1 files changed, 42 insertions, 24 deletions

diff --git a/kernel/perf_counter.c b/kernel/perf_counter.c
index d7cbc579fc80..237fd07a369f 100644
--- a/kernel/perf_counter.c
+++ b/kernel/perf_counter.c
@@ -469,7 +469,8 @@ static void update_counter_times(struct perf_counter *counter)
 	struct perf_counter_context *ctx = counter->ctx;
 	u64 run_end;
 
-	if (counter->state < PERF_COUNTER_STATE_INACTIVE)
+	if (counter->state < PERF_COUNTER_STATE_INACTIVE ||
+	    counter->group_leader->state < PERF_COUNTER_STATE_INACTIVE)
 		return;
 
 	counter->total_time_enabled = ctx->time - counter->tstamp_enabled;
@@ -518,7 +519,7 @@ static void __perf_counter_disable(void *info)
 	 */
 	if (counter->state >= PERF_COUNTER_STATE_INACTIVE) {
 		update_context_time(ctx);
-		update_counter_times(counter);
+		update_group_times(counter);
 		if (counter == counter->group_leader)
 			group_sched_out(counter, cpuctx, ctx);
 		else
@@ -573,7 +574,7 @@ static void perf_counter_disable(struct perf_counter *counter)
 	 * in, so we can change the state safely.
 	 */
 	if (counter->state == PERF_COUNTER_STATE_INACTIVE) {
-		update_counter_times(counter);
+		update_group_times(counter);
 		counter->state = PERF_COUNTER_STATE_OFF;
 	}
 
@@ -851,6 +852,27 @@ retry:
 }
 
 /*
+ * Put a counter into inactive state and update time fields.
+ * Enabling the leader of a group effectively enables all
+ * the group members that aren't explicitly disabled, so we
+ * have to update their ->tstamp_enabled also.
+ * Note: this works for group members as well as group leaders
+ * since the non-leader members' sibling_lists will be empty.
+ */
+static void __perf_counter_mark_enabled(struct perf_counter *counter,
+					struct perf_counter_context *ctx)
+{
+	struct perf_counter *sub;
+
+	counter->state = PERF_COUNTER_STATE_INACTIVE;
+	counter->tstamp_enabled = ctx->time - counter->total_time_enabled;
+	list_for_each_entry(sub, &counter->sibling_list, list_entry)
+		if (sub->state >= PERF_COUNTER_STATE_INACTIVE)
+			sub->tstamp_enabled =
+				ctx->time - sub->total_time_enabled;
+}
+
+/*
  * Cross CPU call to enable a performance counter
  */
 static void __perf_counter_enable(void *info)
@@ -877,8 +899,7 @@ static void __perf_counter_enable(void *info)
 
 	if (counter->state >= PERF_COUNTER_STATE_INACTIVE)
 		goto unlock;
-	counter->state = PERF_COUNTER_STATE_INACTIVE;
-	counter->tstamp_enabled = ctx->time - counter->total_time_enabled;
+	__perf_counter_mark_enabled(counter, ctx);
 
 	/*
 	 * If the counter is in a group and isn't the group leader,
@@ -971,11 +992,9 @@ static void perf_counter_enable(struct perf_counter *counter)
 	 * Since we have the lock this context can't be scheduled
 	 * in, so we can change the state safely.
 	 */
-	if (counter->state == PERF_COUNTER_STATE_OFF) {
-		counter->state = PERF_COUNTER_STATE_INACTIVE;
-		counter->tstamp_enabled =
-			ctx->time - counter->total_time_enabled;
-	}
+	if (counter->state == PERF_COUNTER_STATE_OFF)
+		__perf_counter_mark_enabled(counter, ctx);
+
  out:
 	spin_unlock_irq(&ctx->lock);
 }
@@ -1344,7 +1363,7 @@ static void perf_ctx_adjust_freq(struct perf_counter_context *ctx)
 	u64 interrupts, freq;
 
 	spin_lock(&ctx->lock);
-	list_for_each_entry(counter, &ctx->counter_list, list_entry) {
+	list_for_each_entry_rcu(counter, &ctx->counter_list, event_entry) {
 		if (counter->state != PERF_COUNTER_STATE_ACTIVE)
 			continue;
 
@@ -1479,9 +1498,7 @@ static void perf_counter_enable_on_exec(struct task_struct *task)
 		counter->attr.enable_on_exec = 0;
 		if (counter->state >= PERF_COUNTER_STATE_INACTIVE)
 			continue;
-		counter->state = PERF_COUNTER_STATE_INACTIVE;
-		counter->tstamp_enabled =
-			ctx->time - counter->total_time_enabled;
+		__perf_counter_mark_enabled(counter, ctx);
 		enabled = 1;
 	}
 
@@ -4126,8 +4143,8 @@ done:
 static int perf_copy_attr(struct perf_counter_attr __user *uattr,
 			  struct perf_counter_attr *attr)
 {
-	int ret;
 	u32 size;
+	int ret;
 
 	if (!access_ok(VERIFY_WRITE, uattr, PERF_ATTR_SIZE_VER0))
 		return -EFAULT;
@@ -4152,25 +4169,26 @@ static int perf_copy_attr(struct perf_counter_attr __user *uattr,
 
 	/*
 	 * If we're handed a bigger struct than we know of,
-	 * ensure all the unknown bits are 0.
+	 * ensure all the unknown bits are 0 - i.e. new
+	 * user-space does not rely on any kernel feature
+	 * extensions we dont know about yet.
 	 */
 	if (size > sizeof(*attr)) {
-		unsigned long val;
-		unsigned long __user *addr;
-		unsigned long __user *end;
+		unsigned char __user *addr;
+		unsigned char __user *end;
+		unsigned char val;
 
-		addr = PTR_ALIGN((void __user *)uattr + sizeof(*attr),
-				sizeof(unsigned long));
-		end  = PTR_ALIGN((void __user *)uattr + size,
-				sizeof(unsigned long));
+		addr = (void __user *)uattr + sizeof(*attr);
+		end  = (void __user *)uattr + size;
 
-		for (; addr < end; addr += sizeof(unsigned long)) {
+		for (; addr < end; addr++) {
 			ret = get_user(val, addr);
 			if (ret)
 				return ret;
 			if (val)
 				goto err_size;
 		}
+		size = sizeof(*attr);
 	}
 
 	ret = copy_from_user(attr, uattr, size);