Merge tag 'v5.9-rc2' into drm-misc-fixes

Backmerge requested by Tomi for a fix to omap inconsistent
locking state issue, and because we need at least v5.9-rc2 now.

Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>

1 files changed, 73 insertions, 194 deletions

diff --git a/include/linux/fs.h b/include/linux/fs.h
index f5abba86107d..e019ea2f1347 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -175,6 +175,9 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
 /* File does not contribute to nr_files count */
 #define FMODE_NOACCOUNT		((__force fmode_t)0x20000000)
 
+/* File supports async buffered reads */
+#define FMODE_BUF_RASYNC	((__force fmode_t)0x40000000)
+
 /*
  * Flag for rw_copy_check_uvector and compat_rw_copy_check_uvector
  * that indicates that they should check the contents of the iovec are
@@ -315,6 +318,8 @@ enum rw_hint {
 #define IOCB_SYNC		(1 << 5)
 #define IOCB_WRITE		(1 << 6)
 #define IOCB_NOWAIT		(1 << 7)
+/* iocb->ki_waitq is valid */
+#define IOCB_WAITQ		(1 << 8)
 #define IOCB_NOIO		(1 << 9)
 
 struct kiocb {
@@ -329,7 +334,10 @@ struct kiocb {
 	int			ki_flags;
 	u16			ki_hint;
 	u16			ki_ioprio; /* See linux/ioprio.h */
-	unsigned int		ki_cookie; /* for ->iopoll */
+	union {
+		unsigned int		ki_cookie; /* for ->iopoll */
+		struct wait_page_queue	*ki_waitq; /* for async buffered IO */
+	};
 
 	randomized_struct_fields_end
 };
@@ -471,45 +479,6 @@ struct address_space {
 	 * must be enforced here for CRIS, to let the least significant bit
 	 * of struct page's "mapping" pointer be used for PAGE_MAPPING_ANON.
 	 */
-struct request_queue;
-
-struct block_device {
-	dev_t			bd_dev;  /* not a kdev_t - it's a search key */
-	int			bd_openers;
-	struct inode *		bd_inode;	/* will die */
-	struct super_block *	bd_super;
-	struct mutex		bd_mutex;	/* open/close mutex */
-	void *			bd_claiming;
-	void *			bd_holder;
-	int			bd_holders;
-	bool			bd_write_holder;
-#ifdef CONFIG_SYSFS
-	struct list_head	bd_holder_disks;
-#endif
-	struct block_device *	bd_contains;
-	unsigned		bd_block_size;
-	u8			bd_partno;
-	struct hd_struct *	bd_part;
-	/* number of times partitions within this device have been opened. */
-	unsigned		bd_part_count;
-	int			bd_invalidated;
-	struct gendisk *	bd_disk;
-	struct request_queue *  bd_queue;
-	struct backing_dev_info *bd_bdi;
-	struct list_head	bd_list;
-	/*
-	 * Private data.  You must have bd_claim'ed the block_device
-	 * to use this.  NOTE:  bd_claim allows an owner to claim
-	 * the same device multiple times, the owner must take special
-	 * care to not mess up bd_private for that case.
-	 */
-	unsigned long		bd_private;
-
-	/* The counter of freeze processes */
-	int			bd_fsfreeze_count;
-	/* Mutex for freeze */
-	struct mutex		bd_fsfreeze_mutex;
-} __randomize_layout;
 
 /* XArray tags, for tagging dirty and writeback pages in the pagecache. */
 #define PAGECACHE_TAG_DIRTY	XA_MARK_0
@@ -549,6 +518,16 @@ static inline void i_mmap_unlock_read(struct address_space *mapping)
 	up_read(&mapping->i_mmap_rwsem);
 }
 
+static inline void i_mmap_assert_locked(struct address_space *mapping)
+{
+	lockdep_assert_held(&mapping->i_mmap_rwsem);
+}
+
+static inline void i_mmap_assert_write_locked(struct address_space *mapping)
+{
+	lockdep_assert_held_write(&mapping->i_mmap_rwsem);
+}
+
 /*
  * Might pages of this file be mapped into userspace?
  */
@@ -559,7 +538,7 @@ static inline int mapping_mapped(struct address_space *mapping)
 
 /*
  * Might pages of this file have been modified in userspace?
- * Note that i_mmap_writable counts all VM_SHARED vmas: do_mmap_pgoff
+ * Note that i_mmap_writable counts all VM_SHARED vmas: do_mmap
  * marks vma as VM_SHARED if it is shared, and the file was opened for
  * writing i.e. vma may be mprotected writable even if now readonly.
  *
@@ -908,8 +887,6 @@ static inline unsigned imajor(const struct inode *inode)
 	return MAJOR(inode->i_rdev);
 }
 
-extern struct block_device *I_BDEV(struct inode *inode);
-
 struct fown_struct {
 	rwlock_t lock;          /* protects pid, uid, euid fields */
 	struct pid *pid;	/* pid or -pgrp where SIGIO should be sent */
@@ -1381,6 +1358,7 @@ extern int send_sigurg(struct fown_struct *fown);
 #define SB_NODIRATIME	2048	/* Do not update directory access times */
 #define SB_SILENT	32768
 #define SB_POSIXACL	(1<<16)	/* VFS does not apply the umask */
+#define SB_INLINECRYPT	(1<<17)	/* Use blk-crypto for encrypted files */
 #define SB_KERNMOUNT	(1<<22) /* this is a kern_mount call */
 #define SB_I_VERSION	(1<<23) /* Update inode I_version field */
 #define SB_LAZYTIME	(1<<25) /* Update the on-disk [acm]times lazily */
@@ -1744,6 +1722,10 @@ int vfs_mkobj(struct dentry *, umode_t,
 		int (*f)(struct dentry *, umode_t, void *),
 		void *);
 
+int vfs_fchown(struct file *file, uid_t user, gid_t group);
+int vfs_fchmod(struct file *file, umode_t mode);
+int vfs_utimes(const struct path *path, struct timespec64 *times);
+
 extern long vfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
 
 #ifdef CONFIG_COMPAT
@@ -1775,14 +1757,6 @@ struct dir_context {
 	loff_t pos;
 };
 
-struct block_device_operations;
-
-/* These macros are for out of kernel modules to test that
- * the kernel supports the unlocked_ioctl and compat_ioctl
- * fields in struct file_operations. */
-#define HAVE_COMPAT_IOCTL 1
-#define HAVE_UNLOCKED_IOCTL 1
-
 /*
  * These flags let !MMU mmap() govern direct device mapping vs immediate
  * copying more easily for MAP_PRIVATE, especially for ROM filesystems.
@@ -1982,27 +1956,27 @@ struct super_operations {
 /*
  * Inode flags - they have no relation to superblock flags now
  */
-#define S_SYNC		1	/* Writes are synced at once */
-#define S_NOATIME	2	/* Do not update access times */
-#define S_APPEND	4	/* Append-only file */
-#define S_IMMUTABLE	8	/* Immutable file */
-#define S_DEAD		16	/* removed, but still open directory */
-#define S_NOQUOTA	32	/* Inode is not counted to quota */
-#define S_DIRSYNC	64	/* Directory modifications are synchronous */
-#define S_NOCMTIME	128	/* Do not update file c/mtime */
-#define S_SWAPFILE	256	/* Do not truncate: swapon got its bmaps */
-#define S_PRIVATE	512	/* Inode is fs-internal */
-#define S_IMA		1024	/* Inode has an associated IMA struct */
-#define S_AUTOMOUNT	2048	/* Automount/referral quasi-directory */
-#define S_NOSEC		4096	/* no suid or xattr security attributes */
+#define S_SYNC		(1 << 0)  /* Writes are synced at once */
+#define S_NOATIME	(1 << 1)  /* Do not update access times */
+#define S_APPEND	(1 << 2)  /* Append-only file */
+#define S_IMMUTABLE	(1 << 3)  /* Immutable file */
+#define S_DEAD		(1 << 4)  /* removed, but still open directory */
+#define S_NOQUOTA	(1 << 5)  /* Inode is not counted to quota */
+#define S_DIRSYNC	(1 << 6)  /* Directory modifications are synchronous */
+#define S_NOCMTIME	(1 << 7)  /* Do not update file c/mtime */
+#define S_SWAPFILE	(1 << 8)  /* Do not truncate: swapon got its bmaps */
+#define S_PRIVATE	(1 << 9)  /* Inode is fs-internal */
+#define S_IMA		(1 << 10) /* Inode has an associated IMA struct */
+#define S_AUTOMOUNT	(1 << 11) /* Automount/referral quasi-directory */
+#define S_NOSEC		(1 << 12) /* no suid or xattr security attributes */
 #ifdef CONFIG_FS_DAX
-#define S_DAX		8192	/* Direct Access, avoiding the page cache */
+#define S_DAX		(1 << 13) /* Direct Access, avoiding the page cache */
 #else
-#define S_DAX		0	/* Make all the DAX code disappear */
+#define S_DAX		0	  /* Make all the DAX code disappear */
 #endif
-#define S_ENCRYPTED	16384	/* Encrypted file (using fs/crypto/) */
-#define S_CASEFOLD	32768	/* Casefolded file */
-#define S_VERITY	65536	/* Verity file (using fs/verity/) */
+#define S_ENCRYPTED	(1 << 14) /* Encrypted file (using fs/crypto/) */
+#define S_CASEFOLD	(1 << 15) /* Casefolded file */
+#define S_VERITY	(1 << 16) /* Verity file (using fs/verity/) */
 
 /*
  * Note that nosuid etc flags are inode-specific: setting some file-system
@@ -2264,18 +2238,9 @@ struct file_system_type {
 
 #define MODULE_ALIAS_FS(NAME) MODULE_ALIAS("fs-" NAME)
 
-#ifdef CONFIG_BLOCK
 extern struct dentry *mount_bdev(struct file_system_type *fs_type,
 	int flags, const char *dev_name, void *data,
 	int (*fill_super)(struct super_block *, void *, int));
-#else
-static inline struct dentry *mount_bdev(struct file_system_type *fs_type,
-	int flags, const char *dev_name, void *data,
-	int (*fill_super)(struct super_block *, void *, int))
-{
-	return ERR_PTR(-ENODEV);
-}
-#endif
 extern struct dentry *mount_single(struct file_system_type *fs_type,
 	int flags, void *data,
 	int (*fill_super)(struct super_block *, void *, int));
@@ -2284,14 +2249,7 @@ extern struct dentry *mount_nodev(struct file_system_type *fs_type,
 	int (*fill_super)(struct super_block *, void *, int));
 extern struct dentry *mount_subtree(struct vfsmount *mnt, const char *path);
 void generic_shutdown_super(struct super_block *sb);
-#ifdef CONFIG_BLOCK
 void kill_block_super(struct super_block *sb);
-#else
-static inline void kill_block_super(struct super_block *sb)
-{
-	BUG();
-}
-#endif
 void kill_anon_super(struct super_block *sb);
 void kill_litter_super(struct super_block *sb);
 void deactivate_super(struct super_block *sb);
@@ -2581,93 +2539,16 @@ extern struct kmem_cache *names_cachep;
 #define __getname()		kmem_cache_alloc(names_cachep, GFP_KERNEL)
 #define __putname(name)		kmem_cache_free(names_cachep, (void *)(name))
 
-#ifdef CONFIG_BLOCK
-extern int register_blkdev(unsigned int, const char *);
-extern void unregister_blkdev(unsigned int, const char *);
-extern struct block_device *bdget(dev_t);
-extern struct block_device *bdgrab(struct block_device *bdev);
-extern void bd_set_size(struct block_device *, loff_t size);
-extern void bd_forget(struct inode *inode);
-extern void bdput(struct block_device *);
-extern void invalidate_bdev(struct block_device *);
-extern void iterate_bdevs(void (*)(struct block_device *, void *), void *);
-extern int sync_blockdev(struct block_device *bdev);
-extern struct super_block *freeze_bdev(struct block_device *);
-extern void emergency_thaw_all(void);
-extern void emergency_thaw_bdev(struct super_block *sb);
-extern int thaw_bdev(struct block_device *bdev, struct super_block *sb);
-extern int fsync_bdev(struct block_device *);
-
 extern struct super_block *blockdev_superblock;
-
 static inline bool sb_is_blkdev_sb(struct super_block *sb)
 {
-	return sb == blockdev_superblock;
-}
-#else
-static inline void bd_forget(struct inode *inode) {}
-static inline int sync_blockdev(struct block_device *bdev) { return 0; }
-static inline void invalidate_bdev(struct block_device *bdev) {}
-
-static inline struct super_block *freeze_bdev(struct block_device *sb)
-{
-	return NULL;
-}
-
-static inline int thaw_bdev(struct block_device *bdev, struct super_block *sb)
-{
-	return 0;
+	return IS_ENABLED(CONFIG_BLOCK) && sb == blockdev_superblock;
 }
 
-static inline int emergency_thaw_bdev(struct super_block *sb)
-{
-	return 0;
-}
-
-static inline void iterate_bdevs(void (*f)(struct block_device *, void *), void *arg)
-{
-}
-
-static inline bool sb_is_blkdev_sb(struct super_block *sb)
-{
-	return false;
-}
-#endif
+void emergency_thaw_all(void);
 extern int sync_filesystem(struct super_block *);
 extern const struct file_operations def_blk_fops;
 extern const struct file_operations def_chr_fops;
-#ifdef CONFIG_BLOCK
-extern int blkdev_ioctl(struct block_device *, fmode_t, unsigned, unsigned long);
-extern long compat_blkdev_ioctl(struct file *, unsigned, unsigned long);
-extern int blkdev_get(struct block_device *bdev, fmode_t mode, void *holder);
-extern struct block_device *blkdev_get_by_path(const char *path, fmode_t mode,
-					       void *holder);
-extern struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode,
-					      void *holder);
-extern struct block_device *bd_start_claiming(struct block_device *bdev,
-					      void *holder);
-extern void bd_finish_claiming(struct block_device *bdev,
-			       struct block_device *whole, void *holder);
-extern void bd_abort_claiming(struct block_device *bdev,
-			      struct block_device *whole, void *holder);
-extern void blkdev_put(struct block_device *bdev, fmode_t mode);
-
-#ifdef CONFIG_SYSFS
-extern int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk);
-extern void bd_unlink_disk_holder(struct block_device *bdev,
-				  struct gendisk *disk);
-#else
-static inline int bd_link_disk_holder(struct block_device *bdev,
-				      struct gendisk *disk)
-{
-	return 0;
-}
-static inline void bd_unlink_disk_holder(struct block_device *bdev,
-					 struct gendisk *disk)
-{
-}
-#endif
-#endif
 
 /* fs/char_dev.c */
 #define CHRDEV_MAJOR_MAX 512
@@ -2698,31 +2579,12 @@ static inline void unregister_chrdev(unsigned int major, const char *name)
 	__unregister_chrdev(major, 0, 256, name);
 }
 
-/* fs/block_dev.c */
-#define BDEVNAME_SIZE	32	/* Largest string for a blockdev identifier */
-#define BDEVT_SIZE	10	/* Largest string for MAJ:MIN for blkdev */
-
-#ifdef CONFIG_BLOCK
-#define BLKDEV_MAJOR_MAX	512
-extern const char *bdevname(struct block_device *bdev, char *buffer);
-extern struct block_device *lookup_bdev(const char *);
-extern void blkdev_show(struct seq_file *,off_t);
-
-#else
-#define BLKDEV_MAJOR_MAX	0
-#endif
-
 extern void init_special_inode(struct inode *, umode_t, dev_t);
 
 /* Invalid inode operations -- fs/bad_inode.c */
 extern void make_bad_inode(struct inode *);
 extern bool is_bad_inode(struct inode *);
 
-#ifdef CONFIG_BLOCK
-extern int revalidate_disk(struct gendisk *);
-extern int check_disk_change(struct block_device *);
-extern int __invalidate_device(struct block_device *, bool);
-#endif
 unsigned long invalidate_mapping_pages(struct address_space *mapping,
 					pgoff_t start, pgoff_t end);
 
@@ -2798,7 +2660,7 @@ static inline void filemap_set_wb_err(struct address_space *mapping, int err)
 }
 
 /**
- * filemap_check_wb_error - has an error occurred since the mark was sampled?
+ * filemap_check_wb_err - has an error occurred since the mark was sampled?
  * @mapping: mapping to check for writeback errors
  * @since: previously-sampled errseq_t
  *
@@ -2827,7 +2689,7 @@ static inline errseq_t filemap_sample_wb_err(struct address_space *mapping)
 
 /**
  * file_sample_sb_err - sample the current errseq_t to test for later errors
- * @mapping: mapping to be sampled
+ * @file: file pointer to be sampled
  *
  * Grab the most current superblock-level errseq_t value for the given
  * struct file.
@@ -3098,6 +2960,21 @@ extern void discard_new_inode(struct inode *);
 extern unsigned int get_next_ino(void);
 extern void evict_inodes(struct super_block *sb);
 
+/*
+ * Userspace may rely on the the inode number being non-zero. For example, glibc
+ * simply ignores files with zero i_ino in unlink() and other places.
+ *
+ * As an additional complication, if userspace was compiled with
+ * _FILE_OFFSET_BITS=32 on a 64-bit kernel we'll only end up reading out the
+ * lower 32 bits, so we need to check that those aren't zero explicitly. With
+ * _FILE_OFFSET_BITS=64, this may cause some harmless false-negatives, but
+ * better safe than sorry.
+ */
+static inline bool is_zero_ino(ino_t ino)
+{
+	return (u32)ino == 0;
+}
+
 extern void __iget(struct inode * inode);
 extern void iget_failed(struct inode *);
 extern void clear_inode(struct inode *);
@@ -3123,10 +3000,6 @@ static inline void remove_inode_hash(struct inode *inode)
 
 extern void inode_sb_list_add(struct inode *inode);
 
-#ifdef CONFIG_BLOCK
-extern int bdev_read_only(struct block_device *);
-#endif
-extern int set_blocksize(struct block_device *, int);
 extern int sb_set_blocksize(struct super_block *, int);
 extern int sb_min_blocksize(struct super_block *, int);
 
@@ -3439,22 +3312,28 @@ static inline int iocb_flags(struct file *file)
 
 static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags)
 {
+	int kiocb_flags = 0;
+
+	if (!flags)
+		return 0;
 	if (unlikely(flags & ~RWF_SUPPORTED))
 		return -EOPNOTSUPP;
 
 	if (flags & RWF_NOWAIT) {
 		if (!(ki->ki_filp->f_mode & FMODE_NOWAIT))
 			return -EOPNOTSUPP;
-		ki->ki_flags |= IOCB_NOWAIT;
+		kiocb_flags |= IOCB_NOWAIT | IOCB_NOIO;
 	}
 	if (flags & RWF_HIPRI)
-		ki->ki_flags |= IOCB_HIPRI;
+		kiocb_flags |= IOCB_HIPRI;
 	if (flags & RWF_DSYNC)
-		ki->ki_flags |= IOCB_DSYNC;
+		kiocb_flags |= IOCB_DSYNC;
 	if (flags & RWF_SYNC)
-		ki->ki_flags |= (IOCB_DSYNC | IOCB_SYNC);
+		kiocb_flags |= (IOCB_DSYNC | IOCB_SYNC);
 	if (flags & RWF_APPEND)
-		ki->ki_flags |= IOCB_APPEND;
+		kiocb_flags |= IOCB_APPEND;
+
+	ki->ki_flags |= kiocb_flags;
 	return 0;
 }