btrfs: add remove_bdev() callback

index 7ed858937d45..a0e11166b194 100644
@@ -172,7 +172,7 @@ int exfat_force_shutdown(struct super_block *sb, u32 flags)
 	return 0;
 }
 
-static void exfat_shutdown(struct super_block *sb)
+static void exfat_remove_bdev(struct super_block *sb, struct block_device *bdev)
 {
 	exfat_force_shutdown(sb, EXFAT_GOING_DOWN_NOSYNC);
 }

@@ -202,7 +202,7 @@ static const struct super_operations exfat_sops = {
 	.put_super	= exfat_put_super,
 	.statfs		= exfat_statfs,
 	.show_options	= exfat_show_options,
-	.shutdown	= exfat_shutdown,
+	.remove_bdev	= exfat_remove_bdev,
 };
 
 enum {

index c7d39da7e733..d75b416401ae 100644
@@ -1456,7 +1456,7 @@ static void ext4_destroy_inode(struct inode *inode)
 			 EXT4_I(inode)->i_reserved_data_blocks);
 }
 
-static void ext4_shutdown(struct super_block *sb)
+static void ext4_remove_bdev(struct super_block *sb, struct block_device *bdev)
 {
        ext4_force_shutdown(sb, EXT4_GOING_FLAGS_NOLOGFLUSH);
 }

@@ -1620,7 +1620,7 @@ static const struct super_operations ext4_sops = {
 	.unfreeze_fs	= ext4_unfreeze,
 	.statfs		= ext4_statfs,
 	.show_options	= ext4_show_options,
-	.shutdown	= ext4_shutdown,
+	.remove_bdev	= ext4_remove_bdev,
 #ifdef CONFIG_QUOTA
 	.quota_read	= ext4_quota_read,
 	.quota_write	= ext4_quota_write,

index bbf1dad6843f..8667af9f76e4 100644
@@ -2640,7 +2640,7 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
 	return err;
 }
 
-static void f2fs_shutdown(struct super_block *sb)
+static void f2fs_remove_bdev(struct super_block *sb, struct block_device *bdev)
 {
 	f2fs_do_shutdown(F2FS_SB(sb), F2FS_GOING_DOWN_NOSYNC, false, false);
 }

@@ -3264,7 +3264,7 @@ static const struct super_operations f2fs_sops = {
 	.unfreeze_fs	= f2fs_unfreeze,
 	.statfs		= f2fs_statfs,
 	.remount_fs	= f2fs_remount,
-	.shutdown	= f2fs_shutdown,
+	.remove_bdev	= f2fs_remove_bdev,
 };
 
 #ifdef CONFIG_FS_ENCRYPTION

index 920a1ab47b63..3e69dc805e3a 100644
@@ -762,9 +762,9 @@ static int ntfs_show_options(struct seq_file *m, struct dentry *root)
 }
 
 /*
- * ntfs_shutdown - super_operations::shutdown
+ * ntfs_remove_bdev - super_operations::remove_bdev
  */
-static void ntfs_shutdown(struct super_block *sb)
+static void ntfs_remove_bdev(struct super_block *sb, struct block_device *bdev)
 {
 	set_bit(NTFS_FLAGS_SHUTDOWN_BIT, &ntfs_sb(sb)->flags);
 }

@@ -821,7 +821,7 @@ static const struct super_operations ntfs_sops = {
 	.put_super = ntfs_put_super,
 	.statfs = ntfs_statfs,
 	.show_options = ntfs_show_options,
-	.shutdown = ntfs_shutdown,
+	.remove_bdev = ntfs_remove_bdev,
 	.sync_fs = ntfs_sync_fs,
 	.write_inode = ntfs3_write_inode,
 };

index 80418ca8e215..c972efb38f6a 100644
@@ -1463,8 +1463,8 @@ static void fs_bdev_mark_dead(struct block_device *bdev, bool surprise)
 		sync_filesystem(sb);
 	shrink_dcache_sb(sb);
 	evict_inodes(sb);
-	if (sb->s_op->shutdown)
-		sb->s_op->shutdown(sb);
+	if (sb->s_op->remove_bdev)
+		sb->s_op->remove_bdev(sb, bdev);
 
 	super_unlock_shared(sb);
 }

index 0bc4b5489078..8e307b036133 100644
@@ -1276,8 +1276,9 @@ xfs_fs_free_cached_objects(
 }
 
 static void
-xfs_fs_shutdown(
-	struct super_block	*sb)
+xfs_fs_remove_bdev(
+	struct super_block	*sb,
+	struct block_device	*bdev)
 {
 	xfs_force_shutdown(XFS_M(sb), SHUTDOWN_DEVICE_REMOVED);
 }

@@ -1308,7 +1309,7 @@ static const struct super_operations xfs_super_operations = {
 	.show_options		= xfs_fs_show_options,
 	.nr_cached_objects	= xfs_fs_nr_cached_objects,
 	.free_cached_objects	= xfs_fs_free_cached_objects,
-	.shutdown		= xfs_fs_shutdown,
+	.remove_bdev		= xfs_fs_remove_bdev,
 	.show_stats		= xfs_fs_show_stats,
 };
 

index b085f161ed22..b08af63d2d4f 100644
@@ -2367,7 +2367,12 @@ struct super_operations {
 				  struct shrink_control *);
 	long (*free_cached_objects)(struct super_block *,
 				    struct shrink_control *);
-	void (*shutdown)(struct super_block *sb);
+	/*
+	 * Called when block device @bdev belonging to @sb is removed.
+	 *
+	 * If the fs can't afford the device loss, it should be shutdown.
+	 */
+	void (*remove_bdev)(struct super_block *sb, struct block_device *bdev);
 };
 
 /*

index 5154ad390f31..83d93ef0c451 100644
@@ -29,6 +29,7 @@
 #include "extent-io-tree.h"
 #include "async-thread.h"
 #include "block-rsv.h"
+#include "messages.h"
 
 struct inode;
 struct super_block;

@@ -120,6 +121,12 @@ enum {
 	/* No more delayed iput can be queued. */
 	BTRFS_FS_STATE_NO_DELAYED_IPUT,
 
+	/*
+	 * Emergency shutdown, a step further than trans aborted by rejecting
+	 * all operations.
+	 */
+	BTRFS_FS_STATE_EMERGENCY_SHUTDOWN,
+
 	BTRFS_FS_STATE_COUNT
 };
 

@@ -1094,6 +1101,27 @@ static inline void btrfs_wake_unfinished_drop(struct btrfs_fs_info *fs_info)
 	(unlikely(test_bit(BTRFS_FS_STATE_LOG_CLEANUP_ERROR,		\
 			   &(fs_info)->fs_state)))
 
+static inline bool btrfs_is_shutdown(struct btrfs_fs_info *fs_info)
+{
+	return test_bit(BTRFS_FS_STATE_EMERGENCY_SHUTDOWN, &fs_info->fs_state);
+}
+
+static inline void btrfs_force_shutdown(struct btrfs_fs_info *fs_info)
+{
+	/*
+	 * Here we do not want to use handle_fs_error(), which will mark
+	 * the fs read-only.
+	 * Some call sites like shutdown ioctl will mark the fs shutdown
+	 * when the fs is frozen. But thaw path will handle RO and RW fs
+	 * differently.
+	 *
+	 * So here we only mark the fs error without flipping it RO.
+	 */
+	WRITE_ONCE(fs_info->fs_error, -EIO);
+	if (!test_and_set_bit(BTRFS_FS_STATE_EMERGENCY_SHUTDOWN, &fs_info->fs_state))
+		btrfs_info(fs_info, "emergency shutdown");
+}
+
 /*
  * We use folio flag owner_2 to indicate there is an ordered extent with
  * unfinished IO.

index 363fd28c0268..2bb4bcb7c2cd 100644
@@ -23,6 +23,7 @@ static const char fs_state_chars[] = {
 	[BTRFS_FS_STATE_NO_DATA_CSUMS]		= 'C',
 	[BTRFS_FS_STATE_SKIP_META_CSUMS]	= 'S',
 	[BTRFS_FS_STATE_LOG_CLEANUP_ERROR]	= 'L',
+	[BTRFS_FS_STATE_EMERGENCY_SHUTDOWN]	= 'E',
 };
 
 static void btrfs_state_to_string(const struct btrfs_fs_info *info, char *buf)

index 05b046c6806f..cb7d1d53fc13 100644
@@ -1419,6 +1419,8 @@ ssize_t btrfs_do_write_iter(struct kiocb *iocb, struct iov_iter *from,
 	struct btrfs_inode *inode = BTRFS_I(file_inode(file));
 	ssize_t num_written, num_sync;
 
+	if (unlikely(btrfs_is_shutdown(inode->root->fs_info)))
+		return -EIO;
 	/*
 	 * If the fs flips readonly due to some impossible error, although we
 	 * have opened a file as writable, we have to stop this write operation

@@ -1981,6 +1983,8 @@ static int btrfs_file_mmap(struct file	*filp, struct vm_area_struct *vma)
 {
 	struct address_space *mapping = filp->f_mapping;
 
+	if (unlikely(btrfs_is_shutdown(inode_to_fs_info(file_inode(filp)))))
+		return -EIO;
 	if (!mapping->a_ops->read_folio)
 		return -ENOEXEC;
 

@@ -3040,6 +3044,9 @@ static long btrfs_fallocate(struct file *file, int mode,
 	int blocksize = BTRFS_I(inode)->root->fs_info->sectorsize;
 	int ret;
 
+	if (unlikely(btrfs_is_shutdown(inode_to_fs_info(inode))))
+		return -EIO;
+
 	/* Do not allow fallocate in ZONED mode */
 	if (btrfs_is_zoned(inode_to_fs_info(inode)))
 		return -EOPNOTSUPP;

@@ -3731,6 +3738,9 @@ static int btrfs_file_open(struct inode *inode, struct file *filp)
 {
 	int ret;
 
+	if (unlikely(btrfs_is_shutdown(inode_to_fs_info(inode))))
+		return -EIO;
+
 	filp->f_mode |= FMODE_NOWAIT | FMODE_CAN_ODIRECT;
 
 	ret = fsverity_file_open(inode, filp);

@@ -3743,6 +3753,9 @@ static ssize_t btrfs_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
 {
 	ssize_t ret = 0;
 
+	if (unlikely(btrfs_is_shutdown(inode_to_fs_info(file_inode(iocb->ki_filp)))))
+		return -EIO;
+
 	if (iocb->ki_flags & IOCB_DIRECT) {
 		ret = btrfs_direct_read(iocb, to);
 		if (ret < 0 || !iov_iter_count(to) ||

@@ -3753,10 +3766,20 @@ static ssize_t btrfs_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
 	return filemap_read(iocb, to, ret);
 }
 
+static ssize_t btrfs_file_splice_read(struct file *in, loff_t *ppos,
+				      struct pipe_inode_info *pipe,
+				      size_t len, unsigned int flags)
+{
+	if (unlikely(btrfs_is_shutdown(inode_to_fs_info(file_inode(in)))))
+		return -EIO;
+
+	return filemap_splice_read(in, ppos, pipe, len, flags);
+}
+
 const struct file_operations btrfs_file_operations = {
 	.llseek		= btrfs_file_llseek,
 	.read_iter      = btrfs_file_read_iter,
-	.splice_read	= filemap_splice_read,
+	.splice_read	= btrfs_file_splice_read,
 	.write_iter	= btrfs_file_write_iter,
 	.splice_write	= iter_file_splice_write,
 	.mmap		= btrfs_file_mmap,

index 503c469249e5..2f3b7be13bea 100644
@@ -5048,6 +5048,9 @@ static int btrfs_uring_encoded_write(struct io_uring_cmd *cmd, unsigned int issu
 
 int btrfs_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags)
 {
+	if (unlikely(btrfs_is_shutdown(inode_to_fs_info(file_inode(cmd->file)))))
+		return -EIO;
+
 	switch (cmd->cmd_op) {
 	case BTRFS_IOC_ENCODED_READ:
 #if defined(CONFIG_64BIT) && defined(CONFIG_COMPAT)

index 0197bd9160a7..123a5682514b 100644
@@ -869,6 +869,9 @@ loff_t btrfs_remap_file_range(struct file *src_file, loff_t off,
 	bool same_inode = dst_inode == src_inode;
 	int ret;
 
+	if (unlikely(btrfs_is_shutdown(inode_to_fs_info(file_inode(src_file)))))
+		return -EIO;
+
 	if (remap_flags & ~(REMAP_FILE_DEDUP | REMAP_FILE_ADVISORY))
 		return -EINVAL;
 

index d7a2ea7d121f..0f0c415e82a2 100644
@@ -861,6 +861,9 @@ static void compress_file_range(struct btrfs_work *work)
 	int compress_type = fs_info->compress_type;
 	int compress_level = fs_info->compress_level;
 
+	if (unlikely(btrfs_is_shutdown(fs_info)))
+		goto cleanup_and_bail_uncompressed;
+
 	inode_should_defrag(inode, start, end, end - start + 1, SZ_16K);
 
 	/*

@@ -1276,6 +1279,11 @@ static noinline int cow_file_range(struct btrfs_inode *inode,
 	unsigned long page_ops;
 	int ret = 0;
 
+	if (unlikely(btrfs_is_shutdown(fs_info))) {
+		ret = -EIO;
+		goto out_unlock;
+	}
+
 	if (btrfs_is_free_space_inode(inode)) {
 		ret = -EINVAL;
 		goto out_unlock;

@@ -2026,7 +2034,7 @@ static noinline int run_delalloc_nocow(struct btrfs_inode *inode,
 {
 	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 	struct btrfs_root *root = inode->root;
-	struct btrfs_path *path;
+	struct btrfs_path *path = NULL;
 	u64 cow_start = (u64)-1;
 	/*
 	 * If not 0, represents the inclusive end of the last fallback_to_cow()

@@ -2046,6 +2054,10 @@ static noinline int run_delalloc_nocow(struct btrfs_inode *inode,
 	 */
 	ASSERT(!btrfs_is_zoned(fs_info) || btrfs_is_data_reloc_root(root));
 
+	if (unlikely(btrfs_is_shutdown(fs_info))) {
+		ret = -EIO;
+		goto error;
+	}
 	path = btrfs_alloc_path();
 	if (!path) {
 		ret = -ENOMEM;

index 2f3b7be13bea..94eb7a8499db 100644
@@ -5194,6 +5194,36 @@ static int btrfs_ioctl_subvol_sync(struct btrfs_fs_info *fs_info, void __user *a
 	return 0;
 }
 
+#ifdef CONFIG_BTRFS_EXPERIMENTAL
+static int btrfs_emergency_shutdown(struct btrfs_fs_info *fs_info, u32 flags)
+{
+	int ret = 0;
+
+	if (flags >= BTRFS_SHUTDOWN_FLAGS_LAST)
+		return -EINVAL;
+
+	if (btrfs_is_shutdown(fs_info))
+		return 0;
+
+	switch (flags) {
+	case BTRFS_SHUTDOWN_FLAGS_LOGFLUSH:
+	case BTRFS_SHUTDOWN_FLAGS_DEFAULT:
+		ret = freeze_super(fs_info->sb, FREEZE_HOLDER_KERNEL, NULL);
+		if (ret)
+			return ret;
+		btrfs_force_shutdown(fs_info);
+		ret = thaw_super(fs_info->sb, FREEZE_HOLDER_KERNEL, NULL);
+		if (ret)
+			return ret;
+		break;
+	case BTRFS_SHUTDOWN_FLAGS_NOLOGFLUSH:
+		btrfs_force_shutdown(fs_info);
+		break;
+	}
+	return ret;
+}
+#endif
+
 long btrfs_ioctl(struct file *file, unsigned int
 		cmd, unsigned long arg)
 {

@@ -5201,6 +5231,8 @@ long btrfs_ioctl(struct file *file, unsigned int
 	struct btrfs_fs_info *fs_info = inode_to_fs_info(inode);
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	void __user *argp = (void __user *)arg;
+	/* If @arg is just an unsigned long value. */
+	unsigned long flags;
 
 	switch (cmd) {
 	case FS_IOC_GETVERSION:

@@ -5349,6 +5381,14 @@ long btrfs_ioctl(struct file *file, unsigned int
 #endif
 	case BTRFS_IOC_SUBVOL_SYNC_WAIT:
 		return btrfs_ioctl_subvol_sync(fs_info, argp);
+#ifdef CONFIG_BTRFS_EXPERIMENTAL
+	case BTRFS_IOC_SHUTDOWN:
+		if (!capable(CAP_SYS_ADMIN))
+			return -EPERM;
+		if (get_user(flags, (__u32 __user *)arg))
+			return -EFAULT;
+		return btrfs_emergency_shutdown(fs_info, flags);
+#endif
 	}
 
 	return -ENOTTY;

index dd02160015b2..8f6324cf15d9 100644
@@ -1096,6 +1096,12 @@ enum btrfs_err_code {
 	BTRFS_ERROR_DEV_RAID1C4_MIN_NOT_MET,
 };
 
+/* Flags for IOC_SHUTDOWN, should match XFS' flags. */
+#define BTRFS_SHUTDOWN_FLAGS_DEFAULT	0x0
+#define BTRFS_SHUTDOWN_FLAGS_LOGFLUSH	0x1
+#define BTRFS_SHUTDOWN_FLAGS_NOLOGFLUSH	0x2
+#define BTRFS_SHUTDOWN_FLAGS_LAST	0x3
+
 #define BTRFS_IOC_SNAP_CREATE _IOW(BTRFS_IOCTL_MAGIC, 1, \
 				   struct btrfs_ioctl_vol_args)
 #define BTRFS_IOC_DEFRAG _IOW(BTRFS_IOCTL_MAGIC, 2, \

@@ -1217,6 +1223,9 @@ enum btrfs_err_code {
 #define BTRFS_IOC_SUBVOL_SYNC_WAIT _IOW(BTRFS_IOCTL_MAGIC, 65, \
 					struct btrfs_ioctl_subvol_wait)
 
+/* Shutdown ioctl should follow XFS's interfaces, thus not using btrfs magic. */
+#define BTRFS_IOC_SHUTDOWN	_IOR('X', 125, __u32)
+
 #ifdef __cplusplus
 }
 #endif

index 727d5c1d1bf1..dd6e8a50ac39 100644
@@ -2421,6 +2421,60 @@ static long btrfs_free_cached_objects(struct super_block *sb, struct shrink_cont
 	return 0;
 }
 
+#ifdef CONFIG_BTRFS_EXPERIMENTAL
+static void btrfs_remove_bdev(struct super_block *sb, struct block_device *bdev)
+{
+	struct btrfs_fs_info *fs_info = btrfs_sb(sb);
+	struct btrfs_device *device;
+	struct btrfs_dev_lookup_args lookup_args = { .devt = bdev->bd_dev };
+	bool can_rw;
+
+	mutex_lock(&fs_info->fs_devices->device_list_mutex);
+	device = btrfs_find_device(fs_info->fs_devices, &lookup_args);
+	if (!device) {
+		mutex_unlock(&fs_info->fs_devices->device_list_mutex);
+		btrfs_warn(fs_info, "unable to find btrfs device for block device '%pg'",
+			   bdev);
+		return;
+	}
+	/*
+	 * The to-be-removed device is already missing?
+	 *
+	 * That's weird but no special handling needed and can exit right now.
+	 */
+	if (unlikely(test_and_set_bit(BTRFS_DEV_STATE_MISSING, &device->dev_state))) {
+		mutex_unlock(&fs_info->fs_devices->device_list_mutex);
+		btrfs_warn(fs_info, "btrfs device id %llu is already missing",
+			   device->devid);
+		return;
+	}
+
+	device->fs_devices->missing_devices++;
+	if (test_and_clear_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state)) {
+		list_del_init(&device->dev_alloc_list);
+		WARN_ON(device->fs_devices->rw_devices < 1);
+		device->fs_devices->rw_devices--;
+	}
+	can_rw = btrfs_check_rw_degradable(fs_info, device);
+	mutex_unlock(&fs_info->fs_devices->device_list_mutex);
+	/*
+	 * Now device is considered missing, btrfs_device_name() won't give a
+	 * meaningful result anymore, so only output the devid.
+	 */
+	if (!can_rw) {
+		btrfs_crit(fs_info,
+		"btrfs device id %llu has gone missing, can not maintain read-write",
+			   device->devid);
+		btrfs_force_shutdown(fs_info);
+		return;
+	}
+	btrfs_warn(fs_info,
+		   "btrfs device id %llu has gone missing, continue as degraded",
+		   device->devid);
+	btrfs_set_opt(fs_info->mount_opt, DEGRADED);
+}
+#endif
+
 static const struct super_operations btrfs_super_ops = {
 	.drop_inode	= btrfs_drop_inode,
 	.evict_inode	= btrfs_evict_inode,

@@ -2436,6 +2490,9 @@ static const struct super_operations btrfs_super_ops = {
 	.unfreeze_fs	= btrfs_unfreeze,
 	.nr_cached_objects = btrfs_nr_cached_objects,
 	.free_cached_objects = btrfs_free_cached_objects,
+#ifdef CONFIG_BTRFS_EXPERIMENTAL
+	.remove_bdev	= btrfs_remove_bdev,
+#endif
 };
 
 static const struct file_operations btrfs_ctl_fops = {

index 2098129743e7..340a1bb0c844 100644
@@ -6792,6 +6792,8 @@ static bool dev_args_match_fs_devices(const struct btrfs_dev_lookup_args *args,
 static bool dev_args_match_device(const struct btrfs_dev_lookup_args *args,
 				  const struct btrfs_device *device)
 {
+	if (args->devt)
+		return device->devt == args->devt;
 	if (args->missing) {
 		if (test_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &device->dev_state) &&
 		    !device->bdev)

index 6acb154ccf87..71e570f8337d 100644
@@ -663,6 +663,11 @@ struct btrfs_dev_lookup_args {
 	u64 devid;
 	u8 *uuid;
 	u8 *fsid;
+	/*
+	 * If devt is specified, all other members will be ignored as it is
+	 * enough to uniquely locate a device.
+	 */
+	dev_t devt;
 	bool missing;
 };