Merge tag 'perf-urgent-2020-04-05' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull more perf updates from Thomas Gleixner:
 "Perf updates all over the place:

  core:

   - Support for cgroup tracking in samples to allow cgroup based
     analysis

  tools:

   - Support for cgroup analysis

   - Commandline option and hotkey for perf top to change the sort order

   - A set of fixes all over the place

   - Various build system related improvements

   - Updates of the X86 pmu event JSON data

   - Documentation updates"

* tag 'perf-urgent-2020-04-05' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (55 commits)
  perf python: Fix clang detection to strip out options passed in $CC
  perf tools: Support Python 3.8+ in Makefile
  perf script: Fix invalid read of directory entry after closedir()
  perf script report: Fix SEGFAULT when using DWARF mode
  perf script: add -S/--symbols documentation
  perf pmu-events x86: Use CPU_CLK_UNHALTED.THREAD in Kernel_Utilization metric
  perf events parser: Add missing Intel CPU events to parser
  perf script: Allow --symbol to accept hexadecimal addresses
  perf report/top TUI: Fix title line formatting
  perf top: Support hotkey to change sort order
  perf top: Support --group-sort-idx to change the sort order
  perf symbols: Fix arm64 gap between kernel start and module end
  perf build-test: Honour JOBS to override detection of number of cores
  perf script: Add --show-cgroup-events option
  perf top: Add --all-cgroups option
  perf record: Add --all-cgroups option
  perf record: Support synthesizing cgroup events
  perf report: Add 'cgroup' sort key
  perf cgroup: Maintain cgroup hierarchy
  perf tools: Basic support for CGROUP event
  ...

include/linux/perf_event.h

@@ -1020,6 +1020,7 @@ struct perf_sample_data {
 	u64				stack_user_size;
 
 	u64				phys_addr;
+	u64				cgroup;
 } ____cacheline_aligned;
 
 /* default value for data source */

include/uapi/linux/perf_event.h

@@ -142,8 +142,9 @@ enum perf_event_sample_format {
 	PERF_SAMPLE_REGS_INTR			= 1U << 18,
 	PERF_SAMPLE_PHYS_ADDR			= 1U << 19,
 	PERF_SAMPLE_AUX				= 1U << 20,
+	PERF_SAMPLE_CGROUP			= 1U << 21,
 
-	PERF_SAMPLE_MAX = 1U << 21,		/* non-ABI */
+	PERF_SAMPLE_MAX = 1U << 22,		/* non-ABI */
 
 	__PERF_SAMPLE_CALLCHAIN_EARLY		= 1ULL << 63, /* non-ABI; internal use */
 };
@@ -381,7 +382,8 @@ struct perf_event_attr {
 				ksymbol        :  1, /* include ksymbol events */
 				bpf_event      :  1, /* include bpf events */
 				aux_output     :  1, /* generate AUX records instead of events */
-				__reserved_1   : 32;
+				cgroup         :  1, /* include cgroup events */
+				__reserved_1   : 31;
 
 	union {
 		__u32		wakeup_events;	  /* wakeup every n events */
@@ -1012,6 +1014,16 @@ enum perf_event_type {
 	 */
 	PERF_RECORD_BPF_EVENT			= 18,
 
+	/*
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *	u64				id;
+	 *	char				path[];
+	 *	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_CGROUP			= 19,
+
 	PERF_RECORD_MAX,			/* non-ABI */
 };
 

init/Kconfig

@@ -1029,7 +1029,8 @@ config CGROUP_PERF
 	help
 	  This option extends the perf per-cpu mode to restrict monitoring
 	  to threads which belong to the cgroup specified and run on the
-	  designated cpu.
+	  designated cpu.  Or this can be used to have cgroup ID in samples
+	  so that it can monitor performance events among cgroups.
 
 	  Say N if unsure.
 

kernel/events/core.c

@@ -387,6 +387,7 @@ static atomic_t nr_freq_events __read_mostly;
 static atomic_t nr_switch_events __read_mostly;
 static atomic_t nr_ksymbol_events __read_mostly;
 static atomic_t nr_bpf_events __read_mostly;
+static atomic_t nr_cgroup_events __read_mostly;
 
 static LIST_HEAD(pmus);
 static DEFINE_MUTEX(pmus_lock);
@@ -1861,6 +1862,9 @@ static void __perf_event_header_size(struct perf_event *event, u64 sample_type)
 	if (sample_type & PERF_SAMPLE_PHYS_ADDR)
 		size += sizeof(data->phys_addr);
 
+	if (sample_type & PERF_SAMPLE_CGROUP)
+		size += sizeof(data->cgroup);
+
 	event->header_size = size;
 }
 
@@ -4608,6 +4612,8 @@ static void unaccount_event(struct perf_event *event)
 		atomic_dec(&nr_comm_events);
 	if (event->attr.namespaces)
 		atomic_dec(&nr_namespaces_events);
+	if (event->attr.cgroup)
+		atomic_dec(&nr_cgroup_events);
 	if (event->attr.task)
 		atomic_dec(&nr_task_events);
 	if (event->attr.freq)
@@ -6864,6 +6870,9 @@ void perf_output_sample(struct perf_output_handle *handle,
 	if (sample_type & PERF_SAMPLE_PHYS_ADDR)
 		perf_output_put(handle, data->phys_addr);
 
+	if (sample_type & PERF_SAMPLE_CGROUP)
+		perf_output_put(handle, data->cgroup);
+
 	if (sample_type & PERF_SAMPLE_AUX) {
 		perf_output_put(handle, data->aux_size);
 
@@ -7063,6 +7072,16 @@ void perf_prepare_sample(struct perf_event_header *header,
 	if (sample_type & PERF_SAMPLE_PHYS_ADDR)
 		data->phys_addr = perf_virt_to_phys(data->addr);
 
+#ifdef CONFIG_CGROUP_PERF
+	if (sample_type & PERF_SAMPLE_CGROUP) {
+		struct cgroup *cgrp;
+
+		/* protected by RCU */
+		cgrp = task_css_check(current, perf_event_cgrp_id, 1)->cgroup;
+		data->cgroup = cgroup_id(cgrp);
+	}
+#endif
+
 	if (sample_type & PERF_SAMPLE_AUX) {
 		u64 size;
 
@@ -7735,6 +7754,105 @@ void perf_event_namespaces(struct task_struct *task)
 			NULL);
 }
 
+/*
+ * cgroup tracking
+ */
+#ifdef CONFIG_CGROUP_PERF
+
+struct perf_cgroup_event {
+	char				*path;
+	int				path_size;
+	struct {
+		struct perf_event_header	header;
+		u64				id;
+		char				path[];
+	} event_id;
+};
+
+static int perf_event_cgroup_match(struct perf_event *event)
+{
+	return event->attr.cgroup;
+}
+
+static void perf_event_cgroup_output(struct perf_event *event, void *data)
+{
+	struct perf_cgroup_event *cgroup_event = data;
+	struct perf_output_handle handle;
+	struct perf_sample_data sample;
+	u16 header_size = cgroup_event->event_id.header.size;
+	int ret;
+
+	if (!perf_event_cgroup_match(event))
+		return;
+
+	perf_event_header__init_id(&cgroup_event->event_id.header,
+				   &sample, event);
+	ret = perf_output_begin(&handle, event,
+				cgroup_event->event_id.header.size);
+	if (ret)
+		goto out;
+
+	perf_output_put(&handle, cgroup_event->event_id);
+	__output_copy(&handle, cgroup_event->path, cgroup_event->path_size);
+
+	perf_event__output_id_sample(event, &handle, &sample);
+
+	perf_output_end(&handle);
+out:
+	cgroup_event->event_id.header.size = header_size;
+}
+
+static void perf_event_cgroup(struct cgroup *cgrp)
+{
+	struct perf_cgroup_event cgroup_event;
+	char path_enomem[16] = "//enomem";
+	char *pathname;
+	size_t size;
+
+	if (!atomic_read(&nr_cgroup_events))
+		return;
+
+	cgroup_event = (struct perf_cgroup_event){
+		.event_id  = {
+			.header = {
+				.type = PERF_RECORD_CGROUP,
+				.misc = 0,
+				.size = sizeof(cgroup_event.event_id),
+			},
+			.id = cgroup_id(cgrp),
+		},
+	};
+
+	pathname = kmalloc(PATH_MAX, GFP_KERNEL);
+	if (pathname == NULL) {
+		cgroup_event.path = path_enomem;
+	} else {
+		/* just to be sure to have enough space for alignment */
+		cgroup_path(cgrp, pathname, PATH_MAX - sizeof(u64));
+		cgroup_event.path = pathname;
+	}
+
+	/*
+	 * Since our buffer works in 8 byte units we need to align our string
+	 * size to a multiple of 8. However, we must guarantee the tail end is
+	 * zero'd out to avoid leaking random bits to userspace.
+	 */
+	size = strlen(cgroup_event.path) + 1;
+	while (!IS_ALIGNED(size, sizeof(u64)))
+		cgroup_event.path[size++] = '\0';
+
+	cgroup_event.event_id.header.size += size;
+	cgroup_event.path_size = size;
+
+	perf_iterate_sb(perf_event_cgroup_output,
+			&cgroup_event,
+			NULL);
+
+	kfree(pathname);
+}
+
+#endif
+
 /*
  * mmap tracking
  */
@@ -10778,6 +10896,8 @@ static void account_event(struct perf_event *event)
 		atomic_inc(&nr_comm_events);
 	if (event->attr.namespaces)
 		atomic_inc(&nr_namespaces_events);
+	if (event->attr.cgroup)
+		atomic_inc(&nr_cgroup_events);
 	if (event->attr.task)
 		atomic_inc(&nr_task_events);
 	if (event->attr.freq)
@@ -11157,6 +11277,12 @@ static int perf_copy_attr(struct perf_event_attr __user *uattr,
 
 	if (attr->sample_type & PERF_SAMPLE_REGS_INTR)
 		ret = perf_reg_validate(attr->sample_regs_intr);
+
+#ifndef CONFIG_CGROUP_PERF
+	if (attr->sample_type & PERF_SAMPLE_CGROUP)
+		return -EINVAL;
+#endif
+
 out:
 	return ret;
 
@@ -12754,6 +12880,12 @@ static void perf_cgroup_css_free(struct cgroup_subsys_state *css)
 	kfree(jc);
 }
 
+static int perf_cgroup_css_online(struct cgroup_subsys_state *css)
+{
+	perf_event_cgroup(css->cgroup);
+	return 0;
+}
+
 static int __perf_cgroup_move(void *info)
 {
 	struct task_struct *task = info;
@@ -12775,6 +12907,7 @@ static void perf_cgroup_attach(struct cgroup_taskset *tset)
 struct cgroup_subsys perf_event_cgrp_subsys = {
 	.css_alloc	= perf_cgroup_css_alloc,
 	.css_free	= perf_cgroup_css_free,
+	.css_online	= perf_cgroup_css_online,
 	.attach		= perf_cgroup_attach,
 	/*
 	 * Implicitly enable on dfl hierarchy so that perf events can

tools/build/Makefile.feature

@@ -72,7 +72,8 @@ FEATURE_TESTS_BASIC :=                  \
         setns				\
         libaio				\
         libzstd				\
-        disassembler-four-args
+        disassembler-four-args		\
+        file-handle
 
 # FEATURE_TESTS_BASIC + FEATURE_TESTS_EXTRA is the complete list
 # of all feature tests

tools/build/feature/Makefile

@@ -68,7 +68,8 @@ FILES=                                          \
          test-llvm-version.bin			\
          test-libaio.bin			\
          test-libzstd.bin			\
-         test-clang-bpf-global-var.bin
+         test-clang-bpf-global-var.bin		\
+         test-file-handle.bin
 
 FILES := $(addprefix $(OUTPUT),$(FILES))
 
@@ -327,6 +328,8 @@ $(OUTPUT)test-clang-bpf-global-var.bin:
 	$(CLANG) -S -g -target bpf -o - $(patsubst %.bin,%.c,$(@F)) |	\
 		grep BTF_KIND_VAR
 
+$(OUTPUT)test-file-handle.bin:
+	$(BUILD)
 
 ###############################
 

tools/build/feature/test-file-handle.c

+#define _GNU_SOURCE
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <inttypes.h>
+
+int main(void)
+{
+	struct {
+		struct file_handle fh;
+		uint64_t cgroup_id;
+	} handle;
+	int mount_id;
+
+	name_to_handle_at(AT_FDCWD, "/", &handle.fh, &mount_id, 0);
+	return 0;
+}

tools/include/uapi/linux/perf_event.h

@@ -142,8 +142,9 @@ enum perf_event_sample_format {
 	PERF_SAMPLE_REGS_INTR			= 1U << 18,
 	PERF_SAMPLE_PHYS_ADDR			= 1U << 19,
 	PERF_SAMPLE_AUX				= 1U << 20,
+	PERF_SAMPLE_CGROUP			= 1U << 21,
 
-	PERF_SAMPLE_MAX = 1U << 21,		/* non-ABI */
+	PERF_SAMPLE_MAX = 1U << 22,		/* non-ABI */
 
 	__PERF_SAMPLE_CALLCHAIN_EARLY		= 1ULL << 63, /* non-ABI; internal use */
 };
@@ -381,7 +382,8 @@ struct perf_event_attr {
 				ksymbol        :  1, /* include ksymbol events */
 				bpf_event      :  1, /* include bpf events */
 				aux_output     :  1, /* generate AUX records instead of events */
-				__reserved_1   : 32;
+				cgroup         :  1, /* include cgroup events */
+				__reserved_1   : 31;
 
 	union {
 		__u32		wakeup_events;	  /* wakeup every n events */
@@ -1012,6 +1014,16 @@ enum perf_event_type {
 	 */
 	PERF_RECORD_BPF_EVENT			= 18,
 
+	/*
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *	u64				id;
+	 *	char				path[];
+	 *	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_CGROUP			= 19,
+
 	PERF_RECORD_MAX,			/* non-ABI */
 };
 

tools/lib/perf/include/perf/event.h

@@ -105,6 +105,12 @@ struct perf_record_bpf_event {
 	__u8			 tag[BPF_TAG_SIZE];  // prog tag
 };
 
+struct perf_record_cgroup {
+	struct perf_event_header header;
+	__u64			 id;
+	char			 path[PATH_MAX];
+};
+
 struct perf_record_sample {
 	struct perf_event_header header;
 	__u64			 array[];
@@ -352,6 +358,7 @@ union perf_event {
 	struct perf_record_mmap2		mmap2;
 	struct perf_record_comm			comm;
 	struct perf_record_namespaces		namespaces;
+	struct perf_record_cgroup		cgroup;
 	struct perf_record_fork			fork;
 	struct perf_record_lost			lost;
 	struct perf_record_lost_samples		lost_samples;

tools/perf/Documentation/perf-config.txt

@@ -405,14 +405,16 @@ ui.*::
 		This option is only applied to TUI.
 
 call-graph.*::
-	When sub-commands 'top' and 'report' work with -g/—-children
-	there're options in control of call-graph.
+	The following controls the handling of call-graphs (obtained via the
+	-g/--call-graph options).
 
 	call-graph.record-mode::
-		The record-mode can be 'fp' (frame pointer), 'dwarf' and 'lbr'.
-		The value of 'dwarf' is effective only if perf detect needed library
-		(libunwind or a recent version of libdw).
-		'lbr' only work for cpus that support it.
+		The mode for user space can be 'fp' (frame pointer), 'dwarf'
+		and 'lbr'.  The value 'dwarf' is effective only if libunwind
+		(or a recent version of libdw) is present on the system;
+		the value 'lbr' only works for certain cpus. The method for
+		kernel space is controlled not by this option but by the
+		kernel config (CONFIG_UNWINDER_*).
 
 	call-graph.dump-size::
 		The size of stack to dump in order to do post-unwinding. Default is 8192 (byte).

tools/perf/Documentation/perf-record.txt

@@ -237,16 +237,22 @@ OPTIONS
 	option and remains only for backward compatibility.  See --event.
 
 -g::
-	Enables call-graph (stack chain/backtrace) recording.
+	Enables call-graph (stack chain/backtrace) recording for both
+	kernel space and user space.
 
 --call-graph::
 	Setup and enable call-graph (stack chain/backtrace) recording,
-	implies -g.  Default is "fp".
+	implies -g.  Default is "fp" (for user space).
 
-	Allows specifying "fp" (frame pointer) or "dwarf"
-	(DWARF's CFI - Call Frame Information) or "lbr"
-	(Hardware Last Branch Record facility) as the method to collect
-	the information used to show the call graphs.
+	The unwinding method used for kernel space is dependent on the
+	unwinder used by the active kernel configuration, i.e
+	CONFIG_UNWINDER_FRAME_POINTER (fp) or CONFIG_UNWINDER_ORC (orc)
+
+	Any option specified here controls the method used for user space.
+
+	Valid options are "fp" (frame pointer), "dwarf" (DWARF's CFI -
+	Call Frame Information) or "lbr" (Hardware Last Branch Record
+	facility).
 
 	In some systems, where binaries are build with gcc
 	--fomit-frame-pointer, using the "fp" method will produce bogus
@@ -385,7 +391,10 @@ displayed with the weight and local_weight sort keys.  This currently works for
 abort events and some memory events in precise mode on modern Intel CPUs.
 
 --namespaces::
-Record events of type PERF_RECORD_NAMESPACES.
+Record events of type PERF_RECORD_NAMESPACES.  This enables 'cgroup_id' sort key.
+
+--all-cgroups::
+Record events of type PERF_RECORD_CGROUP.  This enables 'cgroup' sort key.
 
 --transaction::
 Record transaction flags for transaction related events.

tools/perf/Documentation/perf-report.txt

@@ -95,6 +95,7 @@ OPTIONS
 	abort cost. This is the global weight.
 	- local_weight: Local weight version of the weight above.
 	- cgroup_id: ID derived from cgroup namespace device and inode numbers.
+	- cgroup: cgroup pathname in the cgroupfs.
 	- transaction: Transaction abort flags.
 	- overhead: Overhead percentage of sample
 	- overhead_sys: Overhead percentage of sample running in system mode
@@ -377,6 +378,11 @@ OPTIONS
 	Show event group information together. It forces group output also
 	if there are no groups defined in data file.
 
+--group-sort-idx::
+	Sort the output by the event at the index n in group. If n is invalid,
+	sort by the first event. It can support multiple groups with different
+	amount of events. WARNING: This should be used on grouped events.
+
 --demangle::
 	Demangle symbol names to human readable form. It's enabled by default,
 	disable with --no-demangle.

tools/perf/Documentation/perf-script.txt

@@ -319,6 +319,9 @@ OPTIONS
 --show-bpf-events
 	Display bpf events i.e. events of type PERF_RECORD_KSYMBOL and PERF_RECORD_BPF_EVENT.
 
+--show-cgroup-events
+	Display cgroup events i.e. events of type PERF_RECORD_CGROUP.
+
 --demangle::
 	Demangle symbol names to human readable form. It's enabled by default,
 	disable with --no-demangle.
@@ -390,6 +393,9 @@ include::itrace.txt[]
 --reltime::
 	Print time stamps relative to trace start.
 
+--deltatime::
+	Print time stamps relative to previous event.
+
 --per-event-dump::
 	Create per event files with a "perf.data.EVENT.dump" name instead of
         printing to stdout, useful, for instance, for generating flamegraphs.
@@ -406,6 +412,14 @@ include::itrace.txt[]
 --xed::
 	Run xed disassembler on output. Requires installing the xed disassembler.
 
+-S::
+--symbols=symbol[,symbol...]::
+	Only consider the listed symbols. Symbols are typically a name
+	but they may also be hexadecimal address.
+
+	For example, to select the symbol noploop or the address 0x4007a0:
+	perf script --symbols=noploop,0x4007a0
+
 --call-trace::
 	Show call stream for intel_pt traces. The CPUs are interleaved, but
 	can be filtered with -C.

tools/perf/Documentation/perf-top.txt

@@ -53,6 +53,11 @@ Default is to monitor all CPUS.
 --group::
         Put the counters into a counter group.
 
+--group-sort-idx::
+	Sort the output by the event at the index n in group. If n is invalid,
+	sort by the first event. It can support multiple groups with different
+	amount of events. WARNING: This should be used on grouped events.
+
 -F <freq>::
 --freq=<freq>::
 	Profile at this frequency. Use 'max' to use the currently maximum
@@ -272,6 +277,10 @@ Default is to monitor all CPUS.
 	Record events of type PERF_RECORD_NAMESPACES and display it with the
 	'cgroup_id' sort key.
 
+--all-cgroups::
+	Record events of type PERF_RECORD_CGROUP and display it with the
+	'cgroup' sort key.
+
 --switch-on EVENT_NAME::
 	Only consider events after this event is found.
 

tools/perf/Makefile.config

@@ -228,8 +228,17 @@ strip-libs  = $(filter-out -l%,$(1))
 
 PYTHON_CONFIG_SQ := $(call shell-sq,$(PYTHON_CONFIG))
 
+# Python 3.8 changed the output of `python-config --ldflags` to not include the
+# '-lpythonX.Y' flag unless '--embed' is also passed. The feature check for
+# libpython fails if that flag is not included in LDFLAGS
+ifeq ($(shell $(PYTHON_CONFIG_SQ) --ldflags --embed 2>&1 1>/dev/null; echo $$?), 0)
+  PYTHON_CONFIG_LDFLAGS := --ldflags --embed
+else
+  PYTHON_CONFIG_LDFLAGS := --ldflags
+endif
+
 ifdef PYTHON_CONFIG
-  PYTHON_EMBED_LDOPTS := $(shell $(PYTHON_CONFIG_SQ) --ldflags 2>/dev/null)
+  PYTHON_EMBED_LDOPTS := $(shell $(PYTHON_CONFIG_SQ) $(PYTHON_CONFIG_LDFLAGS) 2>/dev/null)
   PYTHON_EMBED_LDFLAGS := $(call strip-libs,$(PYTHON_EMBED_LDOPTS))
   PYTHON_EMBED_LIBADD := $(call grep-libs,$(PYTHON_EMBED_LDOPTS)) -lutil
   PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --includes 2>/dev/null)
@@ -348,6 +357,10 @@ ifeq ($(feature-gettid), 1)
   CFLAGS += -DHAVE_GETTID
 endif
 
+ifeq ($(feature-file-handle), 1)
+  CFLAGS += -DHAVE_FILE_HANDLE
+endif
+
 ifdef NO_LIBELF
   NO_DWARF := 1
   NO_DEMANGLE := 1

tools/perf/Makefile.perf

@@ -231,6 +231,7 @@ TRACE_EVENT_DIR = $(srctree)/tools/lib/traceevent/
 BPF_DIR         = $(srctree)/tools/lib/bpf/
 SUBCMD_DIR      = $(srctree)/tools/lib/subcmd/
 LIBPERF_DIR     = $(srctree)/tools/lib/perf/
+DOC_DIR         = $(srctree)/tools/perf/Documentation/
 
 # Set FEATURE_TESTS to 'all' so all possible feature checkers are executed.
 # Without this setting the output feature dump file misses some features, for
@@ -573,7 +574,7 @@ arch_errno_hdr_dir := $(srctree)/tools
 arch_errno_tbl := $(srctree)/tools/perf/trace/beauty/arch_errno_names.sh
 
 $(arch_errno_name_array): $(arch_errno_tbl)
-	$(Q)$(SHELL) '$(arch_errno_tbl)' $(CC) $(arch_errno_hdr_dir) > $@
+	$(Q)$(SHELL) '$(arch_errno_tbl)' $(firstword $(CC)) $(arch_errno_hdr_dir) > $@
 
 sync_file_range_arrays := $(beauty_outdir)/sync_file_range_arrays.c
 sync_file_range_tbls := $(srctree)/tools/perf/trace/beauty/sync_file_range.sh
@@ -792,7 +793,6 @@ $(LIBSUBCMD): FORCE
 	$(Q)$(MAKE) -C $(SUBCMD_DIR) O=$(OUTPUT) $(OUTPUT)libsubcmd.a
 
 $(LIBSUBCMD)-clean:
-	$(call QUIET_CLEAN, libsubcmd)
 	$(Q)$(MAKE) -C $(SUBCMD_DIR) O=$(OUTPUT) clean
 
 help:
@@ -832,7 +832,7 @@ INSTALL_DOC_TARGETS += quick-install-doc quick-install-man quick-install-html
 
 # 'make doc' should call 'make -C Documentation all'
 $(DOC_TARGETS):
-	$(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) $(@:doc=all)
+	$(Q)$(MAKE) -C $(DOC_DIR) O=$(OUTPUT) $(@:doc=all)
 
 TAG_FOLDERS= . ../lib ../include
 TAG_FILES= ../../include/uapi/linux/perf_event.h
@@ -959,7 +959,7 @@ install-python_ext:
 
 # 'make install-doc' should call 'make -C Documentation install'
 $(INSTALL_DOC_TARGETS):
-	$(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) $(@:-doc=)
+	$(Q)$(MAKE) -C $(DOC_DIR) O=$(OUTPUT) $(@:-doc=)
 
 ### Cleaning rules
 
@@ -1008,7 +1008,8 @@ clean:: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clea
 		$(OUTPUT)$(rename_flags_array) \
 		$(OUTPUT)$(arch_errno_name_array) \
 		$(OUTPUT)$(sync_file_range_arrays)
-	$(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) clean
+	$(call QUIET_CLEAN, Documentation) \
+	$(MAKE) -C $(DOC_DIR) O=$(OUTPUT) clean >/dev/null
 
 #
 # To provide FEATURE-DUMP into $(FEATURE_DUMP_COPY)

tools/perf/arch/arm64/util/Build

 perf-y += header.o
+perf-y += machine.o
 perf-y += perf_regs.o
-perf-y += sym-handling.o
 perf-$(CONFIG_DWARF)     += dwarf-regs.o
 perf-$(CONFIG_LOCAL_LIBUNWIND) += unwind-libunwind.o
 perf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o

tools/perf/arch/arm64/util/machine.c

+// SPDX-License-Identifier: GPL-2.0
+
+#include <stdio.h>
+#include <string.h>
+#include "debug.h"
+#include "symbol.h"
+
+/* On arm64, kernel text segment start at high memory address,
+ * for example 0xffff 0000 8xxx xxxx. Modules start at a low memory
+ * address, like 0xffff 0000 00ax xxxx. When only samll amount of
+ * memory is used by modules, gap between end of module's text segment
+ * and start of kernel text segment may be reach 2G.
+ * Therefore do not fill this gap and do not assign it to the kernel dso map.
+ */
+
+#define SYMBOL_LIMIT (1 << 12) /* 4K */
+
+void arch__symbols__fixup_end(struct symbol *p, struct symbol *c)
+{
+	if ((strchr(p->name, '[') && strchr(c->name, '[') == NULL) ||
+			(strchr(p->name, '[') == NULL && strchr(c->name, '[')))
+		/* Limit range of last symbol in module and kernel */
+		p->end += SYMBOL_LIMIT;
+	else
+		p->end = c->start;
+	pr_debug4("%s sym:%s end:%#lx\n", __func__, p->name, p->end);
+}

tools/perf/arch/arm64/util/sym-handling.c

-// SPDX-License-Identifier: GPL-2.0-only
-/*
- *
- * Copyright (C) 2015 Naveen N. Rao, IBM Corporation
- */
-
-#include "symbol.h" // for the elf__needs_adjust_symbols() prototype
-#include <stdbool.h>
-
-#ifdef HAVE_LIBELF_SUPPORT
-#include <gelf.h>
-
-bool elf__needs_adjust_symbols(GElf_Ehdr ehdr)
-{
-	return ehdr.e_type == ET_EXEC ||
-	       ehdr.e_type == ET_REL ||
-	       ehdr.e_type == ET_DYN;
-}
-#endif

tools/perf/arch/powerpc/util/Build

 perf-y += header.o
-perf-y += sym-handling.o
 perf-y += kvm-stat.o
 perf-y += perf_regs.o
 perf-y += mem-events.o