Merge branch 'net-extend-alloc_skb_with_frags-max-size'

Eric Dumazet says:

====================
net: extend alloc_skb_with_frags() max size

alloc_skb_with_frags(), while being able to use high order allocations,
limits the payload size to PAGE_SIZE * MAX_SKB_FRAGS

Reviewing Tahsin Erdogan patch [1], it was clear to me we need
to remove this limitation.

[1] https://lore.kernel.org/netdev/20230731230736.109216-1-trdgn@amazon.com/

v2: Addressed Willem feedback on 1st patch.
====================

Link: https://lore.kernel.org/r/20230801205254.400094-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

4 files changed, 34 insertions, 34 deletions

diff --git a/drivers/net/tap.c b/drivers/net/tap.c
index 9137fb8c1c42..01574b9d410f 100644
--- a/drivers/net/tap.c
+++ b/drivers/net/tap.c
@@ -614,8 +614,10 @@ static inline struct sk_buff *tap_alloc_skb(struct sock *sk, size_t prepad,
 	if (prepad + len < PAGE_SIZE || !linear)
 		linear = len;
 
+	if (len - linear > MAX_SKB_FRAGS * (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER))
+		linear = len - MAX_SKB_FRAGS * (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER);
 	skb = sock_alloc_send_pskb(sk, prepad + linear, len - linear, noblock,
-				   err, 0);
+				   err, PAGE_ALLOC_COSTLY_ORDER);
 	if (!skb)
 		return NULL;
 
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index d75456adc62a..8a48431e8c5b 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1526,8 +1526,10 @@ static struct sk_buff *tun_alloc_skb(struct tun_file *tfile,
 	if (prepad + len < PAGE_SIZE || !linear)
 		linear = len;
 
+	if (len - linear > MAX_SKB_FRAGS * (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER))
+		linear = len - MAX_SKB_FRAGS * (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER);
 	skb = sock_alloc_send_pskb(sk, prepad + linear, len - linear, noblock,
-				   &err, 0);
+				   &err, PAGE_ALLOC_COSTLY_ORDER);
 	if (!skb)
 		return ERR_PTR(err);
 
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index a298992060e6..c6f98245582c 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -6204,7 +6204,7 @@ EXPORT_SYMBOL_GPL(skb_mpls_dec_ttl);
  *
  * @header_len: size of linear part
  * @data_len: needed length in frags
- * @max_page_order: max page order desired.
+ * @order: max page order desired.
  * @errcode: pointer to error code if any
  * @gfp_mask: allocation mask
  *
@@ -6212,21 +6212,17 @@ EXPORT_SYMBOL_GPL(skb_mpls_dec_ttl);
  */
 struct sk_buff *alloc_skb_with_frags(unsigned long header_len,
 				     unsigned long data_len,
-				     int max_page_order,
+				     int order,
 				     int *errcode,
 				     gfp_t gfp_mask)
 {
-	int npages = (data_len + (PAGE_SIZE - 1)) >> PAGE_SHIFT;
 	unsigned long chunk;
 	struct sk_buff *skb;
 	struct page *page;
-	int i;
+	int nr_frags = 0;
 
 	*errcode = -EMSGSIZE;
-	/* Note this test could be relaxed, if we succeed to allocate
-	 * high order pages...
-	 */
-	if (npages > MAX_SKB_FRAGS)
+	if (unlikely(data_len > MAX_SKB_FRAGS * (PAGE_SIZE << order)))
 		return NULL;
 
 	*errcode = -ENOBUFS;
@@ -6234,34 +6230,32 @@ struct sk_buff *alloc_skb_with_frags(unsigned long header_len,
 	if (!skb)
 		return NULL;
 
-	skb->truesize += npages << PAGE_SHIFT;
-
-	for (i = 0; npages > 0; i++) {
-		int order = max_page_order;
-
-		while (order) {
-			if (npages >= 1 << order) {
-				page = alloc_pages((gfp_mask & ~__GFP_DIRECT_RECLAIM) |
-						   __GFP_COMP |
-						   __GFP_NOWARN,
-						   order);
-				if (page)
-					goto fill_page;
-				/* Do not retry other high order allocations */
-				order = 1;
-				max_page_order = 0;
-			}
+	while (data_len) {
+		if (nr_frags == MAX_SKB_FRAGS - 1)
+			goto failure;
+		while (order && PAGE_ALIGN(data_len) < (PAGE_SIZE << order))
 			order--;
+
+		if (order) {
+			page = alloc_pages((gfp_mask & ~__GFP_DIRECT_RECLAIM) |
+					   __GFP_COMP |
+					   __GFP_NOWARN,
+					   order);
+			if (!page) {
+				order--;
+				continue;
+			}
+		} else {
+			page = alloc_page(gfp_mask);
+			if (!page)
+				goto failure;
 		}
-		page = alloc_page(gfp_mask);
-		if (!page)
-			goto failure;
-fill_page:
 		chunk = min_t(unsigned long, data_len,
 			      PAGE_SIZE << order);
-		skb_fill_page_desc(skb, i, page, 0, chunk);
+		skb_fill_page_desc(skb, nr_frags, page, 0, chunk);
+		nr_frags++;
+		skb->truesize += (PAGE_SIZE << order);
 		data_len -= chunk;
-		npages -= 1 << order;
 	}
 	return skb;
 
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 8e3ddec4c3d5..3b77d255d22d 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2927,8 +2927,10 @@ static struct sk_buff *packet_alloc_skb(struct sock *sk, size_t prepad,
 	if (prepad + len < PAGE_SIZE || !linear)
 		linear = len;
 
+	if (len - linear > MAX_SKB_FRAGS * (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER))
+		linear = len - MAX_SKB_FRAGS * (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER);
 	skb = sock_alloc_send_pskb(sk, prepad + linear, len - linear, noblock,
-				   err, 0);
+				   err, PAGE_ALLOC_COSTLY_ORDER);
 	if (!skb)
 		return NULL;