Merge tag 'perf-tools-for-v6.12-1-2024-09-19' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools

Pull perf tools updates from Arnaldo Carvalho de Melo:

 - Use BPF + BTF to collect and pretty print syscall and tracepoint
   arguments in 'perf trace', done as an GSoC activity

 - Data-type profiling improvements:

     - Cache debuginfo to speed up data type resolution

     - Add the 'typecln' sort order, to show which cacheline in a target
       is hot or cold. The following shows members in the cfs_rq's first
       cache line:

         $ perf report -s type,typecln,typeoff -H
         ...
         -    2.67%        struct cfs_rq
            +    1.23%        struct cfs_rq: cache-line 2
            +    0.57%        struct cfs_rq: cache-line 4
            +    0.46%        struct cfs_rq: cache-line 6
            -    0.41%        struct cfs_rq: cache-line 0
                    0.39%        struct cfs_rq +0x14 (h_nr_running)
                    0.02%        struct cfs_rq +0x38 (tasks_timeline.rb_leftmost)

     - When a typedef resolves to a unnamed struct, use the typedef name

     - When a struct has just one basic type field (int, etc), resolve
       the type sort order to the name of the struct, not the type of
       the field

     - Support type folding/unfolding in the data-type annotation TUI

     - Fix bitfields offsets and sizes

     - Initial support for PowerPC, using libcapstone and the usual
       objdump disassembly parsing routines

 - Add support for disassembling and addr2line using the LLVM libraries,
   speeding up those operations

 - Support --addr2line option in 'perf script' as with other tools

 - Intel branch counters (LBR event logging) support, only available in
   recent Intel processors, for instance, the new "brcntr" field can be
   asked from 'perf script' to print the information collected from this
   feature:

     $ perf script -F +brstackinsn,+brcntr

     # Branch counter abbr list:
     # branch-instructions:ppp = A
     # branch-misses = B
     # '-' No event occurs
     # '+' Event occurrences may be lost due to branch counter saturated
         tchain_edit  332203 3366329.405674:  53030 branch-instructions:ppp:    401781 f3+0x2c (home/sdp/test/tchain_edit)
            f3+31:
         0000000000401774   insn: eb 04                  br_cntr: AA  # PRED 5 cycles [5]
         000000000040177a   insn: 81 7d fc 0f 27 00 00
         0000000000401781   insn: 7e e3                  br_cntr: A   # PRED 1 cycles [6] 2.00 IPC
         0000000000401766   insn: 8b 45 fc
         0000000000401769   insn: 83 e0 01
         000000000040176c   insn: 85 c0
         000000000040176e   insn: 74 06                  br_cntr: A   # PRED 1 cycles [7] 4.00 IPC
         0000000000401776   insn: 83 45 fc 01
         000000000040177a   insn: 81 7d fc 0f 27 00 00
         0000000000401781   insn: 7e e3                  br_cntr: A   # PRED 7 cycles [14] 0.43 IPC

 - Support Timed PEBS (Precise Event-Based Sampling), a recent hardware
   feature in Intel processors

 - Add 'perf ftrace profile' subcommand, using ftrace's function-graph
   tracer so that users can see the total, average, max execution time
   as well as the number of invocations easily, for instance:

     $ sudo perf ftrace profile -G __x64_sys_perf_event_open -- \
       perf stat -e cycles -C1 true 2> /dev/null | head
     # Total (us)  Avg (us)  Max (us)  Count  Function
           65.611    65.611    65.611      1  __x64_sys_perf_event_open
           30.527    30.527    30.527      1  anon_inode_getfile
           30.260    30.260    30.260      1  __anon_inode_getfile
           29.700    29.700    29.700      1  alloc_file_pseudo
           17.578    17.578    17.578      1  d_alloc_pseudo
           17.382    17.382    17.382      1  __d_alloc
           16.738    16.738    16.738      1  kmem_cache_alloc_lru
           15.686    15.686    15.686      1  perf_event_alloc
           14.012     7.006    11.264      2  obj_cgroup_charge

 - 'perf sched timehist' improvements, including the addition of
   priority showing/filtering command line options

 - Varios improvements to the 'perf probe', including 'perf test'
   regression testings

 - Introduce the 'perf check', initially to check if some feature is
   in place, using it in 'perf test'

 - Various fixes for 32-bit systems

 - Address more leak sanitizer failures

 - Fix memory leaks (LBR, disasm lock ops, etc)

 - More reference counting fixes (branch_info, etc)

 - Constify 'struct perf_tool' parameters to improve code generation
   and reduce the chances of having its internals changed, which isn't
   expected

 - More constifications in various other places

 - Add more build tests, including for JEVENTS

 - Add more 'perf test' entries ('perf record LBR', pipe/inject,
   --setup-filter, 'perf ftrace', 'cgroup sampling', etc)

 - Inject build ids for all entries in a call chain in 'perf inject',
   not just for the main sample

 - Improve the BPF based sample filter, allowing root to setup filters
   in bpffs that then can be used by non-root users

 - Allow filtering by cgroups with the BPF based sample filter

 - Allow a more compact way for 'perf mem report' using the
   -T/--type-profile and also provide a --sort option similar to the one
   in 'perf report', 'perf top', to setup the sort order manually

 - Fix --group behavior in 'perf annotate' when leader has no samples,
   where it was not showing anything even when other events in the group
   had samples

 - Fix spinlock and rwlock accounting in 'perf lock contention'

 - Fix libsubcmd fixdep Makefile dependencies

 - Improve 'perf ftrace' error message when ftrace isn't available

 - Update various Intel JSON vendor event files

 - ARM64 CoreSight hardware tracing infrastructure improvements, mostly
   not visible to users

 - Update power10 JSON events

* tag 'perf-tools-for-v6.12-1-2024-09-19' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools: (310 commits)
  perf trace: Mark the 'head' arg in the set_robust_list syscall as coming from user space
  perf trace: Mark the 'rseq' arg in the rseq syscall as coming from user space
  perf env: Find correct branch counter info on hybrid
  perf evlist: Print hint for group
  tools: Drop nonsensical -O6
  perf pmu: To info add event_type_desc
  perf evsel: Add accessor for tool_event
  perf pmus: Fake PMU clean up
  perf list: Avoid potential out of bounds memory read
  perf help: Fix a typo ("bellow")
  perf ftrace: Detect whether ftrace is enabled on system
  perf test shell probe_vfs_getname: Remove extraneous '=' from probe line number regex
  perf build: Require at least clang 16.0.6 to build BPF skeletons
  perf trace: If a syscall arg is marked as 'const', assume it is coming _from_ userspace
  perf parse-events: Remove duplicated include in parse-events.c
  perf callchain: Allow symbols to be optional when resolving a callchain
  perf inject: Lazy build-id mmap2 event insertion
  perf inject: Add new mmap2-buildid-all option
  perf inject: Fix build ID injection
  perf annotate-data: Add pr_debug_scope()
  ...

1 files changed, 94 insertions, 67 deletions

diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c
index 863fcd735dae..651188c1d825 100644
--- a/tools/perf/builtin-mem.c
+++ b/tools/perf/builtin-mem.c
@@ -19,6 +19,7 @@
 #include "util/symbol.h"
 #include "util/pmus.h"
 #include "util/sample.h"
+#include "util/sort.h"
 #include "util/string2.h"
 #include "util/util.h"
 #include <linux/err.h>
@@ -28,12 +29,16 @@
 
 struct perf_mem {
 	struct perf_tool	tool;
-	char const		*input_name;
+	const char		*input_name;
+	const char		*sort_key;
 	bool			hide_unresolved;
 	bool			dump_raw;
 	bool			force;
 	bool			phys_addr;
 	bool			data_page_size;
+	bool			all_kernel;
+	bool			all_user;
+	bool			data_type;
 	int			operation;
 	const char		*cpu_list;
 	DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
@@ -42,7 +47,7 @@ struct perf_mem {
 static int parse_record_events(const struct option *opt,
 			       const char *str, int unset __maybe_unused)
 {
-	struct perf_mem *mem = *(struct perf_mem **)opt->value;
+	struct perf_mem *mem = (struct perf_mem *)opt->value;
 	struct perf_pmu *pmu;
 
 	pmu = perf_mem_events_find_pmu();
@@ -62,33 +67,19 @@ static int parse_record_events(const struct option *opt,
 	return 0;
 }
 
-static const char * const __usage[] = {
-	"perf mem record [<options>] [<command>]",
-	"perf mem record [<options>] -- <command> [<options>]",
-	NULL
-};
-
-static const char * const *record_mem_usage = __usage;
-
-static int __cmd_record(int argc, const char **argv, struct perf_mem *mem)
+static int __cmd_record(int argc, const char **argv, struct perf_mem *mem,
+			const struct option *options)
 {
 	int rec_argc, i = 0, j;
 	int start, end;
 	const char **rec_argv;
 	int ret;
-	bool all_user = false, all_kernel = false;
 	struct perf_mem_event *e;
 	struct perf_pmu *pmu;
-	struct option options[] = {
-	OPT_CALLBACK('e', "event", &mem, "event",
-		     "event selector. use 'perf mem record -e list' to list available events",
-		     parse_record_events),
-	OPT_UINTEGER(0, "ldlat", &perf_mem_events__loads_ldlat, "mem-loads latency"),
-	OPT_INCR('v', "verbose", &verbose,
-		 "be more verbose (show counter open errors, etc)"),
-	OPT_BOOLEAN('U', "all-user", &all_user, "collect only user level data"),
-	OPT_BOOLEAN('K', "all-kernel", &all_kernel, "collect only kernel level data"),
-	OPT_END()
+	const char * const record_usage[] = {
+		"perf mem record [<options>] [<command>]",
+		"perf mem record [<options>] -- <command> [<options>]",
+		NULL
 	};
 
 	pmu = perf_mem_events_find_pmu();
@@ -97,12 +88,12 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem)
 		return -1;
 	}
 
-	if (perf_pmu__mem_events_init(pmu)) {
+	if (perf_pmu__mem_events_init()) {
 		pr_err("failed: memory events not supported\n");
 		return -1;
 	}
 
-	argc = parse_options(argc, argv, options, record_mem_usage,
+	argc = parse_options(argc, argv, options, record_usage,
 			     PARSE_OPT_KEEP_UNKNOWN);
 
 	/* Max number of arguments multiplied by number of PMUs that can support them. */
@@ -126,22 +117,17 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem)
 	if (e->tag &&
 	    (mem->operation & MEM_OPERATION_LOAD) &&
 	    (mem->operation & MEM_OPERATION_STORE)) {
-		e->record = true;
+		perf_mem_record[PERF_MEM_EVENTS__LOAD_STORE] = true;
 		rec_argv[i++] = "-W";
 	} else {
-		if (mem->operation & MEM_OPERATION_LOAD) {
-			e = perf_pmu__mem_events_ptr(pmu, PERF_MEM_EVENTS__LOAD);
-			e->record = true;
-		}
+		if (mem->operation & MEM_OPERATION_LOAD)
+			perf_mem_record[PERF_MEM_EVENTS__LOAD] = true;
 
-		if (mem->operation & MEM_OPERATION_STORE) {
-			e = perf_pmu__mem_events_ptr(pmu, PERF_MEM_EVENTS__STORE);
-			e->record = true;
-		}
+		if (mem->operation & MEM_OPERATION_STORE)
+			perf_mem_record[PERF_MEM_EVENTS__STORE] = true;
 	}
 
-	e = perf_pmu__mem_events_ptr(pmu, PERF_MEM_EVENTS__LOAD);
-	if (e->record)
+	if (perf_mem_record[PERF_MEM_EVENTS__LOAD])
 		rec_argv[i++] = "-W";
 
 	rec_argv[i++] = "-d";
@@ -158,10 +144,10 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem)
 		goto out;
 	end = i;
 
-	if (all_user)
+	if (mem->all_user)
 		rec_argv[i++] = "--all-user";
 
-	if (all_kernel)
+	if (mem->all_kernel)
 		rec_argv[i++] = "--all-kernel";
 
 	if (mem->cpu_list) {
@@ -188,7 +174,7 @@ out:
 }
 
 static int
-dump_raw_samples(struct perf_tool *tool,
+dump_raw_samples(const struct perf_tool *tool,
 		 union perf_event *event,
 		 struct perf_sample *sample,
 		 struct machine *machine)
@@ -262,7 +248,7 @@ out_put:
 	return 0;
 }
 
-static int process_sample_event(struct perf_tool *tool,
+static int process_sample_event(const struct perf_tool *tool,
 				union perf_event *event,
 				struct perf_sample *sample,
 				struct evsel *evsel __maybe_unused,
@@ -285,7 +271,23 @@ static int report_raw_events(struct perf_mem *mem)
 		.force = mem->force,
 	};
 	int ret;
-	struct perf_session *session = perf_session__new(&data, &mem->tool);
+	struct perf_session *session;
+
+	perf_tool__init(&mem->tool, /*ordered_events=*/true);
+	mem->tool.sample		= process_sample_event;
+	mem->tool.mmap		= perf_event__process_mmap;
+	mem->tool.mmap2		= perf_event__process_mmap2;
+	mem->tool.comm		= perf_event__process_comm;
+	mem->tool.lost		= perf_event__process_lost;
+	mem->tool.fork		= perf_event__process_fork;
+	mem->tool.attr		= perf_event__process_attr;
+	mem->tool.build_id	= perf_event__process_build_id;
+	mem->tool.namespaces	= perf_event__process_namespaces;
+	mem->tool.auxtrace_info  = perf_event__process_auxtrace_info;
+	mem->tool.auxtrace       = perf_event__process_auxtrace;
+	mem->tool.auxtrace_error = perf_event__process_auxtrace_error;
+
+	session = perf_session__new(&data, &mem->tool);
 
 	if (IS_ERR(session))
 		return PTR_ERR(session);
@@ -319,16 +321,21 @@ out_delete:
 	perf_session__delete(session);
 	return ret;
 }
+
 static char *get_sort_order(struct perf_mem *mem)
 {
 	bool has_extra_options = (mem->phys_addr | mem->data_page_size) ? true : false;
 	char sort[128];
 
+	if (mem->sort_key)
+		scnprintf(sort, sizeof(sort), "--sort=%s", mem->sort_key);
+	else if (mem->data_type)
+		strcpy(sort, "--sort=mem,snoop,tlb,type");
 	/*
 	 * there is no weight (cost) associated with stores, so don't print
 	 * the column
 	 */
-	if (!(mem->operation & MEM_OPERATION_LOAD)) {
+	else if (!(mem->operation & MEM_OPERATION_LOAD)) {
 		strcpy(sort, "--sort=mem,sym,dso,symbol_daddr,"
 			     "dso_daddr,tlb,locked");
 	} else if (has_extra_options) {
@@ -343,14 +350,26 @@ static char *get_sort_order(struct perf_mem *mem)
 	if (mem->data_page_size)
 		strcat(sort, ",data_page_size");
 
+	/* make sure it has 'type' sort key even -s option is used */
+	if (mem->data_type && !strstr(sort, "type"))
+		strcat(sort, ",type");
+
 	return strdup(sort);
 }
 
-static int report_events(int argc, const char **argv, struct perf_mem *mem)
+static int __cmd_report(int argc, const char **argv, struct perf_mem *mem,
+			const struct option *options)
 {
 	const char **rep_argv;
 	int ret, i = 0, j, rep_argc;
 	char *new_sort_order;
+	const char * const report_usage[] = {
+		"perf mem report [<options>]",
+		NULL
+	};
+
+	argc = parse_options(argc, argv, options, report_usage,
+			     PARSE_OPT_KEEP_UNKNOWN);
 
 	if (mem->dump_raw)
 		return report_raw_events(mem);
@@ -368,10 +387,11 @@ static int report_events(int argc, const char **argv, struct perf_mem *mem)
 	if (new_sort_order)
 		rep_argv[i++] = new_sort_order;
 
-	for (j = 1; j < argc; j++, i++)
+	for (j = 0; j < argc; j++, i++)
 		rep_argv[i] = argv[j];
 
 	ret = cmd_report(i, rep_argv);
+	free(new_sort_order);
 	free(rep_argv);
 	return ret;
 }
@@ -449,47 +469,51 @@ int cmd_mem(int argc, const char **argv)
 {
 	struct stat st;
 	struct perf_mem mem = {
-		.tool = {
-			.sample		= process_sample_event,
-			.mmap		= perf_event__process_mmap,
-			.mmap2		= perf_event__process_mmap2,
-			.comm		= perf_event__process_comm,
-			.lost		= perf_event__process_lost,
-			.fork		= perf_event__process_fork,
-			.attr		= perf_event__process_attr,
-			.build_id	= perf_event__process_build_id,
-			.namespaces	= perf_event__process_namespaces,
-			.auxtrace_info  = perf_event__process_auxtrace_info,
-			.auxtrace       = perf_event__process_auxtrace,
-			.auxtrace_error = perf_event__process_auxtrace_error,
-			.ordered_events	= true,
-		},
 		.input_name		 = "perf.data",
 		/*
 		 * default to both load an store sampling
 		 */
 		.operation		 = MEM_OPERATION_LOAD | MEM_OPERATION_STORE,
 	};
+	char *sort_order_help = sort_help("sort by key(s):", SORT_MODE__MEMORY);
 	const struct option mem_options[] = {
 	OPT_CALLBACK('t', "type", &mem.operation,
 		   "type", "memory operations(load,store) Default load,store",
 		    parse_mem_ops),
+	OPT_STRING('C', "cpu", &mem.cpu_list, "cpu",
+		   "list of cpus to profile"),
+	OPT_BOOLEAN('f', "force", &mem.force, "don't complain, do it"),
+	OPT_INCR('v', "verbose", &verbose,
+		 "be more verbose (show counter open errors, etc)"),
+	OPT_BOOLEAN('p', "phys-data", &mem.phys_addr, "Record/Report sample physical addresses"),
+	OPT_BOOLEAN(0, "data-page-size", &mem.data_page_size, "Record/Report sample data address page size"),
+	OPT_END()
+	};
+	const struct option record_options[] = {
+	OPT_CALLBACK('e', "event", &mem, "event",
+		     "event selector. use 'perf mem record -e list' to list available events",
+		     parse_record_events),
+	OPT_UINTEGER(0, "ldlat", &perf_mem_events__loads_ldlat, "mem-loads latency"),
+	OPT_BOOLEAN('U', "all-user", &mem.all_user, "collect only user level data"),
+	OPT_BOOLEAN('K', "all-kernel", &mem.all_kernel, "collect only kernel level data"),
+	OPT_PARENT(mem_options)
+	};
+	const struct option report_options[] = {
 	OPT_BOOLEAN('D', "dump-raw-samples", &mem.dump_raw,
 		    "dump raw samples in ASCII"),
 	OPT_BOOLEAN('U', "hide-unresolved", &mem.hide_unresolved,
 		    "Only display entries resolved to a symbol"),
 	OPT_STRING('i', "input", &input_name, "file",
 		   "input file name"),
-	OPT_STRING('C', "cpu", &mem.cpu_list, "cpu",
-		   "list of cpus to profile"),
 	OPT_STRING_NOEMPTY('x', "field-separator", &symbol_conf.field_sep,
 		   "separator",
 		   "separator for columns, no spaces will be added"
 		   " between columns '.' is reserved."),
-	OPT_BOOLEAN('f', "force", &mem.force, "don't complain, do it"),
-	OPT_BOOLEAN('p', "phys-data", &mem.phys_addr, "Record/Report sample physical addresses"),
-	OPT_BOOLEAN(0, "data-page-size", &mem.data_page_size, "Record/Report sample data address page size"),
-	OPT_END()
+	OPT_STRING('s', "sort", &mem.sort_key, "key[,key2...]",
+		   sort_order_help),
+	OPT_BOOLEAN('T', "type-profile", &mem.data_type,
+		    "Show data-type profile result"),
+	OPT_PARENT(mem_options)
 	};
 	const char *const mem_subcommands[] = { "record", "report", NULL };
 	const char *mem_usage[] = {
@@ -498,7 +522,7 @@ int cmd_mem(int argc, const char **argv)
 	};
 
 	argc = parse_options_subcommand(argc, argv, mem_options, mem_subcommands,
-					mem_usage, PARSE_OPT_KEEP_UNKNOWN);
+					mem_usage, PARSE_OPT_STOP_AT_NON_OPTION);
 
 	if (!argc || !(strncmp(argv[0], "rec", 3) || mem.operation))
 		usage_with_options(mem_usage, mem_options);
@@ -511,11 +535,14 @@ int cmd_mem(int argc, const char **argv)
 	}
 
 	if (strlen(argv[0]) > 2 && strstarts("record", argv[0]))
-		return __cmd_record(argc, argv, &mem);
+		return __cmd_record(argc, argv, &mem, record_options);
 	else if (strlen(argv[0]) > 2 && strstarts("report", argv[0]))
-		return report_events(argc, argv, &mem);
+		return __cmd_report(argc, argv, &mem, report_options);
 	else
 		usage_with_options(mem_usage, mem_options);
 
+	/* free usage string allocated by parse_options_subcommand */
+	free((void *)mem_usage[0]);
+
 	return 0;
 }