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

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (106 commits)
  perf kvm: Fix copy & paste error in description
  perf script: Kill script_spec__delete
  perf top: Fix a memory leak
  perf stat: Introduce get_ratio_color() helper
  perf session: Remove impossible condition check
  perf tools: Fix feature-bits rework fallout, remove unused variable
  perf script: Add generic perl handler to process events
  perf tools: Use for_each_set_bit() to iterate over feature flags
  perf tools: Unify handling of features when writing feature section
  perf report: Accept fifos as input file
  perf tools: Moving code in some files
  perf tools: Fix out-of-bound access to struct perf_session
  perf tools: Continue processing header on unknown features
  perf tools: Improve macros for struct feature_ops
  perf: builtin-record: Document and check that mmap_pages must be a power of two.
  perf: builtin-record: Provide advice if mmap'ing fails with EPERM.
  perf tools: Fix truncated annotation
  perf script: look up thread using tid instead of pid
  perf tools: Look up thread names for system wide profiling
  perf tools: Fix comm for processes with named threads
  ...

3 files changed, 40 insertions, 5 deletions

diff --git a/include/linux/bitops.h b/include/linux/bitops.h
index a3ef66a2a083..3c1063acb2ab 100644
--- a/include/linux/bitops.h
+++ b/include/linux/bitops.h
@@ -22,8 +22,14 @@ extern unsigned long __sw_hweight64(__u64 w);
 #include <asm/bitops.h>
 
 #define for_each_set_bit(bit, addr, size) \
-        for ((bit) = find_first_bit((addr), (size)); \
-             (bit) < (size); \
+        for ((bit) = find_first_bit((addr), (size));            \
+             (bit) < (size);                                    \
+             (bit) = find_next_bit((addr), (size), (bit) + 1))
+
+/* same as for_each_set_bit() but use bit as value to start with */
+#define for_each_set_bit_cont(bit, addr, size) \
+        for ((bit) = find_next_bit((addr), (size), (bit));      \
+             (bit) < (size);                                    \
              (bit) = find_next_bit((addr), (size), (bit) + 1))
 
 static __inline__ int get_bitmask_order(unsigned int count)
diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h
index 388b0d425b50..5ce8b140428f 100644
--- a/include/linux/jump_label.h
+++ b/include/linux/jump_label.h
@@ -3,6 +3,7 @@
 
 #include <linux/types.h>
 #include <linux/compiler.h>
+#include <linux/workqueue.h>
 
 #if defined(CC_HAVE_ASM_GOTO) && defined(CONFIG_JUMP_LABEL)
 
@@ -14,6 +15,12 @@ struct jump_label_key {
 #endif
 };
 
+struct jump_label_key_deferred {
+        struct jump_label_key key;
+        unsigned long timeout;
+        struct delayed_work work;
+};
+
 # include <asm/jump_label.h>
 # define HAVE_JUMP_LABEL
 #endif  /* CC_HAVE_ASM_GOTO && CONFIG_JUMP_LABEL */
@@ -51,8 +58,11 @@ extern void arch_jump_label_transform_static(struct jump_entry *entry,
 extern int jump_label_text_reserved(void *start, void *end);
 extern void jump_label_inc(struct jump_label_key *key);
 extern void jump_label_dec(struct jump_label_key *key);
+extern void jump_label_dec_deferred(struct jump_label_key_deferred *key);
 extern bool jump_label_enabled(struct jump_label_key *key);
 extern void jump_label_apply_nops(struct module *mod);
+extern void jump_label_rate_limit(struct jump_label_key_deferred *key,
+                unsigned long rl);
 
 #else  /* !HAVE_JUMP_LABEL */
 
@@ -68,6 +78,10 @@ static __always_inline void jump_label_init(void)
 {
 }
 
+struct jump_label_key_deferred {
+        struct jump_label_key  key;
+};
+
 static __always_inline bool static_branch(struct jump_label_key *key)
 {
         if (unlikely(atomic_read(&key->enabled)))
@@ -85,6 +99,11 @@ static inline void jump_label_dec(struct jump_label_key *key)
         atomic_dec(&key->enabled);
 }
 
+static inline void jump_label_dec_deferred(struct jump_label_key_deferred *key)
+{
+        jump_label_dec(&key->key);
+}
+
 static inline int jump_label_text_reserved(void *start, void *end)
 {
         return 0;
@@ -102,6 +121,14 @@ static inline int jump_label_apply_nops(struct module *mod)
 {
         return 0;
 }
+
+static inline void jump_label_rate_limit(struct jump_label_key_deferred *key,
+                unsigned long rl)
+{
+}
 #endif  /* HAVE_JUMP_LABEL */
 
+#define jump_label_key_enabled  ((struct jump_label_key){ .enabled = ATOMIC_INIT(1), })
+#define jump_label_key_disabled ((struct jump_label_key){ .enabled = ATOMIC_INIT(0), })
+
 #endif  /* _LINUX_JUMP_LABEL_H */
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index b1f89122bf6a..08855613ceb3 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -54,6 +54,7 @@ enum perf_hw_id {
         PERF_COUNT_HW_BUS_CYCLES                = 6,
         PERF_COUNT_HW_STALLED_CYCLES_FRONTEND   = 7,
         PERF_COUNT_HW_STALLED_CYCLES_BACKEND    = 8,
+        PERF_COUNT_HW_REF_CPU_CYCLES            = 9,
 
         PERF_COUNT_HW_MAX,                      /* non-ABI */
 };
@@ -890,6 +891,7 @@ struct perf_event_context {
         int                             nr_active;
         int                             is_active;
         int                             nr_stat;
+        int                             nr_freq;
         int                             rotate_disable;
         atomic_t                        refcount;
         struct task_struct              *task;
@@ -1063,12 +1065,12 @@ perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr)
         }
 }
 
-extern struct jump_label_key perf_sched_events;
+extern struct jump_label_key_deferred perf_sched_events;
 
 static inline void perf_event_task_sched_in(struct task_struct *prev,
                                             struct task_struct *task)
 {
-        if (static_branch(&perf_sched_events))
+        if (static_branch(&perf_sched_events.key))
                 __perf_event_task_sched_in(prev, task);
 }
 
@@ -1077,7 +1079,7 @@ static inline void perf_event_task_sched_out(struct task_struct *prev,
 {
         perf_sw_event(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, NULL, 0);
 
-        if (static_branch(&perf_sched_events))
+        if (static_branch(&perf_sched_events.key))
                 __perf_event_task_sched_out(prev, next);
 }