Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf updates from Ingo Molnar:
 "Kernel side changes:

   - Ftrace is one of the last W^X violators (after this only KLP is
     left). These patches move it over to the generic text_poke()
     interface and thereby get rid of this oddity. This requires a
     surprising amount of surgery, by Peter Zijlstra.

   - x86/AMD PMUs: add support for 'Large Increment per Cycle Events' to
     count certain types of events that have a special, quirky hw ABI
     (by Kim Phillips)

   - kprobes fixes by Masami Hiramatsu

  Lots of tooling updates as well, the following subcommands were
  updated: annotate/report/top, c2c, clang, record, report/top TUI,
  sched timehist, tests; plus updates were done to the gtk ui, libperf,
  headers and the parser"

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (57 commits)
  perf/x86/amd: Add support for Large Increment per Cycle Events
  perf/x86/amd: Constrain Large Increment per Cycle events
  perf/x86/intel/rapl: Add Comet Lake support
  tracing: Initialize ret in syscall_enter_define_fields()
  perf header: Use last modification time for timestamp
  perf c2c: Fix return type for histogram sorting comparision functions
  perf beauty sockaddr: Fix augmented syscall format warning
  perf/ui/gtk: Fix gtk2 build
  perf ui gtk: Add missing zalloc object
  perf tools: Use %define api.pure full instead of %pure-parser
  libperf: Setup initial evlist::all_cpus value
  perf report: Fix no libunwind compiled warning break s390 issue
  perf tools: Support --prefix/--prefix-strip
  perf report: Clarify in help that --children is default
  tools build: Fix test-clang.cpp with Clang 8+
  perf clang: Fix build with Clang 9
  kprobes: Fix optimize_kprobe()/unoptimize_kprobe() cancellation logic
  tools lib: Fix builds when glibc contains strlcpy()
  perf report/top: Make 'e' visible in the help and make it toggle showing callchains
  perf report/top: Do not offer annotation for symbols without samples
  ...

68 files changed, 388 insertions, 3999 deletions

diff --git a/tools/perf/Documentation/perf-annotate.txt b/tools/perf/Documentation/perf-annotate.txt
index e8c972f89357..1b5042f134a8 100644
--- a/tools/perf/Documentation/perf-annotate.txt
+++ b/tools/perf/Documentation/perf-annotate.txt
@@ -112,6 +112,12 @@ OPTIONS
 --objdump=<path>::
         Path to objdump binary.
 
+--prefix=PREFIX::
+--prefix-strip=N::
+	Remove first N entries from source file path names in executables
+	and add PREFIX. This allows to display source code compiled on systems
+	with different file system layout.
+
 --skip-missing::
 	Skip symbols that cannot be annotated.
 
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index 8dbe2119686a..db61f16ffa56 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -367,6 +367,12 @@ OPTIONS
 --objdump=<path>::
         Path to objdump binary.
 
+--prefix=PREFIX::
+--prefix-strip=N::
+	Remove first N entries from source file path names in executables
+	and add PREFIX. This allows to display source code compiled on systems
+	with different file system layout.
+
 --group::
 	Show event group information together. It forces group output also
 	if there are no groups defined in data file.
diff --git a/tools/perf/Documentation/perf-sched.txt b/tools/perf/Documentation/perf-sched.txt
index 63f938b887dd..5fbe42bd599b 100644
--- a/tools/perf/Documentation/perf-sched.txt
+++ b/tools/perf/Documentation/perf-sched.txt
@@ -110,6 +110,10 @@ OPTIONS for 'perf sched timehist'
 --max-stack::
 	Maximum number of functions to display in backtrace, default 5.
 
+-C=::
+--cpu=::
+	Only show events for the given CPU(s) (comma separated list).
+
 -p=::
 --pid=::
 	Only show events for given process ID (comma separated list).
diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt
index 5596129a71cf..324b6b53c86b 100644
--- a/tools/perf/Documentation/perf-top.txt
+++ b/tools/perf/Documentation/perf-top.txt
@@ -158,6 +158,12 @@ Default is to monitor all CPUS.
 -M::
 --disassembler-style=:: Set disassembler style for objdump.
 
+--prefix=PREFIX::
+--prefix-strip=N::
+        Remove first N entries from source file path names in executables
+        and add PREFIX. This allows to display source code compiled on systems
+        with different file system layout.
+
 --source::
 	Interleave source code with assembly code. Enabled by default,
 	disable with --no-source.
diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST
index 4934edb5adfd..5d7b947320fb 100644
--- a/tools/perf/MANIFEST
+++ b/tools/perf/MANIFEST
@@ -7,6 +7,7 @@ tools/lib/traceevent
 tools/lib/api
 tools/lib/bpf
 tools/lib/subcmd
+tools/lib/perf
 tools/lib/argv_split.c
 tools/lib/ctype.c
 tools/lib/hweight.c
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index c90f4146e5a2..80e55e796be9 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -286,7 +286,7 @@ ifeq ($(DEBUG),0)
   endif
 endif
 
-INC_FLAGS += -I$(src-perf)/lib/include
+INC_FLAGS += -I$(srctree)/tools/lib/perf/include
 INC_FLAGS += -I$(src-perf)/util/include
 INC_FLAGS += -I$(src-perf)/arch/$(SRCARCH)/include
 INC_FLAGS += -I$(srctree)/tools/include/
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index eae5d5e95952..3eda9d4b88e7 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -230,7 +230,7 @@ LIB_DIR         = $(srctree)/tools/lib/api/
 TRACE_EVENT_DIR = $(srctree)/tools/lib/traceevent/
 BPF_DIR         = $(srctree)/tools/lib/bpf/
 SUBCMD_DIR      = $(srctree)/tools/lib/subcmd/
-LIBPERF_DIR     = $(srctree)/tools/perf/lib/
+LIBPERF_DIR     = $(srctree)/tools/lib/perf/
 
 # Set FEATURE_TESTS to 'all' so all possible feature checkers are executed.
 # Without this setting the output feature dump file misses some features, for
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 5898662bc8fb..ff61795a4d13 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -535,6 +535,10 @@ int cmd_annotate(int argc, const char **argv)
 		    "Display raw encoding of assembly instructions (default)"),
 	OPT_STRING('M', "disassembler-style", &annotate.opts.disassembler_style, "disassembler style",
 		   "Specify disassembler style (e.g. -M intel for intel syntax)"),
+	OPT_STRING(0, "prefix", &annotate.opts.prefix, "prefix",
+		    "Add prefix to source file path names in programs (with --prefix-strip)"),
+	OPT_STRING(0, "prefix-strip", &annotate.opts.prefix_strip, "N",
+		    "Strip first N entries of source file path name in programs (with --prefix)"),
 	OPT_STRING(0, "objdump", &annotate.opts.objdump_path, "path",
 		   "objdump binary to use for disassembly and annotations"),
 	OPT_BOOLEAN(0, "group", &symbol_conf.event_group,
@@ -574,6 +578,9 @@ int cmd_annotate(int argc, const char **argv)
 		annotate.sym_hist_filter = argv[0];
 	}
 
+	if (annotate_check_args(&annotate.opts) < 0)
+		return -EINVAL;
+
 	if (symbol_conf.show_nr_samples && annotate.use_gtk) {
 		pr_err("--show-nr-samples is not available in --gtk mode at this time\n");
 		return ret;
diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c
index e69f44941aad..246ac0b4d54f 100644
--- a/tools/perf/builtin-c2c.c
+++ b/tools/perf/builtin-c2c.c
@@ -595,8 +595,8 @@ tot_hitm_cmp(struct perf_hpp_fmt *fmt __maybe_unused,
 {
 	struct c2c_hist_entry *c2c_left;
 	struct c2c_hist_entry *c2c_right;
-	unsigned int tot_hitm_left;
-	unsigned int tot_hitm_right;
+	uint64_t tot_hitm_left;
+	uint64_t tot_hitm_right;
 
 	c2c_left  = container_of(left, struct c2c_hist_entry, he);
 	c2c_right = container_of(right, struct c2c_hist_entry, he);
@@ -629,7 +629,8 @@ __f ## _cmp(struct perf_hpp_fmt *fmt __maybe_unused,			\
 									\
 	c2c_left  = container_of(left, struct c2c_hist_entry, he);	\
 	c2c_right = container_of(right, struct c2c_hist_entry, he);	\
-	return c2c_left->stats.__f - c2c_right->stats.__f;		\
+	return (uint64_t) c2c_left->stats.__f -				\
+	       (uint64_t) c2c_right->stats.__f;				\
 }
 
 #define STAT_FN(__f)		\
@@ -682,7 +683,8 @@ ld_llcmiss_cmp(struct perf_hpp_fmt *fmt __maybe_unused,
 	c2c_left  = container_of(left, struct c2c_hist_entry, he);
 	c2c_right = container_of(right, struct c2c_hist_entry, he);
 
-	return llc_miss(&c2c_left->stats) - llc_miss(&c2c_right->stats);
+	return (uint64_t) llc_miss(&c2c_left->stats) -
+	       (uint64_t) llc_miss(&c2c_right->stats);
 }
 
 static uint64_t total_records(struct c2c_stats *stats)
@@ -2384,7 +2386,7 @@ static int perf_c2c__browse_cacheline(struct hist_entry *he)
 	c2c_browser__update_nr_entries(browser);
 
 	while (1) {
-		key = hist_browser__run(browser, "? - help", true);
+		key = hist_browser__run(browser, "? - help", true, 0);
 
 		switch (key) {
 		case 's':
@@ -2453,7 +2455,7 @@ static int perf_c2c__hists_browse(struct hists *hists)
 	c2c_browser__update_nr_entries(browser);
 
 	while (1) {
-		key = hist_browser__run(browser, "? - help", true);
+		key = hist_browser__run(browser, "? - help", true, 0);
 
 		switch (key) {
 		case 'q':
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index fb19ef63cc35..4c301466101b 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -62,6 +62,7 @@
 #include <linux/string.h>
 #include <linux/time64.h>
 #include <linux/zalloc.h>
+#include <linux/bitmap.h>
 
 struct switch_output {
 	bool		 enabled;
@@ -93,7 +94,7 @@ struct record {
 	bool			timestamp_boundary;
 	struct switch_output	switch_output;
 	unsigned long long	samples;
-	cpu_set_t		affinity_mask;
+	struct mmap_cpu_mask	affinity_mask;
 	unsigned long		output_max_size;	/* = 0: unlimited */
 };
 
@@ -961,10 +962,15 @@ static struct perf_event_header finished_round_event = {
 static void record__adjust_affinity(struct record *rec, struct mmap *map)
 {
 	if (rec->opts.affinity != PERF_AFFINITY_SYS &&
-	    !CPU_EQUAL(&rec->affinity_mask, &map->affinity_mask)) {
-		CPU_ZERO(&rec->affinity_mask);
-		CPU_OR(&rec->affinity_mask, &rec->affinity_mask, &map->affinity_mask);
-		sched_setaffinity(0, sizeof(rec->affinity_mask), &rec->affinity_mask);
+	    !bitmap_equal(rec->affinity_mask.bits, map->affinity_mask.bits,
+			  rec->affinity_mask.nbits)) {
+		bitmap_zero(rec->affinity_mask.bits, rec->affinity_mask.nbits);
+		bitmap_or(rec->affinity_mask.bits, rec->affinity_mask.bits,
+			  map->affinity_mask.bits, rec->affinity_mask.nbits);
+		sched_setaffinity(0, MMAP_CPU_MASK_BYTES(&rec->affinity_mask),
+				  (cpu_set_t *)rec->affinity_mask.bits);
+		if (verbose == 2)
+			mmap_cpu_mask__scnprintf(&rec->affinity_mask, "thread");
 	}
 }
 
@@ -2433,7 +2439,6 @@ int cmd_record(int argc, const char **argv)
 # undef REASON
 #endif
 
-	CPU_ZERO(&rec->affinity_mask);
 	rec->opts.affinity = PERF_AFFINITY_SYS;
 
 	rec->evlist = evlist__new();
@@ -2499,6 +2504,16 @@ int cmd_record(int argc, const char **argv)
 
 	symbol__init(NULL);
 
+	if (rec->opts.affinity != PERF_AFFINITY_SYS) {
+		rec->affinity_mask.nbits = cpu__max_cpu();
+		rec->affinity_mask.bits = bitmap_alloc(rec->affinity_mask.nbits);
+		if (!rec->affinity_mask.bits) {
+			pr_err("Failed to allocate thread mask for %zd cpus\n", rec->affinity_mask.nbits);
+			return -ENOMEM;
+		}
+		pr_debug2("thread mask[%zd]: empty\n", rec->affinity_mask.nbits);
+	}
+
 	err = record__auxtrace_init(rec);
 	if (err)
 		goto out;
@@ -2613,6 +2628,7 @@ int cmd_record(int argc, const char **argv)
 
 	err = __cmd_record(&record, argc, argv);
 out:
+	bitmap_free(rec->affinity_mask.bits);
 	evlist__delete(rec->evlist);
 	symbol__exit();
 	auxtrace_record__free(rec->itr);
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index de988589d99b..9483b3f0cae3 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -412,10 +412,10 @@ static int report__setup_sample_type(struct report *rep)
 				PERF_SAMPLE_BRANCH_ANY))
 		rep->nonany_branch_mode = true;
 
-#ifndef HAVE_LIBUNWIND_SUPPORT
+#if !defined(HAVE_LIBUNWIND_SUPPORT) && !defined(HAVE_DWARF_SUPPORT)
 	if (dwarf_callchain_users) {
-		ui__warning("Please install libunwind development packages "
-			    "during the perf build.\n");
+		ui__warning("Please install libunwind or libdw "
+			    "development packages during the perf build.\n");
 	}
 #endif
 
@@ -1164,7 +1164,8 @@ int cmd_report(int argc, const char **argv)
 			     report_callchain_help, &report_parse_callchain_opt,
 			     callchain_default_opt),
 	OPT_BOOLEAN(0, "children", &symbol_conf.cumulate_callchain,
-		    "Accumulate callchains of children and show total overhead as well"),
+		    "Accumulate callchains of children and show total overhead as well. "
+		    "Enabled by default, use --no-children to disable."),
 	OPT_INTEGER(0, "max-stack", &report.max_stack,
 		    "Set the maximum stack depth when parsing the callchain, "
 		    "anything beyond the specified depth will be ignored. "
@@ -1207,6 +1208,10 @@ int cmd_report(int argc, const char **argv)
 		    "Display raw encoding of assembly instructions (default)"),
 	OPT_STRING('M', "disassembler-style", &report.annotation_opts.disassembler_style, "disassembler style",
 		   "Specify disassembler style (e.g. -M intel for intel syntax)"),
+	OPT_STRING(0, "prefix", &report.annotation_opts.prefix, "prefix",
+		    "Add prefix to source file path names in programs (with --prefix-strip)"),
+	OPT_STRING(0, "prefix-strip", &report.annotation_opts.prefix_strip, "N",
+		    "Strip first N entries of source file path name in programs (with --prefix)"),
 	OPT_BOOLEAN(0, "show-total-period", &symbol_conf.show_total_period,
 		    "Show a column with the sum of periods"),
 	OPT_BOOLEAN_SET(0, "group", &symbol_conf.event_group, &report.group_set,
@@ -1286,6 +1291,9 @@ int cmd_report(int argc, const char **argv)
 		report.symbol_filter_str = argv[0];
 	}
 
+	if (annotate_check_args(&report.annotation_opts) < 0)
+		return -EINVAL;
+
 	if (report.mmaps_mode)
 		report.tasks_mode = true;
 
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index 8a12d71364c3..82fcc2c15fe4 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -51,6 +51,9 @@
 #define SYM_LEN			129
 #define MAX_PID			1024000
 
+static const char *cpu_list;
+static DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
+
 struct sched_atom;
 
 struct task_desc {
@@ -2008,6 +2011,9 @@ static void timehist_print_sample(struct perf_sched *sched,
 	char nstr[30];
 	u64 wait_time;
 
+	if (cpu_list && !test_bit(sample->cpu, cpu_bitmap))
+		return;
+
 	timestamp__scnprintf_usec(t, tstr, sizeof(tstr));
 	printf("%15s [%04d] ", tstr, sample->cpu);
 
@@ -2994,6 +3000,12 @@ static int perf_sched__timehist(struct perf_sched *sched)
 	if (IS_ERR(session))
 		return PTR_ERR(session);
 
+	if (cpu_list) {
+		err = perf_session__cpu_bitmap(session, cpu_list, cpu_bitmap);
+		if (err < 0)
+			goto out;
+	}
+
 	evlist = session->evlist;
 
 	symbol__init(&session->header.env);
@@ -3429,6 +3441,7 @@ int cmd_sched(int argc, const char **argv)
 		   "analyze events only for given process id(s)"),
 	OPT_STRING('t', "tid", &symbol_conf.tid_list_str, "tid[,tid...]",
 		   "analyze events only for given thread id(s)"),
+	OPT_STRING('C', "cpu", &cpu_list, "cpu", "list of cpus to profile"),
 	OPT_PARENT(sched_options)
 	};
 
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 795e353de095..8affcab75604 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -1512,6 +1512,10 @@ int cmd_top(int argc, const char **argv)
 		    "objdump binary to use for disassembly and annotations"),
 	OPT_STRING('M', "disassembler-style", &top.annotation_opts.disassembler_style, "disassembler style",
 		   "Specify disassembler style (e.g. -M intel for intel syntax)"),
+	OPT_STRING(0, "prefix", &top.annotation_opts.prefix, "prefix",
+		    "Add prefix to source file path names in programs (with --prefix-strip)"),
+	OPT_STRING(0, "prefix-strip", &top.annotation_opts.prefix_strip, "N",
+		    "Strip first N entries of source file path name in programs (with --prefix)"),
 	OPT_STRING('u', "uid", &target->uid_str, "user", "user to profile"),
 	OPT_CALLBACK(0, "percent-limit", &top, "percent",
 		     "Don't show entries under that percent", parse_percent_limit),
@@ -1582,6 +1586,9 @@ int cmd_top(int argc, const char **argv)
 	if (argc)
 		usage_with_options(top_usage, options);
 
+	if (annotate_check_args(&top.annotation_opts) < 0)
+		goto out_delete_evlist;
+
 	if (!top.evlist->core.nr_entries &&
 	    perf_evlist__add_default(top.evlist) < 0) {
 		pr_err("Not enough memory for event selector list\n");
diff --git a/tools/perf/lib/Build b/tools/perf/lib/Build
deleted file mode 100644
index 2ef9a4ec6d99..000000000000
--- a/tools/perf/lib/Build
+++ /dev/null
@@ -1,13 +0,0 @@
-libperf-y += core.o
-libperf-y += cpumap.o
-libperf-y += threadmap.o
-libperf-y += evsel.o
-libperf-y += evlist.o
-libperf-y += mmap.o
-libperf-y += zalloc.o
-libperf-y += xyarray.o
-libperf-y += lib.o
-
-$(OUTPUT)zalloc.o: ../../lib/zalloc.c FORCE
-	$(call rule_mkdir)
-	$(call if_changed_dep,cc_o_c)
diff --git a/tools/perf/lib/Documentation/Makefile b/tools/perf/lib/Documentation/Makefile
deleted file mode 100644
index 586425a88795..000000000000
--- a/tools/perf/lib/Documentation/Makefile
+++ /dev/null
@@ -1,7 +0,0 @@
-all:
-	rst2man man/libperf.rst > man/libperf.7