net: support non paged skb frags

Make skb_frag_page() fail in the case where the frag is not backed
by a page, and fix its relevant callers to handle this case.

Signed-off-by: Mina Almasry <almasrymina@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Link: https://patch.msgid.link/20240910171458.219195-8-almasrymina@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

8 files changed, 67 insertions, 10 deletions

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 5803eb8a157d..1019f14583c9 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -3524,21 +3524,58 @@ static inline void skb_frag_off_copy(skb_frag_t *fragto,
 	fragto->offset = fragfrom->offset;
 }
 
+/* Return: true if the skb_frag contains a net_iov. */
+static inline bool skb_frag_is_net_iov(const skb_frag_t *frag)
+{
+	return netmem_is_net_iov(frag->netmem);
+}
+
+/**
+ * skb_frag_net_iov - retrieve the net_iov referred to by fragment
+ * @frag: the fragment
+ *
+ * Return: the &struct net_iov associated with @frag. Returns NULL if this
+ * frag has no associated net_iov.
+ */
+static inline struct net_iov *skb_frag_net_iov(const skb_frag_t *frag)
+{
+	if (!skb_frag_is_net_iov(frag))
+		return NULL;
+
+	return netmem_to_net_iov(frag->netmem);
+}
+
 /**
  * skb_frag_page - retrieve the page referred to by a paged fragment
  * @frag: the paged fragment
  *
- * Returns the &struct page associated with @frag.
+ * Return: the &struct page associated with @frag. Returns NULL if this frag
+ * has no associated page.
  */
 static inline struct page *skb_frag_page(const skb_frag_t *frag)
 {
+	if (skb_frag_is_net_iov(frag))
+		return NULL;
+
 	return netmem_to_page(frag->netmem);
 }
 
+/**
+ * skb_frag_netmem - retrieve the netmem referred to by a fragment
+ * @frag: the fragment
+ *
+ * Return: the &netmem_ref associated with @frag.
+ */
+static inline netmem_ref skb_frag_netmem(const skb_frag_t *frag)
+{
+	return frag->netmem;
+}
+
 int skb_pp_cow_data(struct page_pool *pool, struct sk_buff **pskb,
 		    unsigned int headroom);
 int skb_cow_data_for_xdp(struct page_pool *pool, struct sk_buff **pskb,
 			 struct bpf_prog *prog);
+
 /**
  * skb_frag_address - gets the address of the data contained in a paged fragment
  * @frag: the paged fragment buffer
@@ -3548,6 +3585,9 @@ int skb_cow_data_for_xdp(struct page_pool *pool, struct sk_buff **pskb,
  */
 static inline void *skb_frag_address(const skb_frag_t *frag)
 {
+	if (!skb_frag_page(frag))
+		return NULL;
+
 	return page_address(skb_frag_page(frag)) + skb_frag_off(frag);
 }
 
diff --git a/include/linux/skbuff_ref.h b/include/linux/skbuff_ref.h
index 16c241a23472..0f3c58007488 100644
--- a/include/linux/skbuff_ref.h
+++ b/include/linux/skbuff_ref.h
@@ -34,14 +34,13 @@ static inline void skb_frag_ref(struct sk_buff *skb, int f)
 
 bool napi_pp_put_page(netmem_ref netmem);
 
-static inline void
-skb_page_unref(struct page *page, bool recycle)
+static inline void skb_page_unref(netmem_ref netmem, bool recycle)
 {
 #ifdef CONFIG_PAGE_POOL
-	if (recycle && napi_pp_put_page(page_to_netmem(page)))
+	if (recycle && napi_pp_put_page(netmem))
 		return;
 #endif
-	put_page(page);
+	put_page(netmem_to_page(netmem));
 }
 
 /**
@@ -54,7 +53,7 @@ skb_page_unref(struct page *page, bool recycle)
  */
 static inline void __skb_frag_unref(skb_frag_t *frag, bool recycle)
 {
-	skb_page_unref(skb_frag_page(frag), recycle);
+	skb_page_unref(skb_frag_netmem(frag), recycle);
 }
 
 /**
diff --git a/net/core/dev.c b/net/core/dev.c
index 7818d7f6295e..517b934bdf9c 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3434,8 +3434,9 @@ static int illegal_highdma(struct net_device *dev, struct sk_buff *skb)
 	if (!(dev->features & NETIF_F_HIGHDMA)) {
 		for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
 			skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
+			struct page *page = skb_frag_page(frag);
 
-			if (PageHighMem(skb_frag_page(frag)))
+			if (page && PageHighMem(page))
 				return 1;
 		}
 	}
diff --git a/net/core/gro.c b/net/core/gro.c
index 3abad1b567dd..802b4a062400 100644
--- a/net/core/gro.c
+++ b/net/core/gro.c
@@ -408,7 +408,8 @@ static inline void skb_gro_reset_offset(struct sk_buff *skb, u32 nhoff)
 	pinfo = skb_shinfo(skb);
 	frag0 = &pinfo->frags[0];
 
-	if (pinfo->nr_frags && !PageHighMem(skb_frag_page(frag0)) &&
+	if (pinfo->nr_frags && skb_frag_page(frag0) &&
+	    !PageHighMem(skb_frag_page(frag0)) &&
 	    (!NET_IP_ALIGN || !((skb_frag_off(frag0) + nhoff) & 3))) {
 		NAPI_GRO_CB(skb)->frag0 = skb_frag_address(frag0);
 		NAPI_GRO_CB(skb)->frag0_len = min_t(unsigned int,
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 8abcc28bb189..671c456b93f5 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -1371,6 +1371,14 @@ void skb_dump(const char *level, const struct sk_buff *skb, bool full_pkt)
 		struct page *p;
 		u8 *vaddr;
 
+		if (skb_frag_is_net_iov(frag)) {
+			printk("%sskb frag %d: not readable\n", level, i);
+			len -= skb_frag_size(frag);
+			if (!len)
+				break;
+			continue;
+		}
+
 		skb_frag_foreach_page(frag, skb_frag_off(frag),
 				      skb_frag_size(frag), p, p_off, p_len,
 				      copied) {
@@ -3163,6 +3171,9 @@ static bool __skb_splice_bits(struct sk_buff *skb, struct pipe_inode_info *pipe,
 	for (seg = 0; seg < skb_shinfo(skb)->nr_frags; seg++) {
 		const skb_frag_t *f = &skb_shinfo(skb)->frags[seg];
 
+		if (WARN_ON_ONCE(!skb_frag_page(f)))
+			return false;
+
 		if (__splice_segment(skb_frag_page(f),
 				     skb_frag_off(f), skb_frag_size(f),
 				     offset, len, spd, false, sk, pipe))
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 47378ca41904..f3281312eb5e 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -115,7 +115,8 @@ static void esp_ssg_unref(struct xfrm_state *x, void *tmp, struct sk_buff *skb)
 	 */
 	if (req->src != req->dst)
 		for (sg = sg_next(req->src); sg; sg = sg_next(sg))
-			skb_page_unref(sg_page(sg), skb->pp_recycle);
+			skb_page_unref(page_to_netmem(sg_page(sg)),
+				       skb->pp_recycle);
 }
 
 #ifdef CONFIG_INET_ESPINTCP
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index e359a9161445..06dcf89e2cca 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2177,6 +2177,9 @@ static int tcp_zerocopy_receive(struct sock *sk,
 			break;
 		}
 		page = skb_frag_page(frags);
+		if (WARN_ON_ONCE(!page))
+			break;
+
 		prefetchw(page);
 		pages[pages_to_map++] = page;
 		length += PAGE_SIZE;
diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c
index 3920e8aa1031..b2400c226a32 100644
--- a/net/ipv6/esp6.c
+++ b/net/ipv6/esp6.c
@@ -132,7 +132,8 @@ static void esp_ssg_unref(struct xfrm_state *x, void *tmp, struct sk_buff *skb)
 	 */
 	if (req->src != req->dst)
 		for (sg = sg_next(req->src); sg; sg = sg_next(sg))
-			skb_page_unref(sg_page(sg), skb->pp_recycle);
+			skb_page_unref(page_to_netmem(sg_page(sg)),
+				       skb->pp_recycle);
 }
 
 #ifdef CONFIG_INET6_ESPINTCP