Received-SPF: pass (google.com: domain of linux-kernel+bounces-94756-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:45e3:2400::1 as permitted sender) client-ip=2604:1380:45e3:2400::1;
Date: Wed,  6 Mar 2024 15:59:19 -0800
In-Reply-To: <20240306235922.282781-1-almasrymina@google.com>
Precedence: bulk
Mime-Version: 1.0
References: <20240306235922.282781-1-almasrymina@google.com>
Message-ID: <20240306235922.282781-2-almasrymina@google.com>
Subject: [RFC PATCH net-next v1 1/2] net: mirror skb frag ref/unref helpers
From: Mina Almasry <almasrymina@google.com>
To: netdev@vger.kernel.org, linux-kernel@vger.kernel.org, 
	linux-rdma@vger.kernel.org
Cc: Mina Almasry <almasrymina@google.com>, Mirko Lindner <mlindner@marvell.com>, 
	Stephen Hemminger <stephen@networkplumber.org>, "David S. Miller" <davem@davemloft.net>, 
	Eric Dumazet <edumazet@google.com>, Jakub Kicinski <kuba@kernel.org>, Paolo Abeni <pabeni@redhat.com>, 
	Tariq Toukan <tariqt@nvidia.com>, Boris Pismenny <borisp@nvidia.com>, 
	John Fastabend <john.fastabend@gmail.com>, Dragos Tatulea <dtatulea@nvidia.com>
Content-Type: text/plain; charset="UTF-8"

Refactor some of the skb frag ref/unref helpers for improved clarity.

Implement napi_pp_get_page() to be the mirror counterpart of
napi_pp_put_page().

Implement napi_frag_ref() to be the mirror counterpart of
napi_frag_unref().

Improve __skb_frag_ref() to become a mirror counterpart of
__skb_frag_unref(). Previously unref could handle pp & non-pp pages,
while the ref could only handle non-pp pages. Now both the ref & unref
helpers can correctly handle both pp & non-pp pages.

Now that __skb_frag_ref() can handle both pp & non-pp pages, remove
skb_pp_frag_ref(), and use __skb_frag_ref() instead.  This lets us
remove pp specific handling from skb_try_coalesce.

Signed-off-by: Mina Almasry <almasrymina@google.com>

---
 include/linux/skbuff.h | 24 +++++++++++++++---
 net/core/skbuff.c      | 56 ++++++++++++++----------------------------
 2 files changed, 39 insertions(+), 41 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index d577e0bee18d..51316b0e20bc 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -3477,15 +3477,31 @@ static inline struct page *skb_frag_page(const skb_frag_t *frag)
 	return netmem_to_page(frag->netmem);
 }
 
+bool napi_pp_get_page(struct page *page);
+
+static inline void napi_frag_ref(skb_frag_t *frag, bool recycle)
+{
+#ifdef CONFIG_PAGE_POOL
+	struct page *page = skb_frag_page(frag);
+
+	if (recycle && napi_pp_get_page(page))
+		return;
+#endif
+	get_page(page);
+}
+
 /**
  * __skb_frag_ref - take an addition reference on a paged fragment.
  * @frag: the paged fragment
+ * @recycle: skb->pp_recycle param of the parent skb.
  *
- * Takes an additional reference on the paged fragment @frag.
+ * Takes an additional reference on the paged fragment @frag. Obtains the
+ * correct reference count depending on whether skb->pp_recycle is set and
+ * whether the frag is a page pool frag.
  */
-static inline void __skb_frag_ref(skb_frag_t *frag)
+static inline void __skb_frag_ref(skb_frag_t *frag, bool recycle)
 {
-	get_page(skb_frag_page(frag));
+	napi_frag_ref(frag, recycle);
 }
 
 /**
@@ -3497,7 +3513,7 @@ static inline void __skb_frag_ref(skb_frag_t *frag)
  */
 static inline void skb_frag_ref(struct sk_buff *skb, int f)
 {
-	__skb_frag_ref(&skb_shinfo(skb)->frags[f]);
+	__skb_frag_ref(&skb_shinfo(skb)->frags[f], skb->pp_recycle);
 }
 
 int skb_pp_cow_data(struct page_pool *pool, struct sk_buff **pskb,
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 1f918e602bc4..6d234faa9d9e 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -1006,6 +1006,21 @@ int skb_cow_data_for_xdp(struct page_pool *pool, struct sk_buff **pskb,
 EXPORT_SYMBOL(skb_cow_data_for_xdp);
 
 #if IS_ENABLED(CONFIG_PAGE_POOL)
+bool napi_pp_get_page(struct page *page)
+{
+
+	struct page *head_page;
+
+	head_page = compound_head(page);
+
+	if (!is_pp_page(page))
+		return false;
+
+	page_pool_ref_page(head_page);
+	return true;
+}
+EXPORT_SYMBOL(napi_pp_get_page);
+
 bool napi_pp_put_page(struct page *page, bool napi_safe)
 {
 	bool allow_direct = false;
@@ -1058,37 +1073,6 @@ static bool skb_pp_recycle(struct sk_buff *skb, void *data, bool napi_safe)
 	return napi_pp_put_page(virt_to_page(data), napi_safe);
 }
 
-/**
- * skb_pp_frag_ref() - Increase fragment references of a page pool aware skb
- * @skb:	page pool aware skb
- *
- * Increase the fragment reference count (pp_ref_count) of a skb. This is
- * intended to gain fragment references only for page pool aware skbs,
- * i.e. when skb->pp_recycle is true, and not for fragments in a
- * non-pp-recycling skb. It has a fallback to increase references on normal
- * pages, as page pool aware skbs may also have normal page fragments.
- */
-static int skb_pp_frag_ref(struct sk_buff *skb)
-{
-	struct skb_shared_info *shinfo;
-	struct page *head_page;
-	int i;
-
-	if (!skb->pp_recycle)
-		return -EINVAL;
-
-	shinfo = skb_shinfo(skb);
-
-	for (i = 0; i < shinfo->nr_frags; i++) {
-		head_page = compound_head(skb_frag_page(&shinfo->frags[i]));
-		if (likely(is_pp_page(head_page)))
-			page_pool_ref_page(head_page);
-		else
-			page_ref_inc(head_page);
-	}
-	return 0;
-}
-
 static void skb_kfree_head(void *head, unsigned int end_offset)
 {
 	if (end_offset == SKB_SMALL_HEAD_HEADROOM)
@@ -4199,7 +4183,7 @@ int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen)
 			to++;
 
 		} else {
-			__skb_frag_ref(fragfrom);
+			__skb_frag_ref(fragfrom, skb->pp_recycle);
 			skb_frag_page_copy(fragto, fragfrom);
 			skb_frag_off_copy(fragto, fragfrom);
 			skb_frag_size_set(fragto, todo);
@@ -4849,7 +4833,7 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb,
 			}
 
 			*nskb_frag = (i < 0) ? skb_head_frag_to_page_desc(frag_skb) : *frag;
-			__skb_frag_ref(nskb_frag);
+			__skb_frag_ref(nskb_frag, nskb->pp_recycle);
 			size = skb_frag_size(nskb_frag);
 
 			if (pos < offset) {
@@ -5980,10 +5964,8 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from,
 	/* if the skb is not cloned this does nothing
 	 * since we set nr_frags to 0.
 	 */
-	if (skb_pp_frag_ref(from)) {
-		for (i = 0; i < from_shinfo->nr_frags; i++)
-			__skb_frag_ref(&from_shinfo->frags[i]);
-	}
+	for (i = 0; i < from_shinfo->nr_frags; i++)
+		__skb_frag_ref(&from_shinfo->frags[i], from->pp_recycle);
 
 	to->truesize += delta;
 	to->len += len;
-- 
2.44.0.278.ge034bb2e1d-goog