From 7c96d8ec96bb71aac54c9f872aaa65d7411ab864 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 13 May 2022 11:34:00 -0700 Subject: ipv6: add struct hop_jumbo_hdr definition Following patches will need to add and remove local IPv6 jumbogram options to enable BIG TCP. Signed-off-by: Eric Dumazet Acked-by: Alexander Duyck Signed-off-by: David S. Miller --- include/net/ipv6.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/net') diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 213612f1680c..63d019953c47 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -151,6 +151,17 @@ struct frag_hdr { __be32 identification; }; +/* + * Jumbo payload option, as described in RFC 2675 2. + */ +struct hop_jumbo_hdr { + u8 nexthdr; + u8 hdrlen; + u8 tlv_type; /* IPV6_TLV_JUMBO, 0xC2 */ + u8 tlv_len; /* 4 */ + __be32 jumbo_payload_len; +}; + #define IP6_MF 0x0001 #define IP6_OFFSET 0xFFF8 -- cgit v1.2.3-71-gd317 From 09f3d1a3a52c696208008618a67e2c7c3fb16d41 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 13 May 2022 11:34:01 -0700 Subject: ipv6/gso: remove temporary HBH/jumbo header ipv6 tcp and gro stacks will soon be able to build big TCP packets, with an added temporary Hop By Hop header. If GSO is involved for these large packets, we need to remove the temporary HBH header before segmentation happens. v2: perform HBH removal from ipv6_gso_segment() instead of skb_segment() (Alexander feedback) Signed-off-by: Eric Dumazet Acked-by: Alexander Duyck Signed-off-by: David S. Miller --- include/net/ipv6.h | 33 +++++++++++++++++++++++++++++++++ net/ipv6/ip6_offload.c | 24 +++++++++++++++++++++++- 2 files changed, 56 insertions(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 63d019953c47..b6df0314aa02 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -467,6 +467,39 @@ bool ipv6_opt_accepted(const struct sock *sk, const struct sk_buff *skb, struct ipv6_txoptions *ipv6_update_options(struct sock *sk, struct ipv6_txoptions *opt); +/* This helper is specialized for BIG TCP needs. + * It assumes the hop_jumbo_hdr will immediately follow the IPV6 header. + * It assumes headers are already in skb->head. + * Returns 0, or IPPROTO_TCP if a BIG TCP packet is there. + */ +static inline int ipv6_has_hopopt_jumbo(const struct sk_buff *skb) +{ + const struct hop_jumbo_hdr *jhdr; + const struct ipv6hdr *nhdr; + + if (likely(skb->len <= GRO_MAX_SIZE)) + return 0; + + if (skb->protocol != htons(ETH_P_IPV6)) + return 0; + + if (skb_network_offset(skb) + + sizeof(struct ipv6hdr) + + sizeof(struct hop_jumbo_hdr) > skb_headlen(skb)) + return 0; + + nhdr = ipv6_hdr(skb); + + if (nhdr->nexthdr != NEXTHDR_HOP) + return 0; + + jhdr = (const struct hop_jumbo_hdr *) (nhdr + 1); + if (jhdr->tlv_type != IPV6_TLV_JUMBO || jhdr->hdrlen != 0 || + jhdr->nexthdr != IPPROTO_TCP) + return 0; + return jhdr->nexthdr; +} + static inline bool ipv6_accept_ra(struct inet6_dev *idev) { /* If forwarding is enabled, RA are not accepted unless the special diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c index c4fc03c1ac99..a6a6c1539c28 100644 --- a/net/ipv6/ip6_offload.c +++ b/net/ipv6/ip6_offload.c @@ -77,7 +77,7 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, struct sk_buff *segs = ERR_PTR(-EINVAL); struct ipv6hdr *ipv6h; const struct net_offload *ops; - int proto; + int proto, nexthdr; struct frag_hdr *fptr; unsigned int payload_len; u8 *prevhdr; @@ -87,6 +87,28 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, bool gso_partial; skb_reset_network_header(skb); + nexthdr = ipv6_has_hopopt_jumbo(skb); + if (nexthdr) { + const int hophdr_len = sizeof(struct hop_jumbo_hdr); + int err; + + err = skb_cow_head(skb, 0); + if (err < 0) + return ERR_PTR(err); + + /* remove the HBH header. + * Layout: [Ethernet header][IPv6 header][HBH][TCP header] + */ + memmove(skb_mac_header(skb) + hophdr_len, + skb_mac_header(skb), + ETH_HLEN + sizeof(struct ipv6hdr)); + skb->data += hophdr_len; + skb->len -= hophdr_len; + skb->network_header += hophdr_len; + skb->mac_header += hophdr_len; + ipv6h = (struct ipv6hdr *)skb->data; + ipv6h->nexthdr = nexthdr; + } nhoff = skb_network_header(skb) - skb_mac_header(skb); if (unlikely(!pskb_may_pull(skb, sizeof(*ipv6h)))) goto out; -- cgit v1.2.3-71-gd317 From 0fe79f28bfaf73b66b7b1562d2468f94aa03bd12 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Fri, 13 May 2022 11:34:03 -0700 Subject: net: allow gro_max_size to exceed 65536 Allow the gro_max_size to exceed a value larger than 65536. There weren't really any external limitations that prevented this other than the fact that IPv4 only supports a 16 bit length field. Since we have the option of adding a hop-by-hop header for IPv6 we can allow IPv6 to exceed this value and for IPv4 and non-TCP flows we can cap things at 65536 via a constant rather than relying on gro_max_size. [edumazet] limit GRO_MAX_SIZE to (8 * 65535) to avoid overflows. Signed-off-by: Alexander Duyck Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 2 +- include/linux/netdevice.h | 6 +++++- include/net/ipv6.h | 2 +- net/core/dev.c | 2 +- net/core/gro.c | 8 ++++++++ net/core/rtnetlink.c | 8 -------- 6 files changed, 16 insertions(+), 12 deletions(-) (limited to 'include/net') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 838870bc6dbd..24de37b79f5a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -2038,7 +2038,7 @@ mlx5e_hw_gro_skb_has_enough_space(struct sk_buff *skb, u16 data_bcnt) { int nr_frags = skb_shinfo(skb)->nr_frags; - return PAGE_SIZE * nr_frags + data_bcnt <= GRO_MAX_SIZE; + return PAGE_SIZE * nr_frags + data_bcnt <= GRO_LEGACY_MAX_SIZE; } static void diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index fd38847d0dc7..d57ce248004c 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2161,7 +2161,11 @@ struct net_device { struct bpf_prog __rcu *xdp_prog; unsigned long gro_flush_timeout; int napi_defer_hard_irqs; -#define GRO_MAX_SIZE 65536 +#define GRO_LEGACY_MAX_SIZE 65536u +/* TCP minimal MSS is 8 (TCP_MIN_GSO_SIZE), + * and shinfo->gso_segs is a 16bit field. + */ +#define GRO_MAX_SIZE (8 * 65535u) unsigned int gro_max_size; rx_handler_func_t __rcu *rx_handler; void __rcu *rx_handler_data; diff --git a/include/net/ipv6.h b/include/net/ipv6.h index b6df0314aa02..5b38bf1a586b 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -477,7 +477,7 @@ static inline int ipv6_has_hopopt_jumbo(const struct sk_buff *skb) const struct hop_jumbo_hdr *jhdr; const struct ipv6hdr *nhdr; - if (likely(skb->len <= GRO_MAX_SIZE)) + if (likely(skb->len <= GRO_LEGACY_MAX_SIZE)) return 0; if (skb->protocol != htons(ETH_P_IPV6)) diff --git a/net/core/dev.c b/net/core/dev.c index 830beb05161a..d93456c75b55 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -10598,7 +10598,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, dev->gso_max_size = GSO_LEGACY_MAX_SIZE; dev->gso_max_segs = GSO_MAX_SEGS; - dev->gro_max_size = GRO_MAX_SIZE; + dev->gro_max_size = GRO_LEGACY_MAX_SIZE; dev->tso_max_size = TSO_LEGACY_MAX_SIZE; dev->tso_max_segs = TSO_MAX_SEGS; dev->upper_level = 1; diff --git a/net/core/gro.c b/net/core/gro.c index 78110edf5d4b..b4190eb08467 100644 --- a/net/core/gro.c +++ b/net/core/gro.c @@ -167,6 +167,14 @@ int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb) if (unlikely(p->len + len >= gro_max_size || NAPI_GRO_CB(skb)->flush)) return -E2BIG; + if (unlikely(p->len + len >= GRO_LEGACY_MAX_SIZE)) { + if (p->protocol != htons(ETH_P_IPV6) || + skb_headroom(p) < sizeof(struct hop_jumbo_hdr) || + ipv6_hdr(p)->nexthdr != IPPROTO_TCP || + p->encapsulation) + return -E2BIG; + } + lp = NAPI_GRO_CB(p)->last; pinfo = skb_shinfo(lp); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index f2b0f747d3d2..ac45328607f7 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2360,14 +2360,6 @@ static int validate_linkmsg(struct net_device *dev, struct nlattr *tb[], } } - if (tb[IFLA_GRO_MAX_SIZE]) { - u32 gro_max_size = nla_get_u32(tb[IFLA_GRO_MAX_SIZE]); - - if (gro_max_size > GRO_MAX_SIZE) { - NL_SET_ERR_MSG(extack, "too big gro_max_size"); - return -EINVAL; - } - } return 0; } -- cgit v1.2.3-71-gd317