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

Pull perf updates and fixes from Ingo Molnar:
 "These are almost all tooling updates: 'perf top', 'perf trace' and
  'perf script' fixes and updates, an UAPI header sync with the merge
  window versions, license marker updates, much improved Sparc support
  from David Miller, and a number of fixes"

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (66 commits)
  perf intel-pt/bts: Calculate cpumode for synthesized samples
  perf intel-pt: Insert callchain context into synthesized callchains
  perf tools: Don't clone maps from parent when synthesizing forks
  perf top: Start display thread earlier
  tools headers uapi: Update linux/if_link.h header copy
  tools headers uapi: Update linux/netlink.h header copy
  tools headers: Sync the various kvm.h header copies
  tools include uapi: Update linux/mmap.h copy
  perf trace beauty: Use the mmap flags table generated from headers
  perf beauty: Wire up the mmap flags table generator to the Makefile
  perf beauty: Add a generator for MAP_ mmap's flag constants
  tools include uapi: Update asound.h copy
  tools arch uapi: Update asm-generic/unistd.h and arm64 unistd.h copies
  tools include uapi: Update linux/fs.h copy
  perf callchain: Honour the ordering of PERF_CONTEXT_{USER,KERNEL,etc}
  perf cs-etm: Correct CPU mode for samples
  perf unwind: Take pgoff into account when reporting elf to libdwfl
  perf top: Do not use overwrite mode by default
  perf top: Allow disabling the overwrite mode
  perf trace: Beautify mount's first pathname arg
  ...

tools/perf/Documentation/perf-top.txt

@@ -242,6 +242,16 @@ Default is to monitor all CPUS.
 --hierarchy::
 	Enable hierarchy output.
 
+--overwrite::
+	Enable this to use just the most recent records, which helps in high core count
+	machines such as Knights Landing/Mill, but right now is disabled by default as
+	the pausing used in this technique is leading to loss of metadata events such
+	as PERF_RECORD_MMAP which makes 'perf top' unable to resolve samples, leading
+	to lots of unknown samples appearing on the UI. Enable this if you are in such
+	machines and profiling a workload that doesn't creates short lived threads and/or
+	doesn't uses many executable mmap operations. Work is being planed to solve
+	this situation, till then, this will remain disabled by default.
+
 --force::
 	Don't do ownership validation.
 

tools/perf/Documentation/perf-trace.txt

@@ -171,6 +171,11 @@ the thread executes on the designated CPUs. Default is to monitor all CPUs.
 --kernel-syscall-graph::
 	 Show the kernel callchains on the syscall exit path.
 
+--max-events=N::
+	Stop after processing N events. Note that strace-like events are considered
+	only at exit time or when a syscall is interrupted, i.e. in those cases this
+	option is equivalent to the number of lines printed.
+
 --max-stack::
         Set the stack depth limit when parsing the callchain, anything
         beyond the specified depth will be ignored. Note that at this point
@@ -238,6 +243,68 @@ Trace syscalls, major and minor pagefaults:
   As you can see, there was major pagefault in python process, from
   CRYPTO_push_info_ routine which faulted somewhere in libcrypto.so.
 
+Trace the first 4 open, openat or open_by_handle_at syscalls (in the future more syscalls may match here):
+
+  $ perf trace -e open* --max-events 4
+  [root@jouet perf]# trace -e open* --max-events 4
+  2272.992 ( 0.037 ms): gnome-shell/1370 openat(dfd: CWD, filename: /proc/self/stat) = 31
+  2277.481 ( 0.139 ms): gnome-shell/3039 openat(dfd: CWD, filename: /proc/self/stat) = 65
+  3026.398 ( 0.076 ms): gnome-shell/3039 openat(dfd: CWD, filename: /proc/self/stat) = 65
+  4294.665 ( 0.015 ms): sed/15879 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC) = 3
+  $
+
+Trace the first minor page fault when running a workload:
+
+  # perf trace -F min --max-stack=7 --max-events 1 sleep 1
+     0.000 ( 0.000 ms): sleep/18006 minfault [__clear_user+0x1a] => 0x5626efa56080 (?k)
+                                       __clear_user ([kernel.kallsyms])
+                                       load_elf_binary ([kernel.kallsyms])
+                                       search_binary_handler ([kernel.kallsyms])
+                                       __do_execve_file.isra.33 ([kernel.kallsyms])
+                                       __x64_sys_execve ([kernel.kallsyms])
+                                       do_syscall_64 ([kernel.kallsyms])
+                                       entry_SYSCALL_64 ([kernel.kallsyms])
+  #
+
+Trace the next min page page fault to take place on the first CPU:
+
+  # perf trace -F min --call-graph=dwarf --max-events 1 --cpu 0
+     0.000 ( 0.000 ms): Web Content/17136 minfault [js::gc::Chunk::fetchNextDecommittedArena+0x4b] => 0x7fbe6181b000 (?.)
+                                       js::gc::FreeSpan::initAsEmpty (inlined)
+                                       js::gc::Arena::setAsNotAllocated (inlined)
+                                       js::gc::Chunk::fetchNextDecommittedArena (/usr/lib64/firefox/libxul.so)
+                                       js::gc::Chunk::allocateArena (/usr/lib64/firefox/libxul.so)
+                                       js::gc::GCRuntime::allocateArena (/usr/lib64/firefox/libxul.so)
+                                       js::gc::ArenaLists::allocateFromArena (/usr/lib64/firefox/libxul.so)
+                                       js::gc::GCRuntime::tryNewTenuredThing<JSString, (js::AllowGC)1> (inlined)
+                                       js::AllocateString<JSString, (js::AllowGC)1> (/usr/lib64/firefox/libxul.so)
+                                       js::Allocate<JSThinInlineString, (js::AllowGC)1> (inlined)
+                                       JSThinInlineString::new_<(js::AllowGC)1> (inlined)
+                                       AllocateInlineString<(js::AllowGC)1, unsigned char> (inlined)
+                                       js::ConcatStrings<(js::AllowGC)1> (/usr/lib64/firefox/libxul.so)
+                                       [0x18b26e6bc2bd] (/tmp/perf-17136.map)
+  #
+
+Trace the next two sched:sched_switch events, four block:*_plug events, the
+next block:*_unplug and the next three net:*dev_queue events, this last one
+with a backtrace of at most 16 entries, system wide:
+
+  # perf trace -e sched:*switch/nr=2/,block:*_plug/nr=4/,block:*_unplug/nr=1/,net:*dev_queue/nr=3,max-stack=16/
+     0.000 :0/0 sched:sched_switch:swapper/2:0 [120] S ==> rcu_sched:10 [120]
+     0.015 rcu_sched/10 sched:sched_switch:rcu_sched:10 [120] R ==> swapper/2:0 [120]
+   254.198 irq/50-iwlwifi/680 net:net_dev_queue:dev=wlp3s0 skbaddr=0xffff93498051f600 len=66
+                                       __dev_queue_xmit ([kernel.kallsyms])
+   273.977 :0/0 net:net_dev_queue:dev=wlp3s0 skbaddr=0xffff93498051f600 len=78
+                                       __dev_queue_xmit ([kernel.kallsyms])
+   274.007 :0/0 net:net_dev_queue:dev=wlp3s0 skbaddr=0xffff93498051ff00 len=78
+                                       __dev_queue_xmit ([kernel.kallsyms])
+  2930.140 kworker/u16:58/2722 block:block_plug:[kworker/u16:58]
+  2930.162 kworker/u16:58/2722 block:block_unplug:[kworker/u16:58] 1
+  4466.094 jbd2/dm-2-8/748 block:block_plug:[jbd2/dm-2-8]
+  8050.123 kworker/u16:30/2694 block:block_plug:[kworker/u16:30]
+  8050.271 kworker/u16:30/2694 block:block_plug:[kworker/u16:30]
+  #
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-script[1]

tools/perf/Makefile.perf

 include ../scripts/Makefile.include
+include ../scripts/Makefile.arch
 
 # The default target of this Makefile is...
 all:
@@ -385,6 +386,8 @@ export INSTALL SHELL_PATH
 SHELL = $(SHELL_PATH)
 
 linux_uapi_dir := $(srctree)/tools/include/uapi/linux
+asm_generic_uapi_dir := $(srctree)/tools/include/uapi/asm-generic
+arch_asm_uapi_dir := $(srctree)/tools/arch/$(ARCH)/include/uapi/asm/
 
 beauty_outdir := $(OUTPUT)trace/beauty/generated
 beauty_ioctl_outdir := $(beauty_outdir)/ioctl
@@ -460,6 +463,18 @@ madvise_behavior_tbl := $(srctree)/tools/perf/trace/beauty/madvise_behavior.sh
 $(madvise_behavior_array): $(madvise_hdr_dir)/mman-common.h $(madvise_behavior_tbl)
 	$(Q)$(SHELL) '$(madvise_behavior_tbl)' $(madvise_hdr_dir) > $@
 
+mmap_flags_array := $(beauty_outdir)/mmap_flags_array.c
+mmap_flags_tbl := $(srctree)/tools/perf/trace/beauty/mmap_flags.sh
+
+$(mmap_flags_array): $(asm_generic_uapi_dir)/mman.h $(asm_generic_uapi_dir)/mman-common.h $(arch_asm_uapi_dir)/mman.h $(mmap_flags_tbl)
+	$(Q)$(SHELL) '$(mmap_flags_tbl)' $(asm_generic_uapi_dir) $(arch_asm_uapi_dir) > $@
+
+mount_flags_array := $(beauty_outdir)/mount_flags_array.c
+mount_flags_tbl := $(srctree)/tools/perf/trace/beauty/mount_flags.sh
+
+$(mount_flags_array): $(linux_uapi_dir)/fs.h $(mount_flags_tbl)
+	$(Q)$(SHELL) '$(mount_flags_tbl)' $(linux_uapi_dir) > $@
+
 prctl_option_array := $(beauty_outdir)/prctl_option_array.c
 prctl_hdr_dir := $(srctree)/tools/include/uapi/linux/
 prctl_option_tbl := $(srctree)/tools/perf/trace/beauty/prctl_option.sh
@@ -577,6 +592,8 @@ prepare: $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h archheaders $(drm_ioc
 	$(socket_ipproto_array) \
 	$(vhost_virtio_ioctl_array) \
 	$(madvise_behavior_array) \
+	$(mmap_flags_array) \
+	$(mount_flags_array) \
 	$(perf_ioctl_array) \
 	$(prctl_option_array) \
 	$(arch_errno_name_array)
@@ -863,6 +880,8 @@ clean:: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clea
 		$(OUTPUT)tests/llvm-src-{base,kbuild,prologue,relocation}.c \
 		$(OUTPUT)pmu-events/pmu-events.c \
 		$(OUTPUT)$(madvise_behavior_array) \
+		$(OUTPUT)$(mmap_flags_array) \
+		$(OUTPUT)$(mount_flags_array) \
 		$(OUTPUT)$(drm_ioctl_array) \
 		$(OUTPUT)$(pkey_alloc_access_rights_array) \
 		$(OUTPUT)$(sndrv_ctl_ioctl_array) \

tools/perf/arch/arm64/entry/syscalls/mksyscalltbl

@@ -23,7 +23,7 @@ create_table_from_c()
 {
 	local sc nr last_sc
 
-	create_table_exe=`mktemp /tmp/create-table-XXXXXX`
+	create_table_exe=`mktemp ${TMPDIR:-/tmp}/create-table-XXXXXX`
 
 	{
 

tools/perf/arch/sparc/Makefile

 ifndef NO_DWARF
 PERF_HAVE_DWARF_REGS := 1
 endif
+
+PERF_HAVE_JITDUMP := 1

tools/perf/arch/sparc/annotate/instructions.c

+// SPDX-License-Identifier: GPL-2.0
+
+static int is_branch_cond(const char *cond)
+{
+	if (cond[0] == '\0')
+		return 1;
+
+	if (cond[0] == 'a' && cond[1] == '\0')
+		return 1;
+
+	if (cond[0] == 'c' &&
+	    (cond[1] == 'c' || cond[1] == 's') &&
+	    cond[2] == '\0')
+		return 1;
+
+	if (cond[0] == 'e' &&
+	    (cond[1] == '\0' ||
+	     (cond[1] == 'q' && cond[2] == '\0')))
+		return 1;
+
+	if (cond[0] == 'g' &&
+	    (cond[1] == '\0' ||
+	     (cond[1] == 't' && cond[2] == '\0') ||
+	     (cond[1] == 'e' && cond[2] == '\0') ||
+	     (cond[1] == 'e' && cond[2] == 'u' && cond[3] == '\0')))
+		return 1;
+
+	if (cond[0] == 'l' &&
+	    (cond[1] == '\0' ||
+	     (cond[1] == 't' && cond[2] == '\0') ||
+	     (cond[1] == 'u' && cond[2] == '\0') ||
+	     (cond[1] == 'e' && cond[2] == '\0') ||
+	     (cond[1] == 'e' && cond[2] == 'u' && cond[3] == '\0')))
+		return 1;
+
+	if (cond[0] == 'n' &&
+	    (cond[1] == '\0' ||
+	     (cond[1] == 'e' && cond[2] == '\0') ||
+	     (cond[1] == 'z' && cond[2] == '\0') ||
+	     (cond[1] == 'e' && cond[2] == 'g' && cond[3] == '\0')))
+		return 1;
+
+	if (cond[0] == 'b' &&
+	    cond[1] == 'p' &&
+	    cond[2] == 'o' &&
+	    cond[3] == 's' &&
+	    cond[4] == '\0')
+		return 1;
+
+	if (cond[0] == 'v' &&
+	    (cond[1] == 'c' || cond[1] == 's') &&
+	    cond[2] == '\0')
+		return 1;
+
+	if (cond[0] == 'b' &&
+	    cond[1] == 'z' &&
+	    cond[2] == '\0')
+		return 1;
+
+	return 0;
+}
+
+static int is_branch_reg_cond(const char *cond)
+{
+	if ((cond[0] == 'n' || cond[0] == 'l') &&
+	    cond[1] == 'z' &&
+	    cond[2] == '\0')
+		return 1;
+
+	if (cond[0] == 'z' &&
+	    cond[1] == '\0')
+		return 1;
+
+	if ((cond[0] == 'g' || cond[0] == 'l') &&
+	    cond[1] == 'e' &&
+	    cond[2] == 'z' &&
+	    cond[3] == '\0')
+		return 1;
+
+	if (cond[0] == 'g' &&
+	    cond[1] == 'z' &&
+	    cond[2] == '\0')
+		return 1;
+
+	return 0;
+}
+
+static int is_branch_float_cond(const char *cond)
+{
+	if (cond[0] == '\0')
+		return 1;
+
+	if ((cond[0] == 'a' || cond[0] == 'e' ||
+	     cond[0] == 'z' || cond[0] == 'g' ||
+	     cond[0] == 'l' || cond[0] == 'n' ||
+	     cond[0] == 'o' || cond[0] == 'u') &&
+	    cond[1] == '\0')
+		return 1;
+
+	if (((cond[0] == 'g' && cond[1] == 'e') ||
+	     (cond[0] == 'l' && (cond[1] == 'e' ||
+				 cond[1] == 'g')) ||
+	     (cond[0] == 'n' && (cond[1] == 'e' ||
+				 cond[1] == 'z')) ||
+	     (cond[0] == 'u' && (cond[1] == 'e' ||
+				 cond[1] == 'g' ||
+				 cond[1] == 'l'))) &&
+	    cond[2] == '\0')
+		return 1;
+
+	if (cond[0] == 'u' &&
+	    (cond[1] == 'g' || cond[1] == 'l') &&
+	    cond[2] == 'e' &&
+	    cond[3] == '\0')
+		return 1;
+
+	return 0;
+}
+
+static struct ins_ops *sparc__associate_instruction_ops(struct arch *arch, const char *name)
+{
+	struct ins_ops *ops = NULL;
+
+	if (!strcmp(name, "call") ||
+	    !strcmp(name, "jmp") ||
+	    !strcmp(name, "jmpl")) {
+		ops = &call_ops;
+	} else if (!strcmp(name, "ret") ||
+		   !strcmp(name, "retl") ||
+		   !strcmp(name, "return")) {
+		ops = &ret_ops;
+	} else if (!strcmp(name, "mov")) {
+		ops = &mov_ops;
+	} else {
+		if (name[0] == 'c' &&
+		    (name[1] == 'w' || name[1] == 'x'))
+			name += 2;
+
+		if (name[0] == 'b') {
+			const char *cond = name + 1;
+
+			if (cond[0] == 'r') {
+				if (is_branch_reg_cond(cond + 1))
+					ops = &jump_ops;
+			} else if (is_branch_cond(cond)) {
+				ops = &jump_ops;
+			}
+		} else if (name[0] == 'f' && name[1] == 'b') {
+			if (is_branch_float_cond(name + 2))
+				ops = &jump_ops;
+		}
+	}
+
+	if (ops)
+		arch__associate_ins_ops(arch, name, ops);
+
+	return ops;
+}
+
+static int sparc__annotate_init(struct arch *arch, char *cpuid __maybe_unused)
+{
+	if (!arch->initialized) {
+		arch->initialized = true;
+		arch->associate_instruction_ops = sparc__associate_instruction_ops;
+		arch->objdump.comment_char = '#';
+	}
+
+	return 0;
+}

tools/perf/builtin-record.c

@@ -592,6 +592,9 @@ static void record__init_features(struct record *rec)
 	if (!rec->opts.full_auxtrace)
 		perf_header__clear_feat(&session->header, HEADER_AUXTRACE);
 
+	if (!(rec->opts.use_clockid && rec->opts.clockid_res_ns))
+		perf_header__clear_feat(&session->header, HEADER_CLOCKID);
+
 	perf_header__clear_feat(&session->header, HEADER_STAT);
 }
 
@@ -897,6 +900,9 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 
 	record__init_features(rec);
 
+	if (rec->opts.use_clockid && rec->opts.clockid_res_ns)
+		session->header.env.clockid_res_ns = rec->opts.clockid_res_ns;
+
 	if (forks) {
 		err = perf_evlist__prepare_workload(rec->evlist, &opts->target,
 						    argv, data->is_pipe,
@@ -1337,6 +1343,19 @@ static const struct clockid_map clockids[] = {
 	CLOCKID_END,
 };
 
+static int get_clockid_res(clockid_t clk_id, u64 *res_ns)
+{
+	struct timespec res;
+
+	*res_ns = 0;
+	if (!clock_getres(clk_id, &res))
+		*res_ns = res.tv_nsec + res.tv_sec * NSEC_PER_SEC;
+	else
+		pr_warning("WARNING: Failed to determine specified clock resolution.\n");
+
+	return 0;
+}
+
 static int parse_clockid(const struct option *opt, const char *str, int unset)
 {
 	struct record_opts *opts = (struct record_opts *)opt->value;
@@ -1360,7 +1379,7 @@ static int parse_clockid(const struct option *opt, const char *str, int unset)
 
 	/* if its a number, we're done */
 	if (sscanf(str, "%d", &opts->clockid) == 1)
-		return 0;
+		return get_clockid_res(opts->clockid, &opts->clockid_res_ns);
 
 	/* allow a "CLOCK_" prefix to the name */
 	if (!strncasecmp(str, "CLOCK_", 6))
@@ -1369,7 +1388,8 @@ static int parse_clockid(const struct option *opt, const char *str, int unset)
 	for (cm = clockids; cm->name; cm++) {
 		if (!strcasecmp(str, cm->name)) {
 			opts->clockid = cm->clockid;
-			return 0;
+			return get_clockid_res(opts->clockid,
+					       &opts->clockid_res_ns);
 		}
 	}
 

tools/perf/builtin-script.c

@@ -44,6 +44,7 @@
 #include <sys/stat.h>
 #include <fcntl.h>
 #include <unistd.h>
+#include <subcmd/pager.h>
 
 #include "sane_ctype.h"
 
@@ -912,7 +913,7 @@ static int grab_bb(u8 *buffer, u64 start, u64 end,
 
 static int ip__fprintf_jump(uint64_t ip, struct branch_entry *en,
 			    struct perf_insn *x, u8 *inbuf, int len,
-			    int insn, FILE *fp)
+			    int insn, FILE *fp, int *total_cycles)
 {
 	int printed = fprintf(fp, "\t%016" PRIx64 "\t%-30s\t#%s%s%s%s", ip,
 			      dump_insn(x, ip, inbuf, len, NULL),
@@ -921,7 +922,8 @@ static int ip__fprintf_jump(uint64_t ip, struct branch_entry *en,
 			      en->flags.in_tx ? " INTX" : "",
 			      en->flags.abort ? " ABORT" : "");
 	if (en->flags.cycles) {
-		printed += fprintf(fp, " %d cycles", en->flags.cycles);
+		*total_cycles += en->flags.cycles;
+		printed += fprintf(fp, " %d cycles [%d]", en->flags.cycles, *total_cycles);
 		if (insn)
 			printed += fprintf(fp, " %.2f IPC", (float)insn / en->flags.cycles);
 	}
@@ -978,6 +980,7 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample,
 	u8 buffer[MAXBB];
 	unsigned off;
 	struct symbol *lastsym = NULL;
+	int total_cycles = 0;
 
 	if (!(br && br->nr))
 		return 0;
@@ -998,7 +1001,7 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample,
 		printed += ip__fprintf_sym(br->entries[nr - 1].from, thread,
 					   x.cpumode, x.cpu, &lastsym, attr, fp);
 		printed += ip__fprintf_jump(br->entries[nr - 1].from, &br->entries[nr - 1],
-					    &x, buffer, len, 0, fp);
+					    &x, buffer, len, 0, fp, &total_cycles);
 	}
 
 	/* Print all blocks */
@@ -1026,7 +1029,8 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample,
 
 			printed += ip__fprintf_sym(ip, thread, x.cpumode, x.cpu, &lastsym, attr, fp);
 			if (ip == end) {
-				printed += ip__fprintf_jump(ip, &br->entries[i], &x, buffer + off, len - off, insn, fp);
+				printed += ip__fprintf_jump(ip, &br->entries[i], &x, buffer + off, len - off, insn, fp,
+							    &total_cycles);
 				break;
 			} else {
 				printed += fprintf(fp, "\t%016" PRIx64 "\t%s\n", ip,
@@ -1104,6 +1108,35 @@ static int perf_sample__fprintf_addr(struct perf_sample *sample,
 	return printed;
 }
 
+static const char *resolve_branch_sym(struct perf_sample *sample,
+				      struct perf_evsel *evsel,
+				      struct thread *thread,
+				      struct addr_location *al,
+				      u64 *ip)
+{
+	struct addr_location addr_al;
+	struct perf_event_attr *attr = &evsel->attr;
+	const char *name = NULL;
+
+	if (sample->flags & (PERF_IP_FLAG_CALL | PERF_IP_FLAG_TRACE_BEGIN)) {
+		if (sample_addr_correlates_sym(attr)) {
+			thread__resolve(thread, &addr_al, sample);
+			if (addr_al.sym)
+				name = addr_al.sym->name;
+			else
+				*ip = sample->addr;
+		} else {
+			*ip = sample->addr;
+		}
+	} else if (sample->flags & (PERF_IP_FLAG_RETURN | PERF_IP_FLAG_TRACE_END)) {
+		if (al->sym)
+			name = al->sym->name;
+		else
+			*ip = sample->ip;
+	}
+	return name;
+}
+
 static int perf_sample__fprintf_callindent(struct perf_sample *sample,
 					   struct perf_evsel *evsel,
 					   struct thread *thread,
@@ -1111,7 +1144,6 @@ static int perf_sample__fprintf_callindent(struct perf_sample *sample,
 {
 	struct perf_event_attr *attr = &evsel->attr;
 	size_t depth = thread_stack__depth(thread);
-	struct addr_location addr_al;
 	const char *name = NULL;
 	static int spacing;
 	int len = 0;
@@ -1125,22 +1157,7 @@ static int perf_sample__fprintf_callindent(struct perf_sample *sample,
 	if (thread->ts && sample->flags & PERF_IP_FLAG_RETURN)
 		depth += 1;
 
-	if (sample->flags & (PERF_IP_FLAG_CALL | PERF_IP_FLAG_TRACE_BEGIN)) {
-		if (sample_addr_correlates_sym(attr)) {
-			thread__resolve(thread, &addr_al, sample);
-			if (addr_al.sym)
-				name = addr_al.sym->name;
-			else
-				ip = sample->addr;
-		} else {
-			ip = sample->addr;
-		}
-	} else if (sample->flags & (PERF_IP_FLAG_RETURN | PERF_IP_FLAG_TRACE_END)) {
-		if (al->sym)
-			name = al->sym->name;
-		else
-			ip = sample->ip;
-	}
+	name = resolve_branch_sym(sample, evsel, thread, al, &ip);
 
 	if (PRINT_FIELD(DSO) && !(PRINT_FIELD(IP) || PRINT_FIELD(ADDR))) {
 		dlen += fprintf(fp, "(");
@@ -1646,6 +1663,47 @@ static void perf_sample__fprint_metric(struct perf_script *script,
 	}
 }
 
+static bool show_event(struct perf_sample *sample,
+		       struct perf_evsel *evsel,
+		       struct thread *thread,
+		       struct addr_location *al)
+{
+	int depth = thread_stack__depth(thread);
+
+	if (!symbol_conf.graph_function)
+		return true;
+
+	if (thread->filter) {
+		if (depth <= thread->filter_entry_depth) {
+			thread->filter = false;
+			return false;
+		}
+		return true;
+	} else {
+		const char *s = symbol_conf.graph_function;
+		u64 ip;
+		const char *name = resolve_branch_sym(sample, evsel, thread, al,
+				&ip);
+		unsigned nlen;
+
+		if (!name)
+			return false;
+		nlen = strlen(name);
+		while (*s) {
+			unsigned len = strcspn(s, ",");
+			if (nlen == len && !strncmp(name, s, len)) {
+				thread->filter = true;
+				thread->filter_entry_depth = depth;
+				return true;
+			}
+			s += len;
+			if (*s == ',')
+				s++;
+		}
+		return false;
+	}
+}
+
 static void process_event(struct perf_script *script,
 			  struct perf_sample *sample, struct perf_evsel *evsel,
 			  struct addr_location *al,
@@ -1660,6 +1718,9 @@ static void process_event(struct perf_script *script,
 	if (output[type].fields == 0)
 		return;
 
+	if (!show_event(sample, evsel, thread, al))
+		return;
+
 	++es->samples;
 
 	perf_sample__fprintf_start(sample, thread, evsel,
@@ -1737,6 +1798,9 @@ static void process_event(struct perf_script *script,
 
 	if (PRINT_FIELD(METRIC))
 		perf_sample__fprint_metric(script, thread, evsel, sample, fp);
+
+	if (verbose)
+		fflush(fp);
 }
 
 static struct scripting_ops	*scripting_ops;
@@ -3100,6 +3164,44 @@ static int perf_script__process_auxtrace_info(struct perf_session *session,
 #define perf_script__process_auxtrace_info 0
 #endif
 
+static int parse_insn_trace(const struct option *opt __maybe_unused,
+			    const char *str __maybe_unused,
+			    int unset __maybe_unused)
+{
+	parse_output_fields(NULL, "+insn,-event,-period", 0);
+	itrace_parse_synth_opts(opt, "i0ns", 0);
+	nanosecs = true;
+	return 0;
+}
+
+static int parse_xed(const struct option *opt __maybe_unused,
+		     const char *str __maybe_unused,
+		     int unset __maybe_unused)
+{
+	force_pager("xed -F insn: -A -64 | less");
+	return 0;
+}
+
+static int parse_call_trace(const struct option *opt __maybe_unused,
+			    const char *str __maybe_unused,
+			    int unset __maybe_unused)
+{
+	parse_output_fields(NULL, "-ip,-addr,-event,-period,+callindent", 0);
+	itrace_parse_synth_opts(opt, "cewp", 0);
+	nanosecs = true;
+	return 0;
+}
+
+static int parse_callret_trace(const struct option *opt __maybe_unused,
+			    const char *str __maybe_unused,
+			    int unset __maybe_unused)
+{
+	parse_output_fields(NULL, "-ip,-addr,-event,-period,+callindent,+flags", 0);
+	itrace_parse_synth_opts(opt, "crewp", 0);
+	nanosecs = true;
+	return 0;
+}
+
 int cmd_script(int argc, const char **argv)
 {
 	bool show_full_info = false;
@@ -3109,7 +3211,10 @@ int cmd_script(int argc, const char **argv)
 	char *rec_script_path = NULL;
 	char *rep_script_path = NULL;
 	struct perf_session *session;
-	struct itrace_synth_opts itrace_synth_opts = { .set = false, };
+	struct itrace_synth_opts itrace_synth_opts = {
+		.set = false,
+		.default_no_sample = true,
+	};
 	char *script_path = NULL;
 	const char **__argv;
 	int i, j, err = 0;
@@ -3184,6 +3289,16 @@ int cmd_script(int argc, const char **argv)
 		    "system-wide collection from all CPUs"),
 	OPT_STRING('S', "symbols", &symbol_conf.sym_list_str, "symbol[,symbol...]",
 		   "only consider these symbols"),
+	OPT_CALLBACK_OPTARG(0, "insn-trace", &itrace_synth_opts, NULL, NULL,
+			"Decode instructions from itrace", parse_insn_trace),
+	OPT_CALLBACK_OPTARG(0, "xed", NULL, NULL, NULL,
+			"Run xed disassembler on output", parse_xed),
+	OPT_CALLBACK_OPTARG(0, "call-trace", &itrace_synth_opts, NULL, NULL,
+			"Decode calls from from itrace", parse_call_trace),
+	OPT_CALLBACK_OPTARG(0, "call-ret-trace", &itrace_synth_opts, NULL, NULL,
+			"Decode calls and returns from itrace", parse_callret_trace),
+	OPT_STRING(0, "graph-function", &symbol_conf.graph_function, "symbol[,symbol...]",
+			"Only print symbols and callees with --call-trace/--call-ret-trace"),
 	OPT_STRING(0, "stop-bt", &symbol_conf.bt_stop_list_str, "symbol[,symbol...]",
 		   "Stop display of callgraph at these symbols"),
 	OPT_STRING('C', "cpu", &cpu_list, "cpu", "list of cpus to profile"),
@@ -3417,8 +3532,10 @@ int cmd_script(int argc, const char **argv)
 		exit(-1);
 	}
 
-	if (!script_name)
+	if (!script_name) {
 		setup_pager();
+		use_browser = 0;
+	}
 
 	session = perf_session__new(&data, false, &script.tool);
 	if (session == NULL)
@@ -3439,7 +3556,8 @@ int cmd_script(int argc, const char **argv)
 	script.session = session;
 	script__setup_sample_type(&script);
 
-	if (output[PERF_TYPE_HARDWARE].fields & PERF_OUTPUT_CALLINDENT)
+	if ((output[PERF_TYPE_HARDWARE].fields & PERF_OUTPUT_CALLINDENT) ||
+	    symbol_conf.graph_function)
 		itrace_synth_opts.thread_stack = true;
 
 	session->itrace_synth_opts = &itrace_synth_opts;

tools/perf/builtin-stat.c

@@ -409,6 +409,28 @@ static struct perf_evsel *perf_evsel__reset_weak_group(struct perf_evsel *evsel)
 	return leader;
 }
 
+static bool is_target_alive(struct target *_target,
+			    struct thread_map *threads)
+{
+	struct stat st;
+	int i;
+
+	if (!target__has_task(_target))
+		return true;
+
+	for (i = 0; i < threads->nr; i++) {
+		char path[PATH_MAX];
+
+		scnprintf(path, PATH_MAX, "%s/%d", procfs__mountpoint(),
+			  threads->map[i].pid);
+
+		if (!stat(path, &st))
+			return true;
+	}
+
+	return false;
+}
+
 static int __run_perf_stat(int argc, const char **argv, int run_idx)
 {
 	int interval = stat_config.interval;
@@ -579,6 +601,8 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
 		enable_counters();
 		while (!done) {
 			nanosleep(&ts, NULL);
+			if (!is_target_alive(&target, evsel_list->threads))
+				break;
 			if (timeout)
 				break;
 			if (interval) {

tools/perf/builtin-top.c

@@ -1134,11 +1134,6 @@ static int __cmd_top(struct perf_top *top)
         if (!target__none(&opts->target))
                 perf_evlist__enable(top->evlist);
 
-	/* Wait for a minimal set of events before starting the snapshot */
-	perf_evlist__poll(top->evlist, 100);
-
-	perf_top__mmap_read(top);
-
 	ret = -1;
 	if (pthread_create(&thread, NULL, (use_browser > 0 ? display_thread_tui :
 							    display_thread), top)) {
@@ -1156,6 +1151,11 @@ static int __cmd_top(struct perf_top *top)
 		}
 	}
 
+	/* Wait for a minimal set of events before starting the snapshot */
+	perf_evlist__poll(top->evlist, 100);
+
+	perf_top__mmap_read(top);
+
 	while (!done) {
 		u64 hits = top->samples;
 
@@ -1257,7 +1257,14 @@ int cmd_top(int argc, const char **argv)
 				.uses_mmap   = true,
 			},
 			.proc_map_timeout    = 500,
-			.overwrite	= 1,
+			/*
+			 * FIXME: This will lose PERF_RECORD_MMAP and other metadata
+			 * when we pause, fix that and reenable. Probably using a
+			 * separate evlist with a dummy event, i.e. a non-overwrite
+			 * ring buffer just for metadata events, while PERF_RECORD_SAMPLE
+			 * stays in overwrite mode. -acme
+			 * */
+			.overwrite	= 0,
 		},
 		.max_stack	     = sysctl__max_stack(),
 		.annotation_opts     = annotation__default_options,
@@ -1372,6 +1379,8 @@ int cmd_top(int argc, const char **argv)
 		    "Show raw trace event output (do not use print fmt or plugins)"),
 	OPT_BOOLEAN(0, "hierarchy", &symbol_conf.report_hierarchy,
 		    "Show entries in a hierarchy"),
+	OPT_BOOLEAN(0, "overwrite", &top.record_opts.overwrite,
+		    "Use a backward ring buffer, default: no"),
 	OPT_BOOLEAN(0, "force", &symbol_conf.force, "don't complain, do it"),
 	OPT_UINTEGER(0, "num-thread-synthesize", &top.nr_threads_synthesize,
 			"number of thread to run event synthesize"),

tools/perf/builtin-trace.c

@@ -89,6 +89,8 @@ struct trace {
 	u64			base_time;
 	FILE			*output;
 	unsigned long		nr_events;
+	unsigned long		nr_events_printed;
+	unsigned long		max_events;
 	struct strlist		*ev_qualifier;
 	struct {
 		size_t		nr;
@@ -612,6 +614,7 @@ static size_t syscall_arg__scnprintf_getrandom_flags(char *bf, size_t size,
 
 struct syscall_arg_fmt {
 	size_t	   (*scnprintf)(char *bf, size_t size, struct syscall_arg *arg);
+	unsigned long (*mask_val)(struct syscall_arg *arg, unsigned long val);
 	void	   *parm;
 	const char *name;
 	bool	   show_zero;
@@ -723,6 +726,10 @@ static struct syscall_fmt {
 	  .arg = { [0] = { .scnprintf = SCA_HEX,	/* addr */ },
 		   [2] = { .scnprintf = SCA_MMAP_PROT,	/* prot */ },
 		   [3] = { .scnprintf = SCA_MMAP_FLAGS,	/* flags */ }, }, },
+	{ .name	    = "mount",
+	  .arg = { [0] = { .scnprintf = SCA_FILENAME, /* dev_name */ },
+		   [3] = { .scnprintf = SCA_MOUNT_FLAGS, /* flags */
+			   .mask_val  = SCAMV_MOUNT_FLAGS, /* flags */ }, }, },
 	{ .name	    = "mprotect",
 	  .arg = { [0] = { .scnprintf = SCA_HEX,	/* start */ },
 		   [2] = { .scnprintf = SCA_MMAP_PROT,	/* prot */ }, }, },
@@ -832,7 +839,8 @@ static struct syscall_fmt {
 	  .arg = { [2] = { .scnprintf = SCA_SIGNUM, /* sig */ }, }, },
 	{ .name	    = "tkill",
 	  .arg = { [1] = { .scnprintf = SCA_SIGNUM, /* sig */ }, }, },
-	{ .name     = "umount2", .alias = "umount", },
+	{ .name     = "umount2", .alias = "umount",
+	  .arg = { [0] = { .scnprintf = SCA_FILENAME, /* name */ }, }, },
 	{ .name	    = "uname", .alias = "newuname", },
 	{ .name	    = "unlinkat",
 	  .arg = { [0] = { .scnprintf = SCA_FDAT, /* dfd */ }, }, },
@@ -856,6 +864,18 @@ static struct syscall_fmt *syscall_fmt__find(const char *name)
 	return bsearch(name, syscall_fmts, nmemb, sizeof(struct syscall_fmt), syscall_fmt__cmp);
 }
 
+static struct syscall_fmt *syscall_fmt__find_by_alias(const char *alias)
+{
+	int i, nmemb = ARRAY_SIZE(syscall_fmts);
+
+	for (i = 0; i < nmemb; ++i) {
+		if (syscall_fmts[i].alias && strcmp(syscall_fmts[i].alias, alias) == 0)
+			return &syscall_fmts[i];
+	}
+
+	return NULL;
+}
+
 /*
  * is_exit: is this "exit" or "exit_group"?
  * is_open: is this "open" or "openat"? To associate the fd returned in sys_exit with the pathname in sys_enter.
@@ -1485,6 +1505,19 @@ static size_t syscall__scnprintf_name(struct syscall *sc, char *bf, size_t size,
 	return scnprintf(bf, size, "arg%d: ", arg->idx);
 }
 
+/*
+ * Check if the value is in fact zero, i.e. mask whatever needs masking, such
+ * as mount 'flags' argument that needs ignoring some magic flag, see comment
+ * in tools/perf/trace/beauty/mount_flags.c
+ */
+static unsigned long syscall__mask_val(struct syscall *sc, struct syscall_arg *arg, unsigned long val)
+{
+	if (sc->arg_fmt && sc->arg_fmt[arg->idx].mask_val)
+		return sc->arg_fmt[arg->idx].mask_val(arg, val);
+
+	return val;
+}
+
 static size_t syscall__scnprintf_val(struct syscall *sc, char *bf, size_t size,
 				     struct syscall_arg *arg, unsigned long val)
 {
@@ -1533,6 +1566,11 @@ static size_t syscall__scnprintf_args(struct syscall *sc, char *bf, size_t size,
 				continue;
 
 			val = syscall_arg__val(&arg, arg.idx);
+			/*
+			 * Some syscall args need some mask, most don't and
+			 * return val untouched.
+			 */
+			val = syscall__mask_val(sc, &arg, val);
 
 			/*
  			 * Suppress this argument if its value is zero and
@@ -1664,6 +1702,8 @@ static int trace__printf_interrupted_entry(struct trace *trace)
 	printed += fprintf(trace->output, "%-70s) ...\n", ttrace->entry_str);
 	ttrace->entry_pending = false;
 
+	++trace->nr_events_printed;
+
 	return printed;
 }
 
@@ -1810,12 +1850,14 @@ static int trace__resolve_callchain(struct trace *trace, struct perf_evsel *evse
 	int max_stack = evsel->attr.sample_max_stack ?
 			evsel->attr.sample_max_stack :
 			trace->max_stack;
+	int err;
 
-	if (machine__resolve(trace->host, &al, sample) < 0 ||
-	    thread__resolve_callchain(al.thread, cursor, evsel, sample, NULL, NULL, max_stack))
+	if (machine__resolve(trace->host, &al, sample) < 0)
 		return -1;
 
-	return 0;
+	err = thread__resolve_callchain(al.thread, cursor, evsel, sample, NULL, NULL, max_stack);
+	addr_location__put(&al);
+	return err;
 }
 
 static int trace__fprintf_callchain(struct trace *trace, struct perf_sample *sample)
@@ -1940,6 +1982,13 @@ errno_print: {
 
 	fputc('\n', trace->output);
 
+	/*
+	 * We only consider an 'event' for the sake of --max-events a non-filtered
+	 * sys_enter + sys_exit and other tracepoint events.
+	 */
+	if (++trace->nr_events_printed == trace->max_events && trace->max_events != ULONG_MAX)
+		interrupted = true;
+
 	if (callchain_ret > 0)
 		trace__fprintf_callchain(trace, sample);
 	else if (callchain_ret < 0)
@@ -2072,14 +2121,25 @@ static void bpf_output__fprintf(struct trace *trace,
 {
 	binary__fprintf(sample->raw_data, sample->raw_size, 8,
 			bpf_output__printer, NULL, trace->output);
+	++trace->nr_events_printed;
 }
 
 static int trace__event_handler(struct trace *trace, struct perf_evsel *evsel,
 				union perf_event *event __maybe_unused,
 				struct perf_sample *sample)
 {
-	struct thread *thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
+	struct thread *thread;
 	int callchain_ret = 0;
+	/*
+	 * Check if we called perf_evsel__disable(evsel) due to, for instance,
+	 * this event's max_events having been hit and this is an entry coming
+	 * from the ring buffer that we should discard, since the max events
+	 * have already been considered/printed.
+	 */
+	if (evsel->disabled)
+		return 0;
+
+	thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
 
 	if (sample->callchain) {
 		callchain_ret = trace__resolve_callchain(trace, evsel, sample, &callchain_cursor);
@@ -2127,6 +2187,12 @@ static int trace__event_handler(struct trace *trace, struct perf_evsel *evsel,
 			event_format__fprintf(evsel->tp_format, sample->cpu,
 					      sample->raw_data, sample->raw_size,
 					      trace->output);
+			++trace->nr_events_printed;
+
+			if (evsel->max_events != ULONG_MAX && ++evsel->nr_events_printed == evsel->max_events) {
+				perf_evsel__disable(evsel);
+				perf_evsel__close(evsel);
+			}
 		}
 	}
 
@@ -2137,8 +2203,8 @@ static int trace__event_handler(struct trace *trace, struct perf_evsel *evsel,
 		trace__fprintf_callchain(trace, sample);
 	else if (callchain_ret < 0)
 		pr_err("Problem processing %s callchain, skipping...\n", perf_evsel__name(evsel));
-	thread__put(thread);
 out:
+	thread__put(thread);
 	return 0;
 }
 
@@ -2225,6 +2291,8 @@ static int trace__pgfault(struct trace *trace,
 		trace__fprintf_callchain(trace, sample);
 	else if (callchain_ret < 0)
 		pr_err("Problem processing %s callchain, skipping...\n", perf_evsel__name(evsel));
+
+	++trace->nr_events_printed;
 out:
 	err = 0;
 out_put:
@@ -2402,6 +2470,9 @@ static void trace__handle_event(struct trace *trace, union perf_event *event, st
 		tracepoint_handler handler = evsel->handler;
 		handler(trace, evsel, event, sample);
 	}
+
+	if (trace->nr_events_printed >= trace->max_events && trace->max_events != ULONG_MAX)
+		interrupted = true;
 }
 
 static int trace__add_syscall_newtp(struct trace *trace)
@@ -2706,7 +2777,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 		int timeout = done ? 100 : -1;
 
 		if (!draining && perf_evlist__poll(evlist, timeout) > 0) {
-			if (perf_evlist__filter_pollfd(evlist, POLLERR | POLLHUP) == 0)
+			if (perf_evlist__filter_pollfd(evlist, POLLERR | POLLHUP | POLLNVAL) == 0)
 				draining = true;
 
 			goto again;
@@ -3138,6 +3209,7 @@ static int trace__parse_events_option(const struct option *opt, const char *str,
 	int len = strlen(str) + 1, err = -1, list, idx;
 	char *strace_groups_dir = system_path(STRACE_GROUPS_DIR);
 	char group_name[PATH_MAX];
+	struct syscall_fmt *fmt;
 
 	if (strace_groups_dir == NULL)
 		return -1;
@@ -3155,12 +3227,19 @@ static int trace__parse_events_option(const struct option *opt, const char *str,
 		if (syscalltbl__id(trace->sctbl, s) >= 0 ||
 		    syscalltbl__strglobmatch_first(trace->sctbl, s, &idx) >= 0) {
 			list = 1;
+			goto do_concat;
+		}
+
+		fmt = syscall_fmt__find_by_alias(s);
+		if (fmt != NULL) {
+			list = 1;
+			s = fmt->name;
 		} else {
 			path__join(group_name, sizeof(group_name), strace_groups_dir, s);
 			if (access(group_name, R_OK) == 0)
 				list = 1;
 		}
-
+do_concat:
 		if (lists[list]) {
 			sprintf(lists[list] + strlen(lists[list]), ",%s", s);
 		} else {
@@ -3249,6 +3328,7 @@ int cmd_trace(int argc, const char **argv)
 		.trace_syscalls = false,
 		.kernel_syscallchains = false,
 		.max_stack = UINT_MAX,
+		.max_events = ULONG_MAX,
 	};
 	const char *output_name = NULL;
 	const struct option trace_options[] = {
@@ -3301,6 +3381,8 @@ int cmd_trace(int argc, const char **argv)
 		     &record_parse_callchain_opt),
 	OPT_BOOLEAN(0, "kernel-syscall-graph", &trace.kernel_syscallchains,
 		    "Show the kernel callchains on the syscall exit path"),
+	OPT_ULONG(0, "max-events", &trace.max_events,
+		"Set the maximum number of events to print, exit after that is reached. "),
 	OPT_UINTEGER(0, "min-stack", &trace.min_stack,
 		     "Set the minimum stack depth when parsing the callchain, "
 		     "anything below the specified depth will be ignored."),

tools/perf/check-headers.sh

@@ -5,6 +5,7 @@ HEADERS='
 include/uapi/drm/drm.h
 include/uapi/drm/i915_drm.h
 include/uapi/linux/fcntl.h
+include/uapi/linux/fs.h
 include/uapi/linux/kcmp.h
 include/uapi/linux/kvm.h
 include/uapi/linux/in.h

tools/perf/perf.h

@@ -81,6 +81,7 @@ struct record_opts {
 	unsigned     initial_delay;
 	bool         use_clockid;
 	clockid_t    clockid;
+	u64          clockid_res_ns;
 	unsigned int proc_map_timeout;
 };
 

tools/perf/scripts/python/call-graph-from-sql.py

-#!/usr/bin/python2
-# call-graph-from-sql.py: create call-graph from sql database
-# Copyright (c) 2014-2017, Intel Corporation.
-#
-# This program is free software; you can redistribute it and/or modify it
-# under the terms and conditions of the GNU General Public License,
-# version 2, as published by the Free Software Foundation.
-#
-# This program is distributed in the hope it will be useful, but WITHOUT
-# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
-# FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
-# more details.
-
-# To use this script you will need to have exported data using either the
-# export-to-sqlite.py or the export-to-postgresql.py script.  Refer to those
-# scripts for details.
-#
-# Following on from the example in the export scripts, a
-# call-graph can be displayed for the pt_example database like this:
-#
-#	python tools/perf/scripts/python/call-graph-from-sql.py pt_example
-#
-# Note that for PostgreSQL, this script supports connecting to remote databases
-# by setting hostname, port, username, password, and dbname e.g.
-#
-#	python tools/perf/scripts/python/call-graph-from-sql.py "hostname=myhost username=myuser password=mypassword dbname=pt_example"
-#
-# The result is a GUI window with a tree representing a context-sensitive
-# call-graph.  Expanding a couple of levels of the tree and adjusting column
-# widths to suit will display something like:
-#
-#                                         Call Graph: pt_example
-# Call Path                          Object      Count   Time(ns)  Time(%)  Branch Count   Branch Count(%)
-# v- ls
-#     v- 2638:2638
-#         v- _start                  ld-2.19.so    1     10074071   100.0         211135            100.0
-#           |- unknown               unknown       1        13198     0.1              1              0.0
-#           >- _dl_start             ld-2.19.so    1      1400980    13.9          19637              9.3
-#           >- _d_linit_internal     ld-2.19.so    1       448152     4.4          11094              5.3
-#           v-__libc_start_main@plt  ls            1      8211741    81.5         180397             85.4
-#              >- _dl_fixup          ld-2.19.so    1         7607     0.1            108              0.1
-#              >- __cxa_atexit       libc-2.19.so  1        11737     0.1             10              0.0
-#              >- __libc_csu_init    ls            1        10354     0.1             10              0.0
-#              |- _setjmp            libc-2.19.so  1            0     0.0              4              0.0
-#              v- main               ls            1      8182043    99.6         180254             99.9
-#
-# Points to note:
-#	The top level is a command name (comm)
-#	The next level is a thread (pid:tid)
-#	Subsequent levels are functions
-#	'Count' is the number of calls
-#	'Time' is the elapsed time until the function returns
-#	Percentages are relative to the level above
-#	'Branch Count' is the total number of branches for that function and all
-#       functions that it calls
-
-import sys
-from PySide.QtCore import *
-from PySide.QtGui import *
-from PySide.QtSql import *
-from decimal import *
-
-class TreeItem():
-
-	def __init__(self, db, row, parent_item):
-		self.db = db
-		self.row = row
-		self.parent_item = parent_item
-		self.query_done = False;
-		self.child_count = 0
-		self.child_items = []
-		self.data = ["", "", "", "", "", "", ""]
-		self.comm_id = 0
-		self.thread_id = 0
-		self.call_path_id = 1
-		self.branch_count = 0
-		self.time = 0
-		if not parent_item:
-			self.setUpRoot()
-
-	def setUpRoot(self):
-		self.query_done = True
-		query = QSqlQuery(self.db)
-		ret = query.exec_('SELECT id, comm FROM comms')
-		if not ret:
-			raise Exception("Query failed: " + query.lastError().text())
-		while query.next():
-			if not query.value(0):
-				continue
-			child_item = TreeItem(self.db, self.child_count, self)
-			self.child_items.append(child_item)
-			self.child_count += 1
-			child_item.setUpLevel1(query.value(0), query.value(1))
-
-	def setUpLevel1(self, comm_id, comm):
-		self.query_done = True;
-		self.comm_id = comm_id
-		self.data[0] = comm
-		self.child_items = []
-		self.child_count = 0
-		query = QSqlQuery(self.db)
-		ret = query.exec_('SELECT thread_id, ( SELECT pid FROM threads WHERE id = thread_id ), ( SELECT tid FROM threads WHERE id = thread_id ) FROM comm_threads WHERE comm_id = ' + str(comm_id))
-		if not ret:
-			raise Exception("Query failed: " + query.lastError().text())
-		while query.next():
-			child_item = TreeItem(self.db, self.child_count, self)
-			self.child_items.append(child_item)
-			self.child_count += 1
-			child_item.setUpLevel2(comm_id, query.value(0), query.value(1), query.value(2))
-
-	def setUpLevel2(self, comm_id, thread_id, pid, tid):
-		self.comm_id = comm_id
-		self.thread_id = thread_id
-		self.data[0] = str(pid) + ":" + str(tid)
-
-	def getChildItem(self, row):
-		return self.child_items[row]
-
-	def getParentItem(self):
-		return self.parent_item
-
-	def getRow(self):
-		return self.row
-
-	def timePercent(self, b):
-		if not self.time:
-			return "0.0"
-		x = (b * Decimal(100)) / self.time
-		return str(x.quantize(Decimal('.1'), rounding=ROUND_HALF_UP))
-
-	def branchPercent(self, b):
-		if not self.branch_count:
-			return "0.0"
-		x = (b * Decimal(100)) / self.branch_count
-		return str(x.quantize(Decimal('.1'), rounding=ROUND_HALF_UP))
-
-	def addChild(self, call_path_id, name, dso, count, time, branch_count):
-		child_item = TreeItem(self.db, self.child_count, self)
-		child_item.comm_id = self.comm_id
-		child_item.thread_id = self.thread_id
-		child_item.call_path_id = call_path_id
-		child_item.branch_count = branch_count
-		child_item.time = time
-		child_item.data[0] = name
-		if dso == "[kernel.kallsyms]":
-			dso = "[kernel]"
-		child_item.data[1] = dso
-		child_item.data[2] = str(count)
-		child_item.data[3] = str(time)
-		child_item.data[4] = self.timePercent(time)
-		child_item.data[5] = str(branch_count)
-		child_item.data[6] = self.branchPercent(branch_count)
-		self.child_items.append(child_item)
-		self.child_count += 1
-
-	def selectCalls(self):
-		self.query_done = True;
-		query = QSqlQuery(self.db)
-		ret = query.exec_('SELECT id, call_path_id, branch_count, call_time, return_time, '
-				  '( SELECT name FROM symbols WHERE id = ( SELECT symbol_id FROM call_paths WHERE id = call_path_id ) ), '
-				  '( SELECT short_name FROM dsos WHERE id = ( SELECT dso_id FROM symbols WHERE id = ( SELECT symbol_id FROM call_paths WHERE id = call_path_id ) ) ), '
-				  '( SELECT ip FROM call_paths where id = call_path_id ) '
-				  'FROM calls WHERE parent_call_path_id = ' + str(self.call_path_id) + ' AND comm_id = ' + str(self.comm_id) + ' AND thread_id = ' + str(self.thread_id) +
-				  ' ORDER BY call_path_id')
-		if not ret:
-			raise Exception("Query failed: " + query.lastError().text())
-		last_call_path_id = 0
-		name = ""
-		dso = ""
-		count = 0
-		branch_count = 0
-		total_branch_count = 0
-		time = 0
-		total_time = 0
-		while query.next():
-			if query.value(1) == last_call_path_id:
-				count += 1
-				branch_count += query.value(2)
-				time += query.value(4) - query.value(3)
-			else:
-				if count:
-					self.addChild(last_call_path_id, name, dso, count, time, branch_count)
-				last_call_path_id = query.value(1)
-				name = query.value(5)
-				dso = query.value(6)
-				count = 1
-				total_branch_count += branch_count
-				total_time += time
-				branch_count = query.value(2)
-				time = query.value(4) - query.value(3)
-		if count:
-			self.addChild(last_call_path_id, name, dso, count, time, branch_count)
-		total_branch_count += branch_count
-		total_time += time
-		# Top level does not have time or branch count, so fix that here
-		if total_branch_count > self.branch_count:
-			self.branch_count = total_branch_count
-			if self.branch_count:
-				for child_item in self.child_items:
-					child_item.data[6] = self.branchPercent(child_item.branch_count)
-		if total_time > self.time:
-			self.time = total_time
-			if self.time:
-				for child_item in self.child_items:
-					child_item.data[4] = self.timePercent(child_item.time)
-
-	def childCount(self):
-		if not self.query_done:
-			self.selectCalls()
-		return self.child_count
-
-	def columnCount(self):
-		return 7
-
-	def columnHeader(self, column):
-		headers = ["Call Path", "Object", "Count ", "Time (ns) ", "Time (%) ", "Branch Count ", "Branch Count (%) "]
-		return headers[column]
-
-	def getData(self, column):
-		return self.data[column]
-
-class TreeModel(QAbstractItemModel):
-
-	def __init__(self, db, parent=None):
-		super(TreeModel, self).__init__(parent)
-		self.db = db
-		self.root = TreeItem(db, 0, None)
-
-	def columnCount(self, parent):
-		return self.root.columnCount()
-
-	def rowCount(self, parent):
-		if parent.isValid():
-			parent_item = parent.internalPointer()
-		else:
-			parent_item = self.root
-		return parent_item.childCount()
-
-	def headerData(self, section, orientation, role):
-		if role == Qt.TextAlignmentRole:
-			if section > 1:
-				return Qt.AlignRight
-		if role != Qt.DisplayRole:
-			return None
-		if orientation != Qt.Horizontal:
-			return None
-		return self.root.columnHeader(section)
-
-	def parent(self, child):
-		child_item = child.internalPointer()
-		if child_item is self.root:
-			return QModelIndex()
-		parent_item = child_item.getParentItem()
-		return self.createIndex(parent_item.getRow(), 0, parent_item)
-
-	def index(self, row, column, parent):
-		if parent.isValid():
-			parent_item = parent.internalPointer()
-		else:
-			parent_item = self.root
-		child_item = parent_item.getChildItem(row)
-		return self.createIndex(row, column, child_item)
-
-	def data(self, index, role):
-		if role == Qt.TextAlignmentRole:
-			if index.column() > 1:
-				return Qt.AlignRight
-		if role != Qt.DisplayRole:
-			return None
-		index_item = index.internalPointer()
-		return index_item.getData(index.column())
-
-class MainWindow(QMainWindow):
-
-	def __init__(self, db, dbname, parent=None):
-		super(MainWindow, self).__init__(parent)
-
-		self.setObjectName("MainWindow")
-		self.setWindowTitle("Call Graph: " + dbname)
-		self.move(100, 100)
-		self.resize(800, 600)
-		style = self.style()
-		icon = style.standardIcon(QStyle.SP_MessageBoxInformation)
-		self.setWindowIcon(icon);
-
-		self.model = TreeModel(db)
-
-		self.view = QTreeView()
-		self.view.setModel(self.model)
-
-		self.setCentralWidget(self.view)
-
-if __name__ == '__main__':
-	if (len(sys.argv) < 2):
-		print >> sys.stderr, "Usage is: call-graph-from-sql.py <database name>"
-		raise Exception("Too few arguments")
-
-	dbname = sys.argv[1]
-
-	is_sqlite3 = False
-	try:
-		f = open(dbname)
-		if f.read(15) == "SQLite format 3":
-			is_sqlite3 = True
-		f.close()
-	except:
-		pass
-
-	if is_sqlite3:
-		db = QSqlDatabase.addDatabase('QSQLITE')
-	else:
-		db = QSqlDatabase.addDatabase('QPSQL')
-		opts = dbname.split()
-		for opt in opts:
-			if '=' in opt:
-				opt = opt.split('=')
-				if opt[0] == 'hostname':
-					db.setHostName(opt[1])
-				elif opt[0] == 'port':
-					db.setPort(int(opt[1]))
-				elif opt[0] == 'username':
-					db.setUserName(opt[1])
-				elif opt[0] == 'password':
-					db.setPassword(opt[1])
-				elif opt[0] == 'dbname':
-					dbname = opt[1]
-			else:
-				dbname = opt
-
-	db.setDatabaseName(dbname)
-	if not db.open():
-		raise Exception("Failed to open database " + dbname + " error: " + db.lastError().text())
-
-	app = QApplication(sys.argv)
-	window = MainWindow(db, dbname)
-	window.show()
-	err = app.exec_()
-	db.close()
-	sys.exit(err)

tools/perf/scripts/python/export-to-postgresql.py

@@ -59,7 +59,7 @@ import datetime
 #	pt_example=# \q
 #
 # An example of using the database is provided by the script
-# call-graph-from-sql.py.  Refer to that script for details.
+# exported-sql-viewer.py.  Refer to that script for details.
 #
 # Tables:
 #

tools/perf/scripts/python/export-to-sqlite.py

@@ -40,7 +40,7 @@ import datetime
 #	sqlite> .quit
 #
 # An example of using the database is provided by the script
-# call-graph-from-sql.py.  Refer to that script for details.
+# exported-sql-viewer.py.  Refer to that script for details.
 #
 # The database structure is practically the same as created by the script
 # export-to-postgresql.py. Refer to that script for details.  A notable

tools/perf/trace/beauty/Build

@@ -5,6 +5,7 @@ ifeq ($(SRCARCH),$(filter $(SRCARCH),x86))
 libperf-y += ioctl.o
 endif
 libperf-y += kcmp.o
+libperf-y += mount_flags.o
 libperf-y += pkey_alloc.o
 libperf-y += prctl.o
 libperf-y += sockaddr.o

tools/perf/trace/beauty/beauty.h

@@ -24,6 +24,7 @@ struct strarray {
 }
 
 size_t strarray__scnprintf(struct strarray *sa, char *bf, size_t size, const char *intfmt, int val);
+size_t strarray__scnprintf_flags(struct strarray *sa, char *bf, size_t size, unsigned long flags);
 
 struct trace;
 struct thread;
@@ -122,6 +123,12 @@ size_t syscall_arg__scnprintf_kcmp_type(char *bf, size_t size, struct syscall_ar
 size_t syscall_arg__scnprintf_kcmp_idx(char *bf, size_t size, struct syscall_arg *arg);
 #define SCA_KCMP_IDX syscall_arg__scnprintf_kcmp_idx
 
+unsigned long syscall_arg__mask_val_mount_flags(struct syscall_arg *arg, unsigned long flags);
+#define SCAMV_MOUNT_FLAGS syscall_arg__mask_val_mount_flags
+
+size_t syscall_arg__scnprintf_mount_flags(char *bf, size_t size, struct syscall_arg *arg);
+#define SCA_MOUNT_FLAGS syscall_arg__scnprintf_mount_flags
+
 size_t syscall_arg__scnprintf_pkey_alloc_access_rights(char *bf, size_t size, struct syscall_arg *arg);
 #define SCA_PKEY_ALLOC_ACCESS_RIGHTS syscall_arg__scnprintf_pkey_alloc_access_rights
 

tools/perf/trace/beauty/clone.c

+// SPDX-License-Identifier: LGPL-2.1
 /*
  * trace/beauty/cone.c
  *
  *  Copyright (C) 2017, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
- *
- * Released under the GPL v2. (and only v2, not any later version)
  */
 
 #include "trace/beauty/beauty.h"