Re: [PATCH v2] ceph: invalidate pages when doing DIO in encrypted inodes

[Xiubo Li]

Hi Luis,

Please try the following patch, to see could it resolve your issue:


diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 5d39d8e54273..3507e4066de4 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -2011,6 +2011,7 @@ static ssize_t ceph_read_iter(struct kiocb *iocb, 
struct iov_iter *to)
                     ceph_cap_string(got));

                if (ci->i_inline_version == CEPH_INLINE_NONE) {
+ filemap_invalidate_lock(inode->i_mapping);
                        if (!retry_op &&
                            (iocb->ki_flags & IOCB_DIRECT) &&
                            !IS_ENCRYPTED(inode)) {
@@ -2021,6 +2022,7 @@ static ssize_t ceph_read_iter(struct kiocb *iocb, 
struct iov_iter *to)
                        } else {
                                ret = ceph_sync_read(iocb, to, &retry_op);
                        }
+ filemap_invalidate_unlock(inode->i_mapping);
                } else {
                        retry_op = READ_INLINE;
                }
@@ -2239,11 +2241,13 @@ static ssize_t ceph_write_iter(struct kiocb 
*iocb, struct iov_iter *from)

                /* we might need to revert back to that point */
                data = *from;
+               filemap_invalidate_lock(inode->i_mapping);
                if ((iocb->ki_flags & IOCB_DIRECT) && !IS_ENCRYPTED(inode))
                        written = ceph_direct_read_write(iocb, &data, 
snapc,
&prealloc_cf);
                else
                        written = ceph_sync_write(iocb, &data, pos, snapc);
+               filemap_invalidate_unlock(inode->i_mapping);
                if (direct_lock)
                        ceph_end_io_direct(inode);
                else



On 4/1/22 9:32 PM, Luís Henriques wrote:
> When doing DIO on an encrypted node, we need to invalidate the page cache in
> the range being written to, otherwise the cache will include invalid data.
>
> Signed-off-by: Luís Henriques <lhenriques@xxxxxxx>
> ---
>   fs/ceph/file.c | 11 ++++++++++-
>   1 file changed, 10 insertions(+), 1 deletion(-)
>
> Changes since v1:
> - Replaced truncate_inode_pages_range() by invalidate_inode_pages2_range
> - Call fscache_invalidate with FSCACHE_INVAL_DIO_WRITE if we're doing DIO
>
> Note: I'm not really sure this last change is required, it doesn't really
> affect generic/647 result, but seems to be the most correct.
>
> diff --git a/fs/ceph/file.c b/fs/ceph/file.c
> index 5072570c2203..b2743c342305 100644
> --- a/fs/ceph/file.c
> +++ b/fs/ceph/file.c
> @@ -1605,7 +1605,7 @@ ceph_sync_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos,
>   	if (ret < 0)
>   		return ret;
>   
> -	ceph_fscache_invalidate(inode, false);
> +	ceph_fscache_invalidate(inode, (iocb->ki_flags & IOCB_DIRECT));
>   	ret = invalidate_inode_pages2_range(inode->i_mapping,
>   					    pos >> PAGE_SHIFT,
>   					    (pos + count - 1) >> PAGE_SHIFT);
> @@ -1895,6 +1895,15 @@ ceph_sync_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos,
>   		req->r_inode = inode;
>   		req->r_mtime = mtime;
>   
> +		if (IS_ENCRYPTED(inode) && (iocb->ki_flags & IOCB_DIRECT)) {
> +			ret = invalidate_inode_pages2_range(
> +				inode->i_mapping,
> +				write_pos >> PAGE_SHIFT,
> +				(write_pos + write_len - 1) >> PAGE_SHIFT);
> +			if (ret < 0)
> +				dout("invalidate_inode_pages2_range returned %d\n", ret);
> +		}
> +
>   		/* Set up the assertion */
>   		if (rmw) {
>   			/*