Merge branch 'for-4.13/block' of git://git.kernel.dk/linux-block

Pull core block/IO updates from Jens Axboe:
 "This is the main pull request for the block layer for 4.13. Not a huge
  round in terms of features, but there's a lot of churn related to some
  core cleanups.

  Note this depends on the UUID tree pull request, that Christoph
  already sent out.

  This pull request contains:

   - A series from Christoph, unifying the error/stats codes in the
     block layer. We now use blk_status_t everywhere, instead of using
     different schemes for different places.

   - Also from Christoph, some cleanups around request allocation and IO
     scheduler interactions in blk-mq.

   - And yet another series from Christoph, cleaning up how we handle
     and do bounce buffering in the block layer.

   - A blk-mq debugfs series from Bart, further improving on the support
     we have for exporting internal information to aid debugging IO
     hangs or stalls.

   - Also from Bart, a series that cleans up the request initialization
     differences across types of devices.

   - A series from Goldwyn Rodrigues, allowing the block layer to return
     failure if we will block and the user asked for non-blocking.

   - Patch from Hannes for supporting setting loop devices block size to
     that of the underlying device.

   - Two series of patches from Javier, fixing various issues with
     lightnvm, particular around pblk.

   - A series from me, adding support for write hints. This comes with
     NVMe support as well, so applications can help guide data placement
     on flash to improve performance, latencies, and write
     amplification.

   - A series from Ming, improving and hardening blk-mq support for
     stopping/starting and quiescing hardware queues.

   - Two pull requests for NVMe updates. Nothing major on the feature
     side, but lots of cleanups and bug fixes. From the usual crew.

   - A series from Neil Brown, greatly improving the bio rescue set
     support. Most notably, this kills the bio rescue work queues, if we
     don't really need them.

   - Lots of other little bug fixes that are all over the place"

* 'for-4.13/block' of git://git.kernel.dk/linux-block: (217 commits)
  lightnvm: pblk: set line bitmap check under debug
  lightnvm: pblk: verify that cache read is still valid
  lightnvm: pblk: add initialization check
  lightnvm: pblk: remove target using async. I/Os
  lightnvm: pblk: use vmalloc for GC data buffer
  lightnvm: pblk: use right metadata buffer for recovery
  lightnvm: pblk: schedule if data is not ready
  lightnvm: pblk: remove unused return variable
  lightnvm: pblk: fix double-free on pblk init
  lightnvm: pblk: fix bad le64 assignations
  nvme: Makefile: remove dead build rule
  blk-mq: map all HWQ also in hyperthreaded system
  nvmet-rdma: register ib_client to not deadlock in device removal
  nvme_fc: fix error recovery on link down.
  nvmet_fc: fix crashes on bad opcodes
  nvme_fc: Fix crash when nvme controller connection fails.
  nvme_fc: replace ioabort msleep loop with completion
  nvme_fc: fix double calls to nvme_cleanup_cmd()
  nvme-fabrics: verify that a controller returns the correct NQN
  nvme: simplify nvme_dev_attrs_are_visible
  ...

1 files changed, 61 insertions, 13 deletions

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 3e68cabb8457..65adbddb3163 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -20,6 +20,7 @@
 #include <linux/rwsem.h>
 #include <linux/capability.h>
 #include <linux/semaphore.h>
+#include <linux/fcntl.h>
 #include <linux/fiemap.h>
 #include <linux/rculist_bl.h>
 #include <linux/atomic.h>
@@ -143,6 +144,9 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
 /* File was opened by fanotify and shouldn't generate fanotify events */
 #define FMODE_NONOTIFY		((__force fmode_t)0x4000000)
 
+/* File is capable of returning -EAGAIN if AIO will block */
+#define FMODE_AIO_NOWAIT	((__force fmode_t)0x8000000)
+
 /*
  * Flag for rw_copy_check_uvector and compat_rw_copy_check_uvector
  * that indicates that they should check the contents of the iovec are
@@ -262,6 +266,18 @@ struct page;
 struct address_space;
 struct writeback_control;
 
+/*
+ * Write life time hint values.
+ */
+enum rw_hint {
+	WRITE_LIFE_NOT_SET	= 0,
+	WRITE_LIFE_NONE		= RWH_WRITE_LIFE_NONE,
+	WRITE_LIFE_SHORT	= RWH_WRITE_LIFE_SHORT,
+	WRITE_LIFE_MEDIUM	= RWH_WRITE_LIFE_MEDIUM,
+	WRITE_LIFE_LONG		= RWH_WRITE_LIFE_LONG,
+	WRITE_LIFE_EXTREME	= RWH_WRITE_LIFE_EXTREME,
+};
+
 #define IOCB_EVENTFD		(1 << 0)
 #define IOCB_APPEND		(1 << 1)
 #define IOCB_DIRECT		(1 << 2)
@@ -269,6 +285,7 @@ struct writeback_control;
 #define IOCB_DSYNC		(1 << 4)
 #define IOCB_SYNC		(1 << 5)
 #define IOCB_WRITE		(1 << 6)
+#define IOCB_NOWAIT		(1 << 7)
 
 struct kiocb {
 	struct file		*ki_filp;
@@ -276,6 +293,7 @@ struct kiocb {
 	void (*ki_complete)(struct kiocb *iocb, long ret, long ret2);
 	void			*private;
 	int			ki_flags;
+	enum rw_hint		ki_hint;
 };
 
 static inline bool is_sync_kiocb(struct kiocb *kiocb)
@@ -283,16 +301,6 @@ static inline bool is_sync_kiocb(struct kiocb *kiocb)
 	return kiocb->ki_complete == NULL;
 }
 
-static inline int iocb_flags(struct file *file);
-
-static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp)
-{
-	*kiocb = (struct kiocb) {
-		.ki_filp = filp,
-		.ki_flags = iocb_flags(filp),
-	};
-}
-
 /*
  * "descriptor" for what we're up to with a read.
  * This allows us to use the same read code yet
@@ -593,6 +601,7 @@ struct inode {
 	spinlock_t		i_lock;	/* i_blocks, i_bytes, maybe i_size */
 	unsigned short          i_bytes;
 	unsigned int		i_blkbits;
+	enum rw_hint		i_write_hint;
 	blkcnt_t		i_blocks;
 
 #ifdef __NEED_I_SIZE_ORDERED
@@ -847,6 +856,7 @@ struct file {
 	 * Must not be taken from IRQ context.
 	 */
 	spinlock_t		f_lock;
+	enum rw_hint		f_write_hint;
 	atomic_long_t		f_count;
 	unsigned int 		f_flags;
 	fmode_t			f_mode;
@@ -1022,8 +1032,6 @@ struct file_lock_context {
 #define OFFT_OFFSET_MAX	INT_LIMIT(off_t)
 #endif
 
-#include <linux/fcntl.h>
-
 extern void send_sigio(struct fown_struct *fown, int fd, int band);
 
 /*
@@ -1874,6 +1882,25 @@ static inline bool HAS_UNMAPPED_ID(struct inode *inode)
 	return !uid_valid(inode->i_uid) || !gid_valid(inode->i_gid);
 }
 
+static inline enum rw_hint file_write_hint(struct file *file)
+{
+	if (file->f_write_hint != WRITE_LIFE_NOT_SET)
+		return file->f_write_hint;
+
+	return file_inode(file)->i_write_hint;
+}
+
+static inline int iocb_flags(struct file *file);
+
+static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp)
+{
+	*kiocb = (struct kiocb) {
+		.ki_filp = filp,
+		.ki_flags = iocb_flags(filp),
+		.ki_hint = file_write_hint(filp),
+	};
+}
+
 /*
  * Inode state bits.  Protected by inode->i_lock
  *
@@ -2518,6 +2545,8 @@ extern int filemap_fdatawait(struct address_space *);
 extern void filemap_fdatawait_keep_errors(struct address_space *);
 extern int filemap_fdatawait_range(struct address_space *, loff_t lstart,
 				   loff_t lend);
+extern bool filemap_range_has_page(struct address_space *, loff_t lstart,
+				  loff_t lend);
 extern int filemap_write_and_wait(struct address_space *mapping);
 extern int filemap_write_and_wait_range(struct address_space *mapping,
 				        loff_t lstart, loff_t lend);
@@ -2844,7 +2873,7 @@ enum {
 	DIO_SKIP_DIO_COUNT = 0x08,
 };
 
-void dio_end_io(struct bio *bio, int error);
+void dio_end_io(struct bio *bio);
 
 ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode,
 			     struct block_device *bdev, struct iov_iter *iter,
@@ -3057,6 +3086,25 @@ static inline int iocb_flags(struct file *file)
 	return res;
 }
 
+static inline int kiocb_set_rw_flags(struct kiocb *ki, int flags)
+{
+	if (unlikely(flags & ~RWF_SUPPORTED))
+		return -EOPNOTSUPP;
+
+	if (flags & RWF_NOWAIT) {
+		if (!(ki->ki_filp->f_mode & FMODE_AIO_NOWAIT))
+			return -EOPNOTSUPP;
+		ki->ki_flags |= IOCB_NOWAIT;
+	}
+	if (flags & RWF_HIPRI)
+		ki->ki_flags |= IOCB_HIPRI;
+	if (flags & RWF_DSYNC)
+		ki->ki_flags |= IOCB_DSYNC;
+	if (flags & RWF_SYNC)
+		ki->ki_flags |= (IOCB_DSYNC | IOCB_SYNC);
+	return 0;
+}
+
 static inline ino_t parent_ino(struct dentry *dentry)
 {
 	ino_t res;