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

Pull perf events update from Ingo Molnar:
 "On the kernel side there's few changes, the one that stands out is
  PEBS machine state sampling support on x86, by Stephane Eranian.

  On the tooling side:

  User visible tooling changes:

   - Don't open the DWARF info multiple times, keeping instead a dwfl
     handle in struct dso, greatly speeding up 'perf report' on powerpc.
     (Sukadev Bhattiprolu)

   - Introduce PARSE_OPT_DISABLED option flag and use it to avoid
     showing undersired options in tools that provides frontends to
     'perf record', like sched, kvm, etc (Namhyung Kim)

   - Fallback to kallsyms when using the minimal 'ELF' loader (Arnaldo
     Carvalho de Melo)

   - Fix annotation with kcore (Adrian Hunter)

   - Support source line numbers in annotate using a hotkey (Andi Kleen)

   - Callchain improvements including:
     * Enable printing the srcline in the history
     * Make get_srcline fall back to sym+offset (Andi Kleen)

   - TUI hist_entry browser fixes, including showing missing overhead
     value for first level callchain.  Detected comparing the output of
     --stdio/--gui (that matched) with --tui, that had this problem.
     (Namhyung Kim)

   - Support handling complete branch stacks as histograms (Andi Kleen)

  Tooling infrastructure changes:

   - Prep work for supporting per-pkg and snapshot counters in 'perf
     stat' (Jiri Olsa)

   - 'perf stat' refactorings, moving stuff from it to evsel.c to use in
     per-pkg/snapshot format changes (Jiri Olsa)

   - Add per-pkg format file parsing (Matt Fleming)

   - Clean up libelf feature support code (Namhyung Kim)

   - Add gzip decompression support for kernel modules (Namhyung Kim)

   - More prep patches for Intel PT, including a a thread stack and more
     stuff made available via the database export mechanism (Adrian
     Hunter)

   - More Intel PT work, including a facility to export sample data
     (comms, threads, symbol names, etc) in a database friendly way,
     with an script to use this to create a postgresql database.
     (Adrian Hunter)

   - Make sure that thread->mg->machine points to the machine where the
     thread exists (it was being set only for the kmaps kernel modules
     case, do it as well for the mmaps) and use it to shorten function
     signatures (Arnaldo Carvalho de Melo)

  ... and lots of other fixes and smaller improvements"

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (91 commits)
  perf report: In branch stack mode use address history sorting
  perf report: Add --branch-history option
  perf callchain: Support handling complete branch stacks as histograms
  perf stat: Add support for snapshot counters
  perf stat: Add support for per-pkg counters
  perf tools: Remove perf_evsel__read interface
  perf stat: Use read_counter in read_counter_aggr
  perf stat: Make read_counter work over the thread dimension
  perf stat: Use perf_evsel__read_cb in read_counter
  perf tools: Add snapshot format file parsing
  perf tools: Add per-pkg format file parsing
  perf evsel: Introduce perf_evsel__read_cb function
  perf evsel: Introduce perf_counts_values__scale function
  perf evsel: Introduce perf_evsel__compute_deltas function
  perf tools: Allow to force redirect pr_debug to stderr.
  perf tools: Fix segfault due to invalid kernel dso access
  perf callchain: Make get_srcline fall back to sym+offset
  perf symbols: Move bfd_demangle stubbing to its only user
  perf callchain: Enable printing the srcline in the history
  perf tools: Collapse first level callchain entry if it has sibling
  ...

1 files changed, 51 insertions, 9 deletions

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 1cd5eef1fcd..3e19d3ebc29 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -4460,7 +4460,7 @@ perf_output_sample_regs(struct perf_output_handle *handle,
 	}
 }
 
-static void perf_sample_regs_user(struct perf_regs_user *regs_user,
+static void perf_sample_regs_user(struct perf_regs *regs_user,
 				  struct pt_regs *regs)
 {
 	if (!user_mode(regs)) {
@@ -4471,11 +4471,22 @@ static void perf_sample_regs_user(struct perf_regs_user *regs_user,
 	}
 
 	if (regs) {
-		regs_user->regs = regs;
 		regs_user->abi  = perf_reg_abi(current);
+		regs_user->regs = regs;
+	} else {
+		regs_user->abi = PERF_SAMPLE_REGS_ABI_NONE;
+		regs_user->regs = NULL;
 	}
 }
 
+static void perf_sample_regs_intr(struct perf_regs *regs_intr,
+				  struct pt_regs *regs)
+{
+	regs_intr->regs = regs;
+	regs_intr->abi  = perf_reg_abi(current);
+}
+
+
 /*
  * Get remaining task size from user stack pointer.
  *
@@ -4857,6 +4868,23 @@ void perf_output_sample(struct perf_output_handle *handle,
 	if (sample_type & PERF_SAMPLE_TRANSACTION)
 		perf_output_put(handle, data->txn);
 
+	if (sample_type & PERF_SAMPLE_REGS_INTR) {
+		u64 abi = data->regs_intr.abi;
+		/*
+		 * If there are no regs to dump, notice it through
+		 * first u64 being zero (PERF_SAMPLE_REGS_ABI_NONE).
+		 */
+		perf_output_put(handle, abi);
+
+		if (abi) {
+			u64 mask = event->attr.sample_regs_intr;
+
+			perf_output_sample_regs(handle,
+						data->regs_intr.regs,
+						mask);
+		}
+	}
+
 	if (!event->attr.watermark) {
 		int wakeup_events = event->attr.wakeup_events;
 
@@ -4922,12 +4950,13 @@ void perf_prepare_sample(struct perf_event_header *header,
 		header->size += size;
 	}
 
+	if (sample_type & (PERF_SAMPLE_REGS_USER | PERF_SAMPLE_STACK_USER))
+		perf_sample_regs_user(&data->regs_user, regs);
+
 	if (sample_type & PERF_SAMPLE_REGS_USER) {
 		/* regs dump ABI info */
 		int size = sizeof(u64);
 
-		perf_sample_regs_user(&data->regs_user, regs);
-
 		if (data->regs_user.regs) {
 			u64 mask = event->attr.sample_regs_user;
 			size += hweight64(mask) * sizeof(u64);
@@ -4943,15 +4972,11 @@ void perf_prepare_sample(struct perf_event_header *header,
 		 * in case new sample type is added, because we could eat
 		 * up the rest of the sample size.
 		 */
-		struct perf_regs_user *uregs = &data->regs_user;
 		u16 stack_size = event->attr.sample_stack_user;
 		u16 size = sizeof(u64);
 
-		if (!uregs->abi)
-			perf_sample_regs_user(uregs, regs);
-
 		stack_size = perf_sample_ustack_size(stack_size, header->size,
-						     uregs->regs);
+						     data->regs_user.regs);
 
 		/*
 		 * If there is something to dump, add space for the dump
@@ -4964,6 +4989,21 @@ void perf_prepare_sample(struct perf_event_header *header,
 		data->stack_user_size = stack_size;
 		header->size += size;
 	}
+
+	if (sample_type & PERF_SAMPLE_REGS_INTR) {
+		/* regs dump ABI info */
+		int size = sizeof(u64);
+
+		perf_sample_regs_intr(&data->regs_intr, regs);
+
+		if (data->regs_intr.regs) {
+			u64 mask = event->attr.sample_regs_intr;
+
+			size += hweight64(mask) * sizeof(u64);
+		}
+
+		header->size += size;
+	}
 }
 
 static void perf_event_output(struct perf_event *event,
@@ -7151,6 +7191,8 @@ static int perf_copy_attr(struct perf_event_attr __user *uattr,
 			ret = -EINVAL;
 	}
 
+	if (attr->sample_type & PERF_SAMPLE_REGS_INTR)
+		ret = perf_reg_validate(attr->sample_regs_intr);
 out:
 	return ret;