perf/core improvements and fixes:

New features:
 
 - Add 'brstackinsn' field in 'perf script' to reuse the x86 instruction
   decoder used in the Intel PT code to study hot paths to samples (Andi Kleen)
 
 Kernel:
 
 - Default UPROBES_EVENTS to Y (Alexei Starovoitov)
 
 - Fix check for kretprobe offset within function entry (Naveen N. Rao)
 
 Infrastructure:
 
 - Introduce util func is_sdt_event() (Ravi Bangoria)
 
 - Make perf_event__synthesize_mmap_events() scale on older kernels where
   reading /proc/pid/maps is way slower than reading /proc/pid/task/pid/maps (Stephane Eranian)
 
 Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
 -----BEGIN PGP SIGNATURE-----
 Version: GnuPG v2
 
 iQIcBAABCAAGBQJYyrdSAAoJENZQFvNTUqpAe+4P/3c4ilBSOxLCCxGO7jDYo9oq
 /KqlvsCIg7+vo5eqrOUJAb4qXFnvpYxwjMMkL5rx7gdsBCRfRXIINGWUMrq5mNyk
 MgxuqYnp+yRuxLYml2wn+tdwLzcHWSN2EO9mqQ14N4I+HvgdLmVPQ44ACQXs6KfL
 dk/Ix8YtnFWl2sDZjvyr7ZBqwCPzzklZgHM6erxNUr/WJspzUiixAWqUmewodOUl
 P3PitlHXkITOK3AxSqOjJ4g1k933215nGih7hr0XdjEm4pIYaYksShQ6k9DASCrv
 dn2o1pF1LTu7KCtAo70aaSB7GXydwoA//o2gRbDkSwJJ25DIImZxJXQz9PAYDOo1
 vXSIhmlQ72c4/Yv/XzVOrIoMMMpmWKS3lGZxMVGR/Ie9Gw4kbotkaoEqEpNQsaDZ
 iIaU5v/EcvvToT7T7VHrGg0+vmHgYxm5gSlyASi2IrO2/wJAs0v2pYfuL6gYhXGp
 mhv/pHUv4l9OW+Ubm+zJEEcg337c2RQU5wT/bk4PihxY6nQyEH2Pn5VzdNbZLuMR
 eWnqTH/md+8/bkhmuZJp71wm60oPHoPvbDjvtfVmXAa52AzO+NWSc9Veke3C/QRm
 XgNkrXlzeKopEso3j4gw2iAolqw9t8FHFLGgbTkS+6UCKjAM7vNLiIV02LQqhM50
 qCnKEusMDCRgzeOXxYt+
 =Bg5M
 -----END PGP SIGNATURE-----

Merge tag 'perf-core-for-mingo-4.12-20170316' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core

Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo:

New features:

 - Add 'brstackinsn' field in 'perf script' to reuse the x86 instruction
   decoder used in the Intel PT code to study hot paths to samples (Andi Kleen)

Kernel changes:

 - Default UPROBES_EVENTS to Y (Alexei Starovoitov)

 - Fix check for kretprobe offset within function entry (Naveen N. Rao)

Infrastructure changes:

 - Introduce util func is_sdt_event() (Ravi Bangoria)

 - Make perf_event__synthesize_mmap_events() scale on older kernels where
   reading /proc/pid/maps is way slower than reading /proc/pid/task/pid/maps (Stephane Eranian)

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

include/linux/kprobes.h

@@ -268,6 +268,7 @@ extern void show_registers(struct pt_regs *regs);
 extern void kprobes_inc_nmissed_count(struct kprobe *p);
 extern bool arch_within_kprobe_blacklist(unsigned long addr);
 extern bool arch_function_offset_within_entry(unsigned long offset);
+extern bool function_offset_within_entry(kprobe_opcode_t *addr, const char *sym, unsigned long offset);
 
 extern bool within_kprobe_blacklist(unsigned long addr);
 

kernel/kprobes.c

@@ -1391,21 +1391,19 @@ bool within_kprobe_blacklist(unsigned long addr)
  * This returns encoded errors if it fails to look up symbol or invalid
  * combination of parameters.
  */
-static kprobe_opcode_t *kprobe_addr(struct kprobe *p)
+static kprobe_opcode_t *_kprobe_addr(kprobe_opcode_t *addr,
+			const char *symbol_name, unsigned int offset)
 {
-	kprobe_opcode_t *addr = p->addr;
+	if ((symbol_name && addr) || (!symbol_name && !addr))
-
-	if ((p->symbol_name && p->addr) ||
-	    (!p->symbol_name && !p->addr))
 		goto invalid;
 
-	if (p->symbol_name) {
+	if (symbol_name) {
-		kprobe_lookup_name(p->symbol_name, addr);
+		kprobe_lookup_name(symbol_name, addr);
 		if (!addr)
 			return ERR_PTR(-ENOENT);
 	}
 
-	addr = (kprobe_opcode_t *)(((char *)addr) + p->offset);
+	addr = (kprobe_opcode_t *)(((char *)addr) + offset);
 	if (addr)
 		return addr;
 
@@ -1413,6 +1411,11 @@ invalid:
 	return ERR_PTR(-EINVAL);
 }
 
+static kprobe_opcode_t *kprobe_addr(struct kprobe *p)
+{
+	return _kprobe_addr(p->addr, p->symbol_name, p->offset);
+}
+
 /* Check passed kprobe is valid and return kprobe in kprobe_table. */
 static struct kprobe *__get_valid_kprobe(struct kprobe *p)
 {
@@ -1881,19 +1884,28 @@ bool __weak arch_function_offset_within_entry(unsigned long offset)
 	return !offset;
 }
 
+bool function_offset_within_entry(kprobe_opcode_t *addr, const char *sym, unsigned long offset)
+{
+	kprobe_opcode_t *kp_addr = _kprobe_addr(addr, sym, offset);
+
+	if (IS_ERR(kp_addr))
+		return false;
+
+	if (!kallsyms_lookup_size_offset((unsigned long)kp_addr, NULL, &offset) ||
+						!arch_function_offset_within_entry(offset))
+		return false;
+
+	return true;
+}
+
 int register_kretprobe(struct kretprobe *rp)
 {
 	int ret = 0;
 	struct kretprobe_instance *inst;
 	int i;
 	void *addr;
-	unsigned long offset;
 
-	addr = kprobe_addr(&rp->kp);
+	if (!function_offset_within_entry(rp->kp.addr, rp->kp.symbol_name, rp->kp.offset))
-	if (!kallsyms_lookup_size_offset((unsigned long)addr, NULL, &offset))
-		return -EINVAL;
-
-	if (!arch_function_offset_within_entry(offset))
 		return -EINVAL;
 
 	if (kretprobe_blacklist_size) {

kernel/trace/Kconfig

@@ -455,7 +455,7 @@ config UPROBE_EVENTS
 	select UPROBES
 	select PROBE_EVENTS
 	select TRACING
-	default n
+	default y
 	help
 	  This allows the user to add tracing events on top of userspace
 	  dynamic events (similar to tracepoints) on the fly via the trace

kernel/trace/trace_kprobe.c

@@ -697,7 +697,7 @@ static int create_trace_kprobe(int argc, char **argv)
 			return ret;
 		}
 		if (offset && is_return &&
-		    !arch_function_offset_within_entry(offset)) {
+		    !function_offset_within_entry(NULL, symbol, offset)) {
 			pr_info("Given offset is not valid for return probe.\n");
 			return -EINVAL;
 		}

tools/arch/x86/include/asm/cpufeatures.h

@@ -100,7 +100,7 @@
 #define X86_FEATURE_XTOPOLOGY	( 3*32+22) /* cpu topology enum extensions */
 #define X86_FEATURE_TSC_RELIABLE ( 3*32+23) /* TSC is known to be reliable */
 #define X86_FEATURE_NONSTOP_TSC	( 3*32+24) /* TSC does not stop in C states */
-/* free, was #define X86_FEATURE_CLFLUSH_MONITOR ( 3*32+25) * "" clflush reqd with monitor */
+#define X86_FEATURE_CPUID	( 3*32+25) /* CPU has CPUID instruction itself */
 #define X86_FEATURE_EXTD_APICID	( 3*32+26) /* has extended APICID (8 bits) */
 #define X86_FEATURE_AMD_DCM     ( 3*32+27) /* multi-node processor */
 #define X86_FEATURE_APERFMPERF	( 3*32+28) /* APERFMPERF */
@@ -186,7 +186,7 @@
  *
  * Reuse free bits when adding new feature flags!
  */
-
+#define X86_FEATURE_RING3MWAIT	( 7*32+ 0) /* Ring 3 MONITOR/MWAIT */
 #define X86_FEATURE_CPB		( 7*32+ 2) /* AMD Core Performance Boost */
 #define X86_FEATURE_EPB		( 7*32+ 3) /* IA32_ENERGY_PERF_BIAS support */
 #define X86_FEATURE_CAT_L3	( 7*32+ 4) /* Cache Allocation Technology L3 */
@@ -321,5 +321,4 @@
 #define X86_BUG_SWAPGS_FENCE	X86_BUG(11) /* SWAPGS without input dep on GS */
 #define X86_BUG_MONITOR		X86_BUG(12) /* IPI required to wake up remote CPU */
 #define X86_BUG_AMD_E400	X86_BUG(13) /* CPU is among the affected by Erratum 400 */
-
 #endif /* _ASM_X86_CPUFEATURES_H */

tools/perf/Documentation/perf-script.txt

@@ -116,7 +116,7 @@ OPTIONS
 --fields::
         Comma separated list of fields to print. Options are:
         comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff,
-        srcline, period, iregs, brstack, brstacksym, flags, bpf-output,
+        srcline, period, iregs, brstack, brstacksym, flags, bpf-output, brstackinsn,
         callindent, insn, insnlen. Field list can be prepended with the type, trace, sw or hw,
         to indicate to which event type the field list applies.
         e.g., -F sw:comm,tid,time,ip,sym  and -F trace:time,cpu,trace
@@ -189,15 +189,20 @@ OPTIONS
 	i.e., -F "" is not allowed.
 
 	The brstack output includes branch related information with raw addresses using the
-	/v/v/v/v/ syntax in the following order:
+	/v/v/v/v/cycles syntax in the following order:
 	FROM: branch source instruction
 	TO  : branch target instruction
         M/P/-: M=branch target mispredicted or branch direction was mispredicted, P=target predicted or direction predicted, -=not supported
 	X/- : X=branch inside a transactional region, -=not in transaction region or not supported
 	A/- : A=TSX abort entry, -=not aborted region or not supported
+	cycles
 
 	The brstacksym is identical to brstack, except that the FROM and TO addresses are printed in a symbolic form if possible.
 
+	When brstackinsn is specified the full assembler sequences of branch sequences for each sample
+	is printed. This is the full execution path leading to the sample. This is only supported when the
+	sample was recorded with perf record -b or -j any.
+
 -k::
 --vmlinux=<file>::
         vmlinux pathname
@@ -302,6 +307,10 @@ include::itrace.txt[]
 	stop time is not given (i.e, time string is 'x.y,') then analysis goes
 	to end of file.
 
+--max-blocks::
+	Set the maximum number of program blocks to print with brstackasm for
+	each sample.
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-script-perl[1],

tools/perf/builtin-script.c

@@ -28,6 +28,7 @@
 #include <linux/time64.h>
 #include "asm/bug.h"
 #include "util/mem-events.h"
+#include "util/dump-insn.h"
 
 static char const		*script_name;
 static char const		*generate_script_lang;
@@ -42,6 +43,7 @@ static bool			nanosecs;
 static const char		*cpu_list;
 static DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
 static struct perf_stat_config	stat_config;
+static int			max_blocks;
 
 unsigned int scripting_max_stack = PERF_MAX_STACK_DEPTH;
 
@@ -69,6 +71,7 @@ enum perf_output_field {
 	PERF_OUTPUT_CALLINDENT	    = 1U << 20,
 	PERF_OUTPUT_INSN	    = 1U << 21,
 	PERF_OUTPUT_INSNLEN	    = 1U << 22,
+	PERF_OUTPUT_BRSTACKINSN	    = 1U << 23,
 };
 
 struct output_option {
@@ -98,6 +101,7 @@ struct output_option {
 	{.str = "callindent", .field = PERF_OUTPUT_CALLINDENT},
 	{.str = "insn", .field = PERF_OUTPUT_INSN},
 	{.str = "insnlen", .field = PERF_OUTPUT_INSNLEN},
+	{.str = "brstackinsn", .field = PERF_OUTPUT_BRSTACKINSN},
 };
 
 /* default set to maintain compatibility with current format */
@@ -292,7 +296,13 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel,
 		       "selected. Hence, no address to lookup the source line number.\n");
 		return -EINVAL;
 	}
-
+	if (PRINT_FIELD(BRSTACKINSN) &&
+	    !(perf_evlist__combined_branch_type(session->evlist) &
+	      PERF_SAMPLE_BRANCH_ANY)) {
+		pr_err("Display of branch stack assembler requested, but non all-branch filter set\n"
+		       "Hint: run 'perf record -b ...'\n");
+		return -EINVAL;
+	}
 	if ((PRINT_FIELD(PID) || PRINT_FIELD(TID)) &&
 		perf_evsel__check_stype(evsel, PERF_SAMPLE_TID, "TID",
 					PERF_OUTPUT_TID|PERF_OUTPUT_PID))
@@ -546,6 +556,233 @@ static void print_sample_brstacksym(struct perf_sample *sample,
 	}
 }
 
+#define MAXBB 16384UL
+
+static int grab_bb(u8 *buffer, u64 start, u64 end,
+		    struct machine *machine, struct thread *thread,
+		    bool *is64bit, u8 *cpumode, bool last)
+{
+	long offset, len;
+	struct addr_location al;
+	bool kernel;
+
+	if (!start || !end)
+		return 0;
+
+	kernel = machine__kernel_ip(machine, start);
+	if (kernel)
+		*cpumode = PERF_RECORD_MISC_KERNEL;
+	else
+		*cpumode = PERF_RECORD_MISC_USER;
+
+	/*
+	 * Block overlaps between kernel and user.
+	 * This can happen due to ring filtering
+	 * On Intel CPUs the entry into the kernel is filtered,
+	 * but the exit is not. Let the caller patch it up.
+	 */
+	if (kernel != machine__kernel_ip(machine, end)) {
+		printf("\tblock %" PRIx64 "-%" PRIx64 " transfers between kernel and user\n",
+				start, end);
+		return -ENXIO;
+	}
+
+	memset(&al, 0, sizeof(al));
+	if (end - start > MAXBB - MAXINSN) {
+		if (last)
+			printf("\tbrstack does not reach to final jump (%" PRIx64 "-%" PRIx64 ")\n", start, end);
+		else
+			printf("\tblock %" PRIx64 "-%" PRIx64 " (%" PRIu64 ") too long to dump\n", start, end, end - start);
+		return 0;
+	}
+
+	thread__find_addr_map(thread, *cpumode, MAP__FUNCTION, start, &al);
+	if (!al.map || !al.map->dso) {
+		printf("\tcannot resolve %" PRIx64 "-%" PRIx64 "\n", start, end);
+		return 0;
+	}
+	if (al.map->dso->data.status == DSO_DATA_STATUS_ERROR) {
+		printf("\tcannot resolve %" PRIx64 "-%" PRIx64 "\n", start, end);
+		return 0;
+	}
+
+	/* Load maps to ensure dso->is_64_bit has been updated */
+	map__load(al.map);
+
+	offset = al.map->map_ip(al.map, start);
+	len = dso__data_read_offset(al.map->dso, machine, offset, (u8 *)buffer,
+				    end - start + MAXINSN);
+
+	*is64bit = al.map->dso->is_64_bit;
+	if (len <= 0)
+		printf("\tcannot fetch code for block at %" PRIx64 "-%" PRIx64 "\n",
+			start, end);
+	return len;
+}
+
+static void print_jump(uint64_t ip, struct branch_entry *en,
+		       struct perf_insn *x, u8 *inbuf, int len,
+		       int insn)
+{
+	printf("\t%016" PRIx64 "\t%-30s\t#%s%s%s%s",
+	       ip,
+	       dump_insn(x, ip, inbuf, len, NULL),
+	       en->flags.predicted ? " PRED" : "",
+	       en->flags.mispred ? " MISPRED" : "",
+	       en->flags.in_tx ? " INTX" : "",
+	       en->flags.abort ? " ABORT" : "");
+	if (en->flags.cycles) {
+		printf(" %d cycles", en->flags.cycles);
+		if (insn)
+			printf(" %.2f IPC", (float)insn / en->flags.cycles);
+	}
+	putchar('\n');
+}
+
+static void print_ip_sym(struct thread *thread, u8 cpumode, int cpu,
+			 uint64_t addr, struct symbol **lastsym,
+			 struct perf_event_attr *attr)
+{
+	struct addr_location al;
+	int off;
+
+	memset(&al, 0, sizeof(al));
+
+	thread__find_addr_map(thread, cpumode, MAP__FUNCTION, addr, &al);
+	if (!al.map)
+		thread__find_addr_map(thread, cpumode, MAP__VARIABLE,
+				      addr, &al);
+	if ((*lastsym) && al.addr >= (*lastsym)->start && al.addr < (*lastsym)->end)
+		return;
+
+	al.cpu = cpu;
+	al.sym = NULL;
+	if (al.map)
+		al.sym = map__find_symbol(al.map, al.addr);
+
+	if (!al.sym)
+		return;
+
+	if (al.addr < al.sym->end)
+		off = al.addr - al.sym->start;
+	else
+		off = al.addr - al.map->start - al.sym->start;
+	printf("\t%s", al.sym->name);
+	if (off)
+		printf("%+d", off);
+	putchar(':');
+	if (PRINT_FIELD(SRCLINE))
+		map__fprintf_srcline(al.map, al.addr, "\t", stdout);
+	putchar('\n');
+	*lastsym = al.sym;
+}
+
+static void print_sample_brstackinsn(struct perf_sample *sample,
+				     struct thread *thread,
+				     struct perf_event_attr *attr,
+				     struct machine *machine)
+{
+	struct branch_stack *br = sample->branch_stack;
+	u64 start, end;
+	int i, insn, len, nr, ilen;
+	struct perf_insn x;
+	u8 buffer[MAXBB];
+	unsigned off;
+	struct symbol *lastsym = NULL;
+
+	if (!(br && br->nr))
+		return;
+	nr = br->nr;
+	if (max_blocks && nr > max_blocks + 1)
+		nr = max_blocks + 1;
+
+	x.thread = thread;
+	x.cpu = sample->cpu;
+
+	putchar('\n');
+
+	/* Handle first from jump, of which we don't know the entry. */
+	len = grab_bb(buffer, br->entries[nr-1].from,
+			br->entries[nr-1].from,
+			machine, thread, &x.is64bit, &x.cpumode, false);
+	if (len > 0) {
+		print_ip_sym(thread, x.cpumode, x.cpu,
+			     br->entries[nr - 1].from, &lastsym, attr);
+		print_jump(br->entries[nr - 1].from, &br->entries[nr - 1],
+			    &x, buffer, len, 0);
+	}
+
+	/* Print all blocks */
+	for (i = nr - 2; i >= 0; i--) {
+		if (br->entries[i].from || br->entries[i].to)
+			pr_debug("%d: %" PRIx64 "-%" PRIx64 "\n", i,
+				 br->entries[i].from,
+				 br->entries[i].to);
+		start = br->entries[i + 1].to;
+		end   = br->entries[i].from;
+
+		len = grab_bb(buffer, start, end, machine, thread, &x.is64bit, &x.cpumode, false);
+		/* Patch up missing kernel transfers due to ring filters */
+		if (len == -ENXIO && i > 0) {
+			end = br->entries[--i].from;
+			pr_debug("\tpatching up to %" PRIx64 "-%" PRIx64 "\n", start, end);
+			len = grab_bb(buffer, start, end, machine, thread, &x.is64bit, &x.cpumode, false);
+		}
+		if (len <= 0)
+			continue;
+
+		insn = 0;
+		for (off = 0;; off += ilen) {
+			uint64_t ip = start + off;
+
+			print_ip_sym(thread, x.cpumode, x.cpu, ip, &lastsym, attr);
+			if (ip == end) {
+				print_jump(ip, &br->entries[i], &x, buffer + off, len - off, insn);
+				break;
+			} else {
+				printf("\t%016" PRIx64 "\t%s\n", ip,
+					dump_insn(&x, ip, buffer + off, len - off, &ilen));
+				if (ilen == 0)
+					break;
+				insn++;
+			}
+		}
+	}
+
+	/*
+	 * Hit the branch? In this case we are already done, and the target
+	 * has not been executed yet.
+	 */
+	if (br->entries[0].from == sample->ip)
+		return;
+	if (br->entries[0].flags.abort)
+		return;
+
+	/*
+	 * Print final block upto sample
+	 */
+	start = br->entries[0].to;
+	end = sample->ip;
+	len = grab_bb(buffer, start, end, machine, thread, &x.is64bit, &x.cpumode, true);
+	print_ip_sym(thread, x.cpumode, x.cpu, start, &lastsym, attr);
+	if (len <= 0) {
+		/* Print at least last IP if basic block did not work */
+		len = grab_bb(buffer, sample->ip, sample->ip,
+			      machine, thread, &x.is64bit, &x.cpumode, false);
+		if (len <= 0)
+			return;
+
+		printf("\t%016" PRIx64 "\t%s\n", sample->ip,
+			dump_insn(&x, sample->ip, buffer, len, NULL));
+		return;
+	}
+	for (off = 0; off <= end - start; off += ilen) {
+		printf("\t%016" PRIx64 "\t%s\n", start + off,
+			dump_insn(&x, start + off, buffer + off, len - off, &ilen));
+		if (ilen == 0)
+			break;
+	}
+}
 
 static void print_sample_addr(struct perf_sample *sample,
 			  struct thread *thread,
@@ -632,7 +869,9 @@ static void print_sample_callindent(struct perf_sample *sample,
 }
 
 static void print_insn(struct perf_sample *sample,
-		       struct perf_event_attr *attr)
+		       struct perf_event_attr *attr,
+		       struct thread *thread,
+		       struct machine *machine)
 {
 	if (PRINT_FIELD(INSNLEN))
 		printf(" ilen: %d", sample->insn_len);
@@ -643,12 +882,15 @@ static void print_insn(struct perf_sample *sample,
 		for (i = 0; i < sample->insn_len; i++)
 			printf(" %02x", (unsigned char)sample->insn[i]);
 	}
+	if (PRINT_FIELD(BRSTACKINSN))
+		print_sample_brstackinsn(sample, thread, attr, machine);
 }
 
 static void print_sample_bts(struct perf_sample *sample,
 			     struct perf_evsel *evsel,
 			     struct thread *thread,
-			     struct addr_location *al)
+			     struct addr_location *al,
+			     struct machine *machine)
 {
 	struct perf_event_attr *attr = &evsel->attr;
 	bool print_srcline_last = false;
@@ -689,7 +931,7 @@ static void print_sample_bts(struct perf_sample *sample,
 	if (print_srcline_last)
 		map__fprintf_srcline(al->map, al->addr, "\n  ", stdout);
 
-	print_insn(sample, attr);
+	print_insn(sample, attr, thread, machine);
 
 	printf("\n");
 }
@@ -872,7 +1114,8 @@ static size_t data_src__printf(u64 data_src)
 
 static void process_event(struct perf_script *script,
 			  struct perf_sample *sample, struct perf_evsel *evsel,
-			  struct addr_location *al)
+			  struct addr_location *al,
+			  struct machine *machine)
 {
 	struct thread *thread = al->thread;
 	struct perf_event_attr *attr = &evsel->attr;
@@ -899,7 +1142,7 @@ static void process_event(struct perf_script *script,
 		print_sample_flags(sample->flags);
 
 	if (is_bts_event(attr)) {
-		print_sample_bts(sample, evsel, thread, al);
+		print_sample_bts(sample, evsel, thread, al, machine);
 		return;
 	}
 
@@ -937,7 +1180,7 @@ static void process_event(struct perf_script *script,
 
 	if (perf_evsel__is_bpf_output(evsel) && PRINT_FIELD(BPF_OUTPUT))
 		print_sample_bpf_output(sample);
-	print_insn(sample, attr);
+	print_insn(sample, attr, thread, machine);
 	printf("\n");
 }
 
@@ -1047,7 +1290,7 @@ static int process_sample_event(struct perf_tool *tool,
 	if (scripting_ops)
 		scripting_ops->process_event(event, sample, evsel, &al);
 	else
-		process_event(scr, sample, evsel, &al);
+		process_event(scr, sample, evsel, &al, machine);
 
 out_put:
 	addr_location__put(&al);
@@ -2191,7 +2434,8 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 		     "Valid types: hw,sw,trace,raw. "
 		     "Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso,"
 		     "addr,symoff,period,iregs,brstack,brstacksym,flags,"
-		     "bpf-output,callindent,insn,insnlen", parse_output_fields),
+		     "bpf-output,callindent,insn,insnlen,brstackinsn",
+		     parse_output_fields),
 	OPT_BOOLEAN('a', "all-cpus", &system_wide,
 		    "system-wide collection from all CPUs"),
 	OPT_STRING('S', "symbols", &symbol_conf.sym_list_str, "symbol[,symbol...]",
@@ -2222,6 +2466,8 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 	OPT_BOOLEAN('\0', "show-namespace-events", &script.show_namespace_events,
 		    "Show namespace events (if recorded)"),
 	OPT_BOOLEAN('f', "force", &symbol_conf.force, "don't complain, do it"),
+	OPT_INTEGER(0, "max-blocks", &max_blocks,
+		    "Maximum number of code blocks to dump with brstackinsn"),
 	OPT_BOOLEAN(0, "ns", &nanosecs,
 		    "Use 9 decimal places when displaying time"),
 	OPT_CALLBACK_OPTARG(0, "itrace", &itrace_synth_opts, NULL, "opts",

tools/perf/util/Build

@@ -82,6 +82,7 @@ libperf-$(CONFIG_AUXTRACE) += intel-pt-decoder/
 libperf-$(CONFIG_AUXTRACE) += intel-pt.o
 libperf-$(CONFIG_AUXTRACE) += intel-bts.o
 libperf-y += parse-branch-options.o
+libperf-y += dump-insn.o
 libperf-y += parse-regs-options.o
 libperf-y += term.o
 libperf-y += help-unknown-cmd.o

tools/perf/util/dump-insn.c

@@ -0,0 +1,14 @@
+#include <linux/compiler.h>
+#include "dump-insn.h"
+
+/* Fallback code */
+
+__weak
+const char *dump_insn(struct perf_insn *x __maybe_unused,
+		      u64 ip __maybe_unused, u8 *inbuf __maybe_unused,
+		      int inlen __maybe_unused, int *lenp)
+{
+	if (lenp)
+		*lenp = 0;
+	return "?";
+}

tools/perf/util/dump-insn.h

@@ -0,0 +1,22 @@
+#ifndef __PERF_DUMP_INSN_H
+#define __PERF_DUMP_INSN_H 1
+
+#define MAXINSN 15
+
+#include <linux/types.h>
+
+struct thread;
+
+struct perf_insn {
+	/* Initialized by callers: */
+	struct thread *thread;
+	u8	      cpumode;
+	bool	      is64bit;
+	int	      cpu;
+	/* Temporary */
+	char	      out[256];
+};
+
+const char *dump_insn(struct perf_insn *x, u64 ip,
+		      u8 *inbuf, int inlen, int *lenp);
+#endif

tools/perf/util/event.c

@@ -325,8 +325,8 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 	if (machine__is_default_guest(machine))
 		return 0;
 
-	snprintf(filename, sizeof(filename), "%s/proc/%d/maps",
+	snprintf(filename, sizeof(filename), "%s/proc/%d/task/%d/maps",
-		 machine->root_dir, pid);
+		 machine->root_dir, pid, pid);
 
 	fp = fopen(filename, "r");
 	if (fp == NULL) {

tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c

@@ -26,6 +26,7 @@
 #include "insn.c"
 
 #include "intel-pt-insn-decoder.h"
+#include "dump-insn.h"
 
 #if INTEL_PT_INSN_BUF_SZ < MAX_INSN_SIZE || INTEL_PT_INSN_BUF_SZ > MAX_INSN
 #error Instruction buffer size too small
@@ -179,6 +180,29 @@ int intel_pt_get_insn(const unsigned char *buf, size_t len, int x86_64,
 	return 0;
 }
 
+const char *dump_insn(struct perf_insn *x, uint64_t ip __maybe_unused,
+		      u8 *inbuf, int inlen, int *lenp)
+{
+	struct insn insn;
+	int n, i;
+	int left;
+
+	insn_init(&insn, inbuf, inlen, x->is64bit);
+	insn_get_length(&insn);
+	if (!insn_complete(&insn) || insn.length > inlen)
+		return "<bad>";
+	if (lenp)
+		*lenp = insn.length;
+	left = sizeof(x->out);
+	n = snprintf(x->out, left, "insn: ");
+	left -= n;
+	for (i = 0; i < insn.length; i++) {
+		n += snprintf(x->out + n, left, "%02x ", inbuf[i]);
+		left -= n;
+	}
+	return x->out;
+}
+
 const char *branch_name[] = {
 	[INTEL_PT_OP_OTHER]	= "Other",
 	[INTEL_PT_OP_CALL]	= "Call",

tools/perf/util/parse-events.h

@@ -8,6 +8,7 @@
 #include <stdbool.h>
 #include <linux/types.h>
 #include <linux/perf_event.h>
+#include <string.h>
 
 struct list_head;
 struct perf_evsel;
@@ -196,4 +197,23 @@ int is_valid_tracepoint(const char *event_string);
 int valid_event_mount(const char *eventfs);
 char *parse_events_formats_error_string(char *additional_terms);
 
+#ifdef HAVE_LIBELF_SUPPORT
+/*
+ * If the probe point starts with '%',
+ * or starts with "sdt_" and has a ':' but no '=',
+ * then it should be a SDT/cached probe point.
+ */
+static inline bool is_sdt_event(char *str)
+{
+	return (str[0] == '%' ||
+		(!strncmp(str, "sdt_", 4) &&
+		 !!strchr(str, ':') && !strchr(str, '=')));
+}
+#else
+static inline bool is_sdt_event(char *str __maybe_unused)
+{
+	return false;
+}
+#endif /* HAVE_LIBELF_SUPPORT */
+
 #endif /* __PERF_PARSE_EVENTS_H */

tools/perf/util/probe-event.c

@@ -1341,14 +1341,7 @@ static int parse_perf_probe_point(char *arg, struct perf_probe_event *pev)
 	if (!arg)
 		return -EINVAL;
 
-	/*
+	if (is_sdt_event(arg)) {
-	 * If the probe point starts with '%',
-	 * or starts with "sdt_" and has a ':' but no '=',
-	 * then it should be a SDT/cached probe point.
-	 */
-	if (arg[0] == '%' ||
-	    (!strncmp(arg, "sdt_", 4) &&
-	     !!strchr(arg, ':') && !strchr(arg, '='))) {
 		pev->sdt = true;
 		if (arg[0] == '%')
 			arg++;