exfat: Implement sops->shutdown and ioctl

mainline inclusion
from mainline-v6.12-rc1

[ Upstream commit f761fcdd289d07e8547fef7ac76c3760fc7803f2 ]

We found that when writing a large file through buffer write, if the
disk is inaccessible, exFAT does not return an error normally, which
leads to the writing process not stopping properly.

To easily reproduce this issue, you can follow the steps below:

1. format a device to exFAT and then mount (with a full disk erase)
2. dd if=/dev/zero of=/exfat_mount/test.img bs=1M count=8192
3. eject the device

You may find that the dd process does not stop immediately and may
continue for a long time.

The root cause of this issue is that during buffer write process,
exFAT does not need to access the disk to look up directory entries
or the FAT table (whereas FAT would do) every time data is written.
Instead, exFAT simply marks the buffer as dirty and returns,
delegating the writeback operation to the writeback process.

If the disk cannot be accessed at this time, the error will only be
returned to the writeback process, and the original process will not
receive the error, so it cannot be returned to the user side.

When the disk cannot be accessed normally, an error should be returned
to stop the writing process.

Implement sops->shutdown and ioctl to shut down the file system
when underlying block device is marked dead.

Signed-off-by: Dongliang Cui <[email protected]>
Signed-off-by: Zhiguo Niu <[email protected]>
Signed-off-by: Namjae Jeon <[email protected]>
(cherry picked from commit f761fcdd289d07e8547fef7ac76c3760fc7803f2)

[dongliang.cui: bdev_freeze & bdev_thaw has a different name in k66
 and mainline, make adaptation modifications.
 Resolve conflicts in 'fs/exfat/inode.c' and 'fs/exfat/namei.c'.]

Change-Id: Icb7ece39d885cded6d54557c382e84b222f8cada
Signed-off-by: dongliang.cui <[email protected]>
(cherry picked from commit 3326d8c45d52d83bd6dd57405e99c1f6938ce18f)

fs/exfat/exfat_fs.h

@@ -10,6 +10,7 @@
 #include <linux/ratelimit.h>
 #include <linux/nls.h>
 #include <linux/blkdev.h>
+#include <uapi/linux/exfat.h>
 
 #define EXFAT_ROOT_INO		1
 
@@ -149,6 +150,9 @@ enum {
 #define DIR_CACHE_SIZE		\
 	(DIV_ROUND_UP(EXFAT_DEN_TO_B(ES_MAX_ENTRY_NUM), SECTOR_SIZE) + 1)
 
+/* Superblock flags */
+#define EXFAT_FLAGS_SHUTDOWN	1
+
 struct exfat_dentry_namebuf {
 	char *lfn;
 	int lfnbuf_len; /* usually MAX_UNINAME_BUF_SIZE */
@@ -265,6 +269,8 @@ struct exfat_sb_info {
 	unsigned int clu_srch_ptr; /* cluster search pointer */
 	unsigned int used_clusters; /* number of used clusters */
 
+	unsigned long s_exfat_flags; /* Exfat superblock flags */
+
 	struct mutex s_lock; /* superblock lock */
 	struct mutex bitmap_lock; /* bitmap lock */
 	struct exfat_mount_options options;
@@ -334,6 +340,11 @@ static inline struct exfat_inode_info *EXFAT_I(struct inode *inode)
 	return container_of(inode, struct exfat_inode_info, vfs_inode);
 }
 
+static inline int exfat_forced_shutdown(struct super_block *sb)
+{
+	return test_bit(EXFAT_FLAGS_SHUTDOWN, &EXFAT_SB(sb)->s_exfat_flags);
+}
+
 /*
  * If ->i_mode can't hold 0222 (i.e. ATTR_RO), we use ->i_attrs to
  * save ATTR_RO instead of ->i_mode.
@@ -459,6 +470,7 @@ int exfat_file_fsync(struct file *file, loff_t start, loff_t end, int datasync);
 long exfat_ioctl(struct file *filp, unsigned int cmd, unsigned long arg);
 long exfat_compat_ioctl(struct file *filp, unsigned int cmd,
 				unsigned long arg);
+int exfat_force_shutdown(struct super_block *sb, u32 flags);
 
 /* namei.c */
 extern const struct dentry_operations exfat_dentry_ops;

fs/exfat/file.c

@@ -249,6 +249,9 @@ int exfat_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 	unsigned int ia_valid;
 	int error;
 
+	if (unlikely(exfat_forced_shutdown(inode->i_sb)))
+		return -EIO;
+
 	if ((attr->ia_valid & ATTR_SIZE) &&
 	    attr->ia_size > i_size_read(inode)) {
 		error = exfat_cont_expand(inode, attr->ia_size);
@@ -343,11 +346,26 @@ static int exfat_ioctl_fitrim(struct inode *inode, unsigned long arg)
 	return 0;
 }
 
+static int exfat_ioctl_shutdown(struct super_block *sb, unsigned long arg)
+{
+	u32 flags;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	if (get_user(flags, (__u32 __user *)arg))
+		return -EFAULT;
+
+	return exfat_force_shutdown(sb, flags);
+}
+
 long exfat_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 {
 	struct inode *inode = file_inode(filp);
 
 	switch (cmd) {
+	case EXFAT_IOC_SHUTDOWN:
+		return exfat_ioctl_shutdown(inode->i_sb, arg);
 	case FITRIM:
 		return exfat_ioctl_fitrim(inode, arg);
 	default:
@@ -368,6 +386,9 @@ int exfat_file_fsync(struct file *filp, loff_t start, loff_t end, int datasync)
 	struct inode *inode = filp->f_mapping->host;
 	int err;
 
+	if (unlikely(exfat_forced_shutdown(inode->i_sb)))
+		return -EIO;
+
 	err = __generic_file_fsync(filp, start, end, datasync);
 	if (err)
 		return err;

fs/exfat/inode.c

@@ -90,6 +90,9 @@ int exfat_write_inode(struct inode *inode, struct writeback_control *wbc)
 {
 	int ret;
 
+	if (unlikely(exfat_forced_shutdown(inode->i_sb)))
+		return -EIO;
+
 	mutex_lock(&EXFAT_SB(inode->i_sb)->s_lock);
 	ret = __exfat_write_inode(inode, wbc->sync_mode == WB_SYNC_ALL);
 	mutex_unlock(&EXFAT_SB(inode->i_sb)->s_lock);
@@ -346,6 +349,9 @@ static void exfat_readahead(struct readahead_control *rac)
 static int exfat_writepages(struct address_space *mapping,
 		struct writeback_control *wbc)
 {
+	if (unlikely(exfat_forced_shutdown(mapping->host->i_sb)))
+		return -EIO;
+
 	return mpage_writepages(mapping, wbc, exfat_get_block);
 }
 
@@ -366,6 +372,9 @@ static int exfat_write_begin(struct file *file, struct address_space *mapping,
 {
 	int ret;
 
+	if (unlikely(exfat_forced_shutdown(mapping->host->i_sb)))
+		return -EIO;
+
 	*pagep = NULL;
 	ret = cont_write_begin(file, mapping, pos, len, pagep, fsdata,
 			       exfat_get_block,

fs/exfat/namei.c

@@ -572,6 +572,9 @@ static int exfat_create(struct mnt_idmap *idmap, struct inode *dir,
 	loff_t i_pos;
 	int err;
 
+	if (unlikely(exfat_forced_shutdown(sb)))
+		return -EIO;
+
 	mutex_lock(&EXFAT_SB(sb)->s_lock);
 	exfat_set_volume_dirty(sb);
 	err = exfat_add_entry(dir, dentry->d_name.name, &cdir, TYPE_FILE,
@@ -793,6 +796,9 @@ static int exfat_unlink(struct inode *dir, struct dentry *dentry)
 	struct buffer_head *bh;
 	int num_entries, entry, err = 0;
 
+	if (unlikely(exfat_forced_shutdown(sb)))
+		return -EIO;
+
 	mutex_lock(&EXFAT_SB(sb)->s_lock);
 	exfat_chain_dup(&cdir, &ei->dir);
 	entry = ei->entry;
@@ -854,6 +860,9 @@ static int exfat_mkdir(struct mnt_idmap *idmap, struct inode *dir,
 	loff_t i_pos;
 	int err;
 
+	if (unlikely(exfat_forced_shutdown(sb)))
+		return -EIO;
+
 	mutex_lock(&EXFAT_SB(sb)->s_lock);
 	exfat_set_volume_dirty(sb);
 	err = exfat_add_entry(dir, dentry->d_name.name, &cdir, TYPE_DIR,
@@ -945,6 +954,9 @@ static int exfat_rmdir(struct inode *dir, struct dentry *dentry)
 	struct buffer_head *bh;
 	int num_entries, entry, err;
 
+	if (unlikely(exfat_forced_shutdown(sb)))
+		return -EIO;
+
 	mutex_lock(&EXFAT_SB(inode->i_sb)->s_lock);
 
 	exfat_chain_dup(&cdir, &ei->dir);
@@ -1019,6 +1031,9 @@ static int exfat_rename_file(struct inode *inode, struct exfat_chain *p_dir,
 	struct buffer_head *new_bh, *old_bh;
 	int sync = IS_DIRSYNC(inode);
 
+	if (unlikely(exfat_forced_shutdown(sb)))
+		return -EIO;
+
 	epold = exfat_get_dentry(sb, p_dir, oldentry, &old_bh);
 	if (!epold)
 		return -EIO;

fs/exfat/super.c

@@ -49,6 +49,9 @@ static int exfat_sync_fs(struct super_block *sb, int wait)
 	struct exfat_sb_info *sbi = EXFAT_SB(sb);
 	int err = 0;
 
+	if (unlikely(exfat_forced_shutdown(sb)))
+		return 0;
+
 	if (!wait)
 		return 0;
 
@@ -168,6 +171,41 @@ static int exfat_show_options(struct seq_file *m, struct dentry *root)
 	return 0;
 }
 
+int exfat_force_shutdown(struct super_block *sb, u32 flags)
+{
+	int ret;
+	struct exfat_sb_info *sbi = sb->s_fs_info;
+	struct exfat_mount_options *opts = &sbi->options;
+
+	if (exfat_forced_shutdown(sb))
+		return 0;
+
+	switch (flags) {
+	case EXFAT_GOING_DOWN_DEFAULT:
+	case EXFAT_GOING_DOWN_FULLSYNC:
+		ret = freeze_bdev(sb->s_bdev);
+		if (ret)
+			return ret;
+		thaw_bdev(sb->s_bdev);
+		set_bit(EXFAT_FLAGS_SHUTDOWN, &sbi->s_exfat_flags);
+		break;
+	case EXFAT_GOING_DOWN_NOSYNC:
+		set_bit(EXFAT_FLAGS_SHUTDOWN, &sbi->s_exfat_flags);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (opts->discard)
+		opts->discard = 0;
+	return 0;
+}
+
+static void exfat_shutdown(struct super_block *sb)
+{
+	exfat_force_shutdown(sb, EXFAT_GOING_DOWN_NOSYNC);
+}
+
 static struct inode *exfat_alloc_inode(struct super_block *sb)
 {
 	struct exfat_inode_info *ei;
@@ -194,6 +232,7 @@ static const struct super_operations exfat_sops = {
 	.sync_fs	= exfat_sync_fs,
 	.statfs		= exfat_statfs,
 	.show_options	= exfat_show_options,
+	.shutdown	= exfat_shutdown,
 };
 
 enum {

include/uapi/linux/exfat.h

@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * Copyright (C) 2024 Unisoc Technologies Co., Ltd.
+ */
+
+#ifndef _UAPI_LINUX_EXFAT_H
+#define _UAPI_LINUX_EXFAT_H
+#include <linux/types.h>
+#include <linux/ioctl.h>
+
+/*
+ * exfat-specific ioctl commands
+ */
+
+#define EXFAT_IOC_SHUTDOWN _IOR('X', 125, __u32)
+
+/*
+ * Flags used by EXFAT_IOC_SHUTDOWN
+ */
+
+#define EXFAT_GOING_DOWN_DEFAULT	0x0	/* default with full sync */
+#define EXFAT_GOING_DOWN_FULLSYNC	0x1     /* going down with full sync*/
+#define EXFAT_GOING_DOWN_NOSYNC         0x2     /* going down */
+
+#endif /* _UAPI_LINUX_EXFAT_H */