net: support ipv4 big tcp
Subsystems (12)
v4 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.v3->v4:
- put gso/gro_ipv4_max_size close to other related fields, so that we do not need an extra cache line miss, as Eric suggested.
- also check ipv6_addr_v4mapped() when reading gso(_ipv4)_max_size in sk_setup_caps(), as Eric noticed.
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 | 26 +++++++++-------- 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, 130 insertions(+), 38 deletions(-)
Signature · 1 line
2.31.1
PATCH v4 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
Re: [PATCHv4 net-next 01/10] net: add a couple of helpers for iph tot_len
Quoted 4 lines · Xin Long
This patch adds three APIs to replace the
iph->tot_lensetting and getting in all places where IPv4 BIG TCP packets may reach, they will be used in the following patches.
Quoted 9 lines
Note that
iph_totlen()will be used when iph is not in linear data of the skb.Signed-off-by Xin Long <[email protected]>--- include/linux/ip.h | 21 +++++++++++++++++++++ include/net/route.h | 3 --- 2 files changed, 21 insertions(+), 3 deletions(-)
PATCH v4 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
Re: [PATCHv4 net-next 02/10] bridge: use skb_ip_totlen in br netfilter
Quoted 37 lines · Xin Long
These 3 places in bridge netfilter are called on RX path after GRO and IPv4 TCP GSO packets may come through, so replace iph
tot_lenaccessing withskb_ip_totlen()in there.Signed-off-by Xin Long <[email protected]>--- 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 +1
-1@@ -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 ;
net/bridge/netfilter/nf_conntrack_bridge.c static unsigned int nf_ct_bridge_pre(void *priv, struct sk_buff *skb, · line 262
Quoted 8 lines
net/bridge/netfilter/nf_conntrack_bridge.c +1
-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 ;
PATCH v4 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
Re: [PATCHv4 net-next 03/10] openvswitch: use skb_ip_totlen in conntrack
Quoted 5 lines · Xin Long
IPv4 GSO packets may get processed in
ovs_skb_network_trim(), and we need to useskb_ip_totlen()to get iph totlen.Signed-off-by Xin Long <[email protected]>---
PATCH v4 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 v4 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 v4 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 v4 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 v4 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
Re: [PATCHv4 net-next 08/10] packet: add TP_STATUS_GSO_TCP for tp_status
Quoted 11 lines · Xin Long
Introduce
TP_STATUS_GSO_TCPtp_statusflag to tell theaf_packetuser that this is a TCP GSO packet. When parsing IPv4 BIG TCP packets in tcpdump/libpcap, it can usetp_lenas the IPv4 packet len when this flag is set, as iphtot_lenis set to 0 for IPv4 BIG TCP packets.Signed-off-by Xin Long <[email protected]>--- include/uapi/linux/if_packet.h | 1 + net/packet/af_packet.c | 4 ++++ 2 files changed, 5 insertions(+)
PATCH v4 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
@@ -1964,6 +1964,8 @@ enum netdev_ml_priv_type {* @gso_max_segs: Maximum number of segments that can be passed to the * NIC for GSO * @tso_max_segs: Device (as in HW) limit on the max TSO segment count +* @gso_ipv4_max_size: Maximum size of generic segmentation offload, +* for IPv4. * * @dcbnl_ops: Data Center Bridging netlink ops * @num_tc: Number of traffic classes in the net device
@@ -2004,6 +2006,8 @@ 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_ipv4_max_size: Maximum size of aggregated packet in generic +* receive offload (GRO), for IPv4. * * @dev_addr_shadow: Copy of @dev_addr to catch direct writes. * @linkwatch_dev_tracker: refcount tracker used by linkwatch.
@@ -2207,6 +2211,7 @@ struct net_device {*/ #define GRO_MAX_SIZE (8 * 65535u)unsigned int gro_max_size; +unsigned int gro_ipv4_max_size;rx_handler_func_t __rcu *rx_handler;void __rcu *rx_handler_data;
@@ -2330,6 +2335,7 @@ struct net_device {u16 gso_max_segs;#define TSO_MAX_SEGS U16_MAXu16 tso_max_segs; +unsigned int gso_ipv4_max_size;#ifdef CONFIG_DCB const struct dcbnl_rtnl_ops *dcbnl_ops;
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);
@@ -10614,6 +10616,8 @@ 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
Paolo Abeni
maintainerRe: [PATCHv4 net-next 09/10] net: add gso_ipv4_max_size and gro_ipv4_max_size per device
Quoted 9 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.
Not a big deal, but I think it would be nice to include the pahole info showing where the new fields are located and why that are good locations.
No need to send a new version for just for the above, unless Eric asks otherwise ;)
Cheers,
Paolo
Re: [PATCHv4 net-next 09/10] net: add gso_ipv4_max_size and gro_ipv4_max_size per device
Quoted 12 lines · Paolo Abeni
Quoted 9 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.
Quoted 7 lines
Not a big deal, but I think it would be nice to include the pahole info showing where the new fields are located and why that are good locations.
No need to send a new version for just for the above, unless Eric asks otherwise ;)
The the pahole info without and with the patch shows below:
- Without the Patch:
# pahole --hex -C net_device vmlinux
struct net_device {
...
long unsigned int gro_flush_timeout; /* 0x330 0x8 */
int napi_defer_hard_irqs; /* 0x338 0x4 */
unsigned int gro_max_size; /* 0x33c 0x4 */ <---------
/* --- cacheline 13 boundary (832 bytes) --- */
rx_handler_func_t * rx_handler; /* 0x340 0x8 */
void * rx_handler_data; /* 0x348 0x8 */
struct mini_Qdisc * miniq_ingress; /* 0x350 0x8 */
struct netdev_queue * ingress_queue; /* 0x358 0x8 */
struct nf_hook_entries * nf_hooks_ingress; /* 0x360 0x8 */
unsigned char broadcast[32]; /* 0x368 0x20 */
/* --- cacheline 14 boundary (896 bytes) was 8 bytes ago --- */
struct cpu_rmap * rx_cpu_rmap; /* 0x388 0x8 */
struct hlist_node index_hlist; /* 0x390 0x10 *//* XXX 32 bytes hole, try to pack */
/* --- cacheline 15 boundary (960 bytes) --- */
struct netdev_queue * _tx __attribute__((__aligned__(64))); /*0x3c0 0x8 */
...
/* --- cacheline 32 boundary (2048 bytes) was 24 bytes ago --- */ const struct attribute_group * sysfs_groups[4]; /* 0x818 0x20 */
const struct attribute_group * sysfs_rx_queue_group; /* 0x838 0x8 */
/* --- cacheline 33 boundary (2112 bytes) --- */
const struct rtnl_link_ops * rtnl_link_ops; /* 0x840 0x8 */ unsigned int gso_max_size; /* 0x848 0x4 */ unsigned int tso_max_size; /* 0x84c 0x4 */ u16 gso_max_segs; /* 0x850 0x2 */ u16 tso_max_segs; /* 0x852 0x2 */ <---------
/* XXX 4 bytes hole, try to pack */
const struct dcbnl_rtnl_ops * dcbnl_ops; /* 0x858 0x8 */ s16 num_tc; /* 0x860 0x2 */ struct netdev_tc_txq tc_to_txq[16]; /* 0x862 0x40 */
/* --- cacheline 34 boundary (2176 bytes) was 34 bytes ago --- */
u8 prio_tc_map[16]; /* 0x8a2 0x10 */
...
}
- With the Patch:
For "gso_ipv4_max_size", it filled the hole as expected.
/* --- cacheline 33 boundary (2112 bytes) --- */
const struct rtnl_link_ops * rtnl_link_ops; /* 0x840 0x8 */ unsigned int gso_max_size; /* 0x848 0x4 */ unsigned int tso_max_size; /* 0x84c 0x4 */ u16 gso_max_segs; /* 0x850 0x2 */ u16 tso_max_segs; /* 0x852 0x2 */ unsigned int gso_ipv4_max_size; /* 0x854 0x4 */ <------- const struct dcbnl_rtnl_ops * dcbnl_ops; /* 0x858 0x8 */ s16 num_tc; /* 0x860 0x2 */ struct netdev_tc_txq tc_to_txq[16]; /* 0x862 0x40 */
/* --- cacheline 34 boundary (2176 bytes) was 34 bytes ago --- */
u8 prio_tc_map[16]; /* 0x8a2 0x10 */
For "gro_ipv4_max_size", these are no byte holes, I just put it in the "Cache lines mostly used on receive path" area, and next to gro_max_size.
long unsigned int gro_flush_timeout; /* 0x330 0x8 */ int napi_defer_hard_irqs; /* 0x338 0x4 */ unsigned int gro_max_size; /* 0x33c 0x4 */
/* --- cacheline 13 boundary (832 bytes) --- */
unsigned int gro_ipv4_max_size; /* 0x340 0x4 */ <------
/* XXX 4 bytes hole, try to pack */
rx_handler_func_t * rx_handler; /* 0x348 0x8 */ void * rx_handler_data; /* 0x350 0x8 */ struct mini_Qdisc * miniq_ingress; /* 0x358 0x8 */ struct netdev_queue * ingress_queue; /* 0x360 0x8 */ struct nf_hook_entries * nf_hooks_ingress; /* 0x368 0x8 */ unsigned char broadcast[32]; /* 0x370 0x20 */ /* --- cacheline 14 boundary (896 bytes) was 16 bytes ago --- */ struct cpu_rmap * rx_cpu_rmap; /* 0x390 0x8 */ struct hlist_node index_hlist; /* 0x398 0x10 */
/* XXX 24 bytes hole, try to pack */
/* --- cacheline 15 boundary (960 bytes) --- */
struct netdev_queue * _tx __attribute__((__aligned__(64))); /*0x3c0 0x8 */
Thanks.
Re: [PATCHv4 net-next 09/10] net: add gso_ipv4_max_size and gro_ipv4_max_size per device
In reply to Xin LongQuoted 10 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.
Quoted 9 lines
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(+)
PATCH v4 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 | 26 ++++++++++++++------------ net/ipv4/af_inet.c | 7 ++++--- net/ipv4/ip_input.c | 2 +- net/ipv4/ip_output.c | 2 +- 5 files changed, 27 insertions(+), 22 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 +14 -12
@@ -2373,17 +2373,22 @@ void sk_free_unlock_clone(struct sock *sk) }EXPORT_SYMBOL_GPL (sk_free_unlock_clone); -static void sk_trim_gso_size (struct sock *sk) +static u32 sk_dst_gso_max_size (struct sock *sk,struct dst_entry *dst) { -if (sk->sk_gso_max_size <=GSO_LEGACY_MAX_SIZE ) -return ; +bool is_ipv6 = false; +u32 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)) -return ; + is_ipv6 = (sk->sk_family ==AF_INET6 && + !ipv6_addr_v4mapped (&sk->sk_v6_rcv_saddr));#endif - sk->sk_gso_max_size =GSO_LEGACY_MAX_SIZE ; +/* pairs with the WRITE_ONCE() in netif_set_gso(_ipv4)_max_size() */ + max_size = is_ipv6 ?READ_ONCE (dst->dev->gso_max_size) : +READ_ONCE (dst->dev->gso_ipv4_max_size); +if (max_size >GSO_LEGACY_MAX_SIZE && !sk_is_tcp (sk)) + max_size =GSO_LEGACY_MAX_SIZE ; + +return max_size - (MAX_TCP_HEADER +1 ); }void sk_setup_caps (struct sock *sk,struct dst_entry *dst)
@@ -2403,10 +2408,7 @@ 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); -sk_trim_gso_size (sk); - sk->sk_gso_max_size -= (MAX_TCP_HEADER +1 ); + sk->sk_gso_max_size =sk_dst_gso_max_size (sk, dst);/* pairs with the WRITE_ONCE() in netif_set_gso_max_segs() */ max_segs =max_t (u32,READ_ONCE (dst->dev->gso_max_segs),1 ); }
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 =iph_totlen (skb, iph);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: [PATCHv4 net-next 10/10] net: add support for ipv4 big tcp
Quoted 24 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.
Quoted 9 lines
Signed-off-by Xin Long <[email protected]>--- net/core/gro.c | 12 +++++++----- net/core/sock.c | 26 ++++++++++++++------------ net/ipv4/af_inet.c | 7 ++++--- net/ipv4/ip_input.c | 2 +- net/ipv4/ip_output.c | 2 +- 5 files changed, 27 insertions(+), 22 deletions(-)
Re: [PATCHv4 net-next 10/10] net: add support for ipv4 big tcp: manual merge
In reply to Xin LongHello,
(I reduced the Cc list to the maintainers of the files modified by this patch)
Quoted 23 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.
(...)
Quoted 5 lines
net/core/gro.c +0
-0
net/core/gro.c int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb) · line 169
Quoted 10 lines
net/core/gro.c +4
-2@@ -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);
FYI, we got a small conflict when merging -net in net-next in the MPTCP tree due to another patch from -net:
7d2c89b32587 ("skb: Do mix page pool and page referenced frags in GRO")
and this one applied in net-next:
b1a78b9b9886 ("net: add support for ipv4 big tcp")
The conflict has been resolved on our side[1] by keeping the modifications from both sides and the resolution we suggest is attached to this email.
Cheers,
Matt
[1] https://github.com/multipath-tcp/mptcp_net-next/commit/56e08652439a
Signature · 2 lines
Tessares | Belgium | Hybrid Access Solutions www.tessares.net
net/core/gro.c +0 -0
@@@ -162,17 -162,10 +162,19 @@@ int skb_gro_receive(struct sk_buff *p,struct sk_buff *lp;int segs; +/* Do not splice page pool based packets w/ non-page pool + * packets. This can result in reference count issues as page + * pool pages will not decrement the reference count and will + * instead be immediately returned to the pool or have frag + * count decremented. + */ + if (p->pp_recycle != skb->pp_recycle) + return -ETOOMANYREFS ; + -/* 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 ;
Quoted 69 lines · Xin Long
This is similar to the BIG TCP patchset added by Eric for IPv6:
https://lwn.net/Articles/895398/
Different from IPv6, IPv4
tot_lenis 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 IPv4tot_lento 0 to indicate this might be a BIG TCP packet and useskb->lenas 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_offsetis exactly the IPv4 packet total length; Also, before implementing the feature, all those places that may get iphtot_lenfrom BIG TCP packets are taken care with some new APIs:Patch 1 adds some APIs for iph
tot_lensetting and getting, which are used in all these places where IPv4 BIG TCP packets may reach in Patch 2-7, Patch 8 adds aGSO_TCPtp_statusforaf_packetusers, 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 -tTCP_RR-H 192.168.100.1 -- -r80000,80000 -O MIN_LATENCY,P90_LATENCY,P99_LATENCY,THROUGHPUT|tail -1; done168 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 4417.82Enable BIG TCP:
ip link set dev ens1f0np0gro_ipv4_max_size128000gso_ipv4_max_size128000
for i in {1..10}; do netperf -tTCP_RR-H 192.168.100.1 -- -r80000,80000 -O MIN_LATENCY,P90_LATENCY,P99_LATENCY,THROUGHPUT|tail -1; done161 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 5080.99Thanks 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.
- addGSO_TCPfortp_statusin packet sockets to tell theaf_packetusers that this is a TCP GSO packet in Patch 8.
- also checkskb_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
Quoted 8 lines
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.v3->v4:
- put gso/gro_ipv4_max_size close to other related fields, so that we do not need an extra cache line miss, as Eric suggested.
- also checkipv6_addr_v4mapped()when reading gso(_ipv4)_max_size insk_setup_caps(), as Eric noticed.
For the series:
Please make sure to add needed changes to tcpdump/libpcap
Quoted 10 lines · Xin Long
This is similar to the BIG TCP patchset added by Eric for IPv6:
https://lwn.net/Articles/895398/
Different from IPv6, IPv4
tot_lenis 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 IPv4tot_lento 0 to indicate this might be a BIG TCP packet and useskb->lenas the real IPv4 total length.
Quoted 7 lines
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_offsetis exactly the IPv4 packet total length; Also, before implementing the feature, all those places that may get iphtot_lenfrom BIG TCP packets are taken care with some new APIs:
Thanks for working on this.
This series was applied to netdev/net-next.git (master) by Jakub Kicinski <[email protected]>:
Hello:
This series was applied to netdev/net-next.git (master) by Jakub Kicinski <[email protected]>:
Quoted 11 lines · On Sat, 28 Jan 2023 10:58:29 -0500 you wrote:
This is similar to the BIG TCP patchset added by Eric for IPv6:
https://lwn.net/Articles/895398/
Different from IPv6, IPv4
tot_lenis 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 IPv4tot_lento 0 to indicate this might be a BIG TCP packet and useskb->lenas the real IPv4 total length.[...]
Here is the summary with links:
- [PATCHv4,net-next,01/10] net: add a couple of helpers for iph tot_len
https://git.kernel.org/netdev/net-next/c/058a8f7f73aa - [PATCHv4,net-next,02/10] bridge: use skb_ip_totlen in br netfilter https://git.kernel.org/netdev/net-next/c/46abd17302ba - [PATCHv4,net-next,03/10] openvswitch: use skb_ip_totlen in conntrack https://git.kernel.org/netdev/net-next/c/ec84c955a0d0 - [PATCHv4,net-next,04/10] net: sched: use skb_ip_totlen and iph_totlen https://git.kernel.org/netdev/net-next/c/043e397e48c5 - [PATCHv4,net-next,05/10] netfilter: use skb_ip_totlen and iph_totlen https://git.kernel.org/netdev/net-next/c/a13fbf5ed5b4 - [PATCHv4,net-next,06/10] cipso_ipv4: use iph_set_totlen in skbuff_setattr https://git.kernel.org/netdev/net-next/c/7eb072be41ba - [PATCHv4,net-next,07/10] ipvlan: use skb_ip_totlen in ipvlan_get_L3_hdr https://git.kernel.org/netdev/net-next/c/50e6fb5c6efb - [PATCHv4,net-next,08/10] packet: add TP_STATUS_GSO_TCP for tp_status https://git.kernel.org/netdev/net-next/c/8e08bb75b60f - [PATCHv4,net-next,09/10] net: add gso_ipv4_max_size and gro_ipv4_max_size per device https://git.kernel.org/netdev/net-next/c/9eefedd58ae1 - [PATCHv4,net-next,10/10] net: add support for ipv4 big tcp https://git.kernel.org/netdev/net-next/c/b1a78b9b9886
You are awesome, thank you!
Signature · 2 lines
Deet-doot-dot, I am a bot. https://korg.docs.kernel.org/patchwork/pwbot.html