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

Pull perf updates from Ingo Molnar:
 "The main kernel side changes were:

   - uprobes enhancements (Masami Hiramatsu)

   - Uncore group events enhancements (David Carrillo-Cisneros)

   - x86 Intel: Add support for Skylake server uncore PMUs (Kan Liang)

   - x86 Intel: LBR cleanups and enhancements, for better branch
     annotation tracking (Peter Zijlstra)

   - x86 Intel: Add support for PTWRITE and power event tracing
     (Alexander Shishkin)

   - ... various fixes, cleanups and smaller enhancements.

  Lots of tooling changes - a couple of highlights:

   - Support event group view with hierarchy mode in 'perf top' and
     'perf report' (Namhyung Kim)

     e.g.:

     $ perf record -e '{cycles,instructions}' make
     $ perf report --hierarchy --stdio
     ...
     #   Overhead  Command / Shared Object / Symbol
     # ......................  ..................................
     ...
     25.74%  27.18%sh
     19.96%  24.14%libc-2.24.so
      9.55%  14.64%[.] __strcmp_sse2
      1.54%   0.00%[.] __tfind
      1.07%   1.13%[.] _int_malloc
      0.95%   0.00%[.] __strchr_sse2
      0.89%   1.39%[.] __tsearch
      0.76%   0.00%[.] strlen

   - Add branch stack / basic block info to 'perf annotate --stdio',
     where for each branch, we add an asm comment after the instruction
     with information on how often it was taken and predicted. See
     example with color output at:

       http://vger.kernel.org/~acme/perf/annotate_basic_blocks.png

     (Peter Zijlstra)

   - Add support for using symbols in address filters with Intel PT and
     ARM CoreSight (hardware assisted tracing facilities) (Adrian
     Hunter, Mathieu Poirier)

   - Add support for interacting with Coresight PMU ETMs/PTMs, that are
     IP blocks to perform hardware assisted tracing on a ARM CPU core
     (Mathieu Poirier)

   - Support generating cross arch probes, i.e. if you specify a vmlinux
     file for different arch than the one in the host machine,

        $ perf probe --definition function_name args

     will generate the probe definition string needed to append to the
     target machine /sys/kernel/debug/tracing/kprobes_events file, using
     scripting (Masami Hiramatsu).

   - Allow configuring the default 'perf report -s' sort order in
     ~/.perfconfig, for instance, "sym,dso" may be more fitting for
     kernel developers. (Arnaldo Carvalho de Melo)

   - ... plus lots of other changes, refactorings, features and fixes"

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (149 commits)
  perf tests: Add dwarf unwind test for powerpc
  perf probe: Match linkage name with mangled name
  perf probe: Fix to cut off incompatible chars from group name
  perf probe: Skip if the function address is 0
  perf probe: Ignore the error of finding inline instance
  perf intel-pt: Fix decoding when there are address filters
  perf intel-pt: Enable decoder to handle TIP.PGD with missing IP
  perf intel-pt: Read address filter from AUXTRACE_INFO event
  perf intel-pt: Record address filter in AUXTRACE_INFO event
  perf intel-pt: Add a helper function for processing AUXTRACE_INFO
  perf intel-pt: Fix missing error codes processing auxtrace_info
  perf intel-pt: Add support for recording the max non-turbo ratio
  perf intel-pt: Fix snapshot overlap detection decoder errors
  perf probe: Increase debug level of SDT debug messages
  perf record: Add support for using symbols in address filters
  perf symbols: Add dso__last_symbol()
  perf record: Fix error paths
  perf record: Rename label 'out_symbol_exit'
  perf script: Fix vanished idle symbols
  perf evsel: Add support for address filters
  ...

2 files changed, 37 insertions, 5 deletions

diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h
index 598bc999f4c2..3b77588a9360 100644
--- a/include/linux/bitmap.h
+++ b/include/linux/bitmap.h
@@ -339,6 +339,24 @@ static inline int bitmap_parse(const char *buf, unsigned int buflen,
 	return __bitmap_parse(buf, buflen, 0, maskp, nmaskbits);
 }
 
+/*
+ * bitmap_from_u64 - Check and swap words within u64.
+ *  @mask: source bitmap
+ *  @dst:  destination bitmap
+ *
+ * In 32-bit Big Endian kernel, when using (u32 *)(&val)[*]
+ * to read u64 mask, we will get the wrong word.
+ * That is "(u32 *)(&val)[0]" gets the upper 32 bits,
+ * but we expect the lower 32-bits of u64.
+ */
+static inline void bitmap_from_u64(unsigned long *dst, u64 mask)
+{
+	dst[0] = mask & ULONG_MAX;
+
+	if (sizeof(mask) > sizeof(unsigned long))
+		dst[1] = mask >> 32;
+}
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* __LINUX_BITMAP_H */
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 2b6b43cc0dd5..5c5362584aba 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -510,9 +510,15 @@ typedef void (*perf_overflow_handler_t)(struct perf_event *,
 					struct perf_sample_data *,
 					struct pt_regs *regs);
 
-enum perf_group_flag {
-	PERF_GROUP_SOFTWARE		= 0x1,
-};
+/*
+ * Event capabilities. For event_caps and groups caps.
+ *
+ * PERF_EV_CAP_SOFTWARE: Is a software event.
+ * PERF_EV_CAP_READ_ACTIVE_PKG: A CPU event (or cgroup event) that can be read
+ * from any CPU in the package where it is active.
+ */
+#define PERF_EV_CAP_SOFTWARE		BIT(0)
+#define PERF_EV_CAP_READ_ACTIVE_PKG	BIT(1)
 
 #define SWEVENT_HLIST_BITS		8
 #define SWEVENT_HLIST_SIZE		(1 << SWEVENT_HLIST_BITS)
@@ -568,7 +574,12 @@ struct perf_event {
 	struct hlist_node		hlist_entry;
 	struct list_head		active_entry;
 	int				nr_siblings;
-	int				group_flags;
+
+	/* Not serialized. Only written during event initialization. */
+	int				event_caps;
+	/* The cumulative AND of all event_caps for events in this group. */
+	int				group_caps;
+
 	struct perf_event		*group_leader;
 	struct pmu			*pmu;
 	void				*pmu_private;
@@ -774,6 +785,9 @@ struct perf_cpu_context {
 #ifdef CONFIG_CGROUP_PERF
 	struct perf_cgroup		*cgrp;
 #endif
+
+	struct list_head		sched_cb_entry;
+	int				sched_cb_usage;
 };
 
 struct perf_output_handle {
@@ -985,7 +999,7 @@ static inline bool is_sampling_event(struct perf_event *event)
  */
 static inline int is_software_event(struct perf_event *event)
 {
-	return event->pmu->task_ctx_nr == perf_sw_context;
+	return event->event_caps & PERF_EV_CAP_SOFTWARE;
 }
 
 extern struct static_key perf_swevent_enabled[PERF_COUNT_SW_MAX];