Open code __generic_file_write_iter to remove the indirect call into
->direct_IO and to prepare using the iomap based write code.
Signed-off-by: Christoph Hellwig <[email protected]>
---
block/fops.c | 44 ++++++++++++++++++++++++++++++++++++++++++--
1 file changed, 42 insertions(+), 2 deletions(-)
diff --git a/block/fops.c b/block/fops.c
index a286bf3325c5d8..eb599a173ef02d 100644
--- a/block/fops.c
+++ b/block/fops.c
@@ -533,6 +533,29 @@ static int blkdev_release(struct inode *inode, struct file *filp)
return 0;
}
+static ssize_t
+blkdev_direct_write(struct kiocb *iocb, struct iov_iter *from)
+{
+ size_t count = iov_iter_count(from);
+ ssize_t written;
+
+ written = kiocb_invalidate_pages(iocb, count);
+ if (written) {
+ if (written == -EBUSY)
+ return 0;
+ return written;
+ }
+
+ written = blkdev_direct_IO(iocb, from);
+ if (written > 0) {
+ kiocb_invalidate_post_direct_write(iocb, count);
+ iocb->ki_pos += written;
+ }
+ if (written != -EIOCBQUEUED)
+ iov_iter_revert(from, count - written - iov_iter_count(from));
+ return written;
+}
+
/*
* Write data to the block device. Only intended for the block device itself
* and the raw driver which basically is a fake block device.
@@ -542,7 +565,8 @@ static int blkdev_release(struct inode *inode, struct file *filp)
*/
static ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
- struct block_device *bdev = I_BDEV(iocb->ki_filp->f_mapping->host);
+ struct file *file = iocb->ki_filp;
+ struct block_device *bdev = I_BDEV(file->f_mapping->host);
struct inode *bd_inode = bdev->bd_inode;
loff_t size = bdev_nr_bytes(bdev);
size_t shorted = 0;
@@ -569,7 +593,23 @@ static ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from)
iov_iter_truncate(from, size);
}
- ret = __generic_file_write_iter(iocb, from);
+ ret = file_remove_privs(file);
+ if (ret)
+ return ret;
+
+ ret = file_update_time(file);
+ if (ret)
+ return ret;
+
+ if (iocb->ki_flags & IOCB_DIRECT) {
+ ret = blkdev_direct_write(iocb, from);
+ if (ret >= 0 && iov_iter_count(from))
+ ret = direct_write_fallback(iocb, from, ret,
+ generic_perform_write(iocb, from));
+ } else {
+ ret = generic_perform_write(iocb, from);
+ }
+
if (ret > 0)
ret = generic_write_sync(iocb, ret);
iov_iter_reexpand(from, iov_iter_count(from) + shorted);
--
2.39.2
Looks good,
Reviewed-by: Johannes Thumshirn <[email protected]>
On 7/20/23 16:04, Christoph Hellwig wrote:
> Open code __generic_file_write_iter to remove the indirect call into
> ->direct_IO and to prepare using the iomap based write code.
>
> Signed-off-by: Christoph Hellwig <[email protected]>
> ---
> block/fops.c | 44 ++++++++++++++++++++++++++++++++++++++++++--
> 1 file changed, 42 insertions(+), 2 deletions(-)
>
Reviewed-by: Hannes Reinecke <[email protected]>
Cheers,
Hannes
--
Dr. Hannes Reinecke Kernel Storage Architect
[email protected] +49 911 74053 688
SUSE Software Solutions GmbH, Maxfeldstr. 5, 90409 Nürnberg
HRB 36809 (AG Nürnberg), Geschäftsführer: Ivo Totev, Andrew
Myers, Andrew McDonald, Martje Boudien Moerman
On Thu, Jul 20, 2023 at 04:04:49PM +0200, Christoph Hellwig wrote:
> Open code __generic_file_write_iter to remove the indirect call into
> ->direct_IO and to prepare using the iomap based write code.
>
> Signed-off-by: Christoph Hellwig <[email protected]>
> ---
> block/fops.c | 44 ++++++++++++++++++++++++++++++++++++++++++--
> 1 file changed, 42 insertions(+), 2 deletions(-)
>
> diff --git a/block/fops.c b/block/fops.c
> index a286bf3325c5d8..eb599a173ef02d 100644
> --- a/block/fops.c
> +++ b/block/fops.c
> @@ -533,6 +533,29 @@ static int blkdev_release(struct inode *inode, struct file *filp)
> return 0;
> }
>
> +static ssize_t
> +blkdev_direct_write(struct kiocb *iocb, struct iov_iter *from)
> +{
> + size_t count = iov_iter_count(from);
> + ssize_t written;
> +
> + written = kiocb_invalidate_pages(iocb, count);
> + if (written) {
> + if (written == -EBUSY)
> + return 0;
> + return written;
> + }
> +
> + written = blkdev_direct_IO(iocb, from);
> + if (written > 0) {
> + kiocb_invalidate_post_direct_write(iocb, count);
> + iocb->ki_pos += written;
> + }
I noted in the last series how this could be negative and then crash:
https://lkml.kernel.org/r/[email protected]
This can be fixed as follows:
diff --git a/block/fops.c b/block/fops.c
index eb599a173ef0..936ed207b5dc 100644
--- a/block/fops.c
+++ b/block/fops.c
@@ -536,9 +536,13 @@ static int blkdev_release(struct inode *inode, struct file *filp)
static ssize_t
blkdev_direct_write(struct kiocb *iocb, struct iov_iter *from)
{
+ struct block_device *bdev = I_BDEV(iocb->ki_filp->f_mapping->host);
size_t count = iov_iter_count(from);
ssize_t written;
+ if (blkdev_dio_unaligned(bdev, iocb->ki_pos, from))
+ return -EINVAL;
+
written = kiocb_invalidate_pages(iocb, count);
if (written) {
if (written == -EBUSY)
With that:
Reviewed-by: Luis Chamberlain <[email protected]>
Luis