Merge git://git.kvack.org/~bcrl/aio-next

Pull aio changes from Ben LaHaise:
 "First off, sorry for this pull request being late in the merge window.
  Al had raised a couple of concerns about 2 items in the series below.
  I addressed the first issue (the race introduced by Gu's use of
  mm_populate()), but he has not provided any further details on how he
  wants to rework the anon_inode.c changes (which were sent out months
  ago but have yet to be commented on).

  The bulk of the changes have been sitting in the -next tree for a few
  months, with all the issues raised being addressed"

* git://git.kvack.org/~bcrl/aio-next: (22 commits)
  aio: rcu_read_lock protection for new rcu_dereference calls
  aio: fix race in ring buffer page lookup introduced by page migration support
  aio: fix rcu sparse warnings introduced by ioctx table lookup patch
  aio: remove unnecessary debugging from aio_free_ring()
  aio: table lookup: verify ctx pointer
  staging/lustre: kiocb->ki_left is removed
  aio: fix error handling and rcu usage in "convert the ioctx list to table lookup v3"
  aio: be defensive to ensure request batching is non-zero instead of BUG_ON()
  aio: convert the ioctx list to table lookup v3
  aio: double aio_max_nr in calculations
  aio: Kill ki_dtor
  aio: Kill ki_users
  aio: Kill unneeded kiocb members
  aio: Kill aio_rw_vect_retry()
  aio: Don't use ctx->tail unnecessarily
  aio: io_cancel() no longer returns the io_event
  aio: percpu ioctx refcount
  aio: percpu reqs_available
  aio: reqs_active -> reqs_available
  aio: fix build when migration is disabled
  ...

include/linux/aio.h

@@ -27,15 +27,13 @@ struct kiocb;
  */
 #define KIOCB_CANCELLED		((void *) (~0ULL))
 
-typedef int (kiocb_cancel_fn)(struct kiocb *, struct io_event *);
+typedef int (kiocb_cancel_fn)(struct kiocb *);
 
 struct kiocb {
-	atomic_t		ki_users;
-
 	struct file		*ki_filp;
 	struct kioctx		*ki_ctx;	/* NULL for sync ops */
 	kiocb_cancel_fn		*ki_cancel;
-	void			(*ki_dtor)(struct kiocb *);
+	void			*private;
 
 	union {
 		void __user		*user;
@@ -44,17 +42,7 @@ struct kiocb {
 
 	__u64			ki_user_data;	/* user's data for completion */
 	loff_t			ki_pos;
-
-	void			*private;
-	/* State that we remember to be able to restart/retry  */
-	unsigned short		ki_opcode;
-	size_t			ki_nbytes; 	/* copy of iocb->aio_nbytes */
-	char 			__user *ki_buf;	/* remaining iocb->aio_buf */
-	size_t			ki_left; 	/* remaining bytes */
-	struct iovec		ki_inline_vec;	/* inline vector */
- 	struct iovec		*ki_iovec;
- 	unsigned long		ki_nr_segs;
- 	unsigned long		ki_cur_seg;
+	size_t			ki_nbytes;	/* copy of iocb->aio_nbytes */
 
 	struct list_head	ki_list;	/* the aio core uses this
 						 * for cancellation */
@@ -74,7 +62,6 @@ static inline bool is_sync_kiocb(struct kiocb *kiocb)
 static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp)
 {
 	*kiocb = (struct kiocb) {
-			.ki_users = ATOMIC_INIT(1),
 			.ki_ctx = NULL,
 			.ki_filp = filp,
 			.ki_obj.tsk = current,
@@ -84,7 +71,6 @@ static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp)
 /* prototypes */
 #ifdef CONFIG_AIO
 extern ssize_t wait_on_sync_kiocb(struct kiocb *iocb);
-extern void aio_put_req(struct kiocb *iocb);
 extern void aio_complete(struct kiocb *iocb, long res, long res2);
 struct mm_struct;
 extern void exit_aio(struct mm_struct *mm);
@@ -93,7 +79,6 @@ extern long do_io_submit(aio_context_t ctx_id, long nr,
 void kiocb_set_cancel_fn(struct kiocb *req, kiocb_cancel_fn *cancel);
 #else
 static inline ssize_t wait_on_sync_kiocb(struct kiocb *iocb) { return 0; }
-static inline void aio_put_req(struct kiocb *iocb) { }
 static inline void aio_complete(struct kiocb *iocb, long res, long res2) { }
 struct mm_struct;
 static inline void exit_aio(struct mm_struct *mm) { }

include/linux/anon_inodes.h

@@ -13,6 +13,9 @@ struct file_operations;
 struct file *anon_inode_getfile(const char *name,
 				const struct file_operations *fops,
 				void *priv, int flags);
+struct file *anon_inode_getfile_private(const char *name,
+				const struct file_operations *fops,
+				void *priv, int flags);
 int anon_inode_getfd(const char *name, const struct file_operations *fops,
 		     void *priv, int flags);
 

include/linux/migrate.h

@@ -53,6 +53,9 @@ extern int migrate_vmas(struct mm_struct *mm,
 extern void migrate_page_copy(struct page *newpage, struct page *page);
 extern int migrate_huge_page_move_mapping(struct address_space *mapping,
 				  struct page *newpage, struct page *page);
+extern int migrate_page_move_mapping(struct address_space *mapping,
+		struct page *newpage, struct page *page,
+		struct buffer_head *head, enum migrate_mode mode);
 #else
 
 static inline void putback_lru_pages(struct list_head *l) {}

include/linux/mm_types.h

@@ -322,6 +322,7 @@ struct mm_rss_stat {
 	atomic_long_t count[NR_MM_COUNTERS];
 };
 
+struct kioctx_table;
 struct mm_struct {
 	struct vm_area_struct * mmap;		/* list of VMAs */
 	struct rb_root mm_rb;
@@ -383,8 +384,8 @@ struct mm_struct {
 
 	struct core_state *core_state; /* coredumping support */
 #ifdef CONFIG_AIO
-	spinlock_t		ioctx_lock;
-	struct hlist_head	ioctx_list;
+	spinlock_t			ioctx_lock;
+	struct kioctx_table __rcu	*ioctx_table;
 #endif
 #ifdef CONFIG_MM_OWNER
 	/*