*/
if ((ei->i_reserved_data_blocks == 0) &&
!inode_is_open_for_write(inode))
- ext4_discard_preallocations(inode);
+ ext4_discard_preallocations(inode, 0);
}
static int __check_block_validity(struct inode *inode, const char *func,
(inode->i_ino ==
le32_to_cpu(EXT4_SB(inode->i_sb)->s_es->s_journal_inum)))
return 0;
- if (!ext4_data_block_valid(EXT4_SB(inode->i_sb), map->m_pblk,
- map->m_len)) {
+ if (!ext4_inode_block_valid(inode, map->m_pblk, map->m_len)) {
ext4_error_inode(inode, func, line, map->m_pblk,
"lblock %lu mapped to illegal pblock %llu "
"(length %d)", (unsigned long) map->m_lblk,
}
if (unlikely(err)) {
page_zero_new_buffers(page, from, to);
- } else if (IS_ENCRYPTED(inode) && S_ISREG(inode->i_mode)) {
+ } else if (fscrypt_inode_uses_fs_layer_crypto(inode)) {
for (i = 0; i < nr_wait; i++) {
int err2;
if (PageChecked(page))
return 0;
if (journal)
- return jbd2_journal_try_to_free_buffers(journal, page, wait);
+ return jbd2_journal_try_to_free_buffers(journal, page);
else
return try_to_free_buffers(page);
}
/* Uhhuh. Read error. Complain and punt. */
if (!buffer_uptodate(bh))
goto unlock;
- if (S_ISREG(inode->i_mode) && IS_ENCRYPTED(inode)) {
+ if (fscrypt_inode_uses_fs_layer_crypto(inode)) {
/* We expect the key to be set. */
BUG_ON(!fscrypt_has_encryption_key(inode));
err = fscrypt_decrypt_pagecache_blocks(page, blocksize,
if (stop_block > first_block) {
down_write(&EXT4_I(inode)->i_data_sem);
- ext4_discard_preallocations(inode);
+ ext4_discard_preallocations(inode, 0);
ret = ext4_es_remove_extent(inode, first_block,
stop_block - first_block);
trace_ext4_truncate_enter(inode);
if (!ext4_can_truncate(inode))
- return 0;
+ goto out_trace;
if (inode->i_size == 0 && !test_opt(inode->i_sb, NO_AUTO_DA_ALLOC))
ext4_set_inode_state(inode, EXT4_STATE_DA_ALLOC_CLOSE);
int has_inline = 1;
err = ext4_inline_data_truncate(inode, &has_inline);
- if (err)
- return err;
- if (has_inline)
- return 0;
+ if (err || has_inline)
+ goto out_trace;
}
/* If we zero-out tail of the page, we have to create jinode for jbd2 */
if (inode->i_size & (inode->i_sb->s_blocksize - 1)) {
if (ext4_inode_attach_jinode(inode) < 0)
- return 0;
+ goto out_trace;
}
if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
credits = ext4_blocks_for_truncate(inode);
handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, credits);
- if (IS_ERR(handle))
- return PTR_ERR(handle);
+ if (IS_ERR(handle)) {
+ err = PTR_ERR(handle);
+ goto out_trace;
+ }
if (inode->i_size & (inode->i_sb->s_blocksize - 1))
ext4_block_truncate_page(handle, mapping, inode->i_size);
down_write(&EXT4_I(inode)->i_data_sem);
- ext4_discard_preallocations(inode);
+ ext4_discard_preallocations(inode, 0);
if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
err = ext4_ext_truncate(handle, inode);
err = err2;
ext4_journal_stop(handle);
+out_trace:
trace_ext4_truncate_exit(inode);
return err;
}
!ext4_test_inode_state(inode, EXT4_STATE_XATTR));
}
-static bool ext4_should_use_dax(struct inode *inode)
+static bool ext4_should_enable_dax(struct inode *inode)
{
- if (!test_opt(inode->i_sb, DAX))
+ struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+
+ if (test_opt2(inode->i_sb, DAX_NEVER))
return false;
if (!S_ISREG(inode->i_mode))
return false;
return false;
if (ext4_test_inode_flag(inode, EXT4_INODE_VERITY))
return false;
- return true;
+ if (!test_bit(EXT4_FLAGS_BDEV_IS_DAX, &sbi->s_ext4_flags))
+ return false;
+ if (test_opt(inode->i_sb, DAX_ALWAYS))
+ return true;
+
+ return ext4_test_inode_flag(inode, EXT4_INODE_DAX);
}
-void ext4_set_inode_flags(struct inode *inode)
+void ext4_set_inode_flags(struct inode *inode, bool init)
{
unsigned int flags = EXT4_I(inode)->i_flags;
unsigned int new_fl = 0;
+ WARN_ON_ONCE(IS_DAX(inode) && init);
+
if (flags & EXT4_SYNC_FL)
new_fl |= S_SYNC;
if (flags & EXT4_APPEND_FL)
new_fl |= S_NOATIME;
if (flags & EXT4_DIRSYNC_FL)
new_fl |= S_DIRSYNC;
- if (ext4_should_use_dax(inode))
+
+ /* Because of the way inode_set_flags() works we must preserve S_DAX
+ * here if already set. */
+ new_fl |= (inode->i_flags & S_DAX);
+ if (init && ext4_should_enable_dax(inode))
new_fl |= S_DAX;
+
if (flags & EXT4_ENCRYPT_FL)
new_fl |= S_ENCRYPTED;
if (flags & EXT4_CASEFOLD_FL)
* not initialized on a new filesystem. */
}
ei->i_flags = le32_to_cpu(raw_inode->i_flags);
- ext4_set_inode_flags(inode);
+ ext4_set_inode_flags(inode, true);
inode->i_blocks = ext4_inode_blocks(raw_inode, ei);
ei->i_file_acl = le32_to_cpu(raw_inode->i_file_acl_lo);
if (ext4_has_feature_64bit(sb))
ret = 0;
if (ei->i_file_acl &&
- !ext4_data_block_valid(EXT4_SB(sb), ei->i_file_acl, 1)) {
+ !ext4_inode_block_valid(inode, ei->i_file_acl, 1)) {
ext4_error_inode(inode, function, line, 0,
"iget: bad extended attribute block %llu",
ei->i_file_acl);
(inode->i_state & I_DIRTY_TIME)) {
struct ext4_inode_info *ei = EXT4_I(inode);
- inode->i_state &= ~(I_DIRTY_TIME | I_DIRTY_TIME_EXPIRED);
+ inode->i_state &= ~I_DIRTY_TIME;
spin_unlock(&inode->i_lock);
spin_lock(&ei->i_raw_lock);
#include "xfs_shared.h"
#include "xfs_format.h"
#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
#include "xfs_inode.h"
#include "xfs_trans.h"
#include "xfs_trans_priv.h"
ASSERT(iip->ili_lock_flags == 0);
iip->ili_lock_flags = lock_flags;
+ ASSERT(!xfs_iflags_test(ip, XFS_ISTALE));
/*
* Get a log_item_desc to point at the new item.
}
/*
- * This is called to mark the fields indicated in fieldmask as needing
- * to be logged when the transaction is committed. The inode must
- * already be associated with the given transaction.
+ * This is called to mark the fields indicated in fieldmask as needing to be
+ * logged when the transaction is committed. The inode must already be
+ * associated with the given transaction.
*
- * The values for fieldmask are defined in xfs_inode_item.h. We always
- * log all of the core inode if any of it has changed, and we always log
- * all of the inline data/extents/b-tree root if any of them has changed.
+ * The values for fieldmask are defined in xfs_inode_item.h. We always log all
+ * of the core inode if any of it has changed, and we always log all of the
+ * inline data/extents/b-tree root if any of them has changed.
+ *
+ * Grab and pin the cluster buffer associated with this inode to avoid RMW
+ * cycles at inode writeback time. Avoid the need to add error handling to every
+ * xfs_trans_log_inode() call by shutting down on read error. This will cause
+ * transactions to fail and everything to error out, just like if we return a
+ * read error in a dirty transaction and cancel it.
*/
void
xfs_trans_log_inode(
- xfs_trans_t *tp,
- xfs_inode_t *ip,
- uint flags)
+ struct xfs_trans *tp,
+ struct xfs_inode *ip,
+ uint flags)
{
- struct inode *inode = VFS_I(ip);
+ struct xfs_inode_log_item *iip = ip->i_itemp;
+ struct inode *inode = VFS_I(ip);
+ uint iversion_flags = 0;
- ASSERT(ip->i_itemp != NULL);
+ ASSERT(iip);
ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
+ ASSERT(!xfs_iflags_test(ip, XFS_ISTALE));
+
+ tp->t_flags |= XFS_TRANS_DIRTY;
/*
* Don't bother with i_lock for the I_DIRTY_TIME check here, as races
* to log the timestamps, or will clear already cleared fields in the
* worst case.
*/
- if (inode->i_state & (I_DIRTY_TIME | I_DIRTY_TIME_EXPIRED)) {
+ if (inode->i_state & I_DIRTY_TIME) {
spin_lock(&inode->i_lock);
- inode->i_state &= ~(I_DIRTY_TIME | I_DIRTY_TIME_EXPIRED);
+ inode->i_state &= ~I_DIRTY_TIME;
spin_unlock(&inode->i_lock);
}
- /*
- * Record the specific change for fdatasync optimisation. This
- * allows fdatasync to skip log forces for inodes that are only
- * timestamp dirty. We do this before the change count so that
- * the core being logged in this case does not impact on fdatasync
- * behaviour.
- */
- ip->i_itemp->ili_fsync_fields |= flags;
-
/*
* First time we log the inode in a transaction, bump the inode change
* counter if it is configured for this to occur. While we have the
* set however, then go ahead and bump the i_version counter
* unconditionally.
*/
- if (!test_and_set_bit(XFS_LI_DIRTY, &ip->i_itemp->ili_item.li_flags) &&
- IS_I_VERSION(VFS_I(ip))) {
- if (inode_maybe_inc_iversion(VFS_I(ip), flags & XFS_ILOG_CORE))
- flags |= XFS_ILOG_CORE;
+ if (!test_and_set_bit(XFS_LI_DIRTY, &iip->ili_item.li_flags)) {
+ if (IS_I_VERSION(inode) &&
+ inode_maybe_inc_iversion(inode, flags & XFS_ILOG_CORE))
+ iversion_flags = XFS_ILOG_CORE;
}
- tp->t_flags |= XFS_TRANS_DIRTY;
+ /*
+ * Record the specific change for fdatasync optimisation. This allows
+ * fdatasync to skip log forces for inodes that are only timestamp
+ * dirty.
+ */
+ spin_lock(&iip->ili_lock);
+ iip->ili_fsync_fields |= flags;
+
+ if (!iip->ili_item.li_buf) {
+ struct xfs_buf *bp;
+ int error;
+
+ /*
+ * We hold the ILOCK here, so this inode is not going to be
+ * flushed while we are here. Further, because there is no
+ * buffer attached to the item, we know that there is no IO in
+ * progress, so nothing will clear the ili_fields while we read
+ * in the buffer. Hence we can safely drop the spin lock and
+ * read the buffer knowing that the state will not change from
+ * here.
+ */
+ spin_unlock(&iip->ili_lock);
+ error = xfs_imap_to_bp(ip->i_mount, tp, &ip->i_imap, NULL,
+ &bp, 0);
+ if (error) {
+ xfs_force_shutdown(ip->i_mount, SHUTDOWN_META_IO_ERROR);
+ return;
+ }
+
+ /*
+ * We need an explicit buffer reference for the log item but
+ * don't want the buffer to remain attached to the transaction.
+ * Hold the buffer but release the transaction reference once
+ * we've attached the inode log item to the buffer log item
+ * list.
+ */
+ xfs_buf_hold(bp);
+ spin_lock(&iip->ili_lock);
+ iip->ili_item.li_buf = bp;
+ bp->b_flags |= _XBF_INODES;
+ list_add_tail(&iip->ili_item.li_bio_list, &bp->b_li_list);
+ xfs_trans_brelse(tp, bp);
+ }
/*
- * Always OR in the bits from the ili_last_fields field.
- * This is to coordinate with the xfs_iflush() and xfs_iflush_done()
- * routines in the eventual clearing of the ili_fields bits.
- * See the big comment in xfs_iflush() for an explanation of
- * this coordination mechanism.
+ * Always OR in the bits from the ili_last_fields field. This is to
+ * coordinate with the xfs_iflush() and xfs_iflush_done() routines in
+ * the eventual clearing of the ili_fields bits. See the big comment in
+ * xfs_iflush() for an explanation of this coordination mechanism.
*/
- flags |= ip->i_itemp->ili_last_fields;
- ip->i_itemp->ili_fields |= flags;
+ iip->ili_fields |= (flags | iip->ili_last_fields | iversion_flags);
+ spin_unlock(&iip->ili_lock);
}
int
/* 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
#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 {
struct file *ki_filp;
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
};
* 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
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?
*/
/*
* 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.
*
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 */
bool (*lm_break)(struct file_lock *);
int (*lm_change)(struct file_lock *, int, struct list_head *);
void (*lm_setup)(struct file_lock *, void **);
+ bool (*lm_breaker_owns_lease)(struct file_lock *);
};
struct lock_manager {
#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 */
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
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.
struct iovec *fast_pointer,
struct iovec **ret_pointer);
-extern ssize_t __vfs_read(struct file *, char __user *, size_t, loff_t *);
extern ssize_t vfs_read(struct file *, char __user *, size_t, loff_t *);
extern ssize_t vfs_write(struct file *, const char __user *, size_t, loff_t *);
extern ssize_t vfs_readv(struct file *, const struct iovec __user *,
/*
* 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
*
* I_DONTCACHE Evict inode as soon as it is not used anymore.
*
+ * I_SYNC_QUEUED Inode is queued in b_io or b_more_io writeback lists.
+ * Used to detect that mark_inode_dirty() should not move
+ * inode between dirty lists.
+ *
* Q: What is the difference between I_WILL_FREE and I_FREEING?
*/
#define I_DIRTY_SYNC (1 << 0)
#define I_DIO_WAKEUP (1 << __I_DIO_WAKEUP)
#define I_LINKABLE (1 << 10)
#define I_DIRTY_TIME (1 << 11)
- #define __I_DIRTY_TIME_EXPIRED 12
- #define I_DIRTY_TIME_EXPIRED (1 << __I_DIRTY_TIME_EXPIRED)
#define I_WB_SWITCH (1 << 13)
#define I_OVL_INUSE (1 << 14)
#define I_CREATING (1 << 15)
#define I_DONTCACHE (1 << 16)
+ #define I_SYNC_QUEUED (1 << 17)
#define I_DIRTY_INODE (I_DIRTY_SYNC | I_DIRTY_DATASYNC)
#define I_DIRTY (I_DIRTY_INODE | I_DIRTY_PAGES)
#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));
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);
#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 void kill_bdev(struct block_device *);
-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 kill_bdev(struct block_device *bdev) {}
-static inline void invalidate_bdev(struct block_device *bdev) {}
-
-static inline struct super_block *freeze_bdev(struct block_device *sb)
-{
- return NULL;
+ return IS_ENABLED(CONFIG_BLOCK) && sb == blockdev_superblock;
}
-static inline int thaw_bdev(struct block_device *bdev, struct super_block *sb)
-{
- return 0;
-}
-
-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
__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);
}
/**
- * 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
*
/**
* 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.
extern int kernel_read_file_from_fd(int, void **, loff_t *, loff_t,
enum kernel_read_file_id);
extern ssize_t kernel_read(struct file *, void *, size_t, loff_t *);
+ssize_t __kernel_read(struct file *file, void *buf, size_t count, loff_t *pos);
extern ssize_t kernel_write(struct file *, const void *, size_t, loff_t *);
extern ssize_t __kernel_write(struct file *, const void *, size_t, loff_t *);
extern struct file * open_exec(const char *);
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 *);
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);
DIO_SKIP_HOLES = 0x02,
};
+void dio_end_io(struct bio *bio);
+
ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode,
struct block_device *bdev, struct iov_iter *iter,
get_block_t get_block,
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;
}
projects / linux.git / commitdiff