Merge branch 'perf-fixes-for-linus-2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'perf-fixes-for-linus-2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
  perf: Fix crash in swevents
  perf buildid-list: Fix --with-hits event processing
  perf scripts python: Give field dict to unhandled callback
  perf hist: fix objdump output parsing
  perf-record: Check correct pid when forking
  perf: Do the comm inheritance per thread in event__process_task
  perf: Use event__process_task from perf sched
  perf: Process comm events by tid
  blktrace: Fix new kernel-doc warnings
  perf_events: Fix unincremented buffer base on partial copy
  perf_events: Fix event scheduling issues introduced by transactional API
  perf_events, trace: Fix perf_trace_destroy(), mutex went missing
  perf_events, trace: Fix probe unregister race
  perf_events: Fix races in group composition
  perf_events: Fix races and clean up perf_event and perf_mmap_data interaction

15 files changed, 309 insertions, 176 deletions

diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index c77586061bcb..5db5b7d65a18 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -106,6 +106,7 @@ struct cpu_hw_events {
 
         int                     n_events;
         int                     n_added;
+        int                     n_txn;
         int                     assign[X86_PMC_IDX_MAX]; /* event to counter assignment */
         u64                     tags[X86_PMC_IDX_MAX];
         struct perf_event       *event_list[X86_PMC_IDX_MAX]; /* in enabled order */
@@ -983,6 +984,7 @@ static int x86_pmu_enable(struct perf_event *event)
 out:
         cpuc->n_events = n;
         cpuc->n_added += n - n0;
+        cpuc->n_txn += n - n0;
 
         return 0;
 }
@@ -1089,6 +1091,14 @@ static void x86_pmu_disable(struct perf_event *event)
         struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
         int i;
 
+        /*
+         * If we're called during a txn, we don't need to do anything.
+         * The events never got scheduled and ->cancel_txn will truncate
+         * the event_list.
+         */
+        if (cpuc->group_flag & PERF_EVENT_TXN_STARTED)
+                return;
+
         x86_pmu_stop(event);
 
         for (i = 0; i < cpuc->n_events; i++) {
@@ -1379,6 +1389,7 @@ static void x86_pmu_start_txn(const struct pmu *pmu)
         struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 
         cpuc->group_flag |= PERF_EVENT_TXN_STARTED;
+        cpuc->n_txn = 0;
 }
 
 /*
@@ -1391,6 +1402,11 @@ static void x86_pmu_cancel_txn(const struct pmu *pmu)
         struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 
         cpuc->group_flag &= ~PERF_EVENT_TXN_STARTED;
+        /*
+         * Truncate the collected events.
+         */
+        cpuc->n_added -= cpuc->n_txn;
+        cpuc->n_events -= cpuc->n_txn;
 }
 
 /*
@@ -1419,6 +1435,12 @@ static int x86_pmu_commit_txn(const struct pmu *pmu)
          */
         memcpy(cpuc->assign, assign, n*sizeof(int));
 
+        /*
+         * Clear out the txn count so that ->cancel_txn() which gets
+         * run after ->commit_txn() doesn't undo things.
+         */
+        cpuc->n_txn = 0;
+
         return 0;
 }
 
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index fb6c91eac7e3..5d0266d94985 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -585,6 +585,7 @@ enum perf_event_active_state {
 struct file;
 
 struct perf_mmap_data {
+        atomic_t                        refcount;
         struct rcu_head                 rcu_head;
 #ifdef CONFIG_PERF_USE_VMALLOC
         struct work_struct              work;
@@ -592,7 +593,6 @@ struct perf_mmap_data {
 #endif
         int                             nr_pages;       /* nr of data pages  */
         int                             writable;       /* are we writable   */
-        int                             nr_locked;      /* nr pages mlocked  */
 
         atomic_t                        poll;           /* POLL_ for wakeups */
 
@@ -631,6 +631,9 @@ struct swevent_hlist {
         struct rcu_head         rcu_head;
 };
 
+#define PERF_ATTACH_CONTEXT     0x01
+#define PERF_ATTACH_GROUP       0x02
+
 /**
  * struct perf_event - performance event kernel representation:
  */
@@ -643,10 +646,10 @@ struct perf_event {
         int                             nr_siblings;
         int                             group_flags;
         struct perf_event               *group_leader;
-        struct perf_event               *output;
         const struct pmu                *pmu;
 
         enum perf_event_active_state    state;
+        unsigned int                    attach_state;
         atomic64_t                      count;
 
         /*
@@ -704,6 +707,8 @@ struct perf_event {
         /* mmap bits */
         struct mutex                    mmap_mutex;
         atomic_t                        mmap_count;
+        int                             mmap_locked;
+        struct user_struct              *mmap_user;
         struct perf_mmap_data           *data;
 
         /* poll related */
diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
index 3d685d1f2a03..5a64905d7278 100644
--- a/include/trace/ftrace.h
+++ b/include/trace/ftrace.h
@@ -725,7 +725,7 @@ perf_trace_##call(void *__data, proto)					\
                                                                         \
         { assign; }                                                     \
                                                                         \
-        head = per_cpu_ptr(event_call->perf_events, smp_processor_id());\
+        head = this_cpu_ptr(event_call->perf_events);                   \
         perf_trace_buf_submit(entry, __entry_size, rctx, __addr,        \
                 __count, &__regs, head);                                \
 }
diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index bd7ce8ca5bb9..31d6afe92594 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -283,14 +283,15 @@ ctx_group_list(struct perf_event *event, struct perf_event_context *ctx)
 static void
 list_add_event(struct perf_event *event, struct perf_event_context *ctx)
 {