@@ -28,6 +28,7 @@
#include <linux/dynamic_debug.h>
#include <linux/refcount.h>
#include <linux/crc32c.h>
+#include <linux/iomap.h>
#include "extent-io-tree.h"
#include "extent_io.h"
#include "extent_map.h"
@@ -3048,7 +3049,9 @@ int btrfs_writepage_cow_fixup(struct page *page, u64 start, u64 end);
void btrfs_writepage_endio_finish_ordered(struct page *page, u64 start,
u64 end, int uptodate);
extern const struct dentry_operations btrfs_dentry_operations;
-ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter);
+extern const struct iomap_ops btrfs_dio_iomap_ops;
+extern const struct iomap_dio_ops btrfs_dio_ops;
+extern const struct iomap_dio_ops btrfs_sync_dops;
/* ioctl.c */
long btrfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
@@ -1855,21 +1855,68 @@ static noinline ssize_t btrfs_buffered_write(struct kiocb *iocb,
return num_written ? num_written : ret;
}
-static ssize_t __btrfs_direct_write(struct kiocb *iocb, struct iov_iter *from)
+static ssize_t check_direct_IO(struct btrfs_fs_info *fs_info,
+ const struct iov_iter *iter, loff_t offset)
+{
+ const unsigned int blocksize_mask = fs_info->sectorsize - 1;
+
+ if (offset & blocksize_mask)
+ return -EINVAL;
+
+ if (iov_iter_alignment(iter) & blocksize_mask)
+ return -EINVAL;
+
+ return 0;
+}
+
+static ssize_t btrfs_direct_write(struct kiocb *iocb, struct iov_iter *from)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file_inode(file);
- loff_t pos;
- ssize_t written;
+ struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+ loff_t pos = iocb->ki_pos;
+ ssize_t written = 0;
+ bool relock = false;
ssize_t written_buffered;
loff_t endbyte;
int err;
- written = btrfs_direct_IO(iocb, from);
+ if (check_direct_IO(fs_info, from, pos))
+ goto buffered;
+
+ /*
+ * If the write DIO is beyond the EOF, we need update
+ * the isize, but it is protected by i_mutex. So we can
+ * not unlock the i_mutex at this case.
+ */
+ if (pos + iov_iter_count(from) <= inode->i_size) {
+ inode_unlock(inode);
+ relock = true;
+ }
+ down_read(&BTRFS_I(inode)->dio_sem);
+
+ /*
+ * We have are actually a sync iocb, so we need our fancy endio to know
+ * if we need to sync.
+ */
+ if (current->journal_info)
+ written = iomap_dio_rw(iocb, from, &btrfs_dio_iomap_ops,
+ &btrfs_sync_dops, is_sync_kiocb(iocb));
+ else
+ written = iomap_dio_rw(iocb, from, &btrfs_dio_iomap_ops,
+ &btrfs_dio_ops, is_sync_kiocb(iocb));
+
+ if (written == -ENOTBLK)
+ written = 0;
+
+ up_read(&BTRFS_I(inode)->dio_sem);
+ if (relock)
+ inode_lock(inode);
if (written < 0 || !iov_iter_count(from))
return written;
+buffered:
pos = iocb->ki_pos;
written_buffered = btrfs_buffered_write(iocb, from);
if (written_buffered < 0) {
@@ -2043,7 +2090,7 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb,
iocb->ki_flags &= ~IOCB_DSYNC;
current->journal_info = BTRFS_DIO_SYNC_STUB;
}
- num_written = __btrfs_direct_write(iocb, from);
+ num_written = btrfs_direct_write(iocb, from);
/*
* As stated above, we cleared journal_info, so we need to do
@@ -3618,16 +3665,47 @@ static int btrfs_file_open(struct inode *inode, struct file *filp)
return generic_file_open(inode, filp);
}
+static int check_direct_read(struct btrfs_fs_info *fs_info,
+ const struct iov_iter *iter, loff_t offset)
+{
+ int ret;
+ int i, seg;
+
+ ret = check_direct_IO(fs_info, iter, offset);
+ if (ret < 0)
+ return ret;
+
+ if (!iter_is_iovec(iter))
+ return 0;
+
+ for (seg = 0; seg < iter->nr_segs; seg++)
+ for (i = seg + 1; i < iter->nr_segs; i++)
+ if (iter->iov[seg].iov_base == iter->iov[i].iov_base)
+ return -EINVAL;
+ return 0;
+}
+
+static ssize_t btrfs_direct_read(struct kiocb *iocb, struct iov_iter *to)
+{
+ struct inode *inode = file_inode(iocb->ki_filp);
+ ssize_t ret;
+
+ if (check_direct_read(btrfs_sb(inode->i_sb), to, iocb->ki_pos))
+ return 0;
+
+ inode_lock_shared(inode);
+ ret = iomap_dio_rw(iocb, to, &btrfs_dio_iomap_ops, &btrfs_dio_ops,
+ is_sync_kiocb(iocb));
+ inode_unlock_shared(inode);
+ return ret;
+}
+
static ssize_t btrfs_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
{
ssize_t ret = 0;
if (iocb->ki_flags & IOCB_DIRECT) {
- struct inode *inode = file_inode(iocb->ki_filp);
-
- inode_lock_shared(inode);
- ret = btrfs_direct_IO(iocb, to);
- inode_unlock_shared(inode);
+ ret = btrfs_direct_read(iocb, to);
if (ret < 0)
return ret;
}
@@ -7898,39 +7898,6 @@ static blk_qc_t btrfs_submit_direct(struct inode *inode, struct iomap *iomap,
return BLK_QC_T_NONE;
}
-static ssize_t check_direct_IO(struct btrfs_fs_info *fs_info,
- const struct iov_iter *iter, loff_t offset)
-{
- int seg;
- int i;
- unsigned int blocksize_mask = fs_info->sectorsize - 1;
- ssize_t retval = -EINVAL;
-
- if (offset & blocksize_mask)
- goto out;
-
- if (iov_iter_alignment(iter) & blocksize_mask)
- goto out;
-
- /* If this is a write we don't need to check anymore */
- if (iov_iter_rw(iter) != READ || !iter_is_iovec(iter))
- return 0;
- /*
- * Check to make sure we don't have duplicate iov_base's in this
- * iovec, if so return EINVAL, otherwise we'll get csum errors
- * when reading back.
- */
- for (seg = 0; seg < iter->nr_segs; seg++) {
- for (i = seg + 1; i < iter->nr_segs; i++) {
- if (iter->iov[seg].iov_base == iter->iov[i].iov_base)
- goto out;
- }
- }
- retval = 0;
-out:
- return retval;
-}
-
static inline int btrfs_maybe_fsync_end_io(struct kiocb *iocb, ssize_t size,
int error, unsigned flags)
{
@@ -7955,72 +7922,20 @@ static inline int btrfs_maybe_fsync_end_io(struct kiocb *iocb, ssize_t size,
return 0;
}
-static const struct iomap_ops btrfs_dio_iomap_ops = {
+const struct iomap_ops btrfs_dio_iomap_ops = {
.iomap_begin = btrfs_dio_iomap_begin,
.iomap_end = btrfs_dio_iomap_end,
};
-static const struct iomap_dio_ops btrfs_dio_ops = {
+const struct iomap_dio_ops btrfs_dio_ops = {
.submit_io = btrfs_submit_direct,
};
-static const struct iomap_dio_ops btrfs_sync_dops = {
+const struct iomap_dio_ops btrfs_sync_dops = {
.submit_io = btrfs_submit_direct,
.end_io = btrfs_maybe_fsync_end_io,
};
-ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
-{
- struct file *file = iocb->ki_filp;
- struct inode *inode = file->f_mapping->host;
- struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
- struct extent_changeset *data_reserved = NULL;
- loff_t offset = iocb->ki_pos;
- size_t count = 0;
- bool relock = false;
- ssize_t ret;
-
- if (check_direct_IO(fs_info, iter, offset))
- return 0;
-
- count = iov_iter_count(iter);
- if (iov_iter_rw(iter) == WRITE) {
- /*
- * If the write DIO is beyond the EOF, we need update
- * the isize, but it is protected by i_mutex. So we can
- * not unlock the i_mutex at this case.
- */
- if (offset + count <= inode->i_size) {
- inode_unlock(inode);
- relock = true;
- }
- down_read(&BTRFS_I(inode)->dio_sem);
- }
-
- /*
- * We have are actually a sync iocb, so we need our fancy endio to know
- * if we need to sync.
- */
- if (current->journal_info)
- ret = iomap_dio_rw(iocb, iter, &btrfs_dio_iomap_ops,
- &btrfs_sync_dops, is_sync_kiocb(iocb));
- else
- ret = iomap_dio_rw(iocb, iter, &btrfs_dio_iomap_ops,
- &btrfs_dio_ops, is_sync_kiocb(iocb));
-
- if (ret == -ENOTBLK)
- ret = 0;
-
- if (iov_iter_rw(iter) == WRITE)
- up_read(&BTRFS_I(inode)->dio_sem);
-
- if (relock)
- inode_lock(inode);
-
- extent_changeset_free(data_reserved);
- return ret;
-}
-
static int btrfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
u64 start, u64 len)
{