On Sat, 18 Jan 2014, Xishi Qiu wrote:
> In the process IO direction, dio_refill_pages will call get_user_pages_fast
> to map the page from user space. If ret is less than 0 and IO is write, the
> function will create a zero page to fill data. This may work for some file
> system, but in some device operate we prefer whole write or fail, not half
> data half zero, e.g. fs metadata, like inode, identy.
So you're attemping to define a behavior for all users of direct IO for a
problem that is filesystem or backing device dependent? Perhaps if you
elaborated on the problem that you're seeing then we could address it.
> This happens often when kill a process which is doing direct IO. Consider
> the following cases, the process A is doing IO process, may enter __get_user_pages
> function, if other processes send process A SIG_KILL, A will enter the
> following branches
> /*
> * If we have a pending SIGKILL, don't keep faulting
> * pages and potentially allocating memory.
> */
> if (unlikely(fatal_signal_pending(current)))
> return i ? i : -ERESTARTSYS;
> Return current pages. direct IO will write the pages, the subsequent pages
> which can’t get will use zero page instead.
>
> Signed-off-by: Xishi Qiu <qiuxishi@xxxxxxxxxx>
> Signed-off-by: Bin Yang <robin.yb@xxxxxxxxxx>
> ---
> fs/direct-io.c | 3 +++
> 1 files changed, 3 insertions(+), 0 deletions(-)
>
> diff --git a/fs/direct-io.c b/fs/direct-io.c
> index 0e04142..b74d565 100644
> --- a/fs/direct-io.c
> +++ b/fs/direct-io.c
> @@ -174,6 +174,9 @@ static inline int dio_refill_pages(struct dio *dio, struct dio_submit *sdio)
> &dio->pages[0]); /* Put results here */
>
> if (ret < 0 && sdio->blocks_available && (dio->rw & WRITE)) {
> + /* If task is killed, do not write anymore */
> + if (ret == -ERESTARTSYS)
> + goto out;
> struct page *page = ZERO_PAGE(0);
> /*
> * A memory fault, but the filesystem has some outstanding
We don't mix declarations and text, please try to compile your patches
before proposing them.
