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:

   - Modernize the kprobe and uprobe creation/destruction tooling ABIs:

     The existing text based APIs (kprobe_events and uprobe_events in
     tracefs), are naive, limited ABIs in that they require user-space
     to clean up after themselves, which is both difficult and fragile
     if the tool is buggy or exits unexpectedly. In other words they are
     not really suited for modern, robust tooling.

     So introduce a modern, file descriptor based ABI that does not have
     these limitations: introduce the 'perf_kprobe' and 'perf_uprobe'
     PMUs and extend the perf_event_open() syscall to create events with
     a kprobe/uprobe attached to them. These [k,u]probe are associated
     with this file descriptor, so they are not available in tracefs.

     (Song Liu)

   - Intel Cannon Lake CPU support (Harry Pan)

   - Intel PT cleanups (Alexander Shishkin)

   - Improve the performance of pinned/flexible event groups by using RB
     trees (Alexey Budankov)

   - Add PERF_EVENT_IOC_MODIFY_ATTRIBUTES which allows the modification
     of hardware breakpoints, which new ABI variant massively speeds up
     existing tooling that uses hardware breakpoints to instrument (and
     debug) memory usage.

     (Milind Chabbi, Jiri Olsa)

   - Various Intel PEBS handling fixes and improvements, and other Intel
     PMU improvements (Kan Liang)

   - Various perf core improvements and optimizations (Peter Zijlstra)

   - ... misc cleanups, fixes and updates.

  There's over 200 tooling commits, here's an (imperfect) list of
  highlights:

   - 'perf annotate' improvements:

      * Recognize and handle jumps to other functions as calls, which
        improves the navigation along jumps and back. (Arnaldo Carvalho
        de Melo)

      * Add the 'P' hotkey in TUI annotation to dump annotation output
        into a file, to ease e-mail reporting of annotation details.
        (Arnaldo Carvalho de Melo)

      * Add an IPC/cycles column to the TUI (Jin Yao)

      * Improve s390 assembly annotation (Thomas Richter)

      * Refactor the output formatting logic to better separate it into
        interactive and non-interactive features and add the --stdio2
        output variant to demonstrate this. (Arnaldo Carvalho de Melo)

   - 'perf script' improvements:

      * Add Python 3 support (Jaroslav Škarvada)

      * Add --show-round-event (Jiri Olsa)

   - 'perf c2c' improvements:

      * Add NUMA analysis support (Jiri Olsa)

   - 'perf trace' improvements:

      * Improve PowerPC support (Ravi Bangoria)

   - 'perf inject' improvements:

      * Integrate ARM CoreSight traces (Robert Walker)

   - 'perf stat' improvements:

      * Add the --interval-count option (yuzhoujian)

      * Add the --timeout option (yuzhoujian)

   - 'perf sched' improvements (Changbin Du)

   - Vendor events improvements :

      * Add IBM s390 vendor events (Thomas Richter)

      * Add and improve arm64 vendor events (John Garry, Ganapatrao
        Kulkarni)

      * Update POWER9 vendor events (Sukadev Bhattiprolu)

   - Intel PT tooling improvements (Adrian Hunter)

   - PMU handling improvements (Agustin Vega-Frias)

   - Record machine topology in perf.data (Jiri Olsa)

   - Various overwrite related cleanups (Kan Liang)

   - Add arm64 dwarf post unwind support (Kim Phillips, Jean Pihet)

   - ... and lots of other changes, cleanups and fixes, see the shortlog
     and Git history for details"

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (262 commits)
  perf/x86/intel: Enable C-state residency events for Cannon Lake
  perf/x86/intel: Add Cannon Lake support for RAPL profiling
  perf/x86/pt, coresight: Clean up address filter structure
  perf vendor events s390: Add JSON files for IBM z14
  perf vendor events s390: Add JSON files for IBM z13
  perf vendor events s390: Add JSON files for IBM zEC12 zBC12
  perf vendor events s390: Add JSON files for IBM z196
  perf vendor events s390: Add JSON files for IBM z10EC z10BC
  perf mmap: Be consistent when checking for an unmaped ring buffer
  perf mmap: Fix accessing unmapped mmap in perf_mmap__read_done()
  perf build: Fix check-headers.sh opts assignment
  perf/x86: Update rdpmc_always_available static key to the modern API
  perf annotate: Use absolute addresses to calculate jump target offsets
  perf annotate: Defer searching for comma in raw line till it is needed
  perf annotate: Support jumping from one function to another
  perf annotate: Add "_local" to jump/offset validation routines
  perf python: Reference Py_None before returning it
  perf annotate: Mark jumps to outher functions with the call arrow
  perf annotate: Pass function descriptor to its instruction parsing routines
  perf annotate: No need to calculate notes->start twice
  ...

4 files changed, 62 insertions, 24 deletions

diff --git a/include/linux/hw_breakpoint.h b/include/linux/hw_breakpoint.h
index cf045885a499..6058c3844a76 100644
--- a/include/linux/hw_breakpoint.h
+++ b/include/linux/hw_breakpoint.h
@@ -53,6 +53,9 @@ register_user_hw_breakpoint(struct perf_event_attr *attr,
 /* FIXME: only change from the attr, and don't unregister */
 extern int
 modify_user_hw_breakpoint(struct perf_event *bp, struct perf_event_attr *attr);
+extern int
+modify_user_hw_breakpoint_check(struct perf_event *bp, struct perf_event_attr *attr,
+				bool check);
 
 /*
  * Kernel breakpoints are not associated with any particular thread.
@@ -97,6 +100,10 @@ register_user_hw_breakpoint(struct perf_event_attr *attr,
 static inline int
 modify_user_hw_breakpoint(struct perf_event *bp,
 			  struct perf_event_attr *attr)	{ return -ENOSYS; }
+static inline int
+modify_user_hw_breakpoint_check(struct perf_event *bp, struct perf_event_attr *attr,
+				bool check)	{ return -ENOSYS; }
+
 static inline struct perf_event *
 register_wide_hw_breakpoint_cpu(struct perf_event_attr *attr,
 				perf_overflow_handler_t	 triggered,
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 7546822a1d74..e71e99eb9a4e 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -449,14 +449,19 @@ struct pmu {
 	int (*filter_match)		(struct perf_event *event); /* optional */
 };
 
+enum perf_addr_filter_action_t {
+	PERF_ADDR_FILTER_ACTION_STOP = 0,
+	PERF_ADDR_FILTER_ACTION_START,
+	PERF_ADDR_FILTER_ACTION_FILTER,
+};
+
 /**
  * struct perf_addr_filter - address range filter definition
  * @entry:	event's filter list linkage
  * @inode:	object file's inode for file-based filters
  * @offset:	filter range offset
- * @size:	filter range size
- * @range:	1: range, 0: address
- * @filter:	1: filter/start, 0: stop
+ * @size:	filter range size (size==0 means single address trigger)
+ * @action:	filter/start/stop
  *
  * This is a hardware-agnostic filter configuration as specified by the user.
  */
@@ -465,8 +470,7 @@ struct perf_addr_filter {
 	struct inode		*inode;
 	unsigned long		offset;
 	unsigned long		size;
-	unsigned int		range	: 1,
-				filter	: 1;
+	enum perf_addr_filter_action_t	action;
 };
 
 /**
@@ -536,6 +540,10 @@ struct pmu_event_list {
 	struct list_head	list;
 };
 
+#define for_each_sibling_event(sibling, event)			\
+	if ((event)->group_leader == (event))			\
+		list_for_each_entry((sibling), &(event)->sibling_list, sibling_list)
+
 /**
  * struct perf_event - performance event kernel representation:
  */
@@ -549,16 +557,16 @@ struct perf_event {
 	struct list_head		event_entry;
 
 	/*
-	 * XXX: group_entry and sibling_list should be mutually exclusive;
-	 * either you're a sibling on a group, or you're the group leader.
-	 * Rework the code to always use the same list element.
-	 *
 	 * Locked for modification by both ctx->mutex and ctx->lock; holding
 	 * either sufficies for read.
 	 */
-	struct list_head		group_entry;
 	struct list_head		sibling_list;
-
+	struct list_head		active_list;
+	/*
+	 * Node on the pinned or flexible tree located at the event context;
+	 */
+	struct rb_node			group_node;
+	u64				group_index;
 	/*
 	 * We need storage to track the entries in perf_pmu_migrate_context; we
 	 * cannot use the event_entry because of RCU and we want to keep the
@@ -690,6 +698,12 @@ struct perf_event {
 #endif /* CONFIG_PERF_EVENTS */
 };
 
+
+struct perf_event_groups {
+	struct rb_root	tree;
+	u64		index;
+};
+
 /**
  * struct perf_event_context - event context structure
  *
@@ -710,9 +724,13 @@ struct perf_event_context {
 	struct mutex			mutex;
 
 	struct list_head		active_ctx_list;
-	struct list_head		pinned_groups;
-	struct list_head		flexible_groups;
+	struct perf_event_groups	pinned_groups;
+	struct perf_event_groups	flexible_groups;
 	struct list_head		event_list;
+
+	struct list_head		pinned_active;
+	struct list_head		flexible_active;
+
 	int				nr_events;
 	int				nr_active;
 	int				is_active;
diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h
index 8a1442c4e513..c20acfcf647d 100644
--- a/include/linux/trace_events.h
+++ b/include/linux/trace_events.h
@@ -540,6 +540,14 @@ extern int  perf_trace_init(struct perf_event *event);
 extern void perf_trace_destroy(struct perf_event *event);
 extern int  perf_trace_add(struct perf_event *event, int flags);
 extern void perf_trace_del(struct perf_event *event, int flags);
+#ifdef CONFIG_KPROBE_EVENTS
+extern int  perf_kprobe_init(struct perf_event *event, bool is_retprobe);
+extern void perf_kprobe_destroy(struct perf_event *event);
+#endif
+#ifdef CONFIG_UPROBE_EVENTS
+extern int  perf_uprobe_init(struct perf_event *event, bool is_retprobe);
+extern void perf_uprobe_destroy(struct perf_event *event);
+#endif
 extern int  ftrace_profile_set_filter(struct perf_event *event, int event_id,
 				     char *filter_str);
 extern void ftrace_profile_free_filter(struct perf_event *event);
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index e0739a1aa4b2..912b85b52344 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -380,10 +380,14 @@ struct perf_event_attr {
 	__u32			bp_type;
 	union {
 		__u64		bp_addr;
+		__u64		kprobe_func; /* for perf_kprobe */
+		__u64		uprobe_path; /* for perf_uprobe */
 		__u64		config1; /* extension of config */
 	};
 	union {
 		__u64		bp_len;
+		__u64		kprobe_addr; /* when kprobe_func == NULL */
+		__u64		probe_offset; /* for perf_[k,u]probe */
 		__u64		config2; /* extension of config1 */
 	};
 	__u64	branch_sample_type; /* enum perf_branch_sample_type */
@@ -444,17 +448,18 @@ struct perf_event_query_bpf {
 /*
  * Ioctls that can be done on a perf event fd:
  */
-#define PERF_EVENT_IOC_ENABLE		_IO ('$', 0)
-#define PERF_EVENT_IOC_DISABLE		_IO ('$', 1)
-#define PERF_EVENT_IOC_REFRESH		_IO ('$', 2)
-#define PERF_EVENT_IOC_RESET		_IO ('$', 3)
-#define PERF_EVENT_IOC_PERIOD		_IOW('$', 4, __u64)
-#define PERF_EVENT_IOC_SET_OUTPUT	_IO ('$', 5)
-#define PERF_EVENT_IOC_SET_FILTER	_IOW('$', 6, char *)
-#define PERF_EVENT_IOC_ID		_IOR('$', 7, __u64 *)
-#define PERF_EVENT_IOC_SET_BPF		_IOW('$', 8, __u32)
-#define PERF_EVENT_IOC_PAUSE_OUTPUT	_IOW('$', 9, __u32)
-#define PERF_EVENT_IOC_QUERY_BPF	_IOWR('$', 10, struct perf_event_query_bpf *)
+#define PERF_EVENT_IOC_ENABLE			_IO ('$', 0)
+#define PERF_EVENT_IOC_DISABLE			_IO ('$', 1)
+#define PERF_EVENT_IOC_REFRESH			_IO ('$', 2)
+#define PERF_EVENT_IOC_RESET			_IO ('$', 3)
+#define PERF_EVENT_IOC_PERIOD			_IOW('$', 4, __u64)
+#define PERF_EVENT_IOC_SET_OUTPUT		_IO ('$', 5)
+#define PERF_EVENT_IOC_SET_FILTER		_IOW('$', 6, char *)
+#define PERF_EVENT_IOC_ID			_IOR('$', 7, __u64 *)
+#define PERF_EVENT_IOC_SET_BPF			_IOW('$', 8, __u32)
+#define PERF_EVENT_IOC_PAUSE_OUTPUT		_IOW('$', 9, __u32)
+#define PERF_EVENT_IOC_QUERY_BPF		_IOWR('$', 10, struct perf_event_query_bpf *)
+#define PERF_EVENT_IOC_MODIFY_ATTRIBUTES	_IOW('$', 11, struct perf_event_attr *)
 
 enum perf_event_ioc_flags {
 	PERF_IOC_FLAG_GROUP		= 1U << 0,