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
  ...

2 files changed, 34 insertions, 18 deletions

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 893a0d07986f..486e84ccb1f9 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -79,7 +79,7 @@ struct perf_branch_stack {
 	struct perf_branch_entry	entries[0];
 };
 
-struct perf_regs_user {
+struct perf_regs {
 	__u64		abi;
 	struct pt_regs	*regs;
 };
@@ -580,34 +580,40 @@ extern u64 perf_event_read_value(struct perf_event *event,
 
 
 struct perf_sample_data {
-	u64				type;
+	/*
+	 * Fields set by perf_sample_data_init(), group so as to
+	 * minimize the cachelines touched.
+	 */
+	u64				addr;
+	struct perf_raw_record		*raw;
+	struct perf_branch_stack	*br_stack;
+	u64				period;
+	u64				weight;
+	u64				txn;
+	union  perf_mem_data_src	data_src;
 
+	/*
+	 * The other fields, optionally {set,used} by
+	 * perf_{prepare,output}_sample().
+	 */
+	u64				type;
 	u64				ip;
 	struct {
 		u32	pid;
 		u32	tid;
 	}				tid_entry;
 	u64				time;
-	u64				addr;
 	u64				id;
 	u64				stream_id;
 	struct {
 		u32	cpu;
 		u32	reserved;
 	}				cpu_entry;
-	u64				period;
-	union  perf_mem_data_src	data_src;
 	struct perf_callchain_entry	*callchain;
-	struct perf_raw_record		*raw;
-	struct perf_branch_stack	*br_stack;
-	struct perf_regs_user		regs_user;
+	struct perf_regs		regs_user;
+	struct perf_regs		regs_intr;
 	u64				stack_user_size;
-	u64				weight;
-	/*
-	 * Transaction flags for abort events:
-	 */
-	u64				txn;
-};
+} ____cacheline_aligned;
 
 /* default value for data source */
 #define PERF_MEM_NA (PERF_MEM_S(OP, NA)   |\
@@ -624,9 +630,6 @@ static inline void perf_sample_data_init(struct perf_sample_data *data,
 	data->raw  = NULL;
 	data->br_stack = NULL;
 	data->period = period;
-	data->regs_user.abi = PERF_SAMPLE_REGS_ABI_NONE;
-	data->regs_user.regs = NULL;
-	data->stack_user_size = 0;
 	data->weight = 0;
 	data->data_src.val = PERF_MEM_NA;
 	data->txn = 0;
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 9d845404d875..9b79abbd1ab8 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -137,8 +137,9 @@ enum perf_event_sample_format {
 	PERF_SAMPLE_DATA_SRC			= 1U << 15,
 	PERF_SAMPLE_IDENTIFIER			= 1U << 16,
 	PERF_SAMPLE_TRANSACTION			= 1U << 17,
+	PERF_SAMPLE_REGS_INTR			= 1U << 18,
 
-	PERF_SAMPLE_MAX = 1U << 18,		/* non-ABI */
+	PERF_SAMPLE_MAX = 1U << 19,		/* non-ABI */
 };
 
 /*
@@ -238,6 +239,7 @@ enum perf_event_read_format {
 #define PERF_ATTR_SIZE_VER2	80	/* add: branch_sample_type */
 #define PERF_ATTR_SIZE_VER3	96	/* add: sample_regs_user */
 					/* add: sample_stack_user */
+#define PERF_ATTR_SIZE_VER4	104	/* add: sample_regs_intr */
 
 /*
  * Hardware event_id to monitor via a performance monitoring event:
@@ -334,6 +336,15 @@ struct perf_event_attr {
 
 	/* Align to u64. */
 	__u32	__reserved_2;
+	/*
+	 * Defines set of regs to dump for each sample
+	 * state captured on:
+	 *  - precise = 0: PMU interrupt
+	 *  - precise > 0: sampled instruction
+	 *
+	 * See asm/perf_regs.h for details.
+	 */
+	__u64	sample_regs_intr;
 };
 
 #define perf_flags(attr)	(*(&(attr)->read_format + 1))
@@ -686,6 +697,8 @@ enum perf_event_type {
 	 *	{ u64			weight;   } && PERF_SAMPLE_WEIGHT
 	 *	{ u64			data_src; } && PERF_SAMPLE_DATA_SRC
 	 *	{ u64			transaction; } && PERF_SAMPLE_TRANSACTION
+	 *	{ u64			abi; # enum perf_sample_regs_abi
+	 *	  u64			regs[weight(mask)]; } && PERF_SAMPLE_REGS_INTR
 	 * };
 	 */
 	PERF_RECORD_SAMPLE			= 9,