Merge tag 'for-5.15-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs fixes from David Sterba:

 - fix max_inline mount option limit on 64k page system

 - lockdep fixes:
     - update bdev time in a safer way
     - move bdev put outside of sb write section when removing device
     - fix possible deadlock when mounting seed/sprout filesystem

 - zoned mode: fix split extent accounting

 - minor include fixup

* tag 'for-5.15-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux:
  btrfs: zoned: fix double counting of split ordered extent
  btrfs: fix lockdep warning while mounting sprout fs
  btrfs: delay blkdev_put until after the device remove
  btrfs: update the bdev time directly when closing
  btrfs: use correct header for div_u64 in misc.h
  btrfs: fix upper limit for max_inline for page size 64K

6 files changed, 77 insertions, 47 deletions

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 2f9515dccce0..355ea88d5c5f 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -3314,6 +3314,30 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device
 	 */
 	fs_info->compress_type = BTRFS_COMPRESS_ZLIB;
 
+	/*
+	 * Flag our filesystem as having big metadata blocks if they are bigger
+	 * than the page size.
+	 */
+	if (btrfs_super_nodesize(disk_super) > PAGE_SIZE) {
+		if (!(features & BTRFS_FEATURE_INCOMPAT_BIG_METADATA))
+			btrfs_info(fs_info,
+				"flagging fs with big metadata feature");
+		features |= BTRFS_FEATURE_INCOMPAT_BIG_METADATA;
+	}
+
+	/* Set up fs_info before parsing mount options */
+	nodesize = btrfs_super_nodesize(disk_super);
+	sectorsize = btrfs_super_sectorsize(disk_super);
+	stripesize = sectorsize;
+	fs_info->dirty_metadata_batch = nodesize * (1 + ilog2(nr_cpu_ids));
+	fs_info->delalloc_batch = sectorsize * 512 * (1 + ilog2(nr_cpu_ids));
+
+	fs_info->nodesize = nodesize;
+	fs_info->sectorsize = sectorsize;
+	fs_info->sectorsize_bits = ilog2(sectorsize);
+	fs_info->csums_per_leaf = BTRFS_MAX_ITEM_SIZE(fs_info) / fs_info->csum_size;
+	fs_info->stripesize = stripesize;
+
 	ret = btrfs_parse_options(fs_info, options, sb->s_flags);
 	if (ret) {
 		err = ret;
@@ -3341,30 +3365,6 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device
 		btrfs_info(fs_info, "has skinny extents");
 
 	/*
-	 * flag our filesystem as having big metadata blocks if
-	 * they are bigger than the page size
-	 */
-	if (btrfs_super_nodesize(disk_super) > PAGE_SIZE) {
-		if (!(features & BTRFS_FEATURE_INCOMPAT_BIG_METADATA))
-			btrfs_info(fs_info,
-				"flagging fs with big metadata feature");
-		features |= BTRFS_FEATURE_INCOMPAT_BIG_METADATA;
-	}
-
-	nodesize = btrfs_super_nodesize(disk_super);
-	sectorsize = btrfs_super_sectorsize(disk_super);
-	stripesize = sectorsize;
-	fs_info->dirty_metadata_batch = nodesize * (1 + ilog2(nr_cpu_ids));
-	fs_info->delalloc_batch = sectorsize * 512 * (1 + ilog2(nr_cpu_ids));
-
-	/* Cache block sizes */
-	fs_info->nodesize = nodesize;
-	fs_info->sectorsize = sectorsize;
-	fs_info->sectorsize_bits = ilog2(sectorsize);
-	fs_info->csums_per_leaf = BTRFS_MAX_ITEM_SIZE(fs_info) / fs_info->csum_size;
-	fs_info->stripesize = stripesize;
-
-	/*
 	 * mixed block groups end up with duplicate but slightly offset
 	 * extent buffers for the same range.  It leads to corruptions
 	 */
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 41524f9aeac3..cc61813213d8 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -3223,6 +3223,8 @@ static long btrfs_ioctl_rm_dev_v2(struct file *file, void __user *arg)
 	struct inode *inode = file_inode(file);
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct btrfs_ioctl_vol_args_v2 *vol_args;
+	struct block_device *bdev = NULL;
+	fmode_t mode;
 	int ret;
 	bool cancel = false;
 
@@ -3255,9 +3257,9 @@ static long btrfs_ioctl_rm_dev_v2(struct file *file, void __user *arg)
 	/* Exclusive operation is now claimed */
 
 	if (vol_args->flags & BTRFS_DEVICE_SPEC_BY_ID)
-		ret = btrfs_rm_device(fs_info, NULL, vol_args->devid);
+		ret = btrfs_rm_device(fs_info, NULL, vol_args->devid, &bdev, &mode);
 	else
-		ret = btrfs_rm_device(fs_info, vol_args->name, 0);
+		ret = btrfs_rm_device(fs_info, vol_args->name, 0, &bdev, &mode);
 
 	btrfs_exclop_finish(fs_info);
 
@@ -3273,6 +3275,8 @@ out:
 	kfree(vol_args);
 err_drop:
 	mnt_drop_write_file(file);
+	if (bdev)
+		blkdev_put(bdev, mode);
 	return ret;
 }
 
@@ -3281,6 +3285,8 @@ static long btrfs_ioctl_rm_dev(struct file *file, void __user *arg)
 	struct inode *inode = file_inode(file);
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct btrfs_ioctl_vol_args *vol_args;
+	struct block_device *bdev = NULL;
+	fmode_t mode;
 	int ret;
 	bool cancel;
 
@@ -3302,7 +3308,7 @@ static long btrfs_ioctl_rm_dev(struct file *file, void __user *arg)
 	ret = exclop_start_or_cancel_reloc(fs_info, BTRFS_EXCLOP_DEV_REMOVE,
 					   cancel);
 	if (ret == 0) {
-		ret = btrfs_rm_device(fs_info, vol_args->name, 0);
+		ret = btrfs_rm_device(fs_info, vol_args->name, 0, &bdev, &mode);
 		if (!ret)
 			btrfs_info(fs_info, "disk deleted %s", vol_args->name);
 		btrfs_exclop_finish(fs_info);
@@ -3311,7 +3317,8 @@ static long btrfs_ioctl_rm_dev(struct file *file, void __user *arg)
 	kfree(vol_args);
 out_drop_write:
 	mnt_drop_write_file(file);
-
+	if (bdev)
+		blkdev_put(bdev, mode);
 	return ret;
 }
 
diff --git a/fs/btrfs/misc.h b/fs/btrfs/misc.h
index 6461ebc3a1c1..340f995652f2 100644
--- a/fs/btrfs/misc.h
+++ b/fs/btrfs/misc.h
@@ -5,7 +5,7 @@
 
 #include <linux/sched.h>
 #include <linux/wait.h>
-#include <asm/div64.h>
+#include <linux/math64.h>
 #include <linux/rbtree.h>
 
 #define in_range(b, first, len) ((b) >= (first) && (b) < (first) + (len))
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index edb65abf0393..6b51fd2ec5ac 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -1049,6 +1049,7 @@ static int clone_ordered_extent(struct btrfs_ordered_extent *ordered, u64 pos,
 				u64 len)
 {
 	struct inode *inode = ordered->inode;
+	struct btrfs_fs_info *fs_info = BTRFS_I(inode)->root->fs_info;
 	u64 file_offset = ordered->file_offset + pos;
 	u64 disk_bytenr = ordered->disk_bytenr + pos;
 	u64 num_bytes = len;
@@ -1066,6 +1067,13 @@ static int clone_ordered_extent(struct btrfs_ordered_extent *ordered, u64 pos,
 	else
 		type = __ffs(flags_masked);
 
+	/*
+	 * The splitting extent is already counted and will be added again
+	 * in btrfs_add_ordered_extent_*(). Subtract num_bytes to avoid
+	 * double counting.
+	 */
+	percpu_counter_add_batch(&fs_info->ordered_bytes, -num_bytes,
+				 fs_info->delalloc_batch);
 	if (test_bit(BTRFS_ORDERED_COMPRESSED, &ordered->flags)) {
 		WARN_ON_ONCE(1);
 		ret = btrfs_add_ordered_extent_compress(BTRFS_I(inode),
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index ec3a874165de..464485aa7318 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -558,6 +558,8 @@ static int btrfs_free_stale_devices(const char *path,
 	struct btrfs_device *device, *tmp_device;
 	int ret = 0;
 
+	lockdep_assert_held(&uuid_mutex);
+
 	if (path)
 		ret = -ENOENT;
 
@@ -988,11 +990,12 @@ static struct btrfs_fs_devices *clone_fs_devices(struct btrfs_fs_devices *orig)
 	struct btrfs_device *orig_dev;
 	int ret = 0;
 
+	lockdep_assert_held(&uuid_mutex);
+
 	fs_devices = alloc_fs_devices(orig->fsid, NULL);
 	if (IS_ERR(fs_devices))
 		return fs_devices;
 
-	mutex_lock(&orig->device_list_mutex);
 	fs_devices->total_devices = orig->total_devices;
 
 	list_for_each_entry(orig_dev, &orig->devices, dev_list) {
@@ -1024,10 +1027,8 @@ static struct btrfs_fs_devices *clone_fs_devices(struct btrfs_fs_devices *orig)
 		device->fs_devices = fs_devices;
 		fs_devices->num_devices++;
 	}
-	mutex_unlock(&orig->device_list_mutex);
 	return fs_devices;
 error:
-	mutex_unlock(&orig->device_list_mutex);
 	free_fs_devices(fs_devices);
 	return ERR_PTR(ret);
 }
@@ -1869,15 +1870,17 @@ out:
  * Function to update ctime/mtime for a given device path.
  * Mainly used for ctime/mtime based probe like libblkid.
  */
-static void update_dev_time(const char *path_name)
+static void update_dev_time(struct block_device *bdev)
 {
-	struct file *filp;
+	struct inode *inode = bdev->bd_inode;
+	struct timespec64 now;
 
-	filp = filp_open(path_name, O_RDWR, 0);
-	if (IS_ERR(filp))
+	/* Shouldn't happen but just in case. */
+	if (!inode)
 		return;
-	file_update_time(filp);
-	filp_close(filp, NULL);
+
+	now = current_time(inode);
+	generic_update_time(inode, &now, S_MTIME | S_CTIME);
 }
 
 static int btrfs_rm_dev_item(struct btrfs_device *device)
@@ -2053,11 +2056,11 @@ void btrfs_scratch_superblocks(struct btrfs_fs_info *fs_info,
 	btrfs_kobject_uevent(bdev, KOBJ_CHANGE);
 
 	/* Update ctime/mtime for device path for libblkid */
-	update_dev_time(device_path);
+	update_dev_time(bdev);
 }
 
 int btrfs_rm_device(struct btrfs_fs_info *fs_info, const char *device_path,
-		    u64 devid)
+		    u64 devid, struct block_device **bdev, fmode_t *mode)
 {
 	struct btrfs_device *device;
 	struct btrfs_fs_devices *cur_devices;
@@ -2171,15 +2174,26 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info, const char *device_path,
 	mutex_unlock(&fs_devices->device_list_mutex);
 
 	/*
-	 * at this point, the device is zero sized and detached from
-	 * the devices list.  All that's left is to zero out the old
-	 * supers and free the device.
+	 * At this point, the device is zero sized and detached from the
+	 * devices list.  All that's left is to zero out the old supers and
+	 * free the device.
+	 *
+	 * We cannot call btrfs_close_bdev() here because we're holding the sb
+	 * write lock, and blkdev_put() will pull in the ->open_mutex on the
+	 * block device and it's dependencies.  Instead just flush the device
+	 * and let the caller do the final blkdev_put.
 	 */
-	if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state))
+	if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state)) {
 		btrfs_scratch_superblocks(fs_info, device->bdev,
 					  device->name->str);
+		if (device->bdev) {
+			sync_blockdev(device->bdev);
+			invalidate_bdev(device->bdev);
+		}
+	}
 
-	btrfs_close_bdev(device);
+	*bdev = device->bdev;
+	*mode = device->mode;
 	synchronize_rcu();
 	btrfs_free_device(device);
 
@@ -2706,7 +2720,7 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
 	btrfs_forget_devices(device_path);
 
 	/* Update ctime/mtime for blkid or udev */
-	update_dev_time(device_path);
+	update_dev_time(bdev);
 
 	return ret;
 
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index b082250b42e0..2183361db614 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -472,7 +472,8 @@ struct btrfs_device *btrfs_alloc_device(struct btrfs_fs_info *fs_info,
 					const u8 *uuid);
 void btrfs_free_device(struct btrfs_device *device);
 int btrfs_rm_device(struct btrfs_fs_info *fs_info,
-		    const char *device_path, u64 devid);
+		    const char *device_path, u64 devid,
+		    struct block_device **bdev, fmode_t *mode);
 void __exit btrfs_cleanup_fs_uuids(void);
 int btrfs_num_copies(struct btrfs_fs_info *fs_info, u64 logical, u64 len);
 int btrfs_grow_device(struct btrfs_trans_handle *trans,