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
  ...

25 files changed, 269 insertions, 66 deletions

diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 28cd6a17491b..6936daf89ddd 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -139,6 +139,7 @@ static int arch__associate_ins_ops(struct arch* arch, const char *name, struct i
 #include "arch/x86/annotate/instructions.c"
 #include "arch/powerpc/annotate/instructions.c"
 #include "arch/s390/annotate/instructions.c"
+#include "arch/sparc/annotate/instructions.c"
 
 static struct arch architectures[] = {
 	{
@@ -170,6 +171,13 @@ static struct arch architectures[] = {
 			.comment_char = '#',
 		},
 	},
+	{
+		.name = "sparc",
+		.init = sparc__annotate_init,
+		.objdump = {
+			.comment_char = '#',
+		},
+	},
 };
 
 static void ins__delete(struct ins_operands *ops)
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index c4617bcfd521..72d5ba2479bf 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -962,16 +962,23 @@ s64 perf_event__process_auxtrace(struct perf_session *session,
 #define PERF_ITRACE_DEFAULT_LAST_BRANCH_SZ	64
 #define PERF_ITRACE_MAX_LAST_BRANCH_SZ		1024
 
-void itrace_synth_opts__set_default(struct itrace_synth_opts *synth_opts)
+void itrace_synth_opts__set_default(struct itrace_synth_opts *synth_opts,
+				    bool no_sample)
 {
-	synth_opts->instructions = true;
 	synth_opts->branches = true;
 	synth_opts->transactions = true;
 	synth_opts->ptwrites = true;
 	synth_opts->pwr_events = true;
 	synth_opts->errors = true;
-	synth_opts->period_type = PERF_ITRACE_DEFAULT_PERIOD_TYPE;
-	synth_opts->period = PERF_ITRACE_DEFAULT_PERIOD;
+	if (no_sample) {
+		synth_opts->period_type = PERF_ITRACE_PERIOD_INSTRUCTIONS;
+		synth_opts->period = 1;
+		synth_opts->calls = true;
+	} else {
+		synth_opts->instructions = true;
+		synth_opts->period_type = PERF_ITRACE_DEFAULT_PERIOD_TYPE;
+		synth_opts->period = PERF_ITRACE_DEFAULT_PERIOD;
+	}
 	synth_opts->callchain_sz = PERF_ITRACE_DEFAULT_CALLCHAIN_SZ;
 	synth_opts->last_branch_sz = PERF_ITRACE_DEFAULT_LAST_BRANCH_SZ;
 	synth_opts->initial_skip = 0;
@@ -999,7 +1006,7 @@ int itrace_parse_synth_opts(const struct option *opt, const char *str,
 	}
 
 	if (!str) {
-		itrace_synth_opts__set_default(synth_opts);
+		itrace_synth_opts__set_default(synth_opts, false);
 		return 0;
 	}
 
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index d88f6e9eb461..8e50f96d4b23 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -58,6 +58,7 @@ enum itrace_period_type {
 /**
  * struct itrace_synth_opts - AUX area tracing synthesis options.
  * @set: indicates whether or not options have been set
+ * @default_no_sample: Default to no sampling.
  * @inject: indicates the event (not just the sample) must be fully synthesized
  *          because 'perf inject' will write it out
  * @instructions: whether to synthesize 'instructions' events
@@ -82,6 +83,7 @@ enum itrace_period_type {
  */
 struct itrace_synth_opts {
 	bool			set;
+	bool			default_no_sample;
 	bool			inject;
 	bool			instructions;
 	bool			branches;
@@ -528,7 +530,8 @@ int perf_event__process_auxtrace_error(struct perf_session *session,
 				       union perf_event *event);
 int itrace_parse_synth_opts(const struct option *opt, const char *str,
 			    int unset);
-void itrace_synth_opts__set_default(struct itrace_synth_opts *synth_opts);
+void itrace_synth_opts__set_default(struct itrace_synth_opts *synth_opts,
+				    bool no_sample);
 
 size_t perf_event__fprintf_auxtrace_error(union perf_event *event, FILE *fp);
 void perf_session__auxtrace_error_inc(struct perf_session *session,
diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index 2ae640257fdb..73430b73570d 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -244,6 +244,27 @@ static void cs_etm__free(struct perf_session *session)
 	zfree(&aux);
 }
 
+static u8 cs_etm__cpu_mode(struct cs_etm_queue *etmq, u64 address)
+{
+	struct machine *machine;
+
+	machine = etmq->etm->machine;
+
+	if (address >= etmq->etm->kernel_start) {
+		if (machine__is_host(machine))
+			return PERF_RECORD_MISC_KERNEL;
+		else
+			return PERF_RECORD_MISC_GUEST_KERNEL;
+	} else {
+		if (machine__is_host(machine))
+			return PERF_RECORD_MISC_USER;
+		else if (perf_guest)
+			return PERF_RECORD_MISC_GUEST_USER;
+		else
+			return PERF_RECORD_MISC_HYPERVISOR;
+	}
+}
+
 static u32 cs_etm__mem_access(struct cs_etm_queue *etmq, u64 address,
 			      size_t size, u8 *buffer)
 {
@@ -258,10 +279,7 @@ static u32 cs_etm__mem_access(struct cs_etm_queue *etmq, u64 address,
 		return -1;
 
 	machine = etmq->etm->machine;
-	if (address >= etmq->etm->kernel_start)
-		cpumode = PERF_RECORD_MISC_KERNEL;
-	else
-		cpumode = PERF_RECORD_MISC_USER;
+	cpumode = cs_etm__cpu_mode(etmq, address);
 
 	thread = etmq->thread;
 	if (!thread) {
@@ -653,7 +671,7 @@ static int cs_etm__synth_instruction_sample(struct cs_etm_queue *etmq,
 	struct perf_sample sample = {.ip = 0,};
 
 	event->sample.header.type = PERF_RECORD_SAMPLE;
-	event->sample.header.misc = PERF_RECORD_MISC_USER;
+	event->sample.header.misc = cs_etm__cpu_mode(etmq, addr);
 	event->sample.header.size = sizeof(struct perf_event_header);
 
 	sample.ip = addr;
@@ -665,7 +683,7 @@ static int cs_etm__synth_instruction_sample(struct cs_etm_queue *etmq,
 	sample.cpu = etmq->packet->cpu;
 	sample.flags = 0;
 	sample.insn_len = 1;
-	sample.cpumode = event->header.misc;
+	sample.cpumode = event->sample.header.misc;
 
 	if (etm->synth_opts.last_branch) {
 		cs_etm__copy_last_branch_rb(etmq);
@@ -706,12 +724,15 @@ static int cs_etm__synth_branch_sample(struct cs_etm_queue *etmq)
 		u64			nr;
 		struct branch_entry	entries;
 	} dummy_bs;
+	u64 ip;
+
+	ip = cs_etm__last_executed_instr(etmq->prev_packet);
 
 	event->sample.header.type = PERF_RECORD_SAMPLE;
-	event->sample.header.misc = PERF_RECORD_MISC_USER;
+	event->sample.header.misc = cs_etm__cpu_mode(etmq, ip);
 	event->sample.header.size = sizeof(struct perf_event_header);
 
-	sample.ip = cs_etm__last_executed_instr(etmq->prev_packet);
+	sample.ip = ip;
 	sample.pid = etmq->pid;
 	sample.tid = etmq->tid;
 	sample.addr = cs_etm__first_executed_instr(etmq->packet);
@@ -720,7 +741,7 @@ static int cs_etm__synth_branch_sample(struct cs_etm_queue *etmq)
 	sample.period = 1;
 	sample.cpu = etmq->packet->cpu;
 	sample.flags = 0;
-	sample.cpumode = PERF_RECORD_MISC_USER;
+	sample.cpumode = event->sample.header.misc;
 
 	/*
 	 * perf report cannot handle events without a branch stack
@@ -1432,7 +1453,8 @@ int cs_etm__process_auxtrace_info(union perf_event *event,
 	if (session->itrace_synth_opts && session->itrace_synth_opts->set) {
 		etm->synth_opts = *session->itrace_synth_opts;
 	} else {
-		itrace_synth_opts__set_default(&etm->synth_opts);
+		itrace_synth_opts__set_default(&etm->synth_opts,
+				session->itrace_synth_opts->default_no_sample);
 		etm->synth_opts.callchain = false;
 	}
 
diff --git a/tools/perf/util/env.h b/tools/perf/util/env.h
index 1f3ccc368530..d01b8355f4ca 100644
--- a/tools/perf/util/env.h
+++ b/tools/perf/util/env.h
@@ -63,6 +63,7 @@ struct perf_env {
 	struct numa_node	*numa_nodes;
 	struct memory_node	*memory_nodes;
 	unsigned long long	 memory_bsize;
+	u64                     clockid_res_ns;
 };
 
 extern struct perf_env perf_env;
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index bc646185f8d9..e9c108a6b1c3 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -308,6 +308,7 @@ static int perf_event__synthesize_fork(struct perf_tool *tool,
 	event->fork.pid  = tgid;
 	event->fork.tid  = pid;
 	event->fork.header.type = PERF_RECORD_FORK;
+	event->fork.header.misc = PERF_RECORD_MISC_FORK_EXEC;
 
 	event->fork.header.size = (sizeof(event->fork) + machine->id_hdr_size);
 
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index be440df29615..e88e6f9b1463 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -358,7 +358,7 @@ void perf_evlist__disable(struct perf_evlist *evlist)
 	struct perf_evsel *pos;
 
 	evlist__for_each_entry(evlist, pos) {
-		if (!perf_evsel__is_group_leader(pos) || !pos->fd)
+		if (pos->disabled || !perf_evsel__is_group_leader(pos) || !pos->fd)
 			continue;
 		perf_evsel__disable(pos);
 	}
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 29d7b97f66fb..6d187059a373 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -232,6 +232,7 @@ void perf_evsel__init(struct perf_evsel *evsel,
 	evsel->leader	   = evsel;
 	evsel->unit	   = "";
 	evsel->scale	   = 1.0;
+	evsel->max_events  = ULONG_MAX;
 	evsel->evlist	   = NULL;
 	evsel->bpf_fd	   = -1;
 	INIT_LIST_HEAD(&evsel->node);
@@ -793,6 +794,9 @@ static void apply_config_terms(struct perf_evsel *evsel,
 		case PERF_EVSEL__CONFIG_TERM_MAX_STACK:
 			max_stack = term->val.max_stack;
 			break;
+		case PERF_EVSEL__CONFIG_TERM_MAX_EVENTS:
+			evsel->max_events = term->val.max_events;
+			break;
 		case PERF_EVSEL__CONFIG_TERM_INHERIT:
 			/*
 			 * attr->inherit should has already been set by
@@ -1203,16 +1207,27 @@ int perf_evsel__append_addr_filter(struct perf_evsel *evsel, const char *filter)
 
 int perf_evsel__enable(struct perf_evsel *evsel)
 {
-	return perf_evsel__run_ioctl(evsel,
-				     PERF_EVENT_IOC_ENABLE,
-				     0);
+	int err = perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_ENABLE, 0);
+
+	if (!err)
+		evsel->disabled = false;
+
+	return err;
 }
 
 int perf_evsel__disable(struct perf_evsel *evsel)
 {
-	return perf_evsel__run_ioctl(evsel,
-				     PERF_EVENT_IOC_DISABLE,
-				     0);
+	int err = perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_DISABLE, 0);
+	/*
+	 * We mark it disabled here so that tools that disable a event can
+	 * ignore events after they disable it. I.e. the ring buffer may have
+	 * already a few more events queued up before the kernel got the stop
+	 * request.
+	 */
+	if (!err)
+		evsel->disabled = true;
+
+	return err;
 }
 
 int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads)
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 4107c39f4a54..3147ca76c6fc 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -46,6 +46,7 @@ enum term_type {
 	PERF_EVSEL__CONFIG_TERM_STACK_USER,
 	PERF_EVSEL__CONFIG_TERM_INHERIT,
 	PERF_EVSEL__CONFIG_TERM_MAX_STACK,
+	PERF_EVSEL__CONFIG_TERM_MAX_EVENTS,
 	PERF_EVSEL__CONFIG_TERM_OVERWRITE,
 	PERF_EVSEL__CONFIG_TERM_DRV_CFG,
 	PERF_EVSEL__CONFIG_TERM_BRANCH,
@@ -65,6 +66,7 @@ struct perf_evsel_config_term {
 		bool	inherit;
 		bool	overwrite;
 		char	*branch;
+		unsigned long max_events;
 	} val;
 	bool weak;
 };
@@ -99,6 +101,8 @@ struct perf_evsel {
 	struct perf_counts	*prev_raw_counts;
 	int			idx;
 	u32			ids;
+	unsigned long		max_events;
+	unsigned long		nr_events_printed;
 	char			*name;
 	double			scale;
 	const char		*unit;
@@ -119,6 +123,7 @@ struct perf_evsel {
 	bool			snapshot;
 	bool 			supported;
 	bool 			needs_swap;
+	bool 			disabled;
 	bool			no_aux_samples;
 	bool			immediate;
 	bool			system_wide;
diff --git a/tools/perf/util/genelf.h b/tools/perf/util/genelf.h
index de322d51c7fe..b72440bf9a79 100644
--- a/tools/perf/util/genelf.h
+++ b/tools/perf/util/genelf.h
@@ -29,6 +29,12 @@ int jit_add_debug_info(Elf *e, uint64_t code_addr, void *debug, int nr_debug_ent
 #elif defined(__powerpc__)
 #define GEN_ELF_ARCH	EM_PPC
 #define GEN_ELF_CLASS	ELFCLASS32
+#elif defined(__sparc__) && defined(__arch64__)
+#define GEN_ELF_ARCH	EM_SPARCV9
+#define GEN_ELF_CLASS	ELFCLASS64
+#elif defined(__sparc__)
+#define GEN_ELF_ARCH	EM_SPARC
+#define GEN_ELF_CLASS	ELFCLASS32
 #else
 #error "unsupported architecture"
 #endif
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 1ec1d9bc2d63..4fd45be95a43 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -1034,6 +1034,13 @@ static int write_auxtrace(struct feat_fd *ff,
 	return err;
 }
 
+static int write_clockid(struct feat_fd *ff,
+			 struct perf_evlist *evlist __maybe_unused)
+{
+	return do_write(ff, &ff->ph->env.clockid_res_ns,
+			sizeof(ff->ph->env.clockid_res_ns));
+}
+
 static int cpu_cache_level__sort(const void *a, const void *b)
 {
 	struct cpu_cache_level *cache_a = (struct cpu_cache_level *)a;
@@ -1508,6 +1515,12 @@ static void print_cpu_topology(struct feat_fd *ff, FILE *fp)
 		fprintf(fp, "# Core ID and Socket ID information is not available\n");
 }
 
+static void print_clockid(struct feat_fd *ff, FILE *fp)
+{
+	fprintf(fp, "# clockid frequency: %"PRIu64" MHz\n",
+		ff->ph->env.clockid_res_ns * 1000);
+}
+
 static void free_event_desc(struct perf_evsel *events)
 {
 	struct perf_evsel *evsel;
@@ -2531,6 +2544,15 @@ out:
 	return ret;
 }
 
+static int process_clockid(struct feat_fd *ff,
+			   void *data __maybe_unused)
+{
+	if (do_read_u64(ff, &ff->ph->env.clockid_res_ns))
+		return -1;
+
+	return 0;
+}
+
 struct feature_ops {
 	int (*write)(struct feat_fd *ff, struct perf_evlist *evlist);
 	void (*print)(struct feat_fd *ff, FILE *fp);
@@ -2590,6 +2612,7 @@ static const struct feature_ops feat_ops[HEADER_LAST_FEATURE] = {
 	FEAT_OPN(CACHE,		cache,		true),
 	FEAT_OPR(SAMPLE_TIME,	sample_time,	false),
 	FEAT_OPR(MEM_TOPOLOGY,	mem_topology,	true),
+	FEAT_OPR(CLOCKID,       clockid,        false)
 };
 
 struct header_print_data {
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index e17903caa71d..0d553ddca0a3 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -38,6 +38,7 @@ enum {
 	HEADER_CACHE,
 	HEADER_SAMPLE_TIME,
 	HEADER_MEM_TOPOLOGY,
+	HEADER_CLOCKID,
 	HEADER_LAST_FEATURE,
 	HEADER_FEAT_BITS	= 256,
 };
diff --git a/tools/perf/util/intel-bts.c b/tools/perf/util/intel-bts.c
index 7f0c83b6332b..7b27d77306c2 100644
--- a/tools/perf/util/intel-bts.c
+++ b/tools/perf/util/intel-bts.c
@@ -269,6 +269,13 @@ static int intel_bts_do_fix_overlap(struct auxtrace_queue *queue,
 	return 0;
 }
 
+static inline u8 intel_bts_cpumode(struct intel_bts *bts, uint64_t ip)
+{
+	return machine__kernel_ip(bts->machine, ip) ?
+	       PERF_RECORD_MISC_KERNEL :
+	       PERF_RECORD_MISC_USER;
+}
+
 static int intel_bts_synth_branch_sample(struct intel_bts_queue *btsq,
 					 struct branch *branch)
 {
@@ -281,12 +288,8 @@ static int intel_bts_synth_branch_sample(struct intel_bts_queue *btsq,
 	    bts->num_events++ <= bts->synth_opts.initial_skip)
 		return 0;
 
-	event.sample.header.type = PERF_RECORD_SAMPLE;
-	event.sample.header.misc = PERF_RECORD_MISC_USER;
-	event.sample.header.size = sizeof(struct perf_event_header);
-
-	sample.cpumode = PERF_RECORD_MISC_USER;
 	sample.ip = le64_to_cpu(branch->from);
+	sample.cpumode = intel_bts_cpumode(bts, sample.ip);
 	sample.pid = btsq->pid;
 	sample.tid = btsq->tid;
 	sample.addr = le64_to_cpu(branch->to);
@@ -298,6 +301,10 @@ static int intel_bts_synth_branch_sample(struct intel_bts_queue *btsq,
 	sample.insn_len = btsq->intel_pt_insn.length;
 	memcpy(sample.insn, btsq->intel_pt_insn.buf, INTEL_PT_INSN_BUF_SZ);
 
+	event.sample.header.type = PERF_RECORD_SAMPLE;
+	event.sample.header.misc = sample.cpumode;
+	event.sample.header.size = sizeof(struct perf_event_header);
+
 	if (bts->synth_opts.inject) {
 		event.sample.header.size = bts->branches_event_size;
 		ret = perf_event__synthesize_sample(&event,
@@ -910,7 +917,8 @@ int intel_bts_process_auxtrace_info(union perf_event *event,
 	if (session->itrace_synth_opts && session->itrace_synth_opts->set) {
 		bts->synth_opts = *session->itrace_synth_opts;
 	} else {
-		itrace_synth_opts__set_default(&bts->synth_opts);
+		itrace_synth_opts__set_default(&bts->synth_opts,
+				session->itrace_synth_opts->default_no_sample);
 		if (session->itrace_synth_opts)
 			bts->synth_opts.thread_stack =
 				session->itrace_synth_opts->thread_stack;
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 48c1d415c6b0..86cc9a64e982 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -407,6 +407,13 @@ intel_pt_cache_lookup(struct dso *dso, struct machine *machine, u64 offset)
 	return auxtrace_cache__lookup(dso->auxtrace_cache, offset);
 }
 
+static inline u8 intel_pt_cpumode(struct intel_pt *pt, uint64_t ip)
+{
+	return ip >= pt->kernel_start ?
+	       PERF_RECORD_MISC_KERNEL :
+	       PERF_RECORD_MISC_USER;
+}
+
 static int intel_pt_walk_next_insn(struct intel_pt_insn *intel_pt_insn,
 				   uint64_t *insn_cnt_ptr, uint64_t *ip,
 				   uint64_t to_ip, uint64_t max_insn_cnt,
@@ -429,10 +436,7 @@ static int intel_pt_walk_next_insn(struct intel_pt_insn *intel_pt_insn,
 	if (to_ip && *ip == to_ip)
 		goto out_no_cache;
 
-	if (*ip >= ptq->pt->kernel_start)
-		cpumode = PERF_RECORD_MISC_KERNEL;
-	else
-		cpumode = PERF_RECORD_MISC_USER;
+	cpumode = intel_pt_cpumode(ptq->pt, *ip);
 
 	thread = ptq->thread;
 	if (!thread) {
@@ -759,7 +763,8 @@ static struct intel_pt_queue *intel_pt_alloc_queue(struct intel_pt *pt,
 	if (pt->synth_opts.callchain) {
 		size_t sz = sizeof(struct ip_callchain);
 
-		sz += pt->synth_opts.callchain_sz * sizeof(u64);
+		/* Add 1 to callchain_sz for callchain context */
+		sz += (pt->synth_opts.callchain_sz + 1) * sizeof(u64);
 		ptq->chain = zalloc(sz);
 		if (!ptq->chain)
 			goto out_free;
@@ -1058,15 +1063,11 @@ static void intel_pt_prep_b_sample(struct intel_pt *pt,
 				   union perf_event *event,
 				   struct perf_sample *sample)
 {
-	event->sample.header.type = PERF_RECORD_SAMPLE;
-	event->sample.header.misc = PERF_RECORD_MISC_USER;
-	event->sample.header.size = sizeof(struct perf_event_header);
-
 	if (!pt->timeless_decoding)
 		sample->time = tsc_to_perf_time(ptq->timestamp, &pt->tc);
 
-	sample->cpumode = PERF_RECORD_MISC_USER;
 	sample->ip = ptq->state->from_ip;
+	sample->cpumode = intel_pt_cpumode(pt, sample->ip);
 	sample->pid = ptq->pid;
 	sample->tid = ptq->tid;
 	sample->addr = ptq->state->to_ip;
@@ -1075,6 +1076,10 @@ static void intel_pt_prep_b_sample(struct intel_pt *pt,
 	sample->flags = ptq->flags;
 	sample->insn_len = ptq->insn_len;
 	memcpy(sample->insn, ptq->insn, INTEL_PT_INSN_BUF_SZ);
+
+	event->sample.header.type = PERF_RECORD_SAMPLE;
+	event->sample.header.misc = sample->cpumode;
+	event->sample.header.size = sizeof(struct perf_event_header);
 }
 
 static int intel_pt_inject_event(union perf_event *event,
@@ -1160,7 +1165,8 @@ static void intel_pt_prep_sample(struct intel_pt *pt,
 
 	if (pt->synth_opts.callchain) {
 		thread_stack__sample(ptq->thread, ptq->chain,
-				     pt->synth_opts.callchain_sz, sample->ip);
+				     pt->synth_opts.callchain_sz + 1,
+				     sample->ip, pt->kernel_start);
 		sample->callchain = ptq->chain;
 	}
 
@@ -2559,7 +2565,8 @@ int intel_pt_process_auxtrace_info(union perf_event *event,
 	if (session->itrace_synth_opts && session->itrace_synth_opts->set) {
 		pt->synth_opts = *session->itrace_synth_opts;
 	} else {
-		itrace_synth_opts__set_default(&pt->synth_opts);
+		itrace_synth_opts__set_default(&pt->synth_opts,
+				session->itrace_synth_opts->default_no_sample);
 		if (use_browser != -1) {
 			pt->synth_opts.branches = false;
 			pt->synth_opts.callchain = true;
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 111ae858cbcb..8f36ce813bc5 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -1708,6 +1708,7 @@ int machine__process_fork_event(struct machine *machine, union perf_event *event
 	struct thread *parent = machine__findnew_thread(machine,
 							event->fork.ppid,
 							event->fork.ptid);
+	bool do_maps_clone = true;
 	int err = 0;
 
 	if (dump_trace)
@@ -1736,9 +1737,25 @@ int machine__process_fork_event(struct machine *machine, union perf_event *event
 
 	thread = machine__findnew_thread(machine, event->fork.pid,
 					 event->fork.tid);
+	/*
+	 * When synthesizing FORK events, we are trying to create thread
+	 * objects for the already running tasks on the machine.
+	 *
+	 * Normally, for a kernel FORK event, we want to clone the parent's
+	 * maps because that is what the kernel just did.
+	 *
+	 * But when synthesizing, this should not be done.  If we do, we end up
+	 * with overlapping maps as we process the sythesized MMAP2 events that
+	 * get delivered shortly thereafter.
+	 *
+	 * Use the FORK event misc flags in an internal way to signal this
+	 * situation, so we can elide the map clone when appropriate.
+	 */
+	if (event->fork.header.misc & PERF_RECORD_MISC_FORK_EXEC)
+		do_maps_clone = false;
 
 	if (thread == NULL || parent == NULL ||
-	    thread__fork(thread, parent, sample->time) < 0) {
+	    thread__fork(thread, parent, sample->time, do_maps_clone) < 0) {
 		dump_printf("problem processing PERF_RECORD_FORK, skipping event.\n");
 		err = -1;
 	}
@@ -2140,6 +2157,27 @@ static int resolve_lbr_callchain_sample(struct thread *thread,
 	return 0;
 }
 
+static int find_prev_cpumode(struct ip_callchain *chain, struct thread *thread,
+			     struct callchain_cursor *cursor,
+			     struct symbol **parent,
+			     struct addr_location *root_al,
+			     u8 *cpumode, int ent)
+{
+	int err = 0;
+
+	while (--ent >= 0) {
+		u64 ip = chain->ips[ent];
+
+		if (ip >= PERF_CONTEXT_MAX) {
+			err = add_callchain_ip(thread, cursor, parent,
+					       root_al, cpumode, ip,
+					       false, NULL, NULL, 0);
+			break;
+		}
+	}
+	return err;
+}
+
 static int thread__resolve_callchain_sample(struct thread *thread,
 					    struct callchain_cursor *cursor,
 					    struct perf_evsel *evsel,
@@ -2246,6 +2284,12 @@ static int thread__resolve_callchain_sample(struct thread *thread,
 	}
 
 check_calls:
+	if (callchain_param.order != ORDER_CALLEE) {
+		err = find_prev_cpumode(chain, thread, cursor, parent, root_al,
+					&cpumode, chain->nr - first_call);
+		if (err)
+			return (err < 0) ? err : 0;
+	}
 	for (i = first_call, nr_entries = 0;
 	     i < chain_nr && nr_entries < max_stack; i++) {
 		u64 ip;
@@ -2260,9 +2304,15 @@ check_calls:
 			continue;
 #endif
 		ip = chain->ips[j];
-
 		if (ip < PERF_CONTEXT_MAX)
                        ++nr_entries;
+		else if (callchain_param.order != ORDER_CALLEE) {
+			err = find_prev_cpumode(chain, thread, cursor, parent,
+						root_al, &cpumode, j);
+			if (err)
+				return (err < 0) ? err : 0;
+			continue;
+		}
 
 		err = add_callchain_ip(thread, cursor, parent,
 				       root_al, &cpumode, ip,
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index f8cd3e7c9186..59be3466d64d 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -926,6 +926,7 @@ static const char *config_term_names[__PARSE_EVENTS__TERM_TYPE_NR] = {
 	[PARSE_EVENTS__TERM_TYPE_NOINHERIT]		= "no-inherit",
 	[PARSE_EVENTS__TERM_TYPE_INHERIT]		= "inherit",
 	[PARSE_EVENTS__TERM_TYPE_MAX_STACK]		= "max-stack",
+	[PARSE_EVENTS__TERM_TYPE_MAX_EVENTS]		= "nr",
 	[PARSE_EVENTS__TERM_TYPE_OVERWRITE]		= "overwrite",
 	[PARSE_EVENTS__TERM_TYPE_NOOVERWRITE]		= "no-overwrite",
 	[PARSE_EVENTS__TERM_TYPE_DRV_CFG]		= "driver-config",
@@ -1037,6 +1038,9 @@ do {									   \
 	case PARSE_EVENTS__TERM_TYPE_MAX_STACK:
 		CHECK_TYPE_VAL(NUM);
 		break;
+	case PARSE_EVENTS__TERM_TYPE_MAX_EVENTS:
+		CHECK_TYPE_VAL(NUM);
+		break;
 	default:
 		err->str = strdup("unknown term");
 		err->idx = term->err_term;
@@ -1084,6 +1088,7 @@ static int config_term_tracepoint(struct perf_event_attr *attr,
 	case PARSE_EVENTS__TERM_TYPE_INHERIT:
 	case PARSE_EVENTS__TERM_TYPE_NOINHERIT:
 	case PARSE_EVENTS__TERM_TYPE_MAX_STACK:
+	case PARSE_EVENTS__TERM_TYPE_MAX_EVENTS:
 	case PARSE_EVENTS__TERM_TYPE_OVERWRITE:
 	case PARSE_EVENTS__TERM_TYPE_NOOVERWRITE:
 		return config_term_common(attr, term, err);
@@ -1162,6 +1167,9 @@ do {								\
 		case PARSE_EVENTS__TERM_TYPE_MAX_STACK:
 			ADD_CONFIG_TERM(MAX_STACK, max_stack, term->val.num);
 			break;
+		case PARSE_EVENTS__TERM_TYPE_MAX_EVENTS:
+			ADD_CONFIG_TERM(MAX_EVENTS, max_events, term->val.num);
+			break;
 		case PARSE_EVENTS__TERM_TYPE_OVERWRITE:
 			ADD_CONFIG_TERM(OVERWRITE, overwrite, term->val.num ? 1 : 0);
 			break;
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index 4473dac27aee..5ed035cbcbb7 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -71,6 +71,7 @@ enum {
 	PARSE_EVENTS__TERM_TYPE_NOINHERIT,
 	PARSE_EVENTS__TERM_TYPE_INHERIT,
 	PARSE_EVENTS__TERM_TYPE_MAX_STACK,
+	PARSE_EVENTS__TERM_TYPE_MAX_EVENTS,
 	PARSE_EVENTS__TERM_TYPE_NOOVERWRITE,
 	PARSE_EVENTS__TERM_TYPE_OVERWRITE,
 	PARSE_EVENTS__TERM_TYPE_DRV_CFG,
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index 5f761f3ed0f3..7805c71aaae2 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -269,6 +269,7 @@ time			{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_TIME); }
 call-graph		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CALLGRAPH); }
 stack-size		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_STACKSIZE); }
 max-stack		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_MAX_STACK); }
+nr			{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_MAX_EVENTS); }
 inherit			{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_INHERIT); }
 no-inherit		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_NOINHERIT); }
 overwrite		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_OVERWRITE); }
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 0281d5e2cd67..66a84d5846c8 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -324,7 +324,17 @@ int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss)
 			plt_entry_size = 16;
 			break;
 
-		default: /* FIXME: s390/alpha/mips/parisc/poperpc/sh/sparc/xtensa need to be checked */
+		case EM_SPARC:
+			plt_header_size = 48;
+			plt_entry_size = 12;
+			break;
+
+		case EM_SPARCV9:
+			plt_header_size = 128;
+			plt_entry_size = 32;
+			break;
+
+		default: /* FIXME: s390/alpha/mips/parisc/poperpc/sh/xtensa need to be checked */
 			plt_header_size = shdr_plt.sh_entsize;
 			plt_entry_size = shdr_plt.sh_entsize;
 			break;
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 20f49779116b..d026d215bdc6 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -123,7 +123,8 @@ struct symbol_conf {
 	const char	*vmlinux_name,
 			*kallsyms_name,
 			*source_prefix,
-			*field_sep;
+			*field_sep,
+			*graph_function;
 	const char	*default_guest_vmlinux_name,
 			*default_guest_kallsyms,
 			*default_guest_modules;
diff --git a/tools/perf/util/thread-stack.c b/tools/perf/util/thread-stack.c
index c091635bf7dc..61a4286a74dc 100644
--- a/tools/perf/util/thread-stack.c
+++ b/tools/perf/util/thread-stack.c
@@ -310,20 +310,46 @@ void thread_stack__free(struct thread *thread)
 	}
 }
 
+static inline u64 callchain_context(u64 ip, u64 kernel_start)
+{
+	return ip < kernel_start ? PERF_CONTEXT_USER : PERF_CONTEXT_KERNEL;
+}
+
 void thread_stack__sample(struct thread *thread, struct ip_callchain *chain,
-			  size_t sz, u64 ip)
+			  size_t sz, u64 ip, u64 kernel_start)
 {
-	size_t i;
+	u64 context = callchain_context(ip, kernel_start);
+	u64 last_context;
+	size_t i, j;
 
-	if (!thread || !thread->ts)
-		chain->nr = 1;
-	else
-		chain->nr = min(sz, thread->ts->cnt + 1);
+	if (sz < 2) {
+		chain->nr = 0;
+		return;
+	}
 
-	chain->ips[0] = ip;
+	chain->ips[0] = context;
+	chain->ips[1] = ip;
+
+	if (!thread || !thread->ts) {
+		chain->nr = 2;
+		return;
+	}
+
+	last_context = context;
+
+	for (i = 2, j = 1; i < sz && j <= thread->ts->cnt; i++, j++) {
+		ip = thread->ts->stack[thread->ts->cnt - j].ret_addr;
+		context = callchain_context(ip, kernel_start);
+		if (context != last_context) {
+			if (i >= sz - 1)
+				break;
+			chain->ips[i++] = context;
+			last_context = context;
+		}
+		chain->ips[i] = ip;
+	}
 
-	for (i = 1; i < chain->nr; i++)
-		chain->ips[i] = thread->ts->stack[thread->ts->cnt - i].ret_addr;
+	chain->nr = i;
 }
 
 struct call_return_processor *
diff --git a/tools/perf/util/thread-stack.h b/tools/perf/util/thread-stack.h
index b7e41c4ebfdd..f97c00a8c251 100644
--- a/tools/perf/util/thread-stack.h
+++ b/tools/perf/util/thread-stack.h
@@ -84,7 +84,7 @@ int thread_stack__event(struct thread *thread, u32 flags, u64 from_ip,
 			u64 to_ip, u16 insn_len, u64 trace_nr);
 void thread_stack__set_trace_nr(struct thread *thread, u64 trace_nr);
 void thread_stack__sample(struct thread *thread, struct ip_callchain *chain,
-			  size_t sz, u64 ip);
+			  size_t sz, u64 ip, u64 kernel_start);
 int thread_stack__flush(struct thread *thread);
 void thread_stack__free(struct thread *thread);
 size_t thread_stack__depth(struct thread *thread);
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 2048d393ece6..3d9ed7d0e281 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -330,7 +330,8 @@ static int thread__prepare_access(struct thread *thread)
 }
 
 static int thread__clone_map_groups(struct thread *thread,
-				    struct thread *parent)
+				    struct thread *parent,
+				    bool do_maps_clone)
 {
 	/* This is new thread, we share map groups for process. */
 	if (thread->pid_ == parent->pid_)
@@ -341,15 +342,11 @@ static int thread__clone_map_groups(struct thread *thread,
 			 thread->pid_, thread->tid, parent->pid_, parent->tid);
 		return 0;
 	}
-
 	/* But this one is new process, copy maps. */
-	if (map_groups__clone(thread, parent->mg) < 0)
-		return -ENOMEM;
-
-	return 0;
+	return do_maps_clone ? map_groups__clone(thread, parent->mg) : 0;
 }
 
-int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp)
+int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp, bool do_maps_clone)
 {
 	if (parent->comm_set) {
 		const char *comm = thread__comm_str(parent);
@@ -362,7 +359,7 @@ int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp)
 	}
 
 	thread->ppid = parent->tid;
-	return thread__clone_map_groups(thread, parent);
+	return thread__clone_map_groups(thread, parent, do_maps_clone);
 }
 
 void thread__find_cpumode_addr_location(struct thread *thread, u64 addr,
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index 07606aa6998d..30e2b4c165fe 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -42,6 +42,8 @@ struct thread {
 	void				*addr_space;
 	struct unwind_libunwind_ops	*unwind_libunwind_ops;
 #endif
+	bool			filter;
+	int			filter_entry_depth;
 };
 
 struct machine;
@@ -87,7 +89,7 @@ struct comm *thread__comm(const struct thread *thread);
 struct comm *thread__exec_comm(const struct thread *thread);
 const char *thread__comm_str(const struct thread *thread);
 int thread__insert_map(struct thread *thread, struct map *map);
-int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp);
+int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp, bool do_maps_clone);
 size_t thread__fprintf(struct thread *thread, FILE *fp);
 
 struct thread *thread__main_thread(struct machine *machine, struct thread *thread);
diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c
index 6f318b15950e..5eff9bfc5758 100644
--- a/tools/perf/util/unwind-libdw.c
+++ b/tools/perf/util/unwind-libdw.c
@@ -45,13 +45,13 @@ static int __report_module(struct addr_location *al, u64 ip,
 		Dwarf_Addr s;
 
 		dwfl_module_info(mod, NULL, &s, NULL, NULL, NULL, NULL, NULL);
-		if (s != al->map->start)
+		if (s != al->map->start - al->map->pgoff)
 			mod = 0;
 	}
 
 	if (!mod)
 		mod = dwfl_report_elf(ui->dwfl, dso->short_name,
-				      (dso->symsrc_filename ? dso->symsrc_filename : dso->long_name), -1, al->map->start,
+				      (dso->symsrc_filename ? dso->symsrc_filename : dso->long_name), -1, al->map->start - al->map->pgoff,
 				      false);
 
 	return mod && dwfl_addrmodule(ui->dwfl, ip) == mod ? 0 : -1;