Message-ID: <20240403152844.4061814-3-almasrymina@google.com>
Date: Wed,  3 Apr 2024 08:28:41 -0700
From: Mina Almasry <almasrymina@...gle.com>
To: netdev@...r.kernel.org, linux-kernel@...r.kernel.org
Cc: Mina Almasry <almasrymina@...gle.com>, Ayush Sawal <ayush.sawal@...lsio.com>, 
	"David S. Miller" <davem@...emloft.net>, Eric Dumazet <edumazet@...gle.com>, 
	Jakub Kicinski <kuba@...nel.org>, Paolo Abeni <pabeni@...hat.com>, 
	Steffen Klassert <steffen.klassert@...unet.com>, Herbert Xu <herbert@...dor.apana.org.au>, 
	David Ahern <dsahern@...nel.org>, Boris Pismenny <borisp@...dia.com>, 
	John Fastabend <john.fastabend@...il.com>, Tariq Toukan <tariqt@...dia.com>, 
	Dragos Tatulea <dtatulea@...dia.com>, Simon Horman <horms@...nel.org>, 
	Sabrina Dubroca <sd@...asysnail.net>, 
	"Ahelenia Ziemiańska" <nabijaczleweli@...ijaczleweli.xyz>, 
	Pavan Chebbi <pavan.chebbi@...adcom.com>, 
	Christophe JAILLET <christophe.jaillet@...adoo.fr>, Yunsheng Lin <linyunsheng@...wei.com>, 
	Florian Westphal <fw@...len.de>, David Howells <dhowells@...hat.com>, 
	Alexander Lobakin <aleksander.lobakin@...el.com>, Lorenzo Bianconi <lorenzo@...nel.org>, 
	Johannes Berg <johannes.berg@...el.com>
Subject: [PATCH net-next v4 2/3] net: mirror skb frag ref/unref helpers

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 skb_page_ref() to be the mirror of skb_page_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.

Additionally, since __skb_frag_ref() can now handle both pp & non-pp
pages, a latent issue in skb_shift() should now be fixed. Previously
this function would do a non-pp ref & pp unref on potential pp frags
(fragfrom). After this patch, skb_shift() should correctly do a pp
ref/unref on pp frags.

Signed-off-by: Mina Almasry <almasrymina@...gle.com>
Reviewed-by: Dragos Tatulea <dtatulea@...dia.com>

---

v4:
- pass skb->pp_recycle instead of 'false' in __skb_frag_ref in
  chcr_ktls.c & cassini.c.
- Add some details on the changes to skb_shift() in this commit in the
  commit message.

v3:
- Fix build errors reported by patchwork.
- Fix drivers/net/veth.c & tls_device_fallback.c callsite I missed to update.
- Fix page_pool_ref_page(head_page) -> page_pool_ref_page(page)

---
 .../chelsio/inline_crypto/ch_ktls/chcr_ktls.c |  2 +-
 drivers/net/ethernet/sun/cassini.c            |  4 +-
 drivers/net/veth.c                            |  2 +-
 include/linux/skbuff.h                        | 22 ++++++--
 net/core/skbuff.c                             | 53 ++++++-------------
 net/tls/tls_device_fallback.c                 |  2 +-
 6 files changed, 39 insertions(+), 46 deletions(-)

diff --git a/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c b/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c
index 6482728794dd..d7e8deafddf1 100644
--- a/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c
+++ b/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c
@@ -1658,7 +1658,7 @@ static void chcr_ktls_copy_record_in_skb(struct sk_buff *nskb,
 	for (i = 0; i < record->num_frags; i++) {
 		skb_shinfo(nskb)->frags[i] = record->frags[i];
 		/* increase the frag ref count */
-		__skb_frag_ref(&skb_shinfo(nskb)->frags[i]);
+		__skb_frag_ref(&skb_shinfo(nskb)->frags[i], nskb->pp_recycle);
 	}
 
 	skb_shinfo(nskb)->nr_frags = record->num_frags;
diff --git a/drivers/net/ethernet/sun/cassini.c b/drivers/net/ethernet/sun/cassini.c
index bfb903506367..31878256feee 100644
--- a/drivers/net/ethernet/sun/cassini.c
+++ b/drivers/net/ethernet/sun/cassini.c
@@ -1999,7 +1999,7 @@ static int cas_rx_process_pkt(struct cas *cp, struct cas_rx_comp *rxc,
 		skb->len      += hlen - swivel;
 
 		skb_frag_fill_page_desc(frag, page->buffer, off, hlen - swivel);
-		__skb_frag_ref(frag);
+		__skb_frag_ref(frag, skb->pp_recycle);
 
 		/* any more data? */
 		if ((words[0] & RX_COMP1_SPLIT_PKT) && ((dlen -= hlen) > 0)) {
@@ -2023,7 +2023,7 @@ static int cas_rx_process_pkt(struct cas *cp, struct cas_rx_comp *rxc,
 			frag++;
 
 			skb_frag_fill_page_desc(frag, page->buffer, 0, hlen);
-			__skb_frag_ref(frag);
+			__skb_frag_ref(frag, skb->pp_recycle);
 			RX_USED_ADD(page, hlen + cp->crc_size);
 		}
 
diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index bcdfbf61eb66..6160a3e8d341 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -716,7 +716,7 @@ static void veth_xdp_get(struct xdp_buff *xdp)
 		return;
 
 	for (i = 0; i < sinfo->nr_frags; i++)
-		__skb_frag_ref(&sinfo->frags[i]);
+		__skb_frag_ref(&sinfo->frags[i], false);
 }
 
 static int veth_convert_skb_to_xdp_buff(struct veth_rq *rq,
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 7dcbd27e1497..71caeee061ca 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -3483,15 +3483,29 @@ 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 skb_page_ref(struct page *page, bool recycle)
+{
+#ifdef CONFIG_PAGE_POOL
+	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. False if no 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));
+	skb_page_ref(skb_frag_page(frag), recycle);
 }
 
 /**
@@ -3503,7 +3517,7 @@ 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 2a5ce6667bbb..ff7e450ec5ea 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -1004,6 +1004,18 @@ 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)
+{
+	page = compound_head(page);
+
+	if (!is_pp_page(page))
+		return false;
+
+	page_pool_ref_page(page);
+	return true;
+}
+EXPORT_SYMBOL(napi_pp_get_page);
+
 bool napi_pp_put_page(struct page *page)
 {
 	page = compound_head(page);
@@ -1032,37 +1044,6 @@ static bool skb_pp_recycle(struct sk_buff *skb, void *data)
 	return napi_pp_put_page(virt_to_page(data));
 }
 
-/**
- * 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)
@@ -4169,7 +4150,7 @@ 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);
@@ -4819,7 +4800,7 @@ 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) {
@@ -5950,10 +5931,8 @@ 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;
diff --git a/net/tls/tls_device_fallback.c b/net/tls/tls_device_fallback.c
index 4e7228f275fa..d4000b4a1f7d 100644
--- a/net/tls/tls_device_fallback.c
+++ b/net/tls/tls_device_fallback.c
@@ -277,7 +277,7 @@ static int fill_sg_in(struct scatterlist *sg_in,
 	for (i = 0; remaining > 0; i++) {
 		skb_frag_t *frag = &record->frags[i];
 
-		__skb_frag_ref(frag);
+		__skb_frag_ref(frag, false);
 		sg_set_page(sg_in + i, skb_frag_page(frag),
 			    skb_frag_size(frag), skb_frag_off(frag));
 
-- 
2.44.0.478.gd926399ef9-goog

Powered by blists - more mailing lists