在 2024/6/19 22:27, Pavel Begunkov 写道:
On 6/19/24 07:38, Chenliang Li wrote:
In io_import_fixed when advancing the iter within the first bvec, the
iter->nr_segs is set to bvec->bv_len. nr_segs should be the number of
bvecs, plus we don't need to adjust it here, so just remove it.
Good catch, quite old. It's our luck that bvec iteration
honours the length and doesn't step outside of the first entry.
Fixes: b000ae0ec2d7 ("io_uring/rsrc: optimise single entry advance")
Signed-off-by: Chenliang Li <cliang01.li@xxxxxxxxxxx>
---
io_uring/rsrc.c | 1 -
1 file changed, 1 deletion(-)
diff --git a/io_uring/rsrc.c b/io_uring/rsrc.c
index 60c00144471a..a860516bf448 100644
--- a/io_uring/rsrc.c
+++ b/io_uring/rsrc.c
@@ -1049,7 +1049,6 @@ int io_import_fixed(int ddir, struct iov_iter
*iter,
* branch doesn't expect non PAGE_SIZE'd chunks.
*/
iter->bvec = bvec;
- iter->nr_segs = bvec->bv_len;
iter->nr_segs = 1, please
Why 1? There could be multiple bvecs.
iter->count -= offset;
iter->iov_offset = offset;
} else {
base-commit: 3b87184f7eff27fef7d7ee18b65f173152e1bb81
