LKML Archive on lore.kernel.org
help / color / mirror / Atom feed
From: Yunsheng Lin <linyunsheng@huawei.com>
To: <davem@davemloft.net>, <kuba@kernel.org>
Cc: <alexander.duyck@gmail.com>, <linux@armlinux.org.uk>,
	<mw@semihalf.com>, <linuxarm@openeuler.org>,
	<yisen.zhuang@huawei.com>, <salil.mehta@huawei.com>,
	<thomas.petazzoni@bootlin.com>, <hawk@kernel.org>,
	<ilias.apalodimas@linaro.org>, <ast@kernel.org>,
	<daniel@iogearbox.net>, <john.fastabend@gmail.com>,
	<akpm@linux-foundation.org>, <peterz@infradead.org>,
	<will@kernel.org>, <willy@infradead.org>, <vbabka@suse.cz>,
	<fenghua.yu@intel.com>, <guro@fb.com>, <peterx@redhat.com>,
	<feng.tang@intel.com>, <jgg@ziepe.ca>, <mcroce@microsoft.com>,
	<hughd@google.com>, <jonathan.lemon@gmail.com>, <alobakin@pm.me>,
	<willemb@google.com>, <wenxu@ucloud.cn>,
	<cong.wang@bytedance.com>, <haokexin@gmail.com>,
	<nogikh@google.com>, <elver@google.com>, <yhs@fb.com>,
	<kpsingh@kernel.org>, <andrii@kernel.org>, <kafai@fb.com>,
	<songliubraving@fb.com>, <netdev@vger.kernel.org>,
	<linux-kernel@vger.kernel.org>, <bpf@vger.kernel.org>,
	<chenhao288@hisilicon.com>
Subject: [PATCH net-next v2 3/4] page_pool: add frag page recycling support in page pool
Date: Fri, 6 Aug 2021 10:46:21 +0800	[thread overview]
Message-ID: <1628217982-53533-4-git-send-email-linyunsheng@huawei.com> (raw)
In-Reply-To: <1628217982-53533-1-git-send-email-linyunsheng@huawei.com>

Currently page pool only support page recycling when there
is only one user of the page, and the split page reusing
implemented in the most driver can not use the page pool as
bing-pong way of reusing requires the multi user support in
page pool.

Those reusing or recycling has below limitations:
1. page from page pool can only be used be one user in order
   for the page recycling to happen.
2. Bing-pong way of reusing in most driver does not support
   multi desc using different part of the same page in order
   to save memory.

So add multi-users support and frag page recycling in page
pool to overcome the above limitation.

Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
---
 include/net/page_pool.h | 15 +++++++++
 net/core/page_pool.c    | 87 +++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 102 insertions(+)

diff --git a/include/net/page_pool.h b/include/net/page_pool.h
index 42e6997..a408240 100644
--- a/include/net/page_pool.h
+++ b/include/net/page_pool.h
@@ -91,6 +91,9 @@ struct page_pool {
 	unsigned long defer_warn;
 
 	u32 pages_state_hold_cnt;
+	unsigned int frag_offset;
+	struct page *frag_page;
+	long frag_users;
 
 	/*
 	 * Data structure for allocation side
@@ -140,6 +143,18 @@ static inline struct page *page_pool_dev_alloc_pages(struct page_pool *pool)
 	return page_pool_alloc_pages(pool, gfp);
 }
 
+struct page *page_pool_alloc_frag(struct page_pool *pool, unsigned int *offset,
+				  unsigned int size, gfp_t gfp);
+
+static inline struct page *page_pool_dev_alloc_frag(struct page_pool *pool,
+						    unsigned int *offset,
+						    unsigned int size)
+{
+	gfp_t gfp = (GFP_ATOMIC | __GFP_NOWARN);
+
+	return page_pool_alloc_frag(pool, offset, size, gfp);
+}
+
 /* get the stored dma direction. A driver might decide to treat this locally and
  * avoid the extra cache line from page_pool to determine the direction
  */
diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index 68fab94..ac11604 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -24,6 +24,8 @@
 #define DEFER_TIME (msecs_to_jiffies(1000))
 #define DEFER_WARN_INTERVAL (60 * HZ)
 
+#define BIAS_MAX	LONG_MAX
+
 static int page_pool_init(struct page_pool *pool,
 			  const struct page_pool_params *params)
 {
@@ -423,6 +425,11 @@ static __always_inline struct page *
 __page_pool_put_page(struct page_pool *pool, struct page *page,
 		     unsigned int dma_sync_size, bool allow_direct)
 {
+	/* It is not the last user for the page frag case */
+	if (pool->p.flags & PP_FLAG_PAGE_FRAG &&
+	    page_pool_atomic_sub_frag_count_return(page, 1))
+		return NULL;
+
 	/* This allocator is optimized for the XDP mode that uses
 	 * one-frame-per-page, but have fallbacks that act like the
 	 * regular page allocator APIs.
@@ -515,6 +522,84 @@ void page_pool_put_page_bulk(struct page_pool *pool, void **data,
 }
 EXPORT_SYMBOL(page_pool_put_page_bulk);
 
+static struct page *page_pool_drain_frag(struct page_pool *pool,
+					 struct page *page)
+{
+	long drain_count = BIAS_MAX - pool->frag_users;
+
+	/* Some user is still using the page frag */
+	if (likely(page_pool_atomic_sub_frag_count_return(page,
+							  drain_count)))
+		return NULL;
+
+	if (page_ref_count(page) == 1 && !page_is_pfmemalloc(page)) {
+		if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV)
+			page_pool_dma_sync_for_device(pool, page, -1);
+
+		return page;
+	}
+
+	page_pool_return_page(pool, page);
+	return NULL;
+}
+
+static void page_pool_free_frag(struct page_pool *pool)
+{
+	long drain_count = BIAS_MAX - pool->frag_users;
+	struct page *page = pool->frag_page;
+
+	pool->frag_page = NULL;
+
+	if (!page ||
+	    page_pool_atomic_sub_frag_count_return(page, drain_count))
+		return;
+
+	page_pool_return_page(pool, page);
+}
+
+struct page *page_pool_alloc_frag(struct page_pool *pool,
+				  unsigned int *offset,
+				  unsigned int size, gfp_t gfp)
+{
+	unsigned int max_size = PAGE_SIZE << pool->p.order;
+	struct page *page = pool->frag_page;
+
+	if (WARN_ON(!(pool->p.flags & PP_FLAG_PAGE_FRAG) ||
+		    size > max_size))
+		return NULL;
+
+	size = ALIGN(size, dma_get_cache_alignment());
+	*offset = pool->frag_offset;
+
+	if (page && *offset + size > max_size) {
+		page = page_pool_drain_frag(pool, page);
+		if (page)
+			goto frag_reset;
+	}
+
+	if (!page) {
+		page = page_pool_alloc_pages(pool, gfp);
+		if (unlikely(!page)) {
+			pool->frag_page = NULL;
+			return NULL;
+		}
+
+		pool->frag_page = page;
+
+frag_reset:
+		pool->frag_users = 1;
+		*offset = 0;
+		pool->frag_offset = size;
+		page_pool_set_frag_count(page, BIAS_MAX);
+		return page;
+	}
+
+	pool->frag_users++;
+	pool->frag_offset = *offset + size;
+	return page;
+}
+EXPORT_SYMBOL(page_pool_alloc_frag);
+
 static void page_pool_empty_ring(struct page_pool *pool)
 {
 	struct page *page;
@@ -620,6 +705,8 @@ void page_pool_destroy(struct page_pool *pool)
 	if (!page_pool_put(pool))
 		return;
 
+	page_pool_free_frag(pool);
+
 	if (!page_pool_release(pool))
 		return;
 
-- 
2.7.4


  parent reply	other threads:[~2021-08-06  2:47 UTC|newest]

Thread overview: 19+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-08-06  2:46 [PATCH net-next v2 0/4] add frag page " Yunsheng Lin
2021-08-06  2:46 ` [PATCH net-next v2 1/4] page_pool: keep pp info as long as page pool owns the page Yunsheng Lin
2021-08-06  2:46 ` [PATCH net-next v2 2/4] page_pool: add interface to manipulate frag count in page pool Yunsheng Lin
2021-08-10 14:58   ` Jesper Dangaard Brouer
2021-08-11  0:48     ` Yunsheng Lin
2021-08-12 15:17   ` Jesper Dangaard Brouer
2021-08-06  2:46 ` Yunsheng Lin [this message]
2021-08-06  2:46 ` [PATCH net-next v2 4/4] net: hns3: support skb's frag page recycling based on " Yunsheng Lin
2021-09-08  8:31   ` moyufeng
2021-09-08 15:08     ` Jakub Kicinski
2021-09-08 15:26       ` Ilias Apalodimas
2021-09-08 15:57         ` Jakub Kicinski
2021-09-08 16:47           ` Jesper Dangaard Brouer
2021-09-08 16:51           ` Ilias Apalodimas
2021-08-10 14:01 ` [PATCH net-next v2 0/4] add frag page support in " Jakub Kicinski
2021-08-10 14:23   ` Jesper Dangaard Brouer
2021-08-10 14:43     ` Jakub Kicinski
2021-08-10 15:09       ` Alexander Duyck
2021-08-11  1:06         ` [Linuxarm] " Yunsheng Lin

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=1628217982-53533-4-git-send-email-linyunsheng@huawei.com \
    --to=linyunsheng@huawei.com \
    --cc=akpm@linux-foundation.org \
    --cc=alexander.duyck@gmail.com \
    --cc=alobakin@pm.me \
    --cc=andrii@kernel.org \
    --cc=ast@kernel.org \
    --cc=bpf@vger.kernel.org \
    --cc=chenhao288@hisilicon.com \
    --cc=cong.wang@bytedance.com \
    --cc=daniel@iogearbox.net \
    --cc=davem@davemloft.net \
    --cc=elver@google.com \
    --cc=feng.tang@intel.com \
    --cc=fenghua.yu@intel.com \
    --cc=guro@fb.com \
    --cc=haokexin@gmail.com \
    --cc=hawk@kernel.org \
    --cc=hughd@google.com \
    --cc=ilias.apalodimas@linaro.org \
    --cc=jgg@ziepe.ca \
    --cc=john.fastabend@gmail.com \
    --cc=jonathan.lemon@gmail.com \
    --cc=kafai@fb.com \
    --cc=kpsingh@kernel.org \
    --cc=kuba@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux@armlinux.org.uk \
    --cc=linuxarm@openeuler.org \
    --cc=mcroce@microsoft.com \
    --cc=mw@semihalf.com \
    --cc=netdev@vger.kernel.org \
    --cc=nogikh@google.com \
    --cc=peterx@redhat.com \
    --cc=peterz@infradead.org \
    --cc=salil.mehta@huawei.com \
    --cc=songliubraving@fb.com \
    --cc=thomas.petazzoni@bootlin.com \
    --cc=vbabka@suse.cz \
    --cc=wenxu@ucloud.cn \
    --cc=will@kernel.org \
    --cc=willemb@google.com \
    --cc=willy@infradead.org \
    --cc=yhs@fb.com \
    --cc=yisen.zhuang@huawei.com \
    --subject='Re: [PATCH net-next v2 3/4] page_pool: add frag page recycling support in page pool' \
    /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

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).