{
struct file *file = iocb->ki_filp;
struct inode *inode = file_inode(iocb->ki_filp);
- struct mutex *aio_mutex = NULL;
struct blk_plug plug;
int o_direct = iocb->ki_flags & IOCB_DIRECT;
+ int unaligned_aio = 0;
int overwrite = 0;
ssize_t ret;
+ inode_lock(inode);
+ ret = generic_write_checks(iocb, from);
+ if (ret <= 0)
+ goto out;
+
/*
- * Unaligned direct AIO must be serialized; see comment above
- * In the case of O_APPEND, assume that we must always serialize
+ * Unaligned direct AIO must be serialized among each other as zeroing
+ * of partial blocks of two competing unaligned AIOs can result in data
+ * corruption.
*/
- if (o_direct &&
- ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS) &&
+ if (o_direct && ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS) &&
!is_sync_kiocb(iocb) &&
- (iocb->ki_flags & IOCB_APPEND ||
- ext4_unaligned_aio(inode, from, iocb->ki_pos))) {
- aio_mutex = ext4_aio_mutex(inode);
- mutex_lock(aio_mutex);
+ ext4_unaligned_aio(inode, from, iocb->ki_pos)) {
+ unaligned_aio = 1;
ext4_unwritten_wait(inode);
}
- inode_lock(inode);
- ret = generic_write_checks(iocb, from);
- if (ret <= 0)
- goto out;
-
/*
* If we have encountered a bitmap-format file, the size limit
* is smaller than s_maxbytes, which is for extent-mapped files.
blk_start_plug(&plug);
/* check whether we do a DIO overwrite or not */
- if (ext4_should_dioread_nolock(inode) && !aio_mutex &&
+ if (ext4_should_dioread_nolock(inode) && !unaligned_aio &&
!file->f_mapping->nrpages && pos + length <= i_size_read(inode)) {
struct ext4_map_blocks map;
unsigned int blkbits = inode->i_blkbits;
if (o_direct)
blk_finish_plug(&plug);
- if (aio_mutex)
- mutex_unlock(aio_mutex);
return ret;
out:
inode_unlock(inode);
- if (aio_mutex)
- mutex_unlock(aio_mutex);
return ret;
}
return result;
}
-static int ext4_dax_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
-{
- int err;
- struct inode *inode = file_inode(vma->vm_file);
-
- sb_start_pagefault(inode->i_sb);
- file_update_time(vma->vm_file);
- down_read(&EXT4_I(inode)->i_mmap_sem);
- err = __dax_mkwrite(vma, vmf, ext4_dax_mmap_get_block, NULL);
- up_read(&EXT4_I(inode)->i_mmap_sem);
- sb_end_pagefault(inode->i_sb);
-
- return err;
-}
-
/*
- * Handle write fault for VM_MIXEDMAP mappings. Similarly to ext4_dax_mkwrite()
+ * Handle write fault for VM_MIXEDMAP mappings. Similarly to ext4_dax_fault()
* handler we check for races agaist truncate. Note that since we cycle through
* i_mmap_sem, we are sure that also any hole punching that began before we
* were called is finished by now and so if it included part of the file we
static const struct vm_operations_struct ext4_dax_vm_ops = {
.fault = ext4_dax_fault,
.pmd_fault = ext4_dax_pmd_fault,
- .page_mkwrite = ext4_dax_mkwrite,
+ .page_mkwrite = ext4_dax_fault,
.pfn_mkwrite = ext4_dax_pfn_mkwrite,
};
#else
struct super_block *sb = inode->i_sb;
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
struct vfsmount *mnt = filp->f_path.mnt;
+ struct dentry *dir;
struct path path;
char buf[64], *cp;
int ret;
if (ext4_encryption_info(inode) == NULL)
return -ENOKEY;
}
+
+ dir = dget_parent(file_dentry(filp));
+ if (ext4_encrypted_inode(d_inode(dir)) &&
+ !ext4_is_child_context_consistent_with_parent(d_inode(dir), inode)) {
+ ext4_warning(inode->i_sb,
+ "Inconsistent encryption contexts: %lu/%lu\n",
+ (unsigned long) d_inode(dir)->i_ino,
+ (unsigned long) inode->i_ino);
+ dput(dir);
+ return -EPERM;
+ }
+ dput(dir);
/*
* Set up the jbd2_inode if we are opening the inode for
* writing and the journal is present
*/
static int ext4_find_unwritten_pgoff(struct inode *inode,
int whence,
- struct ext4_map_blocks *map,
+ ext4_lblk_t end_blk,
loff_t *offset)
{
struct pagevec pvec;
blkbits = inode->i_sb->s_blocksize_bits;
startoff = *offset;
lastoff = startoff;
- endoff = (loff_t)(map->m_lblk + map->m_len) << blkbits;
+ endoff = (loff_t)end_blk << blkbits;
- index = startoff >> PAGE_CACHE_SHIFT;
- end = endoff >> PAGE_CACHE_SHIFT;
+ index = startoff >> PAGE_SHIFT;
+ end = endoff >> PAGE_SHIFT;
pagevec_init(&pvec, 0);
do {
static loff_t ext4_seek_data(struct file *file, loff_t offset, loff_t maxsize)
{
struct inode *inode = file->f_mapping->host;
- struct ext4_map_blocks map;
struct extent_status es;
ext4_lblk_t start, last, end;
loff_t dataoff, isize;
int blkbits;
- int ret = 0;
+ int ret;
inode_lock(inode);
dataoff = offset;
do {
- map.m_lblk = last;
- map.m_len = end - last + 1;
- ret = ext4_map_blocks(NULL, inode, &map, 0);
- if (ret > 0 && !(map.m_flags & EXT4_MAP_UNWRITTEN)) {
- if (last != start)
- dataoff = (loff_t)last << blkbits;
- break;
+ ret = ext4_get_next_extent(inode, last, end - last + 1, &es);
+ if (ret <= 0) {
+ /* No extent found -> no data */
+ if (ret == 0)
+ ret = -ENXIO;
+ inode_unlock(inode);
+ return ret;
}
- /*
- * If there is a delay extent at this offset,
- * it will be as a data.
- */
- ext4_es_find_delayed_extent_range(inode, last, last, &es);
- if (es.es_len != 0 && in_range(last, es.es_lblk, es.es_len)) {
- if (last != start)
- dataoff = (loff_t)last << blkbits;
+ last = es.es_lblk;
+ if (last != start)
+ dataoff = (loff_t)last << blkbits;
+ if (!ext4_es_is_unwritten(&es))
break;
- }
/*
* If there is a unwritten extent at this offset,
* it will be as a data or a hole according to page
* cache that has data or not.
*/
- if (map.m_flags & EXT4_MAP_UNWRITTEN) {
- int unwritten;
- unwritten = ext4_find_unwritten_pgoff(inode, SEEK_DATA,
- &map, &dataoff);
- if (unwritten)
- break;
- }
-
- last++;
+ if (ext4_find_unwritten_pgoff(inode, SEEK_DATA,
+ es.es_lblk + es.es_len, &dataoff))
+ break;
+ last += es.es_len;
dataoff = (loff_t)last << blkbits;
+ cond_resched();
} while (last <= end);
inode_unlock(inode);
static loff_t ext4_seek_hole(struct file *file, loff_t offset, loff_t maxsize)
{
struct inode *inode = file->f_mapping->host;
- struct ext4_map_blocks map;
struct extent_status es;
ext4_lblk_t start, last, end;
loff_t holeoff, isize;
int blkbits;
- int ret = 0;
+ int ret;
inode_lock(inode);
holeoff = offset;
do {
- map.m_lblk = last;
- map.m_len = end - last + 1;
- ret = ext4_map_blocks(NULL, inode, &map, 0);
- if (ret > 0 && !(map.m_flags & EXT4_MAP_UNWRITTEN)) {
- last += ret;
- holeoff = (loff_t)last << blkbits;
- continue;
+ ret = ext4_get_next_extent(inode, last, end - last + 1, &es);
+ if (ret < 0) {
+ inode_unlock(inode);
+ return ret;
}
-
- /*
- * If there is a delay extent at this offset,
- * we will skip this extent.
- */
- ext4_es_find_delayed_extent_range(inode, last, last, &es);
- if (es.es_len != 0 && in_range(last, es.es_lblk, es.es_len)) {
- last = es.es_lblk + es.es_len;
- holeoff = (loff_t)last << blkbits;
- continue;
+ /* Found a hole? */
+ if (ret == 0 || es.es_lblk > last) {
+ if (last != start)
+ holeoff = (loff_t)last << blkbits;
+ break;
}
-
/*
* If there is a unwritten extent at this offset,
* it will be as a data or a hole according to page
* cache that has data or not.
*/
- if (map.m_flags & EXT4_MAP_UNWRITTEN) {
- int unwritten;
- unwritten = ext4_find_unwritten_pgoff(inode, SEEK_HOLE,
- &map, &holeoff);
- if (!unwritten) {
- last += ret;
- holeoff = (loff_t)last << blkbits;
- continue;
- }
- }
+ if (ext4_es_is_unwritten(&es) &&
+ ext4_find_unwritten_pgoff(inode, SEEK_HOLE,
+ last + es.es_len, &holeoff))
+ break;
- /* find a hole */
- break;
+ last += es.es_len;
+ holeoff = (loff_t)last << blkbits;
+ cond_resched();
} while (last <= end);
inode_unlock(inode);
projects / cascardo / linux.git / blobdiff