Merge tag 'v3.7-rc1' into staging/for_v3.8

Linux 3.7-rc1

* tag 'v3.7-rc1': (9579 commits)
  Linux 3.7-rc1
  x86, boot: Explicitly include autoconf.h for hostprogs
  perf: Fix UAPI fallout
  ARM: config: make sure that platforms are ordered by option string
  ARM: config: sort select statements alphanumerically
  UAPI: (Scripted) Disintegrate include/linux/byteorder
  UAPI: (Scripted) Disintegrate include/linux
  UAPI: Unexport linux/blk_types.h
  UAPI: Unexport part of linux/ppp-comp.h
  perf: Handle new rbtree implementation
  procfs: don't need a PATH_MAX allocation to hold a string representation of an int
  vfs: embed struct filename inside of names_cache allocation if possible
  audit: make audit_inode take struct filename
  vfs: make path_openat take a struct filename pointer
  vfs: turn do_path_lookup into wrapper around struct filename variant
  audit: allow audit code to satisfy getname requests from its names_list
  vfs: define struct filename and have getname() return it
  btrfs: Fix compilation with user namespace support enabled
  userns: Fix posix_acl_file_xattr_userns gid conversion
  userns: Properly print bluetooth socket uids
  ...

1 files changed, 61 insertions, 50 deletions

diff --git a/kernel/task_work.c b/kernel/task_work.c
index d320d44903b..65bd3c92d6f 100644
--- a/kernel/task_work.c
+++ b/kernel/task_work.c
@@ -2,26 +2,20 @@
 #include <linux/task_work.h>
 #include <linux/tracehook.h>
 
+static struct callback_head work_exited; /* all we need is ->next == NULL */
+
 int
-task_work_add(struct task_struct *task, struct callback_head *twork, bool notify)
+task_work_add(struct task_struct *task, struct callback_head *work, bool notify)
 {
-	struct callback_head *last, *first;
-	unsigned long flags;
+	struct callback_head *head;
 
-	/*
-	 * Not inserting the new work if the task has already passed
-	 * exit_task_work() is the responisbility of callers.
-	 */
-	raw_spin_lock_irqsave(&task->pi_lock, flags);
-	last = task->task_works;
-	first = last ? last->next : twork;
-	twork->next = first;
-	if (last)
-		last->next = twork;
-	task->task_works = twork;
-	raw_spin_unlock_irqrestore(&task->pi_lock, flags);
+	do {
+		head = ACCESS_ONCE(task->task_works);
+		if (unlikely(head == &work_exited))
+			return -ESRCH;
+		work->next = head;
+	} while (cmpxchg(&task->task_works, head, work) != head);
 
-	/* test_and_set_bit() implies mb(), see tracehook_notify_resume(). */
 	if (notify)
 		set_notify_resume(task);
 	return 0;
@@ -30,52 +24,69 @@ task_work_add(struct task_struct *task, struct callback_head *twork, bool notify
 struct callback_head *
 task_work_cancel(struct task_struct *task, task_work_func_t func)
 {
+	struct callback_head **pprev = &task->task_works;
+	struct callback_head *work = NULL;
 	unsigned long flags;
-	struct callback_head *last, *res = NULL;
-
+	/*
+	 * If cmpxchg() fails we continue without updating pprev.
+	 * Either we raced with task_work_add() which added the
+	 * new entry before this work, we will find it again. Or
+	 * we raced with task_work_run(), *pprev == NULL/exited.
+	 */
 	raw_spin_lock_irqsave(&task->pi_lock, flags);
-	last = task->task_works;
-	if (last) {
-		struct callback_head *q = last, *p = q->next;
-		while (1) {
-			if (p->func == func) {
-				q->next = p->next;
-				if (p == last)
-					task->task_works = q == p ? NULL : q;
-				res = p;
-				break;
-			}
-			if (p == last)
-				break;
-			q = p;
-			p = q->next;
-		}
+	while ((work = ACCESS_ONCE(*pprev))) {
+		read_barrier_depends();
+		if (work->func != func)
+			pprev = &work->next;
+		else if (cmpxchg(pprev, work, work->next) == work)
+			break;
 	}
 	raw_spin_unlock_irqrestore(&task->pi_lock, flags);
-	return res;
+
+	return work;
 }
 
 void task_work_run(void)
 {
 	struct task_struct *task = current;
-	struct callback_head *p, *q;
+	struct callback_head *work, *head, *next;
+
+	for (;;) {
+		/*
+		 * work->func() can do task_work_add(), do not set
+		 * work_exited unless the list is empty.
+		 */
+		do {
+			work = ACCESS_ONCE(task->task_works);
+			head = !work && (task->flags & PF_EXITING) ?
+				&work_exited : NULL;
+		} while (cmpxchg(&task->task_works, work, head) != work);
 
-	while (1) {
-		raw_spin_lock_irq(&task->pi_lock);
-		p = task->task_works;
-		task->task_works = NULL;
-		raw_spin_unlock_irq(&task->pi_lock);
+		if (!work)
+			break;
+		/*
+		 * Synchronize with task_work_cancel(). It can't remove
+		 * the first entry == work, cmpxchg(task_works) should
+		 * fail, but it can play with *work and other entries.
+		 */
+		raw_spin_unlock_wait(&task->pi_lock);
+		smp_mb();
 
-		if (unlikely(!p))
-			return;
+		/* Reverse the list to run the works in fifo order */
+		head = NULL;
+		do {
+			next = work->next;
+			work->next = head;
+			head = work;
+			work = next;
+		} while (work);
 
-		q = p->next; /* head */
-		p->next = NULL; /* cut it */
-		while (q) {
-			p = q->next;
-			q->func(q);
-			q = p;
+		work = head;
+		do {
+			next = work->next;
+			work->func(work);
+			work = next;
 			cond_resched();
-		}
+		} while (work);
 	}
 }