENOENT (No such file or directory)
         0.136 ( 0.002 ms): sleep/19503 arch_prctl(option: SET_FS, arg2: 0x7f9421737580) = 0

     Summary of events:

     sleep (19503), 6 events, 50.0%

       syscall    calls  errors total    min    avg    max  stddev
                                (msec) (msec) (msec) (msec)    (%)
       ---------- -----  ------ ------ ------ ------ ------ ------
       arch_prctl   2       1    0.008  0.002  0.004  0.006 57.22%
       access       1       1    0.006  0.006  0.006  0.006  0.00%

    #

  - Introduce --errno-summary, to drill down a bit more in the errno stats:

    # perf trace --errno-summary -e access,arch_prctl -S sleep 1
         0.000 ( 0.006 ms): sleep/5587 arch_prctl(option: 0x3001, arg2: 0x7ffd6ba6aa00) = -1 EINVAL (Invalid argument)
         0.028 ( 0.007 ms): sleep/5587 access(filename: 0xb83d9510, mode: R)            = -1 ENOENT (No such file or directory)
         0.172 ( 0.003 ms): sleep/5587 arch_prctl(option: SET_FS, arg2: 0x7f45b8392580) = 0

     Summary of events:

     sleep (5587), 6 events, 50.0%

       syscall    calls  errors total    min    avg    max  stddev
                                (msec) (msec) (msec) (msec)   (%)
       ---------- -----  ------ ------ ------ ------ ------ ------
       arch_prctl     2     1    0.009  0.003  0.005  0.006 38.90%
			   EINVAL: 1
       access         1     1    0.007  0.007  0.007  0.007  0.00%
                           ENOENT: 1
    #

  - Filter own pid to avoid a feedback look in 'perf trace record -a'

  - Add the glue for the auto generated x86 IRQ vector array.

  - Show error message when not finding a field used in a filter expression

    # perf trace --max-events=4 -e syscalls:sys_enter_write --filter="cnt>32767"
    Failed to set filter "(cnt>32767) && (common_pid != 19938 && common_pid != 8922)" on event syscalls:sys_enter_write with 22 (Invalid argument)
    #
    # perf trace --max-events=4 -e syscalls:sys_enter_write --filter="count>32767"
         0.000 python3.5/17535 syscalls:sys_enter_write(fd: 3, buf: 0x564b0dc53600, count: 172086)
        12.641 python3.5.post/17535 syscalls:sys_enter_write(fd: 3, buf: 0x564b0db63660, count: 75994)
        27.738 python3.5.post/17535 syscalls:sys_enter_write(fd: 3, buf: 0x564b0db4b1e0, count: 41635)
       136.070 python3.5.post/17535 syscalls:sys_enter_write(fd: 3, buf: 0x564b0dbab510, count: 62232)
    #

  - Add a generator for x86's IRQ vectors -> strings

  - Introduce stroul() (string -> number) methods for the strarray and
    strarrays classes, also strtoul_flags, allowing to go from both strings
    and or-ed strings to numbers, allowing things like:

    # perf trace -e syscalls:sys_enter_mmap --filter="flags==DENYWRITE|PRIVATE|FIXED" sleep 1
         0.000 sleep/22588 syscalls:sys_enter_mmap(addr: 0x7f42d2aa5000, len: 1363968, prot: READ|EXEC, flags: PRIVATE|FIXED|DENYWRITE, fd: 3, off: 0x22000)
         0.011 sleep/22588 syscalls:sys_enter_mmap(addr: 0x7f42d2bf2000, len: 311296, prot: READ, flags: PRIVATE|FIXED|DENYWRITE, fd: 3, off: 0x16f000)
         0.015 sleep/22588 syscalls:sys_enter_mmap(addr: 0x7f42d2c3f000, len: 24576, prot: READ|WRITE, flags: PRIVATE|FIXED|DENYWRITE, fd: 3, off: 0x1bb000)
    #

  Allowing to narrow down from the complete set of mmap calls for that workload:

    # perf trace -e syscalls:sys_enter_mmap sleep 1
         0.000 sleep/22695 syscalls:sys_enter_mmap(len: 134773, prot: READ, flags: PRIVATE, fd: 3)
         0.041 sleep/22695 syscalls:sys_enter_mmap(len: 8192, prot: READ|WRITE, flags: PRIVATE|ANONYMOUS)
         0.053 sleep/22695 syscalls:sys_enter_mmap(len: 1857472, prot: READ, flags: PRIVATE|DENYWRITE, fd: 3)
         0.069 sleep/22695 syscalls:sys_enter_mmap(addr: 0x7fd23ffb6000, len: 1363968, prot: READ|EXEC, flags: PRIVATE|FIXED|DENYWRITE, fd: 3, off: 0x22000)
         0.077 sleep/22695 syscalls:sys_enter_mmap(addr: 0x7fd240103000, len: 311296, prot: READ, flags: PRIVATE|FIXED|DENYWRITE, fd: 3, off: 0x16f000)
         0.083 sleep/22695 syscalls:sys_enter_mmap(addr: 0x7fd240150000, len: 24576, prot: READ|WRITE, flags: PRIVATE|FIXED|DENYWRITE, fd: 3, off: 0x1bb000)
         0.095 sleep/22695 syscalls:sys_enter_mmap(addr: 0x7fd240156000, len: 14272, prot: READ|WRITE, flags: PRIVATE|FIXED|ANONYMOUS)
         0.339 sleep/22695 syscalls:sys_enter_mmap(len: 217750512, prot: READ, flags: PRIVATE, fd: 3)
    #

  Works with all targets, so, for system wide, looking at who calls mmap with flags set to just "PRIVATE":

    # perf trace --max-events=5 -e syscalls:sys_enter_mmap --filter="flags==PRIVATE"
         0.000 pool/2242 syscalls:sys_enter_mmap(len: 756, prot: READ, flags: PRIVATE, fd: 14)
         0.050 pool/2242 syscalls:sys_enter_mmap(len: 756, prot: READ, flags: PRIVATE, fd: 14)
         0.062 pool/2242 syscalls:sys_enter_mmap(len: 756, prot: READ, flags: PRIVATE, fd: 14)
         0.145 goa-identity-s/2240 syscalls:sys_enter_mmap(len: 756, prot: READ, flags: PRIVATE, fd: 18)
         0.183 goa-identity-s/2240 syscalls:sys_enter_mmap(len: 756, prot: READ, flags: PRIVATE, fd: 18)
    #

  # perf trace --max-events=2 -e syscalls:sys_enter_lseek --filter="whence==SET && offset != 0"
         0.000 Cache2 I/O/12047 syscalls:sys_enter_lseek(fd: 277, offset: 43, whence: SET)
      1142.070 mozStorage #5/12302 syscalls:sys_enter_lseek(fd: 44</home/acme/.mozilla/firefox/ina67tev.default/cookies.sqlite-wal>, offset: 393536, whence: SET)
  #

perf annotate:

  - Fix objdump --no-show-raw-insn flag to work with goth gcc and clang.

  - Streamline objdump execution, preserving the right error codes for better
    reporting to user.

perf report:

  - Add warning when libunwind not compiled in.

perf stat:

  Jin Yao:

  - Support --all-kernel/--all-user, to match options available in 'perf record',
    asking that all the events specified work just with kernel or user events.

perf list:

  Jin Yao:

  - Hide deprecated events by default, allow showing them with --deprecated.

libbperf:

  Jiri Olsa:

  - Allow to build with -ltcmalloc.

  - Finish mmap interface, getting more stuff from tools/perf while adding
    abstractions to avoid pulling too much stuff, to get libperf to grow as
    tools needs things like auxtrace, etc.

perf scripting engines:

  Steven Rostedt (VMware):

  - Iterate on tep event arrays directly, fixing script generation with
    '-g python' when having multiple tracepoints in a perf.data file.

core:

  - Allow to build with -ltcmalloc.

perf test:

  Leo Yan:

  - Report failure for mmap events.

  - Avoid infinite loop for task exit case.

  - Remove needless headers for bp_account test.

  - Add dedicated checking helper is_supported().

  - Disable bp_signal testing for arm64.

Vendor events:

arm64:

  John Garry:

  - Fix Hisi hip08 DDRC PMU eventname.

  - Add some missing events for Hisi hip08 DDRC, L3C and HHA PMUs.

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

60 files changed, 1301 insertions, 287 deletions

diff --git a/tools/arch/x86/include/asm/irq_vectors.h b/tools/arch/x86/include/asm/irq_vectors.h
new file mode 100644
index 000000000000..889f8b1b5b7f
--- /dev/null
+++ b/tools/arch/x86/include/asm/irq_vectors.h
@@ -0,0 +1,146 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_IRQ_VECTORS_H
+#define _ASM_X86_IRQ_VECTORS_H
+
+#include <linux/threads.h>
+/*
+ * Linux IRQ vector layout.
+ *
+ * There are 256 IDT entries (per CPU - each entry is 8 bytes) which can
+ * be defined by Linux. They are used as a jump table by the CPU when a
+ * given vector is triggered - by a CPU-external, CPU-internal or
+ * software-triggered event.
+ *
+ * Linux sets the kernel code address each entry jumps to early during
+ * bootup, and never changes them. This is the general layout of the
+ * IDT entries:
+ *
+ *  Vectors   0 ...  31 : system traps and exceptions - hardcoded events
+ *  Vectors  32 ... 127 : device interrupts
+ *  Vector  128         : legacy int80 syscall interface
+ *  Vectors 129 ... LOCAL_TIMER_VECTOR-1
+ *  Vectors LOCAL_TIMER_VECTOR ... 255 : special interrupts
+ *
+ * 64-bit x86 has per CPU IDT tables, 32-bit has one shared IDT table.
+ *
+ * This file enumerates the exact layout of them:
+ */
+
+#define NMI_VECTOR			0x02
+#define MCE_VECTOR			0x12
+
+/*
+ * IDT vectors usable for external interrupt sources start at 0x20.
+ * (0x80 is the syscall vector, 0x30-0x3f are for ISA)
+ */
+#define FIRST_EXTERNAL_VECTOR		0x20
+
+/*
+ * Reserve the lowest usable vector (and hence lowest priority)  0x20 for
+ * triggering cleanup after irq migration. 0x21-0x2f will still be used
+ * for device interrupts.
+ */
+#define IRQ_MOVE_CLEANUP_VECTOR		FIRST_EXTERNAL_VECTOR
+
+#define IA32_SYSCALL_VECTOR		0x80
+
+/*
+ * Vectors 0x30-0x3f are used for ISA interrupts.
+ *   round up to the next 16-vector boundary
+ */
+#define ISA_IRQ_VECTOR(irq)		(((FIRST_EXTERNAL_VECTOR + 16) & ~15) + irq)
+
+/*
+ * Special IRQ vectors used by the SMP architecture, 0xf0-0xff
+ *
+ *  some of the following vectors are 'rare', they are merged
+ *  into a single vector (CALL_FUNCTION_VECTOR) to save vector space.
+ *  TLB, reschedule and local APIC vectors are performance-critical.
+ */
+
+#define SPURIOUS_APIC_VECTOR		0xff
+/*
+ * Sanity check
+ */
+#if ((SPURIOUS_APIC_VECTOR & 0x0F) != 0x0F)
+# error SPURIOUS_APIC_VECTOR definition error
+#endif
+
+#define ERROR_APIC_VECTOR		0xfe
+#define RESCHEDULE_VECTOR		0xfd
+#define CALL_FUNCTION_VECTOR		0xfc
+#define CALL_FUNCTION_SINGLE_VECTOR	0xfb
+#define THERMAL_APIC_VECTOR		0xfa
+#define THRESHOLD_APIC_VECTOR		0xf9
+#define REBOOT_VECTOR			0xf8
+
+/*
+ * Generic system vector for platform specific use
+ */
+#define X86_PLATFORM_IPI_VECTOR		0xf7
+
+/*
+ * IRQ work vector:
+ */
+#define IRQ_WORK_VECTOR			0xf6
+
+#define UV_BAU_MESSAGE			0xf5
+#define DEFERRED_ERROR_VECTOR		0xf4
+
+/* Vector on which hypervisor callbacks will be delivered */
+#define HYPERVISOR_CALLBACK_VECTOR	0xf3
+
+/* Vector for KVM to deliver posted interrupt IPI */
+#ifdef CONFIG_HAVE_KVM
+#define POSTED_INTR_VECTOR		0xf2
+#define POSTED_INTR_WAKEUP_VECTOR	0xf1
+#define POSTED_INTR_NESTED_VECTOR	0xf0
+#endif
+
+#define MANAGED_IRQ_SHUTDOWN_VECTOR	0xef
+
+#if IS_ENABLED(CONFIG_HYPERV)
+#define HYPERV_REENLIGHTENMENT_VECTOR	0xee
+#define HYPERV_STIMER0_VECTOR		0xed
+#endif
+
+#define LOCAL_TIMER_VECTOR		0xec
+
+#define NR_VECTORS			 256
+
+#ifdef CONFIG_X86_LOCAL_APIC
+#define FIRST_SYSTEM_VECTOR		LOCAL_TIMER_VECTOR
+#else
+#define FIRST_SYSTEM_VECTOR		NR_VECTORS
+#endif
+
+/*
+ * Size the maximum number of interrupts.
+ *
+ * If the irq_desc[] array has a sparse layout, we can size things
+ * generously - it scales up linearly with the maximum number of CPUs,
+ * and the maximum number of IO-APICs, whichever is higher.
+ *
+ * In other cases we size more conservatively, to not create too large
+ * static arrays.
+ */
+
+#define NR_IRQS_LEGACY			16
+
+#define CPU_VECTOR_LIMIT		(64 * NR_CPUS)
+#define IO_APIC_VECTOR_LIMIT		(32 * MAX_IO_APICS)
+
+#if defined(CONFIG_X86_IO_APIC) && defined(CONFIG_PCI_MSI)
+#define NR_IRQS						\
+	(CPU_VECTOR_LIMIT > IO_APIC_VECTOR_LIMIT ?	\
+		(NR_VECTORS + CPU_VECTOR_LIMIT)  :	\
+		(NR_VECTORS + IO_APIC_VECTOR_LIMIT))
+#elif defined(CONFIG_X86_IO_APIC)
+#define	NR_IRQS				(NR_VECTORS + IO_APIC_VECTOR_LIMIT)
+#elif defined(CONFIG_PCI_MSI)
+#define NR_IRQS				(NR_VECTORS + CPU_VECTOR_LIMIT)
+#else
+#define NR_IRQS				NR_IRQS_LEGACY
+#endif
+
+#endif /* _ASM_X86_IRQ_VECTORS_H */
diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt
index 18ed1b0fceb3..6345db33c533 100644
--- a/tools/perf/Documentation/perf-list.txt
+++ b/tools/perf/Documentation/perf-list.txt
@@ -36,6 +36,9 @@ Enable debugging output.
 Print how named events are resolved internally into perf events, and also
 any extra expressions computed by perf stat.
 
+--deprecated::
+Print deprecated events. By default the deprecated events are hidden.
+
 [[EVENT_MODIFIERS]]
 EVENT MODIFIERS
 ---------------
diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 930c51c01201..a9af4e440e80 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -323,6 +323,12 @@ The output is SMI cycles%, equals to (aperf - unhalted core cycles) / aperf
 
 Users who wants to get the actual value can apply --no-metric-only.
 
+--all-kernel::
+Configure all used events to run in kernel space.
+
+--all-user::
+Configure all used events to run in user space.
+
 EXAMPLES
 --------
 
diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documentation/perf-trace.txt
index 3bb89c2e9020..abc9b5d83312 100644
--- a/tools/perf/Documentation/perf-trace.txt
+++ b/tools/perf/Documentation/perf-trace.txt
@@ -146,6 +146,10 @@ the thread executes on the designated CPUs. Default is to monitor all CPUs.
 	Show all syscalls followed by a summary by thread with min, max, and
     average times (in msec) and relative stddev.
 
+--errno-summary::
+	To be used with -s or -S, to show stats for the errnos experienced by
+	syscalls, using only this option will trigger --summary.
+
 --tool_stats::
 	Show tool stats such as number of times fd->pathname was discovered thru
 	hooking the open syscall return + vfs_getname or via reading /proc/pid/fd, etc.
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index 063202c53b64..1783427da9b0 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -265,6 +265,11 @@ LDFLAGS += -Wl,-z,noexecstack
 
 EXTLIBS = -lpthread -lrt -lm -ldl
 
+ifneq ($(TCMALLOC),)
+  CFLAGS += -fno-builtin-malloc -fno-builtin-calloc -fno-builtin-realloc -fno-builtin-free
+  EXTLIBS += -ltcmalloc
+endif
+
 ifeq ($(FEATURES_DUMP),)
 include $(srctree)/tools/build/Makefile.feature
 else
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index a099a8a89447..1cd294468a1f 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -114,6 +114,8 @@ include ../scripts/utilities.mak
 # Define NO_LIBZSTD if you do not want support of Zstandard based runtime
 # trace compression in record mode.
 #
+# Define TCMALLOC to enable tcmalloc heap profiling.
+#
 
 # As per kernel Makefile, avoid funny character set dependencies
 unexport LC_ALL
@@ -544,6 +546,12 @@ x86_arch_prctl_code_tbl := $(srctree)/tools/perf/trace/beauty/x86_arch_prctl.sh
 $(x86_arch_prctl_code_array): $(x86_arch_asm_uapi_dir)/prctl.h $(x86_arch_prctl_code_tbl)
 	$(Q)$(SHELL) '$(x86_arch_prctl_code_tbl)' $(x86_arch_asm_uapi_dir) > $@
 
+x86_arch_irq_vectors_array := $(beauty_outdir)/x86_arch_irq_vectors_array.c
+x86_arch_irq_vectors_tbl := $(srctree)/tools/perf/trace/beauty/tracepoints/x86_irq_vectors.sh
+
+$(x86_arch_irq_vectors_array): $(x86_arch_asm_dir)/irq_vectors.h $(x86_arch_irq_vectors_tbl)
+	$(Q)$(SHELL) '$(x86_arch_irq_vectors_tbl)' $(x86_arch_asm_dir) > $@
+
 x86_arch_MSRs_array := $(beauty_outdir)/x86_arch_MSRs_array.c
 x86_arch_MSRs_tbl := $(srctree)/tools/perf/trace/beauty/tracepoints/x86_msr.sh
 
@@ -684,6 +692,7 @@ prepare: $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h archheaders $(drm_ioc
 	$(perf_ioctl_array) \
 	$(prctl_option_array) \
 	$(usbdevfs_ioctl_array) \
+	$(x86_arch_irq_vectors_array) \
 	$(x86_arch_MSRs_array) \
 	$(x86_arch_prctl_code_array) \
 	$(rename_flags_array) \
@@ -989,6 +998,7 @@ clean:: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clea
 		$(OUTPUT)$(perf_ioctl_array) \
 		$(OUTPUT)$(prctl_option_array) \
 		$(OUTPUT)$(usbdevfs_ioctl_array) \
+		$(OUTPUT)$(x86_arch_irq_vectors_array) \
 		$(OUTPUT)$(x86_arch_MSRs_array) \
 		$(OUTPUT)$(x86_arch_prctl_code_array) \
 		$(OUTPUT)$(rename_flags_array) \
diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c
index 08e62ae9d37e..965ef017496f 100644
--- a/tools/perf/builtin-list.c
+++ b/tools/perf/builtin-list.c
@@ -26,6 +26,7 @@ int cmd_list(int argc, const char **argv)
 	int i;
 	bool raw_dump = false;
 	bool long_desc_flag = false;
+	bool deprecated = false;
 	struct option list_options[] = {
 		OPT_BOOLEAN(0, "raw-dump", &raw_dump, "Dump raw events"),
 		OPT_BOOLEAN('d', "desc", &desc_flag,
@@ -34,6 +35,8 @@ int cmd_list(int argc, const char **argv)
 			    "Print longer event descriptions."),
 		OPT_BOOLEAN(0, "details", &details_flag,
 			    "Print information on the perf event names and expressions used internally by events."),
+		OPT_BOOLEAN(0, "deprecated", &deprecated,
+			    "Print deprecated events."),
 		OPT_INCR(0, "debug", &verbose,
 			     "Enable debugging output"),
 		OPT_END()
@@ -55,7 +58,7 @@ int cmd_list(int argc, const char **argv)
 
 	if (argc == 0) {
 		print_events(NULL, raw_dump, !desc_flag, long_desc_flag,
-				details_flag);
+				details_flag, deprecated);
 		return 0;
 	}
 
@@ -78,7 +81,8 @@ int cmd_list(int argc, const char **argv)
 			print_hwcache_events(NULL, raw_dump);
 		else if (strcmp(argv[i], "pmu") == 0)
 			print_pmu_events(NULL, raw_dump, !desc_flag,
-						long_desc_flag, details_flag);
+						long_desc_flag, details_flag,
+						deprecated);
 		else if (strcmp(argv[i], "sdt") == 0)
 			print_sdt_events(NULL, NULL, raw_dump);
 		else if (strcmp(argv[i], "metric") == 0 || strcmp(argv[i], "metrics") == 0)
@@ -91,7 +95,8 @@ int cmd_list(int argc, const char **argv)
 			if (sep == NULL) {
 				print_events(argv[i], raw_dump, !desc_flag,
 							long_desc_flag,
-							details_flag);
+							details_flag,
+							deprecated);
 				continue;
 			}
 			sep_idx = sep - argv[i];
@@ -117,7 +122,8 @@ int cmd_list(int argc, const char **argv)
 			print_hwcache_events(s, raw_dump);
 			print_pmu_events(s, raw_dump, !desc_flag,
 						long_desc_flag,
-						details_flag);
+						details_flag,
+						deprecated);
 			print_tracepoint_events(NULL, s, raw_dump);
 			print_sdt_events(NULL, s, raw_dump);
 			metricgroup__print(true, true, s, raw_dump, details_flag);
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index aae0e57c60fb..7accaf8ef689 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -399,6 +399,13 @@ static int report__setup_sample_type(struct report *rep)
 				PERF_SAMPLE_BRANCH_ANY))
 		rep->nonany_branch_mode = true;
 
+#ifndef HAVE_LIBUNWIND_SUPPORT
+	if (dwarf_callchain_users) {
+		ui__warning("Please install libunwind development packages "
+			    "during the perf build.\n");
+	}
+#endif
+
 	return 0;
 }
 
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 1c797a948ada..f86c5cce5b2c 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -3864,10 +3864,11 @@ int cmd_script(int argc, const char **argv)
 		goto out_delete;
 
 	if (script.time_str) {
-		err = perf_time__parse_for_ranges(script.time_str, session,
+		err = perf_time__parse_for_ranges_reltime(script.time_str, session,
 						  &script.ptime_range,
 						  &script.range_size,
-						  &script.range_num);
+						  &script.range_num,
+						  reltime);
 		if (err < 0)
 			goto out_delete;
 
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 468fc49420ce..c88d4e118409 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -803,6 +803,12 @@ static struct option stat_options[] = {
 	OPT_CALLBACK('M', "metrics", &evsel_list, "metric/metric group list",
 		     "monitor specified metrics or metric groups (separated by ,)",
 		     parse_metric_groups),
+	OPT_BOOLEAN_FLAG(0, "all-kernel", &stat_config.all_kernel,
+			 "Configure all used events to run in kernel space.",
+			 PARSE_OPT_EXCLUSIVE),
+	OPT_BOOLEAN_FLAG(0, "all-user", &stat_config.all_user,
+			 "Configure all used events to run in user space.",
+			 PARSE_OPT_EXCLUSIVE),
 	OPT_END()
 };
 
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 144d417ddb22..43c05eae1768 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -175,6 +175,7 @@ struct trace {
 	bool			multiple_threads;
 	bool			summary;
 	bool			summary_only;
+	bool			errno_summary;
 	bool			failure_only;
 	bool			show_comm;
 	bool			print_sample;
@@ -284,6 +285,87 @@ struct syscall_tp {
 	};
 };
 
+/*
+ * The evsel->priv as used by 'perf trace'
+ * sc:	for raw_syscalls:sys_{enter,exit} and syscalls:sys_{enter,exit}_SYSCALLNAME
+ * fmt: for all the other tracepoints
+ */
+struct evsel_trace {
+	struct syscall_tp	sc;
+	struct syscall_arg_fmt  *fmt;
+};
+
+static struct evsel_trace *evsel_trace__new(void)
+{
+	return zalloc(sizeof(struct evsel_trace));
+}
+
+static void evsel_trace__delete(struct evsel_trace *et)
+{
+	if (et == NULL)
+		return;
+
+	zfree(&et->fmt);
+	free(et);
+}
+
+/*
+ * Used with raw_syscalls:sys_{enter,exit} and with the
+ * syscalls:sys_{enter,exit}_SYSCALL tracepoints
+ */
+static inline struct syscall_tp *__evsel__syscall_tp(struct evsel *evsel)
+{
+	struct evsel_trace *et = evsel->priv;
+
+	return &et->sc;
+}
+
+static struct syscall_tp *evsel__syscall_tp(struct evsel *evsel)
+{
+	if (evsel->priv == NULL) {
+		evsel->priv = evsel_trace__new();
+		if (evsel->priv == NULL)
+			return NULL;
+	}
+
+	return __evsel__syscall_tp(evsel);
+}
+
+/*
+ * Used with all the other tracepoints.
+ */
+static inline struct syscall_arg_fmt *__evsel__syscall_arg_fmt(struct evsel *evsel)
+{
+	struct evsel_trace *et = evsel->priv;
+
+	return et->fmt;
+}
+
+static struct syscall_arg_fmt *evsel__syscall_arg_fmt(struct evsel *evsel)
+{
+	struct evsel_trace *et = evsel->priv;
+
+	if (evsel->priv == NULL) {
+		et = evsel->priv = evsel_trace__new();
+
+		if (et == NULL)
+			return NULL;
+	}
+
+	if (et->fmt == NULL) {
+		et->fmt = calloc(evsel->tp_format->format.nr_fields, sizeof(struct syscall_arg_fmt));
+		if (et->fmt == NULL)
+			goto out_delete;
+	}
+
+	return __evsel__syscall_arg_fmt(evsel);
+
+out_delete:
+	evsel_trace__delete(evsel->priv);
+	evsel->priv = NULL;
+	return NULL;
+}
+
 static int perf_evsel__init_tp_uint_field(struct evsel *evsel,
 					  struct tp_field *field,
 					  const char *name)
@@ -297,7 +379,7 @@ static int perf_evsel__init_tp_uint_field(struct evsel *evsel,
 }
 
 #define perf_evsel__init_sc_tp_uint_field(evsel, name) \
-	({ struct syscall_tp *sc = evsel->priv;\
+	({ struct syscall_tp *sc = __evsel__syscall_tp(evsel);\
 	   perf_evsel__init_tp_uint_field(evsel, &sc->name, #name); })
 
 static int perf_evsel__init_tp_ptr_field(struct evsel *evsel,
@@ -313,7 +395,7 @@ static int perf_evsel__init_tp_ptr_field(struct evsel *evsel,
 }
 
 #define perf_evsel__init_sc_tp_ptr_field(evsel, name) \
-	({ struct syscall_tp *sc = evsel->priv;\
+	({ struct syscall_tp *sc = __evsel__syscall_tp(evsel);\
 	   perf_evsel__init_tp_ptr_field(evsel, &sc->name, #name); })
 
 static void evsel__delete_priv(struct evsel *evsel)
@@ -324,73 +406,61 @@ static void evsel__delete_priv(struct evsel *evsel)
 
 static int perf_evsel__init_syscall_tp(struct evsel *evsel)
 {
-	struct syscall_tp *sc = evsel->priv = malloc(sizeof(struct syscall_tp));
+	struct syscall_tp *sc = evsel__syscall_tp(evsel);
 
-	if (evsel->priv != NULL) {
+	if (sc != NULL) {
 		if (perf_evsel__init_tp_uint_field(evsel, &sc->id, "__syscall_nr") &&
 		    perf_evsel__init_tp_uint_field(evsel, &sc->id, "nr"))
-			goto out_delete;
+			return -ENOENT;
 		return 0;
 	}
 
 	return -ENOMEM;
-out_delete:
-	zfree(&evsel->priv);
-	return -ENOENT;
 }
 
 static int perf_evsel__init_augmented_syscall_tp(struct evsel *evsel, struct evsel *tp)
 {
-	struct syscall_tp *sc = evsel->priv = malloc(sizeof(struct syscall_tp));
+	struct syscall_tp *sc = evsel__syscall_tp(evsel);
 
-	if (evsel->priv != NULL) {
+	if (sc != NULL) {
 		struct tep_format_field *syscall_id = perf_evsel__field(tp, "id");
 		if (syscall_id == NULL)
 			syscall_id = perf_evsel__field(tp, "__syscall_nr");
-		if (syscall_id == NULL)
-			goto out_delete;
-		if (__tp_field__init_uint(&sc->id, syscall_id->size, syscall_id->offset, evsel->needs_swap))
-			goto out_delete;
+		if (syscall_id == NULL ||
+		    __tp_field__init_uint(&sc->id, syscall_id->size, syscall_id->offset, evsel->needs_swap))
+			return -EINVAL;
 
 		return 0;
 	}
 
 	return -ENOMEM;
-out_delete:
-	zfree(&evsel->priv);
-	return -EINVAL;
 }
 
 static int perf_evsel__init_augmented_syscall_tp_args(struct evsel *evsel)
 {
-	struct syscall_tp *sc = evsel->priv;
+	struct syscall_tp *sc = __evsel__syscall_tp(evsel);
 
 	return __tp_field__init_ptr(&sc->args, sc->id.offset + sizeof(u64));
 }
 
 static int perf_evsel__init_augmented_syscall_tp_ret(struct evsel *evsel)
 {
-	struct syscall_tp *sc = evsel->priv;
+	struct syscall_tp *sc = __evsel__syscall_tp(evsel);
 
 	return __tp_field__init_uint(&sc->ret, sizeof(u64), sc->id.offset + sizeof(u64), evsel->needs_swap);
 }
 
 static int perf_evsel__init_raw_syscall_tp(struct evsel *evsel, void *handler)
 {
-	evsel->priv = malloc(sizeof(struct syscall_tp));
-	if (evsel->priv != NULL) {
+	if (evsel__syscall_tp(evsel) != NULL) {
 		if (perf_evsel__init_sc_tp_uint_field(evsel, id))
-			goto out_delete;
+			return -ENOENT;
 
 		evsel->handler = handler;
 		return 0;
 	}
 
 	return -ENOMEM;
-
-out_delete:
-	zfree(&evsel->priv);
-	return -ENOENT;
 }
 
 static struct evsel *perf_evsel__raw_syscall_newtp(const char *direction, void *handler)
@@ -415,13 +485,27 @@ out_delete:
 }
 
 #define perf_evsel__sc_tp_uint(evsel, name, sample) \
-	({ struct syscall_tp *fields = evsel->priv; \
+	({ struct syscall_tp *fields = __evsel__syscall_tp(evsel); \
 	   fields->name.integer(&fields->name, sample); })
 
 #define perf_evsel__sc_tp_ptr(evsel, name, sample) \
-	({ struct syscall_tp *fields = evsel->priv; \
+	({ struct syscall_tp *fields = __evsel__syscall_tp(evsel); \
 	   fields->name.pointer(&fields->name, sample); })
 
+size_t strarray__scnprintf_suffix(struct strarray *sa, char *bf, size_t size, const char *intfmt, bool show_suffix, int val)
+{
+	int idx = val - sa->offset;
+
+	if (idx < 0 || idx >= sa->nr_entries || sa->entries[idx] == NULL) {
+		size_t printed = scnprintf(bf, size, intfmt, val);
+		if (show_suffix)
+			printed += scnprintf(bf + printed, size - printed, " /* %s??? */", sa->prefix);
+		return printed;
+	}
+
+	return scnprintf(bf, size, "%s%s", sa->entries[idx], show_suffix ? sa->prefix : "");
+}
+
 size_t strarray__scnprintf(struct strarray *sa, char *bf, size_t size, const char *intfmt, bool show_prefix, int val)
 {
 	int idx = val - sa->offset;
@@ -451,6 +535,21 @@ static size_t syscall_arg__scnprintf_strarray(char *bf, size_t size,
 
 #define SCA_STRARRAY syscall_arg__scnprintf_strarray
 
+bool syscall_arg__strtoul_strarray(char *bf, size_t size, struct syscall_arg *arg, u64 *ret)
+{
+	return strarray__strtoul(arg->parm, bf, size, ret);
+}
+
+bool syscall_arg__strtoul_strarray_flags(char *bf, size_t size, struct syscall_arg *arg, u64 *ret)
+{
+	return strarray__strtoul_flags(arg->parm, bf, size, ret);
+}
+
+bool syscall_arg__strtoul_strarrays(char *bf, size_t size, struct syscall_arg *arg, u64 *ret)
+{
+	return strarrays__strtoul(arg->parm, bf, size, ret);
+}
+
 size_t syscall_arg__scnprintf_strarray_flags(char *bf, size_t size, struct syscall_arg *arg)
 {
 	return strarray__scnprintf_flags(arg->parm, bf, size, arg->show_string_prefix, arg->val);
@@ -492,6 +591,49 @@ bool strarray__strtoul(struct strarray *sa, char *bf, size_t size, u64 *ret)
 	return false;
 }
 
+bool strarray__strtoul_flags(struct strarray *sa, char *bf, size_t size, u64 *ret)
+{
+	u64 val = 0;
+	char *tok = bf, *sep, *end;
+
+	*ret = 0;
+
+	while (size != 0) {
+		int toklen = size;
+
+		sep = memchr(tok, '|', size);
+		if (sep != NULL) {
+			size -= sep - tok + 1;
+
+			end = sep - 1;
+			while (end > tok && isspace(*end))
+				--end;
+
+			toklen = end - tok + 1;
+		}
+
+		while (isspace(*tok))
+			++tok;
+
+		if (isalpha(*tok) || *tok == '_') {
+			if (!strarray__strtoul(sa, tok, toklen, &val))
+				return false;
+		} else {
+			bool is_hexa = tok[0] == 0 && (tok[1] = 'x' || tok[1] == 'X');
+
+			val = strtoul(tok, NULL, is_hexa ? 16 : 0);
+		}
+
+		*ret |= (1 << (val - 1));
+
+		if (sep == NULL)
+			break;
+		tok = sep + 1;
+	}
+
+	return true;
+}
+
 bool strarrays__strtoul(struct strarrays *sas, char *bf, size_t size, u64 *ret)
 {
 	int i;
@@ -562,7 +704,7 @@ static size_t syscall_arg__scnprintf_char_array(char *bf, size_t size, struct sy
 	// XXX Hey, maybe for sched:sched_switch prev/next comm fields we can
 	//     fill missing comms using thread__set_comm()...
 	//     here or in a special syscall_arg__scnprintf_pid_sched_tp...
-	return scnprintf(bf, size, "\"%-.*s\"", arg->fmt->nr_entries, arg->val);
+	return scnprintf(bf, size, "\"%-.*s\"", arg->fmt->nr_entries ?: arg->len, arg->val);
 }
 
 #define SCA_CHAR_ARRAY syscall_arg__scnprintf_char_array
@@ -740,10 +882,12 @@ static size_t syscall_arg__scnprintf_getrandom_flags(char *bf, size_t size,
 
 #define STRARRAY(name, array) \
 	  { .scnprintf	= SCA_STRARRAY, \
+	    .strtoul	= STUL_STRARRAY, \
 	    .parm	= &strarray__##array, }
 
 #define STRARRAY_FLAGS(name, array) \
 	  { .scnprintf	= SCA_STRARRAY_FLAGS, \
+	    .strtoul	= STUL_STRARRAY_FLAGS, \
 	    .parm	= &strarray__##array, }
 
 #include "trace/beauty/arch_errno_names.c"
@@ -799,7 +943,8 @@ static struct syscall_fmt syscall_fmts[] = {
 	{ .name	    = "fchownat",
 	  .arg = { [0] = { .scnprintf = SCA_FDAT, /* fd */ }, }, },
 	{ .name	    = "fcntl",
-	  .arg = { [1] = { .scnprintf = SCA_FCNTL_CMD, /* cmd */
+	  .arg = { [1] = { .scnprintf = SCA_FCNTL_CMD,  /* cmd */
+			   .strtoul   = STUL_STRARRAYS,
 			   .parm      = &strarrays__fcntl_cmds_arrays,
 			   .show_zero = true, },
 		   [2] = { .scnprintf =  SCA_FCNTL_ARG, /* arg */ }, }, },
@@ -870,7 +1015,9 @@ static struct syscall_fmt syscall_fmts[] = {
 	.alias = "old_mmap",
 #endif
 	  .arg = { [2] = { .scnprintf = SCA_MMAP_PROT,	/* prot */ },
-		   [3] = { .scnprintf = SCA_MMAP_FLAGS,	/* flags */ },
+		   [3] = { .scnprintf = SCA_MMAP_FLAGS,	/* flags */
+			   .strtoul   = STUL_STRARRAY_FLAGS,
+			   .parm      = &strarray__mmap_flags, },
 		   [5] = { .scnprintf = SCA_HEX,	/* offset */ }, }, },
 	{ .name	    = "mount",
 	  .arg = { [0] = { .scnprintf = SCA_FILENAME, /* dev_name */ },
@@ -1513,7 +1660,8 @@ static int syscall__alloc_arg_fmts(struct syscall *sc, int nr_args)
 }
 
 static struct syscall_arg_fmt syscall_arg_fmts__by_name[] = {
-	{ .name = "msr", .scnprintf = SCA_X86_MSR, .strtoul = STUL_X86_MSR, }
+	{ .name = "msr",	.scnprintf = SCA_X86_MSR,	  .strtoul = STUL_X86_MSR,	   },
+	{ .name = "vector",	.scnprintf = SCA_X86_IRQ_VECTORS, .strtoul = STUL_X86_IRQ_VECTORS, },
 };
 
 static int syscall_arg_fmt__cmp(const void *name, const void *fmtp)
@@ -1558,7 +1706,7 @@ syscall_arg_fmt__init_array(struct syscall_arg_fmt *arg, struct tep_format_field
 			arg->scnprintf = SCA_PID;
 		else if (strcmp(field->type, "umode_t") == 0)
 			arg->scnprintf = SCA_MODE_T;
-		else if ((field->flags & TEP_FIELD_IS_ARRAY) && strstarts(field->type, "char")) {
+		else if ((field->flags & TEP_FIELD_IS_ARRAY) && strstr(field->type, "char")) {
 			arg->scnprintf = SCA_CHAR_ARRAY;
 			arg->nr_entries = field->arraylen;
 		} else if ((strcmp(field->type, "int") == 0 ||
@@ -1653,11 +1801,10 @@ static int trace__read_syscall_info(struct trace *trace, int id)
 
 static int perf_evsel__init_tp_arg_scnprintf(struct evsel *evsel)
 {
-	int nr_args = evsel->tp_format->format.nr_fields;
+	struct syscall_arg_fmt *fmt = evsel__syscall_arg_fmt(evsel);
 
-	evsel->priv = calloc(nr_args, sizeof(struct syscall_arg_fmt));
-	if (evsel->priv != NULL) {
-		syscall_arg_fmt__init_array(evsel->priv, evsel->tp_format->format.fields);
+	if (fmt != NULL) {
+		syscall_arg_fmt__init_array(fmt, evsel->tp_format->format.fields);
 		return 0;
 	}
 
@@ -1958,11 +2105,18 @@ out_cant_read:
 	return NULL;
 }
 
-static void thread__update_stats(struct thread_trace *ttrace,
-				 int id, struct perf_sample *sample)
+struct syscall_stats {
+	struct stats stats;
+	u64	     nr_failures;
+	int	     max_errno;
+	u32	     *errnos;
+};
+
+static void thread__update_stats(struct thread *thread, struct thread_trace *ttrace,
+				 int id, struct perf_sample *sample, long err, bool errno_summary)
 {
 	struct int_node *inode;
-	struct stats *stats;
+	struct syscall_stats *stats;
 	u64 duration = 0;
 
 	inode = intlist__findnew(ttrace->syscall_stats, id);
@@ -1971,17 +2125,46 @@ static void thread__update_stats(struct thread_trace *ttrace,
 
 	stats = inode->priv;
 	if (stats == NULL) {
-		stats = malloc(sizeof(struct stats));
+		stats = malloc(sizeof(*stats));
 		if (stats == NULL)
 			return;
-		init_stats(stats);
+
+		stats->nr_failures = 0;
+		stats->max_errno   = 0;
+		stats->errnos	   = NULL;
+		init_stats(&stats->stats);
 		inode->priv = stats;
 	}
 
 	if (ttrace->entry_time && sample->time > ttrace->entry_time)
 		duration = sample->time - ttrace->entry_time;
 
-	update_stats(stats, duration);
+	update_stats(&stats->stats, duration);
+
+	if (err < 0) {
+		++stats->nr_failures;
+
+		if (!errno_summary)
+			return;
+
+		err = -err;
+		if (err > stats->max_errno) {
+			u32 *new_errnos = realloc(stats->errnos, err * sizeof(u32));
+
+			if (new_errnos) {
+				memset(new_errnos + stats->max_errno, 0, (err - stats->max_errno) * sizeof(u32));
+			} else {
+				pr_debug("Not enough memory for errno stats for thread \"%s\"(%d/%d), results will be incomplete\n",
+					 thread__comm_str(thread), thread->pid_, thread->tid);
+				return;
+			}
+
+			stats->errnos = new_errnos;
+			stats->max_errno = err;
+		}
+
+		++stats->errnos[err - 1];
+	}
 }
 
 static int trace__printf_interrupted_entry(struct trace *trace)
@@ -2226,11 +2409,11 @@ static int trace__sys_exit(struct trace *trace, struct evsel *evsel,
 
 	trace__fprintf_sample(trace, evsel, sample, thread);
 
-	if (trace->summary)
-		thread__update_stats(ttrace, id, sample);
-
 	ret = perf_evsel__sc_tp_uint(evsel, ret, sample);
 
+	if (trace->summary)
+		thread__update_stats(thread, ttrace, id, sample, ret, trace->errno_summary);
+
 	if (!trace->fd_path_disabled && sc->is_open && ret >= 0 && ttrace->filename.pending_open) {
 		trace__set_fd_pathname(thread, ret, ttrace->filename.name);
 		ttrace->filename.pending_open = false;
@@ -2466,7 +2649,7 @@ static size_t trace__fprintf_tp_fields(struct trace *trace, struct evsel *evsel,
 	char bf[2048];
 	size_t size = sizeof(bf);
 	struct tep_format_field *field = evsel->tp_format->format.fields;
-	struct syscall_arg_fmt *arg = evsel->priv;
+	struct syscall_arg_fmt *arg = __evsel__syscall_arg_fmt(evsel);
 	size_t printed = 0;
 	unsigned long val;
 	u8 bit = 1;
@@ -2486,10 +2669,19 @@ static size_t trace__fprintf_tp_fields(struct trace *trace, struct evsel *evsel,
 		if (syscall_arg.mask & bit)
 			continue;
 
+		syscall_arg.len = 0;
 		syscall_arg.fmt = arg;
-		if (field->flags & TEP_FIELD_IS_ARRAY)
-			val = (uintptr_t)(sample->raw_data + field->offset);
-		else
+		if (field->flags & TEP_FIELD_IS_ARRAY) {
+			int offset = field->offset;
+
+			if (field->flags & TEP_FIELD_IS_DYNAMIC) {
+				offset = format_field__intval(field, sample, evsel->needs_swap);
+				syscall_arg.len = offset >> 16;
+				offset &= 0xffff;
+			}
+
+			val = (uintptr_t)(sample->raw_data + offset);
+		} else
 			val = format_field__intval(field, sample, evsel->needs_swap);
 		/*
 		 * Some syscall args need some mask, most don't and
@@ -2592,12 +2784,6 @@ static int trace__event_handler(struct trace *trace, struct evsel *evsel,
 			} else {
 				trace__fprintf_tp_fields(trace, evsel, sample, thread, NULL, 0);
 			}
-			++trace->nr_events_printed;
-
-			if (evsel->max_events != ULONG_MAX && ++evsel->nr_events_printed == evsel->max_events) {
-				evsel__disable(evsel);
-				evsel__close(evsel);
-			}
 		}
 	}
 
@@ -2608,6 +2794,13 @@ newline:
 		trace__fprintf_callchain(trace, sample);
 	else if (callchain_ret < 0)
 		pr_err("Problem processing %s callchain, skipping...\n", perf_evsel__name(evsel));
+
+	++trace->nr_events_printed;
+
+	if (evsel->max_events != ULONG_MAX && ++evsel->nr_events_printed == evsel->max_events) {
+		evsel__disable(evsel);
+		evsel__close(evsel);
+	}
 out:
 	thread__put(thread);
 	return 0;
@@ -2759,21 +2952,23 @@ static int trace__record(struct trace *trace, int argc, const char **argv)
 		"-m", "1024",
 		"-c", "1",
 	};
-
+	pid_t pid = getpid();
+	char *filter = asprintf__tp_filter_pids(1, &pid);
 	const char * const sc_args[] = { "-e", };
 	unsigned int sc_args_nr = ARRAY_SIZE(sc_args);
 	const char * const majpf_args[] = { "-e", "major-faults" };
 	unsigned int majpf_args_nr = ARRAY_SIZE(majpf_args);
 	const char * const minpf_args[] = { "-e", "minor-faults" };
 	unsigned int minpf_args_nr = ARRAY_SIZE(minpf_args);
+	int err = -1;
 
-	/* +1 is for the event string below */
-	rec_argc = ARRAY_SIZE(record_args) + sc_args_nr + 1 +
+	/* +3 is for the event string below and the pid filter */
+	rec_argc = ARRAY_SIZE(record_args) + sc_args_nr + 3 +
 		majpf_args_nr + minpf_args_nr + argc;
 	rec_argv = calloc(rec_argc + 1, sizeof(char *));
 
-	if (rec_argv == NULL)
-		return -ENOMEM;
+	if (rec_argv == NULL || filter == NULL)
+		goto out_free;
 
 	j = 0;
 	for (i = 0; i < ARRAY_SIZE(record_args); i++)
@@ -2790,11 +2985,13 @@ static int trace__record(struct trace *trace, int argc, const char **argv)
 			rec_argv[j++] = "syscalls:sys_enter,syscalls:sys_exit";
 		else {
 			pr_err("Neither raw_syscalls nor syscalls events exist.\n");
-			free(rec_argv);
-			return -1;
+			goto out_free;
 		}
 	}
 
+	rec_argv[j++] = "--filter";
+	rec_argv[j++] = filter;
+
 	if (trace->trace_pgfaults & TRACE_PFMAJ)
 		for (i = 0; i < majpf_args_nr; i++)
 			rec_argv[j++] = majpf_args[i];
@@ -2806,7 +3003,11 @@ static int trace__record(struct trace *trace, int argc, const char **argv)
 	for (i = 0; i < (unsigned int)argc; i++)
 		rec_argv[j++] = argv[i];
 
-	return cmd_record(j, rec_argv);
+	err = cmd_record(j, rec_argv);
+out_free:
+	free(filter);
+	free(rec_argv);
+	return err;
 }
 
 static size_t trace__fprintf_thread_summary(struct trace *trace, FILE *fp);
@@ -3488,7 +3689,7 @@ static int ordered_events__deliver_event(struct ordered_events *oe,
 static struct syscall_arg_fmt *perf_evsel__syscall_arg_fmt(struct evsel *evsel, char *arg)
 {
 	struct tep_format_field *field;
-	struct syscall_arg_fmt *fmt = evsel->priv;
+	struct syscall_arg_fmt *fmt = __evsel__syscall_arg_fmt(evsel);
 
 	if (evsel->tp_format == NULL || fmt == NULL)
 		return NULL;
@@ -3526,7 +3727,7 @@ static int trace__expand_filter(struct trace *trace __maybe_unused, struct evsel
 			}
 
 		right_end = right + 1;
-		while (isalnum(*right_end) || *right_end == '_')
+		while (isalnum(*right_end) || *right_end == '_' || *right_end == '|')
 			++right_end;
 
 		if (isalpha(*right)) {
@@ -3542,8 +3743,8 @@ static int trace__expand_filter(struct trace *trace __maybe_unused, struct evsel
 
 			fmt = perf_evsel__syscall_arg_fmt(evsel, arg);
 			if (fmt == NULL) {
-				pr_debug("\"%s\" not found in \"%s\", can't set filter \"%s\"\n",
-					 arg, evsel->name, evsel->filter);
+				pr_err("\"%s\" not found in \"%s\", can't set filter \"%s\"\n",
+				       arg, evsel->name, evsel->filter);
 				return -1;
 			}
 
@@ -3552,7 +3753,11 @@ static int trace__expand_filter(struct trace *trace __maybe_unused, struct evsel
 
 			if (fmt->strtoul) {
 				u64 val;
-				if (fmt->strtoul(right, right_size, NULL, &val)) {
+				struct syscall_arg syscall_arg = {
+					.parm = fmt->parm,
+				};
+
+				if (fmt->strtoul(right, right_size, &syscall_arg, &val)) {
 					char *n, expansion[19];
 					int expansion_lenght = scnprintf(expansion, sizeof(expansion), "%#" PRIx64, val);
 					int expansion_offset = right - new_filter;
@@ -4016,17 +4221,17 @@ static size_t trace__fprintf_threads_header(FILE *fp)
 }
 
 DEFINE_RESORT_RB(syscall_stats, a->msecs > b->msecs,
-	struct stats 	*stats;
-	double		msecs;
-	int		syscall;
+	struct syscall_stats *stats;
+	double		     msecs;
+	int		     syscall;
 )
 {
 	struct int_node *source = rb_entry(nd, struct int_node, rb_node);
-	struct stats *stats = source->priv;
+	struct syscall_stats *stats = source->priv;
 
 	entry->syscall = source->i;
 	entry->stats   = stats;
-	entry->msecs   = stats ? (u64)stats->n * (avg_stats(stats) / NSEC_PER_MSEC) : 0;
+	entry->msecs   = stats ? (u64)stats->stats.n * (avg_stats(&stats->stats) / NSEC_PER_MSEC) : 0;
 }
 
 static size_t thread__dump_stats(struct thread_trace *ttrace,
@@ -4042,27 +4247,37 @@ static size_t thread__dump_stats(struct thread_trace *ttrace,
 
 	printed += fprintf(fp, "\n");
 
-	printed += fprintf(fp, "   syscall            calls    total       min       avg       max      stddev\n");
-	printed += fprintf(fp, "                               (msec)    (msec)    (msec)    (msec)        (%%)\n");
-	printed += fprintf(fp, "   --------------- -------- --------- --------- --------- ---------     ------\n");
+	printed += fprintf(fp, "   syscall            calls  errors  total       min       avg       max       stddev\n");
+	printed += fprintf(fp, "                                     (msec)    (msec)    (msec)    (msec)        (%%)\n");
+	printed += fprintf(fp, "   --------------- --------  ------ -------- --------- --------- ---------     ------\n");
 
 	resort_rb__for_each_entry(nd, syscall_stats) {
-		struct stats *stats = syscall_stats_entry->stats;
+		struct syscall_stats *stats = syscall_stats_entry->stats;
 		if (stats) {
-			double min = (double)(stats->min) / NSEC_PER_MSEC;
-			double max = (double)(stats->max) / NSEC_PER_MSEC;
-			double avg = avg_stats(stats);
+			double min = (double)(stats->stats.min) / NSEC_PER_MSEC;
+			double max = (double)(stats->stats.max) / NSEC_PER_MSEC;
+			double avg = avg_stats(&stats->stats);
 			double pct;
-			u64 n = (u64) stats->n;
+			u64 n = (u64)stats->stats.n;
 
-			pct = avg ? 100.0 * stddev_stats(stats)/avg : 0.0;
+			pct = avg ? 100.0 * stddev_stats(&stats->stats) / avg : 0.0;
 			avg /= NSEC_PER_MSEC;
 
 			sc = &trace->syscalls.table[syscall_stats_entry->syscall];
 			printed += fprintf(fp, "   %-15s", sc->name);
-			printed += fprintf(fp, " %8" PRIu64 " %9.3f %9.3f %9.3f",
-					   n, syscall_stats_entry->msecs, min, avg);
+			printed += fprintf(fp, " %8" PRIu64 " %6" PRIu64 " %9.3f %9.3f %9.3f",
+					   n, stats->nr_failures, syscall_stats_entry->msecs, min, avg);
 			printed += fprintf(fp, " %9.3f %9.2f%%\n", max, pct);
+
+			if (trace->errno_summary && stats->nr_failures) {
+				const char *arch_name = perf_env__arch(trace->host->env);
+				int e;
+
+				for (e = 0; e < stats->max_errno; ++e) {
+					if (stats->errnos[e] != 0)
+						fprintf(fp, "\t\t\t\t%s: %d\n", arch_syscalls__strerrno(arch_name, e + 1), stats->errnos[e]);
+				}
+			}
 		}
 	}
 
@@ -4219,6 +4434,25 @@ static void evlist__set_default_evsel_handler(struct evlist *evlist, void *handl
 	}
 }
 
+static void evsel__set_syscall_arg_fmt(struct evsel *evsel, const char *name)
+{
+	struct syscall_arg_fmt *fmt = evsel__syscall_arg_fmt(evsel);
+
+	if (fmt) {
+		struct syscall_fmt *scfmt = syscall_fmt__find(name);
+
+		if (scfmt) {
+			int skip = 0;
+
+			if (strcmp(evsel->tp_format->format.fields->name, "__syscall_nr") == 0 ||
+			    strcmp(evsel->tp_format->format.fields->name, "nr") == 0)
+				++skip;
+
+			memcpy(fmt + skip, scfmt->arg, (evsel->tp_format->format.nr_fields - skip) * sizeof(*fmt));
+		}
+	}
+}
+
 static int evlist__set_syscall_tp_fields(struct evlist *evlist)
 {
 	struct evsel *evsel;
@@ -4236,15 +4470,19 @@ static int evlist__set_syscall_tp_fields(struct evlist *evlist)
 			return -1;
 
 		if (!strncmp(evsel->tp_format->name, "sys_enter_", 10)) {
-			struct syscall_tp *sc = evsel->priv;
+			struct syscall_tp *sc = __evsel__syscall_tp(evsel);
 
 			if (__tp_field__init_ptr(&sc->args, sc->id.offset + sizeof(u64)))
 				return -1;
+
+			evsel__set_syscall_arg_fmt(evsel, evsel->tp_format->name + sizeof("sys_enter_") - 1);
 		} else if (!strncmp(evsel->tp_format->name, "sys_exit_", 9)) {
-			struct syscall_tp *sc = evsel->priv;
+			struct syscall_tp *sc = __evsel__syscall_tp(evsel);
 
 			if (__tp_field__init_uint(&sc->ret, sizeof(u64), sc->id.offset + sizeof(u64), evsel->needs_swap))
 				return -1;
+
+			evsel__set_syscall_arg_fmt(evsel, evsel->tp_format->name + sizeof("sys_exit_") - 1);
 		}
 	}
 
@@ -4501,6 +4739,8 @@ int cmd_trace(int argc, const char **argv)
 		    "Show only syscall summary with statistics"),
 	OPT_BOOLEAN('S', "with-summary", &trace.summary,
 		    "Show all syscalls and summary with statistics"),
+	OPT_BOOLEAN(0, "errno-summary", &trace.errno_summary,
+		    "Show errno stats per syscall, use with -s or -S"),
 	OPT_CALLBACK_DEFAULT('F', "pf", &trace.trace_pgfaults, "all|maj|min",
 		     "Trace pagefaults", parse_pagefaults, "maj"),
 	OPT_BOOLEAN(0, "syscalls", &trace.trace_syscalls, "Trace syscalls"),
@@ -4775,7 +5015,7 @@ int cmd_trace(int argc, const char **argv)
 init_augmented_syscall_tp:
 				if (perf_evsel__init_augmented_syscall_tp(evsel, evsel))
 					goto out;
-				sc = evsel->priv;
+				sc = __evsel__syscall_tp(evsel);
 				/*
 				 * For now with BPF raw_augmented we hook into
 				 * raw_syscalls:sys_enter and there we get all
@@ -4806,6 +5046,10 @@ init_augmented_syscall_tp:
 	if ((argc >= 1) && (strcmp(argv[0], "record") == 0))
 		return trace__record(&trace, argc-1, &argv[1]);
 
+	/* Using just --errno-summary will trigger --summary */
+	if (trace.errno_summary && !trace.summary && !trace.summary_only)
+		trace.summary_only = true;
+
 	/* summary_only implies summary option, but don't overwrite summary if set */
 	if (trace.summary_only)
 		trace.summary = trace.summary_only;
diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh
index 93c46d38024e..48290a0c917c 100755
--- a/tools/perf/check-headers.sh
+++ b/tools/perf/check-headers.sh
@@ -28,6 +28,7 @@ arch/x86/include/asm/disabled-features.h
 arch/x86/include/asm/required-features.h
 arch/x86/include/asm/cpufeatures.h
 arch/x86/include/asm/inat_types.h
+arch/x86/include/asm/irq_vectors.h
 arch/x86/include/asm/msr-index.h
 arch/x86/include/uapi/asm/prctl.h
 arch/x86/lib/x86-opcode-map.txt
diff --git a/tools/perf/lib/Makefile b/tools/perf/lib/Makefile
index 0889c9c3ec19..0f233638ef1f 100644
--- a/tools/perf/lib/Makefile
+++ b/tools/perf/lib/Makefile
@@ -107,6 +107,7 @@ else
 endif
 
 LIBAPI = $(API_PATH)libapi.a
+export LIBAPI
 
 $(LIBAPI): FORCE
 	$(Q)$(MAKE) -C $(LIB_DIR) O=$(OUTPUT) $(OUTPUT)libapi.a
diff --git a/tools/perf/lib/evlist.c b/tools/perf/lib/evlist.c
index 65045614c938..205ddbb80bc1 100644
--- a/tools/perf/lib/evlist.c
+++ b/tools/perf/lib/evlist.c
@@ -338,15 +338,13 @@ static struct perf_mmap* perf_evlist__alloc_mmap(struct perf_evlist *evlist, boo
 	int i;
 	struct perf_mmap *map;
 
-	evlist->nr_mmaps = perf_cpu_map__nr(evlist->cpus);
-	if (perf_cpu_map__empty(evlist->cpus))
-		evlist->nr_mmaps = perf_thread_map__nr(evlist->threads);
-
 	map = zalloc(evlist->nr_mmaps * sizeof(struct perf_mmap));
 	if (!map)
 		return NULL;
 
 	for (i = 0; i < evlist->nr_mmaps; i++) {
+		struct perf_mmap *prev = i ? &map[i - 1] : NULL;
+
 		/*
 		 * When the perf_mmap() call is made we grab one refcount, plus
 		 * one extra to let perf_mmap__consume() get the last
@@ -356,7 +354,7 @@ static struct perf_mmap* perf_evlist__alloc_mmap(struct perf_evlist *evlist, boo
 		 * Each PERF_EVENT_IOC_SET_OUTPUT points to this mmap and
 		 * thus does perf_mmap__get() on it.
 		 */
-		perf_mmap__init(&map[i], overwrite, NULL);
+		perf_mmap__init(&map[i], prev, overwrite, NULL);
 	}
 
 	return map;
@@ -382,18 +380,22 @@ static void perf_evlist__set_sid_idx(struct perf_evlist *evlist,
 static struct perf_mmap*
 perf_evlist__mmap_cb_get(struct perf_evlist *evlist, bool overwrite, int idx)
 {
-	struct perf_mmap *map = &evlist->mmap[idx];
+	struct perf_mmap *maps;
 
-	if (overwrite) {
-		if (!evlist->mmap_ovw) {
-			evlist->mmap_ovw = perf_evlist__alloc_mmap(evlist, true);
-			if (!evlist->mmap_ovw)
-				return NULL;
-		}
-		map = &evlist->mmap_ovw[idx];
+	maps = overwrite ? evlist->mmap_ovw : evlist->mmap;
+
+	if (!maps) {
+		maps = perf_evlist__alloc_mmap(evlist, overwrite);
+		if (!maps)
+			return NULL;
+
+		if (overwrite)
+			evlist->mmap_ovw = maps;
+		else
+			evlist->mmap = maps;
 	}
 
-	return map;
+	return &maps[idx];
 }
 
 #define FD(e, x, y) (*(int *) xyarray__entry(e->fd, x, y))
@@ -405,6 +407,15 @@ perf_evlist__mmap_cb_mmap(struct perf_mmap *map, struct perf_mmap_param *mp,
 	return perf_mmap__mmap(map, mp, output, cpu);
 }
 
+static void perf_evlist__set_mmap_first(struct perf_evlist *evlist, struct perf_mmap *map,
+					bool overwrite)
+{
+	if (overwrite)
+		evlist->mmap_ovw_first = map;
+	else
+		evlist->mmap_first = map;
+}
+
 static int
 mmap_per_evsel(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops,
 	       int idx, struct perf_mmap_param *mp, int cpu_idx,
@@ -460,6 +471,9 @@ mmap_per_evsel(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops,
 
 			if (ops->mmap(map, mp, *output, evlist_cpu) < 0)
 				return -1;
+
+			if (!idx)
+				perf_evlist__set_mmap_first(evlist, map, overwrite);
 		} else {
 			if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT, *output) != 0)
 				return -1;
@@ -542,6 +556,17 @@ out_unmap:
 	return -1;
 }
 
+static int perf_evlist__nr_mmaps(struct perf_evlist *evlist)
+{
+	int nr_mmaps;
+
+	nr_mmaps = perf_cpu_map__nr(evlist->cpus);
+	if (perf_cpu_map__empty(evlist->cpus))
+		nr_mmaps = perf_thread_map__nr(evlist->threads);
+
+	return nr_mmaps;
+}
+
 int perf_evlist__mmap_ops(struct perf_evlist *evlist,
 			  struct perf_evlist_mmap_ops *ops,
 			  struct perf_mmap_param *mp)
@@ -553,10 +578,9 @@ int perf_evlist__mmap_ops(struct perf_evlist *evlist,
 	if (!ops || !ops->get || !ops->mmap)
 		return -EINVAL;
 
-	if (!evlist->mmap)
-		evlist->mmap = perf_evlist__alloc_mmap(evlist, false);
-	if (!evlist->mmap)
-		return -ENOMEM;
+	mp->mask = evlist->mmap_len - page_size - 1;
+
+	evlist->nr_mmaps = perf_evlist__nr_mmaps(evlist);
 
 	perf_evlist__for_each_entry(evlist, evsel) {
 		if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
@@ -583,7 +607,6 @@ int perf_evlist__mmap(struct perf_evlist *evlist, int pages)
 	};
 
 	evlist->mmap_len = (pages + 1) * page_size;
-	mp.mask = evlist->mmap_len - page_size - 1;
 
 	return perf_evlist__mmap_ops(evlist, &ops, &mp);
 }
@@ -605,3 +628,13 @@ void perf_evlist__munmap(struct perf_evlist *evlist)
 	zfree(&evlist->mmap);
 	zfree(&evlist->mmap_ovw);
 }
+
+struct perf_mmap*
+perf_evlist__next_mmap(struct perf_evlist *evlist, struct perf_mmap *map,
+		       bool overwrite)
+{
+	if (map)
+		return map->next;
+
+	return overwrite ? evlist->mmap_ovw_first : evlist->mmap_first;
+}
diff --git a/tools/perf/lib/include/internal/evlist.h b/tools/perf/lib/include/internal/evlist.h
index be0b25a70730..a2fbccf1922f 100644
--- a/tools/perf/lib/include/internal/evlist.h
+++ b/tools/perf/lib/include/internal/evlist.h
@@ -25,6 +25,8 @@ struct perf_evlist {
 	struct hlist_head	 heads[PERF_EVLIST__HLIST_SIZE];
 	struct perf_mmap	*mmap;
 	struct perf_mmap	*mmap_ovw;
+	struct perf_mmap	*mmap_first;
+	struct perf_mmap	*mmap_ovw_first;
 };
 
 typedef void
@@ -48,6 +50,7 @@ int perf_evlist__mmap_ops(struct perf_evlist *evlist,
 			  struct perf_evlist_mmap_ops *ops,
 			  struct perf_mmap_param *mp);
 
+void perf_evlist__init(struct perf_evlist *evlist);
 void perf_evlist__exit(struct perf_evlist *evlist);
 
 /**
diff --git a/tools/perf/lib/include/internal/evsel.h b/tools/perf/lib/include/internal/evsel.h
index a69b8299c36f..1ffd083b235e 100644
--- a/tools/perf/lib/include/internal/evsel.h
+++ b/tools/perf/lib/include/internal/evsel.h
@@ -50,6 +50,7 @@ struct perf_evsel {
 	bool			 system_wide;
 };
 
+void perf_evsel__init(struct perf_evsel *evsel, struct perf_event_attr *attr);
 int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads);
 void perf_evsel__close_fd(struct perf_evsel *evsel);
 void perf_evsel__free_fd(struct perf_evsel *evsel);
diff --git a/tools/perf/lib/include/internal/mmap.h b/tools/perf/lib/include/internal/mmap.h
index ee536c4441bb..be7556e0a2b2 100644
--- a/tools/perf/lib/include/internal/mmap.h
+++ b/tools/perf/lib/include/internal/mmap.h
@@ -32,6 +32,7 @@ struct perf_mmap {
 	u64			 flush;
 	libperf_unmap_cb_t	 unmap_cb;
 	char			 event_copy[PERF_SAMPLE_MAX_SIZE] __aligned(8);
+	struct perf_mmap	*next;
 };
 
 struct perf_mmap_param {
@@ -41,8 +42,8 @@ struct perf_mmap_param {
 
 size_t perf_mmap__mmap_len(struct perf_mmap *map);
 
-void perf_mmap__init(struct perf_mmap *map, bool overwrite,
-		     libperf_unmap_cb_t unmap_cb);
+void perf_mmap__init(struct perf_mmap *map, struct perf_mmap *prev,
+		     bool overwrite, libperf_unmap_cb_t unmap_cb);
 int perf_mmap__mmap(struct perf_mmap *map, struct perf_mmap_param *mp,
 		    int fd, int cpu);
 void perf_mmap__munmap(struct perf_mmap *map);
diff --git a/tools/perf/lib/include/internal/tests.h b/tools/perf/lib/include/internal/tests.h
index b7a20cd24ee1..2093e8868a67 100644
--- a/tools/perf/lib/include/internal/tests.h
+++ b/tools/perf/lib/include/internal/tests.h
@@ -4,14 +4,28 @@
 
 #include <stdio.h>
 
-#define __T_START fprintf(stdout, "- running %s...", __FILE__)
-#define __T_OK    fprintf(stdout, "OK\n")
-#define __T_FAIL  fprintf(stdout, "FAIL\n")
+int tests_failed;
+
+#define __T_START					\
+do {							\
+	fprintf(stdout, "- running %s...", __FILE__);	\
+	fflush(NULL);					\
+	tests_failed = 0;				\
+} while (0)
+
+#define __T_END								\
+do {									\
+	if (tests_failed)						\
+		fprintf(stdout, "  FAILED (%d)\n", tests_failed);	\
+	else								\
+		fprintf(stdout, "OK\n");				\
+} while (0)
 
 #define __T(text, cond)                                                          \
 do {                                                                             \
 	if (!(cond)) {                                                           \
 		fprintf(stderr, "FAILED %s:%d %s\n", __FILE__, __LINE__, text);  \
+		tests_failed++;                                                  \
 		return -1;                                                       \
 	}                                                                        \
 } while (0)
diff --git a/tools/perf/lib/include/perf/core.h b/tools/perf/lib/include/perf/core.h
index 2a80e4b6f819..a3f6d68edad7 100644
--- a/tools/perf/lib/include/perf/core.h
+++ b/tools/perf/lib/include/perf/core.h
@@ -9,6 +9,7 @@
 #endif
 
 enum libperf_print_level {
+	LIBPERF_ERR,
 	LIBPERF_WARN,
 	LIBPERF_INFO,
 	LIBPERF_DEBUG,
diff --git a/tools/perf/lib/include/perf/evlist.h b/tools/perf/lib/include/perf/evlist.h
index 16f526e74d13..0a7479dc13bf 100644
--- a/tools/perf/lib/include/perf/evlist.h
+++ b/tools/perf/lib/include/perf/evlist.h
@@ -3,13 +3,13 @@
 #define __LIBPERF_EVLIST_H
 
 #include <perf/core.h>
+#include <stdbool.h>
 
 struct perf_evlist;
 struct perf_evsel;
 struct perf_cpu_map;
 struct perf_thread_map;
 
-LIBPERF_API void perf_evlist__init(struct perf_evlist *evlist);
 LIBPERF_API void perf_evlist__add(struct perf_evlist *evlist,
 				  struct perf_evsel *evsel);
 LIBPERF_API void perf_evlist__remove(struct perf_evlist *evlist,
@@ -38,4 +38,12 @@ LIBPERF_API int perf_evlist__filter_pollfd(struct perf_evlist *evlist,
 LIBPERF_API int perf_evlist__mmap(struct perf_evlist *evlist, int pages);
 LIBPERF_API void perf_evlist__munmap(struct perf_evlist *evlist);
 
+LIBPERF_API struct perf_mmap *perf_evlist__next_mmap(struct perf_evlist *evlist,
+						     struct perf_mmap *map,
+						     bool overwrite);
+#define perf_evlist__for_each_mmap(evlist, pos, overwrite)		\
+	for ((pos) = perf_evlist__next_mmap((evlist), NULL, overwrite);	\
+	     (pos) != NULL;						\
+	     (pos) = perf_evlist__next_mmap((evlist), (pos), overwrite))
+
 #endif /* __LIBPERF_EVLIST_H */
diff --git a/tools/perf/lib/include/perf/evsel.h b/tools/perf/lib/include/perf/evsel.h
index 4388667f265c..557f5815a9c9 100644
--- a/tools/perf/lib/include/perf/evsel.h
+++ b/tools/perf/lib/include/perf/evsel.h
@@ -21,8 +21,6 @@ struct perf_counts_values {
 	};
 };
 
-LIBPERF_API void perf_evsel__init(struct perf_evsel *evsel,
-				  struct perf_event_attr *attr);
 LIBPERF_API struct perf_evsel *perf_evsel__new(struct perf_event_attr *attr);
 LIBPERF_API void perf_evsel__delete(struct perf_evsel *evsel);
 LIBPERF_API int perf_evsel__open(struct perf_evsel *evsel, struct perf_cpu_map *cpus,
diff --git a/tools/perf/lib/internal.h b/tools/perf/lib/internal.h
index 37db745e1502..2c27e158de6b 100644
--- a/tools/perf/lib/internal.h
+++ b/tools/perf/lib/internal.h
@@ -2,6 +2,8 @@
 #ifndef __LIBPERF_INTERNAL_H
 #define __LIBPERF_INTERNAL_H
 
+#include <perf/core.h>
+
 void libperf_print(enum libperf_print_level level,
 		   const char *format, ...)
 	__attribute__((format(printf, 2, 3)));
@@ -11,6 +13,7 @@ do {                            \
 	libperf_print(level, "libperf: " fmt, ##__VA_ARGS__);     \
 } while (0)
 
+#define pr_err(fmt, ...)        __pr(LIBPERF_ERR, fmt, ##__VA_ARGS__)
 #define pr_warning(fmt, ...)    __pr(LIBPERF_WARN, fmt, ##__VA_ARGS__)
 #define pr_info(fmt, ...)       __pr(LIBPERF_INFO, fmt, ##__VA_ARGS__)
 #define pr_debug(fmt, ...)      __pr(LIBPERF_DEBUG, fmt, ##__VA_ARGS__)
diff --git a/tools/perf/lib/libperf.map b/tools/perf/lib/libperf.map
index 2184aba36c3f..7be1af8a546c 100644
--- a/tools/perf/lib/libperf.map
+++ b/tools/perf/lib/libperf.map
@@ -21,7 +21,6 @@ LIBPERF_0.0.1 {
 		perf_evsel__delete;
 		perf_evsel__enable;
 		perf_evsel__disable;
-		perf_evsel__init;
 		perf_evsel__open;
 		perf_evsel__close;
 		perf_evsel__read;
@@ -34,7 +33,6 @@ LIBPERF_0.0.1 {
 		perf_evlist__close;
 		perf_evlist__enable;
 		perf_evlist__disable;
-		perf_evlist__init;
 		perf_evlist__add;
 		perf_evlist__remove;
 		perf_evlist__next;
@@ -43,6 +41,7 @@ LIBPERF_0.0.1 {
 		perf_evlist__mmap;
 		perf_evlist__munmap;
 		perf_evlist__filter_pollfd;
+		perf_evlist__next_mmap;
 		perf_mmap__consume;
 		perf_mmap__read_init;
 		perf_mmap__read_done;
diff --git a/tools/perf/lib/mmap.c b/tools/perf/lib/mmap.c
index 0752c193b0fb..79d5ed6c38cc 100644
--- a/tools/perf/lib/mmap.c
+++ b/tools/perf/lib/mmap.c
@@ -13,13 +13,15 @@
 #include <linux/kernel.h>
 #include "internal.h"
 
-void perf_mmap__init(struct perf_mmap *map, bool overwrite,
-		     libperf_unmap_cb_t unmap_cb)
+void perf_mmap__init(struct perf_mmap *map, struct perf_mmap *prev,
+		     bool overwrite, libperf_unmap_cb_t unmap_cb)
 {
 	map->fd = -1;
 	map->overwrite = overwrite;
 	map->unmap_cb  = unmap_cb;
 	refcount_set(&map->refcnt, 0);
+	if (prev)
+		prev->next = map;
 }
 
 size_t perf_mmap__mmap_len(struct perf_mmap *map)
diff --git a/tools/perf/lib/tests/Makefile b/tools/perf/lib/tests/Makefile
index 1ee4e9ba848b..a43cd08c5c03 100644
--- a/tools/perf/lib/tests/Makefile
+++ b/tools/perf/lib/tests/Makefile
@@ -16,13 +16,13 @@ all:
 
 include $(srctree)/tools/scripts/Makefile.include
 
-INCLUDE = -I$(srctree)/tools/perf/lib/include -I$(srctree)/tools/include
+INCLUDE = -I$(srctree)/tools/perf/lib/include -I$(srctree)/tools/include -I$(srctree)/tools/lib
 
 $(TESTS_A): FORCE
-	$(QUIET_LINK)$(CC) $(INCLUDE) $(CFLAGS) -o $@ $(subst -a,.c,$@) ../libperf.a
+	$(QUIET_LINK)$(CC) $(INCLUDE) $(CFLAGS) -o $@ $(subst -a,.c,$@) ../libperf.a $(LIBAPI)
 
 $(TESTS_SO): FORCE
-	$(QUIET_LINK)$(CC) $(INCLUDE) $(CFLAGS) -L.. -o $@ $(subst -so,.c,$@) -lperf
+	$(QUIET_LINK)$(CC) $(INCLUDE) $(CFLAGS) -L.. -o $@ $(subst -so,.c,$@) $(LIBAPI) -lperf
 
 all: $(TESTS_A) $(TESTS_SO)
 
diff --git a/tools/perf/lib/tests/test-cpumap.c b/tools/perf/lib/tests/test-cpumap.c
index aa34c20df07e..c8d45091e7c2 100644
--- a/tools/perf/lib/tests/test-cpumap.c
+++ b/tools/perf/lib/tests/test-cpumap.c
@@ -26,6 +26,6 @@ int main(int argc, char **argv)
 	perf_cpu_map__put(cpus);
 	perf_cpu_map__put(cpus);
 
-	__T_OK;
+	__T_END;
 	return 0;
 }
diff --git a/tools/perf/lib/tests/test-evlist.c b/tools/perf/lib/tests/test-evlist.c
index e6b2ab2e2bde..6d8ebe0c2504 100644
--- a/tools/perf/lib/tests/test-evlist.c
+++ b/tools/perf/lib/tests/test-evlist.c
@@ -1,12 +1,23 @@
 // SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE // needed for sched.h to get sched_[gs]etaffinity and CPU_(ZERO,SET)
+#include <sched.h>
 #include <stdio.h>
 #include <stdarg.h>
+#include <unistd.h>
+#include <stdlib.h>
 #include <linux/perf_event.h>
+#include <linux/limits.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <sys/prctl.h>
 #include <perf/cpumap.h>
 #include <perf/threadmap.h>
 #include <perf/evlist.h>
 #include <perf/evsel.h>
+#include <perf/mmap.h>
+#include <perf/event.h>
 #include <internal/tests.h>
+#include <api/fs/fs.h>
 
 static int libperf_print(enum libperf_print_level level,
 			 const char *fmt, va_list ap)
@@ -181,6 +192,210 @@ static int test_stat_thread_enable(void)
 	return 0;
 }
 
+static int test_mmap_thread(void)
+{
+	struct perf_evlist *evlist;
+	struct perf_evsel *evsel;
+	struct perf_mmap *map;
+	struct perf_cpu_map *cpus;
+	struct perf_thread_map *threads;
+	struct perf_event_attr attr = {
+		.type             = PERF_TYPE_TRACEPOINT,
+		.sample_period    = 1,
+		.wakeup_watermark = 1,
+		.disabled         = 1,
+	};
+	char path[PATH_MAX];
+	int id, err, pid, go_pipe[2];
+	union perf_event *event;
+	char bf;
+	int count = 0;
+
+	snprintf(path, PATH_MAX, "%s/kernel/debug/tracing/events/syscalls/sys_enter_prctl/id",
+		 sysfs__mountpoint());
+
+	if (filename__read_int(path, &id)) {
+		fprintf(stderr, "error: failed to get tracepoint id: %s\n", path);
+		return -1;
+	}
+
+	attr.config = id;
+
+	err = pipe(go_pipe);
+	__T("failed to create pipe", err == 0);
+
+	fflush(NULL);
+
+	pid = fork();
+	if (!pid) {
+		int i;
+
+		read(go_pipe[0], &bf, 1);
+
+		/* Generate 100 prctl calls. */
+		for (i = 0; i < 100; i++)
+			prctl(0, 0, 0, 0, 0);
+
+		exit(0);
+	}
+
+	threads = perf_thread_map__new_dummy();
+	__T("failed to create threads", threads);
+
+	cpus = perf_cpu_map__dummy_new();
+	__T("failed to create cpus", cpus);
+
+	perf_thread_map__set_pid(threads, 0, pid);
+
+	evlist = perf_evlist__new();
+	__T("failed to create evlist", evlist);
+
+	evsel = perf_evsel__new(&attr);
+	__T("failed to create evsel1", evsel);
+
+	perf_evlist__add(evlist, evsel);
+
+	perf_evlist__set_maps(evlist, cpus, threads);
+
+	err = perf_evlist__open(evlist);
+	__T("failed to open evlist", err == 0);
+
+	err = perf_evlist__mmap(evlist, 4);
+	__T("failed to mmap evlist", err == 0);
+
+	perf_evlist__enable(evlist);
+
+	/* kick the child and wait for it to finish */
+	write(go_pipe[1], &bf, 1);
+	waitpid(pid, NULL, 0);
+
+	/*
+	 * There's no need to call perf_evlist__disable,
+	 * monitored process is dead now.
+	 */
+
+	perf_evlist__for_each_mmap(evlist, map, false) {
+		if (perf_mmap__read_init(map) < 0)
+			continue;
+
+		while ((event = perf_mmap__read_event(map)) != NULL) {
+			count++;
+			perf_mmap__consume(map);
+		}
+
+		perf_mmap__read_done(map);
+	}
+
+	/* calls perf_evlist__munmap/perf_evlist__close */
+	perf_evlist__delete(evlist);
+
+	perf_thread_map__put(threads);
+	perf_cpu_map__put(cpus);
+
+	/*
+	 * The generated prctl calls should match the
+	 * number of events in the buffer.
+	 */
+	__T("failed count", count == 100);
+
+	return 0;
+}
+
+static int test_mmap_cpus(void)
+{
+	struct perf_evlist *evlist;
+	struct perf_evsel *evsel;
+	struct perf_mmap *map;
+	struct perf_cpu_map *cpus;
+	struct perf_event_attr attr = {
+		.type             = PERF_TYPE_TRACEPOINT,
+		.sample_period    = 1,
+		.wakeup_watermark = 1,
+		.disabled         = 1,
+	};
+	cpu_set_t saved_mask;
+	char path[PATH_MAX];
+	int id, err, cpu, tmp;
+	union perf_event *event;
+	int count = 0;
+
+	snprintf(path, PATH_MAX, "%s/kernel/debug/tracing/events/syscalls/sys_enter_prctl/id",
+		 sysfs__mountpoint());
+
+	if (filename__read_int(path, &id)) {
+		fprintf(stderr, "error: failed to get tracepoint id: %s\n", path);
+		return -1;
+	}
+
+	attr.config = id;
+
+	cpus = perf_cpu_map__new(NULL);
+	__T("failed to create cpus", cpus);
+
+	evlist = perf_evlist__new();
+	__T("failed to create evlist", evlist);
+
+	evsel = perf_evsel__new(&attr);
+	__T("failed to create evsel1", evsel);
+
+	perf_evlist__add(evlist, evsel);
+
+	perf_evlist__set_maps(evlist, cpus, NULL);
+
+	err = perf_evlist__open(evlist);
+	__T("failed to open evlist", err == 0);
+
+	err = perf_evlist__mmap(evlist, 4);
+	__T("failed to mmap evlist", err == 0);
+
+	perf_evlist__enable(evlist);
+
+	err = sched_getaffinity(0, sizeof(saved_mask), &saved_mask);
+	__T("sched_getaffinity failed", err == 0);
+
+	perf_cpu_map__for_each_cpu(cpu, tmp, cpus) {
+		cpu_set_t mask;
+
+		CPU_ZERO(&mask);
+		CPU_SET(cpu, &mask);
+
+		err = sched_setaffinity(0, sizeof(mask), &mask);
+		__T("sched_setaffinity failed", err == 0);
+
+		prctl(0, 0, 0, 0, 0);
+	}
+
+	err = sched_setaffinity(0, sizeof(saved_mask), &saved_mask);
+	__T("sched_setaffinity failed", err == 0);
+
+	perf_evlist__disable(evlist);
+
+	perf_evlist__for_each_mmap(evlist, map, false) {
+		if (perf_mmap__read_init(map) < 0)
+			continue;
+
+		while ((event = perf_mmap__read_event(map)) != NULL) {
+			count++;
+			perf_mmap__consume(map);
+		}
+
+		perf_mmap__read_done(map);
+	}
+
+	/* calls perf_evlist__munmap/perf_evlist__close */
+	perf_evlist__delete(evlist);
+
+	/*
+	 * The generated prctl events should match the
+	 * number of cpus or be bigger (we are system-wide).
+	 */
+	__T("failed count", count >= perf_cpu_map__nr(cpus));
+
+	perf_cpu_map__put(cpus);
+
+	return 0;
+}
+
 int main(int argc, char **argv)
 {
 	__T_START;
@@ -190,7 +405,9 @@ int main(int argc, char **argv)
 	test_stat_cpu();
 	test_stat_thread();
 	test_stat_thread_enable();
+	test_mmap_thread();
+	test_mmap_cpus();
 
-	__T_OK;
+	__T_END;
 	return 0;
 }
diff --git a/tools/perf/lib/tests/test-evsel.c b/tools/perf/lib/tests/test-evsel.c
index 1b6c4285ac2b..135722ac965b 100644
--- a/tools/perf/lib/tests/test-evsel.c
+++ b/tools/perf/lib/tests/test-evsel.c
@@ -130,6 +130,6 @@ int main(int argc, char **argv)
 	test_stat_thread();
 	test_stat_thread_enable();
 
-	__T_OK;
+	__T_END;
 	return 0;
 }
diff --git a/tools/perf/lib/tests/test-threadmap.c b/tools/perf/lib/tests/test-threadmap.c
index 8c5f47247d9e..7dc4d6fbedde 100644
--- a/tools/perf/lib/tests/test-threadmap.c
+++ b/tools/perf/lib/tests/test-threadmap.c
@@ -26,6 +26,6 @@ int main(int argc, char **argv)
 	perf_thread_map__put(threads);
 	perf_thread_map__put(threads);
 
-	__T_OK;
+	__T_END;
 	return 0;
 }
diff --git a/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-ddrc.json b/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-ddrc.json
index 0d1556fcdffe..7da86942dae2 100644
--- a/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-ddrc.json
+++ b/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-ddrc.json
@@ -1,5 +1,19 @@
 [
    {
+	    "EventCode": "0x00",
+	    "EventName": "uncore_hisi_ddrc.flux_wr",
+	    "BriefDescription": "DDRC total write operations",
+	    "PublicDescription": "DDRC total write operations",
+	    "Unit": "hisi_sccl,ddrc",
+   },
+   {
+	    "EventCode": "0x01",
+	    "EventName": "uncore_hisi_ddrc.flux_rd",
+	    "BriefDescription": "DDRC total read operations",
+	    "PublicDescription": "DDRC total read operations",
+	    "Unit": "hisi_sccl,ddrc",
+   },
+   {
 	    "EventCode": "0x02",
 	    "EventName": "uncore_hisi_ddrc.flux_wcmd",
 	    "BriefDescription": "DDRC write commands",
@@ -15,7 +29,7 @@
    },
    {
 	    "EventCode": "0x04",
-	    "EventName": "uncore_hisi_ddrc.flux_wr",
+	    "EventName": "uncore_hisi_ddrc.pre_cmd",
 	    "BriefDescription": "DDRC precharge commands",
 	    "PublicDescription": "DDRC precharge commands",
 	    "Unit": "hisi_sccl,ddrc",
diff --git a/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-hha.json b/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-hha.json
index 447d3064de90..3be418a248ea 100644
--- a/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-hha.json
+++ b/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-hha.json
@@ -21,6 +21,13 @@
 	    "Unit": "hisi_sccl,hha",
    },
    {
+	    "EventCode": "0x03",
+	    "EventName": "uncore_hisi_hha.rx_ccix",
+	    "BriefDescription": "Count of the number of operations that HHA has received from CCIX",
+	    "PublicDescription": "Count of the number of operations that HHA has received from CCIX",
+	    "Unit": "hisi_sccl,hha",
+   },
+   {
 	    "EventCode": "0x1c",
 	    "EventName": "uncore_hisi_hha.rd_ddr_64b",
 	    "BriefDescription": "The number of read operations sent by HHA to DDRC which size is 64 bytes",
@@ -29,7 +36,7 @@
    },
    {
 	    "EventCode": "0x1d",
-	    "EventName": "uncore_hisi_hha.wr_dr_64b",
+	    "EventName": "uncore_hisi_hha.wr_ddr_64b",
 	    "BriefDescription": "The number of write operations sent by HHA to DDRC which size is 64 bytes",
 	    "PublicDescription": "The number of write operations sent by HHA to DDRC which size is 64 bytes",
 	    "Unit": "hisi_sccl,hha",
@@ -48,4 +55,18 @@
 	    "PublicDescription": "The number of write operations sent by HHA to DDRC which size is 128 bytes",
 	    "Unit": "hisi_sccl,hha",
    },
+   {
+	    "EventCode": "0x20",
+	    "EventName": "uncore_hisi_hha.spill_num",
+	    "BriefDescription": "Count of the number of spill operations that the HHA has sent",
+	    "PublicDescription": "Count of the number of spill operations that the HHA has sent",
+	    "Unit": "hisi_sccl,hha",
+   },
+   {
+	    "EventCode": "0x21",
+	    "EventName": "uncore_hisi_hha.spill_success",
+	    "BriefDescription": "Count of the number of successful spill operations that the HHA has sent",
+	    "PublicDescription": "Count of the number of successful spill operations that the HHA has sent",
+	    "Unit": "hisi_sccl,hha",
+   },
 ]
diff --git a/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-l3c.json b/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-l3c.json
index ca48747642e1..f463d0acfaef 100644
--- a/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-l3c.json
+++ b/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-l3c.json
@@ -34,4 +34,60 @@
 	    "PublicDescription": "l3c precharge commands",
 	    "Unit": "hisi_sccl,l3c",
    },
+   {
+	    "EventCode": "0x20",
+	    "EventName": "uncore_hisi_l3c.rd_spipe",
+	    "BriefDescription": "Count of the number of read lines that come from this cluster of CPU core in spipe",
+	    "PublicDescription": "Count of the number of read lines that come from this cluster of CPU core in spipe",
+	    "Unit": "hisi_sccl,l3c",
+   },
+   {
+	    "EventCode": "0x21",
+	    "EventName": "uncore_hisi_l3c.wr_spipe",
+	    "BriefDescription": "Count of the number of write lines that come from this cluster of CPU core in spipe",
+	    "PublicDescription": "Count of the number of write lines that come from this cluster of CPU core in spipe",
+	    "Unit": "hisi_sccl,l3c",
+   },
+   {
+	    "EventCode": "0x22",
+	    "EventName": "uncore_hisi_l3c.rd_hit_spipe",
+	    "BriefDescription": "Count of the number of read lines that hits in spipe of this L3C",
+	    "PublicDescription": "Count of the number of read lines that hits in spipe of this L3C",
+	    "Unit": "hisi_sccl,l3c",
+   },
+   {
+	    "EventCode": "0x23",
+	    "EventName": "uncore_hisi_l3c.wr_hit_spipe",
+	    "BriefDescription": "Count of the number of write lines that hits in spipe of this L3C",
+	    "PublicDescription": "Count of the number of write lines that hits in spipe of this L3C",
+	    "Unit": "hisi_sccl,l3c",
+   },
+   {
+	    "EventCode": "0x29",
+	    "EventName": "uncore_hisi_l3c.back_invalid",
+	    "BriefDescription": "Count of the number of L3C back invalid operations",
+	    "PublicDescription": "Count of the number of L3C back invalid operations",
+	    "Unit": "hisi_sccl,l3c",
+   },
+   {
+	    "EventCode": "0x40",
+	    "EventName": "uncore_hisi_l3c.retry_cpu",
+	    "BriefDescription": "Count of the number of retry that L3C suppresses the CPU operations",
+	    "PublicDescription": "Count of the number of retry that L3C suppresses the CPU operations",
+	    "Unit": "hisi_sccl,l3c",
+   },
+   {
+	    "EventCode": "0x41",
+	    "EventName": "uncore_hisi_l3c.retry_ring",
+	    "BriefDescription": "Count of the number of retry that L3C suppresses the ring operations",
+	    "PublicDescription": "Count of the number of retry that L3C suppresses the ring operations",
+	    "Unit": "hisi_sccl,l3c",
+   },
+   {
+	    "EventCode": "0x42",
+	    "EventName": "uncore_hisi_l3c.prefetch_drop",
+	    "BriefDescription": "Count of the number of prefetch drops from this L3C",
+	    "PublicDescription": "Count of the number of prefetch drops from this L3C",
+	    "Unit": "hisi_sccl,l3c",
+   },
 ]
diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c
index e2837260ca4d..7d69727f44bd 100644
--- a/tools/perf/pmu-events/jevents.c
+++ b/tools/perf/pmu-events/jevents.c
@@ -322,7 +322,8 @@ static int print_events_table_entry(void *data, char *name, char *event,
 				    char *desc, char *long_desc,
 				    char *pmu, char *unit, char *perpkg,
 				    char *metric_expr,
-				    char *metric_name, char *metric_group)
+				    char *metric_name, char *metric_group,
+				    char *deprecated)
 {
 	struct perf_entry_data *pd = data;
 	FILE *outfp = pd->outfp;
@@ -354,6 +355,8 @@ static int print_events_table_entry(void *data, char *name, char *event,
 		fprintf(outfp, "\t.metric_name = \"%s\",\n", metric_name);
 	if (metric_group)
 		fprintf(outfp, "\t.metric_group = \"%s\",\n", metric_group);
+	if (deprecated)
+		fprintf(outfp, "\t.deprecated = \"%s\",\n", deprecated);
 	fprintf(outfp, "},\n");
 
 	return 0;
@@ -371,6 +374,7 @@ struct event_struct {
 	char *metric_expr;
 	char *metric_name;
 	char *metric_group;
+	char *deprecated;
 };
 
 #define ADD_EVENT_FIELD(field) do { if (field) {		\
@@ -398,6 +402,7 @@ struct event_struct {
 	op(metric_expr);					\
 	op(metric_name);					\
 	op(metric_group);					\
+	op(deprecated);						\
 } while (0)
 
 static LIST_HEAD(arch_std_events);
@@ -416,7 +421,8 @@ static void free_arch_std_events(void)
 static int save_arch_std_events(void *data, char *name, char *event,
 				char *desc, char *long_desc, char *pmu,
 				char *unit, char *perpkg, char *metric_expr,
-				char *metric_name, char *metric_group)
+				char *metric_name, char *metric_group,
+				char *deprecated)
 {
 	struct event_struct *es;
 
@@ -479,7 +485,8 @@ static int
 try_fixup(const char *fn, char *arch_std, char **event, char **desc,
 	  char **name, char **long_desc, char **pmu, char **filter,
 	  char **perpkg, char **unit, char **metric_expr, char **metric_name,
-	  char **metric_group, unsigned long long eventcode)
+	  char **metric_group, unsigned long long eventcode,
+	  char **deprecated)
 {
 	/* try to find matching event from arch standard values */
 	struct event_struct *es;
@@ -507,7 +514,8 @@ int json_events(const char *fn,
 		      char *long_desc,
 		      char *pmu, char *unit, char *perpkg,
 		      char *metric_expr,
-		      char *metric_name, char *metric_group),
+		      char *metric_name, char *metric_group,
+		      char *deprecated),
 	  void *data)
 {
 	int err;
@@ -536,6 +544,7 @@ int json_events(const char *fn,
 		char *metric_expr = NULL;
 		char *metric_name = NULL;
 		char *metric_group = NULL;
+		char *deprecated = NULL;
 		char *arch_std = NULL;
 		unsigned long long eventcode = 0;
 		struct msrmap *msr = NULL;
@@ -614,6 +623,8 @@ int json_events(const char *fn,
 				addfield(map, &unit, "", "", val);
 			} else if (json_streq(map, field, "PerPkg")) {
 				addfield(map, &perpkg, "", "", val);
+			} else if (json_streq(map, field, "Deprecated")) {
+				addfield(map, &deprecated, "", "", val);
 			} else if (json_streq(map, field, "MetricName")) {
 				addfield(map, &metric_name, "", "", val);
 			} else if (json_streq(map, field, "MetricGroup")) {
@@ -658,12 +669,14 @@ int json_events(const char *fn,
 			err = try_fixup(fn, arch_std, &event, &desc, &name,
 					&long_desc, &pmu, &filter, &perpkg,
 					&unit, &metric_expr, &metric_name,
-					&metric_group, eventcode);
+					&metric_group, eventcode,
+					&deprecated);
 			if (err)
 				goto free_strings;
 		}
 		err = func(data, name, real_event(name, event), desc, long_desc,
-			   pmu, unit, perpkg, metric_expr, metric_name, metric_group);
+			   pmu, unit, perpkg, metric_expr, metric_name,
+			   metric_group, deprecated);
 free_strings:
 		free(event);
 		free(desc);
@@ -673,6 +686,7 @@ free_strings:
 		free(pmu);
 		free(filter);
 		free(perpkg);
+		free(deprecated);
 		free(unit);
 		free(metric_expr);
 		free(metric_name);
diff --git a/tools/perf/pmu-events/jevents.h b/tools/perf/pmu-events/jevents.h
index 4684c673c445..5cda49a42143 100644
--- a/tools/perf/pmu-events/jevents.h
+++ b/tools/perf/pmu-events/jevents.h
@@ -7,7 +7,8 @@ int json_events(const char *fn,
 				char *long_desc,
 				char *pmu,
 				char *unit, char *perpkg, char *metric_expr,
-				char *metric_name, char *metric_group),
+				char *metric_name, char *metric_group,
+				char *deprecated),
 		void *data);
 char *get_cpu_str(void);
 
diff --git a/tools/perf/pmu-events/pmu-events.h b/tools/perf/pmu-events/pmu-events.h
index 92a4d15ee0b9..caeb577d36c9 100644
--- a/tools/perf/pmu-events/pmu-events.h
+++ b/tools/perf/pmu-events/pmu-events.h
@@ -17,6 +17,7 @@ struct pmu_event {
 	const char *metric_expr;
 	const char *metric_name;
 	const char *metric_group;
+	const char *deprecated;
 };
 
 /*
diff --git a/tools/perf/tests/bp_account.c b/tools/perf/tests/bp_account.c
index 016bba2c142d..d0b935356274 100644
--- a/tools/perf/tests/bp_account.c
+++ b/tools/perf/tests/bp_account.c
@@ -10,11 +10,7 @@
 #include <unistd.h>
 #include <string.h>
 #include <sys/ioctl.h>
-#include <time.h>
 #include <fcntl.h>
-#include <signal.h>
-#include <sys/mman.h>
-#include <linux/compiler.h>
 #include <linux/hw_breakpoint.h>
 
 #include "tests.h"
@@ -192,3 +188,19 @@ int test__bp_accounting(struct test *test __maybe_unused, int subtest __maybe_un
 
 	return bp_accounting(wp_cnt, share);
 }
+
+bool test__bp_account_is_supported(void)
+{
+	/*
+	 * PowerPC and S390 do not support creation of instruction
+	 * breakpoints using the perf_event interface.
+	 *
+	 * Just disable the test for these architectures until these
+	 * issues are resolved.
+	 */
+#if defined(__powerpc__) || defined(__s390x__)
+	return false;
+#else
+	return true;
+#endif
+}
diff --git a/tools/perf/tests/bp_signal.c b/tools/perf/tests/bp_signal.c
index c1c2c13de254..166f411568a5 100644
--- a/tools/perf/tests/bp_signal.c
+++ b/tools/perf/tests/bp_signal.c
@@ -49,14 +49,6 @@ asm (
 	"__test_function:\n"
 	"incq (%rdi)\n"
 	"ret\n");
-#elif defined (__aarch64__)
-extern void __test_function(volatile long *ptr);
-asm (
-	".globl __test_function\n"
-	"__test_function:\n"
-	"str x30, [x0]\n"
-	"ret\n");
-
 #else
 static void __test_function(volatile long *ptr)
 {
@@ -302,10 +294,15 @@ bool test__bp_signal_is_supported(void)
 	 * stepping into the SIGIO handler and getting stuck on the
 	 * breakpointed instruction.
 	 *
+	 * Since arm64 has the same issue with arm for the single-step
+	 * handling, this case also gets suck on the breakpointed
+	 * instruction.
+	 *
 	 * Just disable the test for these architectures until these
 	 * issues are resolved.
 	 */
-#if defined(__powerpc__) || defined(__s390x__) || defined(__arm__)
+#if defined(__powerpc__) || defined(__s390x__) || defined(__arm__) || \
+    defined(__aarch64__)
 	return false;
 #else
 	return true;
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 55774baffc2a..8b286e9b7549 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -121,7 +121,7 @@ static struct test generic_tests[] = {
 	{
 		.desc = "Breakpoint accounting",
 		.func = test__bp_accounting,
-		.is_supported = test__bp_signal_is_supported,
+		.is_supported = test__bp_account_is_supported,
 	},
 	{
 		.desc = "Watchpoint",
diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c
index 4965f8b9055b..adaff9044331 100644
--- a/tools/perf/tests/task-exit.c
+++ b/tools/perf/tests/task-exit.c
@@ -54,6 +54,7 @@ int test__task_exit(struct test *test __maybe_unused, int subtest __maybe_unused
 	struct perf_cpu_map *cpus;
 	struct perf_thread_map *threads;
 	struct mmap *md;
+	int retry_count = 0;
 
 	signal(SIGCHLD, sig_handler);
 
@@ -111,6 +112,7 @@ int test__task_exit(struct test *test __maybe_unused, int subtest __maybe_unused
 	if (evlist__mmap(evlist, 128) < 0) {
 		pr_debug("failed to mmap events: %d (%s)\n", errno,
 			 str_error_r(errno, sbuf, sizeof(sbuf)));
+		err = -1;
 		goto out_delete_evlist;
 	}
 
@@ -132,6 +134,13 @@ retry:
 out_init:
 	if (!exited || !nr_exit) {
 		evlist__poll(evlist, -1);
+
+		if (retry_count++ > 1000) {
+			pr_debug("Failed after retrying 1000 times\n");
+			err = -1;
+			goto out_free_maps;
+		}
+
 		goto retry;
 	}
 
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index 72912eb473cb..9837b6e93023 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -111,6 +111,7 @@ int test__map_groups__merge_in(struct test *t, int subtest);
 int test__time_utils(struct test *t, int subtest);
 
 bool test__bp_signal_is_supported(void);
+bool test__bp_account_is_supported(void);
 bool test__wp_is_supported(void);
 
 #if defined(__arm__) || defined(__aarch64__)
diff --git a/tools/perf/trace/beauty/beauty.h b/tools/perf/trace/beauty/beauty.h
index 77ad80a399fd..5a61043c2ff7 100644
--- a/tools/perf/trace/beauty/beauty.h
+++ b/tools/perf/trace/beauty/beauty.h
@@ -28,9 +28,11 @@ struct strarray {
 }
 
 size_t strarray__scnprintf(struct strarray *sa, char *bf, size_t size, const char *intfmt, bool show_prefix, int val);
+size_t strarray__scnprintf_suffix(struct strarray *sa, char *bf, size_t size, const char *intfmt, bool show_suffix, int val);
 size_t strarray__scnprintf_flags(struct strarray *sa, char *bf, size_t size, bool show_prefix, unsigned long flags);
 
 bool strarray__strtoul(struct strarray *sa, char *bf, size_t size, u64 *ret);
+bool strarray__strtoul_flags(struct strarray *sa, char *bf, size_t size, u64 *ret);
 
 struct trace;
 struct thread;
@@ -87,6 +89,7 @@ struct syscall_arg_fmt;
 
 /**
  * @val: value of syscall argument being formatted
+ * @len: for tracepoint dynamic arrays, if fmt->nr_entries == 0, then its not a fixed array, look at arg->len
  * @args: All the args, use syscall_args__val(arg, nth) to access one
  * @augmented_args: Extra data that can be collected, for instance, with eBPF for expanding the pathname for open, etc
  * @augmented_args_size: augmented_args total payload size
@@ -109,6 +112,7 @@ struct syscall_arg {
 	struct thread *thread;
 	struct trace  *trace;
 	void	      *parm;
+	u16	      len;
 	u8	      idx;
 	u8	      mask;
 	bool	      show_string_prefix;
@@ -119,6 +123,21 @@ unsigned long syscall_arg__val(struct syscall_arg *arg, u8 idx);
 size_t syscall_arg__scnprintf_strarray_flags(char *bf, size_t size, struct syscall_arg *arg);
 #define SCA_STRARRAY_FLAGS syscall_arg__scnprintf_strarray_flags
 
+bool syscall_arg__strtoul_strarray(char *bf, size_t size, struct syscall_arg *arg, u64 *ret);
+#define STUL_STRARRAY syscall_arg__strtoul_strarray
+
+bool syscall_arg__strtoul_strarray_flags(char *bf, size_t size, struct syscall_arg *arg, u64 *ret);
+#define STUL_STRARRAY_FLAGS syscall_arg__strtoul_strarray_flags
+
+bool syscall_arg__strtoul_strarrays(char *bf, size_t size, struct syscall_arg *arg, u64 *ret);
+#define STUL_STRARRAYS syscall_arg__strtoul_strarrays
+
+size_t syscall_arg__scnprintf_x86_irq_vectors(char *bf, size_t size, struct syscall_arg *arg);
+#define SCA_X86_IRQ_VECTORS syscall_arg__scnprintf_x86_irq_vectors
+
+bool syscall_arg__strtoul_x86_irq_vectors(char *bf, size_t size, struct syscall_arg *arg, u64 *ret);
+#define STUL_X86_IRQ_VECTORS syscall_arg__strtoul_x86_irq_vectors
+
 size_t syscall_arg__scnprintf_x86_MSR(char *bf, size_t size, struct syscall_arg *arg);
 #define SCA_X86_MSR syscall_arg__scnprintf_x86_MSR
 
diff --git a/tools/perf/trace/beauty/mmap.c b/tools/perf/trace/beauty/mmap.c
index 859a8a9db2c6..9fa771a90d79 100644
--- a/tools/perf/trace/beauty/mmap.c
+++ b/tools/perf/trace/beauty/mmap.c
@@ -33,11 +33,11 @@ static size_t syscall_arg__scnprintf_mmap_prot(char *bf, size_t size,
 
 #define SCA_MMAP_PROT syscall_arg__scnprintf_mmap_prot
 
-static size_t mmap__scnprintf_flags(unsigned long flags, char *bf, size_t size, bool show_prefix)
-{
 #include "trace/beauty/generated/mmap_flags_array.c"
        static DEFINE_STRARRAY(mmap_flags, "MAP_");
 
+static size_t mmap__scnprintf_flags(unsigned long flags, char *bf, size_t size, bool show_prefix)
+{
        return strarray__scnprintf_flags(&strarray__mmap_flags, bf, size, show_prefix, flags);
 }
 
diff --git a/tools/perf/trace/beauty/tracepoints/Build b/tools/perf/trace/beauty/tracepoints/Build
index 625a67663de3..e35087fdd108 100644
--- a/tools/perf/trace/beauty/tracepoints/Build
+++ b/tools/perf/trace/beauty/tracepoints/Build
@@ -1 +1,2 @@
+perf-y += x86_irq_vectors.o
 perf-y += x86_msr.o
diff --git a/tools/perf/trace/beauty/tracepoints/x86_irq_vectors.c b/tools/perf/trace/beauty/tracepoints/x86_irq_vectors.c
new file mode 100644
index 000000000000..8eb9bc8534ac
--- /dev/null
+++ b/tools/perf/trace/beauty/tracepoints/x86_irq_vectors.c
@@ -0,0 +1,29 @@
+// SPDX-License-Identifier: LGPL-2.1
+/*
+ * trace/beauty/x86_irq_vectors.c
+ *
+ *  Copyright (C) 2019, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+ */
+
+#include "trace/beauty/beauty.h"
+
+#include "trace/beauty/generated/x86_arch_irq_vectors_array.c"
+
+static DEFINE_STRARRAY(x86_irq_vectors, "_VECTOR");
+
+static size_t x86_irq_vectors__scnprintf(unsigned long vector, char *bf, size_t size, bool show_prefix)
+{
+	return strarray__scnprintf_suffix(&strarray__x86_irq_vectors, bf, size, "%#x", show_prefix, vector);
+}
+
+size_t syscall_arg__scnprintf_x86_irq_vectors(char *bf, size_t size, struct syscall_arg *arg)
+{
+	unsigned long vector = arg->val;
+
+	return x86_irq_vectors__scnprintf(vector, bf, size, arg->show_string_prefix);
+}
+
+bool syscall_arg__strtoul_x86_irq_vectors(char *bf, size_t size, struct syscall_arg *arg __maybe_unused, u64 *ret)
+{
+	return strarray__strtoul(&strarray__x86_irq_vectors, bf, size, ret);
+}
diff --git a/tools/perf/trace/beauty/tracepoints/x86_irq_vectors.sh b/tools/perf/trace/beauty/tracepoints/x86_irq_vectors.sh
new file mode 100755
index 000000000000..f920003723b3
--- /dev/null
+++ b/tools/perf/trace/beauty/tracepoints/x86_irq_vectors.sh
@@ -0,0 +1,27 @@
+#!/bin/sh
+# SPDX-License-Identifier: LGPL-2.1
+# (C) 2019, Arnaldo Carvalho de Melo <acme@redhat.com>
+
+if [ $# -ne 1 ] ; then
+	arch_x86_header_dir=tools/arch/x86/include/asm/
+else
+	arch_x86_header_dir=$1
+fi
+
+x86_irq_vectors=${arch_x86_header_dir}/irq_vectors.h
+
+# FIRST_EXTERNAL_VECTOR is not that useful, find what is its number
+# and then replace whatever is using it and that is useful, which at
+# the time of writing of this script was: IRQ_MOVE_CLEANUP_VECTOR.
+
+first_external_regex='^#define[[:space:]]+FIRST_EXTERNAL_VECTOR[[:space:]]+(0x[[:xdigit:]]+)$'
+first_external_vector=$(egrep ${first_external_regex} ${x86_irq_vectors} | sed -r "s/${first_external_regex}/\1/g")
+
+printf "static const char *x86_irq_vectors[] = {\n"
+regex='^#define[[:space:]]+([[:alnum:]_]+)_VECTOR[[:space:]]+(0x[[:xdigit:]]+)$'
+sed -r "s/FIRST_EXTERNAL_VECTOR/${first_external_vector}/g" ${x86_irq_vectors} | \
+egrep ${regex} | \
+	sed -r "s/${regex}/\2 \1/g" | sort -n | \
+	xargs printf "\t[%s] = \"%s\",\n"
+printf "};\n\n"
+
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index bc69ca63b88e..ef1866a902c4 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -43,6 +43,7 @@
 #include <linux/string.h>
 #include <bpf/libbpf.h>
 #include <subcmd/parse-options.h>
+#include <subcmd/run-command.h>
 
 /* FIXME: For the HE_COLORSET */
 #include "ui/browser.h"
@@ -1489,44 +1490,26 @@ annotation_line__print(struct annotation_line *al, struct symbol *sym, u64 start
  * means that it's not a disassembly line so should be treated differently.
  * The ops.raw part will be parsed further according to type of the instruction.
  */
-static int symbol__parse_objdump_line(struct symbol *sym, FILE *file,
+static int symbol__parse_objdump_line(struct symbol *sym,
 				      struct annotate_args *args,
-				      int *line_nr)
+				      char *parsed_line, int *line_nr)
 {
 	struct map *map = args->ms.map;
 	struct annotation *notes = symbol__annotation(sym);
 	struct disasm_line *dl;
-	char *line = NULL, *parsed_line, *tmp, *tmp2;
-	size_t line_len;
+	char *tmp;
 	s64 line_ip, offset = -1;
 	regmatch_t match[2];
 
-	if (getline(&line, &line_len, file) < 0)
-		return -1;
-
-	if (!line)
-		return -1;
-
-	line_ip = -1;
-	parsed_line = strim(line);
-
 	/* /filename:linenr ? Save line number and ignore. */
 	if (regexec(&file_lineno, parsed_line, 2, match, 0) == 0) {
 		*line_nr = atoi(parsed_line + match[1].rm_so);
 		return 0;
 	}
 
-	tmp = skip_spaces(parsed_line);
-	if (*tmp) {
-		/*
-		 * Parse hexa addresses followed by ':'
-		 */
-		line_ip = strtoull(tmp, &tmp2, 16);
-		if (*tmp2 != ':' || tmp == tmp2 || tmp2[1] == '\0')
-			line_ip = -1;
-	}
-
-	if (line_ip != -1) {
+	/* Process hex address followed by ':'. */
+	line_ip = strtoull(parsed_line, &tmp, 16);
+	if (parsed_line != tmp && tmp[0] == ':' && tmp[1] != '\0') {
 		u64 start = map__rip_2objdump(map, sym->start),
 		    end = map__rip_2objdump(map, sym->end);
 
@@ -1534,7 +1517,7 @@ static int symbol__parse_objdump_line(struct symbol *sym, FILE *file,
 		if ((u64)line_ip < start || (u64)line_ip >= end)
 			offset = -1;
 		else
-			parsed_line = tmp2 + 1;
+			parsed_line = tmp + 1;
 	}
 
 	args->offset  = offset;
@@ -1543,7 +1526,6 @@ static int symbol__parse_objdump_line(struct symbol *sym, FILE *file,
 	args->ms.sym  = sym;
 
 	dl = disasm_line__new(args);
-	free(line);
 	(*line_nr)++;
 
 	if (dl == NULL)
@@ -1861,6 +1843,67 @@ static int symbol__disassemble_bpf(struct symbol *sym __maybe_unused,
 }
 #endif // defined(HAVE_LIBBFD_SUPPORT) && defined(HAVE_LIBBPF_SUPPORT)
 
+/*
+ * Possibly create a new version of line with tabs expanded. Returns the
+ * existing or new line, storage is updated if a new line is allocated. If
+ * allocation fails then NULL is returned.
+ */
+static char *expand_tabs(char *line, char **storage, size_t *storage_len)
+{
+	size_t i, src, dst, len, new_storage_len, num_tabs;
+	char *new_line;
+	size_t line_len = strlen(line);
+
+	for (num_tabs = 0, i = 0; i < line_len; i++)
+		if (line[i] == '\t')
+			num_tabs++;
+
+	if (num_tabs == 0)
+		return line;
+
+	/*
+	 * Space for the line and '\0', less the leading and trailing
+	 * spaces. Each tab may introduce 7 additional spaces.
+	 */
+	new_storage_len = line_len + 1 + (num_tabs * 7);
+
+	new_line = malloc(new_storage_len);
+	if (new_line == NULL) {
+		pr_err("Failure allocating memory for tab expansion\n");
+		return NULL;
+	}
+
+	/*
+	 * Copy regions starting at src and expand tabs. If there are two
+	 * adjacent tabs then 'src == i', the memcpy is of size 0 and the spaces
+	 * are inserted.
+	 */
+	for (i = 0, src = 0, dst = 0; i < line_len && num_tabs; i++) {
+		if (line[i] == '\t') {
+			len = i - src;
+			memcpy(&new_line[dst], &line[src], len);
+			dst += len;
+			new_line[dst++] = ' ';
+			while (dst % 8 != 0)
+				new_line[dst++] = ' ';
+			src = i + 1;
+			num_tabs--;
+		}
+	}
+
+	/* Expand the last region. */
+	len = line_len + 1 - src;
+	memcpy(&new_line[dst], &line[src], len);
+	dst += len;
+	new_line[dst] = '\0';
+
+	free(*storage);
+	*storage = new_line;
+	*storage_len = new_storage_len;
+	return new_line;
+
+}
+
 static int symbol__disassemble(struct symbol *sym, struct annotate_args *args)
 {
 	struct annotation_options *opts = args->options;
@@ -1872,10 +1915,19 @@ static int symbol__disassemble(struct symbol *sym, struct annotate_args *args)
 	struct kcore_extract kce;
 	bool delete_extract = false;
 	bool decomp = false;
-	int stdout_fd[2];
 	int lineno = 0;
 	int nline;
-	pid_t pid;
+	char *line;
+	size_t line_len;
+	const char *objdump_argv[] = {
+		"/bin/sh",
+		"-c",
+		NULL, /* Will be the objdump command to run. */
+		"--",
+		NULL, /* Will be the symfs path. */
+		NULL,
+	};
+	struct child_process objdump_process;
 	int err = dso__disassemble_filename(dso, symfs_filename, sizeof(symfs_filename));
 
 	if (err)
@@ -1905,7 +1957,7 @@ static int symbol__disassemble(struct symbol *sym, struct annotate_args *args)
 
 		if (dso__decompress_kmodule_path(dso, symfs_filename,
 						 tmp, sizeof(tmp)) < 0)
-			goto out;
+			return -1;
 
 		decomp = true;
 		strcpy(symfs_filename, tmp);
@@ -1914,13 +1966,13 @@ static int symbol__disassemble(struct symbol *sym, struct annotate_args *args)
 	err = asprintf(&command,
 		 "%s %s%s --start-address=0x%016" PRIx64
 		 " --stop-address=0x%016" PRIx64
-		 " -l -d %s %s -C \"$1\" 2>/dev/null|grep -v \"$1:\"|expand",
+		 " -l -d %s %s -C \"$1\"",
 		 opts->objdump_path ?: "objdump",
 		 opts->disassembler_style ? "-M " : "",
 		 opts->disassembler_style ?: "",
 		 map__rip_2objdump(map, sym->start),
 		 map__rip_2objdump(map, sym->end),
-		 opts->show_asm_raw ? "" : "--no-show-raw",
+		 opts->show_asm_raw ? "" : "--no-show-raw-insn",
 		 opts->annotate_src ? "-S" : "");
 
 	if (err < 0) {
@@ -1930,55 +1982,73 @@ static int symbol__disassemble(struct symbol *sym, struct annotate_args *args)
 
 	pr_debug("Executing: %s\n", command);
 
-	err = -1;
-	if (pipe(stdout_fd) < 0) {
-		pr_err("Failure creating the pipe to run %s\n", command);
-		goto out_free_command;
-	}
+	objdump_argv[2] = command;
+	objdump_argv[4] = symfs_filename;
 
-	pid = fork();
-	if (pid < 0) {
-		pr_err("Failure forking to run %s\n", command);
-		goto out_close_stdout;
-	}
-
-	if (pid == 0) {
-		close(stdout_fd[0]);
-		dup2(stdout_fd[1], 1);
-		close(stdout_fd[1]);
-		execl("/bin/sh", "sh", "-c", command, "--", symfs_filename,
-		      NULL);
-		perror(command);
-		exit(-1);
+	/* Create a pipe to read from for stdout */
+	memset(&objdump_process, 0, sizeof(objdump_process));
+	objdump_process.argv = objdump_argv;
+	objdump_process.out = -1;
+	if (start_command(&objdump_process)) {
+		pr_err("Failure starting to run %s\n", command);
+		err = -1;
+		goto out_free_command;
 	}
 
-	close(stdout_fd[1]);
-
-	file = fdopen(stdout_fd[0], "r");
+	file = fdopen(objdump_process.out, "r");
 	if (!file) {
 		pr_err("Failure creating FILE stream for %s\n", command);
 		/*
 		 * If we were using debug info should retry with
 		 * original binary.
 		 */
-		goto out_free_command;
+		err = -1;
+		goto out_close_stdout;
 	}
 
+	/* Storage for getline. */
+	line = NULL;
+	line_len = 0;
+
 	nline = 0;
 	while (!feof(file)) {
+		const char *match;
+		char *expanded_line;
+
+		if (getline(&line, &line_len, file) < 0 || !line)
+			break;
+
+		/* Skip lines containing "filename:" */
+		match = strstr(line, symfs_filename);
+		if (match && match[strlen(symfs_filename)] == ':')
+			continue;
+
+		expanded_line = strim(line);
+		expanded_line = expand_tabs(expanded_line, &line, &line_len);
+		if (!expanded_line)
+			break;
+
 		/*
 		 * The source code line number (lineno) needs to be kept in
 		 * across calls to symbol__parse_objdump_line(), so that it
 		 * can associate it with the instructions till the next one.
 		 * See disasm_line__new() and struct disasm_line::line_nr.
 		 */
-		if (symbol__parse_objdump_line(sym, file, args, &lineno) < 0)
+		if (symbol__parse_objdump_line(sym, args, expanded_line,
+					       &lineno) < 0)
 			break;
 		nline++;
 	}
+	free(line);
+
+	err = finish_command(&objdump_process);
+	if (err)
+		pr_err("Error running %s\n", command);
 
-	if (nline == 0)
+	if (nline == 0) {
+		err = -1;
 		pr_err("No output from %s\n", command);
+	}
 
 	/*
 	 * kallsyms does not have symbol sizes so there may a nop at the end.
@@ -1988,23 +2058,21 @@ static int symbol__disassemble(struct symbol *sym, struct annotate_args *args)
 		delete_last_nop(sym);
 
 	fclose(file);
-	err = 0;
+
+out_close_stdout:
+	close(objdump_process.out);
+
 out_free_command:
 	free(command);
-out_remove_tmp:
-	close(stdout_fd[0]);
 
+out_remove_tmp:
 	if (decomp)
 		unlink(symfs_filename);
 
 	if (delete_extract)
 		kcore_extract__delete(&kce);
-out:
-	return err;
 
-out_close_stdout:
-	close(stdout_fd[1]);
-	goto out_free_command;
+	return err;
 }
 
 static void calc_percent(struct sym_hist *sym_hist,
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 8793b4e322b0..fdce590d2278 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -21,6 +21,7 @@
 #include "../perf.h"
 #include "asm/bug.h"
 #include "bpf-event.h"
+#include "util/string2.h"
 #include <signal.h>
 #include <unistd.h>
 #include <sched.h>
@@ -598,14 +599,13 @@ static struct mmap *evlist__alloc_mmap(struct evlist *evlist,
 	int i;
 	struct mmap *map;
 
-	evlist->core.nr_mmaps = perf_cpu_map__nr(evlist->core.cpus);
-	if (perf_cpu_map__empty(evlist->core.cpus))
-		evlist->core.nr_mmaps = perf_thread_map__nr(evlist->core.threads);
 	map = zalloc(evlist->core.nr_mmaps * sizeof(struct mmap));
 	if (!map)
 		return NULL;
 
 	for (i = 0; i < evlist->core.nr_mmaps; i++) {
+		struct perf_mmap *prev = i ? &map[i - 1].core : NULL;
+
 		/*
 		 * When the perf_mmap() call is made we grab one refcount, plus
 		 * one extra to let perf_mmap__consume() get the last
@@ -615,7 +615,7 @@ static struct mmap *evlist__alloc_mmap(struct evlist *evlist,
 		 * Each PERF_EVENT_IOC_SET_OUTPUT points to this mmap and
 		 * thus does perf_mmap__get() on it.
 		 */
-		perf_mmap__init(&map[i].core, overwrite, perf_mmap__unmap_cb);
+		perf_mmap__init(&map[i].core, prev, overwrite, perf_mmap__unmap_cb);
 	}
 
 	return map;
@@ -636,19 +636,21 @@ static struct perf_mmap*
 perf_evlist__mmap_cb_get(struct perf_evlist *_evlist, bool overwrite, int idx)
 {
 	struct evlist *evlist = container_of(_evlist, struct evlist, core);
-	struct mmap *maps = evlist->mmap;
+	struct mmap *maps;
 
-	if (overwrite) {
-		maps = evlist->overwrite_mmap;
+	maps = overwrite ? evlist->overwrite_mmap : evlist->mmap;
 
-		if (!maps) {
-			maps = evlist__alloc_mmap(evlist, true);
-			if (!maps)
-				return NULL;
+	if (!maps) {
+		maps = evlist__alloc_mmap(evlist, overwrite);
+		if (!maps)
+			return NULL;
 
+		if (overwrite) {
 			evlist->overwrite_mmap = maps;
 			if (evlist->bkw_mmap_state == BKW_MMAP_NOTREADY)
 				perf_evlist__toggle_bkw_mmap(evlist, BKW_MMAP_RUNNING);
+		} else {
+			evlist->mmap = maps;
 		}
 	}
 
@@ -809,14 +811,8 @@ int evlist__mmap_ex(struct evlist *evlist, unsigned int pages,
 		.mmap = perf_evlist__mmap_cb_mmap,
 	};
 
-	if (!evlist->mmap)
-		evlist->mmap = evlist__alloc_mmap(evlist, false);
-	if (!evlist->mmap)
-		return -ENOMEM;
-
 	evlist->core.mmap_len = evlist__mmap_size(pages);
 	pr_debug("mmap size %zuB\n", evlist->core.mmap_len);
-	mp.core.mask = evlist->core.mmap_len - page_size - 1;
 
 	auxtrace_mmap_params__init(&mp.auxtrace_mp, evlist->core.mmap_len,
 				   auxtrace_pages, auxtrace_overwrite);
@@ -959,7 +955,7 @@ int perf_evlist__append_tp_filter(struct evlist *evlist, const char *filter)
 	return err;
 }
 
-static char *asprintf__tp_filter_pids(size_t npids, pid_t *pids)
+char *asprintf__tp_filter_pids(size_t npids, pid_t *pids)
 {
 	char *filter;
 	size_t i;
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index b5e2adef49de..db882f630f7e 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -2600,7 +2600,7 @@ out_enomem:
  * Print the help text for the event symbols:
  */
 void print_events(const char *event_glob, bool name_only, bool quiet_flag,
-			bool long_desc, bool details_flag)
+			bool long_desc, bool details_flag, bool deprecated)
 {
 	print_symbol_events(event_glob, PERF_TYPE_HARDWARE,
 			    event_symbols_hw, PERF_COUNT_HW_MAX, name_only);
@@ -2612,7 +2612,7 @@ void print_events(const char *event_glob, bool name_only, bool quiet_flag,
 	print_hwcache_events(event_glob, name_only);
 
 	print_pmu_events(event_glob, name_only, quiet_flag, long_desc,
-			details_flag);
+			details_flag, deprecated);
 
 	if (event_glob != NULL)
 		return;
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index 616ca1eda0eb..769e07cddaa2 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -195,7 +195,7 @@ void parse_events_evlist_error(struct parse_events_state *parse_state,
 			       int idx, const char *str);
 
 void print_events(const char *event_glob, bool name_only, bool quiet,
-		  bool long_desc, bool details_flag);
+		  bool long_desc, bool details_flag, bool deprecated);
 
 struct event_symbol {
 	const char	*symbol;
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 5608da82ad23..adbe97e941dd 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -308,7 +308,8 @@ static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name,
 				 char *long_desc, char *topic,
 				 char *unit, char *perpkg,
 				 char *metric_expr,
-				 char *metric_name)
+				 char *metric_name,
+				 char *deprecated)
 {
 	struct parse_events_term *term;
 	struct perf_pmu_alias *alias;
@@ -325,6 +326,7 @@ static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name,
 	alias->unit[0] = '\0';
 	alias->per_pkg = false;
 	alias->snapshot = false;
+	alias->deprecated = false;
 
 	ret = parse_events_terms(&alias->terms, val);
 	if (ret) {
@@ -379,6 +381,9 @@ static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name,
 	alias->per_pkg = perpkg && sscanf(perpkg, "%d", &num) == 1 && num == 1;
 	alias->str = strdup(newval);
 
+	if (deprecated)
+		alias->deprecated = true;
+
 	if (!perf_pmu_merge_alias(alias, list))
 		list_add_tail(&alias->list, list);
 
@@ -400,7 +405,7 @@ static int perf_pmu__new_alias(struct list_head *list, char *dir, char *name, FI
 	strim(buf);
 
 	return __perf_pmu__new_alias(list, dir, name, NULL, buf, NULL, NULL, NULL,
-				     NULL, NULL, NULL);
+				     NULL, NULL, NULL, NULL);
 }
 
 static inline bool pmu_alias_info_file(char *name)
@@ -787,7 +792,8 @@ new_alias:
 				(char *)pe->long_desc, (char *)pe->topic,
 				(char *)pe->unit, (char *)pe->perpkg,
 				(char *)pe->metric_expr,
-				(char *)pe->metric_name);
+				(char *)pe->metric_name,
+				(char *)pe->deprecated);
 	}
 }
 
@@ -1383,7 +1389,7 @@ static void wordwrap(char *s, int start, int max, int corr)
 }
 
 void print_pmu_events(const char *event_glob, bool name_only, bool quiet_flag,
-			bool long_desc, bool details_flag)
+			bool long_desc, bool details_flag, bool deprecated)
 {
 	struct perf_pmu *pmu;
 	struct perf_pmu_alias *alias;
@@ -1414,6 +1420,9 @@ void print_pmu_events(const char *event_glob, bool name_only, bool quiet_flag,
 				format_alias(buf, sizeof(buf), pmu, alias);
 			bool is_cpu = !strcmp(pmu->name, "cpu");
 
+			if (alias->deprecated && !deprecated)
+				continue;
+
 			if (event_glob != NULL &&
 			    !(strglobmatch_nocase(name, event_glob) ||
 			      (!is_cpu && strglobmatch_nocase(alias->name,
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index f36ade6df76d..3e8cd31a89cc 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -57,6 +57,7 @@ struct perf_pmu_alias {
 	double scale;
 	bool per_pkg;
 	bool snapshot;
+	bool deprecated;
 	char *metric_expr;
 	char *metric_name;
 };
@@ -85,7 +86,8 @@ int perf_pmu__format_parse(char *dir, struct list_head *head);
 struct perf_pmu *perf_pmu__scan(struct perf_pmu *pmu);
 
 void print_pmu_events(const char *event_glob, bool name_only, bool quiet,
-		      bool long_desc, bool details_flag);
+		      bool long_desc, bool details_flag,
+		      bool deprecated);
 bool pmu_have_event(const char *pname, const char *name);
 
 int perf_pmu__scan_file(struct perf_pmu *pmu, const char *name, const char *fmt, ...) __scanf(3, 4);
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index 15961854ba67..741f040648b5 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -539,10 +539,11 @@ static int perl_stop_script(void)
 
 static int perl_generate_script(struct tep_handle *pevent, const char *outfile)
 {
+	int i, not_first, count, nr_events;
+	struct tep_event **all_events;
 	struct tep_event *event = NULL;
 	struct tep_format_field *f;
 	char fname[PATH_MAX];
-	int not_first, count;
 	FILE *ofp;
 
 	sprintf(fname, "%s.pl", outfile);
@@ -603,8 +604,11 @@ sub print_backtrace\n\
 }\n\n\
 ");
 
+	nr_events = tep_get_events_count(pevent);
+	all_events = tep_list_events(pevent, TEP_EVENT_SORT_ID);
 
-	while ((event = trace_find_next_event(pevent, event))) {
+	for (i = 0; all_events && i < nr_events; i++) {
+		event = all_events[i];
 		fprintf(ofp, "sub %s::%s\n{\n", event->system, event->name);
 		fprintf(ofp, "\tmy (");
 
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 5d341efc3237..93c03b39cd9c 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -1687,10 +1687,11 @@ static int python_stop_script(void)
 
 static int python_generate_script(struct tep_handle *pevent, const char *outfile)
 {
+	int i, not_first, count, nr_events;
+	struct tep_event **all_events;
 	struct tep_event *event = NULL;
 	struct tep_format_field *f;
 	char fname[PATH_MAX];
-	int not_first, count;
 	FILE *ofp;
 
 	sprintf(fname, "%s.py", outfile);
@@ -1735,7 +1736,11 @@ static int python_generate_script(struct tep_handle *pevent, const char *outfile
 	fprintf(ofp, "def trace_end():\n");
 	fprintf(ofp, "\tprint(\"in trace_end\")\n\n");
 
-	while ((event = trace_find_next_event(pevent, event))) {
+	nr_events = tep_get_events_count(pevent);
+	all_events = tep_list_events(pevent, TEP_EVENT_SORT_ID);
+
+	for (i = 0; all_events && i < nr_events; i++) {
+		event = all_events[i];
 		fprintf(ofp, "def %s__%s(", event->system, event->name);
 		fprintf(ofp, "event_name, ");
 		fprintf(ofp, "context, ");
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index ebdd130557fb..6822e4ffe224 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -490,6 +490,16 @@ int create_perf_stat_counter(struct evsel *evsel,
 	if (config->identifier)
 		attr->sample_type = PERF_SAMPLE_IDENTIFIER;
 
+	if (config->all_user) {
+		attr->exclude_kernel = 1;
+		attr->exclude_user   = 0;
+	}
+
+	if (config->all_kernel) {
+		attr->exclude_kernel = 0;
+		attr->exclude_user   = 1;
+	}
+
 	/*
 	 * Disabling all counters initially, they will be enabled
 	 * either manually by us or by kernel via enable_on_exec
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index edbeb2f63e8d..081c4a5113c6 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -106,6 +106,8 @@ struct perf_stat_config {
 	bool			 big_num;
 	bool			 no_merge;
 	bool			 walltime_run_table;
+	bool			 all_kernel;
+	bool			 all_user;
 	FILE			*output;
 	unsigned int		 interval;
 	unsigned int		 timeout;
diff --git a/tools/perf/util/string2.h b/tools/perf/util/string2.h
index 708805f5573e..73df616ced43 100644
--- a/tools/perf/util/string2.h
+++ b/tools/perf/util/string2.h
@@ -4,6 +4,7 @@
 
 #include <linux/string.h>
 #include <linux/types.h>
+#include <sys/types.h> // pid_t
 #include <stddef.h>
 #include <string.h>
 
@@ -32,6 +33,8 @@ static inline char *asprintf_expr_not_in_ints(const char *var, size_t nints, int
 	return asprintf_expr_inout_ints(var, false, nints, ints);
 }
 
+char *asprintf__tp_filter_pids(size_t npids, pid_t *pids);
+
 char *strpbrk_esc(char *str, const char *stopset);
 char *strdup_esc(const char *str);
 
diff --git a/tools/perf/util/time-utils.c b/tools/perf/util/time-utils.c
index 9796a2e43f67..302443921681 100644
--- a/tools/perf/util/time-utils.c
+++ b/tools/perf/util/time-utils.c
@@ -458,10 +458,11 @@ bool perf_time__ranges_skip_sample(struct perf_time_interval *ptime_buf,
 	return true;
 }
 
-int perf_time__parse_for_ranges(const char *time_str,
+int perf_time__parse_for_ranges_reltime(const char *time_str,
 				struct perf_session *session,
 				struct perf_time_interval **ranges,
-				int *range_size, int *range_num)
+				int *range_size, int *range_num,
+				bool reltime)
 {
 	bool has_percent = strchr(time_str, '%');
 	struct perf_time_interval *ptime_range;
@@ -471,7 +472,7 @@ int perf_time__parse_for_ranges(const char *time_str,
 	if (!ptime_range)
 		return -ENOMEM;
 
-	if (has_percent) {
+	if (has_percent || reltime) {
 		if (session->evlist->first_sample_time == 0 &&
 		    session->evlist->last_sample_time == 0) {
 			pr_err("HINT: no first/last sample time found in perf data.\n"
@@ -479,7 +480,9 @@ int perf_time__parse_for_ranges(const char *time_str,
 			       "(if '--buildid-all' is enabled, please set '--timestamp-boundary').\n");
 			goto error;
 		}
+	}
 
+	if (has_percent) {
 		num = perf_time__percent_parse_str(
 				ptime_range, size,
 				time_str,
@@ -492,6 +495,15 @@ int perf_time__parse_for_ranges(const char *time_str,
 	if (num < 0)
 		goto error_invalid;
 
+	if (reltime) {
+		int i;
+
+		for (i = 0; i < num; i++) {
+			ptime_range[i].start += session->evlist->first_sample_time;
+			ptime_range[i].end += session->evlist->first_sample_time;
+		}
+	}
+
 	*range_size = size;
 	*range_num = num;
 	*ranges = ptime_range;
@@ -504,6 +516,15 @@ error:
 	return ret;
 }
 
+int perf_time__parse_for_ranges(const char *time_str,
+				struct perf_session *session,
+				struct perf_time_interval **ranges,
+				int *range_size, int *range_num)
+{
+	return perf_time__parse_for_ranges_reltime(time_str, session, ranges,
+					range_size, range_num, false);
+}
+
 int timestamp__scnprintf_usec(u64 timestamp, char *buf, size_t sz)
 {
 	u64  sec = timestamp / NSEC_PER_SEC;
diff --git a/tools/perf/util/time-utils.h b/tools/perf/util/time-utils.h
index 4f42988eb2f7..1142b0bddd5e 100644
--- a/tools/perf/util/time-utils.h
+++ b/tools/perf/util/time-utils.h
@@ -26,6 +26,11 @@ bool perf_time__ranges_skip_sample(struct perf_time_interval *ptime_buf,
 
 struct perf_session;
 
+int perf_time__parse_for_ranges_reltime(const char *str, struct perf_session *session,
+				struct perf_time_interval **ranges,
+				int *range_size, int *range_num,
+				bool reltime);
+
 int perf_time__parse_for_ranges(const char *str, struct perf_session *session,
 				struct perf_time_interval **ranges,
 				int *range_size, int *range_num);
diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c
index 5d6bfc70b210..9634f0ae57be 100644
--- a/tools/perf/util/trace-event-parse.c
+++ b/tools/perf/util/trace-event-parse.c
@@ -173,37 +173,6 @@ int parse_event_file(struct tep_handle *pevent,
 	return tep_parse_event(pevent, buf, size, sys);
 }
 
-struct tep_event *trace_find_next_event(struct tep_handle *pevent,
-					struct tep_event *event)
-{
-	static int idx;
-	int events_count;
-	struct tep_event *all_events;
-
-	all_events = tep_get_first_event(pevent);
-	events_count = tep_get_events_count(pevent);
-	if (!pevent || !all_events || events_count < 1)
-		return NULL;
-
-	if (!event) {
-		idx = 0;
-		return all_events;
-	}
-
-	if (idx < events_count && event == (all_events + idx)) {
-		idx++;
-		if (idx == events_count)
-			return NULL;
-		return (all_events + idx);
-	}
-
-	for (idx = 1; idx < events_count; idx++) {
-		if (event == (all_events + (idx - 1)))
-			return (all_events + idx);
-	}
-	return NULL;
-}
-
 struct flag {
 	const char *name;
 	unsigned long long value;
diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h
index 2e158387b3d7..72fdf2a3577c 100644
--- a/tools/perf/util/trace-event.h
+++ b/tools/perf/util/trace-event.h
@@ -47,8 +47,6 @@ void parse_saved_cmdline(struct tep_handle *pevent, char *file, unsigned int siz
 
 ssize_t trace_report(int fd, struct trace_event *tevent, bool repipe);
 
-struct tep_event *trace_find_next_event(struct tep_handle *pevent,
-					struct tep_event *event);
 unsigned long long read_size(struct tep_event *event, void *ptr, int size);
 unsigned long long eval_flag(const char *flag);