[RFC,v3,1/2] fs: Add IOCB_NOIO flag for generic_file_read_iter
diff mbox series

Message ID 20200707144457.1603400-2-agruenba@redhat.com
State New, archived
Headers show
Series
  • Fix gfs2 readahead deadlocks
Related show

Commit Message

Andreas Gruenbacher July 7, 2020, 2:44 p.m. UTC
Add an IOCB_NOIO flag that indicates to generic_file_read_iter that it
shouldn't trigger any filesystem I/O for the actual request or for
readahead.  This allows to do tentative reads out of the page cache as
some filesystems allow, and to take the appropriate locks and retry the
reads only if the requested pages are not cached.

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 include/linux/fs.h |  1 +
 mm/filemap.c       | 23 +++++++++++++++++++++--
 2 files changed, 22 insertions(+), 2 deletions(-)

Comments

Jens Axboe July 7, 2020, 6:39 p.m. UTC | #1
On 7/7/20 8:44 AM, Andreas Gruenbacher wrote:
> diff --git a/include/linux/fs.h b/include/linux/fs.h
> index 3f881a892ea7..1ab2ea19e883 100644
> --- a/include/linux/fs.h
> +++ b/include/linux/fs.h
> @@ -315,6 +315,7 @@ enum rw_hint {
>  #define IOCB_SYNC		(1 << 5)
>  #define IOCB_WRITE		(1 << 6)
>  #define IOCB_NOWAIT		(1 << 7)
> +#define IOCB_NOIO		(1 << 8)

Just to make this even more trivial in terms of merge conflicts, could
you do 1 << 9 instead?
Andreas Gr├╝nbacher July 7, 2020, 9:42 p.m. UTC | #2
Am Di., 7. Juli 2020 um 20:40 Uhr schrieb Jens Axboe <axboe@kernel.dk>:
> On 7/7/20 8:44 AM, Andreas Gruenbacher wrote:
> > diff --git a/include/linux/fs.h b/include/linux/fs.h
> > index 3f881a892ea7..1ab2ea19e883 100644
> > --- a/include/linux/fs.h
> > +++ b/include/linux/fs.h
> > @@ -315,6 +315,7 @@ enum rw_hint {
> >  #define IOCB_SYNC            (1 << 5)
> >  #define IOCB_WRITE           (1 << 6)
> >  #define IOCB_NOWAIT          (1 << 7)
> > +#define IOCB_NOIO            (1 << 8)
>
> Just to make this even more trivial in terms of merge conflicts, could
> you do 1 << 9 instead?

Sure.

Andreas

Patch
diff mbox series

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 3f881a892ea7..1ab2ea19e883 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -315,6 +315,7 @@  enum rw_hint {
 #define IOCB_SYNC		(1 << 5)
 #define IOCB_WRITE		(1 << 6)
 #define IOCB_NOWAIT		(1 << 7)
+#define IOCB_NOIO		(1 << 8)
 
 struct kiocb {
 	struct file		*ki_filp;
diff --git a/mm/filemap.c b/mm/filemap.c
index f0ae9a6308cb..385759c4ce4b 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2028,7 +2028,7 @@  ssize_t generic_file_buffered_read(struct kiocb *iocb,
 
 		page = find_get_page(mapping, index);
 		if (!page) {
-			if (iocb->ki_flags & IOCB_NOWAIT)
+			if (iocb->ki_flags & (IOCB_NOWAIT | IOCB_NOIO))
 				goto would_block;
 			page_cache_sync_readahead(mapping,
 					ra, filp,
@@ -2038,6 +2038,10 @@  ssize_t generic_file_buffered_read(struct kiocb *iocb,
 				goto no_cached_page;
 		}
 		if (PageReadahead(page)) {
+			if (iocb->ki_flags & IOCB_NOIO) {
+				put_page(page);
+				goto out;
+			}
 			page_cache_async_readahead(mapping,
 					ra, filp, page,
 					index, last_index - index);
@@ -2160,6 +2164,11 @@  ssize_t generic_file_buffered_read(struct kiocb *iocb,
 		}
 
 readpage:
+		if (iocb->ki_flags & IOCB_NOIO) {
+			unlock_page(page);
+			put_page(page);
+			goto would_block;
+		}
 		/*
 		 * A previous I/O error may have been due to temporary
 		 * failures, eg. multipath errors.
@@ -2249,9 +2258,19 @@  EXPORT_SYMBOL_GPL(generic_file_buffered_read);
  *
  * This is the "read_iter()" routine for all filesystems
  * that can use the page cache directly.
+ *
+ * The IOCB_NOWAIT flag in iocb->ki_flags indicates that -EAGAIN shall
+ * be returned when no data can be read without waiting for I/O requests
+ * to complete; it doesn't prevent readahead.
+ *
+ * The IOCB_NOIO flag in iocb->ki_flags indicates that no new I/O
+ * requests shall be made for the read or for readahead.  When no data
+ * can be read, -EAGAIN shall be returned.  When readahead would be
+ * triggered, a partial, possibly empty read shall be returned.
+ *
  * Return:
  * * number of bytes copied, even for partial reads
- * * negative error code if nothing was read
+ * * negative error code (or 0 if IOCB_NOIO) if nothing was read
  */
 ssize_t
 generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter)