Merge branch 'for-5.7/glorious' into for-linus

- report descriptor fix for Glorious PC Gaming Race device from Samuel Čavoj

47 files changed, 373 insertions, 331 deletions

diff --git a/tools/perf/Documentation/perf-config.txt b/tools/perf/Documentation/perf-config.txt
index c4dd23c4b478..8ead55593984 100644
--- a/tools/perf/Documentation/perf-config.txt
+++ b/tools/perf/Documentation/perf-config.txt
@@ -239,7 +239,6 @@ buildid.*::
 		set buildid.dir to /dev/null. The default is $HOME/.debug
 
 annotate.*::
-	These options work only for TUI.
 	These are in control of addresses, jump function, source code
 	in lines of assembly code from a specific program.
 
@@ -269,6 +268,8 @@ annotate.*::
 		│        mov    (%rdi),%rdx
 		│              return n;
 
+		This option works with tui, stdio2 browsers.
+
         annotate.use_offset::
 		Basing on a first address of a loaded function, offset can be used.
 		Instead of using original addresses of assembly code,
@@ -287,6 +288,8 @@ annotate.*::
 
 		             368:│  mov    0x8(%r14),%rdi
 
+		This option works with tui, stdio2 browsers.
+
 	annotate.jump_arrows::
 		There can be jump instruction among assembly code.
 		Depending on a boolean value of jump_arrows,
@@ -306,6 +309,8 @@ annotate.*::
 		│1330:   mov    %r15,%r10
 		│1333:   cmp    %r15,%r14
 
+		This option works with tui browser.
+
         annotate.show_linenr::
 		When showing source code if this option is 'true',
 		line numbers are printed as below.
@@ -325,6 +330,8 @@ annotate.*::
 		│                     array++;
 		│             }
 
+		This option works with tui, stdio2 browsers.
+
         annotate.show_nr_jumps::
 		Let's see a part of assembly code.
 
@@ -335,6 +342,8 @@ annotate.*::
 
 		│1 1382:   movb   $0x1,-0x270(%rbp)
 
+		This option works with tui, stdio2 browsers.
+
         annotate.show_total_period::
 		To compare two records on an instruction base, with this option
 		provided, display total number of samples that belong to a line
@@ -348,11 +357,30 @@ annotate.*::
 
 		99.93 │      mov    %eax,%eax
 
+		This option works with tui, stdio2, stdio browsers.
+
+	annotate.show_nr_samples::
+		By default perf annotate shows percentage of samples. This option
+		can be used to print absolute number of samples. Ex, when set as
+		false:
+
+		Percent│
+		 74.03 │      mov    %fs:0x28,%rax
+
+		When set as true:
+
+		Samples│
+		     6 │      mov    %fs:0x28,%rax
+
+		This option works with tui, stdio2, stdio browsers.
+
 	annotate.offset_level::
 		Default is '1', meaning just jump targets will have offsets show right beside
 		the instruction. When set to '2' 'call' instructions will also have its offsets
 		shown, 3 or higher will show offsets for all instructions.
 
+		This option works with tui, stdio2 browsers.
+
 hist.*::
 	hist.percentage::
 		This option control the way to calculate overhead of filtered entries -
@@ -490,6 +518,12 @@ top.*::
 		column by default.
 		The default is 'true'.
 
+	top.call-graph::
+		This is identical to 'call-graph.record-mode', except it is
+		applicable only for 'top' subcommand. This option ONLY setup
+		the unwind method. To enable 'perf top' to actually use it,
+		the command line option -g must be specified.
+
 man.*::
 	man.viewer::
 		This option can assign a tool to view manual pages when 'help'
@@ -517,6 +551,16 @@ record.*::
 		But if this option is 'no-cache', it will not update the build-id cache.
 		'skip' skips post-processing and does not update the cache.
 
+	record.call-graph::
+		This is identical to 'call-graph.record-mode', except it is
+		applicable only for 'record' subcommand. This option ONLY setup
+		the unwind method. To enable 'perf record' to actually use it,
+		the command line option -g must be specified.
+
+	record.aio::
+		Use 'n' control blocks in asynchronous (Posix AIO) trace writing
+		mode ('n' default: 1, max: 4).
+
 diff.*::
 	diff.order::
 		This option sets the number of columns to sort the result.
@@ -566,6 +610,11 @@ trace.*::
 		"libbeauty", the default, to use the same argument beautifiers used in the
 		strace-like sys_enter+sys_exit lines.
 
+ftrace.*::
+	ftrace.tracer::
+		Can be used to select the default tracer. Possible values are
+		'function' and 'function_graph'.
+
 llvm.*::
 	llvm.clang-path::
 		Path to clang. If omit, search it from $PATH.
@@ -610,6 +659,29 @@ scripts.*::
 	The script gets the same options passed as a full perf script,
 	in particular -i perfdata file, --cpu, --tid
 
+convert.*::
+
+	convert.queue-size::
+		Limit the size of ordered_events queue, so we could control
+		allocation size of perf data files without proper finished
+		round events.
+
+intel-pt.*::
+
+	intel-pt.cache-divisor::
+
+	intel-pt.mispred-all::
+		If set, Intel PT decoder will set the mispred flag on all
+		branches.
+
+auxtrace.*::
+
+	auxtrace.dumpdir::
+		s390 only. The directory to save the auxiliary trace buffer
+		can be changed using this option. Ex, auxtrace.dumpdir=/tmp.
+		If the directory does not exist or has the wrong file type,
+		the current directory is used.
+
 SEE ALSO
 --------
 linkperf:perf[1]
diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c
index 2898cfdf8fe1..941f814820b8 100644
--- a/tools/perf/arch/arm/util/cs-etm.c
+++ b/tools/perf/arch/arm/util/cs-etm.c
@@ -858,21 +858,6 @@ static void cs_etm_recording_free(struct auxtrace_record *itr)
 	free(ptr);
 }
 
-static int cs_etm_read_finish(struct auxtrace_record *itr, int idx)
-{
-	struct cs_etm_recording *ptr =
-			container_of(itr, struct cs_etm_recording, itr);
-	struct evsel *evsel;
-
-	evlist__for_each_entry(ptr->evlist, evsel) {
-		if (evsel->core.attr.type == ptr->cs_etm_pmu->type)
-			return perf_evlist__enable_event_idx(ptr->evlist,
-							     evsel, idx);
-	}
-
-	return -EINVAL;
-}
-
 struct auxtrace_record *cs_etm_record_init(int *err)
 {
 	struct perf_pmu *cs_etm_pmu;
@@ -892,6 +877,7 @@ struct auxtrace_record *cs_etm_record_init(int *err)
 	}
 
 	ptr->cs_etm_pmu			= cs_etm_pmu;
+	ptr->itr.pmu			= cs_etm_pmu;
 	ptr->itr.parse_snapshot_options	= cs_etm_parse_snapshot_options;
 	ptr->itr.recording_options	= cs_etm_recording_options;
 	ptr->itr.info_priv_size		= cs_etm_info_priv_size;
@@ -901,7 +887,7 @@ struct auxtrace_record *cs_etm_record_init(int *err)
 	ptr->itr.snapshot_finish	= cs_etm_snapshot_finish;
 	ptr->itr.reference		= cs_etm_reference;
 	ptr->itr.free			= cs_etm_recording_free;
-	ptr->itr.read_finish		= cs_etm_read_finish;
+	ptr->itr.read_finish		= auxtrace_record__read_finish;
 
 	*err = 0;
 	return &ptr->itr;
diff --git a/tools/perf/arch/arm64/util/arm-spe.c b/tools/perf/arch/arm64/util/arm-spe.c
index eba6541ec0f1..27653be24447 100644
--- a/tools/perf/arch/arm64/util/arm-spe.c
+++ b/tools/perf/arch/arm64/util/arm-spe.c
@@ -11,17 +11,17 @@
 #include <linux/zalloc.h>
 #include <time.h>
 
-#include "../../util/cpumap.h"
-#include "../../util/event.h"
-#include "../../util/evsel.h"
-#include "../../util/evlist.h"
-#include "../../util/session.h"
+#include "../../../util/cpumap.h"
+#include "../../../util/event.h"
+#include "../../../util/evsel.h"
+#include "../../../util/evlist.h"
+#include "../../../util/session.h"
 #include <internal/lib.h> // page_size
-#include "../../util/pmu.h"
-#include "../../util/debug.h"
-#include "../../util/auxtrace.h"
-#include "../../util/record.h"
-#include "../../util/arm-spe.h"
+#include "../../../util/pmu.h"
+#include "../../../util/debug.h"
+#include "../../../util/auxtrace.h"
+#include "../../../util/record.h"
+#include "../../../util/arm-spe.h"
 
 #define KiB(x) ((x) * 1024)
 #define MiB(x) ((x) * 1024 * 1024)
@@ -158,20 +158,6 @@ static void arm_spe_recording_free(struct auxtrace_record *itr)
 	free(sper);
 }
 
-static int arm_spe_read_finish(struct auxtrace_record *itr, int idx)
-{
-	struct arm_spe_recording *sper =
-			container_of(itr, struct arm_spe_recording, itr);
-	struct evsel *evsel;
-
-	evlist__for_each_entry(sper->evlist, evsel) {
-		if (evsel->core.attr.type == sper->arm_spe_pmu->type)
-			return perf_evlist__enable_event_idx(sper->evlist,
-							     evsel, idx);
-	}
-	return -EINVAL;
-}
-
 struct auxtrace_record *arm_spe_recording_init(int *err,
 					       struct perf_pmu *arm_spe_pmu)
 {
@@ -189,12 +175,13 @@ struct auxtrace_record *arm_spe_recording_init(int *err,
 	}
 
 	sper->arm_spe_pmu = arm_spe_pmu;
+	sper->itr.pmu = arm_spe_pmu;
 	sper->itr.recording_options = arm_spe_recording_options;
 	sper->itr.info_priv_size = arm_spe_info_priv_size;
 	sper->itr.info_fill = arm_spe_info_fill;
 	sper->itr.free = arm_spe_recording_free;
 	sper->itr.reference = arm_spe_reference;
-	sper->itr.read_finish = arm_spe_read_finish;
+	sper->itr.read_finish = auxtrace_record__read_finish;
 	sper->itr.alignment = 0;
 
 	*err = 0;
diff --git a/tools/perf/arch/arm64/util/perf_regs.c b/tools/perf/arch/arm64/util/perf_regs.c
index 2864e2e3776d..2833e101a7c6 100644
--- a/tools/perf/arch/arm64/util/perf_regs.c
+++ b/tools/perf/arch/arm64/util/perf_regs.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-#include "../../util/perf_regs.h"
+#include "../../../util/perf_regs.h"
 
 const struct sample_reg sample_reg_masks[] = {
 	SMPL_REG_END
diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
index 43f736ed47f2..35b61bfc1b1a 100644
--- a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
@@ -517,3 +517,5 @@
 433	common	fspick				sys_fspick
 434	common	pidfd_open			sys_pidfd_open
 435	nospu	clone3				ppc_clone3
+437	common	openat2				sys_openat2
+438	common	pidfd_getfd			sys_pidfd_getfd
diff --git a/tools/perf/arch/powerpc/util/perf_regs.c b/tools/perf/arch/powerpc/util/perf_regs.c
index e9c436eeffc9..0a5242900248 100644
--- a/tools/perf/arch/powerpc/util/perf_regs.c
+++ b/tools/perf/arch/powerpc/util/perf_regs.c
@@ -4,8 +4,8 @@
 #include <regex.h>
 #include <linux/zalloc.h>
 
-#include "../../util/perf_regs.h"
-#include "../../util/debug.h"
+#include "../../../util/perf_regs.h"
+#include "../../../util/debug.h"
 
 #include <linux/kernel.h>
 
diff --git a/tools/perf/arch/x86/util/auxtrace.c b/tools/perf/arch/x86/util/auxtrace.c
index 7abc9fd4cbec..3da506e13f49 100644
--- a/tools/perf/arch/x86/util/auxtrace.c
+++ b/tools/perf/arch/x86/util/auxtrace.c
@@ -7,13 +7,13 @@
 #include <errno.h>
 #include <stdbool.h>
 
-#include "../../util/header.h"
-#include "../../util/debug.h"
-#include "../../util/pmu.h"
-#include "../../util/auxtrace.h"
-#include "../../util/intel-pt.h"
-#include "../../util/intel-bts.h"
-#include "../../util/evlist.h"
+#include "../../../util/header.h"
+#include "../../../util/debug.h"
+#include "../../../util/pmu.h"
+#include "../../../util/auxtrace.h"
+#include "../../../util/intel-pt.h"
+#include "../../../util/intel-bts.h"
+#include "../../../util/evlist.h"
 
 static
 struct auxtrace_record *auxtrace_record__init_intel(struct evlist *evlist,
diff --git a/tools/perf/arch/x86/util/event.c b/tools/perf/arch/x86/util/event.c
index ac45015cc6ba..047dc00eafa6 100644
--- a/tools/perf/arch/x86/util/event.c
+++ b/tools/perf/arch/x86/util/event.c
@@ -3,12 +3,12 @@
 #include <linux/string.h>
 #include <linux/zalloc.h>
 
-#include "../../util/event.h"
-#include "../../util/synthetic-events.h"
-#include "../../util/machine.h"
-#include "../../util/tool.h"
-#include "../../util/map.h"
-#include "../../util/debug.h"
+#include "../../../util/event.h"
+#include "../../../util/synthetic-events.h"
+#include "../../../util/machine.h"
+#include "../../../util/tool.h"
+#include "../../../util/map.h"
+#include "../../../util/debug.h"
 
 #if defined(__x86_64__)
 
diff --git a/tools/perf/arch/x86/util/header.c b/tools/perf/arch/x86/util/header.c
index aa6deb463bf3..578c8c568ffd 100644
--- a/tools/perf/arch/x86/util/header.c
+++ b/tools/perf/arch/x86/util/header.c
@@ -7,8 +7,8 @@
 #include <string.h>
 #include <regex.h>
 
-#include "../../util/debug.h"
-#include "../../util/header.h"
+#include "../../../util/debug.h"
+#include "../../../util/header.h"
 
 static inline void
 cpuid(unsigned int op, unsigned int *a, unsigned int *b, unsigned int *c,
diff --git a/tools/perf/arch/x86/util/intel-bts.c b/tools/perf/arch/x86/util/intel-bts.c
index 27d9e214d068..09f93800bffd 100644
--- a/tools/perf/arch/x86/util/intel-bts.c
+++ b/tools/perf/arch/x86/util/intel-bts.c
@@ -11,18 +11,18 @@
 #include <linux/log2.h>
 #include <linux/zalloc.h>
 
-#include "../../util/cpumap.h"
-#include "../../util/event.h"
-#include "../../util/evsel.h"
-#include "../../util/evlist.h"
-#include "../../util/mmap.h"
-#include "../../util/session.h"
-#include "../../util/pmu.h"
-#include "../../util/debug.h"
-#include "../../util/record.h"
-#include "../../util/tsc.h"
-#include "../../util/auxtrace.h"
-#include "../../util/intel-bts.h"
+#include "../../../util/cpumap.h"
+#include "../../../util/event.h"
+#include "../../../util/evsel.h"
+#include "../../../util/evlist.h"
+#include "../../../util/mmap.h"
+#include "../../../util/session.h"
+#include "../../../util/pmu.h"
+#include "../../../util/debug.h"
+#include "../../../util/record.h"
+#include "../../../util/tsc.h"
+#include "../../../util/auxtrace.h"
+#include "../../../util/intel-bts.h"
 #include <internal/lib.h> // page_size
 
 #define KiB(x) ((x) * 1024)
@@ -413,20 +413,6 @@ out_err:
 	return err;
 }
 
-static int intel_bts_read_finish(struct auxtrace_record *itr, int idx)
-{
-	struct intel_bts_recording *btsr =
-			container_of(itr, struct intel_bts_recording, itr);
-	struct evsel *evsel;
-
-	evlist__for_each_entry(btsr->evlist, evsel) {
-		if (evsel->core.attr.type == btsr->intel_bts_pmu->type)
-			return perf_evlist__enable_event_idx(btsr->evlist,
-							     evsel, idx);
-	}
-	return -EINVAL;
-}
-
 struct auxtrace_record *intel_bts_recording_init(int *err)
 {
 	struct perf_pmu *intel_bts_pmu = perf_pmu__find(INTEL_BTS_PMU_NAME);
@@ -447,6 +433,7 @@ struct auxtrace_record *intel_bts_recording_init(int *err)
 	}
 
 	btsr->intel_bts_pmu = intel_bts_pmu;
+	btsr->itr.pmu = intel_bts_pmu;
 	btsr->itr.recording_options = intel_bts_recording_options;
 	btsr->itr.info_priv_size = intel_bts_info_priv_size;
 	btsr->itr.info_fill = intel_bts_info_fill;
@@ -456,7 +443,7 @@ struct auxtrace_record *intel_bts_recording_init(int *err)
 	btsr->itr.find_snapshot = intel_bts_find_snapshot;
 	btsr->itr.parse_snapshot_options = intel_bts_parse_snapshot_options;
 	btsr->itr.reference = intel_bts_reference;
-	btsr->itr.read_finish = intel_bts_read_finish;
+	btsr->itr.read_finish = auxtrace_record__read_finish;
 	btsr->itr.alignment = sizeof(struct branch);
 	return &btsr->itr;
 }
diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c
index 20df442fdf36..1643aed8c4c8 100644
--- a/tools/perf/arch/x86/util/intel-pt.c
+++ b/tools/perf/arch/x86/util/intel-pt.c
@@ -13,23 +13,23 @@
 #include <linux/zalloc.h>
 #include <cpuid.h>
 
-#include "../../util/session.h"
-#include "../../util/event.h"
-#include "../../util/evlist.h"
-#include "../../util/evsel.h"
-#include "../../util/evsel_config.h"
-#include "../../util/cpumap.h"
-#include "../../util/mmap.h"
+#include "../../../util/session.h"
+#include "../../../util/event.h"
+#include "../../../util/evlist.h"
+#include "../../../util/evsel.h"
+#include "../../../util/evsel_config.h"
+#include "../../../util/cpumap.h"
+#include "../../../util/mmap.h"
 #include <subcmd/parse-options.h>
-#include "../../util/parse-events.h"
-#include "../../util/pmu.h"
-#include "../../util/debug.h"
-#include "../../util/auxtrace.h"
-#include "../../util/record.h"
-#include "../../util/target.h"
-#include "../../util/tsc.h"
+#include "../../../util/parse-events.h"
+#include "../../../util/pmu.h"
+#include "../../../util/debug.h"
+#include "../../../util/auxtrace.h"
+#include "../../../util/record.h"
+#include "../../../util/target.h"
+#include "../../../util/tsc.h"
 #include <internal/lib.h> // page_size
-#include "../../util/intel-pt.h"
+#include "../../../util/intel-pt.h"
 
 #define KiB(x) ((x) * 1024)
 #define MiB(x) ((x) * 1024 * 1024)
@@ -1166,20 +1166,6 @@ static u64 intel_pt_reference(struct auxtrace_record *itr __maybe_unused)
 	return rdtsc();
 }
 
-static int intel_pt_read_finish(struct auxtrace_record *itr, int idx)
-{
-	struct intel_pt_recording *ptr =
-			container_of(itr, struct intel_pt_recording, itr);
-	struct evsel *evsel;
-
-	evlist__for_each_entry(ptr->evlist, evsel) {
-		if (evsel->core.attr.type == ptr->intel_pt_pmu->type)
-			return perf_evlist__enable_event_idx(ptr->evlist, evsel,
-							     idx);
-	}
-	return -EINVAL;
-}
-
 struct auxtrace_record *intel_pt_recording_init(int *err)
 {
 	struct perf_pmu *intel_pt_pmu = perf_pmu__find(INTEL_PT_PMU_NAME);
@@ -1200,6 +1186,7 @@ struct auxtrace_record *intel_pt_recording_init(int *err)
 	}
 
 	ptr->intel_pt_pmu = intel_pt_pmu;
+	ptr->itr.pmu = intel_pt_pmu;
 	ptr->itr.recording_options = intel_pt_recording_options;
 	ptr->itr.info_priv_size = intel_pt_info_priv_size;
 	ptr->itr.info_fill = intel_pt_info_fill;
@@ -1209,7 +1196,7 @@ struct auxtrace_record *intel_pt_recording_init(int *err)
 	ptr->itr.find_snapshot = intel_pt_find_snapshot;
 	ptr->itr.parse_snapshot_options = intel_pt_parse_snapshot_options;
 	ptr->itr.reference = intel_pt_reference;
-	ptr->itr.read_finish = intel_pt_read_finish;
+	ptr->itr.read_finish = auxtrace_record__read_finish;
 	/*
 	 * Decoding starts at a PSB packet. Minimum PSB period is 2K so 4K
 	 * should give at least 1 PSB per sample.
diff --git a/tools/perf/arch/x86/util/machine.c b/tools/perf/arch/x86/util/machine.c
index e17e080e76f4..31679c35d493 100644
--- a/tools/perf/arch/x86/util/machine.c
+++ b/tools/perf/arch/x86/util/machine.c
@@ -5,9 +5,9 @@
 #include <stdlib.h>
 
 #include <internal/lib.h> // page_size
-#include "../../util/machine.h"
-#include "../../util/map.h"
-#include "../../util/symbol.h"
+#include "../../../util/machine.h"
+#include "../../../util/map.h"
+#include "../../../util/symbol.h"
 #include <linux/ctype.h>
 
 #include <symbol/kallsyms.h>
diff --git a/tools/perf/arch/x86/util/perf_regs.c b/tools/perf/arch/x86/util/perf_regs.c
index c218b83e063b..fca81b39b09f 100644
--- a/tools/perf/arch/x86/util/perf_regs.c
+++ b/tools/perf/arch/x86/util/perf_regs.c
@@ -5,10 +5,10 @@
 #include <linux/kernel.h>
 #include <linux/zalloc.h>
 
-#include "../../perf-sys.h"
-#include "../../util/perf_regs.h"
-#include "../../util/debug.h"
-#include "../../util/event.h"
+#include "../../../perf-sys.h"
+#include "../../../util/perf_regs.h"
+#include "../../../util/debug.h"
+#include "../../../util/event.h"
 
 const struct sample_reg sample_reg_masks[] = {
 	SMPL_REG(AX, PERF_REG_X86_AX),
diff --git a/tools/perf/arch/x86/util/pmu.c b/tools/perf/arch/x86/util/pmu.c
index e33ef5bc31c5..d48d608517fd 100644
--- a/tools/perf/arch/x86/util/pmu.c
+++ b/tools/perf/arch/x86/util/pmu.c
@@ -4,9 +4,9 @@
 #include <linux/stddef.h>
 #include <linux/perf_event.h>
 
-#include "../../util/intel-pt.h"
-#include "../../util/intel-bts.h"
-#include "../../util/pmu.h"
+#include "../../../util/intel-pt.h"
+#include "../../../util/intel-bts.h"
+#include "../../../util/pmu.h"
 
 struct perf_event_attr *perf_pmu__get_default_config(struct perf_pmu *pmu __maybe_unused)
 {
diff --git a/tools/perf/bench/bench.h b/tools/perf/bench/bench.h
index fddb3ced9db6..4aa6de1aa67d 100644
--- a/tools/perf/bench/bench.h
+++ b/tools/perf/bench/bench.h
@@ -2,6 +2,10 @@
 #ifndef BENCH_H
 #define BENCH_H
 
+#include <sys/time.h>
+
+extern struct timeval bench__start, bench__end, bench__runtime;
+
 /*
  * The madvise transparent hugepage constants were added in glibc
  * 2.13. For compatibility with older versions of glibc, define these
diff --git a/tools/perf/bench/epoll-ctl.c b/tools/perf/bench/epoll-ctl.c
index bb617e568841..cadc18d42aa4 100644
--- a/tools/perf/bench/epoll-ctl.c
+++ b/tools/perf/bench/epoll-ctl.c
@@ -35,7 +35,6 @@
 
 static unsigned int nthreads = 0;
 static unsigned int nsecs    = 8;
-struct timeval start, end, runtime;
 static bool done, __verbose, randomize;
 
 /*
@@ -94,8 +93,8 @@ static void toggle_done(int sig __maybe_unused,
 {
 	/* inform all threads that we're done for the day */
 	done = true;
-	gettimeofday(&end, NULL);
-	timersub(&end, &start, &runtime);
+	gettimeofday(&bench__end, NULL);
+	timersub(&bench__end, &bench__start, &bench__runtime);
 }
 
 static void nest_epollfd(void)
@@ -313,6 +312,7 @@ int bench_epoll_ctl(int argc, const char **argv)
 		exit(EXIT_FAILURE);
 	}
 
+	memset(&act, 0, sizeof(act));
 	sigfillset(&act.sa_mask);
 	act.sa_sigaction = toggle_done;
 	sigaction(SIGINT, &act, NULL);
@@ -361,7 +361,7 @@ int bench_epoll_ctl(int argc, const char **argv)
 
 	threads_starting = nthreads;
 
-	gettimeofday(&start, NULL);
+	gettimeofday(&bench__start, NULL);
 
 	do_threads(worker, cpu);
 
diff --git a/tools/perf/bench/epoll-wait.c b/tools/perf/bench/epoll-wait.c
index 7af694437f4e..f938c585d512 100644
--- a/tools/perf/bench/epoll-wait.c
+++ b/tools/perf/bench/epoll-wait.c
@@ -90,7 +90,6 @@
 
 static unsigned int nthreads = 0;
 static unsigned int nsecs    = 8;
-struct timeval start, end, runtime;
 static bool wdone, done, __verbose, randomize, nonblocking;
 
 /*
@@ -276,8 +275,8 @@ static void toggle_done(int sig __maybe_unused,
 {
 	/* inform all threads that we're done for the day */
 	done = true;
-	gettimeofday(&end, NULL);
-	timersub(&end, &start, &runtime);
+	gettimeofday(&bench__end, NULL);
+	timersub(&bench__end, &bench__start, &bench__runtime);
 }
 
 static void print_summary(void)
@@ -287,7 +286,7 @@ static void print_summary(void)
 
 	printf("\nAveraged %ld operations/sec (+- %.2f%%), total secs = %d\n",
 	       avg, rel_stddev_stats(stddev, avg),
-	       (int) runtime.tv_sec);
+	       (int)bench__runtime.tv_sec);
 }
 
 static int do_threads(struct worker *worker, struct perf_cpu_map *cpu)
@@ -427,6 +426,7 @@ int bench_epoll_wait(int argc, const char **argv)
 		exit(EXIT_FAILURE);
 	}
 
+	memset(&act, 0, sizeof(act));
 	sigfillset(&act.sa_mask);
 	act.sa_sigaction = toggle_done;
 	sigaction(SIGINT, &act, NULL);
@@ -479,7 +479,7 @@ int bench_epoll_wait(int argc, const char **argv)
 
 	threads_starting = nthreads;
 
-	gettimeofday(&start, NULL);
+	gettimeofday(&bench__start, NULL);
 
 	do_threads(worker, cpu);
 
@@ -519,7 +519,7 @@ int bench_epoll_wait(int argc, const char **argv)
 		qsort(worker, nthreads, sizeof(struct worker), cmpworker);
 
 	for (i = 0; i < nthreads; i++) {
-		unsigned long t = worker[i].ops/runtime.tv_sec;
+		unsigned long t = worker[i].ops / bench__runtime.tv_sec;
 
 		update_stats(&throughput_stats, t);
 
diff --git a/tools/perf/bench/futex-hash.c b/tools/perf/bench/futex-hash.c
index 8ba0c3330a9a..65eebe06c04d 100644
--- a/tools/perf/bench/futex-hash.c
+++ b/tools/perf/bench/futex-hash.c
@@ -37,7 +37,7 @@ static unsigned int nfutexes = 1024;
 static bool fshared = false, done = false, silent = false;
 static int futex_flag = 0;
 
-struct timeval start, end, runtime;
+struct timeval bench__start, bench__end, bench__runtime;
 static pthread_mutex_t thread_lock;
 static unsigned int threads_starting;
 static struct stats throughput_stats;
@@ -103,8 +103,8 @@ static void toggle_done(int sig __maybe_unused,
 {
 	/* inform all threads that we're done for the day */
 	done = true;
-	gettimeofday(&end, NULL);
-	timersub(&end, &start, &runtime);
+	gettimeofday(&bench__end, NULL);
+	timersub(&bench__end, &bench__start, &bench__runtime);
 }
 
 static void print_summary(void)
@@ -114,7 +114,7 @@ static void print_summary(void)
 
 	printf("%sAveraged %ld operations/sec (+- %.2f%%), total secs = %d\n",
 	       !silent ? "\n" : "", avg, rel_stddev_stats(stddev, avg),
-	       (int) runtime.tv_sec);
+	       (int)bench__runtime.tv_sec);
 }
 
 int bench_futex_hash(int argc, const char **argv)
@@ -137,6 +137,7 @@ int bench_futex_hash(int argc, const char **argv)
 	if (!cpu)
 		goto errmem;
 
+	memset(&act, 0, sizeof(act));
 	sigfillset(&act.sa_mask);
 	act.sa_sigaction = toggle_done;
 	sigaction(SIGINT, &act, NULL);
@@ -161,7 +162,7 @@ int bench_futex_hash(int argc, const char **argv)
 
 	threads_starting = nthreads;
 	pthread_attr_init(&thread_attr);
-	gettimeofday(&start, NULL);
+	gettimeofday(&bench__start, NULL);
 	for (i = 0; i < nthreads; i++) {
 		worker[i].tid = i;
 		worker[i].futex = calloc(nfutexes, sizeof(*worker[i].futex));
@@ -204,7 +205,7 @@ int bench_futex_hash(int argc, const char **argv)
 	pthread_mutex_destroy(&thread_lock);
 
 	for (i = 0; i < nthreads; i++) {
-		unsigned long t = worker[i].ops/runtime.tv_sec;
+		unsigned long t = worker[i].ops / bench__runtime.tv_sec;
 		update_stats(&throughput_stats, t);
 		if (!silent) {
 			if (nfutexes == 1)
diff --git a/tools/perf/bench/futex-lock-pi.c b/tools/perf/bench/futex-lock-pi.c
index d0cae8125423..89fd8f325f38 100644
--- a/tools/perf/bench/futex-lock-pi.c
+++ b/tools/perf/bench/futex-lock-pi.c
@@ -37,7 +37,6 @@ static bool silent = false, multi = false;
 static bool done = false, fshared = false;
 static unsigned int nthreads = 0;
 static int futex_flag = 0;
-struct timeval start, end, runtime;
 static pthread_mutex_t thread_lock;
 static unsigned int threads_starting;
 static struct stats throughput_stats;
@@ -64,7 +63,7 @@ static void print_summary(void)
 
 	printf("%sAveraged %ld operations/sec (+- %.2f%%), total secs = %d\n",
 	       !silent ? "\n" : "", avg, rel_stddev_stats(stddev, avg),
-	       (int) runtime.tv_sec);
+	       (int)bench__runtime.tv_sec);
 }
 
 static void toggle_done(int sig __maybe_unused,
@@ -73,8 +72,8 @@ static void toggle_done(int sig __maybe_unused,
 {
 	/* inform all threads that we're done for the day */
 	done = true;
-	gettimeofday(&end, NULL);
-	timersub(&end, &start, &runtime);
+	gettimeofday(&bench__end, NULL);
+	timersub(&bench__end, &bench__start, &bench__runtime);
 }
 
 static void *workerfn(void *arg)
@@ -161,6 +160,7 @@ int bench_futex_lock_pi(int argc, const char **argv)
 	if (!cpu)
 		err(EXIT_FAILURE, "calloc");
 
+	memset(&act, 0, sizeof(act));
 	sigfillset(&act.sa_mask);
 	act.sa_sigaction = toggle_done;
 	sigaction(SIGINT, &act, NULL);
@@ -185,7 +185,7 @@ int bench_futex_lock_pi(int argc, const char **argv)
 
 	threads_starting = nthreads;
 	pthread_attr_init(&thread_attr);
-	gettimeofday(&start, NULL);
+	gettimeofday(&bench__start, NULL);
 
 	create_threads(worker, thread_attr, cpu);
 	pthread_attr_destroy(&thread_attr);
@@ -211,7 +211,7 @@ int bench_futex_lock_pi(int argc, const char **argv)
 	pthread_mutex_destroy(&thread_lock);
 
 	for (i = 0; i < nthreads; i++) {
-		unsigned long t = worker[i].ops/runtime.tv_sec;
+		unsigned long t = worker[i].ops / bench__runtime.tv_sec;
 
 		update_stats(&throughput_stats, t);
 		if (!silent)
diff --git a/tools/perf/bench/futex-requeue.c b/tools/perf/bench/futex-requeue.c
index a00a6891447a..7a15c2e61022 100644
--- a/tools/perf/bench/futex-requeue.c
+++ b/tools/perf/bench/futex-requeue.c
@@ -128,6 +128,7 @@ int bench_futex_requeue(int argc, const char **argv)
 	if (!cpu)
 		err(EXIT_FAILURE, "cpu_map__new");
 
+	memset(&act, 0, sizeof(act));
 	sigfillset(&act.sa_mask);
 	act.sa_sigaction = toggle_done;
 	sigaction(SIGINT, &act, NULL);
diff --git a/tools/perf/bench/futex-wake-parallel.c b/tools/perf/bench/futex-wake-parallel.c
index a053cf2b7039..cd2b81a845ac 100644
--- a/tools/perf/bench/futex-wake-parallel.c
+++ b/tools/perf/bench/futex-wake-parallel.c
@@ -234,6 +234,7 @@ int bench_futex_wake_parallel(int argc, const char **argv)
 		exit(EXIT_FAILURE);
 	}
 
+	memset(&act, 0, sizeof(act));
 	sigfillset(&act.sa_mask);
 	act.sa_sigaction = toggle_done;
 	sigaction(SIGINT, &act, NULL);
diff --git a/tools/perf/bench/futex-wake.c b/tools/perf/bench/futex-wake.c
index df810096abfe..2dfcef3e371e 100644
--- a/tools/perf/bench/futex-wake.c
+++ b/tools/perf/bench/futex-wake.c
@@ -43,7 +43,7 @@ static bool done = false, silent = false, fshared = false;
 static pthread_mutex_t thread_lock;
 static pthread_cond_t thread_parent, thread_worker;
 static struct stats waketime_stats, wakeup_stats;
-static unsigned int ncpus, threads_starting, nthreads = 0;
+static unsigned int threads_starting, nthreads = 0;
 static int futex_flag = 0;
 
 static const struct option options[] = {
@@ -136,12 +136,13 @@ int bench_futex_wake(int argc, const char **argv)
 	if (!cpu)
 		err(EXIT_FAILURE, "calloc");
 
+	memset(&act, 0, sizeof(act));
 	sigfillset(&act.sa_mask);
 	act.sa_sigaction = toggle_done;
 	sigaction(SIGINT, &act, NULL);
 
 	if (!nthreads)
-		nthreads = ncpus;
+		nthreads = cpu->nr;
 
 	worker = calloc(nthreads, sizeof(*worker));
 	if (!worker)
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index ff61795a4d13..6c0a0412502e 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -566,6 +566,8 @@ int cmd_annotate(int argc, const char **argv)
 	if (ret < 0)
 		return ret;
 
+	annotation_config__init(&annotate.opts);
+
 	argc = parse_options(argc, argv, options, annotate_usage, 0);
 	if (argc) {
 		/*
@@ -605,8 +607,6 @@ int cmd_annotate(int argc, const char **argv)
 	if (ret < 0)
 		goto out_delete;
 
-	annotation_config__init();
-
 	symbol_conf.try_vmlinux_path = true;
 
 	ret = symbol__init(&annotate.session->header.env);
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index f8b6ae557d8b..c03c36fde7e2 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -1312,7 +1312,8 @@ static int cycles_printf(struct hist_entry *he, struct hist_entry *pair,
 	end_line = map__srcline(he->ms.map, bi->sym->start + bi->end,
 				he->ms.sym);
 
-	if ((start_line != SRCLINE_UNKNOWN) && (end_line != SRCLINE_UNKNOWN)) {
+	if ((strncmp(start_line, SRCLINE_UNKNOWN, strlen(SRCLINE_UNKNOWN)) != 0) &&
+	    (strncmp(end_line, SRCLINE_UNKNOWN, strlen(SRCLINE_UNKNOWN)) != 0)) {
 		scnprintf(buf, sizeof(buf), "[%s -> %s] %4ld",
 			  start_line, end_line, block_he->diff.cycles);
 	} else {
diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c
index 26bc5923e6b5..70548df2abb9 100644
--- a/tools/perf/builtin-probe.c
+++ b/tools/perf/builtin-probe.c
@@ -449,7 +449,8 @@ static int perf_del_probe_events(struct strfilter *filter)
 		ret = probe_file__del_strlist(kfd, klist);
 		if (ret < 0)
 			goto error;
-	}
+	} else if (ret == -ENOMEM)
+		goto error;
 
 	ret2 = probe_file__get_events(ufd, filter, ulist);
 	if (ret2 == 0) {
@@ -459,7 +460,8 @@ static int perf_del_probe_events(struct strfilter *filter)
 		ret2 = probe_file__del_strlist(ufd, ulist);
 		if (ret2 < 0)
 			goto error;
-	}
+	} else if (ret2 == -ENOMEM)
+		goto error;
 
 	if (ret == -ENOENT && ret2 == -ENOENT)
 		pr_warning("\"%s\" does not hit any event.\n", str);
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 9483b3f0cae3..72a12b69f120 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -1507,7 +1507,7 @@ repeat:
 			symbol_conf.priv_size += sizeof(u32);
 			symbol_conf.sort_by_name = true;
 		}
-		annotation_config__init();
+		annotation_config__init(&report.annotation_opts);
 	}
 
 	if (symbol__init(&session->header.env) < 0)
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 8affcab75604..d2539b793f9d 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -143,7 +143,7 @@ static int perf_top__parse_source(struct perf_top *top, struct hist_entry *he)
 		return err;
 	}
 
-	err = symbol__annotate(&he->ms, evsel, 0, &top->annotation_opts, NULL);
+	err = symbol__annotate(&he->ms, evsel, &top->annotation_opts, NULL);
 	if (err == 0) {
 		top->sym_filter_entry = he;
 	} else {
@@ -684,7 +684,9 @@ repeat:
 	delay_msecs = top->delay_secs * MSEC_PER_SEC;
 	set_term_quiet_input(&save);
 	/* trash return*/
-	getc(stdin);
+	clearerr(stdin);
+	if (poll(&stdin_poll, 1, 0) > 0)
+		getc(stdin);
 
 	while (!done) {
 		perf_top__print_sym_table(top);
@@ -1683,7 +1685,7 @@ int cmd_top(int argc, const char **argv)
 	if (status < 0)
 		goto out_delete_evlist;
 
-	annotation_config__init();
+	annotation_config__init(&top.annotation_opts);
 
 	symbol_conf.try_vmlinux_path = (symbol_conf.vmlinux_name == NULL);
 	status = symbol__init(NULL);
diff --git a/tools/perf/include/bpf/pid_filter.h b/tools/perf/include/bpf/pid_filter.h
index 607189a315b2..6e61c4bdf548 100644
--- a/tools/perf/include/bpf/pid_filter.h
+++ b/tools/perf/include/bpf/pid_filter.h
@@ -3,7 +3,7 @@
 #ifndef _PERF_BPF_PID_FILTER_
 #define _PERF_BPF_PID_FILTER_
 
-#include <bpf/bpf.h>
+#include <bpf.h>
 
 #define pid_filter(name) pid_map(name, bool)
 
diff --git a/tools/perf/include/bpf/stdio.h b/tools/perf/include/bpf/stdio.h
index 7ca6fa5463ee..316af5b2ff35 100644
--- a/tools/perf/include/bpf/stdio.h
+++ b/tools/perf/include/bpf/stdio.h
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 
-#include <bpf/bpf.h>
+#include <bpf.h>
 
 struct bpf_map SEC("maps") __bpf_stdout__ = {
        .type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
diff --git a/tools/perf/include/bpf/unistd.h b/tools/perf/include/bpf/unistd.h
index d1a35b6c649d..ca7877f9a976 100644
--- a/tools/perf/include/bpf/unistd.h
+++ b/tools/perf/include/bpf/unistd.h
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: LGPL-2.1
 
-#include <bpf/bpf.h>
+#include <bpf.h>
 
 static int (*bpf_get_current_pid_tgid)(void) = (void *)BPF_FUNC_get_current_pid_tgid;
 
diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c
index 079c77b6a2fd..27b4da80f751 100644
--- a/tools/perf/pmu-events/jevents.c
+++ b/tools/perf/pmu-events/jevents.c
@@ -1082,10 +1082,9 @@ static int process_one_file(const char *fpath, const struct stat *sb,
  */
 int main(int argc, char *argv[])
 {
-	int rc;
+	int rc, ret = 0;
 	int maxfds;
 	char ldirname[PATH_MAX];
-
 	const char *arch;
 	const char *output_file;
 	const char *start_dirname;
@@ -1156,7 +1155,8 @@ int main(int argc, char *argv[])
 		/* Make build fail */
 		fclose(eventsfp);
 		free_arch_std_events();
-		return 1;
+		ret = 1;
+		goto out_free_mapfile;
 	} else if (rc) {
 		goto empty_map;
 	}
@@ -1174,14 +1174,17 @@ int main(int argc, char *argv[])
 		/* Make build fail */
 		fclose(eventsfp);
 		free_arch_std_events();
-		return 1;
+		ret = 1;
 	}
 
-	return 0;
+
+	goto out_free_mapfile;
 
 empty_map:
 	fclose(eventsfp);
 	create_empty_mapping(output_file);
 	free_arch_std_events();
-	return 0;
+out_free_mapfile:
+	free(mapfile);
+	return ret;
 }
diff --git a/tools/perf/tests/bp_account.c b/tools/perf/tests/bp_account.c
index d0b935356274..489b50604cf2 100644
--- a/tools/perf/tests/bp_account.c
+++ b/tools/perf/tests/bp_account.c
@@ -19,7 +19,7 @@
 #include "../perf-sys.h"
 #include "cloexec.h"
 
-volatile long the_var;
+static volatile long the_var;
 
 static noinline int test_function(void)
 {
diff --git a/tools/perf/tests/shell/lib/probe_vfs_getname.sh b/tools/perf/tests/shell/lib/probe_vfs_getname.sh
index 7cb99b433888..c2cc42daf924 100644
--- a/tools/perf/tests/shell/lib/probe_vfs_getname.sh
+++ b/tools/perf/tests/shell/lib/probe_vfs_getname.sh
@@ -14,7 +14,7 @@ add_probe_vfs_getname() {
 	if [ $had_vfs_getname -eq 1 ] ; then
 		line=$(perf probe -L getname_flags 2>&1 | egrep 'result.*=.*filename;' | sed -r 's/[[:space:]]+([[:digit:]]+)[[:space:]]+result->uptr.*/\1/')
 		perf probe -q       "vfs_getname=getname_flags:${line} pathname=result->name:string" || \
-		perf probe $verbose "vfs_getname=getname_flags:${line} pathname=filename:string"
+		perf probe $verbose "vfs_getname=getname_flags:${line} pathname=filename:ustring"
 	fi
 }
 
diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index badbddbb30f8..9023267e5643 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -754,10 +754,9 @@ static int annotate_browser__run(struct annotate_browser *browser,
 		"?             Search string backwards\n");
 			continue;
 		case 'r':
-			{
-				script_browse(NULL, NULL);
-				continue;
-			}
+			script_browse(NULL, NULL);
+			annotate_browser__show(&browser->b, title, help);
+			continue;
 		case 'k':
 			notes->options->show_linenr = !notes->options->show_linenr;
 			break;
@@ -834,13 +833,13 @@ show_sup_ins:
 			map_symbol__annotation_dump(ms, evsel, browser->opts);
 			continue;
 		case 't':
-			if (notes->options->show_total_period) {
-				notes->options->show_total_period = false;
-				notes->options->show_nr_samples = true;
-			} else if (notes->options->show_nr_samples)
-				notes->options->show_nr_samples = false;
+			if (symbol_conf.show_total_period) {
+				symbol_conf.show_total_period = false;
+				symbol_conf.show_nr_samples = true;
+			} else if (symbol_conf.show_nr_samples)
+				symbol_conf.show_nr_samples = false;
 			else
-				notes->options->show_total_period = true;
+				symbol_conf.show_total_period = true;
 			annotation__update_column_widths(notes);
 			continue;
 		case 'c':
diff --git a/tools/perf/ui/gtk/annotate.c b/tools/perf/ui/gtk/annotate.c
index 22cc240f7371..35f9641bf670 100644
--- a/tools/perf/ui/gtk/annotate.c
+++ b/tools/perf/ui/gtk/annotate.c
@@ -174,7 +174,7 @@ static int symbol__gtk_annotate(struct map_symbol *ms, struct evsel *evsel,
 	if (ms->map->dso->annotate_warned)
 		return -1;
 
-	err = symbol__annotate(ms, evsel, 0, &annotation__default_options, NULL);
+	err = symbol__annotate(ms, evsel, &annotation__default_options, NULL);
 	if (err) {
 		char msg[BUFSIZ];
 		symbol__strerror_disassemble(ms, err, msg, sizeof(msg));
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index ca73fb74ad03..0ea95be84b3b 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -1143,93 +1143,70 @@ out:
 }
 
 struct annotate_args {
-	size_t			 privsize;
-	struct arch		*arch;
-	struct map_symbol	 ms;
-	struct evsel	*evsel;
+	struct arch		  *arch;
+	struct map_symbol	  ms;
+	struct evsel		  *evsel;
 	struct annotation_options *options;
-	s64			 offset;
-	char			*line;
-	int			 line_nr;
+	s64			  offset;
+	char			  *line;
+	int			  line_nr;
 };
 
-static void annotation_line__delete(struct annotation_line *al)
+static void annotation_line__init(struct annotation_line *al,
+				  struct annotate_args *args,
+				  int nr)
 {
-	void *ptr = (void *) al - al->privsize;
+	al->offset = args->offset;
+	al->line = strdup(args->line);
+	al->line_nr = args->line_nr;
+	al->data_nr = nr;
+}
 
+static void annotation_line__exit(struct annotation_line *al)
+{
 	free_srcline(al->path);
 	zfree(&al->line);
-	free(ptr);
 }
 
-/*
- * Allocating the annotation line data with following
- * structure:
- *
- *    --------------------------------------
- *    private space | struct annotation_line
- *    --------------------------------------
- *
- * Size of the private space is stored in 'struct annotation_line'.
- *
- */
-static struct annotation_line *
-annotation_line__new(struct annotate_args *args, size_t privsize)
+static size_t disasm_line_size(int nr)
 {
 	struct annotation_line *al;
-	struct evsel *evsel = args->evsel;
-	size_t size = privsize + sizeof(*al);
-	int nr = 1;
-
-	if (perf_evsel__is_group_event(evsel))
-		nr = evsel->core.nr_members;
 
-	size += sizeof(al->data[0]) * nr;
-
-	al = zalloc(size);
-	if (al) {
-		al = (void *) al + privsize;
-		al->privsize   = privsize;
-		al->offset     = args->offset;
-		al->line       = strdup(args->line);
-		al->line_nr    = args->line_nr;
-		al->data_nr    = nr;
-	}
-
-	return al;
+	return (sizeof(struct disasm_line) + (sizeof(al->data[0]) * nr));
 }
 
 /*
  * Allocating the disasm annotation line data with
  * following structure:
  *
- *    ------------------------------------------------------------
- *    privsize space | struct disasm_line | struct annotation_line
- *    ------------------------------------------------------------
+ *    -------------------------------------------
+ *    struct disasm_line | struct annotation_line
+ *    -------------------------------------------
  *
  * We have 'struct annotation_line' member as last member
  * of 'struct disasm_line' to have an easy access.
- *
  */
 static struct disasm_line *disasm_line__new(struct annotate_args *args)
 {
 	struct disasm_line *dl = NULL;
-	struct annotation_line *al;
-	size_t privsize = args->privsize + offsetof(struct disasm_line, al);
+	int nr = 1;
 
-	al = annotation_line__new(args, privsize);
-	if (al != NULL) {
-		dl = disasm_line(al);
+	if (perf_evsel__is_group_event(args->evsel))
+		nr = args->evsel->core.nr_members;
 
-		if (dl->al.line == NULL)
-			goto out_delete;
+	dl = zalloc(disasm_line_size(nr));
+	if (!dl)
+		return NULL;
 
-		if (args->offset != -1) {
-			if (disasm_line__parse(dl->al.line, &dl->ins.name, &dl->ops.raw) < 0)
-				goto out_free_line;
+	annotation_line__init(&dl->al, args, nr);
+	if (dl->al.line == NULL)
+		goto out_delete;
 
-			disasm_line__init_ins(dl, args->arch, &args->ms);
-		}
+	if (args->offset != -1) {
+		if (disasm_line__parse(dl->al.line, &dl->ins.name, &dl->ops.raw) < 0)
+			goto out_free_line;
+
+		disasm_line__init_ins(dl, args->arch, &args->ms);
 	}
 
 	return dl;
@@ -1248,7 +1225,8 @@ void disasm_line__free(struct disasm_line *dl)
 	else
 		ins__delete(&dl->ops);
 	zfree(&dl->ins.name);
-	annotation_line__delete(&dl->al);
+	annotation_line__exit(&dl->al);
+	free(dl);
 }
 
 int disasm_line__scnprintf(struct disasm_line *dl, char *bf, size_t size, bool raw, int max_ins_name)
@@ -2149,13 +2127,12 @@ void symbol__calc_percent(struct symbol *sym, struct evsel *evsel)
 	annotation__calc_percent(notes, evsel, symbol__size(sym));
 }
 
-int symbol__annotate(struct map_symbol *ms, struct evsel *evsel, size_t privsize,
+int symbol__annotate(struct map_symbol *ms, struct evsel *evsel,
 		     struct annotation_options *options, struct arch **parch)
 {
 	struct symbol *sym = ms->sym;
 	struct annotation *notes = symbol__annotation(sym);
 	struct annotate_args args = {
-		.privsize	= privsize,
 		.evsel		= evsel,
 		.options	= options,
 	};
@@ -2644,6 +2621,8 @@ void annotation__set_offsets(struct annotation *notes, s64 size)
 	struct annotation_line *al;
 
 	notes->max_line_len = 0;
+	notes->nr_entries = 0;
+	notes->nr_asm_entries = 0;
 
 	list_for_each_entry(al, &notes->src->source, node) {
 		size_t line_len = strlen(al->line);
@@ -2790,7 +2769,7 @@ int symbol__tty_annotate(struct map_symbol *ms, struct evsel *evsel,
 	struct symbol *sym = ms->sym;
 	struct rb_root source_line = RB_ROOT;
 
-	if (symbol__annotate(ms, evsel, 0, opts, NULL) < 0)
+	if (symbol__annotate(ms, evsel, opts, NULL) < 0)
 		return -1;
 
 	symbol__calc_percent(sym, evsel);
@@ -2915,9 +2894,9 @@ static void __annotation_line__write(struct annotation_line *al, struct annotati
 			percent = annotation_data__percent(&al->data[i], percent_type);
 
 			obj__set_percent_color(obj, percent, current_entry);
-			if (notes->options->show_total_period) {
+			if (symbol_conf.show_total_period) {
 				obj__printf(obj, "%11" PRIu64 " ", al->data[i].he.period);
-			} else if (notes->options->show_nr_samples) {
+			} else if (symbol_conf.show_nr_samples) {
 				obj__printf(obj, "%6" PRIu64 " ",
 						   al->data[i].he.nr_samples);
 			} else {
@@ -2931,8 +2910,8 @@ static void __annotation_line__write(struct annotation_line *al, struct annotati
 			obj__printf(obj, "%-*s", pcnt_width, " ");
 		else {
 			obj__printf(obj, "%-*s", pcnt_width,
-					   notes->options->show_total_period ? "Period" :
-					   notes->options->show_nr_samples ? "Samples" : "Percent");
+					   symbol_conf.show_total_period ? "Period" :
+					   symbol_conf.show_nr_samples ? "Samples" : "Percent");
 		}
 	}
 
@@ -3070,7 +3049,7 @@ int symbol__annotate2(struct map_symbol *ms, struct evsel *evsel,
 	if (perf_evsel__is_group_event(evsel))
 		nr_pcnt = evsel->core.nr_members;
 
-	err = symbol__annotate(ms, evsel, 0, options, parch);
+	err = symbol__annotate(ms, evsel, options, parch);
 	if (err)
 		goto out_free_offsets;
 
@@ -3094,69 +3073,46 @@ out_free_offsets:
 	return err;
 }
 
-#define ANNOTATION__CFG(n) \
-	{ .name = #n, .value = &annotation__default_options.n, }
-
-/*
- * Keep the entries sorted, they are bsearch'ed
- */
-static struct annotation_config {
-	const char *name;
-	void *value;
-} annotation__configs[] = {
-	ANNOTATION__CFG(hide_src_code),
-	ANNOTATION__CFG(jump_arrows),
-	ANNOTATION__CFG(offset_level),
-	ANNOTATION__CFG(show_linenr),
-	ANNOTATION__CFG(show_nr_jumps),
-	ANNOTATION__CFG(show_nr_samples),
-	ANNOTATION__CFG(show_total_period),
-	ANNOTATION__CFG(use_offset),
-};
-
-#undef ANNOTATION__CFG
-
-static int annotation_config__cmp(const void *name, const void *cfgp)
-{
-	const struct annotation_config *cfg = cfgp;
-
-	return strcmp(name, cfg->name);
-}
-
-static int annotation__config(const char *var, const char *value,
-			    void *data __maybe_unused)
+static int annotation__config(const char *var, const char *value, void *data)
 {
-	struct annotation_config *cfg;
-	const char *name;
+	struct annotation_options *opt = data;
 
 	if (!strstarts(var, "annotate."))
 		return 0;
 
-	name = var + 9;
-	cfg = bsearch(name, annotation__configs, ARRAY_SIZE(annotation__configs),
-		      sizeof(struct annotation_config), annotation_config__cmp);
-
-	if (cfg == NULL)
-		pr_debug("%s variable unknown, ignoring...", var);
-	else if (strcmp(var, "annotate.offset_level") == 0) {
-		perf_config_int(cfg->value, name, value);
-
-		if (*(int *)cfg->value > ANNOTATION__MAX_OFFSET_LEVEL)
-			*(int *)cfg->value = ANNOTATION__MAX_OFFSET_LEVEL;
-		else if (*(int *)cfg->value < ANNOTATION__MIN_OFFSET_LEVEL)
-			*(int *)cfg->value = ANNOTATION__MIN_OFFSET_LEVEL;
+	if (!strcmp(var, "annotate.offset_level")) {
+		perf_config_u8(&opt->offset_level, "offset_level", value);
+
+		if (opt->offset_level > ANNOTATION__MAX_OFFSET_LEVEL)
+			opt->offset_level = ANNOTATION__MAX_OFFSET_LEVEL;
+		else if (opt->offset_level < ANNOTATION__MIN_OFFSET_LEVEL)
+			opt->offset_level = ANNOTATION__MIN_OFFSET_LEVEL;
+	} else if (!strcmp(var, "annotate.hide_src_code")) {
+		opt->hide_src_code = perf_config_bool("hide_src_code", value);
+	} else if (!strcmp(var, "annotate.jump_arrows")) {
+		opt->jump_arrows = perf_config_bool("jump_arrows", value);
+	} else if (!strcmp(var, "annotate.show_linenr")) {
+		opt->show_linenr = perf_config_bool("show_linenr", value);
+	} else if (!strcmp(var, "annotate.show_nr_jumps")) {
+		opt->show_nr_jumps = perf_config_bool("show_nr_jumps", value);
+	} else if (!strcmp(var, "annotate.show_nr_samples")) {
+		symbol_conf.show_nr_samples = perf_config_bool("show_nr_samples",
+								value);
+	} else if (!strcmp(var, "annotate.show_total_period")) {
+		symbol_conf.show_total_period = perf_config_bool("show_total_period",
+								value);
+	} else if (!strcmp(var, "annotate.use_offset")) {
+		opt->use_offset = perf_config_bool("use_offset", value);
 	} else {
-		*(bool *)cfg->value = perf_config_bool(name, value);
+		pr_debug("%s variable unknown, ignoring...", var);
 	}
+
 	return 0;
 }
 
-void annotation_config__init(void)
+void annotation_config__init(struct annotation_options *opt)
 {
-	perf_config(annotation__config, NULL);
-
-	annotation__default_options.show_total_period = symbol_conf.show_total_period;
-	annotation__default_options.show_nr_samples   = symbol_conf.show_nr_samples;
+	perf_config(annotation__config, opt);
 }
 
 static unsigned int parse_percent_type(char *str1, char *str2)
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index 455403e8fede..001258601a37 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -83,8 +83,6 @@ struct annotation_options {
 	     full_path,
 	     show_linenr,
 	     show_nr_jumps,
-	     show_nr_samples,
-	     show_total_period,
 	     show_minmax_cycle,
 	     show_asm_raw,
 	     annotate_src;
@@ -141,7 +139,6 @@ struct annotation_line {
 	u64			 cycles;
 	u64			 cycles_max;
 	u64			 cycles_min;
-	size_t			 privsize;
 	char			*path;
 	u32			 idx;
 	int			 idx_asm;
@@ -309,7 +306,7 @@ static inline int annotation__cycles_width(struct annotation *notes)
 
 static inline int annotation__pcnt_width(struct annotation *notes)
 {
-	return (notes->options->show_total_period ? 12 : 7) * notes->nr_events;
+	return (symbol_conf.show_total_period ? 12 : 7) * notes->nr_events;
 }
 
 static inline bool annotation_line__filter(struct annotation_line *al, struct annotation *notes)
@@ -352,7 +349,7 @@ struct annotated_source *symbol__hists(struct symbol *sym, int nr_hists);
 void symbol__annotate_zero_histograms(struct symbol *sym);
 
 int symbol__annotate(struct map_symbol *ms,
-		     struct evsel *evsel, size_t privsize,
+		     struct evsel *evsel,
 		     struct annotation_options *options,
 		     struct arch **parch);
 int symbol__annotate2(struct map_symbol *ms,
@@ -413,7 +410,7 @@ static inline int symbol__tui_annotate(struct map_symbol *ms __maybe_unused,
 }
 #endif
 
-void annotation_config__init(void);
+void annotation_config__init(struct annotation_options *opt);
 
 int annotate_parse_percent_type(const struct option *opt, const char *_str,
 				int unset);
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index eb087e7df6f4..3571ce72ca28 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -629,8 +629,10 @@ int auxtrace_record__options(struct auxtrace_record *itr,
 			     struct evlist *evlist,
 			     struct record_opts *opts)
 {
-	if (itr)
+	if (itr) {
+		itr->evlist = evlist;
 		return itr->recording_options(itr, evlist, opts);
+	}
 	return 0;
 }
 
@@ -664,6 +666,24 @@ int auxtrace_parse_snapshot_options(struct auxtrace_record *itr,
 	return -EINVAL;
 }
 
+int auxtrace_record__read_finish(struct auxtrace_record *itr, int idx)
+{
+	struct evsel *evsel;
+
+	if (!itr->evlist || !itr->pmu)
+		return -EINVAL;
+
+	evlist__for_each_entry(itr->evlist, evsel) {
+		if (evsel->core.attr.type == itr->pmu->type) {
+			if (evsel->disabled)
+				return 0;
+			return perf_evlist__enable_event_idx(itr->evlist, evsel,
+							     idx);
+		}
+	}
+	return -EINVAL;
+}
+
 /*
  * Event record size is 16-bit which results in a maximum size of about 64KiB.
  * Allow about 4KiB for the rest of the sample record, to give a maximum
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index 749d72cd9c7b..e58ef160b599 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -29,6 +29,7 @@ struct record_opts;
 struct perf_record_auxtrace_error;
 struct perf_record_auxtrace_info;
 struct events_stats;
+struct perf_pmu;
 
 enum auxtrace_error_type {
        PERF_AUXTRACE_ERROR_ITRACE  = 1,
@@ -322,6 +323,8 @@ struct auxtrace_mmap_params {
  * @read_finish: called after reading from an auxtrace mmap
  * @alignment: alignment (if any) for AUX area data
  * @default_aux_sample_size: default sample size for --aux sample option
+ * @pmu: associated pmu
+ * @evlist: selected events list
  */
 struct auxtrace_record {
 	int (*recording_options)(struct auxtrace_record *itr,
@@ -346,6 +349,8 @@ struct auxtrace_record {
 	int (*read_finish)(struct auxtrace_record *itr, int idx);
 	unsigned int alignment;
 	unsigned int default_aux_sample_size;
+	struct perf_pmu *pmu;
+	struct evlist *evlist;
 };
 
 /**
@@ -537,6 +542,7 @@ int auxtrace_record__find_snapshot(struct auxtrace_record *itr, int idx,
 				   struct auxtrace_mmap *mm,
 				   unsigned char *data, u64 *head, u64 *old);
 u64 auxtrace_record__reference(struct auxtrace_record *itr);
+int auxtrace_record__read_finish(struct auxtrace_record *itr, int idx);
 
 int auxtrace_index__auxtrace_event(struct list_head *head, union perf_event *event,
 				   off_t file_offset);
diff --git a/tools/perf/util/block-info.c b/tools/perf/util/block-info.c
index c4b030bf6ec2..fbbb6d640dad 100644
--- a/tools/perf/util/block-info.c
+++ b/tools/perf/util/block-info.c
@@ -295,7 +295,8 @@ static int block_range_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
 	end_line = map__srcline(he->ms.map, bi->sym->start + bi->end,
 				he->ms.sym);
 
-	if ((start_line != SRCLINE_UNKNOWN) && (end_line != SRCLINE_UNKNOWN)) {
+	if ((strncmp(start_line, SRCLINE_UNKNOWN, strlen(SRCLINE_UNKNOWN)) != 0) &&
+	    (strncmp(end_line, SRCLINE_UNKNOWN, strlen(SRCLINE_UNKNOWN)) != 0)) {
 		scnprintf(buf, sizeof(buf), "[%s -> %s]",
 			  start_line, end_line);
 	} else {
diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c
index 0bc9c4d7fdc5..ef38eba56ed0 100644
--- a/tools/perf/util/config.c
+++ b/tools/perf/util/config.c
@@ -374,6 +374,18 @@ int perf_config_int(int *dest, const char *name, const char *value)
 	return 0;
 }
 
+int perf_config_u8(u8 *dest, const char *name, const char *value)
+{
+	long ret = 0;
+
+	if (!perf_parse_long(value, &ret)) {
+		bad_config(name);
+		return -1;
+	}
+	*dest = ret;
+	return 0;
+}
+
 static int perf_config_bool_or_int(const char *name, const char *value, int *is_bool)
 {
 	int ret;
diff --git a/tools/perf/util/config.h b/tools/perf/util/config.h
index bd0a5897c76a..c10b66dde2f3 100644
--- a/tools/perf/util/config.h
+++ b/tools/perf/util/config.h
@@ -29,6 +29,7 @@ typedef int (*config_fn_t)(const char *, const char *, void *);
 int perf_default_config(const char *, const char *, void *);
 int perf_config(config_fn_t fn, void *);
 int perf_config_int(int *dest, const char *, const char *);
+int perf_config_u8(u8 *dest, const char *name, const char *value);
 int perf_config_u64(u64 *dest, const char *, const char *);
 int perf_config_bool(const char *, const char *);
 int config_error_nonbool(const char *);
diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c
index 6242a9215df7..4154f944f474 100644
--- a/tools/perf/util/env.c
+++ b/tools/perf/util/env.c
@@ -343,11 +343,11 @@ static const char *normalize_arch(char *arch)
 
 const char *perf_env__arch(struct perf_env *env)
 {
-	struct utsname uts;
 	char *arch_name;
 
 	if (!env || !env->arch) { /* Assume local operation */
-		if (uname(&uts) < 0)
+		static struct utsname uts = { .machine[0] = '\0', };
+		if (uts.machine[0] == '\0' && uname(&uts) < 0)
 			return NULL;
 		arch_name = uts.machine;
 	} else
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index a08ca276098e..95428511300d 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -431,7 +431,7 @@ int map__fprintf_srcline(struct map *map, u64 addr, const char *prefix,
 
 	if (map && map->dso) {
 		char *srcline = map__srcline(map, addr, NULL);
-		if (srcline != SRCLINE_UNKNOWN)
+		if (strncmp(srcline, SRCLINE_UNKNOWN, strlen(SRCLINE_UNKNOWN)) != 0)
 			ret = fprintf(fp, "%s%s", prefix, srcline);
 		free_srcline(srcline);
 	}
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index c01ba6f8fdad..a14995835d85 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -257,21 +257,15 @@ struct tracepoint_path *tracepoint_id_to_path(u64 config)
 				path = zalloc(sizeof(*path));
 				if (!path)
 					return NULL;
-				path->system = malloc(MAX_EVENT_LENGTH);
-				if (!path->system) {
+				if (asprintf(&path->system, "%.*s", MAX_EVENT_LENGTH, sys_dirent->d_name) < 0) {
 					free(path);
 					return NULL;
 				}
-				path->name = malloc(MAX_EVENT_LENGTH);
-				if (!path->name) {
+				if (asprintf(&path->name, "%.*s", MAX_EVENT_LENGTH, evt_dirent->d_name) < 0) {
 					zfree(&path->system);
 					free(path);
 					return NULL;
 				}
-				strncpy(path->system, sys_dirent->d_name,
-					MAX_EVENT_LENGTH);
-				strncpy(path->name, evt_dirent->d_name,
-					MAX_EVENT_LENGTH);
 				return path;
 			}
 		}
diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c
index 5003ba403345..0f5fda11675f 100644
--- a/tools/perf/util/probe-file.c
+++ b/tools/perf/util/probe-file.c
@@ -301,10 +301,15 @@ int probe_file__get_events(int fd, struct strfilter *filter,
 		p = strchr(ent->s, ':');
 		if ((p && strfilter__compare(filter, p + 1)) ||
 		    strfilter__compare(filter, ent->s)) {
-			strlist__add(plist, ent->s);
+			ret = strlist__add(plist, ent->s);
+			if (ret == -ENOMEM) {
+				pr_err("strlist__add failed with -ENOMEM\n");
+				goto out;
+			}
 			ret = 0;
 		}
 	}
+out:
 	strlist__delete(namelist);
 
 	return ret;
@@ -511,7 +516,11 @@ static int probe_cache__load(struct probe_cache *pcache)
 				ret = -EINVAL;
 				goto out;
 			}
-			strlist__add(entry->tevlist, buf);
+			ret = strlist__add(entry->tevlist, buf);
+			if (ret == -ENOMEM) {
+				pr_err("strlist__add failed with -ENOMEM\n");
+				goto out;
+			}
 		}
 	}
 out:
@@ -672,7 +681,12 @@ int probe_cache__add_entry(struct probe_cache *pcache,
 		command = synthesize_probe_trace_command(&tevs[i]);
 		if (!command)
 			goto out_err;
-		strlist__add(entry->tevlist, command);
+		ret = strlist__add(entry->tevlist, command);
+		if (ret == -ENOMEM) {
+			pr_err("strlist__add failed with -ENOMEM\n");
+			goto out_err;
+		}
+
 		free(command);
 	}
 	list_add_tail(&entry->node, &pcache->entries);
@@ -853,9 +867,15 @@ int probe_cache__scan_sdt(struct probe_cache *pcache, const char *pathname)
 			break;
 		}
 
-		strlist__add(entry->tevlist, buf);
+		ret = strlist__add(entry->tevlist, buf);
+
 		free(buf);
 		entry = NULL;
+
+		if (ret == -ENOMEM) {
+			pr_err("strlist__add failed with -ENOMEM\n");
+			break;
+		}
 	}
 	if (entry) {
 		list_del_init(&entry->node);
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 1077013d8ce2..26bc6a0096ce 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1622,7 +1622,12 @@ int dso__load(struct dso *dso, struct map *map)
 		goto out;
 	}
 
-	if (dso->kernel) {
+	kmod = dso->symtab_type == DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE ||
+		dso->symtab_type == DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP ||
+		dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE ||
+		dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE_COMP;
+
+	if (dso->kernel && !kmod) {
 		if (dso->kernel == DSO_TYPE_KERNEL)
 			ret = dso__load_kernel_sym(dso, map);
 		else if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
@@ -1650,12 +1655,6 @@ int dso__load(struct dso *dso, struct map *map)
 	if (!name)
 		goto out;
 
-	kmod = dso->symtab_type == DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE ||
-		dso->symtab_type == DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP ||
-		dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE ||
-		dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE_COMP;
-
-
 	/*
 	 * Read the build id if possible. This is required for
 	 * DSO_BINARY_TYPE__BUILDID_DEBUGINFO to work