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

Pull block fixes from Jens Axboe:
 "A collection of fixes from the past few weeks that should go into 4.5.
  This contains:

   - Overflow fix for sysfs discard show function from Alan.

   - A stacking limit init fix for max_dev_sectors, so we don't end up
     artificially capping some use cases.  From Keith.

   - Have blk-mq proper end unstarted requests on a dying queue, instead
     of pushing that to the driver.  From Keith.

   - NVMe:
        - Update to Kconfig description for NVME_SCSI, since it was
          vague and having it on is important for some SUSE distros.
          From Christoph.
        - Set of fixes from Keith, around surprise removal. Also kills
          the no-merge flag, so it supports merging.

   - Set of fixes for lightnvm from Matias, Javier, and Wenwei.

   - Fix null_blk oops when asked for lightnvm, but not available.  From
     Matias.

   - Copy-to-user EINTR fix from Hannes, fixing a case where SG_IO fails
     if interrupted by a signal.

   - Two floppy fixes from Jiri, fixing signal handling and blocking
     open.

   - A use-after-free fix for O_DIRECT, from Mike Krinkin.

   - A block module ref count fix from Roman Pen.

   - An fs IO wait accounting fix for O_DSYNC from Stephane Gasparini.

   - Smaller reallo fix for xen-blkfront from Bob Liu.

   - Removal of an unused struct member in the deadline IO scheduler,
     from Tahsin.

   - Also from Tahsin, properly initialize inode struct members
     associated with cgroup writeback, if enabled.

   - From Tejun, ensure that we keep the superblock pinned during cgroup
     writeback"

* 'for-linus' of git://git.kernel.dk/linux-block: (25 commits)
  blk: fix overflow in queue_discard_max_hw_show
  writeback: initialize inode members that track writeback history
  writeback: keep superblock pinned during cgroup writeback association switches
  bio: return EINTR if copying to user space got interrupted
  NVMe: Rate limit nvme IO warnings
  NVMe: Poll device while still active during remove
  NVMe: Requeue requests on suspended queues
  NVMe: Allow request merges
  NVMe: Fix io incapable return values
  blk-mq: End unstarted requests on dying queue
  block: Initialize max_dev_sectors to 0
  null_blk: oops when initializing without lightnvm
  block: fix module reference leak on put_disk() call for cgroups throttle
  nvme: fix Kconfig description for BLK_DEV_NVME_SCSI
  kernel/fs: fix I/O wait not accounted for RW O_DSYNC
  floppy: refactor open() flags handling
  lightnvm: allow to force mm initialization
  lightnvm: check overflow and correct mlc pairs
  lightnvm: fix request intersection locking in rrpc
  lightnvm: warn if irqs are disabled in lock laddr
  ...

block/bio.c

@@ -874,7 +874,7 @@ int submit_bio_wait(int rw, struct bio *bio)
 	bio->bi_private = &ret;
 	bio->bi_end_io = submit_bio_wait_endio;
 	submit_bio(rw, bio);
-	wait_for_completion(&ret.event);
+	wait_for_completion_io(&ret.event);
 
 	return ret.error;
 }
@@ -1090,9 +1090,12 @@ int bio_uncopy_user(struct bio *bio)
 	if (!bio_flagged(bio, BIO_NULL_MAPPED)) {
 		/*
 		 * if we're in a workqueue, the request is orphaned, so
-		 * don't copy into a random user address space, just free.
+		 * don't copy into a random user address space, just free
+		 * and return -EINTR so user space doesn't expect any data.
 		 */
-		if (current->mm && bio_data_dir(bio) == READ)
+		if (!current->mm)
+			ret = -EINTR;
+		else if (bio_data_dir(bio) == READ)
 			ret = bio_copy_to_iter(bio, bmd->iter);
 		if (bmd->is_our_pages)
 			bio_free_pages(bio);

block/blk-cgroup.c

@@ -788,6 +788,7 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
 {
 	struct gendisk *disk;
 	struct blkcg_gq *blkg;
+	struct module *owner;
 	unsigned int major, minor;
 	int key_len, part, ret;
 	char *body;
@@ -804,7 +805,9 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
 	if (!disk)
 		return -ENODEV;
 	if (part) {
+		owner = disk->fops->owner;
 		put_disk(disk);
+		module_put(owner);
 		return -ENODEV;
 	}
 
@@ -820,7 +823,9 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
 		ret = PTR_ERR(blkg);
 		rcu_read_unlock();
 		spin_unlock_irq(disk->queue->queue_lock);
+		owner = disk->fops->owner;
 		put_disk(disk);
+		module_put(owner);
 		/*
 		 * If queue was bypassing, we should retry.  Do so after a
 		 * short msleep().  It isn't strictly necessary but queue
@@ -851,9 +856,13 @@ EXPORT_SYMBOL_GPL(blkg_conf_prep);
 void blkg_conf_finish(struct blkg_conf_ctx *ctx)
 	__releases(ctx->disk->queue->queue_lock) __releases(rcu)
 {
+	struct module *owner;
+
 	spin_unlock_irq(ctx->disk->queue->queue_lock);
 	rcu_read_unlock();
+	owner = ctx->disk->fops->owner;
 	put_disk(ctx->disk);
+	module_put(owner);
 }
 EXPORT_SYMBOL_GPL(blkg_conf_finish);
 

block/blk-mq.c

@@ -599,8 +599,10 @@ static void blk_mq_check_expired(struct blk_mq_hw_ctx *hctx,
 		 * If a request wasn't started before the queue was
 		 * marked dying, kill it here or it'll go unnoticed.
 		 */
-		if (unlikely(blk_queue_dying(rq->q)))
-			blk_mq_complete_request(rq, -EIO);
+		if (unlikely(blk_queue_dying(rq->q))) {
+			rq->errors = -EIO;
+			blk_mq_end_request(rq, rq->errors);
+		}
 		return;
 	}
 

block/blk-settings.c

@@ -91,8 +91,8 @@ void blk_set_default_limits(struct queue_limits *lim)
 	lim->seg_boundary_mask = BLK_SEG_BOUNDARY_MASK;
 	lim->virt_boundary_mask = 0;
 	lim->max_segment_size = BLK_MAX_SEGMENT_SIZE;
-	lim->max_sectors = lim->max_dev_sectors = lim->max_hw_sectors =
-		BLK_SAFE_MAX_SECTORS;
+	lim->max_sectors = lim->max_hw_sectors = BLK_SAFE_MAX_SECTORS;
+	lim->max_dev_sectors = 0;
 	lim->chunk_sectors = 0;
 	lim->max_write_same_sectors = 0;
 	lim->max_discard_sectors = 0;

block/blk-sysfs.c

@@ -147,10 +147,9 @@ static ssize_t queue_discard_granularity_show(struct request_queue *q, char *pag
 
 static ssize_t queue_discard_max_hw_show(struct request_queue *q, char *page)
 {
-	unsigned long long val;
 
-	val = q->limits.max_hw_discard_sectors << 9;
-	return sprintf(page, "%llu\n", val);
+	return sprintf(page, "%llu\n",
+		(unsigned long long)q->limits.max_hw_discard_sectors << 9);
 }
 
 static ssize_t queue_discard_max_show(struct request_queue *q, char *page)

block/deadline-iosched.c

@@ -39,7 +39,6 @@ struct deadline_data {
 	 */
 	struct request *next_rq[2];
 	unsigned int batching;		/* number of sequential requests made */
-	sector_t last_sector;		/* head position */
 	unsigned int starved;		/* times reads have starved writes */
 
 	/*
@@ -210,8 +209,6 @@ deadline_move_request(struct deadline_data *dd, struct request *rq)
 	dd->next_rq[WRITE] = NULL;
 	dd->next_rq[data_dir] = deadline_latter_request(rq);
 
-	dd->last_sector = rq_end_sector(rq);
-
 	/*
 	 * take it off the sort and fifo list, move
 	 * to dispatch queue

drivers/block/floppy.c

@@ -866,7 +866,7 @@ static void set_fdc(int drive)
 }
 
 /* locks the driver */
-static int lock_fdc(int drive, bool interruptible)
+static int lock_fdc(int drive)
 {
 	if (WARN(atomic_read(&usage_count) == 0,
 		 "Trying to lock fdc while usage count=0\n"))
@@ -2173,7 +2173,7 @@ static int do_format(int drive, struct format_descr *tmp_format_req)
 {
 	int ret;
 
-	if (lock_fdc(drive, true))
+	if (lock_fdc(drive))
 		return -EINTR;
 
 	set_floppy(drive);
@@ -2960,7 +2960,7 @@ static int user_reset_fdc(int drive, int arg, bool interruptible)
 {
 	int ret;
 
-	if (lock_fdc(drive, interruptible))
+	if (lock_fdc(drive))
 		return -EINTR;
 
 	if (arg == FD_RESET_ALWAYS)
@@ -3243,7 +3243,7 @@ static int set_geometry(unsigned int cmd, struct floppy_struct *g,
 		if (!capable(CAP_SYS_ADMIN))
 			return -EPERM;
 		mutex_lock(&open_lock);
-		if (lock_fdc(drive, true)) {
+		if (lock_fdc(drive)) {
 			mutex_unlock(&open_lock);
 			return -EINTR;
 		}
@@ -3263,7 +3263,7 @@ static int set_geometry(unsigned int cmd, struct floppy_struct *g,
 	} else {
 		int oldStretch;
 
-		if (lock_fdc(drive, true))
+		if (lock_fdc(drive))
 			return -EINTR;
 		if (cmd != FDDEFPRM) {
 			/* notice a disk change immediately, else
@@ -3349,7 +3349,7 @@ static int get_floppy_geometry(int drive, int type, struct floppy_struct **g)
 	if (type)
 		*g = &floppy_type[type];
 	else {
-		if (lock_fdc(drive, false))
+		if (lock_fdc(drive))
 			return -EINTR;
 		if (poll_drive(false, 0) == -EINTR)
 			return -EINTR;
@@ -3433,7 +3433,7 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, unsigned int
 		if (UDRS->fd_ref != 1)
 			/* somebody else has this drive open */
 			return -EBUSY;
-		if (lock_fdc(drive, true))
+		if (lock_fdc(drive))
 			return -EINTR;
 
 		/* do the actual eject. Fails on
@@ -3445,7 +3445,7 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, unsigned int
 		process_fd_request();
 		return ret;
 	case FDCLRPRM:
-		if (lock_fdc(drive, true))
+		if (lock_fdc(drive))
 			return -EINTR;
 		current_type[drive] = NULL;
 		floppy_sizes[drive] = MAX_DISK_SIZE << 1;
@@ -3467,7 +3467,7 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, unsigned int
 		UDP->flags &= ~FTD_MSG;
 		return 0;
 	case FDFMTBEG:
-		if (lock_fdc(drive, true))
+		if (lock_fdc(drive))
 			return -EINTR;
 		if (poll_drive(true, FD_RAW_NEED_DISK) == -EINTR)
 			return -EINTR;
@@ -3484,7 +3484,7 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, unsigned int
 		return do_format(drive, &inparam.f);
 	case FDFMTEND:
 	case FDFLUSH:
-		if (lock_fdc(drive, true))
+		if (lock_fdc(drive))
 			return -EINTR;
 		return invalidate_drive(bdev);
 	case FDSETEMSGTRESH:
@@ -3507,7 +3507,7 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, unsigned int
 		outparam = UDP;
 		break;
 	case FDPOLLDRVSTAT:
-		if (lock_fdc(drive, true))
+		if (lock_fdc(drive))
 			return -EINTR;
 		if (poll_drive(true, FD_RAW_NEED_DISK) == -EINTR)
 			return -EINTR;
@@ -3530,7 +3530,7 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, unsigned int
 	case FDRAWCMD:
 		if (type)
 			return -EINVAL;
-		if (lock_fdc(drive, true))
+		if (lock_fdc(drive))
 			return -EINTR;
 		set_floppy(drive);
 		i = raw_cmd_ioctl(cmd, (void __user *)param);
@@ -3539,7 +3539,7 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, unsigned int
 		process_fd_request();
 		return i;
 	case FDTWADDLE:
-		if (lock_fdc(drive, true))
+		if (lock_fdc(drive))
 			return -EINTR;
 		twaddle();
 		process_fd_request();
@@ -3663,6 +3663,11 @@ static int floppy_open(struct block_device *bdev, fmode_t mode)
 
 	opened_bdev[drive] = bdev;
 
+	if (!(mode & (FMODE_READ|FMODE_WRITE))) {
+		res = -EINVAL;
+		goto out;
+	}
+
 	res = -ENXIO;
 
 	if (!floppy_track_buffer) {
@@ -3706,21 +3711,20 @@ static int floppy_open(struct block_device *bdev, fmode_t mode)
 	if (UFDCS->rawcmd == 1)
 		UFDCS->rawcmd = 2;
 
-	if (!(mode & FMODE_NDELAY)) {
-		if (mode & (FMODE_READ|FMODE_WRITE)) {
-			UDRS->last_checked = 0;
-			clear_bit(FD_OPEN_SHOULD_FAIL_BIT, &UDRS->flags);
-			check_disk_change(bdev);
-			if (test_bit(FD_DISK_CHANGED_BIT, &UDRS->flags))
-				goto out;
-			if (test_bit(FD_OPEN_SHOULD_FAIL_BIT, &UDRS->flags))
-				goto out;
-		}
-		res = -EROFS;
-		if ((mode & FMODE_WRITE) &&
-		    !test_bit(FD_DISK_WRITABLE_BIT, &UDRS->flags))
-			goto out;
-	}
+	UDRS->last_checked = 0;
+	clear_bit(FD_OPEN_SHOULD_FAIL_BIT, &UDRS->flags);
+	check_disk_change(bdev);
+	if (test_bit(FD_DISK_CHANGED_BIT, &UDRS->flags))
+		goto out;
+	if (test_bit(FD_OPEN_SHOULD_FAIL_BIT, &UDRS->flags))
+		goto out;
+
+	res = -EROFS;
+
+	if ((mode & FMODE_WRITE) &&
+			!test_bit(FD_DISK_WRITABLE_BIT, &UDRS->flags))
+		goto out;
+
 	mutex_unlock(&open_lock);
 	mutex_unlock(&floppy_mutex);
 	return 0;
@@ -3748,7 +3752,8 @@ static unsigned int floppy_check_events(struct gendisk *disk,
 		return DISK_EVENT_MEDIA_CHANGE;
 
 	if (time_after(jiffies, UDRS->last_checked + UDP->checkfreq)) {
-		lock_fdc(drive, false);
+		if (lock_fdc(drive))
+			return -EINTR;
 		poll_drive(false, 0);
 		process_fd_request();
 	}
@@ -3847,7 +3852,9 @@ static int floppy_revalidate(struct gendisk *disk)
 			 "VFS: revalidate called on non-open device.\n"))
 			return -EFAULT;
 
-		lock_fdc(drive, false);
+		res = lock_fdc(drive);
+		if (res)
+			return res;
 		cf = (test_bit(FD_DISK_CHANGED_BIT, &UDRS->flags) ||
 		      test_bit(FD_VERIFY_BIT, &UDRS->flags));
 		if (!(cf || test_bit(drive, &fake_change) || drive_no_geom(drive))) {

drivers/block/null_blk.c

@@ -478,7 +478,7 @@ static int null_lnvm_id(struct nvm_dev *dev, struct nvm_id *id)
 	id->ver_id = 0x1;
 	id->vmnt = 0;
 	id->cgrps = 1;
-	id->cap = 0x3;
+	id->cap = 0x2;
 	id->dom = 0x1;
 
 	id->ppaf.blk_offset = 0;
@@ -707,9 +707,7 @@ static int null_add_dev(void)
 	queue_flag_set_unlocked(QUEUE_FLAG_NONROT, nullb->q);
 	queue_flag_clear_unlocked(QUEUE_FLAG_ADD_RANDOM, nullb->q);
 
-
 	mutex_lock(&lock);
-	list_add_tail(&nullb->list, &nullb_list);
 	nullb->index = nullb_indexes++;
 	mutex_unlock(&lock);
 
@@ -743,6 +741,10 @@ static int null_add_dev(void)
 	strncpy(disk->disk_name, nullb->disk_name, DISK_NAME_LEN);
 
 	add_disk(disk);
+
+	mutex_lock(&lock);
+	list_add_tail(&nullb->list, &nullb_list);
+	mutex_unlock(&lock);
 done:
 	return 0;