Currently, NETIF_F_TSO_MANGLEID indicates that the inner-most ID can be mangled. Outer IDs can always be mangled. Make GSO preserve outer IDs by default, with NETIF_F_TSO_MANGLEID allowing both inner and outer IDs to be mangled. In the future, we could add NETIF_F_TSO_MANGLEID_INNER to provide more granular control to drivers. This commit also modifies a few drivers that use SKB_GSO_FIXEDID directly. Signed-off-by: Richard Gobert --- drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 8 ++++++-- drivers/net/ethernet/sfc/ef100_tx.c | 12 +++++++----- include/linux/netdevice.h | 9 +++++++-- include/linux/skbuff.h | 6 +++++- net/core/dev.c | 7 +++---- net/ipv4/af_inet.c | 13 ++++++------- net/ipv4/tcp_offload.c | 5 +---- 7 files changed, 35 insertions(+), 25 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index b8c609d91d11..505c4ce7cef8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -1289,8 +1289,12 @@ static void mlx5e_shampo_update_ipv4_tcp_hdr(struct mlx5e_rq *rq, struct iphdr * tcp->check = ~tcp_v4_check(skb->len - tcp_off, ipv4->saddr, ipv4->daddr, 0); skb_shinfo(skb)->gso_type |= SKB_GSO_TCPV4; - if (ntohs(ipv4->id) == rq->hw_gro_data->second_ip_id) - skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_FIXEDID; + if (ntohs(ipv4->id) == rq->hw_gro_data->second_ip_id) { + bool encap = rq->hw_gro_data->fk.control.flags & FLOW_DIS_ENCAPSULATION; + + skb_shinfo(skb)->gso_type |= encap ? + SKB_GSO_TCP_FIXEDID_INNER : SKB_GSO_TCP_FIXEDID; + } skb->csum_start = (unsigned char *)tcp - skb->head; skb->csum_offset = offsetof(struct tcphdr, check); diff --git a/drivers/net/ethernet/sfc/ef100_tx.c b/drivers/net/ethernet/sfc/ef100_tx.c index e6b6be549581..4efd22b44986 100644 --- a/drivers/net/ethernet/sfc/ef100_tx.c +++ b/drivers/net/ethernet/sfc/ef100_tx.c @@ -189,7 +189,8 @@ static void ef100_make_tso_desc(struct efx_nic *efx, { bool gso_partial = skb_shinfo(skb)->gso_type & SKB_GSO_PARTIAL; unsigned int len, ip_offset, tcp_offset, payload_segs; - u32 mangleid = ESE_GZ_TX_DESC_IP4_ID_INC_MOD16; + u32 mangleid_outer = ESE_GZ_TX_DESC_IP4_ID_INC_MOD16; + u32 mangleid_inner = ESE_GZ_TX_DESC_IP4_ID_INC_MOD16; unsigned int outer_ip_offset, outer_l4_offset; u16 vlan_tci = skb_vlan_tag_get(skb); u32 mss = skb_shinfo(skb)->gso_size; @@ -201,7 +202,9 @@ static void ef100_make_tso_desc(struct efx_nic *efx, u32 paylen; if (skb_shinfo(skb)->gso_type & SKB_GSO_TCP_FIXEDID) - mangleid = ESE_GZ_TX_DESC_IP4_ID_NO_OP; + mangleid_outer = ESE_GZ_TX_DESC_IP4_ID_NO_OP; + if (skb_shinfo(skb)->gso_type & SKB_GSO_TCP_FIXEDID_INNER) + mangleid_inner = ESE_GZ_TX_DESC_IP4_ID_NO_OP; if (efx->net_dev->features & NETIF_F_HW_VLAN_CTAG_TX) vlan_enable = skb_vlan_tag_present(skb); @@ -239,14 +242,13 @@ static void ef100_make_tso_desc(struct efx_nic *efx, ESF_GZ_TX_TSO_CSO_INNER_L4, 1, ESF_GZ_TX_TSO_INNER_L3_OFF_W, ip_offset >> 1, ESF_GZ_TX_TSO_INNER_L4_OFF_W, tcp_offset >> 1, - ESF_GZ_TX_TSO_ED_INNER_IP4_ID, mangleid, + ESF_GZ_TX_TSO_ED_INNER_IP4_ID, mangleid_inner, ESF_GZ_TX_TSO_ED_INNER_IP_LEN, 1, ESF_GZ_TX_TSO_OUTER_L3_OFF_W, outer_ip_offset >> 1, ESF_GZ_TX_TSO_OUTER_L4_OFF_W, outer_l4_offset >> 1, ESF_GZ_TX_TSO_ED_OUTER_UDP_LEN, udp_encap && !gso_partial, ESF_GZ_TX_TSO_ED_OUTER_IP_LEN, encap && !gso_partial, - ESF_GZ_TX_TSO_ED_OUTER_IP4_ID, encap ? mangleid : - ESE_GZ_TX_DESC_IP4_ID_NO_OP, + ESF_GZ_TX_TSO_ED_OUTER_IP4_ID, mangleid_outer, ESF_GZ_TX_TSO_VLAN_INSERT_EN, vlan_enable, ESF_GZ_TX_TSO_VLAN_INSERT_TCI, vlan_tci ); diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 5e5de4b0a433..f47d4d67bce9 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -5287,13 +5287,18 @@ void skb_warn_bad_offload(const struct sk_buff *skb); static inline bool net_gso_ok(netdev_features_t features, int gso_type) { - netdev_features_t feature = (netdev_features_t)gso_type << NETIF_F_GSO_SHIFT; + netdev_features_t feature; + + if (gso_type & (SKB_GSO_TCP_FIXEDID | SKB_GSO_TCP_FIXEDID_INNER)) + gso_type |= __SKB_GSO_TCP_FIXEDID; + + feature = ((netdev_features_t)gso_type << NETIF_F_GSO_SHIFT) & NETIF_F_GSO_MASK; /* check flags correspondence */ BUILD_BUG_ON(SKB_GSO_TCPV4 != (NETIF_F_TSO >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_DODGY != (NETIF_F_GSO_ROBUST >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_TCP_ECN != (NETIF_F_TSO_ECN >> NETIF_F_GSO_SHIFT)); - BUILD_BUG_ON(SKB_GSO_TCP_FIXEDID != (NETIF_F_TSO_MANGLEID >> NETIF_F_GSO_SHIFT)); + BUILD_BUG_ON(__SKB_GSO_TCP_FIXEDID != (NETIF_F_TSO_MANGLEID >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_TCPV6 != (NETIF_F_TSO6 >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_FCOE != (NETIF_F_FSO >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_GRE != (NETIF_F_GSO_GRE >> NETIF_F_GSO_SHIFT)); diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 14b923ddb6df..9e4540d379ba 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -674,7 +674,7 @@ enum { /* This indicates the tcp segment has CWR set. */ SKB_GSO_TCP_ECN = 1 << 2, - SKB_GSO_TCP_FIXEDID = 1 << 3, + __SKB_GSO_TCP_FIXEDID = 1 << 3, SKB_GSO_TCPV6 = 1 << 4, @@ -707,6 +707,10 @@ enum { SKB_GSO_FRAGLIST = 1 << 18, SKB_GSO_TCP_ACCECN = 1 << 19, + + /* These don't correspond with netdev features. */ + SKB_GSO_TCP_FIXEDID = 1 << 30, + SKB_GSO_TCP_FIXEDID_INNER = 1 << 31, }; #if BITS_PER_LONG > 32 diff --git a/net/core/dev.c b/net/core/dev.c index 68dc47d7e700..9941c39b5970 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3772,10 +3772,9 @@ static netdev_features_t gso_features_check(const struct sk_buff *skb, * IPv4 header has the potential to be fragmented. */ if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4) { - struct iphdr *iph = skb->encapsulation ? - inner_ip_hdr(skb) : ip_hdr(skb); - - if (!(iph->frag_off & htons(IP_DF))) + if (!(ip_hdr(skb)->frag_off & htons(IP_DF)) || + (skb->encapsulation && + !(inner_ip_hdr(skb)->frag_off & htons(IP_DF)))) features &= ~NETIF_F_TSO_MANGLEID; } diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 76e38092cd8a..fc7a6955fa0a 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1393,14 +1393,13 @@ struct sk_buff *inet_gso_segment(struct sk_buff *skb, segs = ERR_PTR(-EPROTONOSUPPORT); - if (!skb->encapsulation || encap) { - udpfrag = !!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP); - fixedid = !!(skb_shinfo(skb)->gso_type & SKB_GSO_TCP_FIXEDID); + /* fixed ID is invalid if DF bit is not set */ + fixedid = !!(skb_shinfo(skb)->gso_type & (SKB_GSO_TCP_FIXEDID << encap)); + if (fixedid && !(ip_hdr(skb)->frag_off & htons(IP_DF))) + goto out; - /* fixed ID is invalid if DF bit is not set */ - if (fixedid && !(ip_hdr(skb)->frag_off & htons(IP_DF))) - goto out; - } + if (!skb->encapsulation || encap) + udpfrag = !!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP); ops = rcu_dereference(inet_offloads[proto]); if (likely(ops && ops->callbacks.gso_segment)) { diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c index 56817ef12ad2..be5c2294610e 100644 --- a/net/ipv4/tcp_offload.c +++ b/net/ipv4/tcp_offload.c @@ -472,7 +472,6 @@ INDIRECT_CALLABLE_SCOPE int tcp4_gro_complete(struct sk_buff *skb, int thoff) const u16 offset = NAPI_GRO_CB(skb)->network_offsets[skb->encapsulation]; const struct iphdr *iph = (struct iphdr *)(skb->data + offset); struct tcphdr *th = tcp_hdr(skb); - bool is_fixedid; if (unlikely(NAPI_GRO_CB(skb)->is_flist)) { skb_shinfo(skb)->gso_type |= SKB_GSO_FRAGLIST | SKB_GSO_TCPV4; @@ -486,10 +485,8 @@ INDIRECT_CALLABLE_SCOPE int tcp4_gro_complete(struct sk_buff *skb, int thoff) th->check = ~tcp_v4_check(skb->len - thoff, iph->saddr, iph->daddr, 0); - is_fixedid = (NAPI_GRO_CB(skb)->ip_fixedid >> skb->encapsulation) & 1; - skb_shinfo(skb)->gso_type |= SKB_GSO_TCPV4 | - (is_fixedid * SKB_GSO_TCP_FIXEDID); + (NAPI_GRO_CB(skb)->ip_fixedid * SKB_GSO_TCP_FIXEDID); tcp_gro_complete(skb); return 0; -- 2.36.1