| Message ID | 20161123155301.GP1555@ZenIV.linux.org.uk |
|---|---|
| State | Not Applicable, archived |
| Delegated to: | David Miller |
| Headers | show |
On Wed, Nov 23, 2016 at 03:53:01PM +0000, Al Viro wrote: > On Wed, Nov 23, 2016 at 12:58:11AM -0800, Alexei Starovoitov wrote: > > > if I read it correctly 9p actually responded with 8192 bytes of requests... > > whereas the file size was 9624. > > For large file sizes (in megabytes) the difference between what > > sendfile is reporting and actual file size can be 3x. > > In the small file case (like above dump) it looks rounded to page size for some reason. > > OK, I think I see one bug in there; could you check if this gets it back to > normal? > > diff --git a/fs/splice.c b/fs/splice.c > index dcaf185..5a7750b 100644 > --- a/fs/splice.c > +++ b/fs/splice.c > @@ -408,7 +408,8 @@ static ssize_t default_file_splice_read(struct file *in, loff_t *ppos, > if (res <= 0) > return -ENOMEM; > > - nr_pages = res / PAGE_SIZE; > + BUG_ON(dummy); > + nr_pages = DIV_ROUND_UP(res, PAGE_SIZE); Hooray. It fixed it :) Feel free to add my Tested-by: Alexei Starovoitov <ast@kernel.org> when you submit it. Thanks for fixing it so quickly!
diff --git a/fs/splice.c b/fs/splice.c index dcaf185..5a7750b 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -408,7 +408,8 @@ static ssize_t default_file_splice_read(struct file *in, loff_t *ppos, if (res <= 0) return -ENOMEM; - nr_pages = res / PAGE_SIZE; + BUG_ON(dummy); + nr_pages = DIV_ROUND_UP(res, PAGE_SIZE); vec = __vec; if (nr_pages > PIPE_DEF_BUFFERS) {