1 files changed, 50 insertions, 72 deletions

diff --git a/drivers/oprofile/cpu_buffer.c b/drivers/oprofile/cpu_buffer.c
index 166b67ea622..8aa73fac6ad 100644
--- a/drivers/oprofile/cpu_buffer.c
+++ b/drivers/oprofile/cpu_buffer.c
@@ -30,23 +30,7 @@
 
 #define OP_BUFFER_FLAGS	0
 
-/*
- * Read and write access is using spin locking. Thus, writing to the
- * buffer by NMI handler (x86) could occur also during critical
- * sections when reading the buffer. To avoid this, there are 2
- * buffers for independent read and write access. Read access is in
- * process context only, write access only in the NMI handler. If the
- * read buffer runs empty, both buffers are swapped atomically. There
- * is potentially a small window during swapping where the buffers are
- * disabled and samples could be lost.
- *
- * Using 2 buffers is a little bit overhead, but the solution is clear
- * and does not require changes in the ring buffer implementation. It
- * can be changed to a single buffer solution when the ring buffer
- * access is implemented as non-locking atomic code.
- */
-static struct ring_buffer *op_ring_buffer_read;
-static struct ring_buffer *op_ring_buffer_write;
+static struct ring_buffer *op_ring_buffer;
 DEFINE_PER_CPU(struct oprofile_cpu_buffer, op_cpu_buffer);
 
 static void wq_sync_buffer(struct work_struct *work);
@@ -68,12 +52,9 @@ void oprofile_cpu_buffer_inc_smpl_lost(void)
 
 void free_cpu_buffers(void)
 {
-	if (op_ring_buffer_read)
-		ring_buffer_free(op_ring_buffer_read);
-	op_ring_buffer_read = NULL;
-	if (op_ring_buffer_write)
-		ring_buffer_free(op_ring_buffer_write);
-	op_ring_buffer_write = NULL;
+	if (op_ring_buffer)
+		ring_buffer_free(op_ring_buffer);
+	op_ring_buffer = NULL;
 }
 
 #define RB_EVENT_HDR_SIZE 4
@@ -86,11 +67,8 @@ int alloc_cpu_buffers(void)
 	unsigned long byte_size = buffer_size * (sizeof(struct op_sample) +
 						 RB_EVENT_HDR_SIZE);
 
-	op_ring_buffer_read = ring_buffer_alloc(byte_size, OP_BUFFER_FLAGS);
-	if (!op_ring_buffer_read)
-		goto fail;
-	op_ring_buffer_write = ring_buffer_alloc(byte_size, OP_BUFFER_FLAGS);
-	if (!op_ring_buffer_write)
+	op_ring_buffer = ring_buffer_alloc(byte_size, OP_BUFFER_FLAGS);
+	if (!op_ring_buffer)
 		goto fail;
 
 	for_each_possible_cpu(i) {
@@ -133,17 +111,19 @@ void start_cpu_work(void)
 
 void end_cpu_work(void)
 {
-	int i;
-
 	work_enabled = 0;
+}
+
+void flush_cpu_work(void)
+{
+	int i;
 
 	for_each_online_cpu(i) {
 		struct oprofile_cpu_buffer *b = &per_cpu(op_cpu_buffer, i);
 
-		cancel_delayed_work(&b->work);
+		/* these works are per-cpu, no need for flush_sync */
+		flush_delayed_work(&b->work);
 	}
-
-	flush_scheduled_work();
 }
 
 /*
@@ -162,16 +142,11 @@ struct op_sample
 *op_cpu_buffer_write_reserve(struct op_entry *entry, unsigned long size)
 {
 	entry->event = ring_buffer_lock_reserve
-		(op_ring_buffer_write, sizeof(struct op_sample) +
+		(op_ring_buffer, sizeof(struct op_sample) +
 		 size * sizeof(entry->sample->data[0]));
-	if (entry->event)
-		entry->sample = ring_buffer_event_data(entry->event);
-	else
-		entry->sample = NULL;
-
-	if (!entry->sample)
+	if (!entry->event)
 		return NULL;
-
+	entry->sample = ring_buffer_event_data(entry->event);
 	entry->size = size;
 	entry->data = entry->sample->data;
 
@@ -180,25 +155,16 @@ struct op_sample
 
 int op_cpu_buffer_write_commit(struct op_entry *entry)
 {
-	return ring_buffer_unlock_commit(op_ring_buffer_write, entry->event);
+	return ring_buffer_unlock_commit(op_ring_buffer, entry->event);
 }
 
 struct op_sample *op_cpu_buffer_read_entry(struct op_entry *entry, int cpu)
 {
 	struct ring_buffer_event *e;
-	e = ring_buffer_consume(op_ring_buffer_read, cpu, NULL);
-	if (e)
-		goto event;
-	if (ring_buffer_swap_cpu(op_ring_buffer_read,
-				 op_ring_buffer_write,
-				 cpu))
+	e = ring_buffer_consume(op_ring_buffer, cpu, NULL, NULL);
+	if (!e)
 		return NULL;
-	e = ring_buffer_consume(op_ring_buffer_read, cpu, NULL);
-	if (e)
-		goto event;
-	return NULL;
 
-event:
 	entry->event = e;
 	entry->sample = ring_buffer_event_data(e);
 	entry->size = (ring_buffer_event_length(e) - sizeof(struct op_sample))
@@ -209,8 +175,7 @@ event:
 
 unsigned long op_cpu_buffer_entries(int cpu)
 {
-	return ring_buffer_entries_cpu(op_ring_buffer_read, cpu)
-		+ ring_buffer_entries_cpu(op_ring_buffer_write, cpu);
+	return ring_buffer_entries_cpu(op_ring_buffer, cpu);
 }
 
 static int
@@ -293,8 +258,10 @@ op_add_sample(struct oprofile_cpu_buffer *cpu_buf,
  */
 static int
 log_sample(struct oprofile_cpu_buffer *cpu_buf, unsigned long pc,
-	   unsigned long backtrace, int is_kernel, unsigned long event)
+	   unsigned long backtrace, int is_kernel, unsigned long event,
+	   struct task_struct *task)
 {
+	struct task_struct *tsk = task ? task : current;
 	cpu_buf->sample_received++;
 
 	if (pc == ESCAPE_CODE) {
@@ -302,7 +269,7 @@ log_sample(struct oprofile_cpu_buffer *cpu_buf, unsigned long pc,
 		return 0;
 	}
 
-	if (op_add_code(cpu_buf, backtrace, is_kernel, current))
+	if (op_add_code(cpu_buf, backtrace, is_kernel, tsk))
 		goto fail;
 
 	if (op_add_sample(cpu_buf, pc, event))
@@ -327,7 +294,8 @@ static inline void oprofile_end_trace(struct oprofile_cpu_buffer *cpu_buf)
 
 static inline void
 __oprofile_add_ext_sample(unsigned long pc, struct pt_regs * const regs,
-			  unsigned long event, int is_kernel)
+			  unsigned long event, int is_kernel,
+			  struct task_struct *task)
 {
 	struct oprofile_cpu_buffer *cpu_buf = &__get_cpu_var(op_cpu_buffer);
 	unsigned long backtrace = oprofile_backtrace_depth;
@@ -336,7 +304,7 @@ __oprofile_add_ext_sample(unsigned long pc, struct pt_regs * const regs,
 	 * if log_sample() fail we can't backtrace since we lost the
 	 * source of this event
 	 */
-	if (!log_sample(cpu_buf, pc, backtrace, is_kernel, event))
+	if (!log_sample(cpu_buf, pc, backtrace, is_kernel, event, task))
 		/* failed */
 		return;
 
@@ -348,18 +316,33 @@ __oprofile_add_ext_sample(unsigned long pc, struct pt_regs * const regs,
 	oprofile_end_trace(cpu_buf);
 }
 
+void oprofile_add_ext_hw_sample(unsigned long pc, struct pt_regs * const regs,
+				unsigned long event, int is_kernel,
+				struct task_struct *task)
+{
+	__oprofile_add_ext_sample(pc, regs, event, is_kernel, task);
+}
+
 void oprofile_add_ext_sample(unsigned long pc, struct pt_regs * const regs,
 			     unsigned long event, int is_kernel)
 {
-	__oprofile_add_ext_sample(pc, regs, event, is_kernel);
+	__oprofile_add_ext_sample(pc, regs, event, is_kernel, NULL);
 }
 
 void oprofile_add_sample(struct pt_regs * const regs, unsigned long event)
 {
-	int is_kernel = !user_mode(regs);
-	unsigned long pc = profile_pc(regs);
+	int is_kernel;
+	unsigned long pc;
+
+	if (likely(regs)) {
+		is_kernel = !user_mode(regs);
+		pc = profile_pc(regs);
+	} else {
+		is_kernel = 0;    /* This value will not be used */
+		pc = ESCAPE_CODE; /* as this causes an early return. */
+	}
 
-	__oprofile_add_ext_sample(pc, regs, event, is_kernel);
+	__oprofile_add_ext_sample(pc, regs, event, is_kernel, NULL);
 }
 
 /*
@@ -430,7 +413,7 @@ int oprofile_write_commit(struct op_entry *entry)
 void oprofile_add_pc(unsigned long pc, int is_kernel, unsigned long event)
 {
 	struct oprofile_cpu_buffer *cpu_buf = &__get_cpu_var(op_cpu_buffer);
-	log_sample(cpu_buf, pc, 0, is_kernel, event);
+	log_sample(cpu_buf, pc, 0, is_kernel, event, NULL);
 }
 
 void oprofile_add_trace(unsigned long pc)
@@ -468,14 +451,9 @@ static void wq_sync_buffer(struct work_struct *work)
 {
 	struct oprofile_cpu_buffer *b =
 		container_of(work, struct oprofile_cpu_buffer, work.work);
-	if (b->cpu != smp_processor_id()) {
-		printk(KERN_DEBUG "WQ on CPU%d, prefer CPU%d\n",
-		       smp_processor_id(), b->cpu);
-
-		if (!cpu_online(b->cpu)) {
-			cancel_delayed_work(&b->work);
-			return;
-		}
+	if (b->cpu != smp_processor_id() && !cpu_online(b->cpu)) {
+		cancel_delayed_work(&b->work);
+		return;
 	}
 	sync_buffer(b->cpu);