netdev - [PATCH net v2 2/2] udp: only do GSO if # of segs

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <1570037363-12485-2-git-send-email-johunt@akamai.com>
Date:   Wed,  2 Oct 2019 13:29:23 -0400
From:   Josh Hunt <johunt@...mai.com>
To:     davem@...emloft.net
Cc:     netdev@...r.kernel.org, edumazet@...gle.com, willemb@...gle.com,
        alexander.h.duyck@...el.com, Josh Hunt <johunt@...mai.com>
Subject: [PATCH net v2 2/2] udp: only do GSO if # of segs > 1

Prior to this change an application sending <= 1MSS worth of data and
enabling UDP GSO would fail if the system had SW GSO enabled, but the
same send would succeed if HW GSO offload is enabled. In addition to this
inconsistency the error in the SW GSO case does not get back to the
application if sending out of a real device so the user is unaware of this
failure.

With this change we only perform GSO if the # of segments is > 1 even
if the application has enabled segmentation. I've also updated the
relevant udpgso selftests.

Fixes: bec1f6f69736 ("udp: generate gso with UDP_SEGMENT")
Signed-off-by: Josh Hunt <johunt@...mai.com>
---
 net/ipv4/udp.c                       | 11 +++++++----
 net/ipv6/udp.c                       | 11 +++++++----
 tools/testing/selftests/net/udpgso.c | 16 ++++------------
 3 files changed, 18 insertions(+), 20 deletions(-)

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index be98d0b8f014..c31c7c353fcb 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -821,6 +821,7 @@ static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4,
 	int is_udplite = IS_UDPLITE(sk);
 	int offset = skb_transport_offset(skb);
 	int len = skb->len - offset;
+	int datalen = len - sizeof(*uh);
 	__wsum csum = 0;
 
 	/*
@@ -854,10 +855,12 @@ static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4,
 			return -EIO;
 		}
 
-		skb_shinfo(skb)->gso_size = cork->gso_size;
-		skb_shinfo(skb)->gso_type = SKB_GSO_UDP_L4;
-		skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(len - sizeof(*uh),
-							 cork->gso_size);
+		if (datalen > cork->gso_size) {
+			skb_shinfo(skb)->gso_size = cork->gso_size;
+			skb_shinfo(skb)->gso_type = SKB_GSO_UDP_L4;
+			skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(datalen,
+								 cork->gso_size);
+		}
 		goto csum_partial;
 	}
 
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index eb9a9934ac05..6324d3a8cb53 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1109,6 +1109,7 @@ static int udp_v6_send_skb(struct sk_buff *skb, struct flowi6 *fl6,
 	__wsum csum = 0;
 	int offset = skb_transport_offset(skb);
 	int len = skb->len - offset;
+	int datalen = len - sizeof(*uh);
 
 	/*
 	 * Create a UDP header
@@ -1141,10 +1142,12 @@ static int udp_v6_send_skb(struct sk_buff *skb, struct flowi6 *fl6,
 			return -EIO;
 		}
 
-		skb_shinfo(skb)->gso_size = cork->gso_size;
-		skb_shinfo(skb)->gso_type = SKB_GSO_UDP_L4;
-		skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(len - sizeof(*uh),
-							 cork->gso_size);
+		if (datalen > cork->gso_size) {
+			skb_shinfo(skb)->gso_size = cork->gso_size;
+			skb_shinfo(skb)->gso_type = SKB_GSO_UDP_L4;
+			skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(datalen,
+								 cork->gso_size);
+		}
 		goto csum_partial;
 	}
 
diff --git a/tools/testing/selftests/net/udpgso.c b/tools/testing/selftests/net/udpgso.c
index b8265ee9923f..614b31aad168 100644
--- a/tools/testing/selftests/net/udpgso.c
+++ b/tools/testing/selftests/net/udpgso.c
@@ -89,12 +89,9 @@ struct testcase testcases_v4[] = {
 		.tfail = true,
 	},
 	{
-		/* send a single MSS: will fail with GSO, because the segment
-		 * logic in udp4_ufo_fragment demands a gso skb to be > MTU
-		 */
+		/* send a single MSS: will fall back to no GSO */
 		.tlen = CONST_MSS_V4,
 		.gso_len = CONST_MSS_V4,
-		.tfail = true,
 		.r_num_mss = 1,
 	},
 	{
@@ -139,10 +136,9 @@ struct testcase testcases_v4[] = {
 		.tfail = true,
 	},
 	{
-		/* send a single 1B MSS: will fail, see single MSS above */
+		/* send a single 1B MSS: will fall back to no GSO */
 		.tlen = 1,
 		.gso_len = 1,
-		.tfail = true,
 		.r_num_mss = 1,
 	},
 	{
@@ -196,12 +192,9 @@ struct testcase testcases_v6[] = {
 		.tfail = true,
 	},
 	{
-		/* send a single MSS: will fail with GSO, because the segment
-		 * logic in udp4_ufo_fragment demands a gso skb to be > MTU
-		 */
+		/* send a single MSS: will fall back to no GSO */
 		.tlen = CONST_MSS_V6,
 		.gso_len = CONST_MSS_V6,
-		.tfail = true,
 		.r_num_mss = 1,
 	},
 	{
@@ -246,10 +239,9 @@ struct testcase testcases_v6[] = {
 		.tfail = true,
 	},
 	{
-		/* send a single 1B MSS: will fail, see single MSS above */
+		/* send a single 1B MSS: will fall back to no GSO */
 		.tlen = 1,
 		.gso_len = 1,
-		.tfail = true,
 		.r_num_mss = 1,
 	},
 	{
-- 
2.7.4