net: support ipv4 big tcp
Subsystems (12)
v3 cover net: support ipv4 big tcp
This is similar to the BIG TCP patchset added by Eric for IPv6:
https://lwn.net/Articles/895398/
Different from IPv6, IPv4 tot_len is 16-bit long only, and IPv4 header doesn't have exthdrs(options) for the BIG TCP packets' length. To make it simple, as David and Paolo suggested, we set IPv4 tot_len to 0 to indicate this might be a BIG TCP packet and use skb->len as the real IPv4 total length.
This will work safely, as all BIG TCP packets are GSO/GRO packets and processed on the same host as they were created; There is no padding in GSO/GRO packets, and skb->len - network_offset is exactly the IPv4 packet total length; Also, before implementing the feature, all those places that may get iph tot_len from BIG TCP packets are taken care with some new APIs:
Patch 1 adds some APIs for iph tot_len setting and getting, which are used in all these places where IPv4 BIG TCP packets may reach in Patch 2-7, Patch 8 adds a GSO_TCP tp_status for af_packet users, and Patch 9 add new netlink attributes to make IPv4 BIG TCP independent from IPv6 BIG TCP on configuration, and Patch 10 implements this feature.
Note that the similar change as in Patch 2-6 are also needed for IPv6 BIG TCP packets, and will be addressed in another patchset.
The similar performance test is done for IPv4 BIG TCP with 25Gbit NIC and 1.5K MTU:
No BIG TCP:
for i in {1..10}; do netperf -t TCP_RR -H 192.168.100.1 -- -r80000,80000 -O MIN_LATENCY,P90_LATENCY,P99_LATENCY,THROUGHPUT|tail -1; done
168 322 337 3776.49 143 236 277 4654.67 128 258 288 4772.83 171 229 278 4645.77 175 228 243 4678.93 149 239 279 4599.86 164 234 268 4606.94 155 276 289 4235.82 180 255 268 4418.95 168 241 249 4417.82
Enable BIG TCP:
ip link set dev ens1f0np0 gro_ipv4_max_size 128000 gso_ipv4_max_size 128000
for i in {1..10}; do netperf -t TCP_RR -H 192.168.100.1 -- -r80000,80000 -O MIN_LATENCY,P90_LATENCY,P99_LATENCY,THROUGHPUT|tail -1; done
161 241 252 4821.73 174 205 217 5098.28 167 208 220 5001.43 164 228 249 4883.98 150 233 249 4914.90 180 233 244 4819.66 154 208 219 5004.92 157 209 247 4999.78 160 218 246 4842.31 174 206 217 5080.99
Thanks for the feedback from Eric and David Ahern.
v1->v2:
- remove the fixes and the selftest for IPv6 BIG TCP, will do it in another patchset.
- add GSO_TCP for tp_status in packet sockets to tell the af_packet users that this is a TCP GSO packet in Patch 8.
- also check skb_is_gso() when checking if it's a GSO TCP packet in Patch 1.v2->v3:
- add gso/gro_ipv4_max_size per device and netlink attributes for them in Patch 9, so that we can selectively enable BIG TCP for IPv6, and not for IPv4, as Eric required.
- remove the selftest, as it requires userspace iproute2 change after making IPv4 BIG TCP independent from IPv6 BIG TCP on configuration.
Xin Long (10):
net: add a couple of helpers for iph tot_len
bridge: use skb_ip_totlen in br netfilter
openvswitch: use skb_ip_totlen in conntrack
net: sched: use skb_ip_totlen and iph_totlen
netfilter: use skb_ip_totlen and iph_totlen
cipso_ipv4: use iph_set_totlen in skbuff_setattr
ipvlan: use skb_ip_totlen in ipvlan_get_L3_hdr
packet: add TP_STATUS_GSO_TCP for tp_status
net: add gso_ipv4_max_size and gro_ipv4_max_size per device
net: add support for ipv4 big tcp
drivers/net/ipvlan/ipvlan_core.c | 2 +- include/linux/ip.h | 21 ++++++++++++++ include/linux/netdevice.h | 6 ++++ include/net/netfilter/nf_tables_ipv4.h | 4 +-- include/net/route.h | 3 -- include/uapi/linux/if_link.h | 3 ++ include/uapi/linux/if_packet.h | 1 + net/bridge/br_netfilter_hooks.c | 2 +- net/bridge/netfilter/nf_conntrack_bridge.c | 4 +-- net/core/dev.c | 4 +++ net/core/dev.h | 18 ++++++++++++ net/core/gro.c | 12 ++++---- net/core/rtnetlink.c | 33 ++++++++++++++++++++++ net/core/sock.c | 8 ++++-- net/ipv4/af_inet.c | 7 +++-- net/ipv4/cipso_ipv4.c | 2 +- net/ipv4/ip_input.c | 2 +- net/ipv4/ip_output.c | 2 +- net/netfilter/ipvs/ip_vs_xmit.c | 2 +- net/netfilter/nf_log_syslog.c | 2 +- net/netfilter/xt_length.c | 2 +- net/openvswitch/conntrack.c | 2 +- net/packet/af_packet.c | 4 +++ net/sched/act_ct.c | 2 +- net/sched/sch_cake.c | 2 +- 25 files changed, 122 insertions(+), 28 deletions(-)
Signature · 1 line
2.31.1
PATCH v3 1/10 net: add a couple of helpers for iph tot_len
This patch adds three APIs to replace the iph->tot_len setting and getting in all places where IPv4 BIG TCP packets may reach, they will be used in the following patches.
Note that iph_totlen() will be used when iph is not in linear data of the skb.
--- include/linux/ip.h | 21 +++++++++++++++++++++ include/net/route.h | 3 --- 2 files changed, 21 insertions(+), 3 deletions(-)
include/linux/ip.h +21 -0
@@ -35,4 +35,25 @@ static inline unsigned int ip_transport_len(const struct sk_buff *skb) {return ntohs (ip_hdr (skb)->tot_len) -skb_network_header_len (skb); } + +static inline unsigned int iph_totlen (const struct sk_buff *skb,const struct iphdr *iph) +{ +u32 len =ntohs (iph->tot_len); + +return (len || !skb_is_gso (skb) || !skb_is_gso_tcp (skb)) ? + len : skb->len -skb_network_offset (skb); +} + +static inline unsigned int skb_ip_totlen (const struct sk_buff *skb) +{ +return iph_totlen (skb,ip_hdr (skb)); +} + +/* IPv4 datagram length is stored into 16bit field (tot_len) */ +#define IP_MAX_MTU 0xFFFFU + +static inline void iph_set_totlen (struct iphdr *iph,unsigned int len) +{ + iph->tot_len = len <=IP_MAX_MTU ?htons (len) :0 ; +}#endif /* _LINUX_IP_H */
include/net/route.h +0 -3
@@ -35,9 +35,6 @@#include <linux/cache.h> #include <linux/security.h> -/* IPv4 datagram length is stored into 16bit field (tot_len) */ -#define IP_MAX_MTU 0xFFFFU -#define RTO_ONLINK 0x01#define RT_CONN_FLAGS (sk) (RT_TOS(inet_sk(sk)->tos) | sock_flag(sk, SOCK_LOCALROUTE))
Signature · 1 line
2.31.1
PATCH v3 2/10 bridge: use skb_ip_totlen in br netfilter
In reply to Xin LongThese 3 places in bridge netfilter are called on RX path after GRO and IPv4 TCP GSO packets may come through, so replace iph tot_len accessing with skb_ip_totlen() in there.
--- net/bridge/br_netfilter_hooks.c | 2 +- net/bridge/netfilter/nf_conntrack_bridge.c | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-)
net/bridge/br_netfilter_hooks.c +1 -1
@@ -214,7 +214,7 @@ static int br_validate_ipv4(struct net *net, struct sk_buff *skb)if (unlikely (ip_fast_csum ((u8 *)iph, iph->ihl))) goto csum_error; - len =ntohs (iph->tot_len); + len =skb_ip_totlen (skb);if (skb->len < len) {__IP_INC_STATS (net,IPSTATS_MIB_INTRUNCATEDPKTS ); goto drop;
net/bridge/netfilter/nf_conntrack_bridge.c +2 -2
@@ -212,7 +212,7 @@ static int nf_ct_br_ip_check(const struct sk_buff *skb) iph->version != 4)return -1 ; - len =ntohs (iph->tot_len); + len =skb_ip_totlen (skb);if (skb->len < nhoff + len || len < (iph->ihl *4 ))return -1 ;
@@ -256,7 +256,7 @@ static unsigned int nf_ct_bridge_pre(void *priv, struct sk_buff *skb,if (!pskb_may_pull (skb,sizeof (struct iphdr )))return NF_ACCEPT ; - len =ntohs (ip_hdr (skb)->tot_len); + len =skb_ip_totlen (skb);if (pskb_trim_rcsum (skb, len))return NF_ACCEPT ;
Signature · 1 line
2.31.1
PATCH v3 3/10 openvswitch: use skb_ip_totlen in conntrack
In reply to Xin LongIPv4 GSO packets may get processed in ovs_skb_network_trim(), and we need to use skb_ip_totlen() to get iph totlen.
--- net/openvswitch/conntrack.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
net/openvswitch/conntrack.c +1 -1
@@ -1103,7 +1103,7 @@ static int ovs_skb_network_trim(struct sk_buff *skb)switch (skb->protocol) {case htons (ETH_P_IP ): - len =ntohs (ip_hdr (skb)->tot_len); + len =skb_ip_totlen (skb);break ;case htons (ETH_P_IPV6 ): len =sizeof (struct ipv6hdr )
Signature · 1 line
2.31.1
PATCH v3 4/10 net: sched: use skb_ip_totlen and iph_totlen
In reply to Xin LongThere are 1 action and 1 qdisc that may process IPv4 TCP GSO packets and access iph->tot_len, replace them with skb_ip_totlen() and iph_totlen() accordingly.
Note that we don't need to replace the one in tcf_csum_ipv4(), as it will return for TCP GSO packets in tcf_csum_ipv4_tcp().
--- net/sched/act_ct.c | 2 +- net/sched/sch_cake.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-)
net/sched/act_ct.c +1 -1
@@ -707,7 +707,7 @@ static int tcf_ct_skb_network_trim(struct sk_buff *skb, int family)switch (family) {case NFPROTO_IPV4 : - len =ntohs (ip_hdr (skb)->tot_len); + len =skb_ip_totlen (skb);break ;case NFPROTO_IPV6 : len =sizeof (struct ipv6hdr )
net/sched/sch_cake.c +1 -1
@@ -1209,7 +1209,7 @@ static struct sk_buff *cake_ack_filter(struct cake_sched_data *q, iph_check->daddr != iph->daddr)continue ; - seglen =ntohs (iph_check->tot_len) - + seglen =iph_totlen (skb, iph_check) - (4 * iph_check->ihl); }else if (iph_check->version ==6 ) { ipv6h = (struct ipv6hdr *)iph;
Signature · 1 line
2.31.1
PATCH v3 5/10 netfilter: use skb_ip_totlen and iph_totlen
In reply to Xin LongThere are also quite some places in netfilter that may process IPv4 TCP GSO packets, we need to replace them too.
In length_mt(), we have to use u_int32_t/int to accept skb_ip_totlen() return value, otherwise it may overflow and mismatch. This change will also help us add selftest for IPv4 BIG TCP in the following patch.
Note that we don't need to replace the one in tcpmss_tg4(), as it will return if there is data after tcphdr in tcpmss_mangle_packet(). The same in mangle_contents() in nf_nat_helper.c, it returns false when skb->len + extra > 65535 in enlarge_skb().
--- include/net/netfilter/nf_tables_ipv4.h | 4 ++-- net/netfilter/ipvs/ip_vs_xmit.c | 2 +- net/netfilter/nf_log_syslog.c | 2 +- net/netfilter/xt_length.c | 2 +- 4 files changed, 5 insertions(+), 5 deletions(-)
include/net/netfilter/nf_tables_ipv4.h +2 -2
@@ -29,7 +29,7 @@ static inline int __nft_set_pktinfo_ipv4_validate(struct nft_pktinfo *pkt)if (iph->ihl <5 || iph->version !=4 )return -1 ; - len =ntohs (iph->tot_len); + len =iph_totlen (pkt->skb, iph); thoff = iph->ihl *4 ;if (pkt->skb->len < len)return -1 ;
@@ -64,7 +64,7 @@ static inline int nft_set_pktinfo_ipv4_ingress(struct nft_pktinfo *pkt)if (iph->ihl <5 || iph->version !=4 ) goto inhdr_error; - len =ntohs (iph->tot_len); + len =iph_totlen (pkt->skb, iph); thoff = iph->ihl *4 ;if (pkt->skb->len < len) {__IP_INC_STATS (nft_net (pkt),IPSTATS_MIB_INTRUNCATEDPKTS );
net/netfilter/ipvs/ip_vs_xmit.c +1 -1
@@ -994,7 +994,7 @@ ip_vs_prepare_tunneled_skb(struct sk_buff *skb, int skb_af, old_dsfield =ipv4_get_dsfield (old_iph); *ttl = old_iph->ttl;if (payload_len) - *payload_len =ntohs (old_iph->tot_len); + *payload_len =skb_ip_totlen (skb); }/* Implement full-functionality option for ECN encapsulation */
net/netfilter/nf_log_syslog.c +1 -1
@@ -322,7 +322,7 @@ dump_ipv4_packet(struct net *net, struct nf_log_buf *m,/* Max length: 46 "LEN=65535 TOS=0xFF PREC=0xFF TTL=255 ID=65535 " */ nf_log_buf_add (m,"LEN=%u TOS=0x%02X PREC=0x%02X TTL=%u ID=%u " , -ntohs (ih->tot_len), ih->tos &IPTOS_TOS_MASK , +iph_totlen (skb, ih), ih->tos &IPTOS_TOS_MASK , ih->tos &IPTOS_PREC_MASK , ih->ttl,ntohs (ih->id));/* Max length: 6 "CE DF MF " */
net/netfilter/xt_length.c +1 -1
@@ -21,7 +21,7 @@ static bool length_mt(const struct sk_buff *skb, struct xt_action_param *par) { const struct xt_length_info *info = par->matchinfo; -u_int16_t pktlen =ntohs (ip_hdr (skb)->tot_len); +u32 pktlen =skb_ip_totlen (skb);return (pktlen >= info->min && pktlen <= info->max) ^ info->invert; }
Signature · 1 line
2.31.1
PATCH v3 6/10 cipso_ipv4: use iph_set_totlen in skbuff_setattr
In reply to Xin LongIt may process IPv4 TCP GSO packets in cipso_v4_skbuff_setattr(), so the iph->tot_len update should use iph_set_totlen().
Note that for these non GSO packets, the new iph tot_len with extra iph option len added may become greater than 65535, the old process will cast it and set iph->tot_len to it, which is a bug. In theory, iph options shouldn't be added for these big packets in here, a fix may be needed here in the future. For now this patch is only to set iph->tot_len to 0 when it happens.
--- net/ipv4/cipso_ipv4.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
net/ipv4/cipso_ipv4.c +1 -1
@@ -2222,7 +2222,7 @@ int cipso_v4_skbuff_setattr(struct sk_buff *skb,memset ((char *)(iph +1 ) + buf_len,0 , opt_len - buf_len);if (len_delta !=0 ) { iph->ihl =5 + (opt_len >>2 ); - iph->tot_len =htons (skb->len); +iph_set_totlen (iph, skb->len); }ip_send_check (iph);
Signature · 1 line
2.31.1
PATCH v3 7/10 ipvlan: use skb_ip_totlen in ipvlan_get_L3_hdr
In reply to Xin Longipvlan devices calls netif_inherit_tso_max() to get the tso_max_size/segs from the lower device, so when lower device supports BIG TCP, the ipvlan devices support it too. We also should consider its iph tot_len accessing.
--- drivers/net/ipvlan/ipvlan_core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/net/ipvlan/ipvlan_core.c +1 -1
@@ -157,7 +157,7 @@ void *ipvlan_get_L3_hdr(struct ipvl_port *port, struct sk_buff *skb, int *type)return NULL ; ip4h =ip_hdr (skb); - pktlen =ntohs (ip4h->tot_len); + pktlen =skb_ip_totlen (skb);if (ip4h->ihl <5 || ip4h->version !=4 )return NULL ;if (skb->len < pktlen || pktlen < (ip4h->ihl *4 ))
Signature · 1 line
2.31.1
PATCH v3 8/10 packet: add TP_STATUS_GSO_TCP for tp_status
In reply to Xin LongIntroduce TP_STATUS_GSO_TCP tp_status flag to tell the af_packet user that this is a TCP GSO packet. When parsing IPv4 BIG TCP packets in tcpdump/libpcap, it can use tp_len as the IPv4 packet len when this flag is set, as iph tot_len is set to 0 for IPv4 BIG TCP packets.
--- include/uapi/linux/if_packet.h | 1 + net/packet/af_packet.c | 4 ++++ 2 files changed, 5 insertions(+)
include/uapi/linux/if_packet.h +1 -0
@@ -115,6 +115,7 @@ struct tpacket_auxdata {#define TP_STATUS_BLK_TMO (1 << 5)#define TP_STATUS_VLAN_TPID_VALID (1 << 6)/* auxdata has valid tp_vlan_tpid */ #define TP_STATUS_CSUM_VALID (1 << 7) +#define TP_STATUS_GSO_TCP (1 << 8)/* Tx ring - header status */ #define TP_STATUS_AVAILABLE 0
net/packet/af_packet.c +4 -0
@@ -2296,6 +2296,8 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,else if (skb->pkt_type !=PACKET_OUTGOING &&skb_csum_unnecessary (skb)) status |=TP_STATUS_CSUM_VALID ; +if (skb_is_gso (skb) &&skb_is_gso_tcp (skb)) + status |=TP_STATUS_GSO_TCP ;if (snaplen > res) snaplen = res;
@@ -3522,6 +3524,8 @@ static int packet_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,else if (skb->pkt_type !=PACKET_OUTGOING &&skb_csum_unnecessary (skb)) aux.tp_status |=TP_STATUS_CSUM_VALID ; +if (skb_is_gso (skb) &&skb_is_gso_tcp (skb)) + aux.tp_status |=TP_STATUS_GSO_TCP ; aux.tp_len = origlen; aux.tp_snaplen = skb->len;
Signature · 1 line
2.31.1
PATCH v3 9/10 net: add gso_ipv4_max_size and gro_ipv4_max_size per device
In reply to Xin LongThis patch introduces gso_ipv4_max_size and gro_ipv4_max_size per device and adds netlink attributes for them, so that IPV4 BIG TCP can be guarded by a separate tunable in the next patch.
To not break the old application using "gso/gro_max_size" for IPv4 GSO packets, this patch updates "gso/gro_ipv4_max_size" in netif_set_gso/gro_max_size() if the new size isn't greater than GSO_LEGACY_MAX_SIZE, so that nothing will change even if userspace doesn't realize the new netlink attributes.
--- include/linux/netdevice.h | 6 ++++++ include/uapi/linux/if_link.h | 3 +++ net/core/dev.c | 4 ++++ net/core/dev.h | 18 ++++++++++++++++++ net/core/rtnetlink.c | 33 +++++++++++++++++++++++++++++++++ 5 files changed, 64 insertions(+)
include/linux/netdevice.h +6 -0
@@ -2010,6 +2010,9 @@ enum netdev_ml_priv_type {* SET_NETDEV_DEVLINK_PORT macro. This pointer is static * during the time netdevice is registered. * +* @gso_ipv4_max_size: Maximum size of IPv4 GSO packets. +* @gro_ipv4_max_size: Maximum size of IPv4 GRO packets. +* * FIXME: cleanup struct net_device such that network protocol info * moves out. */
@@ -2362,6 +2365,9 @@ struct net_device {struct rtnl_hw_stats64 *offload_xstats_l3;struct devlink_port *devlink_port; + +unsigned int gso_ipv4_max_size; +unsigned int gro_ipv4_max_size; };#define to_net_dev (d) container_of(d, struct net_device, dev)
include/uapi/linux/if_link.h +3 -0
@@ -374,6 +374,9 @@ enum {IFLA_DEVLINK_PORT , +IFLA_GSO_IPV4_MAX_SIZE , +IFLA_GRO_IPV4_MAX_SIZE , + __IFLA_MAX };
net/core/dev.c +4 -0
@@ -3001,6 +3001,8 @@ void netif_set_tso_max_size(struct net_device *dev, unsigned int size) dev->tso_max_size =min (GSO_MAX_SIZE , size);if (size <READ_ONCE (dev->gso_max_size))netif_set_gso_max_size (dev, size); +if (size <READ_ONCE (dev->gso_ipv4_max_size)) +netif_set_gso_ipv4_max_size (dev, size); }EXPORT_SYMBOL (netif_set_tso_max_size);
@@ -10610,6 +10612,8 @@ 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_LEGACY_MAX_SIZE ; + dev->gso_ipv4_max_size =GSO_LEGACY_MAX_SIZE ; + dev->gro_ipv4_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 ;
net/core/dev.h +18 -0
@@ -100,6 +100,8 @@ 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); +if (size <=GSO_LEGACY_MAX_SIZE ) +WRITE_ONCE (dev->gso_ipv4_max_size, size); } static inline void netif_set_gso_max_segs(struct net_device *dev,
@@ -114,6 +116,22 @@ static inline void netif_set_gro_max_size(struct net_device *dev, {/* This pairs with the READ_ONCE() in skb_gro_receive() */ WRITE_ONCE (dev->gro_max_size, size); +if (size <=GRO_LEGACY_MAX_SIZE ) +WRITE_ONCE (dev->gro_ipv4_max_size, size); +} + +static inline void netif_set_gso_ipv4_max_size (struct net_device *dev, +unsigned int size) +{ +/* dev->gso_ipv4_max_size is read locklessly from sk_setup_caps() */ +WRITE_ONCE (dev->gso_ipv4_max_size, size); +} + +static inline void netif_set_gro_ipv4_max_size (struct net_device *dev, +unsigned int size) +{ +/* This pairs with the READ_ONCE() in skb_gro_receive() */ +WRITE_ONCE (dev->gro_ipv4_max_size, size); }#endif
net/core/rtnetlink.c +33 -0
@@ -1074,6 +1074,8 @@ 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_GSO_IPV4_MAX_SIZE */ + +nla_total_size (4 )/* IFLA_GRO_IPV4_MAX_SIZE */ +nla_total_size (4 )/* IFLA_TSO_MAX_SIZE */ +nla_total_size (4 )/* IFLA_TSO_MAX_SEGS */ +nla_total_size (1 )/* IFLA_OPERSTATE */
@@ -1807,6 +1809,8 @@ 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_GSO_IPV4_MAX_SIZE , dev->gso_ipv4_max_size) || +nla_put_u32 (skb,IFLA_GRO_IPV4_MAX_SIZE , dev->gro_ipv4_max_size) ||nla_put_u32 (skb,IFLA_TSO_MAX_SIZE , dev->tso_max_size) ||nla_put_u32 (skb,IFLA_TSO_MAX_SEGS , dev->tso_max_segs) || #ifdef CONFIG_RPS
@@ -1968,6 +1972,8 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = { [IFLA_TSO_MAX_SIZE] = { .type = NLA_REJECT }, [IFLA_TSO_MAX_SEGS] = { .type = NLA_REJECT }, [IFLA_ALLMULTI] = { .type = NLA_REJECT }, + [IFLA_GSO_IPV4_MAX_SIZE] = { .type = NLA_U32 }, + [IFLA_GRO_IPV4_MAX_SIZE] = { .type = NLA_U32 }, };static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX +1 ] = {
@@ -2883,6 +2889,29 @@ static int do_setlink(const struct sk_buff *skb, } } +if (tb[IFLA_GSO_IPV4_MAX_SIZE ]) { +u32 max_size =nla_get_u32 (tb[IFLA_GSO_IPV4_MAX_SIZE ]); + +if (max_size > dev->tso_max_size) { + err = -EINVAL ; + goto errout; + } + +if (dev->gso_ipv4_max_size ^ max_size) { +netif_set_gso_ipv4_max_size (dev, max_size); + status |=DO_SETLINK_MODIFIED ; + } + } + +if (tb[IFLA_GRO_IPV4_MAX_SIZE ]) { +u32 gro_max_size =nla_get_u32 (tb[IFLA_GRO_IPV4_MAX_SIZE ]); + +if (dev->gro_ipv4_max_size ^ gro_max_size) { +netif_set_gro_ipv4_max_size (dev, gro_max_size); + status |=DO_SETLINK_MODIFIED ; + } + } +if (tb[IFLA_OPERSTATE ])set_operstate (dev,nla_get_u8 (tb[IFLA_OPERSTATE ]));
@@ -3325,6 +3354,10 @@ 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_IPV4_MAX_SIZE ]) +netif_set_gso_ipv4_max_size (dev,nla_get_u32 (tb[IFLA_GSO_IPV4_MAX_SIZE ])); +if (tb[IFLA_GRO_IPV4_MAX_SIZE ]) +netif_set_gro_ipv4_max_size (dev,nla_get_u32 (tb[IFLA_GRO_IPV4_MAX_SIZE ]));return dev; }
Signature · 1 line
2.31.1
Re: [PATCHv3 net-next 09/10] net: add gso_ipv4_max_size and gro_ipv4_max_size per device
Quoted 35 lines · Xin Long
This patch introduces
gso_ipv4_max_sizeandgro_ipv4_max_sizeper device and adds netlink attributes for them, so that IPV4 BIG TCP can be guarded by a separate tunable in the next patch.To not break the old application using "gso/gro_max_size" for IPv4 GSO packets, this patch updates "gso/gro_ipv4_max_size" in netif_set_gso/gro_max_size() if the new size isn't greater than
GSO_LEGACY_MAX_SIZE, so that nothing will change even if userspace doesn't realize the new netlink attributes.Signed-off-by Xin Long <[email protected]>--- include/linux/netdevice.h | 6 ++++++ include/uapi/linux/if_link.h | 3 +++ net/core/dev.c | 4 ++++ net/core/dev.h | 18 ++++++++++++++++++ net/core/rtnetlink.c | 33 +++++++++++++++++++++++++++++++++ 5 files changed, 64 insertions(+)include/linux/netdevice.h +3
-0@@ -2010,6 +2010,9 @@ enum netdev_ml_priv_type {* SET_NETDEV_DEVLINK_PORT macro. This pointer is static * during the time netdevice is registered. * +* @gso_ipv4_max_size: Maximum size of IPv4 GSO packets. +* @gro_ipv4_max_size: Maximum size of IPv4 GRO packets. +* * FIXME: cleanup struct net_device such that network protocol info * moves out. */
include/linux/netdevice.h struct net_device { · line 2370
Quoted 6 lines
include/linux/netdevice.h +3
-0@@ -2362,6 +2365,9 @@ struct net_device {struct rtnl_hw_stats64 *offload_xstats_l3;struct devlink_port *devlink_port; + +unsigned int gso_ipv4_max_size; +unsigned int gro_ipv4_max_size;
This seems a pretty bad choice in terms of data locality.
Field order in "struct net_device" is very important for performance.
Please put gro_ipv4_max_size close to other related fields, so that we do not need an extra cache line miss.
Same for gso_ipv4_max_size.
Use "pahole --hex" to study how "struct net_device" is currently partitioned. It seems we have a hole after tso_max_segs, so this would be for gso_ipv4_max_size
Quoted 4 lines
include/linux/netdevice.h +0
-0};#define to_net_dev (d) container_of(d, struct net_device, dev)
PATCH v3 10/10 net: add support for ipv4 big tcp
In reply to Xin LongSimilar to Eric's IPv6 BIG TCP, this patch is to enable IPv4 BIG TCP.
Firstly, allow sk->sk_gso_max_size to be set to a value greater than GSO_LEGACY_MAX_SIZE by not trimming gso_max_size in sk_trim_gso_size() for IPv4 TCP sockets.
Then on TX path, set IP header tot_len to 0 when skb->len > IP_MAX_MTU in __ip_local_out() to allow to send BIG TCP packets, and this implies that skb->len is the length of a IPv4 packet; On RX path, use skb->len as the length of the IPv4 packet when the IP header tot_len is 0 and skb->len > IP_MAX_MTU in ip_rcv_core(). As the API iph_set_totlen() and skb_ip_totlen() are used in __ip_local_out() and ip_rcv_core(), we only need to update these APIs.
Also in GRO receive, add the check for ETH_P_IP/IPPROTO_TCP, and allows the merged packet size >= GRO_LEGACY_MAX_SIZE in skb_gro_receive(). In GRO complete, set IP header tot_len to 0 when the merged packet size greater than IP_MAX_MTU in iph_set_totlen() so that it can be processed on RX path.
Note that by checking skb_is_gso_tcp() in API iph_totlen(), it makes this implementation safe to use iph->len == 0 indicates IPv4 BIG TCP packets.
--- net/core/gro.c | 12 +++++++----- net/core/sock.c | 8 ++++++-- net/ipv4/af_inet.c | 7 ++++--- net/ipv4/ip_input.c | 2 +- net/ipv4/ip_output.c | 2 +- 5 files changed, 19 insertions(+), 12 deletions(-)
net/core/gro.c +7 -5
@@ -162,16 +162,18 @@ int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb)struct sk_buff *lp;int segs; -/* pairs with WRITE_ONCE() in netif_set_gro_max_size() */ - gro_max_size =READ_ONCE (p->dev->gro_max_size); +/* pairs with WRITE_ONCE() in netif_set_gro(_ipv4)_max_size() */ + gro_max_size = p->protocol ==htons (ETH_P_IPV6 ) ? +READ_ONCE (p->dev->gro_max_size) : +READ_ONCE (p->dev->gro_ipv4_max_size);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 || +if (NAPI_GRO_CB (skb)->proto !=IPPROTO_TCP || + (p->protocol ==htons (ETH_P_IPV6 ) && +skb_headroom (p) <sizeof (struct hop_jumbo_hdr )) || p->encapsulation)return -E2BIG ; }
net/core/sock.c +6 -2
@@ -2383,6 +2383,8 @@ static void sk_trim_gso_size(struct sock *sk) !ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr)) return;#endif +if (sk->sk_family ==AF_INET &&sk_is_tcp (sk)) +return ; sk->sk_gso_max_size =GSO_LEGACY_MAX_SIZE ; }
@@ -2403,8 +2405,10 @@ void sk_setup_caps(struct sock *sk, struct dst_entry *dst) sk->sk_route_caps &= ~NETIF_F_GSO_MASK ; }else { 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); +/* pairs with the WRITE_ONCE() in netif_set_gso(_ipv4)_max_size() */ + sk->sk_gso_max_size = sk->sk_family ==AF_INET6 ? +READ_ONCE (dst->dev->gso_max_size) : +READ_ONCE (dst->dev->gso_ipv4_max_size);sk_trim_gso_size (sk); sk->sk_gso_max_size -= (MAX_TCP_HEADER +1 );/* pairs with the WRITE_ONCE() in netif_set_gso_max_segs() */
net/ipv4/af_inet.c +4 -3
@@ -1485,6 +1485,7 @@ struct sk_buff *inet_gro_receive(struct list_head *head, struct sk_buff *skb)if (unlikely (ip_fast_csum ((u8 *)iph,5 ))) goto out; +NAPI_GRO_CB (skb)->proto = proto; id =ntohl (*(__be32 *)&iph->id); flush = (u16)((ntohl (*(__be32 *)iph) ^skb_gro_len (skb)) | (id & ~IP_DF )); id >>=16 ;
@@ -1618,9 +1619,9 @@ int inet_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)int inet_gro_complete (struct sk_buff *skb,int nhoff) { -__be16 newlen =htons (skb->len - nhoff);struct iphdr *iph = (struct iphdr *)(skb->data + nhoff);const struct net_offload *ops; +__be16 totlen = iph->tot_len;int proto = iph->protocol;int err = -ENOSYS ;
@@ -1629,8 +1630,8 @@ int inet_gro_complete(struct sk_buff *skb, int nhoff)skb_set_inner_network_header (skb, nhoff); } -csum_replace2 (&iph->check, iph->tot_len, newlen); - iph->tot_len = newlen; +iph_set_totlen (iph, skb->len - nhoff); +csum_replace2 (&iph->check, totlen, iph->tot_len); ops =rcu_dereference (inet_offloads[proto]);if (WARN_ON (!ops || !ops->callbacks.gro_complete))
net/ipv4/ip_input.c +1 -1
@@ -511,7 +511,7 @@ static struct sk_buff *ip_rcv_core(struct sk_buff *skb, struct net *net)if (unlikely (ip_fast_csum ((u8 *)iph, iph->ihl))) goto csum_error; - len =ntohs (iph->tot_len); + len =skb_ip_totlen (skb);if (skb->len < len) { drop_reason =SKB_DROP_REASON_PKT_TOO_SMALL ;__IP_INC_STATS (net,IPSTATS_MIB_INTRUNCATEDPKTS );
net/ipv4/ip_output.c +1 -1
@@ -100,7 +100,7 @@ int __ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb) {struct iphdr *iph =ip_hdr (skb); - iph->tot_len =htons (skb->len); +iph_set_totlen (iph, skb->len);ip_send_check (iph);/* if egress device is enslaved to an L3 master device pass the
Signature · 1 line
2.31.1
Re: [PATCHv3 net-next 10/10] net: add support for ipv4 big tcp
Quoted 67 lines · Xin Long
Similar to Eric's IPv6 BIG TCP, this patch is to enable IPv4 BIG TCP.
Firstly, allow
sk->sk_gso_max_sizeto be set to a value greater thanGSO_LEGACY_MAX_SIZEby not trimminggso_max_sizeinsk_trim_gso_size()for IPv4 TCP sockets.Then on TX path, set IP header
tot_lento 0 whenskb->len>IP_MAX_MTUin__ip_local_out()to allow to send BIG TCP packets, and this implies thatskb->lenis the length of a IPv4 packet; On RX path, useskb->lenas the length of the IPv4 packet when the IP headertot_lenis 0 andskb->len>IP_MAX_MTUinip_rcv_core(). As the APIiph_set_totlen()andskb_ip_totlen()are used in__ip_local_out()andip_rcv_core(), we only need to update these APIs.Also in GRO receive, add the check for ETH_P_IP/IPPROTO_TCP, and allows the merged packet size >=
GRO_LEGACY_MAX_SIZEinskb_gro_receive(). In GRO complete, set IP headertot_lento 0 when the merged packet size greater thanIP_MAX_MTUiniph_set_totlen()so that it can be processed on RX path.Note that by checking
skb_is_gso_tcp()in APIiph_totlen(), it makes this implementation safe to useiph->len== 0 indicates IPv4 BIG TCP packets.Signed-off-by Xin Long <[email protected]>--- net/core/gro.c | 12 +++++++----- net/core/sock.c | 8 ++++++-- net/ipv4/af_inet.c | 7 ++++--- net/ipv4/ip_input.c | 2 +- net/ipv4/ip_output.c | 2 +- 5 files changed, 19 insertions(+), 12 deletions(-)net/core/gro.c +7
-5@@ -162,16 +162,18 @@ int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb)struct sk_buff *lp;int segs; -/* pairs with WRITE_ONCE() in netif_set_gro_max_size() */ - gro_max_size =READ_ONCE (p->dev->gro_max_size); +/* pairs with WRITE_ONCE() in netif_set_gro(_ipv4)_max_size() */ + gro_max_size = p->protocol ==htons (ETH_P_IPV6 ) ? +READ_ONCE (p->dev->gro_max_size) : +READ_ONCE (p->dev->gro_ipv4_max_size);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 || +if (NAPI_GRO_CB (skb)->proto !=IPPROTO_TCP || + (p->protocol ==htons (ETH_P_IPV6 ) && +skb_headroom (p) <sizeof (struct hop_jumbo_hdr )) || p->encapsulation)return -E2BIG ; }net/core/sock.c +0
-0
net/core/sock.c static void sk_trim_gso_size(struct sock *sk) · line 2387
Quoted 5 lines
net/core/sock.c +2
-0@@ -2383,6 +2383,8 @@ static void sk_trim_gso_size(struct sock *sk) !ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr))return ;#endif +if (sk->sk_family ==AF_INET &&sk_is_tcp (sk)) +return ;
Or simply
net/core/sock.c +0 -0
100644
net/core/sock.c +2 -7
@@ -2375,14 +2375,9 @@ EXPORT_SYMBOL_GPL(sk_free_unlock_clone);static void sk_trim_gso_size (struct sock *sk) { -if (sk->sk_gso_max_size <=GSO_LEGACY_MAX_SIZE ) +if (sk->sk_gso_max_size <=GSO_LEGACY_MAX_SIZE || +sk_is_tcp (sk))return ; -#if IS_ENABLED (CONFIG_IPV6 ) -if (sk->sk_family ==AF_INET6 && -sk_is_tcp (sk) && - !ipv6_addr_v4mapped (&sk->sk_v6_rcv_saddr)) -return ; -#endif sk->sk_gso_max_size =GSO_LEGACY_MAX_SIZE ; }
Quoted 55 lines
net/core/sock.c +4
-2sk->sk_gso_max_size =GSO_LEGACY_MAX_SIZE ; }@@ -2403,8 +2405,10 @@ void sk_setup_caps(struct sock *sk, struct dst_entry *dst) sk->sk_route_caps &= ~NETIF_F_GSO_MASK ; }else { 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); +/* pairs with the WRITE_ONCE() in netif_set_gso(_ipv4)_max_size() */ + sk->sk_gso_max_size = sk->sk_family ==AF_INET6 ? +READ_ONCE (dst->dev->gso_max_size) : +READ_ONCE (dst->dev->gso_ipv4_max_size);sk_trim_gso_size (sk); sk->sk_gso_max_size -= (MAX_TCP_HEADER +1 );/* pairs with the WRITE_ONCE() in netif_set_gso_max_segs() */ net/ipv4/af_inet.c +4
-3@@ -1485,6 +1485,7 @@ struct sk_buff *inet_gro_receive(struct list_head *head, struct sk_buff *skb)if (unlikely (ip_fast_csum ((u8 *)iph,5 ))) goto out; +NAPI_GRO_CB (skb)->proto = proto; id =ntohl (*(__be32 *)&iph->id); flush = (u16)((ntohl (*(__be32 *)iph) ^skb_gro_len (skb)) | (id & ~IP_DF )); id >>=16 ;@@ -1618,9 +1619,9 @@ int inet_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)int inet_gro_complete (struct sk_buff *skb,int nhoff) { -__be16 newlen =htons (skb->len - nhoff);struct iphdr *iph = (struct iphdr *)(skb->data + nhoff);const struct net_offload *ops; +__be16 totlen = iph->tot_len;int proto = iph->protocol;int err = -ENOSYS ;@@ -1629,8 +1630,8 @@ int inet_gro_complete(struct sk_buff *skb, int nhoff)skb_set_inner_network_header (skb, nhoff); } -csum_replace2 (&iph->check, iph->tot_len, newlen); - iph->tot_len = newlen; +iph_set_totlen (iph, skb->len - nhoff); +csum_replace2 (&iph->check, totlen, iph->tot_len); ops =rcu_dereference (inet_offloads[proto]);if (WARN_ON (!ops || !ops->callbacks.gro_complete))net/ipv4/ip_input.c +0
-0
net/ipv4/ip_input.c static struct sk_buff *ip_rcv_core(struct sk_buff *skb, struct net *net) · line 514
Quoted 5 lines
net/ipv4/ip_input.c +1
-1@@ -511,7 +511,7 @@ static struct sk_buff *ip_rcv_core(struct sk_buff *skb, struct net *net)if (unlikely (ip_fast_csum ((u8 *)iph, iph->ihl))) goto csum_error; - len =ntohs (iph->tot_len); + len =skb_ip_totlen (skb);
len = iph_totlen(skb, iph);
Quoted 19 lines
net/ipv4/ip_input.c +0
-0if (skb->len < len) { drop_reason =SKB_DROP_REASON_PKT_TOO_SMALL ;__IP_INC_STATS (net,IPSTATS_MIB_INTRUNCATEDPKTS );net/ipv4/ip_output.c +1
-2@@ -100,7 +100,7 @@ int __ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb) {struct iphdr *iph =ip_hdr (skb); - iph->tot_len =htons (skb->len); +iph_set_totlen (iph, skb->len);ip_send_check (iph);/* if egress device is enslaved to an L3 master device pass the -- 2.31.1
Re: [PATCHv3 net-next 10/10] net: add support for ipv4 big tcp
Quoted 88 lines · Eric Dumazet
Quoted 67 lines · Xin Long
Similar to Eric's IPv6 BIG TCP, this patch is to enable IPv4 BIG TCP.
Firstly, allow
sk->sk_gso_max_sizeto be set to a value greater thanGSO_LEGACY_MAX_SIZEby not trimminggso_max_sizeinsk_trim_gso_size()for IPv4 TCP sockets.Then on TX path, set IP header
tot_lento 0 whenskb->len>IP_MAX_MTUin__ip_local_out()to allow to send BIG TCP packets, and this implies thatskb->lenis the length of a IPv4 packet; On RX path, useskb->lenas the length of the IPv4 packet when the IP headertot_lenis 0 andskb->len>IP_MAX_MTUinip_rcv_core(). As the APIiph_set_totlen()andskb_ip_totlen()are used in__ip_local_out()andip_rcv_core(), we only need to update these APIs.Also in GRO receive, add the check for ETH_P_IP/IPPROTO_TCP, and allows the merged packet size >=
GRO_LEGACY_MAX_SIZEinskb_gro_receive(). In GRO complete, set IP headertot_lento 0 when the merged packet size greater thanIP_MAX_MTUiniph_set_totlen()so that it can be processed on RX path.Note that by checking
skb_is_gso_tcp()in APIiph_totlen(), it makes this implementation safe to useiph->len== 0 indicates IPv4 BIG TCP packets.Signed-off-by Xin Long <[email protected]>--- net/core/gro.c | 12 +++++++----- net/core/sock.c | 8 ++++++-- net/ipv4/af_inet.c | 7 ++++--- net/ipv4/ip_input.c | 2 +- net/ipv4/ip_output.c | 2 +- 5 files changed, 19 insertions(+), 12 deletions(-)net/core/gro.c +7
-5@@ -162,16 +162,18 @@ int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb)struct sk_buff *lp;int segs; -/* pairs with WRITE_ONCE() in netif_set_gro_max_size() */ - gro_max_size =READ_ONCE (p->dev->gro_max_size); +/* pairs with WRITE_ONCE() in netif_set_gro(_ipv4)_max_size() */ + gro_max_size = p->protocol ==htons (ETH_P_IPV6 ) ? +READ_ONCE (p->dev->gro_max_size) : +READ_ONCE (p->dev->gro_ipv4_max_size);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 || +if (NAPI_GRO_CB (skb)->proto !=IPPROTO_TCP || + (p->protocol ==htons (ETH_P_IPV6 ) && +skb_headroom (p) <sizeof (struct hop_jumbo_hdr )) || p->encapsulation)return -E2BIG ; }net/core/sock.c +0
-0net/core/sock.c static void sk_trim_gso_size(struct sock *sk) · line 2387
Quoted 5 lines
net/core/sock.c +2
-0@@ -2383,6 +2383,8 @@ static void sk_trim_gso_size(struct sock *sk) !ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr))return ;#endif +if (sk->sk_family ==AF_INET &&sk_is_tcp (sk)) +return ;Or simply
net/core/sock.c +0
-0100644
net/core/sock.c +1
-1@@ -2375,14 +2375,9 @@ EXPORT_SYMBOL_GPL(sk_free_unlock_clone);static void sk_trim_gso_size (struct sock *sk) { -if (sk->sk_gso_max_size <=GSO_LEGACY_MAX_SIZE ) + if (sk->sk_gso_max_size <= GSO_LEGACY_MAX_SIZE ||
net/core/sock.c EXPORT_SYMBOL_GPL(sk_free_unlock_clone); · line 2382
Quoted 10 lines
net/core/sock.c +1
-6+ sk_is_tcp(sk))return ; -#if IS_ENABLED (CONFIG_IPV6 ) -if (sk->sk_family ==AF_INET6 && -sk_is_tcp (sk) && - !ipv6_addr_v4mapped (&sk->sk_v6_rcv_saddr)) -return ; -#endif sk->sk_gso_max_size =GSO_LEGACY_MAX_SIZE ; }
There's a difference, AF_INET6 TCP socket may send ipv4 packets with ipv6_addr_v4mapped, if we don't check ipv6_addr_v4mapped(), IPV4 GSO packets might go with the "gso_max_size" for IPV6.
I think we could use the change you wrote above, but we also need to use dst->ops->family instead of sk->sk_family in sk_setup_caps():
+ sk->sk_gso_max_size = dst->ops->family == AF_INET6 ?
+ READ_ONCE(dst->dev->gso_max_size) :
+READ_ONCE(dst->dev->gso_ipv4_max_size);
Quoted 61 lines
net/core/sock.c +0
-0> sk->sk_gso_max_size = GSO_LEGACY_MAX_SIZE;Quoted 57 lines
net/core/sock.c +4
-2}@@ -2403,8 +2405,10 @@ void sk_setup_caps(struct sock *sk, struct dst_entry *dst) sk->sk_route_caps &= ~NETIF_F_GSO_MASK ; }else { 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); +/* pairs with the WRITE_ONCE() in netif_set_gso(_ipv4)_max_size() */ + sk->sk_gso_max_size = sk->sk_family ==AF_INET6 ? +READ_ONCE (dst->dev->gso_max_size) : +READ_ONCE (dst->dev->gso_ipv4_max_size);sk_trim_gso_size (sk); sk->sk_gso_max_size -= (MAX_TCP_HEADER +1 );/* pairs with the WRITE_ONCE() in netif_set_gso_max_segs() */ net/ipv4/af_inet.c +4
-3@@ -1485,6 +1485,7 @@ struct sk_buff *inet_gro_receive(struct list_head *head, struct sk_buff *skb)if (unlikely (ip_fast_csum ((u8 *)iph,5 ))) goto out; +NAPI_GRO_CB (skb)->proto = proto; id =ntohl (*(__be32 *)&iph->id); flush = (u16)((ntohl (*(__be32 *)iph) ^skb_gro_len (skb)) | (id & ~IP_DF )); id >>=16 ;@@ -1618,9 +1619,9 @@ int inet_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)int inet_gro_complete (struct sk_buff *skb,int nhoff) { -__be16 newlen =htons (skb->len - nhoff);struct iphdr *iph = (struct iphdr *)(skb->data + nhoff);const struct net_offload *ops; +__be16 totlen = iph->tot_len;int proto = iph->protocol;int err = -ENOSYS ;@@ -1629,8 +1630,8 @@ int inet_gro_complete(struct sk_buff *skb, int nhoff)skb_set_inner_network_header (skb, nhoff); } -csum_replace2 (&iph->check, iph->tot_len, newlen); - iph->tot_len = newlen; +iph_set_totlen (iph, skb->len - nhoff); +csum_replace2 (&iph->check, totlen, iph->tot_len); ops =rcu_dereference (inet_offloads[proto]);if (WARN_ON (!ops || !ops->callbacks.gro_complete))net/ipv4/ip_input.c +0
-0@@ -511,7 +511,7 @@ static struct sk_buff *ip_rcv_core(struct sk_buff *skb, struct net *net)if (unlikely (ip_fast_csum ((u8 *)iph, iph->ihl))) goto csum_error;
Quoted 4 lines
net/ipv4/ip_input.c static struct sk_buff *ip_rcv_core(struct sk_buff *skb, struct net *net) · line 514
Quoted 2 lines
net/ipv4/ip_input.c +1
-1- len =ntohs (iph->tot_len); + len =skb_ip_totlen (skb);len =
iph_totlen(skb, iph);
OK, thanks.
Re: [PATCHv3 net-next 10/10] net: add support for ipv4 big tcp
Quoted 95 lines · Xin Long
Quoted 93 lines · Eric Dumazet
Quoted 67 lines · Xin Long
Similar to Eric's IPv6 BIG TCP, this patch is to enable IPv4 BIG TCP.
Firstly, allow
sk->sk_gso_max_sizeto be set to a value greater thanGSO_LEGACY_MAX_SIZEby not trimminggso_max_sizeinsk_trim_gso_size()for IPv4 TCP sockets.Then on TX path, set IP header
tot_lento 0 whenskb->len>IP_MAX_MTUin__ip_local_out()to allow to send BIG TCP packets, and this implies thatskb->lenis the length of a IPv4 packet; On RX path, useskb->lenas the length of the IPv4 packet when the IP headertot_lenis 0 andskb->len>IP_MAX_MTUinip_rcv_core(). As the APIiph_set_totlen()andskb_ip_totlen()are used in__ip_local_out()andip_rcv_core(), we only need to update these APIs.Also in GRO receive, add the check for ETH_P_IP/IPPROTO_TCP, and allows the merged packet size >=
GRO_LEGACY_MAX_SIZEinskb_gro_receive(). In GRO complete, set IP headertot_lento 0 when the merged packet size greater thanIP_MAX_MTUiniph_set_totlen()so that it can be processed on RX path.Note that by checking
skb_is_gso_tcp()in APIiph_totlen(), it makes this implementation safe to useiph->len== 0 indicates IPv4 BIG TCP packets.Signed-off-by Xin Long <[email protected]>--- net/core/gro.c | 12 +++++++----- net/core/sock.c | 8 ++++++-- net/ipv4/af_inet.c | 7 ++++--- net/ipv4/ip_input.c | 2 +- net/ipv4/ip_output.c | 2 +- 5 files changed, 19 insertions(+), 12 deletions(-)net/core/gro.c +7
-5@@ -162,16 +162,18 @@ int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb)struct sk_buff *lp;int segs; -/* pairs with WRITE_ONCE() in netif_set_gro_max_size() */ - gro_max_size =READ_ONCE (p->dev->gro_max_size); +/* pairs with WRITE_ONCE() in netif_set_gro(_ipv4)_max_size() */ + gro_max_size = p->protocol ==htons (ETH_P_IPV6 ) ? +READ_ONCE (p->dev->gro_max_size) : +READ_ONCE (p->dev->gro_ipv4_max_size);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 || +if (NAPI_GRO_CB (skb)->proto !=IPPROTO_TCP || + (p->protocol ==htons (ETH_P_IPV6 ) && +skb_headroom (p) <sizeof (struct hop_jumbo_hdr )) || p->encapsulation)return -E2BIG ; }net/core/sock.c +0
-0net/core/sock.c static void sk_trim_gso_size(struct sock *sk) · line 2387
Quoted 5 lines
net/core/sock.c +2
-0@@ -2383,6 +2383,8 @@ static void sk_trim_gso_size(struct sock *sk) !ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr))return ;#endif +if (sk->sk_family ==AF_INET &&sk_is_tcp (sk)) +return ;Or simply
net/core/sock.c +0
-0100644
net/core/sock.c +2
-4@@ -2375,14 +2375,9 @@ EXPORT_SYMBOL_GPL(sk_free_unlock_clone);static void sk_trim_gso_size (struct sock *sk) { -if (sk->sk_gso_max_size <=GSO_LEGACY_MAX_SIZE ) +if (sk->sk_gso_max_size <=GSO_LEGACY_MAX_SIZE || +sk_is_tcp (sk))return ; -#if IS_ENABLED (CONFIG_IPV6 ) - if (sk->sk_family == AF_INET6 && - sk_is_tcp(sk) &&
Quoted 9 lines
net/core/sock.c EXPORT_SYMBOL_GPL(sk_free_unlock_clone); · line 2382
Quoted 5 lines
net/core/sock.c +0
-3- !ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr)) -return ; -#endif sk->sk_gso_max_size =GSO_LEGACY_MAX_SIZE ; }There's a difference,
AF_INET6TCP socket may send ipv4 packets withipv6_addr_v4mapped, if we don't checkipv6_addr_v4mapped(), IPV4 GSO packets might go with the "gso_max_size" for IPV6.
But the change you wrote in sk_setup_caps() only checked sk_family.
Quoted 14 lines
I think we could use the change you wrote above, but we also need to use
dst->ops->familyinstead ofsk->sk_familyinsk_setup_caps():(quoted diff) +3
-0+ sk->sk_gso_max_size = dst->ops->family == AF_INET6 ? + READ_ONCE(dst->dev->gso_max_size) : +
READ_ONCE(dst->dev->gso_ipv4_max_size);Quoted 6 lines
net/core/sock.c +0
-0> sk->sk_gso_max_size = GSO_LEGACY_MAX_SIZE;Quoted 2 lines
net/core/sock.c +0
-0}
Quoted 10 lines
Quoted 10 lines
net/core/sock.c void sk_setup_caps(struct sock *sk, struct dst_entry *dst) · line 2411
Quoted 10 lines
net/core/sock.c +4
-2@@ -2403,8 +2405,10 @@ void sk_setup_caps(struct sock *sk, struct dst_entry *dst) sk->sk_route_caps &= ~NETIF_F_GSO_MASK ; }else { 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); +/* pairs with the WRITE_ONCE() in netif_set_gso(_ipv4)_max_size() */ + sk->sk_gso_max_size = sk->sk_family ==AF_INET6 ? +READ_ONCE (dst->dev->gso_max_size) : +READ_ONCE (dst->dev->gso_ipv4_max_size);
Here...
So if you need ipv6_addr_v4mapped() this should be done here anyway.
Quoted 50 lines
Quoted 45 lines
Quoted 45 lines
net/core/sock.c +0
-0sk_trim_gso_size (sk); sk->sk_gso_max_size -= (MAX_TCP_HEADER +1 );/* pairs with the WRITE_ONCE() in netif_set_gso_max_segs() */ net/ipv4/af_inet.c +4
-3@@ -1485,6 +1485,7 @@ struct sk_buff *inet_gro_receive(struct list_head *head, struct sk_buff *skb)if (unlikely (ip_fast_csum ((u8 *)iph,5 ))) goto out; +NAPI_GRO_CB (skb)->proto = proto; id =ntohl (*(__be32 *)&iph->id); flush = (u16)((ntohl (*(__be32 *)iph) ^skb_gro_len (skb)) | (id & ~IP_DF )); id >>=16 ;@@ -1618,9 +1619,9 @@ int inet_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)int inet_gro_complete (struct sk_buff *skb,int nhoff) { -__be16 newlen =htons (skb->len - nhoff);struct iphdr *iph = (struct iphdr *)(skb->data + nhoff);const struct net_offload *ops; +__be16 totlen = iph->tot_len;int proto = iph->protocol;int err = -ENOSYS ;@@ -1629,8 +1630,8 @@ int inet_gro_complete(struct sk_buff *skb, int nhoff)skb_set_inner_network_header (skb, nhoff); } -csum_replace2 (&iph->check, iph->tot_len, newlen); - iph->tot_len = newlen; +iph_set_totlen (iph, skb->len - nhoff); +csum_replace2 (&iph->check, totlen, iph->tot_len); ops =rcu_dereference (inet_offloads[proto]);if (WARN_ON (!ops || !ops->callbacks.gro_complete))net/ipv4/ip_input.c +0
-0@@ -511,7 +511,7 @@ static struct sk_buff *ip_rcv_core(struct sk_buff *skb, struct net *net)if (unlikely (ip_fast_csum ((u8 *)iph, iph->ihl))) goto csum_error;Quoted 4 lines
net/ipv4/ip_input.c static struct sk_buff *ip_rcv_core(struct sk_buff *skb, struct net *net) · line 514
Quoted 2 lines
net/ipv4/ip_input.c +1
-1- len =ntohs (iph->tot_len); + len =skb_ip_totlen (skb);len =
iph_totlen(skb, iph);OK, thanks.