Merge tag 'perf-tools-for-v6.5-2-2023-07-06' of git://git.kernel.org/…

…pub/scm/linux/kernel/git/perf/perf-tools-next

Pull more perf tools updates from Namhyung Kim:
 "These are remaining changes and fixes for this cycle.

  Build:

   - Allow generating vmlinux.h from BTF using `make GEN_VMLINUX_H=1`
     and skip if the vmlinux has no BTF.

   - Replace deprecated clang -target xxx option by --target=xxx.

  perf record:

   - Print event attributes with well known type and config symbols in
     the debug output like below:

       # perf record -e cycles,cpu-clock -C0 -vv true
       <SNIP>
       ------------------------------------------------------------
       perf_event_attr:
         type                             0 (PERF_TYPE_HARDWARE)
         size                             136
         config                           0 (PERF_COUNT_HW_CPU_CYCLES)
         { sample_period, sample_freq }   4000
         sample_type                      IP|TID|TIME|CPU|PERIOD|IDENTIFIER
         read_format                      ID
         disabled                         1
         inherit                          1
         freq                             1
         sample_id_all                    1
         exclude_guest                    1
       ------------------------------------------------------------
       sys_perf_event_open: pid -1  cpu 0  group_fd -1  flags 0x8 = 5
       ------------------------------------------------------------
       perf_event_attr:
         type                             1 (PERF_TYPE_SOFTWARE)
         size                             136
         config                           0 (PERF_COUNT_SW_CPU_CLOCK)
         { sample_period, sample_freq }   4000
         sample_type                      IP|TID|TIME|CPU|PERIOD|IDENTIFIER
         read_format                      ID
         disabled                         1
         inherit                          1
         freq                             1
         sample_id_all                    1
         exclude_guest                    1

   - Update AMD IBS event error message since it now support per-process
     profiling but no priviledge filters.

       $ sudo perf record -e ibs_op//k -C 0
       Error:
       AMD IBS doesn't support privilege filtering. Try again without
       the privilege modifiers (like 'k') at the end.

  perf lock contention:

   - Support CSV style output using -x option

       $ sudo perf lock con -ab -x, sleep 1
       # output: contended, total wait, max wait, avg wait, type, caller
       19, 194232, 21415, 10222, spinlock, process_one_work+0x1f0
       15, 162748, 23843, 10849, rwsem:R, do_user_addr_fault+0x40e
       4, 86740, 23415, 21685, rwlock:R, ep_poll_callback+0x2d
       1, 84281, 84281, 84281, mutex, iwl_mvm_async_handlers_wk+0x135
       8, 67608, 27404, 8451, spinlock, __queue_work+0x174
       3, 58616, 31125, 19538, rwsem:W, do_mprotect_pkey+0xff
       3, 52953, 21172, 17651, rwlock:W, do_epoll_wait+0x248
       2, 30324, 19704, 15162, rwsem:R, do_madvise+0x3ad
       1, 24619, 24619, 24619, spinlock, rcu_core+0xd4

   - Add --output option to save the data to a file not to be interfered
     by other debug messages.

  Test:

   - Fix event parsing test on ARM where there's no raw PMU nor supports
     PERF_PMU_CAP_EXTENDED_HW_TYPE.

   - Update the lock contention test case for CSV output.

   - Fix a segfault in the daemon command test.

  Vendor events (JSON):

   - Add has_event() to check if the given event is available on system
     at runtime. On Intel machines, some transaction events may not be
     present when TSC extensions are disabled.

   - Update Intel event metrics.

  Misc:

   - Sort symbols by name using an external array of pointers instead of
     a rbtree node in the symbol. This will save 16-bytes or 24-bytes
     per symbol whether the sorting is actually requested or not.

   - Fix unwinding DWARF callstacks using libdw when --symfs option is
     used"

* tag 'perf-tools-for-v6.5-2-2023-07-06' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools-next: (38 commits)
  perf test: Fix event parsing test when PERF_PMU_CAP_EXTENDED_HW_TYPE isn't supported.
  perf test: Fix event parsing test on Arm
  perf evsel amd: Fix IBS error message
  perf: unwind: Fix symfs with libdw
  perf symbol: Fix uninitialized return value in symbols__find_by_name()
  perf test: Test perf lock contention CSV output
  perf lock contention: Add --output option
  perf lock contention: Add -x option for CSV style output
  perf lock: Remove stale comments
  perf vendor events intel: Update tigerlake to 1.13
  perf vendor events intel: Update skylakex to 1.31
  perf vendor events intel: Update skylake to 57
  perf vendor events intel: Update sapphirerapids to 1.14
  perf vendor events intel: Update icelakex to 1.21
  perf vendor events intel: Update icelake to 1.19
  perf vendor events intel: Update cascadelakex to 1.19
  perf vendor events intel: Update meteorlake to 1.03
  perf vendor events intel: Add rocketlake events/metrics
  perf vendor metrics intel: Make transaction metrics conditional
  perf jevents: Support for has_event function
  ...

tools/perf/Documentation/perf-config.txt

@@ -669,7 +669,7 @@ llvm.*::
 		"$CLANG_OPTIONS $PERF_BPF_INC_OPTIONS $KERNEL_INC_OPTIONS " \
 		"-Wno-unused-value -Wno-pointer-sign "		\
 		"-working-directory $WORKING_DIR "		\
-		"-c \"$CLANG_SOURCE\" -target bpf $CLANG_EMIT_LLVM -O2 -o - $LLVM_OPTIONS_PIPE"
+		"-c \"$CLANG_SOURCE\" --target=bpf $CLANG_EMIT_LLVM -O2 -o - $LLVM_OPTIONS_PIPE"
 
 	llvm.clang-opt::
 		Options passed to clang.

tools/perf/Documentation/perf-lock.txt

@@ -36,6 +36,9 @@ COMMON OPTIONS
 --input=<file>::
         Input file name. (default: perf.data unless stdin is a fifo)
 
+--output=<file>::
+        Output file name for perf lock contention and report.
+
 -v::
 --verbose::
         Be more verbose (show symbol address, etc).
@@ -200,6 +203,11 @@ CONTENTION OPTIONS
 	Note that it matches the substring so 'rq' would match both 'raw_spin_rq_lock'
 	and 'irq_enter_rcu'.
 
+-x::
+--field-separator=<SEP>::
+	Show results using a CSV-style output to make it easy to import directly
+	into spreadsheets. Columns are separated by the string specified in SEP.
+
 
 SEE ALSO
 --------

tools/perf/Makefile.config

@@ -315,6 +315,9 @@ FEATURE_CHECK_LDFLAGS-libpython := $(PYTHON_EMBED_LDOPTS)
 
 FEATURE_CHECK_LDFLAGS-libaio = -lrt
 
+FEATURE_CHECK_LDFLAGS-disassembler-four-args = -lbfd -lopcodes -ldl
+FEATURE_CHECK_LDFLAGS-disassembler-init-styled = -lbfd -lopcodes -ldl
+
 CORE_CFLAGS += -fno-omit-frame-pointer
 CORE_CFLAGS += -ggdb3
 CORE_CFLAGS += -funwind-tables
@@ -344,8 +347,8 @@ ifneq ($(TCMALLOC),)
 endif
 
 ifeq ($(FEATURES_DUMP),)
-# We will display at the end of this Makefile.config, using $(call feature_display_entries),
-# as we may retry some feature detection here.
+# We will display at the end of this Makefile.config, using $(call feature_display_entries)
+# As we may retry some feature detection here, see the disassembler-four-args case, for instance
   FEATURE_DISPLAY_DEFERRED := 1
 include $(srctree)/tools/build/Makefile.feature
 else
@@ -680,6 +683,10 @@ ifdef BUILD_BPF_SKEL
   CFLAGS += -DHAVE_BPF_SKEL
 endif
 
+ifndef GEN_VMLINUX_H
+  VMLINUX_H=$(src-perf)/util/bpf_skel/vmlinux/vmlinux.h
+endif
+
 dwarf-post-unwind := 1
 dwarf-post-unwind-text := BUG
 
@@ -903,9 +910,13 @@ ifdef BUILD_NONDISTRO
 
     ifeq ($(feature-libbfd-liberty), 1)
       EXTLIBS += -lbfd -lopcodes -liberty
+      FEATURE_CHECK_LDFLAGS-disassembler-four-args += -liberty -ldl
+      FEATURE_CHECK_LDFLAGS-disassembler-init-styled += -liberty -ldl
     else
       ifeq ($(feature-libbfd-liberty-z), 1)
         EXTLIBS += -lbfd -lopcodes -liberty -lz
+        FEATURE_CHECK_LDFLAGS-disassembler-four-args += -liberty -lz -ldl
+        FEATURE_CHECK_LDFLAGS-disassembler-init-styled += -liberty -lz -ldl
       endif
     endif
     $(call feature_check,disassembler-four-args)
@@ -1329,6 +1340,6 @@ endif
 
 # re-generate FEATURE-DUMP as we may have called feature_check, found out
 # extra libraries to add to LDFLAGS of some other test and then redo those
-# tests.
+# tests, see the block about libbfd, disassembler-four-args, for instance.
 $(shell rm -f $(FEATURE_DUMP_FILENAME))
 $(foreach feat,$(FEATURE_TESTS),$(shell echo "$(call feature_assign,$(feat))" >> $(FEATURE_DUMP_FILENAME)))

tools/perf/Makefile.perf

@@ -132,6 +132,8 @@ include ../scripts/utilities.mak
 # Define EXTRA_TESTS to enable building extra tests useful mainly to perf
 # developers, such as:
 #	x86 instruction decoder - new instructions test
+#
+# Define GEN_VMLINUX_H to generate vmlinux.h from the BTF.
 
 # As per kernel Makefile, avoid funny character set dependencies
 unexport LC_ALL
@@ -197,6 +199,7 @@ FLEX    ?= flex
 BISON   ?= bison
 STRIP   = strip
 AWK     = awk
+READELF ?= readelf
 
 # include Makefile.config by default and rule out
 # non-config cases
@@ -1061,7 +1064,7 @@ $(SKEL_TMP_OUT) $(LIBAPI_OUTPUT) $(LIBBPF_OUTPUT) $(LIBPERF_OUTPUT) $(LIBSUBCMD_
 ifdef BUILD_BPF_SKEL
 BPFTOOL := $(SKEL_TMP_OUT)/bootstrap/bpftool
 # Get Clang's default includes on this system, as opposed to those seen by
-# '-target bpf'. This fixes "missing" files on some architectures/distros,
+# '--target=bpf'. This fixes "missing" files on some architectures/distros,
 # such as asm/byteorder.h, asm/socket.h, asm/sockios.h, sys/cdefs.h etc.
 #
 # Use '-idirafter': Don't interfere with include mechanics except where the
@@ -1084,8 +1087,44 @@ $(BPFTOOL): | $(SKEL_TMP_OUT)
 	$(Q)CFLAGS= $(MAKE) -C ../bpf/bpftool \
 		OUTPUT=$(SKEL_TMP_OUT)/ bootstrap
 
-$(SKEL_TMP_OUT)/%.bpf.o: util/bpf_skel/%.bpf.c $(LIBBPF) | $(SKEL_TMP_OUT)
-	$(QUIET_CLANG)$(CLANG) -g -O2 -target bpf -Wall -Werror $(BPF_INCLUDE) $(TOOLS_UAPI_INCLUDE) \
+# Paths to search for a kernel to generate vmlinux.h from.
+VMLINUX_BTF_ELF_PATHS ?= $(if $(O),$(O)/vmlinux)			\
+		     $(if $(KBUILD_OUTPUT),$(KBUILD_OUTPUT)/vmlinux)	\
+		     ../../vmlinux					\
+		     /boot/vmlinux-$(shell uname -r)
+
+# Paths to BTF information.
+VMLINUX_BTF_BTF_PATHS ?= /sys/kernel/btf/vmlinux
+
+# Filter out kernels that don't exist or without a BTF section.
+VMLINUX_BTF_ELF_ABSPATHS ?= $(abspath $(wildcard $(VMLINUX_BTF_ELF_PATHS)))
+VMLINUX_BTF_PATHS ?= $(shell for file in $(VMLINUX_BTF_ELF_ABSPATHS); \
+			do \
+				if [ -f $$file ] && ($(READELF) -S "$$file" | grep -q .BTF); \
+				then \
+					echo "$$file"; \
+				fi; \
+			done) \
+			$(wildcard $(VMLINUX_BTF_BTF_PATHS))
+
+# Select the first as the source of vmlinux.h.
+VMLINUX_BTF ?= $(firstword $(VMLINUX_BTF_PATHS))
+
+ifeq ($(VMLINUX_H),)
+  ifeq ($(VMLINUX_BTF),)
+    $(error Missing bpftool input for generating vmlinux.h)
+  endif
+endif
+
+$(SKEL_OUT)/vmlinux.h: $(VMLINUX_BTF) $(BPFTOOL)
+ifeq ($(VMLINUX_H),)
+	$(QUIET_GEN)$(BPFTOOL) btf dump file $< format c > $@
+else
+	$(Q)cp "$(VMLINUX_H)" $@
+endif
+
+$(SKEL_TMP_OUT)/%.bpf.o: util/bpf_skel/%.bpf.c $(LIBBPF) $(SKEL_OUT)/vmlinux.h | $(SKEL_TMP_OUT)
+	$(QUIET_CLANG)$(CLANG) -g -O2 --target=bpf -Wall -Werror $(BPF_INCLUDE) $(TOOLS_UAPI_INCLUDE) \
 	  -c $(filter util/bpf_skel/%.bpf.c,$^) -o $@
 
 $(SKEL_OUT)/%.skel.h: $(SKEL_TMP_OUT)/%.bpf.o | $(BPFTOOL)

tools/perf/arch/x86/util/evsel.c

@@ -102,3 +102,23 @@ void arch__post_evsel_config(struct evsel *evsel, struct perf_event_attr *attr)
 		}
 	}
 }
+
+int arch_evsel__open_strerror(struct evsel *evsel, char *msg, size_t size)
+{
+	if (!x86__is_amd_cpu())
+		return 0;
+
+	if (!evsel->core.attr.precise_ip &&
+	    !(evsel->pmu_name && !strncmp(evsel->pmu_name, "ibs", 3)))
+		return 0;
+
+	/* More verbose IBS errors. */
+	if (evsel->core.attr.exclude_kernel || evsel->core.attr.exclude_user ||
+	    evsel->core.attr.exclude_hv || evsel->core.attr.exclude_idle ||
+	    evsel->core.attr.exclude_host || evsel->core.attr.exclude_guest) {
+		return scnprintf(msg, size, "AMD IBS doesn't support privilege filtering. Try "
+				 "again without the privilege modifiers (like 'k') at the end.");
+	}
+
+	return 0;
+}

tools/perf/builtin-daemon.c

@@ -1524,7 +1524,7 @@ int cmd_daemon(int argc, const char **argv)
 	if (argc) {
 		if (!strcmp(argv[0], "start"))
 			ret = __cmd_start(&__daemon, daemon_options, argc, argv);
-		if (!strcmp(argv[0], "signal"))
+		else if (!strcmp(argv[0], "signal"))
 			ret = __cmd_signal(&__daemon, daemon_options, argc, argv);
 		else if (!strcmp(argv[0], "stop"))
 			ret = __cmd_stop(&__daemon, daemon_options, argc, argv);

tools/perf/builtin-kallsyms.c

@@ -62,7 +62,6 @@ int cmd_kallsyms(int argc, const char **argv)
 	if (argc < 1)
 		usage_with_options(kallsyms_usage, options);
 
-	symbol_conf.sort_by_name = true;
 	symbol_conf.try_vmlinux_path = (symbol_conf.vmlinux_name == NULL);
 	if (symbol__init(NULL) < 0)
 		return -1;