From: Jakub Kicinski <kuba@kernel•org>
To: netdev@vger•kernel.org
Cc: almasrymina@google•com, hawk@kernel•org,
ilias.apalodimas@linaro•org, edumazet@google•com,
dsahern@gmail•com, michael.chan@broadcom•com, willemb@google•com,
Jakub Kicinski <kuba@kernel•org>
Subject: [RFC 05/12] net: page_pool: factor out releasing DMA from releasing the page
Date: Fri, 7 Jul 2023 11:39:28 -0700 [thread overview]
Message-ID: <20230707183935.997267-6-kuba@kernel.org> (raw)
In-Reply-To: <20230707183935.997267-1-kuba@kernel.org>
Releasing the DMA mapping will be useful for other types
of pages, so factor it out. Make sure compiler inlines it,
to avoid any regressions.
Signed-off-by: Jakub Kicinski <kuba@kernel•org>
---
net/core/page_pool.c | 25 ++++++++++++++++---------
1 file changed, 16 insertions(+), 9 deletions(-)
diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index 7ca456bfab71..09f8c34ad4a7 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -487,21 +487,16 @@ static s32 page_pool_inflight(struct page_pool *pool)
return inflight;
}
-/* Disconnects a page (from a page_pool). API users can have a need
- * to disconnect a page (from a page_pool), to allow it to be used as
- * a regular page (that will eventually be returned to the normal
- * page-allocator via put_page).
- */
-static void page_pool_return_page(struct page_pool *pool, struct page *page)
+static __always_inline
+void __page_pool_release_page_dma(struct page_pool *pool, struct page *page)
{
dma_addr_t dma;
- int count;
if (!(pool->p.flags & PP_FLAG_DMA_MAP))
/* Always account for inflight pages, even if we didn't
* map them
*/
- goto skip_dma_unmap;
+ return;
dma = page_pool_get_dma_addr(page);
@@ -510,7 +505,19 @@ static void page_pool_return_page(struct page_pool *pool, struct page *page)
PAGE_SIZE << pool->p.order, pool->p.dma_dir,
DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING);
page_pool_set_dma_addr(page, 0);
-skip_dma_unmap:
+}
+
+/* Disconnects a page (from a page_pool). API users can have a need
+ * to disconnect a page (from a page_pool), to allow it to be used as
+ * a regular page (that will eventually be returned to the normal
+ * page-allocator via put_page).
+ */
+void page_pool_return_page(struct page_pool *pool, struct page *page)
+{
+ int count;
+
+ __page_pool_release_page_dma(pool, page);
+
page_pool_clear_pp_info(page);
/* This may be the last page returned, releasing the pool, so
--
2.41.0
next prev parent reply other threads:[~2023-07-07 18:39 UTC|newest]
Thread overview: 33+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-07-07 18:39 [RFC 00/12] net: huge page backed page_pool Jakub Kicinski
2023-07-07 18:39 ` [RFC 01/12] net: hack together some page sharing Jakub Kicinski
2023-07-07 18:39 ` [RFC 02/12] net: create a 1G-huge-page-backed allocator Jakub Kicinski
2023-07-07 18:39 ` [RFC 03/12] net: page_pool: hide page_pool_release_page() Jakub Kicinski
2023-07-07 18:39 ` [RFC 04/12] net: page_pool: merge page_pool_release_page() with page_pool_return_page() Jakub Kicinski
2023-07-10 16:07 ` Jesper Dangaard Brouer
2023-07-07 18:39 ` Jakub Kicinski [this message]
2023-07-07 18:39 ` [RFC 06/12] net: page_pool: create hooks for custom page providers Jakub Kicinski
2023-07-07 19:50 ` Mina Almasry
2023-07-07 22:28 ` Jakub Kicinski
2023-07-07 18:39 ` [RFC 07/12] net: page_pool: add huge page backed memory providers Jakub Kicinski
2023-07-07 18:39 ` [RFC 08/12] eth: bnxt: let the page pool manage the DMA mapping Jakub Kicinski
2023-07-10 10:12 ` Jesper Dangaard Brouer
2023-07-26 6:56 ` Ilias Apalodimas
2023-07-07 18:39 ` [RFC 09/12] eth: bnxt: use the page pool for data pages Jakub Kicinski
2023-07-10 4:22 ` Michael Chan
2023-07-10 17:04 ` Jakub Kicinski
2023-07-07 18:39 ` [RFC 10/12] eth: bnxt: make sure we make for recycle skbs before freeing them Jakub Kicinski
2023-07-07 18:39 ` [RFC 11/12] eth: bnxt: wrap coherent allocations into helpers Jakub Kicinski
2023-07-07 18:39 ` [RFC 12/12] eth: bnxt: hack in the use of MEP Jakub Kicinski
2023-07-07 19:45 ` [RFC 00/12] net: huge page backed page_pool Mina Almasry
2023-07-07 22:45 ` Jakub Kicinski
2023-07-10 17:31 ` Mina Almasry
2023-07-11 15:49 ` Jesper Dangaard Brouer
2023-07-12 0:08 ` Jakub Kicinski
2023-07-12 11:47 ` Yunsheng Lin
2023-07-12 12:43 ` Jesper Dangaard Brouer
2023-07-12 17:01 ` Jakub Kicinski
2023-07-14 13:05 ` Yunsheng Lin
2023-07-12 14:00 ` Jesper Dangaard Brouer
2023-07-12 17:19 ` Jakub Kicinski
2023-07-13 10:07 ` Jesper Dangaard Brouer
2023-07-13 16:27 ` Jakub Kicinski
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=20230707183935.997267-6-kuba@kernel.org \
--to=kuba@kernel$(echo .)org \
--cc=almasrymina@google$(echo .)com \
--cc=dsahern@gmail$(echo .)com \
--cc=edumazet@google$(echo .)com \
--cc=hawk@kernel$(echo .)org \
--cc=ilias.apalodimas@linaro$(echo .)org \
--cc=michael.chan@broadcom$(echo .)com \
--cc=netdev@vger$(echo .)kernel.org \
--cc=willemb@google$(echo .)com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
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