btrfs: add remove_bdev() callback

index 814bbc9417d2..777da6526bb2 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;

@@ -124,6 +125,12 @@ 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
 };
 

@@ -1120,6 +1127,27 @@ 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 a0cf8effe008..2f853de44473 100644
@@ -24,6 +24,7 @@ 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 dcbd038d1ad1..837da30303fd 100644
@@ -1440,6 +1440,8 @@ 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

@@ -2042,6 +2044,8 @@ static int btrfs_file_mmap_prepare(struct vm_area_desc *desc)
 	struct file *filp = desc->file;
 	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;
 

@@ -3101,6 +3105,9 @@ 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;

@@ -3792,6 +3799,9 @@ 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);

@@ -3804,6 +3814,9 @@ 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) ||

@@ -3814,10 +3827,20 @@ 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_prepare	= btrfs_file_mmap_prepare,

index 938286bee6a8..342c8412c859 100644
@@ -5077,6 +5077,9 @@ 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 5465a5eae9b2..1bbe3bb7e1bb 100644
@@ -868,6 +868,9 @@ 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 ac2fd589697d..509309edcf5d 100644
@@ -871,6 +871,9 @@ 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);
 
 	/*

@@ -1286,6 +1289,11 @@ 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;

@@ -2004,7 +2012,7 @@ 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()

@@ -2034,6 +2042,10 @@ 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 342c8412c859..80dffe5780b0 100644
@@ -5223,6 +5223,43 @@ static int btrfs_ioctl_subvol_sync(struct btrfs_fs_info *fs_info, void __user *a
 	return 0;
 }
 
+#ifdef CONFIG_BTRFS_EXPERIMENTAL
+static int btrfs_ioctl_shutdown(struct btrfs_fs_info *fs_info, unsigned long arg)
+{
+	int ret = 0;
+	uint32_t flags;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	if (get_user(flags, (uint32_t __user *)arg))
+		return -EFAULT;
+
+	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)
 {

@@ -5378,6 +5415,10 @@ 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:
+		return btrfs_ioctl_shutdown(fs_info, arg);
+#endif
 	}
 
 	return -ENOTTY;

index 8e710bbb688e..f40b300bd664 100644
@@ -1099,6 +1099,12 @@ 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, \

@@ -1220,6 +1226,9 @@ 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, uint32_t)
+
 #ifdef __cplusplus
 }
 #endif

index aadc02374b2a..b02ab17077af 100644
@@ -2424,6 +2424,68 @@ static long btrfs_free_cached_objects(struct super_block *sb, struct shrink_cont
 	return 0;
 }
 
+#ifdef CONFIG_BTRFS_EXPERIMENTAL
+static int 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);
+		/* Device not found, should not affect the running fs, just give a warning. */
+		btrfs_warn(fs_info, "unable to find btrfs device for block device '%pg'",
+			   bdev);
+		return 0;
+	}
+	/*
+	 * 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 0;
+	}
+
+	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);
+		return -EIO;
+	}
+	btrfs_warn(fs_info,
+		   "btrfs device id %llu has gone missing, continue as degraded",
+		   device->devid);
+	btrfs_set_opt(fs_info->mount_opt, DEGRADED);
+	return 0;
+}
+
+static void btrfs_shutdown(struct super_block *sb)
+{
+	struct btrfs_fs_info *fs_info = btrfs_sb(sb);
+
+	btrfs_force_shutdown(fs_info);
+}
+#endif
+
 static const struct super_operations btrfs_super_ops = {
 	.drop_inode	= btrfs_drop_inode,
 	.evict_inode	= btrfs_evict_inode,

@@ -2439,6 +2501,10 @@ 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,
+	.shutdown	= btrfs_shutdown,
+#endif
 };
 
 static const struct file_operations btrfs_ctl_fops = {

index 65b02a93db31..928fc6a061b6 100644
@@ -6802,6 +6802,8 @@ 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 2cbf8080eade..adbd9e6c09ff 100644
@@ -662,6 +662,11 @@ 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;
 };