public inbox for [email protected]
 help / color / mirror / Atom feed
From: Chenliang Li <[email protected]>
To: [email protected], [email protected]
Cc: [email protected], [email protected],
	[email protected], [email protected],
	[email protected], Chenliang Li <[email protected]>
Subject: [PATCH v3 4/5] io_uring/rsrc: enable multi-hugepage buffer coalescing
Date: Mon, 13 May 2024 16:22:59 +0800	[thread overview]
Message-ID: <[email protected]> (raw)
In-Reply-To: <[email protected]>

Modify the original buffer registration path to expand the
one-hugepage coalescing feature to work with multi-hugepage
buffers. Separated from previous patches to make it more
easily reviewed.

Signed-off-by: Chenliang Li <[email protected]>
---
 io_uring/rsrc.c | 44 ++++++++------------------------------------
 1 file changed, 8 insertions(+), 36 deletions(-)

diff --git a/io_uring/rsrc.c b/io_uring/rsrc.c
index 53fac5f27bbf..5e5c1d6f3501 100644
--- a/io_uring/rsrc.c
+++ b/io_uring/rsrc.c
@@ -1047,7 +1047,7 @@ static int io_sqe_buffer_register(struct io_ring_ctx *ctx, struct iovec *iov,
 	unsigned long off;
 	size_t size;
 	int ret, nr_pages, i;
-	struct folio *folio = NULL;
+	struct io_imu_folio_data data;
 
 	*pimu = (struct io_mapped_ubuf *)&dummy_ubuf;
 	if (!iov->iov_base)
@@ -1062,30 +1062,11 @@ static int io_sqe_buffer_register(struct io_ring_ctx *ctx, struct iovec *iov,
 		goto done;
 	}
 
-	/* If it's a huge page, try to coalesce them into a single bvec entry */
-	if (nr_pages > 1) {
-		folio = page_folio(pages[0]);
-		for (i = 1; i < nr_pages; i++) {
-			/*
-			 * Pages must be consecutive and on the same folio for
-			 * this to work
-			 */
-			if (page_folio(pages[i]) != folio ||
-			    pages[i] != pages[i - 1] + 1) {
-				folio = NULL;
-				break;
-			}
-		}
-		if (folio) {
-			/*
-			 * The pages are bound to the folio, it doesn't
-			 * actually unpin them but drops all but one reference,
-			 * which is usually put down by io_buffer_unmap().
-			 * Note, needs a better helper.
-			 */
-			unpin_user_pages(&pages[1], nr_pages - 1);
-			nr_pages = 1;
-		}
+	/* If it's huge page(s), try to coalesce them into fewer bvec entries */
+	if (io_sqe_buffer_try_coalesce(pages, nr_pages, &data)) {
+		ret = io_coalesced_imu_alloc(ctx, iov, pimu, last_hpage,
+						pages, &data);
+		goto done;
 	}
 
 	imu = kvmalloc(struct_size(imu, bvec, nr_pages), GFP_KERNEL);
@@ -1109,10 +1090,6 @@ static int io_sqe_buffer_register(struct io_ring_ctx *ctx, struct iovec *iov,
 	*pimu = imu;
 	ret = 0;
 
-	if (folio) {
-		bvec_set_page(&imu->bvec[0], pages[0], size, off);
-		goto done;
-	}
 	for (i = 0; i < nr_pages; i++) {
 		size_t vec_len;
 
@@ -1218,23 +1195,18 @@ int io_import_fixed(int ddir, struct iov_iter *iter,
 		 * we know that:
 		 *
 		 * 1) it's a BVEC iter, we set it up
-		 * 2) all bvecs are PAGE_SIZE in size, except potentially the
+		 * 2) all bvecs are the same in size, except potentially the
 		 *    first and last bvec
 		 *
 		 * So just find our index, and adjust the iterator afterwards.
 		 * If the offset is within the first bvec (or the whole first
 		 * bvec, just use iov_iter_advance(). This makes it easier
 		 * since we can just skip the first segment, which may not
-		 * be PAGE_SIZE aligned.
+		 * be folio_size aligned.
 		 */
 		const struct bio_vec *bvec = imu->bvec;
 
 		if (offset < bvec->bv_len) {
-			/*
-			 * Note, huge pages buffers consists of one large
-			 * bvec entry and should always go this way. The other
-			 * branch doesn't expect non PAGE_SIZE'd chunks.
-			 */
 			iter->bvec = bvec;
 			iter->nr_segs = bvec->bv_len;
 			iter->count -= offset;
-- 
2.34.1


  parent reply	other threads:[~2024-05-13  8:33 UTC|newest]

Thread overview: 12+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <CGME20240513082306epcas5p2fd8ea6fd88b2c4ab1d17b1508fe2af97@epcas5p2.samsung.com>
2024-05-13  8:22 ` [PATCH v3 0/5] io_uring/rsrc: coalescing multi-hugepage registered buffers Chenliang Li
     [not found]   ` <CGME20240513082308epcas5p3c38ce4d44fa1613988bbae84eaec41b9@epcas5p3.samsung.com>
2024-05-13  8:22     ` [PATCH v3 1/5] io_uring/rsrc: add hugepage buffer coalesce helpers Chenliang Li
     [not found]   ` <CGME20240513082310epcas5p27576a80eae3ee09e40102b179ce46fa9@epcas5p2.samsung.com>
2024-05-13  8:22     ` [PATCH v3 2/5] io_uring/rsrc: store folio shift and mask into imu Chenliang Li
     [not found]   ` <CGME20240513082311epcas5p3556d301a1f1faca0c6b613555324861e@epcas5p3.samsung.com>
2024-05-13  8:22     ` [PATCH v3 3/5] io_uring/rsrc: add init and account functions for coalesced imus Chenliang Li
     [not found]   ` <CGME20240513082313epcas5p2a781d3393e4bf92d13d04ac62bb28fb7@epcas5p2.samsung.com>
2024-05-13  8:22     ` Chenliang Li [this message]
2024-05-13 12:11       ` [PATCH v3 4/5] io_uring/rsrc: enable multi-hugepage buffer coalescing Anuj gupta
     [not found]   ` <CGME20240513082314epcas5p309fa70575596792b5c9923ce76a3778f@epcas5p3.samsung.com>
2024-05-13  8:23     ` [PATCH v3 5/5] liburing: add test cases for hugepage registered buffers Chenliang Li
2024-05-13 12:09   ` [PATCH v3 0/5] io_uring/rsrc: coalescing multi-hugepage " Anuj gupta
2024-05-13 13:40     ` Jens Axboe
     [not found]       ` <CGME20240514001813epcas5p455c8a3dd6f2164626a526c05f7fd92c4@epcas5p4.samsung.com>
2024-05-14  0:18         ` Chenliang Li
     [not found]     ` <CGME20240514001443epcas5p362c60c233ed2aecdb5e144099b44d9be@epcas5p3.samsung.com>
2024-05-14  0:14       ` [PATCH v3 4/5] io_uring/rsrc: enable multi-hugepage buffer coalescing Chenliang Li
     [not found]     ` <CGME20240514001620epcas5p10d8c08ffc3dbd746213df21e47df19f7@epcas5p1.samsung.com>
2024-05-14  0:16       ` [PATCH v3 0/5] io_uring/rsrc: coalescing multi-hugepage registered buffers Chenliang Li

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 \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    /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