linux-block.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Jens Axboe <axboe@kernel.dk>
To: linux-aio@kvack.org, linux-block@vger.kernel.org,
	linux-api@vger.kernel.org
Cc: hch@lst.de, jmoyer@redhat.com, avi@scylladb.com,
	jannh@google.com, viro@ZenIV.linux.org.uk,
	Jens Axboe <axboe@kernel.dk>
Subject: [PATCH 11/19] block: implement bio helper to add iter bvec pages to bio
Date: Fri,  8 Feb 2019 10:34:15 -0700	[thread overview]
Message-ID: <20190208173423.27014-12-axboe@kernel.dk> (raw)
In-Reply-To: <20190208173423.27014-1-axboe@kernel.dk>

For an ITER_BVEC, we can just iterate the iov and add the pages
to the bio directly. This requires that the caller doesn't releases
the pages on IO completion, we add a BIO_NO_PAGE_REF flag for that.

The current two callers of bio_iov_iter_get_pages() are updated to
check if they need to release pages on completion. This makes them
work with bvecs that contain kernel mapped pages already.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/bio.c               | 59 ++++++++++++++++++++++++++++++++-------
 fs/block_dev.c            |  5 ++--
 fs/iomap.c                |  5 ++--
 include/linux/blk_types.h |  1 +
 4 files changed, 56 insertions(+), 14 deletions(-)

diff --git a/block/bio.c b/block/bio.c
index 4db1008309ed..330df572cfb8 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -828,6 +828,23 @@ int bio_add_page(struct bio *bio, struct page *page,
 }
 EXPORT_SYMBOL(bio_add_page);
 
+static int __bio_iov_bvec_add_pages(struct bio *bio, struct iov_iter *iter)
+{
+	const struct bio_vec *bv = iter->bvec;
+	unsigned int len;
+	size_t size;
+
+	len = min_t(size_t, bv->bv_len, iter->count);
+	size = bio_add_page(bio, bv->bv_page, len,
+				bv->bv_offset + iter->iov_offset);
+	if (size == len) {
+		iov_iter_advance(iter, size);
+		return 0;
+	}
+
+	return -EINVAL;
+}
+
 #define PAGE_PTRS_PER_BVEC     (sizeof(struct bio_vec) / sizeof(struct page *))
 
 /**
@@ -876,23 +893,43 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
 }
 
 /**
- * bio_iov_iter_get_pages - pin user or kernel pages and add them to a bio
+ * bio_iov_iter_get_pages - add user or kernel pages to a bio
  * @bio: bio to add pages to
- * @iter: iov iterator describing the region to be mapped
+ * @iter: iov iterator describing the region to be added
+ *
+ * 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. If we're adding kernel pages, 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.
  *
- * Pins pages from *iter and appends them to @bio's bvec array. The
- * pages will have to be released using put_page() when done.
  * 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 MM encounters an error pinning the requested pages, it stops.
- * Error is returned only if 0 pages could be pinned.
+ * fit into the bio, or are requested in *iter, whatever is smaller. If
+ * MM encounters an error pinning the requested pages, it stops. Error
+ * is returned only if 0 pages could be pinned.
  */
 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 (is_bvec)
+		bio_set_flag(bio, BIO_NO_PAGE_REF);
+
 	do {
-		int ret = __bio_iov_iter_get_pages(bio, iter);
+		int ret;
+
+		if (is_bvec)
+			ret = __bio_iov_bvec_add_pages(bio, iter);
+		else
+			ret = __bio_iov_iter_get_pages(bio, iter);
 
 		if (unlikely(ret))
 			return bio->bi_vcnt > orig_vcnt ? 0 : ret;
@@ -1634,7 +1671,8 @@ static void bio_dirty_fn(struct work_struct *work)
 		next = bio->bi_private;
 
 		bio_set_pages_dirty(bio);
-		bio_release_pages(bio);
+		if (!bio_flagged(bio, BIO_NO_PAGE_REF))
+			bio_release_pages(bio);
 		bio_put(bio);
 	}
 }
@@ -1650,7 +1688,8 @@ void bio_check_pages_dirty(struct bio *bio)
 			goto defer;
 	}
 
-	bio_release_pages(bio);
+	if (!bio_flagged(bio, BIO_NO_PAGE_REF))
+		bio_release_pages(bio);
 	bio_put(bio);
 	return;
 defer:
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 392e2bfb636f..051ab41d1c61 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -338,8 +338,9 @@ static void blkdev_bio_end_io(struct bio *bio)
 		struct bio_vec *bvec;
 		int i;
 
-		bio_for_each_segment_all(bvec, bio, i)
-			put_page(bvec->bv_page);
+		if (!bio_flagged(bio, BIO_NO_PAGE_REF))
+			bio_for_each_segment_all(bvec, bio, i)
+				put_page(bvec->bv_page);
 		bio_put(bio);
 	}
 }
diff --git a/fs/iomap.c b/fs/iomap.c
index 2ac9eb746d44..9389cf0a1c6f 100644
--- a/fs/iomap.c
+++ b/fs/iomap.c
@@ -1591,8 +1591,9 @@ static void iomap_dio_bio_end_io(struct bio *bio)
 		struct bio_vec *bvec;
 		int i;
 
-		bio_for_each_segment_all(bvec, bio, i)
-			put_page(bvec->bv_page);
+		if (!bio_flagged(bio, BIO_NO_PAGE_REF))
+			bio_for_each_segment_all(bvec, bio, i)
+				put_page(bvec->bv_page);
 		bio_put(bio);
 	}
 }
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index d66bf5f32610..791fee35df88 100644
--- a/include/linux/blk_types.h
+++ b/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 */
-- 
2.17.1


  parent reply	other threads:[~2019-02-08 17:34 UTC|newest]

Thread overview: 89+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-02-08 17:34 [PATCHSET v13] io_uring IO interface Jens Axboe
2019-02-08 17:34 ` [PATCH 01/19] fs: add an iopoll method to struct file_operations Jens Axboe
2019-02-09  9:20   ` Hannes Reinecke
2019-02-08 17:34 ` [PATCH 02/19] block: wire up block device iopoll method Jens Axboe
2019-02-09  9:22   ` Hannes Reinecke
2019-02-08 17:34 ` [PATCH 03/19] block: add bio_set_polled() helper Jens Axboe
2019-02-09  9:24   ` Hannes Reinecke
2019-02-08 17:34 ` [PATCH 04/19] iomap: wire up the iopoll method Jens Axboe
2019-02-09  9:25   ` Hannes Reinecke
2019-02-08 17:34 ` [PATCH 05/19] Add io_uring IO interface Jens Axboe
2019-02-08 22:12   ` Jann Horn
2019-02-09  4:15     ` Jens Axboe
2019-02-12 21:42       ` Jann Horn
2019-02-12 22:03         ` Jens Axboe
2019-02-12 22:06           ` Jens Axboe
2019-02-12 22:40             ` Jann Horn
2019-02-12 22:45               ` Jens Axboe
2019-02-12 22:52                 ` Jens Axboe
2019-02-12 22:57                   ` Jann Horn
2019-02-12 23:00                     ` Jens Axboe
2019-02-12 23:11                       ` Jann Horn
2019-02-12 23:19                         ` Jens Axboe
2019-02-12 23:28                           ` Jann Horn
2019-02-12 23:46                             ` Jens Axboe
2019-02-12 23:53                               ` Jens Axboe
2019-02-13  0:07                                 ` Andy Lutomirski
2019-02-13  0:14                                   ` Jann Horn
2019-02-13  0:24                                   ` Jens Axboe
2019-02-09  9:35   ` Hannes Reinecke
2019-02-08 17:34 ` [PATCH 06/19] io_uring: add fsync support Jens Axboe
2019-02-08 22:36   ` Jann Horn
2019-02-08 23:31     ` Jens Axboe
2019-02-09  9:37   ` Hannes Reinecke
2019-02-08 17:34 ` [PATCH 07/19] io_uring: support for IO polling Jens Axboe
2019-02-09  9:39   ` Hannes Reinecke
2019-02-08 17:34 ` [PATCH 08/19] fs: add fget_many() and fput_many() Jens Axboe
2019-02-09  9:41   ` Hannes Reinecke
2019-02-08 17:34 ` [PATCH 09/19] io_uring: use fget/fput_many() for file references Jens Axboe
2019-02-09  9:42   ` Hannes Reinecke
2019-02-08 17:34 ` [PATCH 10/19] io_uring: batch io_kiocb allocation Jens Axboe
2019-02-09  9:43   ` Hannes Reinecke
2019-02-08 17:34 ` Jens Axboe [this message]
2019-02-09  9:45   ` [PATCH 11/19] block: implement bio helper to add iter bvec pages to bio Hannes Reinecke
2019-02-08 17:34 ` [PATCH 12/19] io_uring: add support for pre-mapped user IO buffers Jens Axboe
2019-02-08 22:54   ` Jann Horn
2019-02-08 23:38     ` Jens Axboe
2019-02-09 16:50       ` Jens Axboe
2019-02-09  9:48   ` Hannes Reinecke
2019-02-08 17:34 ` [PATCH 13/19] net: split out functions related to registering inflight socket files Jens Axboe
2019-02-08 19:49   ` David Miller
2019-02-08 19:51     ` Jens Axboe
2019-02-09  9:49   ` Hannes Reinecke
2019-02-08 17:34 ` [PATCH 14/19] io_uring: add file set registration Jens Axboe
2019-02-08 20:26   ` Jann Horn
2019-02-09  0:16     ` Jens Axboe
2019-02-09  9:50   ` Hannes Reinecke
2019-02-08 17:34 ` [PATCH 15/19] io_uring: add submission polling Jens Axboe
2019-02-09  9:53   ` Hannes Reinecke
2019-02-08 17:34 ` [PATCH 16/19] io_uring: add io_kiocb ref count Jens Axboe
2019-02-08 17:34 ` [PATCH 17/19] io_uring: add support for IORING_OP_POLL Jens Axboe
2019-02-08 17:34 ` [PATCH 18/19] io_uring: allow workqueue item to handle multiple buffered requests Jens Axboe
2019-02-08 17:34 ` [PATCH 19/19] io_uring: add io_uring_event cache hit information Jens Axboe
2019-02-09 21:13 [PATCHSET v14] io_uring IO interface Jens Axboe
2019-02-09 21:13 ` [PATCH 11/19] block: implement bio helper to add iter bvec pages to bio Jens Axboe
2019-02-11 19:00 [PATCHSET v15] io_uring IO interface Jens Axboe
2019-02-11 19:00 ` [PATCH 11/19] block: implement bio helper to add iter bvec pages to bio Jens Axboe
2019-02-20 22:58   ` Ming Lei
2019-02-21 17:45     ` Jens Axboe
2019-02-26  3:46       ` Eric Biggers
2019-02-26  4:34         ` Jens Axboe
2019-02-26 15:54           ` Jens Axboe
2019-02-27  1:21             ` Ming Lei
2019-02-27  1:47               ` Jens Axboe
2019-02-27  1:53                 ` Ming Lei
2019-02-27  1:57                   ` Jens Axboe
2019-02-27  2:21                     ` Ming Lei
2019-02-27  2:28                       ` Jens Axboe
2019-02-27  2:37                         ` Ming Lei
2019-02-27  2:43                           ` Jens Axboe
2019-02-27  3:09                             ` Ming Lei
2019-02-27  3:37                               ` Jens Axboe
2019-02-27  3:43                                 ` Jens Axboe
2019-02-27  3:44                                 ` Ming Lei
2019-02-27  4:05                                   ` Jens Axboe
2019-02-27  4:06                                     ` Jens Axboe
2019-02-27 19:42                                       ` Christoph Hellwig
2019-02-28  8:37                                         ` Ming Lei
2019-02-27 23:35                         ` Ming Lei
2019-03-08  7:55                         ` Christoph Hellwig
2019-03-08  9:12                           ` Ming Lei
2019-03-08  8:18                     ` Christoph Hellwig

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20190208173423.27014-12-axboe@kernel.dk \
    --to=axboe@kernel.dk \
    --cc=avi@scylladb.com \
    --cc=hch@lst.de \
    --cc=jannh@google.com \
    --cc=jmoyer@redhat.com \
    --cc=linux-aio@kvack.org \
    --cc=linux-api@vger.kernel.org \
    --cc=linux-block@vger.kernel.org \
    --cc=viro@ZenIV.linux.org.uk \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).