Merge remote-tracking branch 'torvalds/master' into perf/core

To pick up fixes from perf/urgent.

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

33 files changed, 167 insertions, 98 deletions

diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h
index 742d89a00721..211ba3375ee9 100644
--- a/tools/arch/x86/include/asm/msr-index.h
+++ b/tools/arch/x86/include/asm/msr-index.h
@@ -537,9 +537,9 @@
 /* K8 MSRs */
 #define MSR_K8_TOP_MEM1			0xc001001a
 #define MSR_K8_TOP_MEM2			0xc001001d
-#define MSR_K8_SYSCFG			0xc0010010
-#define MSR_K8_SYSCFG_MEM_ENCRYPT_BIT	23
-#define MSR_K8_SYSCFG_MEM_ENCRYPT	BIT_ULL(MSR_K8_SYSCFG_MEM_ENCRYPT_BIT)
+#define MSR_AMD64_SYSCFG		0xc0010010
+#define MSR_AMD64_SYSCFG_MEM_ENCRYPT_BIT	23
+#define MSR_AMD64_SYSCFG_MEM_ENCRYPT	BIT_ULL(MSR_AMD64_SYSCFG_MEM_ENCRYPT_BIT)
 #define MSR_K8_INT_PENDING_MSG		0xc0010055
 /* C1E active bits in int pending message */
 #define K8_INTP_C1E_ACTIVE_MASK		0x18000000
diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h
index 5a3022c8af82..0662f644aad9 100644
--- a/tools/arch/x86/include/uapi/asm/kvm.h
+++ b/tools/arch/x86/include/uapi/asm/kvm.h
@@ -437,6 +437,8 @@ struct kvm_vmx_nested_state_hdr {
 		__u16 flags;
 	} smm;
 
+	__u16 pad;
+
 	__u32 flags;
 	__u64 preemption_timer_deadline;
 };
diff --git a/tools/build/Makefile.build b/tools/build/Makefile.build
index cd72016c3cfa..715092fc6a23 100644
--- a/tools/build/Makefile.build
+++ b/tools/build/Makefile.build
@@ -51,39 +51,39 @@ subdir-obj-y :=
 build-file := $(dir)/Build
 -include $(build-file)
 
-quiet_cmd_flex  = FLEX     $@
-quiet_cmd_bison = BISON    $@
+quiet_cmd_flex  = FLEX    $@
+quiet_cmd_bison = BISON   $@
 
 # Create directory unless it exists
-quiet_cmd_mkdir = MKDIR    $(dir $@)
+quiet_cmd_mkdir = MKDIR   $(dir $@)
       cmd_mkdir = mkdir -p $(dir $@)
      rule_mkdir = $(if $(wildcard $(dir $@)),,@$(call echo-cmd,mkdir) $(cmd_mkdir))
 
 # Compile command
-quiet_cmd_cc_o_c = CC       $@
+quiet_cmd_cc_o_c = CC      $@
       cmd_cc_o_c = $(CC) $(c_flags) -c -o $@ $<
 
-quiet_cmd_host_cc_o_c = HOSTCC   $@
+quiet_cmd_host_cc_o_c = HOSTCC  $@
       cmd_host_cc_o_c = $(HOSTCC) $(host_c_flags) -c -o $@ $<
 
-quiet_cmd_cxx_o_c = CXX      $@
+quiet_cmd_cxx_o_c = CXX     $@
       cmd_cxx_o_c = $(CXX) $(cxx_flags) -c -o $@ $<
 
-quiet_cmd_cpp_i_c = CPP      $@
+quiet_cmd_cpp_i_c = CPP     $@
       cmd_cpp_i_c = $(CC) $(c_flags) -E -o $@ $<
 
-quiet_cmd_cc_s_c = AS       $@
+quiet_cmd_cc_s_c = AS      $@
       cmd_cc_s_c = $(CC) $(c_flags) -S -o $@ $<
 
-quiet_cmd_gen = GEN      $@
+quiet_cmd_gen = GEN     $@
 
 # Link agregate command
 # If there's nothing to link, create empty $@ object.
-quiet_cmd_ld_multi = LD       $@
+quiet_cmd_ld_multi = LD      $@
       cmd_ld_multi = $(if $(strip $(obj-y)),\
                      $(LD) -r -o $@  $(filter $(obj-y),$^),rm -f $@; $(AR) rcs $@)
 
-quiet_cmd_host_ld_multi = HOSTLD   $@
+quiet_cmd_host_ld_multi = HOSTLD  $@
       cmd_host_ld_multi = $(if $(strip $(obj-y)),\
                           $(HOSTLD) -r -o $@  $(filter $(obj-y),$^),rm -f $@; $(HOSTAR) rcs $@)
 
diff --git a/tools/include/linux/bits.h b/tools/include/linux/bits.h
index 7f475d59a097..87d112650dfb 100644
--- a/tools/include/linux/bits.h
+++ b/tools/include/linux/bits.h
@@ -22,7 +22,7 @@
 #include <linux/build_bug.h>
 #define GENMASK_INPUT_CHECK(h, l) \
 	(BUILD_BUG_ON_ZERO(__builtin_choose_expr( \
-		__builtin_constant_p((l) > (h)), (l) > (h), 0)))
+		__is_constexpr((l) > (h)), (l) > (h), 0)))
 #else
 /*
  * BUILD_BUG_ON_ZERO is not available in h files included from asm files,
diff --git a/tools/include/linux/const.h b/tools/include/linux/const.h
index 81b8aae5a855..435ddd72d2c4 100644
--- a/tools/include/linux/const.h
+++ b/tools/include/linux/const.h
@@ -3,4 +3,12 @@
 
 #include <vdso/const.h>
 
+/*
+ * This returns a constant expression while determining if an argument is
+ * a constant expression, most importantly without evaluating the argument.
+ * Glory to Martin Uecker <Martin.Uecker@med.uni-goettingen.de>
+ */
+#define __is_constexpr(x) \
+	(sizeof(int) == sizeof(*(8 ? ((void *)((long)(x) * 0l)) : (int *)8)))
+
 #endif /* _LINUX_CONST_H */
diff --git a/tools/include/uapi/linux/fs.h b/tools/include/uapi/linux/fs.h
index f44eb0a04afd..4c32e97dcdf0 100644
--- a/tools/include/uapi/linux/fs.h
+++ b/tools/include/uapi/linux/fs.h
@@ -185,7 +185,7 @@ struct fsxattr {
 #define BLKROTATIONAL _IO(0x12,126)
 #define BLKZEROOUT _IO(0x12,127)
 /*
- * A jump here: 130-131 are reserved for zoned block devices
+ * A jump here: 130-136 are reserved for zoned block devices
  * (see uapi/linux/blkzoned.h)
  */
 
diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
index bf8143505c49..f92880a15645 100644
--- a/tools/include/uapi/linux/perf_event.h
+++ b/tools/include/uapi/linux/perf_event.h
@@ -464,7 +464,7 @@ struct perf_event_attr {
 
 	/*
 	 * User provided data if sigtrap=1, passed back to user via
-	 * siginfo_t::si_perf, e.g. to permit user to identify the event.
+	 * siginfo_t::si_perf_data, e.g. to permit user to identify the event.
 	 */
 	__u64	sig_data;
 };
diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c
index cedf3ede7545..24295d39713b 100644
--- a/tools/objtool/arch/x86/decode.c
+++ b/tools/objtool/arch/x86/decode.c
@@ -19,6 +19,7 @@
 #include <objtool/elf.h>
 #include <objtool/arch.h>
 #include <objtool/warn.h>
+#include <objtool/endianness.h>
 #include <arch/elf.h>
 
 static int is_x86_64(const struct elf *elf)
@@ -725,7 +726,7 @@ static int elf_add_alternative(struct elf *elf,
 		return -1;
 	}
 
-	alt->cpuid = cpuid;
+	alt->cpuid = bswap_if_needed(cpuid);
 	alt->instrlen = orig_len;
 	alt->replacementlen = repl_len;
 
diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c
index d08f5f3670f8..743c2e9d0f56 100644
--- a/tools/objtool/elf.c
+++ b/tools/objtool/elf.c
@@ -762,6 +762,7 @@ struct symbol *elf_create_undef_symbol(struct elf *elf, const char *name)
 	data->d_buf = &sym->sym;
 	data->d_size = sizeof(sym->sym);
 	data->d_align = 1;
+	data->d_type = ELF_T_SYM;
 
 	sym->idx = symtab->len / sizeof(sym->sym);
 
diff --git a/tools/perf/Documentation/perf-intel-pt.txt b/tools/perf/Documentation/perf-intel-pt.txt
index 8d6cce062a5f..e382dbd4ff0a 100644
--- a/tools/perf/Documentation/perf-intel-pt.txt
+++ b/tools/perf/Documentation/perf-intel-pt.txt
@@ -108,9 +108,9 @@ displayed as follows:
 
 	perf script --itrace=ibxwpe -F+flags
 
-The flags are "bcrosyiABEx" which stand for branch, call, return, conditional,
-system, asynchronous, interrupt, transaction abort, trace begin, trace end, and
-in transaction, respectively.
+The flags are "bcrosyiABExgh" which stand for branch, call, return, conditional,
+system, asynchronous, interrupt, transaction abort, trace begin, trace end,
+in transaction, VM-entry, and VM-exit respectively.
 
 perf script also supports higher level ways to dump instruction traces:
 
diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index 5b8b61075039..48a5f5b26dd4 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -183,14 +183,15 @@ OPTIONS
 	At this point usage is displayed, and perf-script exits.
 
 	The flags field is synthesized and may have a value when Instruction
-	Trace decoding. The flags are "bcrosyiABEx" which stand for branch,
+	Trace decoding. The flags are "bcrosyiABExgh" which stand for branch,
 	call, return, conditional, system, asynchronous, interrupt,
-	transaction abort, trace begin, trace end, and in transaction,
+	transaction abort, trace begin, trace end, in transaction, VM-Entry, and VM-Exit
 	respectively. Known combinations of flags are printed more nicely e.g.
 	"call" for "bc", "return" for "br", "jcc" for "bo", "jmp" for "b",
 	"int" for "bci", "iret" for "bri", "syscall" for "bcs", "sysret" for "brs",
 	"async" for "by", "hw int" for "bcyi", "tx abrt" for "bA", "tr strt" for "bB",
-	"tr end" for "bE". However the "x" flag will be display separately in those
+	"tr end" for "bE", "vmentry" for "bcg", "vmexit" for "bch".
+	However the "x" flag will be displayed separately in those
 	cases e.g. "jcc     (x)" for a condition branch within a transaction.
 
 	The callindent field is synthesized and may have a value when
diff --git a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl
index 9974f5f8e49b..9cd1c34f31b5 100644
--- a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl
+++ b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl
@@ -357,7 +357,7 @@
 440	n64	process_madvise			sys_process_madvise
 441	n64	epoll_pwait2			sys_epoll_pwait2
 442	n64	mount_setattr			sys_mount_setattr
-443	n64	quotactl_path			sys_quotactl_path
+# 443 reserved for quotactl_path
 444	n64	landlock_create_ruleset		sys_landlock_create_ruleset
 445	n64	landlock_add_rule		sys_landlock_add_rule
 446	n64	landlock_restrict_self		sys_landlock_restrict_self
diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
index 2e68fbb57cc6..8f052ff4058c 100644
--- a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
@@ -522,7 +522,7 @@
 440	common	process_madvise			sys_process_madvise
 441	common	epoll_pwait2			sys_epoll_pwait2		compat_sys_epoll_pwait2
 442	common	mount_setattr			sys_mount_setattr
-443	common	quotactl_path			sys_quotactl_path
+# 443 reserved for quotactl_path
 444	common	landlock_create_ruleset		sys_landlock_create_ruleset
 445	common	landlock_add_rule		sys_landlock_add_rule
 446	common	landlock_restrict_self		sys_landlock_restrict_self
diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl
index 7e4a2aba366d..0690263df1dd 100644
--- a/tools/perf/arch/s390/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/s390/entry/syscalls/syscall.tbl
@@ -445,7 +445,7 @@
 440  common	process_madvise		sys_process_madvise		sys_process_madvise
 441  common	epoll_pwait2		sys_epoll_pwait2		compat_sys_epoll_pwait2
 442  common	mount_setattr		sys_mount_setattr		sys_mount_setattr
-443  common	quotactl_path		sys_quotactl_path		sys_quotactl_path
+# 443 reserved for quotactl_path
 444  common	landlock_create_ruleset	sys_landlock_create_ruleset	sys_landlock_create_ruleset
 445  common	landlock_add_rule	sys_landlock_add_rule		sys_landlock_add_rule
 446  common	landlock_restrict_self	sys_landlock_restrict_self	sys_landlock_restrict_self
diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
index ecd551b08d05..ce18119ea0d0 100644
--- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
@@ -364,7 +364,7 @@
 440	common	process_madvise		sys_process_madvise
 441	common	epoll_pwait2		sys_epoll_pwait2
 442	common	mount_setattr		sys_mount_setattr
-443	common	quotactl_path		sys_quotactl_path
+# 443 reserved for quotactl_path
 444	common	landlock_create_ruleset	sys_landlock_create_ruleset
 445	common	landlock_add_rule	sys_landlock_add_rule
 446	common	landlock_restrict_self	sys_landlock_restrict_self
diff --git a/tools/perf/builtin-buildid-list.c b/tools/perf/builtin-buildid-list.c
index 87f5b1a4a7fa..833405c27dae 100644
--- a/tools/perf/builtin-buildid-list.c
+++ b/tools/perf/builtin-buildid-list.c
@@ -80,6 +80,9 @@ static int perf_session__list_build_ids(bool force, bool with_hits)
 	if (!perf_header__has_feat(&session->header, HEADER_BUILD_ID))
 		with_hits = true;
 
+	if (zstd_init(&(session->zstd_data), 0) < 0)
+		pr_warning("Decompression initialization failed. Reported data may be incomplete.\n");
+
 	/*
 	 * in pipe-mode, the only way to get the buildids is to parse
 	 * the record stream. Buildids are stored as RECORD_HEADER_BUILD_ID
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 5a830ae09418..f9f74a514315 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -572,7 +572,8 @@ static int enable_counters(void)
 	 * - we have initial delay configured
 	 */
 	if (!target__none(&target) || stat_config.initial_delay) {
-		evlist__enable(evsel_list);
+		if (!all_counters_use_bpf)
+			evlist__enable(evsel_list);
 		if (stat_config.initial_delay > 0)
 			pr_info(EVLIST_ENABLED_MSG);
 	}
@@ -581,13 +582,19 @@ static int enable_counters(void)
 
 static void disable_counters(void)
 {
+	struct evsel *counter;
+
 	/*
 	 * If we don't have tracee (attaching to task or cpu), counters may
 	 * still be running. To get accurate group ratios, we must stop groups
 	 * from counting before reading their constituent counters.
 	 */
-	if (!target__none(&target))
-		evlist__disable(evsel_list);
+	if (!target__none(&target)) {
+		evlist__for_each_entry(evsel_list, counter)
+			bpf_counter__disable(counter);
+		if (!all_counters_use_bpf)
+			evlist__disable(evsel_list);
+	}
 }
 
 static volatile int workload_exec_errno;
diff --git a/tools/perf/scripts/python/exported-sql-viewer.py b/tools/perf/scripts/python/exported-sql-viewer.py
index 7daa8bb70a5a..711d4f9f5645 100755
--- a/tools/perf/scripts/python/exported-sql-viewer.py
+++ b/tools/perf/scripts/python/exported-sql-viewer.py
@@ -91,6 +91,11 @@
 from __future__ import print_function
 
 import sys
+# Only change warnings if the python -W option was not used
+if not sys.warnoptions:
+	import warnings
+	# PySide2 causes deprecation warnings, ignore them.
+	warnings.filterwarnings("ignore", category=DeprecationWarning)
 import argparse
 import weakref
 import threading
@@ -125,8 +130,9 @@ if pyside_version_1:
 	from PySide.QtGui import *
 	from PySide.QtSql import *
 
-from decimal import *
-from ctypes import *
+from decimal import Decimal, ROUND_HALF_UP
+from ctypes import CDLL, Structure, create_string_buffer, addressof, sizeof, \
+		   c_void_p, c_bool, c_byte, c_char, c_int, c_uint, c_longlong, c_ulonglong
 from multiprocessing import Process, Array, Value, Event
 
 # xrange is range in Python3
@@ -3868,7 +3874,7 @@ def CopyTableCellsToClipboard(view, as_csv=False, with_hdr=False):
 	if with_hdr:
 		model = indexes[0].model()
 		for col in range(min_col, max_col + 1):
-			val = model.headerData(col, Qt.Horizontal)
+			val = model.headerData(col, Qt.Horizontal, Qt.DisplayRole)
 			if as_csv:
 				text += sep + ToCSValue(val)
 				sep = ","
diff --git a/tools/perf/tests/pfm.c b/tools/perf/tests/pfm.c
index 76a53126efdf..d4b0ef74defc 100644
--- a/tools/perf/tests/pfm.c
+++ b/tools/perf/tests/pfm.c
@@ -131,8 +131,8 @@ static int test__pfm_group(void)
 		},
 		{
 			.events = "{},{instructions}",
-			.nr_events = 0,
-			.nr_groups = 0,
+			.nr_events = 1,
+			.nr_groups = 1,
 		},
 		{
 			.events = "{instructions},{instructions}",
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 8a62fb39e365..19ad64f2bd83 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -100,7 +100,7 @@ enum {
 	PERF_IP_FLAG_VMEXIT		= 1ULL << 12,
 };
 
-#define PERF_IP_FLAG_CHARS "bcrosyiABEx"
+#define PERF_IP_FLAG_CHARS "bcrosyiABExgh"
 
 #define PERF_BRANCH_MASK		(\
 	PERF_IP_FLAG_BRANCH		|\
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 6e5c41528c7d..6ea3e677dc1e 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -425,9 +425,6 @@ static void __evlist__disable(struct evlist *evlist, char *evsel_name)
 	if (affinity__setup(&affinity) < 0)
 		return;
 
-	evlist__for_each_entry(evlist, pos)
-		bpf_counter__disable(pos);
-
 	/* Disable 'immediate' events last */
 	for (imm = 0; imm <= 1; imm++) {
 		evlist__for_each_cpu(evlist, i, cpu) {
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
index 0db5f948801f..cb2520abf261 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
@@ -1205,6 +1205,8 @@ static bool intel_pt_fup_event(struct intel_pt_decoder *decoder)
 		decoder->set_fup_tx_flags = false;
 		decoder->tx_flags = decoder->fup_tx_flags;
 		decoder->state.type = INTEL_PT_TRANSACTION;
+		if (decoder->fup_tx_flags & INTEL_PT_ABORT_TX)
+			decoder->state.type |= INTEL_PT_BRANCH;
 		decoder->state.from_ip = decoder->ip;
 		decoder->state.to_ip = 0;
 		decoder->state.flags = decoder->fup_tx_flags;
@@ -1279,8 +1281,10 @@ static int intel_pt_walk_fup(struct intel_pt_decoder *decoder)
 			return 0;
 		if (err == -EAGAIN ||
 		    intel_pt_fup_with_nlip(decoder, &intel_pt_insn, ip, err)) {
+			bool no_tip = decoder->pkt_state != INTEL_PT_STATE_FUP;
+
 			decoder->pkt_state = INTEL_PT_STATE_IN_SYNC;
-			if (intel_pt_fup_event(decoder))
+			if (intel_pt_fup_event(decoder) && no_tip)
 				return 0;
 			return -EAGAIN;
 		}
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 2a5fe1514e65..154a1077f22e 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -778,8 +778,10 @@ static int intel_pt_walk_next_insn(struct intel_pt_insn *intel_pt_insn,
 
 			*ip += intel_pt_insn->length;
 
-			if (to_ip && *ip == to_ip)
+			if (to_ip && *ip == to_ip) {
+				intel_pt_insn->length = 0;
 				goto out_no_cache;
+			}
 
 			if (*ip >= al.map->end)
 				break;
@@ -1301,6 +1303,7 @@ static void intel_pt_set_pid_tid_cpu(struct intel_pt *pt,
 
 static void intel_pt_sample_flags(struct intel_pt_queue *ptq)
 {
+	ptq->insn_len = 0;
 	if (ptq->state->flags & INTEL_PT_ABORT_TX) {
 		ptq->flags = PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_TX_ABORT;
 	} else if (ptq->state->flags & INTEL_PT_ASYNC) {
@@ -1314,7 +1317,6 @@ static void intel_pt_sample_flags(struct intel_pt_queue *ptq)
 			ptq->flags = PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL |
 				     PERF_IP_FLAG_ASYNC |
 				     PERF_IP_FLAG_INTERRUPT;
-		ptq->insn_len = 0;
 	} else {
 		if (ptq->state->from_ip)
 			ptq->flags = intel_pt_insn_type(ptq->state->insn_op);
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 4dad14265b81..84108c17f48d 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -150,6 +150,10 @@ struct event_symbol event_symbols_sw[PERF_COUNT_SW_MAX] = {
 		.symbol = "bpf-output",
 		.alias  = "",
 	},
+	[PERF_COUNT_SW_CGROUP_SWITCHES] = {
+		.symbol = "cgroup-switches",
+		.alias  = "",
+	},
 };
 
 #define __PERF_EVENT_FIELD(config, name) \
@@ -2928,9 +2932,14 @@ restart:
 	}
 
 	for (i = 0; i < max; i++, syms++) {
+		/*
+		 * New attr.config still not supported here, the latest
+		 * example was PERF_COUNT_SW_CGROUP_SWITCHES
+		 */
+		if (syms->symbol == NULL)
+			continue;
 
-		if (event_glob != NULL && syms->symbol != NULL &&
-		    !(strglobmatch(syms->symbol, event_glob) ||
+		if (event_glob != NULL && !(strglobmatch(syms->symbol, event_glob) ||
 		      (syms->alias && strglobmatch(syms->alias, event_glob))))
 			continue;
 
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index fb8646cc3e83..923849024b15 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -347,6 +347,7 @@ emulation-faults				{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_EM
 dummy						{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_DUMMY); }
 duration_time					{ return tool(yyscanner, PERF_TOOL_DURATION_TIME); }
 bpf-output					{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_BPF_OUTPUT); }
+cgroup-switches					{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CGROUP_SWITCHES); }
 
 	/*
 	 * We have to handle the kernel PMU event cycles-ct/cycles-t/mem-loads/mem-stores separately.
diff --git a/tools/perf/util/pfm.c b/tools/perf/util/pfm.c
index d735acb6c29c..6eef6dfeaa57 100644
--- a/tools/perf/util/pfm.c
+++ b/tools/perf/util/pfm.c
@@ -62,8 +62,16 @@ int parse_libpfm_events_option(const struct option *opt, const char *str,
 		}
 
 		/* no event */
-		if (*q == '\0')
+		if (*q == '\0') {
+			if (*sep == '}') {
+				if (grp_evt < 0) {
+					ui__error("cannot close a non-existing event group\n");
+					goto error;
+				}
+				grp_evt--;
+			}
 			continue;
+		}
 
 		memset(&attr, 0, sizeof(attr));
 		event_attr_init(&attr);
@@ -107,6 +115,7 @@ int parse_libpfm_events_option(const struct option *opt, const char *str,
 			grp_evt = -1;
 		}
 	}
+	free(p_orig);
 	return 0;
 error:
 	free(p_orig);
diff --git a/tools/scripts/Makefile.include b/tools/scripts/Makefile.include
index f9271f3ea912..071312f5eb92 100644
--- a/tools/scripts/Makefile.include
+++ b/tools/scripts/Makefile.include
@@ -131,29 +131,29 @@ QUIET_SUBDIR1  =
 
 ifneq ($(silent),1)
   ifneq ($(V),1)
-	QUIET_CC       = @echo '  CC       '$@;
-	QUIET_CC_FPIC  = @echo '  CC FPIC  '$@;
-	QUIET_CLANG    = @echo '  CLANG    '$@;
-	QUIET_AR       = @echo '  AR       '$@;
-	QUIET_LINK     = @echo '  LINK     '$@;
-	QUIET_MKDIR    = @echo '  MKDIR    '$@;
-	QUIET_GEN      = @echo '  GEN      '$@;
+	QUIET_CC       = @echo '  CC      '$@;
+	QUIET_CC_FPIC  = @echo '  CC FPIC '$@;
+	QUIET_CLANG    = @echo '  CLANG   '$@;
+	QUIET_AR       = @echo '  AR      '$@;
+	QUIET_LINK     = @echo '  LINK    '$@;
+	QUIET_MKDIR    = @echo '  MKDIR   '$@;
+	QUIET_GEN      = @echo '  GEN     '$@;
 	QUIET_SUBDIR0  = +@subdir=
 	QUIET_SUBDIR1  = ;$(NO_SUBDIR) \
-			  echo '  SUBDIR   '$$subdir; \
+			  echo '  SUBDIR  '$$subdir; \
 			 $(MAKE) $(PRINT_DIR) -C $$subdir
-	QUIET_FLEX     = @echo '  FLEX     '$@;
-	QUIET_BISON    = @echo '  BISON    '$@;
-	QUIET_GENSKEL  = @echo '  GEN-SKEL '$@;
+	QUIET_FLEX     = @echo '  FLEX    '$@;
+	QUIET_BISON    = @echo '  BISON   '$@;
+	QUIET_GENSKEL  = @echo '  GENSKEL '$@;
 
 	descend = \
-		+@echo	       '  DESCEND  '$(1); \
+		+@echo	       '  DESCEND '$(1); \
 		mkdir -p $(OUTPUT)$(1) && \
 		$(MAKE) $(COMMAND_O) subdir=$(if $(subdir),$(subdir)/$(1),$(1)) $(PRINT_DIR) -C $(1) $(2)
 
-	QUIET_CLEAN    = @printf '  CLEAN    %s\n' $1;
-	QUIET_INSTALL  = @printf '  INSTALL  %s\n' $1;
-	QUIET_UNINST   = @printf '  UNINST   %s\n' $1;
+	QUIET_CLEAN    = @printf '  CLEAN   %s\n' $1;
+	QUIET_INSTALL  = @printf '  INSTALL %s\n' $1;
+	QUIET_UNINST   = @printf '  UNINST  %s\n' $1;
   endif
 endif
 
diff --git a/tools/testing/nvdimm/test/iomap.c b/tools/testing/nvdimm/test/iomap.c
index c62d372d426f..ed563bdd88f3 100644
--- a/tools/testing/nvdimm/test/iomap.c
+++ b/tools/testing/nvdimm/test/iomap.c
@@ -62,7 +62,7 @@ struct nfit_test_resource *get_nfit_res(resource_size_t resource)
 }
 EXPORT_SYMBOL(get_nfit_res);
 
-void __iomem *__nfit_test_ioremap(resource_size_t offset, unsigned long size,
+static void __iomem *__nfit_test_ioremap(resource_size_t offset, unsigned long size,
 		void __iomem *(*fallback_fn)(resource_size_t, unsigned long))
 {
 	struct nfit_test_resource *nfit_res = get_nfit_res(offset);
diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c
index 9b185bf82da8..54f367cbadae 100644
--- a/tools/testing/nvdimm/test/nfit.c
+++ b/tools/testing/nvdimm/test/nfit.c
@@ -1871,9 +1871,16 @@ static void smart_init(struct nfit_test *t)
 	}
 }
 
+static size_t sizeof_spa(struct acpi_nfit_system_address *spa)
+{
+	/* until spa location cookie support is added... */
+	return sizeof(*spa) - 8;
+}
+
 static int nfit_test0_alloc(struct nfit_test *t)
 {
-	size_t nfit_size = sizeof(struct acpi_nfit_system_address) * NUM_SPA
+	struct acpi_nfit_system_address *spa = NULL;
+	size_t nfit_size = sizeof_spa(spa) * NUM_SPA
 			+ sizeof(struct acpi_nfit_memory_map) * NUM_MEM
 			+ sizeof(struct acpi_nfit_control_region) * NUM_DCR
 			+ offsetof(struct acpi_nfit_control_region,
@@ -1937,7 +1944,8 @@ static int nfit_test0_alloc(struct nfit_test *t)
 
 static int nfit_test1_alloc(struct nfit_test *t)
 {
-	size_t nfit_size = sizeof(struct acpi_nfit_system_address) * 2
+	struct acpi_nfit_system_address *spa = NULL;
+	size_t nfit_size = sizeof_spa(spa) * 2
 		+ sizeof(struct acpi_nfit_memory_map) * 2
 		+ offsetof(struct acpi_nfit_control_region, window_size) * 2;
 	int i;
@@ -2000,7 +2008,7 @@ static void nfit_test0_setup(struct nfit_test *t)
 	 */
 	spa = nfit_buf;
 	spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS;
-	spa->header.length = sizeof(*spa);
+	spa->header.length = sizeof_spa(spa);
 	memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_PM), 16);
 	spa->range_index = 0+1;
 	spa->address = t->spa_set_dma[0];
@@ -2014,7 +2022,7 @@ static void nfit_test0_setup(struct nfit_test *t)
 	 */
 	spa = nfit_buf + offset;
 	spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS;
-	spa->header.length = sizeof(*spa);
+	spa->header.length = sizeof_spa(spa);
 	memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_PM), 16);
 	spa->range_index = 1+1;
 	spa->address = t->spa_set_dma[1];
@@ -2024,7 +2032,7 @@ static void nfit_test0_setup(struct nfit_test *t)
 	/* spa2 (dcr0) dimm0 */
 	spa = nfit_buf + offset;
 	spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS;
-	spa->header.length = sizeof(*spa);
+	spa->header.length = sizeof_spa(spa);
 	memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_DCR), 16);
 	spa->range_index = 2+1;
 	spa->address = t->dcr_dma[0];
@@ -2034,7 +2042,7 @@ static void nfit_test0_setup(struct nfit_test *t)
 	/* spa3 (dcr1) dimm1 */
 	spa = nfit_buf + offset;
 	spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS;
-	spa->header.length = sizeof(*spa);
+	spa->header.length = sizeof_spa(spa);
 	memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_DCR), 16);
 	spa->range_index = 3+1;
 	spa->address = t->dcr_dma[1];
@@ -2044,7 +2052,7 @@ static void nfit_test0_setup(struct nfit_test *t)
 	/* spa4 (dcr2) dimm2 */
 	spa = nfit_buf + offset;
 	spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS;
-	spa->header.length = sizeof(*spa);
+	spa->header.length = sizeof_spa(spa);
 	memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_DCR), 16);
 	spa->range_index = 4+1;
 	spa->address = t->dcr_dma[2];
@@ -2054,7 +2062,7 @@ static void nfit_test0_setup(struct nfit_test *t)
 	/* spa5 (dcr3) dimm3 */
 	spa = nfit_buf + offset;
 	spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS;
-	spa->header.length = sizeof(*spa);
+	spa->header.length = sizeof_spa(spa);
 	memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_DCR), 16);
 	spa->range_index = 5+1;
 	spa->address = t->dcr_dma[3];
@@ -2064,7 +2072,7 @@ static void nfit_test0_setup(struct nfit_test *t)
 	/* spa6 (bdw for dcr0) dimm0 */
 	spa = nfit_buf + offset;
 	spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS;
-	spa->header.length = sizeof(*spa);
+	spa->header.length = sizeof_spa(spa);
 	memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_BDW), 16);
 	spa->range_index = 6+1;
 	spa->address = t->dimm_dma[0];
@@ -2074,7 +2082,7 @@ static void nfit_test0_setup(struct nfit_test *t)
 	/* spa7 (bdw for dcr1) dimm1 */
 	spa = nfit_buf + offset;
 	spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS;
-	spa->header.length = sizeof(*spa);
+	spa->header.length = sizeof_spa(spa);
 	memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_BDW), 16);
 	spa->range_index = 7+1;
 	spa->address = t->dimm_dma[1];
@@ -2084,7 +2092,7 @@ static void nfit_test0_setup(struct nfit_test *t)
 	/* spa8 (bdw for dcr2) dimm2 */
 	spa = nfit_buf + offset;
 	spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS;
-	spa->header.length = sizeof(*spa);
+	spa->header.length = sizeof_spa(spa);
 	memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_BDW), 16);
 	spa->range_index = 8+1;
 	spa->address = t->dimm_dma[2];
@@ -2094,7 +2102,7 @@ static void nfit_test0_setup(struct nfit_test *t)
 	/* spa9 (bdw for dcr3) dimm3 */
 	spa = nfit_buf + offset;
 	spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS;
-	spa->header.length = sizeof(*spa);
+	spa->header.length = sizeof_spa(spa);
 	memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_BDW), 16);
 	spa->range_index = 9+1;
 	spa->address = t->dimm_dma[3];
@@ -2581,7 +2589,7 @@ static void nfit_test0_setup(struct nfit_test *t)
 		/* spa10 (dcr4) dimm4 */
 		spa = nfit_buf + offset;
 		spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS;
-		spa->header.length = sizeof(*spa);
+		spa->header.length = sizeof_spa(spa);
 		memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_DCR), 16);
 		spa->range_index = 10+1;
 		spa->address = t->dcr_dma[4];
@@ -2595,7 +2603,7 @@ static void nfit_test0_setup(struct nfit_test *t)
 		 */
 		spa = nfit_buf + offset;
 		spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS;
-		spa->header.length = sizeof(*spa);
+		spa->header.length = sizeof_spa(spa);
 		memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_PM), 16);
 		spa->range_index = 11+1;
 		spa->address = t->spa_set_dma[2];
@@ -2605,7 +2613,7 @@ static void nfit_test0_setup(struct nfit_test *t)
 		/* spa12 (bdw for dcr4) dimm4 */
 		spa = nfit_buf + offset;
 		spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS;
-		spa->header.length = sizeof(*spa);
+		spa->header.length = sizeof_spa(spa);
 		memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_BDW), 16);
 		spa->range_index = 12+1;
 		spa->address = t->dimm_dma[4];
@@ -2739,7 +2747,7 @@ static void nfit_test1_setup(struct nfit_test *t)
 	/* spa0 (flat range with no bdw aliasing) */
 	spa = nfit_buf + offset;
 	spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS;
-	spa->header.length = sizeof(*spa);
+	spa->header.length = sizeof_spa(spa);
 	memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_PM), 16);
 	spa->range_index = 0+1;
 	spa->address = t->spa_set_dma[0];
@@ -2749,7 +2757,7 @@ static void nfit_test1_setup(struct nfit_test *t)
 	/* virtual cd region */
 	spa = nfit_buf + offset;
 	spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS;
-	spa->header.length = sizeof(*spa);
+	spa->header.length = sizeof_spa(spa);
 	memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_VCD), 16);
 	spa->range_index = 0;
 	spa->address = t->spa_set_dma[1];
diff --git a/tools/testing/selftests/arm64/bti/test.c b/tools/testing/selftests/arm64/bti/test.c
index 656b04976ccc..67b77ab83c20 100644
--- a/tools/testing/selftests/arm64/bti/test.c
+++ b/tools/testing/selftests/arm64/bti/test.c
@@ -6,6 +6,7 @@
 
 #include "system.h"
 
+#include <stddef.h>
 #include <linux/errno.h>
 #include <linux/auxvec.h>
 #include <linux/signal.h>
diff --git a/tools/testing/selftests/exec/Makefile b/tools/testing/selftests/exec/Makefile
index cf69b2fcce59..dd61118df66e 100644
--- a/tools/testing/selftests/exec/Makefile
+++ b/tools/testing/selftests/exec/Makefile
@@ -28,8 +28,8 @@ $(OUTPUT)/execveat.denatured: $(OUTPUT)/execveat
 	cp $< $@
 	chmod -x $@
 $(OUTPUT)/load_address_4096: load_address.c
-	$(CC) $(CFLAGS) $(LDFLAGS) -Wl,-z,max-page-size=0x1000 -pie $< -o $@
+	$(CC) $(CFLAGS) $(LDFLAGS) -Wl,-z,max-page-size=0x1000 -pie -static $< -o $@
 $(OUTPUT)/load_address_2097152: load_address.c
-	$(CC) $(CFLAGS) $(LDFLAGS) -Wl,-z,max-page-size=0x200000 -pie $< -o $@
+	$(CC) $(CFLAGS) $(LDFLAGS) -Wl,-z,max-page-size=0x200000 -pie -static $< -o $@
 $(OUTPUT)/load_address_16777216: load_address.c
-	$(CC) $(CFLAGS) $(LDFLAGS) -Wl,-z,max-page-size=0x1000000 -pie $< -o $@
+	$(CC) $(CFLAGS) $(LDFLAGS) -Wl,-z,max-page-size=0x1000000 -pie -static $< -o $@
diff --git a/tools/testing/selftests/perf_events/sigtrap_threads.c b/tools/testing/selftests/perf_events/sigtrap_threads.c
index 78ddf5e11625..8e83cf91513a 100644
--- a/tools/testing/selftests/perf_events/sigtrap_threads.c
+++ b/tools/testing/selftests/perf_events/sigtrap_threads.c
@@ -43,7 +43,7 @@ static struct {
 	siginfo_t first_siginfo;	/* First observed siginfo_t. */
 } ctx;
 
-/* Unique value to check si_perf is correctly set from perf_event_attr::sig_data. */
+/* Unique value to check si_perf_data is correctly set from perf_event_attr::sig_data. */
 #define TEST_SIG_DATA(addr) (~(unsigned long)(addr))
 
 static struct perf_event_attr make_event_attr(bool enabled, volatile void *addr)
@@ -164,8 +164,8 @@ TEST_F(sigtrap_threads, enable_event)
 	EXPECT_EQ(ctx.signal_count, NUM_THREADS);
 	EXPECT_EQ(ctx.tids_want_signal, 0);
 	EXPECT_EQ(ctx.first_siginfo.si_addr, &ctx.iterate_on);
-	EXPECT_EQ(ctx.first_siginfo.si_errno, PERF_TYPE_BREAKPOINT);
-	EXPECT_EQ(ctx.first_siginfo.si_perf, TEST_SIG_DATA(&ctx.iterate_on));
+	EXPECT_EQ(ctx.first_siginfo.si_perf_type, PERF_TYPE_BREAKPOINT);
+	EXPECT_EQ(ctx.first_siginfo.si_perf_data, TEST_SIG_DATA(&ctx.iterate_on));
 
 	/* Check enabled for parent. */
 	ctx.iterate_on = 0;
@@ -183,8 +183,8 @@ TEST_F(sigtrap_threads, modify_and_enable_event)
 	EXPECT_EQ(ctx.signal_count, NUM_THREADS);
 	EXPECT_EQ(ctx.tids_want_signal, 0);
 	EXPECT_EQ(ctx.first_siginfo.si_addr, &ctx.iterate_on);
-	EXPECT_EQ(ctx.first_siginfo.si_errno, PERF_TYPE_BREAKPOINT);
-	EXPECT_EQ(ctx.first_siginfo.si_perf, TEST_SIG_DATA(&ctx.iterate_on));
+	EXPECT_EQ(ctx.first_siginfo.si_perf_type, PERF_TYPE_BREAKPOINT);
+	EXPECT_EQ(ctx.first_siginfo.si_perf_data, TEST_SIG_DATA(&ctx.iterate_on));
 
 	/* Check enabled for parent. */
 	ctx.iterate_on = 0;
@@ -203,8 +203,8 @@ TEST_F(sigtrap_threads, signal_stress)
 	EXPECT_EQ(ctx.signal_count, NUM_THREADS * ctx.iterate_on);
 	EXPECT_EQ(ctx.tids_want_signal, 0);
 	EXPECT_EQ(ctx.first_siginfo.si_addr, &ctx.iterate_on);
-	EXPECT_EQ(ctx.first_siginfo.si_errno, PERF_TYPE_BREAKPOINT);
-	EXPECT_EQ(ctx.first_siginfo.si_perf, TEST_SIG_DATA(&ctx.iterate_on));
+	EXPECT_EQ(ctx.first_siginfo.si_perf_type, PERF_TYPE_BREAKPOINT);
+	EXPECT_EQ(ctx.first_siginfo.si_perf_data, TEST_SIG_DATA(&ctx.iterate_on));
 }
 
 TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c
index 98c3b647f54d..e3d5c77a8612 100644
--- a/tools/testing/selftests/seccomp/seccomp_bpf.c
+++ b/tools/testing/selftests/seccomp/seccomp_bpf.c
@@ -1753,16 +1753,25 @@ TEST_F(TRACE_poke, getpid_runs_normally)
 # define SYSCALL_RET_SET(_regs, _val)				\
 	do {							\
 		typeof(_val) _result = (_val);			\
-		/*						\
-		 * A syscall error is signaled by CR0 SO bit	\
-		 * and the code is stored as a positive value.	\
-		 */						\
-		if (_result < 0) {				\
-			SYSCALL_RET(_regs) = -_result;		\
-			(_regs).ccr |= 0x10000000;		\
-		} else {					\
+		if ((_regs.trap & 0xfff0) == 0x3000) {		\
+			/*					\
+			 * scv 0 system call uses -ve result	\
+			 * for error, so no need to adjust.	\
+			 */					\
 			SYSCALL_RET(_regs) = _result;		\
-			(_regs).ccr &= ~0x10000000;		\
+		} else {					\
+			/*					\
+			 * A syscall error is signaled by the	\
+			 * CR0 SO bit and the code is stored as	\
+			 * a positive value.			\
+			 */					\
+			if (_result < 0) {			\
+				SYSCALL_RET(_regs) = -_result;	\
+				(_regs).ccr |= 0x10000000;	\
+			} else {				\
+				SYSCALL_RET(_regs) = _result;	\
+				(_regs).ccr &= ~0x10000000;	\
+			}					\
 		}						\
 	} while (0)
 # define SYSCALL_RET_SET_ON_PTRACE_EXIT