Merge tag 'io_uring-20190323' of git://git.kernel.dk/linux-block

Pull io_uring fixes and improvements from Jens Axboe:
 "The first five in this series are heavily inspired by the work Al did
  on the aio side to fix the races there.

  The last two re-introduce a feature that was in io_uring before it got
  merged, but which I pulled since we didn't have a good way to have
  BVEC iters that already have a stable reference. These aren't
  necessarily related to block, it's just how io_uring pins fixed
  buffers"

* tag 'io_uring-20190323' of git://git.kernel.dk/linux-block:
  block: add BIO_NO_PAGE_REF flag
  iov_iter: add ITER_BVEC_FLAG_NO_REF flag
  io_uring: mark me as the maintainer
  io_uring: retry bulk slab allocs as single allocs
  io_uring: fix poll races
  io_uring: fix fget/fput handling
  io_uring: add prepped flag
  io_uring: make io_read/write return an integer
  io_uring: use regular request ref counts

MAINTAINERS

@@ -8096,6 +8096,16 @@ F:	include/linux/iommu.h
 F:	include/linux/of_iommu.h
 F:	include/linux/iova.h
 
+IO_URING
+M:	Jens Axboe <axboe@kernel.dk>
+L:	linux-block@vger.kernel.org
+L:	linux-fsdevel@vger.kernel.org
+T:	git git://git.kernel.dk/linux-block
+T:	git git://git.kernel.dk/liburing
+S:	Maintained
+F:	fs/io_uring.c
+F:	include/uapi/linux/io_uring.h
+
 IP MASQUERADING
 M:	Juanjo Ciarlante <jjciarla@raiz.uncu.edu.ar>
 S:	Maintained

block/bio.c

@@ -849,20 +849,14 @@ static int __bio_iov_bvec_add_pages(struct bio *bio, struct iov_iter *iter)
 	size = bio_add_page(bio, bv->bv_page, len,
 				bv->bv_offset + iter->iov_offset);
 	if (size == len) {
+		if (!bio_flagged(bio, BIO_NO_PAGE_REF)) {
 			struct page *page;
 			int i;
 
-		/*
-		 * For the normal O_DIRECT case, we could skip grabbing this
-		 * reference and then not have to put them again when IO
-		 * completes. But this breaks some in-kernel users, like
-		 * splicing to/from a loop device, where we release the pipe
-		 * pages unconditionally. If we can fix that case, we can
-		 * get rid of the get here and the need to call
-		 * bio_release_pages() at IO completion time.
-		 */
 			mp_bvec_for_each_page(page, bv, i)
 				get_page(page);
+		}
+
 		iov_iter_advance(iter, size);
 		return 0;
 	}
@@ -925,10 +919,12 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
  * This takes either an iterator pointing to user memory, or one pointing to
  * kernel pages (BVEC iterator). If we're adding user pages, we pin them and
  * map them into the kernel. On IO completion, the caller should put those
- * pages. For now, when adding kernel pages, we still grab a reference to the
- * page. This isn't strictly needed for the common case, but some call paths
- * end up releasing pages from eg a pipe and we can't easily control these.
- * See comment in __bio_iov_bvec_add_pages().
+ * pages. If we're adding kernel pages, and the caller told us it's safe to
+ * do so, we just have to add the pages to the bio directly. We don't grab an
+ * extra reference to those pages (the user should already have that), and we
+ * don't put the page on IO completion. The caller needs to check if the bio is
+ * flagged BIO_NO_PAGE_REF on IO completion. If it isn't, then pages should be
+ * released.
  *
  * The function tries, but does not guarantee, to pin as many pages as
  * fit into the bio, or are requested in *iter, whatever is smaller. If
@@ -940,6 +936,13 @@ int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
 	const bool is_bvec = iov_iter_is_bvec(iter);
 	unsigned short orig_vcnt = bio->bi_vcnt;
 
+	/*
+	 * If this is a BVEC iter, then the pages are kernel pages. Don't
+	 * release them on IO completion, if the caller asked us to.
+	 */
+	if (is_bvec && iov_iter_bvec_no_ref(iter))
+		bio_set_flag(bio, BIO_NO_PAGE_REF);
+
 	do {
 		int ret;
 
@@ -1696,6 +1699,7 @@ static void bio_dirty_fn(struct work_struct *work)
 		next = bio->bi_private;
 
 		bio_set_pages_dirty(bio);
+		if (!bio_flagged(bio, BIO_NO_PAGE_REF))
 			bio_release_pages(bio);
 		bio_put(bio);
 	}
@@ -1713,6 +1717,7 @@ void bio_check_pages_dirty(struct bio *bio)
 			goto defer;
 	}
 
+	if (!bio_flagged(bio, BIO_NO_PAGE_REF))
 		bio_release_pages(bio);
 	bio_put(bio);
 	return;

fs/block_dev.c

@@ -336,12 +336,14 @@ static void blkdev_bio_end_io(struct bio *bio)
 	if (should_dirty) {
 		bio_check_pages_dirty(bio);
 	} else {
+		if (!bio_flagged(bio, BIO_NO_PAGE_REF)) {
+			struct bvec_iter_all iter_all;
 			struct bio_vec *bvec;
 			int i;
-		struct bvec_iter_all iter_all;
 
 			bio_for_each_segment_all(bvec, bio, i, iter_all)
 				put_page(bvec->bv_page);
+		}
 		bio_put(bio);
 	}
 }

fs/iomap.c

@@ -1589,12 +1589,14 @@ static void iomap_dio_bio_end_io(struct bio *bio)
 	if (should_dirty) {
 		bio_check_pages_dirty(bio);
 	} else {
+		if (!bio_flagged(bio, BIO_NO_PAGE_REF)) {
+			struct bvec_iter_all iter_all;
 			struct bio_vec *bvec;
 			int i;
-		struct bvec_iter_all iter_all;
 
 			bio_for_each_segment_all(bvec, bio, i, iter_all)
 				put_page(bvec->bv_page);
+		}
 		bio_put(bio);
 	}
 }

include/linux/blk_types.h

@@ -215,6 +215,7 @@ struct bio {
 /*
  * bio flags
  */
+#define BIO_NO_PAGE_REF	0	/* don't put release vec pages */
 #define BIO_SEG_VALID	1	/* bi_phys_segments valid */
 #define BIO_CLONED	2	/* doesn't own data */
 #define BIO_BOUNCED	3	/* bio is a bounce bio */

include/linux/uio.h

@@ -23,14 +23,23 @@ struct kvec {
 };
 
 enum iter_type {
-	ITER_IOVEC = 0,
-	ITER_KVEC = 2,
-	ITER_BVEC = 4,
-	ITER_PIPE = 8,
-	ITER_DISCARD = 16,
+	/* set if ITER_BVEC doesn't hold a bv_page ref */
+	ITER_BVEC_FLAG_NO_REF = 2,
+
+	/* iter types */
+	ITER_IOVEC = 4,
+	ITER_KVEC = 8,
+	ITER_BVEC = 16,
+	ITER_PIPE = 32,
+	ITER_DISCARD = 64,
 };
 
 struct iov_iter {
+	/*
+	 * Bit 0 is the read/write bit, set if we're writing.
+	 * Bit 1 is the BVEC_FLAG_NO_REF bit, set if type is a bvec and
+	 * the caller isn't expecting to drop a page reference when done.
+	 */
 	unsigned int type;
 	size_t iov_offset;
 	size_t count;
@@ -84,6 +93,11 @@ static inline unsigned char iov_iter_rw(const struct iov_iter *i)
 	return i->type & (READ | WRITE);
 }
 
+static inline bool iov_iter_bvec_no_ref(const struct iov_iter *i)
+{
+	return (i->type & ITER_BVEC_FLAG_NO_REF) != 0;
+}
+
 /*
  * Total number of bytes covered by an iovec.
  *