Merge remote branch 'rmk/for-linus' into for-linus

* rmk/for-linus: (1557 commits)
  ARM: 6806/1: irq: introduce entry and exit functions for chained handlers
  ARM: 6781/1: Thumb-2: Work around buggy Thumb-2 short branch relocations in gas
  ARM: 6747/1: P2V: Thumb2 support
  ARM: 6798/1: aout-core: zero thread debug registers in a.out core dump
  ARM: 6796/1: Footbridge: Fix I/O mappings for NOMMU mode
  ARM: 6784/1: errata: no automatic Store Buffer drain on Cortex-A9
  ARM: 6772/1: errata: possible fault MMU translations following an ASID switch
  ARM: 6776/1: mach-ux500: activate fix for errata 753970
  ARM: 6794/1: SPEAr: Append UL to device address macros.
  ARM: 6793/1: SPEAr: Remove unused *_SIZE macros from spear*.h files
  ARM: 6792/1: SPEAr: Replace SIZE macro's with SZ_4K macros
  ARM: 6791/1: SPEAr3xx: Declare device structures after shirq code
  ARM: 6790/1: SPEAr: Clock Framework: Rename usbd clock and align apb_clk entry
  ARM: 6789/1: SPEAr3xx: Rename sdio to sdhci
  ARM: 6788/1: SPEAr: Include mach/hardware.h instead of mach/spear.h
  ARM: 6787/1: SPEAr: Reorder #includes in .h & .c files.
  ARM: 6681/1: SPEAr: add debugfs support to clk API
  ARM: 6703/1: SPEAr: update clk API support
  ARM: 6679/1: SPEAr: make clk API functions more generic
  ARM: 6737/1: SPEAr: formalized timer support
  ...

Conflicts:
	arch/arm/mach-msm/board-msm7x27.c
	arch/arm/mach-msm/board-msm7x30.c
	arch/arm/mach-msm/board-qsd8x50.c
	arch/arm/mach-msm/board-sapphire.c
	arch/arm/mach-msm/include/mach/memory.h

1 files changed, 47 insertions, 28 deletions

diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index 84522c7..656222f 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -782,6 +782,10 @@ retry:
 	raw_spin_unlock_irq(&ctx->lock);
 }
 
+#define MAX_INTERRUPTS (~0ULL)
+
+static void perf_log_throttle(struct perf_event *event, int enable);
+
 static int
 event_sched_in(struct perf_event *event,
 		 struct perf_cpu_context *cpuctx,
@@ -794,6 +798,17 @@ event_sched_in(struct perf_event *event,
 
 	event->state = PERF_EVENT_STATE_ACTIVE;
 	event->oncpu = smp_processor_id();
+
+	/*
+	 * Unthrottle events, since we scheduled we might have missed several
+	 * ticks already, also for a heavily scheduling task there is little
+	 * guarantee it'll get a tick in a timely manner.
+	 */
+	if (unlikely(event->hw.interrupts == MAX_INTERRUPTS)) {
+		perf_log_throttle(event, 1);
+		event->hw.interrupts = 0;
+	}
+
 	/*
 	 * The new state must be visible before we turn it on in the hardware:
 	 */
@@ -1596,10 +1611,6 @@ void __perf_event_task_sched_in(struct task_struct *task)
 	}
 }
 
-#define MAX_INTERRUPTS (~0ULL)
-
-static void perf_log_throttle(struct perf_event *event, int enable);
-
 static u64 perf_calculate_period(struct perf_event *event, u64 nsec, u64 count)
 {
 	u64 frequency = event->attr.sample_freq;
@@ -1901,11 +1912,12 @@ static void __perf_event_read(void *info)
 		return;
 
 	raw_spin_lock(&ctx->lock);
-	update_context_time(ctx);
+	if (ctx->is_active)
+		update_context_time(ctx);
 	update_event_times(event);
+	if (event->state == PERF_EVENT_STATE_ACTIVE)
+		event->pmu->read(event);
 	raw_spin_unlock(&ctx->lock);
-
-	event->pmu->read(event);
 }
 
 static inline u64 perf_event_count(struct perf_event *event)
@@ -1999,8 +2011,7 @@ static int alloc_callchain_buffers(void)
 	 * accessed from NMI. Use a temporary manual per cpu allocation
 	 * until that gets sorted out.
 	 */
-	size = sizeof(*entries) + sizeof(struct perf_callchain_entry *) *
-		num_possible_cpus();
+	size = offsetof(struct callchain_cpus_entries, cpu_entries[nr_cpu_ids]);
 
 	entries = kzalloc(size, GFP_KERNEL);
 	if (!entries)
@@ -2201,13 +2212,6 @@ find_lively_task_by_vpid(pid_t vpid)
 	if (!task)
 		return ERR_PTR(-ESRCH);
 
-	/*
-	 * Can't attach events to a dying task.
-	 */
-	err = -ESRCH;
-	if (task->flags & PF_EXITING)
-		goto errout;
-
 	/* Reuse ptrace permission checks for now. */
 	err = -EACCES;
 	if (!ptrace_may_access(task, PTRACE_MODE_READ))
@@ -2268,14 +2272,27 @@ retry:
 
 		get_ctx(ctx);
 
-		if (cmpxchg(&task->perf_event_ctxp[ctxn], NULL, ctx)) {
-			/*
-			 * We raced with some other task; use
-			 * the context they set.
-			 */
+		err = 0;
+		mutex_lock(&task->perf_event_mutex);
+		/*
+		 * If it has already passed perf_event_exit_task().
+		 * we must see PF_EXITING, it takes this mutex too.
+		 */
+		if (task->flags & PF_EXITING)
+			err = -ESRCH;
+		else if (task->perf_event_ctxp[ctxn])
+			err = -EAGAIN;
+		else
+			rcu_assign_pointer(task->perf_event_ctxp[ctxn], ctx);
+		mutex_unlock(&task->perf_event_mutex);
+
+		if (unlikely(err)) {
 			put_task_struct(task);
 			kfree(ctx);
-			goto retry;
+
+			if (err == -EAGAIN)
+				goto retry;
+			goto errout;
 		}
 	}
 
@@ -5374,6 +5391,8 @@ free_dev:
 	goto out;
 }
 
+static struct lock_class_key cpuctx_mutex;
+
 int perf_pmu_register(struct pmu *pmu, char *name, int type)
 {
 	int cpu, ret;
@@ -5422,6 +5441,7 @@ skip_type:
 
 		cpuctx = per_cpu_ptr(pmu->pmu_cpu_context, cpu);
 		__perf_event_init_context(&cpuctx->ctx);
+		lockdep_set_class(&cpuctx->ctx.mutex, &cpuctx_mutex);
 		cpuctx->ctx.type = cpu_context;
 		cpuctx->ctx.pmu = pmu;
 		cpuctx->jiffies_interval = 1;
@@ -6127,7 +6147,7 @@ static void perf_event_exit_task_context(struct task_struct *child, int ctxn)
 	 * scheduled, so we are now safe from rescheduling changing
 	 * our context.
 	 */
-	child_ctx = child->perf_event_ctxp[ctxn];
+	child_ctx = rcu_dereference_raw(child->perf_event_ctxp[ctxn]);
 	task_ctx_sched_out(child_ctx, EVENT_ALL);
 
 	/*
@@ -6440,11 +6460,6 @@ int perf_event_init_context(struct task_struct *child, int ctxn)
 	unsigned long flags;
 	int ret = 0;
 
-	child->perf_event_ctxp[ctxn] = NULL;
-
-	mutex_init(&child->perf_event_mutex);
-	INIT_LIST_HEAD(&child->perf_event_list);
-
 	if (likely(!parent->perf_event_ctxp[ctxn]))
 		return 0;
 
@@ -6533,6 +6548,10 @@ int perf_event_init_task(struct task_struct *child)
 {
 	int ctxn, ret;
 
+	memset(child->perf_event_ctxp, 0, sizeof(child->perf_event_ctxp));
+	mutex_init(&child->perf_event_mutex);
+	INIT_LIST_HEAD(&child->perf_event_list);
+
 	for_each_task_context_nr(ctxn) {
 		ret = perf_event_init_context(child, ctxn);
 		if (ret)