tcp: BIG TCP implementation
Subsystems (10)
v3 cover tcp: BIG TCP implementation
From: Eric Dumazet <[email protected]>
This series implements BIG TCP as presented in netdev 0x15:
https://netdevconf.info/0x15/session.html?BIG-TCP
Jonathan Corbet made a nice summary: https://lwn.net/Articles/884104/
Standard TSO/GRO packet limit is 64KB
With BIG TCP, we allow bigger TSO/GRO packet sizes for IPv6 traffic.
Note that this feature is by default not enabled, because it might break some eBPF programs assuming TCP header immediately follows IPv6 header.
While tcpdump recognizes the HBH/Jumbo header, standard pcap filters are unable to skip over IPv6 extension headers.
Reducing number of packets traversing networking stack usually improves performance, as shown on this experiment using a 100Gbit NIC, and 4K MTU.
'Standard' performance with current (74KB) limits.
for i in {1..10}; do ./netperf -t TCP_RR -H iroa23 -- -r80000,80000 -O MIN_LATENCY,P90_LATENCY,P99_LATENCY,THROUGHPUT|tail -1; done
77 138 183 8542.19 79 143 178 8215.28 70 117 164 9543.39 80 144 176 8183.71 78 126 155 9108.47 80 146 184 8115.19 71 113 165 9510.96 74 113 164 9518.74 79 137 178 8575.04 73 111 171 9561.73
Now enable BIG TCP on both hosts.
ip link set dev eth0 gro_ipv6_max_size 185000 gso_ipv6_max_size 185000
for i in {1..10}; do ./netperf -t TCP_RR -H iroa23 -- -r80000,80000 -O MIN_LATENCY,P90_LATENCY,P99_LATENCY,THROUGHPUT|tail -1; done
57 83 117 13871.38 64 118 155 11432.94 65 116 148 11507.62 60 105 136 12645.15 60 103 135 12760.34 60 102 134 12832.64 62 109 132 10877.68 58 82 115 14052.93 57 83 124 14212.58 57 82 119 14196.01
We see an increase of transactions per second, and lower latencies as well.
v3: Fixed a typo in RFC number (Alexander)
Added Reviewed-by: tags from Tariq on mlx4/mlx5 parts.
v2: Removed the MAX_SKB_FRAGS change, this belongs to a different series.
Addressed feedback, for Alexander and nvidia folks.
Coco Li (5):
ipv6: add dev->gso_ipv6_max_size
ipv6: add GRO_IPV6_MAX_SIZE
ipv6: Add hop-by-hop header to jumbograms in ip6_output
ipvlan: enable BIG TCP Packets
mlx5: support BIG TCP packets
Eric Dumazet (9):
net: add netdev->tso_ipv6_max_size attribute
tcp_cubic: make hystart_ack_delay() aware of BIG TCP
ipv6: add struct hop_jumbo_hdr definition ipv6/gso: remove temporary HBH/jumbo header ipv6/gro: insert temporary HBH/jumbo header
net: loopback: enable BIG TCP packets
bonding: update dev->tso_ipv6_max_size
macvlan: enable BIG TCP Packets
mlx4: support BIG TCP packets
drivers/net/bonding/bond_main.c | 3 + .../net/ethernet/mellanox/mlx4/en_netdev.c | 3 + drivers/net/ethernet/mellanox/mlx4/en_tx.c | 47 +++++++++-- .../net/ethernet/mellanox/mlx5/core/en_main.c | 1 + .../net/ethernet/mellanox/mlx5/core/en_tx.c | 82 +++++++++++++++---- drivers/net/ipvlan/ipvlan_main.c | 1 + drivers/net/loopback.c | 2 + drivers/net/macvlan.c | 1 + include/linux/ipv6.h | 1 + include/linux/netdevice.h | 32 ++++++++ include/net/ipv6.h | 44 ++++++++++ include/uapi/linux/if_link.h | 3 + net/core/dev.c | 4 + net/core/gro.c | 20 ++++- net/core/rtnetlink.c | 33 ++++++++ net/core/sock.c | 6 ++ net/ipv4/tcp_cubic.c | 4 +- net/ipv6/ip6_offload.c | 56 ++++++++++++- net/ipv6/ip6_output.c | 22 ++++- tools/include/uapi/linux/if_link.h | 3 + 20 files changed, 334 insertions(+), 34 deletions(-)
Signature · 1 line
2.35.1.616.g0bdcbb4464-goog
PATCH v3 1/14 net: add netdev->tso_ipv6_max_size attribute
From: Eric Dumazet <[email protected]>
Some NIC (or virtual devices) are LSOv2 compatible.
BIG TCP plans using the large LSOv2 feature for IPv6.
New netlink attribute IFLA_TSO_IPV6_MAX_SIZE is defined.
Drivers should use netif_set_tso_ipv6_max_size() to advertize their limit.
Unchanged drivers are not allowing big TSO packets to be sent.
--- include/linux/netdevice.h | 10 ++++++++++ include/uapi/linux/if_link.h | 1 + net/core/dev.c | 2 ++ net/core/rtnetlink.c | 3 +++ tools/include/uapi/linux/if_link.h | 1 + 5 files changed, 17 insertions(+)
include/linux/netdevice.h +10 -0
@@ -1951,6 +1951,7 @@ enum netdev_ml_priv_type {* @dev_registered_tracker: tracker for reference held while * registered * @offload_xstats_l3: L3 HW stats for this netdevice. +* @tso_ipv6_max_size: Maximum size of IPv6 TSO packets (driver/NIC limit) * * FIXME: cleanup struct net_device such that network protocol info * moves out.
@@ -2289,6 +2290,7 @@ struct net_device {netdevice_tracker watchdog_dev_tracker;netdevice_tracker dev_registered_tracker;struct rtnl_hw_stats64 *offload_xstats_l3; +unsigned int tso_ipv6_max_size; };#define to_net_dev (d) container_of(d, struct net_device, dev)
@@ -4888,6 +4890,14 @@ static inline void netif_set_gro_max_size(struct net_device *dev,WRITE_ONCE (dev->gro_max_size, size); } +/* Used by drivers to give their hardware/firmware limit for LSOv2 packets */ +static inline void netif_set_tso_ipv6_max_size (struct net_device *dev, +unsigned int size) +{ + dev->tso_ipv6_max_size = size; +} + +static inline void skb_gso_error_unwind (struct sk_buff *skb,__be16 protocol,int pulled_hlen,u16 mac_offset,int mac_len)
include/uapi/linux/if_link.h +1 -0
@@ -363,6 +363,7 @@ enum {IFLA_PARENT_DEV_NAME ,IFLA_PARENT_DEV_BUS_NAME ,IFLA_GRO_MAX_SIZE , +IFLA_TSO_IPV6_MAX_SIZE , __IFLA_MAX };
net/core/dev.c +2 -0
@@ -10467,6 +10467,8 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, dev->gso_max_size =GSO_MAX_SIZE ; dev->gso_max_segs =GSO_MAX_SEGS ; dev->gro_max_size =GRO_MAX_SIZE ; + dev->tso_ipv6_max_size =GSO_MAX_SIZE ; + dev->upper_level =1 ; dev->lower_level =1 ;#ifdef CONFIG_LOCKDEP
net/core/rtnetlink.c +3 -0
@@ -1027,6 +1027,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev, +nla_total_size (4 )/* IFLA_GSO_MAX_SEGS */ +nla_total_size (4 )/* IFLA_GSO_MAX_SIZE */ +nla_total_size (4 )/* IFLA_GRO_MAX_SIZE */ + +nla_total_size (4 )/* IFLA_TSO_IPV6_MAX_SIZE */ +nla_total_size (1 )/* IFLA_OPERSTATE */ +nla_total_size (1 )/* IFLA_LINKMODE */ +nla_total_size (4 )/* IFLA_CARRIER_CHANGES */
@@ -1732,6 +1733,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, nla_put_u32(skb, IFLA_GSO_MAX_SEGS, dev->gso_max_segs) || nla_put_u32(skb, IFLA_GSO_MAX_SIZE, dev->gso_max_size) || nla_put_u32(skb, IFLA_GRO_MAX_SIZE, dev->gro_max_size) || + nla_put_u32(skb, IFLA_TSO_IPV6_MAX_SIZE, dev->tso_ipv6_max_size) ||#ifdef CONFIG_RPS nla_put_u32(skb, IFLA_NUM_RX_QUEUES, dev->num_rx_queues) ||#endif
@@ -1885,6 +1887,7 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = { [IFLA_NEW_IFINDEX] = NLA_POLICY_MIN(NLA_S32, 1), [IFLA_PARENT_DEV_NAME] = { .type = NLA_NUL_STRING }, [IFLA_GRO_MAX_SIZE] = { .type = NLA_U32 }, + [IFLA_TSO_IPV6_MAX_SIZE] = { .type = NLA_U32 }, };static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX +1 ] = {
tools/include/uapi/linux/if_link.h +1 -0
@@ -348,6 +348,7 @@ enum {IFLA_PARENT_DEV_NAME ,IFLA_PARENT_DEV_BUS_NAME ,IFLA_GRO_MAX_SIZE , +IFLA_TSO_IPV6_MAX_SIZE , __IFLA_MAX };
Signature · 1 line
2.35.1.616.g0bdcbb4464-goog
PATCH v3 2/14 ipv6: add dev->gso_ipv6_max_size
In reply to Eric DumazetFrom: Coco Li <[email protected]>
This enable TCP stack to build TSO packets bigger than 64KB if the driver is LSOv2 compatible.
This patch introduces new variable gso_ipv6_max_size that is modifiable through ip link.
ip link set dev eth0 gso_ipv6_max_size 185000
User input is capped by driver limit (tso_ipv6_max_size) added in previous patch.
--- include/linux/netdevice.h | 12 ++++++++++++ include/uapi/linux/if_link.h | 1 + net/core/dev.c | 1 + net/core/rtnetlink.c | 15 +++++++++++++++ net/core/sock.c | 6 ++++++ tools/include/uapi/linux/if_link.h | 1 + 6 files changed, 36 insertions(+)
include/linux/netdevice.h +12 -0
@@ -1952,6 +1952,7 @@ enum netdev_ml_priv_type {* registered * @offload_xstats_l3: L3 HW stats for this netdevice. * @tso_ipv6_max_size: Maximum size of IPv6 TSO packets (driver/NIC limit) +* @gso_ipv6_max_size: Maximum size of IPv6 GSO packets (user/admin limit) * * FIXME: cleanup struct net_device such that network protocol info * moves out.
@@ -2291,6 +2292,7 @@ struct net_device {netdevice_tracker dev_registered_tracker;struct rtnl_hw_stats64 *offload_xstats_l3;unsigned int tso_ipv6_max_size; +unsigned int gso_ipv6_max_size; };#define to_net_dev (d) container_of(d, struct net_device, dev)
@@ -4874,6 +4876,10 @@ static inline void netif_set_gso_max_size(struct net_device *dev, {/* dev->gso_max_size is read locklessly from sk_setup_caps() */ WRITE_ONCE (dev->gso_max_size, size); + +/* legacy drivers want to lower gso_max_size, regardless of family. */ + size =min (size, dev->gso_ipv6_max_size); +WRITE_ONCE (dev->gso_ipv6_max_size, size); } static inline void netif_set_gso_max_segs(struct net_device *dev,
@@ -4897,6 +4903,12 @@ static inline void netif_set_tso_ipv6_max_size(struct net_device *dev, dev->tso_ipv6_max_size = size; } +static inline void netif_set_gso_ipv6_max_size (struct net_device *dev, +unsigned int size) +{ + size =min (size, dev->tso_ipv6_max_size); +WRITE_ONCE (dev->gso_ipv6_max_size, size); +} static inline void skb_gso_error_unwind(struct sk_buff *skb, __be16 protocol, int pulled_hlen, u16 mac_offset,
include/uapi/linux/if_link.h +1 -0
@@ -364,6 +364,7 @@ enum {IFLA_PARENT_DEV_BUS_NAME ,IFLA_GRO_MAX_SIZE ,IFLA_TSO_IPV6_MAX_SIZE , +IFLA_GSO_IPV6_MAX_SIZE , __IFLA_MAX };
net/core/dev.c +1 -0
@@ -10468,6 +10468,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, dev->gso_max_segs =GSO_MAX_SEGS ; dev->gro_max_size =GRO_MAX_SIZE ; dev->tso_ipv6_max_size =GSO_MAX_SIZE ; + dev->gso_ipv6_max_size =GSO_MAX_SIZE ; dev->upper_level =1 ; dev->lower_level =1 ;
net/core/rtnetlink.c +15 -0
@@ -1028,6 +1028,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev, +nla_total_size (4 )/* IFLA_GSO_MAX_SIZE */ +nla_total_size (4 )/* IFLA_GRO_MAX_SIZE */ +nla_total_size (4 )/* IFLA_TSO_IPV6_MAX_SIZE */ + +nla_total_size (4 )/* IFLA_GSO_IPV6_MAX_SIZE */ +nla_total_size (1 )/* IFLA_OPERSTATE */ +nla_total_size (1 )/* IFLA_LINKMODE */ +nla_total_size (4 )/* IFLA_CARRIER_CHANGES */
@@ -1734,6 +1735,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, nla_put_u32(skb, IFLA_GSO_MAX_SIZE, dev->gso_max_size) || nla_put_u32(skb, IFLA_GRO_MAX_SIZE, dev->gro_max_size) || nla_put_u32(skb, IFLA_TSO_IPV6_MAX_SIZE, dev->tso_ipv6_max_size) || + nla_put_u32(skb, IFLA_GSO_IPV6_MAX_SIZE, dev->gso_ipv6_max_size) ||#ifdef CONFIG_RPS nla_put_u32(skb, IFLA_NUM_RX_QUEUES, dev->num_rx_queues) ||#endif
@@ -1888,6 +1890,7 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = { [IFLA_PARENT_DEV_NAME] = { .type = NLA_NUL_STRING }, [IFLA_GRO_MAX_SIZE] = { .type = NLA_U32 }, [IFLA_TSO_IPV6_MAX_SIZE] = { .type = NLA_U32 }, + [IFLA_GSO_IPV6_MAX_SIZE] = { .type = NLA_U32 }, };static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX +1 ] = {
@@ -2774,6 +2777,15 @@ static int do_setlink(const struct sk_buff *skb, } } +if (tb[IFLA_GSO_IPV6_MAX_SIZE ]) { +u32 max_size =nla_get_u32 (tb[IFLA_GSO_IPV6_MAX_SIZE ]); + +if (dev->gso_ipv6_max_size ^ max_size) { +netif_set_gso_ipv6_max_size (dev, max_size); + status |=DO_SETLINK_MODIFIED ; + } + } +if (tb[IFLA_GSO_MAX_SEGS ]) {u32 max_segs =nla_get_u32 (tb[IFLA_GSO_MAX_SEGS ]);
@@ -3249,6 +3261,9 @@ struct net_device *rtnl_create_link(struct net *net, const char *ifname,netif_set_gso_max_segs (dev,nla_get_u32 (tb[IFLA_GSO_MAX_SEGS ]));if (tb[IFLA_GRO_MAX_SIZE ])netif_set_gro_max_size (dev,nla_get_u32 (tb[IFLA_GRO_MAX_SIZE ])); +if (tb[IFLA_GSO_IPV6_MAX_SIZE ]) +netif_set_gso_ipv6_max_size (dev, +nla_get_u32 (tb[IFLA_GSO_IPV6_MAX_SIZE ]));return dev; }
net/core/sock.c +6 -0
@@ -2279,6 +2279,12 @@ void sk_setup_caps(struct sock *sk, struct dst_entry *dst) sk->sk_route_caps |=NETIF_F_SG |NETIF_F_HW_CSUM ;/* pairs with the WRITE_ONCE() in netif_set_gso_max_size() */ sk->sk_gso_max_size =READ_ONCE (dst->dev->gso_max_size); +#if IS_ENABLED (CONFIG_IPV6 ) +if (sk->sk_family ==AF_INET6 && +sk_is_tcp (sk) && + !ipv6_addr_v4mapped (&sk->sk_v6_rcv_saddr)) + sk->sk_gso_max_size =READ_ONCE (dst->dev->gso_ipv6_max_size); +#endif sk->sk_gso_max_size -= (MAX_TCP_HEADER +1 );/* pairs with the WRITE_ONCE() in netif_set_gso_max_segs() */ max_segs =max_t (u32,READ_ONCE (dst->dev->gso_max_segs),1 );
tools/include/uapi/linux/if_link.h +1 -0
@@ -349,6 +349,7 @@ enum {IFLA_PARENT_DEV_BUS_NAME ,IFLA_GRO_MAX_SIZE ,IFLA_TSO_IPV6_MAX_SIZE , +IFLA_GSO_IPV6_MAX_SIZE , __IFLA_MAX };
Signature · 1 line
2.35.1.616.g0bdcbb4464-goog
PATCH v3 3/14 tcp_cubic: make hystart_ack_delay() aware of BIG TCP
In reply to Eric DumazetFrom: Eric Dumazet <[email protected]>
hystart_ack_delay() had the assumption that a TSO packet would not be bigger than GSO_MAX_SIZE.
This will no longer be true.
We should use sk->sk_gso_max_size instead.
This reduces chances of spurious Hystart ACK train detections.
--- net/ipv4/tcp_cubic.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
net/ipv4/tcp_cubic.c +2 -2
@@ -372,7 +372,7 @@ static void cubictcp_state(struct sock *sk, u8 new_state)* We apply another 100% factor because @rate is doubled at this point. * We cap the cushion to 1ms. */ -static u32 hystart_ack_delay (struct sock *sk) +static u32 hystart_ack_delay (const struct sock *sk) {unsigned long rate;
@@ -380,7 +380,7 @@ static u32 hystart_ack_delay(struct sock *sk)if (!rate)return 0 ;return min_t (u64,USEC_PER_MSEC , -div64_ul ((u64 )GSO_MAX_SIZE *4 *USEC_PER_SEC , rate)); +div64_ul ((u64 )sk->sk_gso_max_size *4 *USEC_PER_SEC , rate)); }static void hystart_update (struct sock *sk,u32 delay)
Signature · 1 line
2.35.1.616.g0bdcbb4464-goog
PATCH v3 4/14 ipv6: add struct hop_jumbo_hdr definition
In reply to Eric DumazetFrom: Eric Dumazet <[email protected]>
Following patches will need to add and remove local IPv6 jumbogram options to enable BIG TCP.
--- include/net/ipv6.h | 11 +++++++++++ 1 file changed, 11 insertions(+)
include/net/ipv6.h +11 -0
@@ -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
Signature · 1 line
2.35.1.616.g0bdcbb4464-goog
PATCH v3 5/14 ipv6/gso: remove temporary HBH/jumbo header
In reply to Eric DumazetFrom: Eric Dumazet <[email protected]>
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)
--- include/net/ipv6.h | 33 +++++++++++++++++++++++++++++++++ net/ipv6/ip6_offload.c | 24 +++++++++++++++++++++++- 2 files changed, 56 insertions(+), 1 deletion(-)
include/net/ipv6.h +33 -0
@@ -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
net/ipv6/ip6_offload.c +23 -1
@@ -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;
Signature · 1 line
2.35.1.616.g0bdcbb4464-goog
PATCH v3 6/14 ipv6/gro: insert temporary HBH/jumbo header
In reply to Eric DumazetFrom: Eric Dumazet <[email protected]>
Following patch will add GRO_IPV6_MAX_SIZE, allowing gro to build BIG TCP ipv6 packets (bigger than 64K).
This patch changes ipv6_gro_complete() to insert a HBH/jumbo header so that resulting packet can go through IPv6/TCP stacks.
--- net/ipv6/ip6_offload.c | 32 ++++++++++++++++++++++++++++++-- 1 file changed, 30 insertions(+), 2 deletions(-)
net/ipv6/ip6_offload.c +30 -2
@@ -342,15 +342,43 @@ static struct sk_buff *ip4ip6_gro_receive(struct list_head *head, INDIRECT_CALLABLE_SCOPE int ipv6_gro_complete(struct sk_buff *skb, int nhoff) {const struct net_offload *ops; -struct ipv6hdr *iph = (struct ipv6hdr *)(skb->data + nhoff); +struct ipv6hdr *iph;int err = -ENOSYS ; +u32 payload_len;if (skb->encapsulation) {skb_set_inner_protocol (skb,cpu_to_be16 (ETH_P_IPV6 ));skb_set_inner_network_header (skb, nhoff); } - iph->payload_len =htons (skb->len - nhoff -sizeof (*iph)); + payload_len = skb->len - nhoff -sizeof (*iph); +if (unlikely (payload_len >IPV6_MAXPLEN )) { +struct hop_jumbo_hdr *hop_jumbo; +int hoplen =sizeof (*hop_jumbo); + +/* Move network header left */ +memmove (skb_mac_header (skb) - hoplen,skb_mac_header (skb), + skb->transport_header - skb->mac_header); + skb->data -= hoplen; + skb->len += hoplen; + skb->mac_header -= hoplen; + skb->network_header -= hoplen; + iph = (struct ipv6hdr *)(skb->data + nhoff); + hop_jumbo = (struct hop_jumbo_hdr *)(iph +1 ); + +/* Build hop-by-hop options */ + hop_jumbo->nexthdr = iph->nexthdr; + hop_jumbo->hdrlen =0 ; + hop_jumbo->tlv_type =IPV6_TLV_JUMBO ; + hop_jumbo->tlv_len =4 ; + hop_jumbo->jumbo_payload_len =htonl (payload_len + hoplen); + + iph->nexthdr =NEXTHDR_HOP ; + iph->payload_len =0 ; + }else { + iph = (struct ipv6hdr *)(skb->data + nhoff); + iph->payload_len =htons (payload_len); + } nhoff +=sizeof (*iph) +ipv6_exthdrs_len (iph, &ops);if (WARN_ON (!ops || !ops->callbacks.gro_complete))
Signature · 1 line
2.35.1.616.g0bdcbb4464-goog
PATCH v3 7/14 ipv6: add GRO_IPV6_MAX_SIZE
In reply to Eric DumazetFrom: Coco Li <[email protected]>
Enable GRO to have IPv6 specific limit for max packet size.
This patch introduces new dev->gro_ipv6_max_size that is modifiable through ip link.
ip link set dev eth0 gro_ipv6_max_size 185000
Note that this value is only considered if bigger than gro_max_size, and for non encapsulated TCP/ipv6 packets.
--- include/linux/netdevice.h | 10 ++++++++++ include/uapi/linux/if_link.h | 1 + net/core/dev.c | 1 + net/core/gro.c | 20 ++++++++++++++++++-- net/core/rtnetlink.c | 15 +++++++++++++++ tools/include/uapi/linux/if_link.h | 1 + 6 files changed, 46 insertions(+), 2 deletions(-)
include/linux/netdevice.h +10 -0
@@ -1944,6 +1944,8 @@ enum netdev_ml_priv_type {* keep a list of interfaces to be deleted. * @gro_max_size: Maximum size of aggregated packet in generic * receive offload (GRO) +* @gro_ipv6_max_size: Maximum size of aggregated packet in generic +* receive offload (GRO), for IPv6 * * @dev_addr_shadow: Copy of @dev_addr to catch direct writes. * @linkwatch_dev_tracker: refcount tracker used by linkwatch.
@@ -2140,6 +2142,7 @@ struct net_device {int napi_defer_hard_irqs;#define GRO_MAX_SIZE 65536unsigned int gro_max_size; +unsigned int gro_ipv6_max_size;rx_handler_func_t __rcu *rx_handler;void __rcu *rx_handler_data;
@@ -4910,6 +4913,13 @@ static inline void netif_set_gso_ipv6_max_size(struct net_device *dev,WRITE_ONCE (dev->gso_ipv6_max_size, size); } +static inline void netif_set_gro_ipv6_max_size (struct net_device *dev, +unsigned int size) +{ +/* This pairs with the READ_ONCE() in skb_gro_receive() */ +WRITE_ONCE (dev->gro_ipv6_max_size, size); +} +static inline void skb_gso_error_unwind (struct sk_buff *skb,__be16 protocol,int pulled_hlen,u16 mac_offset,int mac_len)
include/uapi/linux/if_link.h +1 -0
@@ -365,6 +365,7 @@ enum {IFLA_GRO_MAX_SIZE ,IFLA_TSO_IPV6_MAX_SIZE ,IFLA_GSO_IPV6_MAX_SIZE , +IFLA_GRO_IPV6_MAX_SIZE , __IFLA_MAX };
net/core/dev.c +1 -0
@@ -10469,6 +10469,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, dev->gro_max_size =GRO_MAX_SIZE ; dev->tso_ipv6_max_size =GSO_MAX_SIZE ; dev->gso_ipv6_max_size =GSO_MAX_SIZE ; + dev->gro_ipv6_max_size =GRO_MAX_SIZE ; dev->upper_level =1 ; dev->lower_level =1 ;
net/core/gro.c +18 -2
@@ -136,11 +136,27 @@ int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb)unsigned int new_truesize;struct sk_buff *lp; +if (unlikely (NAPI_GRO_CB (skb)->flush)) +return -E2BIG ; +/* pairs with WRITE_ONCE() in netif_set_gro_max_size() */ gro_max_size =READ_ONCE (p->dev->gro_max_size); -if (unlikely (p->len + len >= gro_max_size ||NAPI_GRO_CB (skb)->flush)) -return -E2BIG ; +if (unlikely (p->len + len >= gro_max_size)) { +/* pairs with WRITE_ONCE() in netif_set_gro_ipv6_max_size() */ +unsigned int gro6_max_size =READ_ONCE (p->dev->gro_ipv6_max_size); + +if (gro6_max_size > gro_max_size && + p->protocol ==htons (ETH_P_IPV6 ) && +skb_headroom (p) >=sizeof (struct hop_jumbo_hdr ) && +ipv6_hdr (p)->nexthdr ==IPPROTO_TCP && + !p->encapsulation) + gro_max_size = gro6_max_size; + +if (p->len + len >= gro_max_size) +return -E2BIG ; + } + lp =NAPI_GRO_CB (p)->last; pinfo =skb_shinfo (lp);
net/core/rtnetlink.c +15 -0
@@ -1029,6 +1029,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev, +nla_total_size (4 )/* IFLA_GRO_MAX_SIZE */ +nla_total_size (4 )/* IFLA_TSO_IPV6_MAX_SIZE */ +nla_total_size (4 )/* IFLA_GSO_IPV6_MAX_SIZE */ + +nla_total_size (4 )/* IFLA_GRO_IPV6_MAX_SIZE */ +nla_total_size (1 )/* IFLA_OPERSTATE */ +nla_total_size (1 )/* IFLA_LINKMODE */ +nla_total_size (4 )/* IFLA_CARRIER_CHANGES */
@@ -1736,6 +1737,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb,nla_put_u32 (skb,IFLA_GRO_MAX_SIZE , dev->gro_max_size) ||nla_put_u32 (skb,IFLA_TSO_IPV6_MAX_SIZE , dev->tso_ipv6_max_size) ||nla_put_u32 (skb,IFLA_GSO_IPV6_MAX_SIZE , dev->gso_ipv6_max_size) || +nla_put_u32 (skb,IFLA_GRO_IPV6_MAX_SIZE , dev->gro_ipv6_max_size) || #ifdef CONFIG_RPS nla_put_u32(skb, IFLA_NUM_RX_QUEUES, dev->num_rx_queues) || #endif
@@ -1891,6 +1893,7 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = { [IFLA_GRO_MAX_SIZE] = { .type = NLA_U32 }, [IFLA_TSO_IPV6_MAX_SIZE] = { .type = NLA_U32 }, [IFLA_GSO_IPV6_MAX_SIZE] = { .type = NLA_U32 }, + [IFLA_GRO_IPV6_MAX_SIZE] = { .type = NLA_U32 }, };static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX +1 ] = {
@@ -2786,6 +2789,15 @@ static int do_setlink(const struct sk_buff *skb, } } +if (tb[IFLA_GRO_IPV6_MAX_SIZE ]) { +u32 max_size =nla_get_u32 (tb[IFLA_GRO_IPV6_MAX_SIZE ]); + +if (dev->gro_ipv6_max_size ^ max_size) { +netif_set_gro_ipv6_max_size (dev, max_size); + status |=DO_SETLINK_MODIFIED ; + } + } +if (tb[IFLA_GSO_MAX_SEGS ]) {u32 max_segs =nla_get_u32 (tb[IFLA_GSO_MAX_SEGS ]);
@@ -3264,6 +3276,9 @@ struct net_device *rtnl_create_link(struct net *net, const char *ifname,if (tb[IFLA_GSO_IPV6_MAX_SIZE ])netif_set_gso_ipv6_max_size (dev,nla_get_u32 (tb[IFLA_GSO_IPV6_MAX_SIZE ])); +if (tb[IFLA_GRO_IPV6_MAX_SIZE ]) +netif_set_gro_ipv6_max_size (dev, +nla_get_u32 (tb[IFLA_GRO_IPV6_MAX_SIZE ]));return dev; }
tools/include/uapi/linux/if_link.h +1 -0
@@ -350,6 +350,7 @@ enum {IFLA_GRO_MAX_SIZE ,IFLA_TSO_IPV6_MAX_SIZE ,IFLA_GSO_IPV6_MAX_SIZE , +IFLA_GRO_IPV6_MAX_SIZE , __IFLA_MAX };
Signature · 1 line
2.35.1.616.g0bdcbb4464-goog
PATCH v3 8/14 ipv6: Add hop-by-hop header to jumbograms in ip6_output
In reply to Eric DumazetFrom: Coco Li <[email protected]>
Instead of simply forcing a 0 payload_len in IPv6 header, implement RFC 2675 and insert a custom extension header.
Note that only TCP stack is currently potentially generating jumbograms, and that this extension header is purely local, it wont be sent on a physical link.
This is needed so that packet capture (tcpdump and friends) can properly dissect these large packets.
--- include/linux/ipv6.h | 1 + net/ipv6/ip6_output.c | 22 ++++++++++++++++++++-- 2 files changed, 21 insertions(+), 2 deletions(-)
include/linux/ipv6.h +1 -0
@@ -144,6 +144,7 @@ struct inet6_skb_parm {#define IP6SKB_L3SLAVE 64#define IP6SKB_JUMBOGRAM 128#define IP6SKB_SEG6 256 +#define IP6SKB_FAKEJUMBO 512 };#if defined(CONFIG_NET_L3_MASTER_DEV )
net/ipv6/ip6_output.c +20 -2
@@ -180,7 +180,9 @@ static int __ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff#endif mtu =ip6_skb_dst_mtu (skb); -if (skb_is_gso (skb) && !skb_gso_validate_network_len (skb, mtu)) +if (skb_is_gso (skb) && + !(IP6CB (skb)->flags &IP6SKB_FAKEJUMBO ) && + !skb_gso_validate_network_len (skb, mtu))return ip6_finish_output_gso_slowpath_drop (net, sk, skb, mtu); if ((skb->len > mtu && !skb_is_gso(skb)) ||
@@ -251,6 +253,8 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,struct dst_entry *dst =skb_dst (skb);struct net_device *dev = dst->dev;struct inet6_dev *idev =ip6_dst_idev (dst); +struct hop_jumbo_hdr *hop_jumbo; +int hoplen =sizeof (*hop_jumbo);unsigned int head_room;struct ipv6hdr *hdr;u8 proto = fl6->flowi6_proto;
@@ -258,7 +262,7 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,int hlimit =-1 ;u32 mtu; - head_room =sizeof (struct ipv6hdr ) +LL_RESERVED_SPACE (dev); + head_room =sizeof (struct ipv6hdr ) + hoplen +LL_RESERVED_SPACE (dev);if (opt) head_room += opt->opt_nflen + opt->opt_flen;
@@ -281,6 +285,20 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, &fl6->saddr); } +if (unlikely (seg_len >IPV6_MAXPLEN )) { + hop_jumbo =skb_push (skb, hoplen); + + hop_jumbo->nexthdr = proto; + hop_jumbo->hdrlen =0 ; + hop_jumbo->tlv_type =IPV6_TLV_JUMBO ; + hop_jumbo->tlv_len =4 ; + hop_jumbo->jumbo_payload_len =htonl (seg_len + hoplen); + + proto =IPPROTO_HOPOPTS ; + seg_len =0 ; +IP6CB (skb)->flags |=IP6SKB_FAKEJUMBO ; + } +skb_push (skb,sizeof (struct ipv6hdr ));skb_reset_network_header (skb); hdr =ipv6_hdr (skb);
Signature · 1 line
2.35.1.616.g0bdcbb4464-goog
PATCH v3 9/14 net: loopback: enable BIG TCP packets
In reply to Eric DumazetFrom: Eric Dumazet <[email protected]>
Set the driver limit to 512 KB per TSO ipv6 packet.
This allows the admin/user to set a GSO ipv6 limit up to this value.
Tested:
ip link set dev lo gso_ipv6_max_size 200000 netperf -H ::1 -t TCP_RR -l 100 -- -r 80000,80000 &
tcpdump shows :
18:28:42.962116 IP6 ::1 > ::1: HBH 40051 > 63780: Flags [P.], seq 3626480001:3626560001, ack 3626560001, win 17743, options [nop,nop,TS val 3771179265 ecr 3771179265], length 80000 18:28:42.962138 IP6 ::1.63780 > ::1.40051: Flags [.], ack 3626560001, win 17743, options [nop,nop,TS val 3771179265 ecr 3771179265], length 0 18:28:42.962152 IP6 ::1 > ::1: HBH 63780 > 40051: Flags [P.], seq 3626560001:3626640001, ack 3626560001, win 17743, options [nop,nop,TS val 3771179265 ecr 3771179265], length 80000 18:28:42.962157 IP6 ::1.40051 > ::1.63780: Flags [.], ack 3626640001, win 17743, options [nop,nop,TS val 3771179265 ecr 3771179265], length 0 18:28:42.962180 IP6 ::1 > ::1: HBH 40051 > 63780: Flags [P.], seq 3626560001:3626640001, ack 3626640001, win 17743, options [nop,nop,TS val 3771179265 ecr 3771179265], length 80000 18:28:42.962214 IP6 ::1.63780 > ::1.40051: Flags [.], ack 3626640001, win 17743, options [nop,nop,TS val 3771179266 ecr 3771179265], length 0 18:28:42.962228 IP6 ::1 > ::1: HBH 63780 > 40051: Flags [P.], seq 3626640001:3626720001, ack 3626640001, win 17743, options [nop,nop,TS val 3771179266 ecr 3771179265], length 80000 18:28:42.962233 IP6 ::1.40051 > ::1.63780: Flags [.], ack 3626720001, win 17743, options [nop,nop,TS val 3771179266 ecr 3771179266], length 0
--- drivers/net/loopback.c | 2 ++ 1 file changed, 2 insertions(+)
drivers/net/loopback.c +2 -0
@@ -191,6 +191,8 @@ static void gen_lo_setup(struct net_device *dev, dev->netdev_ops = dev_ops; dev->needs_free_netdev = true; dev->priv_destructor = dev_destructor; + +netif_set_tso_ipv6_max_size (dev,512 *1024 ); }/* The loopback device is special. There is only one instance
Signature · 1 line
2.35.1.616.g0bdcbb4464-goog
PATCH v3 10/14 bonding: update dev->tso_ipv6_max_size
In reply to Eric DumazetFrom: Eric Dumazet <[email protected]>
Use the minimal value found in the set of lower devices.
--- drivers/net/bonding/bond_main.c | 3 +++ 1 file changed, 3 insertions(+)
drivers/net/bonding/bond_main.c +3 -0
@@ -1420,6 +1420,7 @@ static void bond_compute_features(struct bonding *bond)struct slave *slave;unsigned short max_hard_header_len =ETH_HLEN ;unsigned int gso_max_size =GSO_MAX_SIZE ; +unsigned int tso_ipv6_max_size = ~0U ;u16 gso_max_segs =GSO_MAX_SEGS ;if (!bond_has_slaves (bond))
@@ -1450,6 +1451,7 @@ static void bond_compute_features(struct bonding *bond) max_hard_header_len = slave->dev->hard_header_len; gso_max_size =min (gso_max_size, slave->dev->gso_max_size); + tso_ipv6_max_size =min (tso_ipv6_max_size, slave->dev->tso_ipv6_max_size); gso_max_segs =min (gso_max_segs, slave->dev->gso_max_segs); } bond_dev->hard_header_len = max_hard_header_len;
@@ -1465,6 +1467,7 @@ static void bond_compute_features(struct bonding *bond) bond_dev->mpls_features = mpls_features;netif_set_gso_max_segs (bond_dev, gso_max_segs);netif_set_gso_max_size (bond_dev, gso_max_size); +netif_set_tso_ipv6_max_size (bond_dev, tso_ipv6_max_size); bond_dev->priv_flags &= ~IFF_XMIT_DST_RELEASE ; if ((bond_dev->priv_flags & IFF_XMIT_DST_RELEASE_PERM) &&
Signature · 1 line
2.35.1.616.g0bdcbb4464-goog
PATCH v3 11/14 macvlan: enable BIG TCP Packets
In reply to Eric DumazetFrom: Eric Dumazet <[email protected]>
Inherit tso_ipv6_max_size from lower device.
--- drivers/net/macvlan.c | 1 + 1 file changed, 1 insertion(+)
drivers/net/macvlan.c +1 -0
@@ -902,6 +902,7 @@ static int macvlan_init(struct net_device *dev) dev->hw_enc_features |= dev->features;netif_set_gso_max_size (dev, lowerdev->gso_max_size);netif_set_gso_max_segs (dev, lowerdev->gso_max_segs); +netif_set_tso_ipv6_max_size (dev, lowerdev->tso_ipv6_max_size); dev->hard_header_len = lowerdev->hard_header_len;macvlan_set_lockdep_class (dev);
Signature · 1 line
2.35.1.616.g0bdcbb4464-goog
PATCH v3 12/14 ipvlan: enable BIG TCP Packets
In reply to Eric DumazetFrom: Coco Li <[email protected]>
Inherit tso_ipv6_max_size from physical device.
Tested:
eth0 tso_ipv6_max_size is set to 524288
ip link add link eth0 name ipvl1 type ipvlan
ip -d link show ipvl1
10: ipvl1@eth0:...
ipvlan mode l3 bridge addrgenmode eui64 numtxqueues 1 numrxqueues 1 gso_max_size 65536 gso_max_segs 65535 gro_max_size 65536 gso_ipv6_max_size 65535 tso_ipv6_max_size 524288 gro_ipv6_max_size 65536
--- drivers/net/ipvlan/ipvlan_main.c | 1 + 1 file changed, 1 insertion(+)
drivers/net/ipvlan/ipvlan_main.c +1 -0
@@ -141,6 +141,7 @@ static int ipvlan_init(struct net_device *dev) dev->hw_enc_features |= dev->features;netif_set_gso_max_size (dev, phy_dev->gso_max_size);netif_set_gso_max_segs (dev, phy_dev->gso_max_segs); +netif_set_tso_ipv6_max_size (dev, phy_dev->tso_ipv6_max_size); dev->hard_header_len = phy_dev->hard_header_len;netdev_lockdep_set_classes (dev);
Signature · 1 line
2.35.1.616.g0bdcbb4464-goog
PATCH v3 13/14 mlx4: support BIG TCP packets
In reply to Eric DumazetFrom: Eric Dumazet <[email protected]>
mlx4 supports LSOv2 just fine.
IPv6 stack inserts a temporary Hop-by-Hop header
with JUMBO TLV for big packets.
We need to ignore the HBH header when populating TX descriptor.
Tested:
Before: (not enabling bigger TSO/GRO packets)
ip link set dev eth0 gso_ipv6_max_size 65536 gro_ipv6_max_size 65536
netperf -H lpaa18 -t TCP_RR -T2,2 -l 10 -Cc -- -r 70000,70000
MIGRATED TCP REQUEST/RESPONSE TEST from ::0 (::) port 0 AF_INET6 to lpaa18.prod.google.com () port 0 AF_INET6 : first burst 0 : cpu bind Local /Remote
Socket Size Request Resp. Elapsed Trans. CPU CPU S.dem S.dem Send Recv Size Size Time Rate local remote local remote bytes bytes bytes bytes secs. per sec % S % S us/Tr us/Tr
262144 540000 70000 70000 10.00 6591.45 0.86 1.34 62.490 97.446
262144 540000
After: (enabling bigger TSO/GRO packets)
ip link set dev eth0 gso_ipv6_max_size 185000 gro_ipv6_max_size 185000
netperf -H lpaa18 -t TCP_RR -T2,2 -l 10 -Cc -- -r 70000,70000
MIGRATED TCP REQUEST/RESPONSE TEST from ::0 (::) port 0 AF_INET6 to lpaa18.prod.google.com () port 0 AF_INET6 : first burst 0 : cpu bind Local /Remote
Socket Size Request Resp. Elapsed Trans. CPU CPU S.dem S.dem Send Recv Size Size Time Rate local remote local remote bytes bytes bytes bytes secs. per sec % S % S us/Tr us/Tr
262144 540000 70000 70000 10.00 8383.95 0.95 1.01 54.432 57.584
262144 540000
--- .../net/ethernet/mellanox/mlx4/en_netdev.c | 3 ++ drivers/net/ethernet/mellanox/mlx4/en_tx.c | 47 +++++++++++++++---- 2 files changed, 41 insertions(+), 9 deletions(-)
drivers/net/ethernet/mellanox/mlx4/en_netdev.c +3 -0
@@ -3417,6 +3417,9 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port, dev->min_mtu =ETH_MIN_MTU ; dev->max_mtu = priv->max_mtu; +/* supports LSOv2 packets, 512KB limit has been tested. */ +netif_set_tso_ipv6_max_size (dev,512 *1024 ); + mdev->pndev[port] = dev; mdev->upper[port] =NULL ;
drivers/net/ethernet/mellanox/mlx4/en_tx.c +38 -9
103 lines not on this page · raw message
Signature · 1 line
2.35.1.616.g0bdcbb4464-goog
PATCH v3 14/14 mlx5: support BIG TCP packets
In reply to Eric DumazetFrom: Coco Li <[email protected]>
mlx5 supports LSOv2.
IPv6 gro/tcp stacks insert a temporary Hop-by-Hop header with JUMBO TLV for big packets.
We need to ignore/skip this HBH header when populating TX descriptor.
Note that ipv6_has_hopopt_jumbo() only recognizes very specific packet layout, thus mlx5e_sq_xmit_wqe() is taking care of this layout only.
v2: clear hopbyhop in mlx5e_tx_get_gso_ihs()
--- .../net/ethernet/mellanox/mlx5/core/en_main.c | 1 + .../net/ethernet/mellanox/mlx5/core/en_tx.c | 82 +++++++++++++++---- 2 files changed, 67 insertions(+), 16 deletions(-)
drivers/net/ethernet/mellanox/mlx5/core/en_main.c +1 -0
@@ -4910,6 +4910,7 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev) netdev->priv_flags |=IFF_UNICAST_FLT ; +netif_set_tso_ipv6_max_size (netdev,512 *1024 );mlx5e_set_netdev_dev_addr (netdev);mlx5e_ipsec_build_netdev (priv);mlx5e_tls_build_netdev (priv);
drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +66 -16
156 lines not on this page · raw message
Signature · 1 line
2.35.1.616.g0bdcbb4464-goog
Jakub Kicinski
maintainerRe: [PATCH v3 net-next 14/14] mlx5: support BIG TCP packets
Quoted 11 lines · On Wed, 9 Mar 2022 16:28:46 -0800 Eric Dumazet wrote:
drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +6
-1@@ -918,12 +953,27 @@ void mlx5i_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb, eseg->mss = attr.mss;if (attr.ihs) { -memcpy (eseg->inline_hdr.start, skb->data, attr.ihs); +if (unlikely (attr.hopbyhop)) { +/* remove the HBH header. +* Layout: [Ethernet header][IPv6 header][HBH][TCP header] +*/ +memcpy (eseg->inline_hdr.start, skb->data,ETH_HLEN +sizeof (*h6)); + h6 = (struct ipv6hdr *)((char *)eseg->inline_hdr.start +ETH_HLEN );
drivers/net/ethernet/mellanox/mlx5/core/en_tx.c void mlx5i_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb, · line 971
Quoted 10 lines
drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +10
-0+ h6->nexthdr =IPPROTO_TCP ; +/* Copy the TCP header after the IPv6 one */ +memcpy (h6 +1 , + skb->data +ETH_HLEN +sizeof (*h6) + +sizeof (struct hop_jumbo_hdr ), +tcp_hdrlen (skb)); +/* Leave ipv6 payload_len set to 0, as LSO v2 specs request. */ + }else { +memcpy (eseg->inline_hdr.start, skb->data, attr.ihs); + }
Compiler says there's no h6 in mlx5i_sq_xmit().
Re: [PATCH v3 net-next 14/14] mlx5: support BIG TCP packets
Quoted 17 lines · Jakub Kicinski
Quoted 15 lines · On Wed, 9 Mar 2022 16:28:46 -0800 Eric Dumazet wrote:
drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +10
-1@@ -918,12 +953,27 @@ void mlx5i_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb, eseg->mss = attr.mss;if (attr.ihs) { -memcpy (eseg->inline_hdr.start, skb->data, attr.ihs); +if (unlikely (attr.hopbyhop)) { +/* remove the HBH header. +* Layout: [Ethernet header][IPv6 header][HBH][TCP header] +*/ +memcpy (eseg->inline_hdr.start, skb->data,ETH_HLEN +sizeof (*h6)); + h6 = (struct ipv6hdr *)((char *)eseg->inline_hdr.start +ETH_HLEN ); + h6->nexthdr =IPPROTO_TCP ; +/* Copy the TCP header after the IPv6 one */ + memcpy(h6 + 1, + skb->data + ETH_HLEN + sizeof(*h6) +
Quoted 8 lines
drivers/net/ethernet/mellanox/mlx5/core/en_tx.c void mlx5i_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb, · line 971
Quoted 6 lines
drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +6
-0+sizeof (struct hop_jumbo_hdr ), + tcp_hdrlen(skb)); +/* Leave ipv6 payload_len set to 0, as LSO v2 specs request. */ + }else { +memcpy (eseg->inline_hdr.start, skb->data, attr.ihs); + }Compiler says there's no h6 in
mlx5i_sq_xmit().
Ah, we missed CONFIG_MLX5_CORE_IPOIB=y it seems.
Let me take a look before sending the fix.
Re: [PATCH v3 net-next 14/14] mlx5: support BIG TCP packets
Quoted 28 lines · Eric Dumazet
Quoted 17 lines · Jakub Kicinski
Quoted 15 lines · On Wed, 9 Mar 2022 16:28:46 -0800 Eric Dumazet wrote:
(quoted diff) +10
-1@@ -918,12 +953,27 @@ void mlx5i_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb, eseg->mss = attr.mss; if (attr.ihs) { - memcpy(eseg->inline_hdr.start, skb->data, attr.ihs); + if (unlikely(attr.hopbyhop)) { + /* remove the HBH header. + * Layout: [Ethernet header][IPv6 header][HBH][TCP header] + */ + memcpy(eseg->inline_hdr.start, skb->data, ETH_HLEN + sizeof(*h6)); + h6 = (struct ipv6hdr *)((char *)eseg->inline_hdr.start + ETH_HLEN); + h6->nexthdr = IPPROTO_TCP; + /* Copy the TCP header after the IPv6 one */ + memcpy(h6 + 1, + skb->data + ETH_HLEN + sizeof(*h6) +Quoted 8 lines
Review void mlx5i_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb, · line 971
Quoted 6 lines
(quoted diff) +6
-0+ sizeof(struct hop_jumbo_hdr), + tcp_hdrlen(skb)); + /* Leave ipv6 payload_len set to 0, as LSO v2 specs request. */ + } else { + memcpy(eseg->inline_hdr.start, skb->data, attr.ihs); + }Compiler says there's no h6 in
mlx5i_sq_xmit().
Quoted 3 lines
Ah, we missed
CONFIG_MLX5_CORE_IPOIB=yit seems.Let me take a look before sending the fix.
I will squash this:
(quoted diff) +0 -0
b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index c6f6ca2d216692e1d3fd99e540198b11145788cd..b4fc45ba1b347fb9ad0f46b9c091cc45e4d3d84f 100644
drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +0 -0
@@ -954,6 +954,8 @@ void mlx5i_sq_xmit(struct mlx5e_txqsq *sq, struct
sk_buff *skb,
if (attr.ihs) {
if (unlikely(attr.hopbyhop)) {+ struct ipv6hdr *h6;
+
/* remove the HBH header.
* Layout: [Ethernet header][IPv6
header][HBH][TCP header]
*/