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
  ...

1 files changed, 19 insertions, 12 deletions

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;