Merge tag 'for-5.8/drivers-2020-06-01' of git://git.kernel.dk/linux-block

Pull block driver updates from Jens Axboe:
 "On top of the core changes, here are the block driver changes for this
  merge window:

   - NVMe changes:
        - NVMe over Fibre Channel protocol updates, which also reach
          over to drivers/scsi/lpfc (James Smart)
        - namespace revalidation support on the target (Anthony
          Iliopoulos)
        - gcc zero length array fix (Arnd Bergmann)
        - nvmet cleanups (Chaitanya Kulkarni)
        - misc cleanups and fixes (me, Keith Busch, Sagi Grimberg)
        - use a SRQ per completion vector (Max Gurtovoy)
        - fix handling of runtime changes to the queue count (Weiping
          Zhang)
        - t10 protection information support for nvme-rdma and
          nvmet-rdma (Israel Rukshin and Max Gurtovoy)
        - target side AEN improvements (Chaitanya Kulkarni)
        - various fixes and minor improvements all over, icluding the
          nvme part of the lpfc driver"

   - Floppy code cleanup series (Willy, Denis)

   - Floppy contention fix (Jiri)

   - Loop CONFIGURE support (Martijn)

   - bcache fixes/improvements (Coly, Joe, Colin)

   - q->queuedata cleanups (Christoph)

   - Get rid of ioctl_by_bdev (Christoph, Stefan)

   - md/raid5 allocation fixes (Coly)

   - zero length array fixes (Gustavo)

   - swim3 task state fix (Xu)"

* tag 'for-5.8/drivers-2020-06-01' of git://git.kernel.dk/linux-block: (166 commits)
  bcache: configure the asynchronous registertion to be experimental
  bcache: asynchronous devices registration
  bcache: fix refcount underflow in bcache_device_free()
  bcache: Convert pr_<level> uses to a more typical style
  bcache: remove redundant variables i and n
  lpfc: Fix return value in __lpfc_nvme_ls_abort
  lpfc: fix axchg pointer reference after free and double frees
  lpfc: Fix pointer checks and comments in LS receive refactoring
  nvme: set dma alignment to qword
  nvmet: cleanups the loop in nvmet_async_events_process
  nvmet: fix memory leak when removing namespaces and controllers concurrently
  nvmet-rdma: add metadata/T10-PI support
  nvmet: add metadata support for block devices
  nvmet: add metadata/T10-PI support
  nvme: add Metadata Capabilities enumerations
  nvmet: rename nvmet_check_data_len to nvmet_check_transfer_len
  nvmet: rename nvmet_rw_len to nvmet_rw_data_len
  nvmet: add metadata characteristics for a namespace
  nvme-rdma: add metadata/T10-PI support
  nvme-rdma: introduce nvme_rdma_sgl structure
  ...

1 files changed, 226 insertions, 157 deletions

diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 13dbe2f168820b..4212288ab157cf 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -228,26 +228,36 @@ static void __loop_update_dio(struct loop_device *lo, bool dio)
 		blk_mq_unfreeze_queue(lo->lo_queue);
 }
 
+/**
+ * loop_validate_block_size() - validates the passed in block size
+ * @bsize: size to validate
+ */
 static int
-figure_loop_size(struct loop_device *lo, loff_t offset, loff_t sizelimit)
+loop_validate_block_size(unsigned short bsize)
 {
-	loff_t size = get_size(offset, sizelimit, lo->lo_backing_file);
-	sector_t x = (sector_t)size;
-	struct block_device *bdev = lo->lo_device;
+	if (bsize < 512 || bsize > PAGE_SIZE || !is_power_of_2(bsize))
+		return -EINVAL;
 
-	if (unlikely((loff_t)x != size))
-		return -EFBIG;
-	if (lo->lo_offset != offset)
-		lo->lo_offset = offset;
-	if (lo->lo_sizelimit != sizelimit)
-		lo->lo_sizelimit = sizelimit;
-	set_capacity(lo->lo_disk, x);
-	bd_set_size(bdev, (loff_t)get_capacity(bdev->bd_disk) << 9);
-	/* let user-space know about the new size */
-	kobject_uevent(&disk_to_dev(bdev->bd_disk)->kobj, KOBJ_CHANGE);
 	return 0;
 }
 
+/**
+ * loop_set_size() - sets device size and notifies userspace
+ * @lo: struct loop_device to set the size for
+ * @size: new size of the loop device
+ *
+ * Callers must validate that the size passed into this function fits into
+ * a sector_t, eg using loop_validate_size()
+ */
+static void loop_set_size(struct loop_device *lo, loff_t size)
+{
+	struct block_device *bdev = lo->lo_device;
+
+	bd_set_size(bdev, size << SECTOR_SHIFT);
+
+	set_capacity_revalidate_and_notify(lo->lo_disk, size, false);
+}
+
 static inline int
 lo_do_transfer(struct loop_device *lo, int cmd,
 	       struct page *rpage, unsigned roffs,
@@ -952,23 +962,125 @@ static void loop_update_rotational(struct loop_device *lo)
 		blk_queue_flag_clear(QUEUE_FLAG_NONROT, q);
 }
 
-static int loop_set_fd(struct loop_device *lo, fmode_t mode,
-		       struct block_device *bdev, unsigned int arg)
+static int
+loop_release_xfer(struct loop_device *lo)
+{
+	int err = 0;
+	struct loop_func_table *xfer = lo->lo_encryption;
+
+	if (xfer) {
+		if (xfer->release)
+			err = xfer->release(lo);
+		lo->transfer = NULL;
+		lo->lo_encryption = NULL;
+		module_put(xfer->owner);
+	}
+	return err;
+}
+
+static int
+loop_init_xfer(struct loop_device *lo, struct loop_func_table *xfer,
+	       const struct loop_info64 *i)
+{
+	int err = 0;
+
+	if (xfer) {
+		struct module *owner = xfer->owner;
+
+		if (!try_module_get(owner))
+			return -EINVAL;
+		if (xfer->init)
+			err = xfer->init(lo, i);
+		if (err)
+			module_put(owner);
+		else
+			lo->lo_encryption = xfer;
+	}
+	return err;
+}
+
+/**
+ * loop_set_status_from_info - configure device from loop_info
+ * @lo: struct loop_device to configure
+ * @info: struct loop_info64 to configure the device with
+ *
+ * Configures the loop device parameters according to the passed
+ * in loop_info64 configuration.
+ */
+static int
+loop_set_status_from_info(struct loop_device *lo,
+			  const struct loop_info64 *info)
+{
+	int err;
+	struct loop_func_table *xfer;
+	kuid_t uid = current_uid();
+
+	if ((unsigned int) info->lo_encrypt_key_size > LO_KEY_SIZE)
+		return -EINVAL;
+
+	err = loop_release_xfer(lo);
+	if (err)
+		return err;
+
+	if (info->lo_encrypt_type) {
+		unsigned int type = info->lo_encrypt_type;
+
+		if (type >= MAX_LO_CRYPT)
+			return -EINVAL;
+		xfer = xfer_funcs[type];
+		if (xfer == NULL)
+			return -EINVAL;
+	} else
+		xfer = NULL;
+
+	err = loop_init_xfer(lo, xfer, info);
+	if (err)
+		return err;
+
+	lo->lo_offset = info->lo_offset;
+	lo->lo_sizelimit = info->lo_sizelimit;
+	memcpy(lo->lo_file_name, info->lo_file_name, LO_NAME_SIZE);
+	memcpy(lo->lo_crypt_name, info->lo_crypt_name, LO_NAME_SIZE);
+	lo->lo_file_name[LO_NAME_SIZE-1] = 0;
+	lo->lo_crypt_name[LO_NAME_SIZE-1] = 0;
+
+	if (!xfer)
+		xfer = &none_funcs;
+	lo->transfer = xfer->transfer;
+	lo->ioctl = xfer->ioctl;
+
+	lo->lo_flags = info->lo_flags;
+
+	lo->lo_encrypt_key_size = info->lo_encrypt_key_size;
+	lo->lo_init[0] = info->lo_init[0];
+	lo->lo_init[1] = info->lo_init[1];
+	if (info->lo_encrypt_key_size) {
+		memcpy(lo->lo_encrypt_key, info->lo_encrypt_key,
+		       info->lo_encrypt_key_size);
+		lo->lo_key_owner = uid;
+	}
+
+	return 0;
+}
+
+static int loop_configure(struct loop_device *lo, fmode_t mode,
+			  struct block_device *bdev,
+			  const struct loop_config *config)
 {
 	struct file	*file;
 	struct inode	*inode;
 	struct address_space *mapping;
 	struct block_device *claimed_bdev = NULL;
-	int		lo_flags = 0;
 	int		error;
 	loff_t		size;
 	bool		partscan;
+	unsigned short  bsize;
 
 	/* This is safe, since we have a reference from open(). */
 	__module_get(THIS_MODULE);
 
 	error = -EBADF;
-	file = fget(arg);
+	file = fget(config->fd);
 	if (!file)
 		goto out;
 
@@ -977,7 +1089,7 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode,
 	 * here to avoid changing device under exclusive owner.
 	 */
 	if (!(mode & FMODE_EXCL)) {
-		claimed_bdev = bd_start_claiming(bdev, loop_set_fd);
+		claimed_bdev = bd_start_claiming(bdev, loop_configure);
 		if (IS_ERR(claimed_bdev)) {
 			error = PTR_ERR(claimed_bdev);
 			goto out_putf;
@@ -999,52 +1111,58 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode,
 	mapping = file->f_mapping;
 	inode = mapping->host;
 
+	size = get_loop_size(lo, file);
+
+	if ((config->info.lo_flags & ~LOOP_CONFIGURE_SETTABLE_FLAGS) != 0) {
+		error = -EINVAL;
+		goto out_unlock;
+	}
+
+	if (config->block_size) {
+		error = loop_validate_block_size(config->block_size);
+		if (error)
+			goto out_unlock;
+	}
+
+	error = loop_set_status_from_info(lo, &config->info);
+	if (error)
+		goto out_unlock;
+
 	if (!(file->f_mode & FMODE_WRITE) || !(mode & FMODE_WRITE) ||
 	    !file->f_op->write_iter)
-		lo_flags |= LO_FLAGS_READ_ONLY;
+		lo->lo_flags |= LO_FLAGS_READ_ONLY;
 
-	error = -EFBIG;
-	size = get_loop_size(lo, file);
-	if ((loff_t)(sector_t)size != size)
-		goto out_unlock;
 	error = loop_prepare_queue(lo);
 	if (error)
 		goto out_unlock;
 
-	error = 0;
-
-	set_device_ro(bdev, (lo_flags & LO_FLAGS_READ_ONLY) != 0);
+	set_device_ro(bdev, (lo->lo_flags & LO_FLAGS_READ_ONLY) != 0);
 
-	lo->use_dio = false;
+	lo->use_dio = lo->lo_flags & LO_FLAGS_DIRECT_IO;
 	lo->lo_device = bdev;
-	lo->lo_flags = lo_flags;
 	lo->lo_backing_file = file;
-	lo->transfer = NULL;
-	lo->ioctl = NULL;
-	lo->lo_sizelimit = 0;
 	lo->old_gfp_mask = mapping_gfp_mask(mapping);
 	mapping_set_gfp_mask(mapping, lo->old_gfp_mask & ~(__GFP_IO|__GFP_FS));
 
-	if (!(lo_flags & LO_FLAGS_READ_ONLY) && file->f_op->fsync)
+	if (!(lo->lo_flags & LO_FLAGS_READ_ONLY) && file->f_op->fsync)
 		blk_queue_write_cache(lo->lo_queue, true, false);
 
-	if (io_is_direct(lo->lo_backing_file) && inode->i_sb->s_bdev) {
+	if (config->block_size)
+		bsize = config->block_size;
+	else if (io_is_direct(lo->lo_backing_file) && inode->i_sb->s_bdev)
 		/* In case of direct I/O, match underlying block size */
-		unsigned short bsize = bdev_logical_block_size(
-			inode->i_sb->s_bdev);
+		bsize = bdev_logical_block_size(inode->i_sb->s_bdev);
+	else
+		bsize = 512;
 
-		blk_queue_logical_block_size(lo->lo_queue, bsize);
-		blk_queue_physical_block_size(lo->lo_queue, bsize);
-		blk_queue_io_min(lo->lo_queue, bsize);
-	}
+	blk_queue_logical_block_size(lo->lo_queue, bsize);
+	blk_queue_physical_block_size(lo->lo_queue, bsize);
+	blk_queue_io_min(lo->lo_queue, bsize);
 
 	loop_update_rotational(lo);
 	loop_update_dio(lo);
-	set_capacity(lo->lo_disk, size);
-	bd_set_size(bdev, size << 9);
 	loop_sysfs_init(lo);
-	/* let user-space know about the new size */
-	kobject_uevent(&disk_to_dev(bdev->bd_disk)->kobj, KOBJ_CHANGE);
+	loop_set_size(lo, size);
 
 	set_blocksize(bdev, S_ISBLK(inode->i_mode) ?
 		      block_size(inode->i_bdev) : PAGE_SIZE);
@@ -1062,14 +1180,14 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode,
 	if (partscan)
 		loop_reread_partitions(lo, bdev);
 	if (claimed_bdev)
-		bd_abort_claiming(bdev, claimed_bdev, loop_set_fd);
+		bd_abort_claiming(bdev, claimed_bdev, loop_configure);
 	return 0;
 
 out_unlock:
 	mutex_unlock(&loop_ctl_mutex);
 out_bdev:
 	if (claimed_bdev)
-		bd_abort_claiming(bdev, claimed_bdev, loop_set_fd);
+		bd_abort_claiming(bdev, claimed_bdev, loop_configure);
 out_putf:
 	fput(file);
 out:
@@ -1078,43 +1196,6 @@ out:
 	return error;
 }
 
-static int
-loop_release_xfer(struct loop_device *lo)
-{
-	int err = 0;
-	struct loop_func_table *xfer = lo->lo_encryption;
-
-	if (xfer) {
-		if (xfer->release)
-			err = xfer->release(lo);
-		lo->transfer = NULL;
-		lo->lo_encryption = NULL;
-		module_put(xfer->owner);
-	}
-	return err;
-}
-
-static int
-loop_init_xfer(struct loop_device *lo, struct loop_func_table *xfer,
-	       const struct loop_info64 *i)
-{
-	int err = 0;
-
-	if (xfer) {
-		struct module *owner = xfer->owner;
-
-		if (!try_module_get(owner))
-			return -EINVAL;
-		if (xfer->init)
-			err = xfer->init(lo, i);
-		if (err)
-			module_put(owner);
-		else
-			lo->lo_encryption = xfer;
-	}
-	return err;
-}
-
 static int __loop_clr_fd(struct loop_device *lo, bool release)
 {
 	struct file *filp = NULL;
@@ -1263,10 +1344,11 @@ static int
 loop_set_status(struct loop_device *lo, const struct loop_info64 *info)
 {
 	int err;
-	struct loop_func_table *xfer;
-	kuid_t uid = current_uid();
 	struct block_device *bdev;
+	kuid_t uid = current_uid();
+	int prev_lo_flags;
 	bool partscan = false;
+	bool size_changed = false;
 
 	err = mutex_lock_killable(&loop_ctl_mutex);
 	if (err)
@@ -1281,13 +1363,10 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info)
 		err = -ENXIO;
 		goto out_unlock;
 	}
-	if ((unsigned int) info->lo_encrypt_key_size > LO_KEY_SIZE) {
-		err = -EINVAL;
-		goto out_unlock;
-	}
 
 	if (lo->lo_offset != info->lo_offset ||
 	    lo->lo_sizelimit != info->lo_sizelimit) {
+		size_changed = true;
 		sync_blockdev(lo->lo_device);
 		kill_bdev(lo->lo_device);
 	}
@@ -1295,79 +1374,44 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info)
 	/* I/O need to be drained during transfer transition */
 	blk_mq_freeze_queue(lo->lo_queue);
 
-	err = loop_release_xfer(lo);
-	if (err)
+	if (size_changed && lo->lo_device->bd_inode->i_mapping->nrpages) {
+		/* If any pages were dirtied after kill_bdev(), try again */
+		err = -EAGAIN;
+		pr_warn("%s: loop%d (%s) has still dirty pages (nrpages=%lu)\n",
+			__func__, lo->lo_number, lo->lo_file_name,
+			lo->lo_device->bd_inode->i_mapping->nrpages);
 		goto out_unfreeze;
+	}
 
-	if (info->lo_encrypt_type) {
-		unsigned int type = info->lo_encrypt_type;
-
-		if (type >= MAX_LO_CRYPT) {
-			err = -EINVAL;
-			goto out_unfreeze;
-		}
-		xfer = xfer_funcs[type];
-		if (xfer == NULL) {
-			err = -EINVAL;
-			goto out_unfreeze;
-		}
-	} else
-		xfer = NULL;
+	prev_lo_flags = lo->lo_flags;
 
-	err = loop_init_xfer(lo, xfer, info);
+	err = loop_set_status_from_info(lo, info);
 	if (err)
 		goto out_unfreeze;
 
-	if (lo->lo_offset != info->lo_offset ||
-	    lo->lo_sizelimit != info->lo_sizelimit) {
-		/* kill_bdev should have truncated all the pages */
-		if (lo->lo_device->bd_inode->i_mapping->nrpages) {
-			err = -EAGAIN;
-			pr_warn("%s: loop%d (%s) has still dirty pages (nrpages=%lu)\n",
-				__func__, lo->lo_number, lo->lo_file_name,
-				lo->lo_device->bd_inode->i_mapping->nrpages);
-			goto out_unfreeze;
-		}
-		if (figure_loop_size(lo, info->lo_offset, info->lo_sizelimit)) {
-			err = -EFBIG;
-			goto out_unfreeze;
-		}
+	/* Mask out flags that can't be set using LOOP_SET_STATUS. */
+	lo->lo_flags &= ~LOOP_SET_STATUS_SETTABLE_FLAGS;
+	/* For those flags, use the previous values instead */
+	lo->lo_flags |= prev_lo_flags & ~LOOP_SET_STATUS_SETTABLE_FLAGS;
+	/* For flags that can't be cleared, use previous values too */
+	lo->lo_flags |= prev_lo_flags & ~LOOP_SET_STATUS_CLEARABLE_FLAGS;
+
+	if (size_changed) {
+		loff_t new_size = get_size(lo->lo_offset, lo->lo_sizelimit,
+					   lo->lo_backing_file);
+		loop_set_size(lo, new_size);
 	}
 
 	loop_config_discard(lo);
 
-	memcpy(lo->lo_file_name, info->lo_file_name, LO_NAME_SIZE);
-	memcpy(lo->lo_crypt_name, info->lo_crypt_name, LO_NAME_SIZE);
-	lo->lo_file_name[LO_NAME_SIZE-1] = 0;
-	lo->lo_crypt_name[LO_NAME_SIZE-1] = 0;
-
-	if (!xfer)
-		xfer = &none_funcs;
-	lo->transfer = xfer->transfer;
-	lo->ioctl = xfer->ioctl;
-
-	if ((lo->lo_flags & LO_FLAGS_AUTOCLEAR) !=
-	     (info->lo_flags & LO_FLAGS_AUTOCLEAR))
-		lo->lo_flags ^= LO_FLAGS_AUTOCLEAR;
-
-	lo->lo_encrypt_key_size = info->lo_encrypt_key_size;
-	lo->lo_init[0] = info->lo_init[0];
-	lo->lo_init[1] = info->lo_init[1];
-	if (info->lo_encrypt_key_size) {
-		memcpy(lo->lo_encrypt_key, info->lo_encrypt_key,
-		       info->lo_encrypt_key_size);
-		lo->lo_key_owner = uid;
-	}
-
 	/* update dio if lo_offset or transfer is changed */
 	__loop_update_dio(lo, lo->use_dio);
 
 out_unfreeze:
 	blk_mq_unfreeze_queue(lo->lo_queue);
 
-	if (!err && (info->lo_flags & LO_FLAGS_PARTSCAN) &&
-	     !(lo->lo_flags & LO_FLAGS_PARTSCAN)) {
-		lo->lo_flags |= LO_FLAGS_PARTSCAN;
+	if (!err && (lo->lo_flags & LO_FLAGS_PARTSCAN) &&
+	     !(prev_lo_flags & LO_FLAGS_PARTSCAN)) {
 		lo->lo_disk->flags &= ~GENHD_FL_NO_PART_SCAN;
 		bdev = lo->lo_device;
 		partscan = true;
@@ -1531,10 +1575,15 @@ loop_get_status64(struct loop_device *lo, struct loop_info64 __user *arg) {
 
 static int loop_set_capacity(struct loop_device *lo)
 {
+	loff_t size;
+
 	if (unlikely(lo->lo_state != Lo_bound))
 		return -ENXIO;
 
-	return figure_loop_size(lo, lo->lo_offset, lo->lo_sizelimit);
+	size = get_loop_size(lo, lo->lo_backing_file);
+	loop_set_size(lo, size);
+
+	return 0;
 }
 
 static int loop_set_dio(struct loop_device *lo, unsigned long arg)
@@ -1558,8 +1607,9 @@ static int loop_set_block_size(struct loop_device *lo, unsigned long arg)
 	if (lo->lo_state != Lo_bound)
 		return -ENXIO;
 
-	if (arg < 512 || arg > PAGE_SIZE || !is_power_of_2(arg))
-		return -EINVAL;
+	err = loop_validate_block_size(arg);
+	if (err)
+		return err;
 
 	if (lo->lo_queue->limits.logical_block_size == arg)
 		return 0;
@@ -1617,11 +1667,31 @@ static int lo_ioctl(struct block_device *bdev, fmode_t mode,
 	unsigned int cmd, unsigned long arg)
 {
 	struct loop_device *lo = bdev->bd_disk->private_data;
+	void __user *argp = (void __user *) arg;
 	int err;
 
 	switch (cmd) {
-	case LOOP_SET_FD:
-		return loop_set_fd(lo, mode, bdev, arg);
+	case LOOP_SET_FD: {
+		/*
+		 * Legacy case - pass in a zeroed out struct loop_config with
+		 * only the file descriptor set , which corresponds with the
+		 * default parameters we'd have used otherwise.
+		 */
+		struct loop_config config;
+
+		memset(&config, 0, sizeof(config));
+		config.fd = arg;
+
+		return loop_configure(lo, mode, bdev, &config);
+	}
+	case LOOP_CONFIGURE: {
+		struct loop_config config;
+
+		if (copy_from_user(&config, argp, sizeof(config)))
+			return -EFAULT;
+
+		return loop_configure(lo, mode, bdev, &config);
+	}
 	case LOOP_CHANGE_FD:
 		return loop_change_fd(lo, bdev, arg);
 	case LOOP_CLR_FD:
@@ -1629,21 +1699,19 @@ static int lo_ioctl(struct block_device *bdev, fmode_t mode,
 	case LOOP_SET_STATUS:
 		err = -EPERM;
 		if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN)) {
-			err = loop_set_status_old(lo,
-					(struct loop_info __user *)arg);
+			err = loop_set_status_old(lo, argp);
 		}
 		break;
 	case LOOP_GET_STATUS:
-		return loop_get_status_old(lo, (struct loop_info __user *) arg);
+		return loop_get_status_old(lo, argp);
 	case LOOP_SET_STATUS64:
 		err = -EPERM;
 		if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN)) {
-			err = loop_set_status64(lo,
-					(struct loop_info64 __user *) arg);
+			err = loop_set_status64(lo, argp);
 		}
 		break;
 	case LOOP_GET_STATUS64:
-		return loop_get_status64(lo, (struct loop_info64 __user *) arg);
+		return loop_get_status64(lo, argp);
 	case LOOP_SET_CAPACITY:
 	case LOOP_SET_DIRECT_IO:
 	case LOOP_SET_BLOCK_SIZE:
@@ -1795,6 +1863,7 @@ static int lo_compat_ioctl(struct block_device *bdev, fmode_t mode,
 	case LOOP_CLR_FD:
 	case LOOP_GET_STATUS64:
 	case LOOP_SET_STATUS64:
+	case LOOP_CONFIGURE:
 		arg = (unsigned long) compat_ptr(arg);
 		/* fall through */
 	case LOOP_SET_FD: