Merge branch 'work.misc' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs

torvalds · torvalds · commit 5ceabb6078b8 · 2021-02-27T08:07:12.000-08:00
Pull misc vfs updates from Al Viro:
 "Assorted stuff pile - no common topic here"

* 'work.misc' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs:
  whack-a-mole: don't open-code iminor/imajor
  9p: fix misuse of sscanf() in v9fs_stat2inode()
  audit_alloc_mark(): don't open-code ERR_CAST()
  fs/inode.c: make inode_init_always() initialize i_ino to 0
  vfs: don't unnecessarily clone write access for writable fds
diff --git a/Documentation/filesystems/porting.rst b/Documentation/filesystems/porting.rst
@@ -883,3 +883,10 @@ For bvec based itererators bio_iov_iter_get_pages() now doesn't copy bvecs but
 uses the one provided. Anyone issuing kiocb-I/O should ensure that the bvec and
 page references stay until I/O has completed, i.e. until ->ki_complete() has
 been called or returned with non -EIOCBQUEUED code.
+
+---
+
+**mandatory**
+
+mnt_want_write_file() can now only be paired with mnt_drop_write_file(),
+whereas previously it could be paired with mnt_drop_write() as well.
diff --git a/arch/sh/boards/mach-landisk/gio.c b/arch/sh/boards/mach-landisk/gio.c
@@ -27,11 +27,10 @@ static int openCnt;
 
 static int gio_open(struct inode *inode, struct file *filp)
 {
-	int minor;
+	int minor = iminor(inode);
 	int ret = -ENOENT;
 
 	preempt_disable();
-	minor = MINOR(inode->i_rdev);
 	if (minor < DEVCOUNT) {
 		if (openCnt > 0) {
 			ret = -EALREADY;
@@ -46,9 +45,8 @@ static int gio_open(struct inode *inode, struct file *filp)
 
 static int gio_close(struct inode *inode, struct file *filp)
 {
-	int minor;
+	int minor = iminor(inode);
 
-	minor = MINOR(inode->i_rdev);
 	if (minor < DEVCOUNT) {
 		openCnt--;
 	}
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
@@ -663,7 +663,7 @@ static inline int is_loop_device(struct file *file)
 {
 	struct inode *i = file->f_mapping->host;
 
-	return i && S_ISBLK(i->i_mode) && MAJOR(i->i_rdev) == LOOP_MAJOR;
+	return i && S_ISBLK(i->i_mode) && imajor(i) == LOOP_MAJOR;
 }
 
 static int loop_validate_file(struct file *file, struct block_device *bdev)
diff --git a/drivers/dax/super.c b/drivers/dax/super.c
@@ -480,7 +480,7 @@ static void dax_free_inode(struct inode *inode)
 	kfree(dax_dev->host);
 	dax_dev->host = NULL;
 	if (inode->i_rdev)
-		ida_simple_remove(&dax_minor_ida, MINOR(inode->i_rdev));
+		ida_simple_remove(&dax_minor_ida, iminor(inode));
 	kmem_cache_free(dax_cache, dax_dev);
 }
 
diff --git a/drivers/rtc/rtc-m41t80.c b/drivers/rtc/rtc-m41t80.c
@@ -785,7 +785,7 @@ static long wdt_unlocked_ioctl(struct file *file, unsigned int cmd,
  */
 static int wdt_open(struct inode *inode, struct file *file)
 {
-	if (MINOR(inode->i_rdev) == WATCHDOG_MINOR) {
+	if (iminor(inode) == WATCHDOG_MINOR) {
 		mutex_lock(&m41t80_rtc_mutex);
 		if (test_and_set_bit(0, &wdt_is_open)) {
 			mutex_unlock(&m41t80_rtc_mutex);
@@ -809,7 +809,7 @@ static int wdt_open(struct inode *inode, struct file *file)
  */
 static int wdt_release(struct inode *inode, struct file *file)
 {
-	if (MINOR(inode->i_rdev) == WATCHDOG_MINOR)
+	if (iminor(inode) == WATCHDOG_MINOR)
 		clear_bit(0, &wdt_is_open);
 	return 0;
 }
diff --git a/drivers/s390/char/vmur.c b/drivers/s390/char/vmur.c
@@ -681,7 +681,7 @@ static int ur_open(struct inode *inode, struct file *file)
 	 * We treat the minor number as the devno of the ur device
 	 * to find in the driver tree.
 	 */
-	devno = MINOR(file_inode(file)->i_rdev);
+	devno = iminor(file_inode(file));
 
 	urd = urdev_get_from_devno(devno);
 	if (!urd) {
diff --git a/drivers/staging/vme/devices/vme_user.c b/drivers/staging/vme/devices/vme_user.c
@@ -175,7 +175,7 @@ static ssize_t buffer_from_user(unsigned int minor, const char __user *buf,
 static ssize_t vme_user_read(struct file *file, char __user *buf, size_t count,
 			     loff_t *ppos)
 {
-	unsigned int minor = MINOR(file_inode(file)->i_rdev);
+	unsigned int minor = iminor(file_inode(file));
 	ssize_t retval;
 	size_t image_size;
 
@@ -218,7 +218,7 @@ static ssize_t vme_user_read(struct file *file, char __user *buf, size_t count,
 static ssize_t vme_user_write(struct file *file, const char __user *buf,
 			      size_t count, loff_t *ppos)
 {
-	unsigned int minor = MINOR(file_inode(file)->i_rdev);
+	unsigned int minor = iminor(file_inode(file));
 	ssize_t retval;
 	size_t image_size;
 
@@ -260,7 +260,7 @@ static ssize_t vme_user_write(struct file *file, const char __user *buf,
 
 static loff_t vme_user_llseek(struct file *file, loff_t off, int whence)
 {
-	unsigned int minor = MINOR(file_inode(file)->i_rdev);
+	unsigned int minor = iminor(file_inode(file));
 	size_t image_size;
 	loff_t res;
 
@@ -294,7 +294,7 @@ static int vme_user_ioctl(struct inode *inode, struct file *file,
 	struct vme_slave slave;
 	struct vme_irq_id irq_req;
 	unsigned long copied;
-	unsigned int minor = MINOR(inode->i_rdev);
+	unsigned int minor = iminor(inode);
 	int retval;
 	dma_addr_t pci_addr;
 	void __user *argp = (void __user *)arg;
@@ -412,7 +412,7 @@ vme_user_unlocked_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 {
 	int ret;
 	struct inode *inode = file_inode(file);
-	unsigned int minor = MINOR(inode->i_rdev);
+	unsigned int minor = iminor(inode);
 
 	mutex_lock(&image[minor].mutex);
 	ret = vme_user_ioctl(inode, file, cmd, arg);
@@ -481,7 +481,7 @@ static int vme_user_master_mmap(unsigned int minor, struct vm_area_struct *vma)
 
 static int vme_user_mmap(struct file *file, struct vm_area_struct *vma)
 {
-	unsigned int minor = MINOR(file_inode(file)->i_rdev);
+	unsigned int minor = iminor(file_inode(file));
 
 	if (type[minor] == MASTER_MINOR)
 		return vme_user_master_mmap(minor, vma);
diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
@@ -1139,9 +1139,6 @@ v9fs_stat2inode(struct p9_wstat *stat, struct inode *inode,
 		 struct super_block *sb, unsigned int flags)
 {
 	umode_t mode;
-	char ext[32];
-	char tag_name[14];
-	unsigned int i_nlink;
 	struct v9fs_session_info *v9ses = sb->s_fs_info;
 	struct v9fs_inode *v9inode = V9FS_I(inode);
 
@@ -1159,18 +1156,18 @@ v9fs_stat2inode(struct p9_wstat *stat, struct inode *inode,
 		inode->i_gid = stat->n_gid;
 	}
 	if ((S_ISREG(inode->i_mode)) || (S_ISDIR(inode->i_mode))) {
-		if (v9fs_proto_dotu(v9ses) && (stat->extension[0] != '\0')) {
+		if (v9fs_proto_dotu(v9ses)) {
+			unsigned int i_nlink;
 			/*
-			 * Hadlink support got added later to
-			 * to the .u extension. So there can be
-			 * server out there that doesn't support
-			 * this even with .u extension. So check
-			 * for non NULL stat->extension
+			 * Hadlink support got added later to the .u extension.
+			 * So there can be a server out there that doesn't
+			 * support this even with .u extension. That would
+			 * just leave us with stat->extension being an empty
+			 * string, though.
 			 */
-			strlcpy(ext, stat->extension, sizeof(ext));
 			/* HARDLINKCOUNT %u */
-			sscanf(ext, "%13s %u", tag_name, &i_nlink);
-			if (!strncmp(tag_name, "HARDLINKCOUNT", 13))
+			if (sscanf(stat->extension,
+				   " HARDLINKCOUNT %u", &i_nlink) == 1)
 				set_nlink(inode, i_nlink);
 		}
 	}
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
@@ -491,8 +491,8 @@ static void init_dinode(struct gfs2_inode *dip, struct gfs2_inode *ip,
 	di = (struct gfs2_dinode *)dibh->b_data;
 	gfs2_dinode_out(ip, di);
 
-	di->di_major = cpu_to_be32(MAJOR(ip->i_inode.i_rdev));
-	di->di_minor = cpu_to_be32(MINOR(ip->i_inode.i_rdev));
+	di->di_major = cpu_to_be32(imajor(&ip->i_inode));
+	di->di_minor = cpu_to_be32(iminor(&ip->i_inode));
 	di->__pad1 = 0;
 	di->__pad2 = 0;
 	di->__pad3 = 0;
diff --git a/fs/inode.c b/fs/inode.c
@@ -142,6 +142,7 @@ int inode_init_always(struct super_block *sb, struct inode *inode)
 	atomic_set(&inode->i_count, 1);
 	inode->i_op = &empty_iops;
 	inode->i_fop = &no_open_fops;
+	inode->i_ino = 0;
 	inode->__i_nlink = 1;
 	inode->i_opflags = 0;
 	if (sb->s_xattr)
diff --git a/fs/jfs/super.c b/fs/jfs/super.c
@@ -551,7 +551,6 @@ static int jfs_fill_super(struct super_block *sb, void *data, int silent)
 		ret = -ENOMEM;
 		goto out_unload;
 	}
-	inode->i_ino = 0;
 	inode->i_size = i_size_read(sb->s_bdev->bd_inode);
 	inode->i_mapping->a_ops = &jfs_metapage_aops;
 	inode_fake_hash(inode);
diff --git a/fs/namespace.c b/fs/namespace.c
@@ -380,51 +380,37 @@ int mnt_want_write(struct vfsmount *m)
 }
 EXPORT_SYMBOL_GPL(mnt_want_write);
 
-/**
- * mnt_clone_write - get write access to a mount
- * @mnt: the mount on which to take a write
- *
- * This is effectively like mnt_want_write, except
- * it must only be used to take an extra write reference
- * on a mountpoint that we already know has a write reference
- * on it. This allows some optimisation.
- *
- * After finished, mnt_drop_write must be called as usual to
- * drop the reference.
- */
-int mnt_clone_write(struct vfsmount *mnt)
-{
-	/* superblock may be r/o */
-	if (__mnt_is_readonly(mnt))
-		return -EROFS;
-	preempt_disable();
-	mnt_inc_writers(real_mount(mnt));
-	preempt_enable();
-	return 0;
-}
-EXPORT_SYMBOL_GPL(mnt_clone_write);
-
 /**
  * __mnt_want_write_file - get write access to a file's mount
  * @file: the file who's mount on which to take a write
  *
- * This is like __mnt_want_write, but it takes a file and can
- * do some optimisations if the file is open for write already
+ * This is like __mnt_want_write, but if the file is already open for writing it
+ * skips incrementing mnt_writers (since the open file already has a reference)
+ * and instead only does the check for emergency r/o remounts.  This must be
+ * paired with __mnt_drop_write_file.
  */
 int __mnt_want_write_file(struct file *file)
 {
-	if (!(file->f_mode & FMODE_WRITER))
-		return __mnt_want_write(file->f_path.mnt);
-	else
-		return mnt_clone_write(file->f_path.mnt);
+	if (file->f_mode & FMODE_WRITER) {
+		/*
+		 * Superblock may have become readonly while there are still
+		 * writable fd's, e.g. due to a fs error with errors=remount-ro
+		 */
+		if (__mnt_is_readonly(file->f_path.mnt))
+			return -EROFS;
+		return 0;
+	}
+	return __mnt_want_write(file->f_path.mnt);
 }
 
 /**
  * mnt_want_write_file - get write access to a file's mount
  * @file: the file who's mount on which to take a write
  *
- * This is like mnt_want_write, but it takes a file and can
- * do some optimisations if the file is open for write already
+ * This is like mnt_want_write, but if the file is already open for writing it
+ * skips incrementing mnt_writers (since the open file already has a reference)
+ * and instead only does the freeze protection and the check for emergency r/o
+ * remounts.  This must be paired with mnt_drop_write_file.
  */
 int mnt_want_write_file(struct file *file)
 {
@@ -470,7 +456,8 @@ EXPORT_SYMBOL_GPL(mnt_drop_write);
 
 void __mnt_drop_write_file(struct file *file)
 {
-	__mnt_drop_write(file->f_path.mnt);
+	if (!(file->f_mode & FMODE_WRITER))
+		__mnt_drop_write(file->f_path.mnt);
 }
 
 void mnt_drop_write_file(struct file *file)
diff --git a/include/linux/mount.h b/include/linux/mount.h
@@ -86,7 +86,6 @@ struct path;
 
 extern int mnt_want_write(struct vfsmount *mnt);
 extern int mnt_want_write_file(struct file *file);
-extern int mnt_clone_write(struct vfsmount *mnt);
 extern void mnt_drop_write(struct vfsmount *mnt);
 extern void mnt_drop_write_file(struct file *file);
 extern void mntput(struct vfsmount *mnt);
diff --git a/kernel/audit_fsnotify.c b/kernel/audit_fsnotify.c
@@ -84,7 +84,7 @@ struct audit_fsnotify_mark *audit_alloc_mark(struct audit_krule *krule, char *pa
 
 	dentry = kern_path_locked(pathname, &path);
 	if (IS_ERR(dentry))
-		return (void *)dentry; /* returning an error */
+		return ERR_CAST(dentry); /* returning an error */
 	inode = path.dentry->d_inode;
 	inode_unlock(inode);
 

Original file line number	Diff line number	Diff line change
`@@ -27,11 +27,10 @@ static int openCnt;`
`27`	`27`
`28`	`28`	`static int gio_open(struct inode inode, struct file filp)`
`29`	`29`	`{`
`30`		`- int minor;`
	`30`	`+ int minor = iminor(inode);`
`31`	`31`	`int ret = -ENOENT;`
`32`	`32`
`33`	`33`	`preempt_disable();`
`34`		`- minor = MINOR(inode->i_rdev);`
`35`	`34`	`if (minor < DEVCOUNT) {`
`36`	`35`	`if (openCnt > 0) {`
`37`	`36`	`ret = -EALREADY;`
`@@ -46,9 +45,8 @@ static int gio_open(struct inode inode, struct file filp)`
`46`	`45`
`47`	`46`	`static int gio_close(struct inode inode, struct file filp)`
`48`	`47`	`{`
`49`		`- int minor;`
	`48`	`+ int minor = iminor(inode);`
`50`	`49`
`51`		`- minor = MINOR(inode->i_rdev);`
`52`	`50`	`if (minor < DEVCOUNT) {`
`53`	`51`	`openCnt--;`
`54`	`52`	`}`
Original file line number	Diff line number	Diff line change
`@@ -663,7 +663,7 @@ static inline int is_loop_device(struct file *file)`
`663`	`663`	`{`
`664`	`664`	`struct inode *i = file->f_mapping->host;`
`665`	`665`
`666`		`- return i && S_ISBLK(i->i_mode) && MAJOR(i->i_rdev) == LOOP_MAJOR;`
	`666`	`+ return i && S_ISBLK(i->i_mode) && imajor(i) == LOOP_MAJOR;`
`667`	`667`	`}`
`668`	`668`
`669`	`669`	`static int loop_validate_file(struct file file, struct block_device bdev)`
Original file line number	Diff line number	Diff line change
`@@ -480,7 +480,7 @@ static void dax_free_inode(struct inode *inode)`
`480`	`480`	`kfree(dax_dev->host);`
`481`	`481`	`dax_dev->host = NULL;`
`482`	`482`	`if (inode->i_rdev)`
`483`		`- ida_simple_remove(&dax_minor_ida, MINOR(inode->i_rdev));`
	`483`	`+ ida_simple_remove(&dax_minor_ida, iminor(inode));`
`484`	`484`	`kmem_cache_free(dax_cache, dax_dev);`
`485`	`485`	`}`
`486`	`486`
Original file line number	Diff line number	Diff line change
`@@ -785,7 +785,7 @@ static long wdt_unlocked_ioctl(struct file *file, unsigned int cmd,`
`785`	`785`	`*/`
`786`	`786`	`static int wdt_open(struct inode inode, struct file file)`
`787`	`787`	`{`
`788`		`- if (MINOR(inode->i_rdev) == WATCHDOG_MINOR) {`
	`788`	`+ if (iminor(inode) == WATCHDOG_MINOR) {`
`789`	`789`	`mutex_lock(&m41t80_rtc_mutex);`
`790`	`790`	`if (test_and_set_bit(0, &wdt_is_open)) {`
`791`	`791`	`mutex_unlock(&m41t80_rtc_mutex);`
`@@ -809,7 +809,7 @@ static int wdt_open(struct inode inode, struct file file)`
`809`	`809`	`*/`
`810`	`810`	`static int wdt_release(struct inode inode, struct file file)`
`811`	`811`	`{`
`812`		`- if (MINOR(inode->i_rdev) == WATCHDOG_MINOR)`
	`812`	`+ if (iminor(inode) == WATCHDOG_MINOR)`
`813`	`813`	`clear_bit(0, &wdt_is_open);`
`814`	`814`	`return 0;`
`815`	`815`	`}`