From 26c4f7da3e413da697a7beb22ad496390eda7da0 Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Tue, 10 Feb 2015 16:30:27 -0800 Subject: net: Fix remcsum in GRO path to not change packet Remote checksum offload processing is currently the same for both the GRO and non-GRO path. When the remote checksum offload option is encountered, the checksum field referred to is modified in the packet. So in the GRO case, the packet is modified in the GRO path and then the operation is skipped when the packet goes through the normal path based on skb->remcsum_offload. There is a problem in that the packet may be modified in the GRO path, but then forwarded off host still containing the remote checksum option. A remote host will again perform RCO but now the checksum verification will fail since GRO RCO already modified the checksum. To fix this, we ensure that GRO restores a packet to it's original state before returning. In this model, when GRO processes a remote checksum option it still changes the checksum per the algorithm but on return from lower layer processing the checksum is restored to its original value. In this patch we add define gro_remcsum structure which is passed to skb_gro_remcsum_process to save offset and delta for the checksum being changed. After lower layer processing, skb_gro_remcsum_cleanup is called to restore the checksum before returning from GRO. Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- include/net/checksum.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/net') diff --git a/include/net/checksum.h b/include/net/checksum.h index e339a9513e29..0a55ac715077 100644 --- a/include/net/checksum.h +++ b/include/net/checksum.h @@ -167,4 +167,9 @@ static inline __wsum remcsum_adjust(void *ptr, __wsum csum, return delta; } +static inline void remcsum_unadjust(__sum16 *psum, __wsum delta) +{ + *psum = csum_fold(csum_sub(delta, *psum)); +} + #endif -- cgit v1.2.3 From 0ace2ca89cbd6bcdf2b9d2df1fa0fa24ea9d1653 Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Tue, 10 Feb 2015 16:30:32 -0800 Subject: vxlan: Use checksum partial with remote checksum offload Change remote checksum handling to set checksum partial as default behavior. Added an iflink parameter to configure not using checksum partial (calling csum_partial to update checksum). Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- drivers/net/vxlan.c | 25 +++++++++++++++++++------ include/net/vxlan.h | 4 +++- include/uapi/linux/if_link.h | 1 + 3 files changed, 23 insertions(+), 7 deletions(-) (limited to 'include/net') diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 4f04443cfd33..1e0a775ea882 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -555,7 +555,8 @@ static int vxlan_fdb_append(struct vxlan_fdb *f, static struct vxlanhdr *vxlan_gro_remcsum(struct sk_buff *skb, unsigned int off, struct vxlanhdr *vh, size_t hdrlen, - u32 data, struct gro_remcsum *grc) + u32 data, struct gro_remcsum *grc, + bool nopartial) { size_t start, offset, plen; @@ -580,7 +581,7 @@ static struct vxlanhdr *vxlan_gro_remcsum(struct sk_buff *skb, } skb_gro_remcsum_process(skb, (void *)vh + hdrlen, - start, offset, grc, true); + start, offset, grc, nopartial); skb->remcsum_offload = 1; @@ -618,7 +619,9 @@ static struct sk_buff **vxlan_gro_receive(struct sk_buff **head, if ((flags & VXLAN_HF_RCO) && (vs->flags & VXLAN_F_REMCSUM_RX)) { vh = vxlan_gro_remcsum(skb, off_vx, vh, sizeof(struct vxlanhdr), - ntohl(vh->vx_vni), &grc); + ntohl(vh->vx_vni), &grc, + !!(vs->flags & + VXLAN_F_REMCSUM_NOPARTIAL)); if (!vh) goto out; @@ -1155,7 +1158,7 @@ static void vxlan_igmp_leave(struct work_struct *work) } static struct vxlanhdr *vxlan_remcsum(struct sk_buff *skb, struct vxlanhdr *vh, - size_t hdrlen, u32 data) + size_t hdrlen, u32 data, bool nopartial) { size_t start, offset, plen; @@ -1171,7 +1174,8 @@ static struct vxlanhdr *vxlan_remcsum(struct sk_buff *skb, struct vxlanhdr *vh, vh = (struct vxlanhdr *)(udp_hdr(skb) + 1); - skb_remcsum_process(skb, (void *)vh + hdrlen, start, offset, true); + skb_remcsum_process(skb, (void *)vh + hdrlen, start, offset, + nopartial); return vh; } @@ -1208,7 +1212,8 @@ static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb) goto drop; if ((flags & VXLAN_HF_RCO) && (vs->flags & VXLAN_F_REMCSUM_RX)) { - vxh = vxlan_remcsum(skb, vxh, sizeof(struct vxlanhdr), vni); + vxh = vxlan_remcsum(skb, vxh, sizeof(struct vxlanhdr), vni, + !!(vs->flags & VXLAN_F_REMCSUM_NOPARTIAL)); if (!vxh) goto drop; @@ -2437,6 +2442,7 @@ static const struct nla_policy vxlan_policy[IFLA_VXLAN_MAX + 1] = { [IFLA_VXLAN_REMCSUM_TX] = { .type = NLA_U8 }, [IFLA_VXLAN_REMCSUM_RX] = { .type = NLA_U8 }, [IFLA_VXLAN_GBP] = { .type = NLA_FLAG, }, + [IFLA_VXLAN_REMCSUM_NOPARTIAL] = { .type = NLA_FLAG }, }; static int vxlan_validate(struct nlattr *tb[], struct nlattr *data[]) @@ -2760,6 +2766,9 @@ static int vxlan_newlink(struct net *src_net, struct net_device *dev, if (data[IFLA_VXLAN_GBP]) vxlan->flags |= VXLAN_F_GBP; + if (data[IFLA_VXLAN_REMCSUM_NOPARTIAL]) + vxlan->flags |= VXLAN_F_REMCSUM_NOPARTIAL; + if (vxlan_find_vni(src_net, vni, use_ipv6 ? AF_INET6 : AF_INET, vxlan->dst_port, vxlan->flags)) { pr_info("duplicate VNI %u\n", vni); @@ -2909,6 +2918,10 @@ static int vxlan_fill_info(struct sk_buff *skb, const struct net_device *dev) nla_put_flag(skb, IFLA_VXLAN_GBP)) goto nla_put_failure; + if (vxlan->flags & VXLAN_F_REMCSUM_NOPARTIAL && + nla_put_flag(skb, IFLA_VXLAN_REMCSUM_NOPARTIAL)) + goto nla_put_failure; + return 0; nla_put_failure: diff --git a/include/net/vxlan.h b/include/net/vxlan.h index 2927d6244481..eabd3a038674 100644 --- a/include/net/vxlan.h +++ b/include/net/vxlan.h @@ -128,13 +128,15 @@ struct vxlan_sock { #define VXLAN_F_REMCSUM_TX 0x200 #define VXLAN_F_REMCSUM_RX 0x400 #define VXLAN_F_GBP 0x800 +#define VXLAN_F_REMCSUM_NOPARTIAL 0x1000 /* Flags that are used in the receive patch. These flags must match in * order for a socket to be shareable */ #define VXLAN_F_RCV_FLAGS (VXLAN_F_GBP | \ VXLAN_F_UDP_ZERO_CSUM6_RX | \ - VXLAN_F_REMCSUM_RX) + VXLAN_F_REMCSUM_RX | \ + VXLAN_F_REMCSUM_NOPARTIAL) struct vxlan_sock *vxlan_sock_add(struct net *net, __be16 port, vxlan_rcv_t *rcv, void *data, diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 0deee3eeddbf..dfd0bb22e554 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -374,6 +374,7 @@ enum { IFLA_VXLAN_REMCSUM_TX, IFLA_VXLAN_REMCSUM_RX, IFLA_VXLAN_GBP, + IFLA_VXLAN_REMCSUM_NOPARTIAL, __IFLA_VXLAN_MAX }; #define IFLA_VXLAN_MAX (__IFLA_VXLAN_MAX - 1) -- cgit v1.2.3