Merge tag 'perf-tools-fixes-for-v5.13-2021-05-24' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux

Pull perf tool fixes from Arnaldo Carvalho de Melo:

 - Fix 'perf script' decoding of Intel PT traces for abort handling and
   sample instruction bytes.

 - Add missing PERF_IP_FLAG_CHARS for VM-Entry and VM-Exit to Intel PT
   'perf script' decoder.

 - Fixes for the python based Intel PT trace viewer GUI.

 - Sync UAPI copies (unwire quotactl_path, some comment fixes).

 - Fix handling of missing kernel software events, such as the recently
   added 'cgroup-switches', and add the trivial glue for it in the
   tooling side, since it was added in this merge window.

 - Add missing initialization of zstd_data in 'perf buildid-list',
   detected with valgrind's memcheck.

 - Remove needless event enable/disable when all events uses BPF.

 - Fix libpfm4 support (63) test error for nested event groups.

* tag 'perf-tools-fixes-for-v5.13-2021-05-24' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux:
  perf stat: Skip evlist__[enable|disable] when all events uses BPF
  perf script: Add missing PERF_IP_FLAG_CHARS for VM-Entry and VM-Exit
  perf scripts python: exported-sql-viewer.py: Fix warning display
  perf scripts python: exported-sql-viewer.py: Fix Array TypeError
  perf scripts python: exported-sql-viewer.py: Fix copy to clipboard from Top Calls by elapsed Time report
  tools headers UAPI: Sync files changed by the quotactl_path unwiring
  tools headers UAPI: Sync linux/perf_event.h with the kernel sources
  tools headers UAPI: Sync linux/fs.h with the kernel sources
  perf parse-events: Check if the software events array slots are populated
  perf tools: Add 'cgroup-switches' software event
  perf intel-pt: Remove redundant setting of ptq->insn_len
  perf intel-pt: Fix sample instruction bytes
  perf intel-pt: Fix transaction abort handling
  perf test: Fix libpfm4 support (63) test error for nested event groups
  tools arch kvm: Sync kvm headers with the kernel sources
  perf buildid-list: Initialize zstd_data

20 files changed, 71 insertions, 30 deletions

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/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/perf/Documentation/perf-intel-pt.txt b/tools/perf/Documentation/perf-intel-pt.txt
index 1dcec73c910c..bcf3eca5afbe 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 8c59677bee13..20ad663978cc 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
@@ -1146,6 +1146,8 @@ 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;
@@ -1220,8 +1222,10 @@ 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 8658d42ce57a..0dfec8761b9a 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -707,8 +707,10 @@ 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;
@@ -1198,6 +1200,7 @@ 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) {
@@ -1211,7 +1214,6 @@ 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);