diff options
Diffstat (limited to 'include')
| -rw-r--r-- | include/linux/if_vlan.h | 2 | ||||
| -rw-r--r-- | include/linux/netdev_features.h | 14 | ||||
| -rw-r--r-- | include/linux/netdevice.h | 118 | ||||
| -rw-r--r-- | include/linux/skbuff.h | 143 | ||||
| -rw-r--r-- | include/net/sock.h | 9 | ||||
| -rw-r--r-- | include/net/vxlan.h | 2 |
6 files changed, 236 insertions, 52 deletions
diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 05f5879821b8..a5f6ce6b578c 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -621,7 +621,7 @@ static inline netdev_features_t vlan_features_check(const struct sk_buff *skb, NETIF_F_SG | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST | - NETIF_F_GEN_CSUM | + NETIF_F_HW_CSUM | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX); diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index f0d87347df19..d9654f0eecb3 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -52,7 +52,7 @@ enum { NETIF_F_GSO_TUNNEL_REMCSUM_BIT, NETIF_F_FCOE_CRC_BIT, /* FCoE CRC32 */ - NETIF_F_SCTP_CSUM_BIT, /* SCTP checksum offload */ + NETIF_F_SCTP_CRC_BIT, /* SCTP checksum offload */ NETIF_F_FCOE_MTU_BIT, /* Supports max FCoE MTU, 2158 bytes*/ NETIF_F_NTUPLE_BIT, /* N-tuple filters supported */ NETIF_F_RXHASH_BIT, /* Receive hashing offload */ @@ -103,7 +103,7 @@ enum { #define NETIF_F_NTUPLE __NETIF_F(NTUPLE) #define NETIF_F_RXCSUM __NETIF_F(RXCSUM) #define NETIF_F_RXHASH __NETIF_F(RXHASH) -#define NETIF_F_SCTP_CSUM __NETIF_F(SCTP_CSUM) +#define NETIF_F_SCTP_CRC __NETIF_F(SCTP_CRC) #define NETIF_F_SG __NETIF_F(SG) #define NETIF_F_TSO6 __NETIF_F(TSO6) #define NETIF_F_TSO_ECN __NETIF_F(TSO_ECN) @@ -146,10 +146,12 @@ enum { #define NETIF_F_GSO_SOFTWARE (NETIF_F_TSO | NETIF_F_TSO_ECN | \ NETIF_F_TSO6 | NETIF_F_UFO) -#define NETIF_F_GEN_CSUM NETIF_F_HW_CSUM -#define NETIF_F_V4_CSUM (NETIF_F_GEN_CSUM | NETIF_F_IP_CSUM) -#define NETIF_F_V6_CSUM (NETIF_F_GEN_CSUM | NETIF_F_IPV6_CSUM) -#define NETIF_F_ALL_CSUM (NETIF_F_V4_CSUM | NETIF_F_V6_CSUM) +/* List of IP checksum features. Note that NETIF_F_ HW_CSUM should not be + * set in features when NETIF_F_IP_CSUM or NETIF_F_IPV6_CSUM are set-- + * this would be contradictory + */ +#define NETIF_F_CSUM_MASK (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | \ + NETIF_F_HW_CSUM) #define NETIF_F_ALL_TSO (NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_TSO_ECN) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 1bb21ff0fa64..9fb6395967de 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2522,6 +2522,71 @@ static inline void skb_gro_remcsum_cleanup(struct sk_buff *skb, remcsum_unadjust((__sum16 *)ptr, grc->delta); } +struct skb_csum_offl_spec { + __u16 ipv4_okay:1, + ipv6_okay:1, + encap_okay:1, + ip_options_okay:1, + ext_hdrs_okay:1, + tcp_okay:1, + udp_okay:1, + sctp_okay:1, + vlan_okay:1, + no_encapped_ipv6:1, + no_not_encapped:1; +}; + +bool __skb_csum_offload_chk(struct sk_buff *skb, + const struct skb_csum_offl_spec *spec, + bool *csum_encapped, + bool csum_help); + +static inline bool skb_csum_offload_chk(struct sk_buff *skb, + const struct skb_csum_offl_spec *spec, + bool *csum_encapped, + bool csum_help) +{ + if (skb->ip_summed != CHECKSUM_PARTIAL) + return false; + + return __skb_csum_offload_chk(skb, spec, csum_encapped, csum_help); +} + +static inline bool skb_csum_offload_chk_help(struct sk_buff *skb, + const struct skb_csum_offl_spec *spec) +{ + bool csum_encapped; + + return skb_csum_offload_chk(skb, spec, &csum_encapped, true); +} + +static inline bool skb_csum_off_chk_help_cmn(struct sk_buff *skb) +{ + static const struct skb_csum_offl_spec csum_offl_spec = { + .ipv4_okay = 1, + .ip_options_okay = 1, + .ipv6_okay = 1, + .vlan_okay = 1, + .tcp_okay = 1, + .udp_okay = 1, + }; + + return skb_csum_offload_chk_help(skb, &csum_offl_spec); +} + +static inline bool skb_csum_off_chk_help_cmn_v4_only(struct sk_buff *skb) +{ + static const struct skb_csum_offl_spec csum_offl_spec = { + .ipv4_okay = 1, + .ip_options_okay = 1, + .tcp_okay = 1, + .udp_okay = 1, + .vlan_okay = 1, + }; + + return skb_csum_offload_chk_help(skb, &csum_offl_spec); +} + static inline int dev_hard_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, const void *daddr, const void *saddr, @@ -3691,13 +3756,37 @@ __be16 skb_network_protocol(struct sk_buff *skb, int *depth); static inline bool can_checksum_protocol(netdev_features_t features, __be16 protocol) { - return ((features & NETIF_F_GEN_CSUM) || - ((features & NETIF_F_V4_CSUM) && - protocol == htons(ETH_P_IP)) || - ((features & NETIF_F_V6_CSUM) && - protocol == htons(ETH_P_IPV6)) || - ((features & NETIF_F_FCOE_CRC) && - protocol == htons(ETH_P_FCOE))); + if (protocol == htons(ETH_P_FCOE)) + return !!(features & NETIF_F_FCOE_CRC); + + /* Assume this is an IP checksum (not SCTP CRC) */ + + if (features & NETIF_F_HW_CSUM) { + /* Can checksum everything */ + return true; + } + + switch (protocol) { + case htons(ETH_P_IP): + return !!(features & NETIF_F_IP_CSUM); + case htons(ETH_P_IPV6): + return !!(features & NETIF_F_IPV6_CSUM); + default: + return false; + } +} + +/* Map an ethertype into IP protocol if possible */ +static inline int eproto_to_ipproto(int eproto) +{ + switch (eproto) { + case htons(ETH_P_IP): + return IPPROTO_IP; + case htons(ETH_P_IPV6): + return IPPROTO_IPV6; + default: + return -1; + } } #ifdef CONFIG_BUG @@ -3762,15 +3851,14 @@ void linkwatch_run_queue(void); static inline netdev_features_t netdev_intersect_features(netdev_features_t f1, netdev_features_t f2) { - if (f1 & NETIF_F_GEN_CSUM) - f1 |= (NETIF_F_ALL_CSUM & ~NETIF_F_GEN_CSUM); - if (f2 & NETIF_F_GEN_CSUM) - f2 |= (NETIF_F_ALL_CSUM & ~NETIF_F_GEN_CSUM); - f1 &= f2; - if (f1 & NETIF_F_GEN_CSUM) - f1 &= ~(NETIF_F_ALL_CSUM & ~NETIF_F_GEN_CSUM); + if ((f1 ^ f2) & NETIF_F_HW_CSUM) { + if (f1 & NETIF_F_HW_CSUM) + f1 |= (NETIF_F_IP_CSUM|NETIF_F_IP_CSUM); + else + f2 |= (NETIF_F_IP_CSUM|NETIF_F_IP_CSUM); + } - return f1; + return f1 & f2; } static inline netdev_features_t netdev_get_wanted_features( diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index af4f6ac025b6..6b6bd42d6134 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -39,11 +39,55 @@ #include <linux/in6.h> #include <net/flow.h> -/* A. Checksumming of received packets by device. +/* The interface for checksum offload between the stack and networking drivers + * is as follows... + * + * A. IP checksum related features + * + * Drivers advertise checksum offload capabilities in the features of a device. + * From the stack's point of view these are capabilities offered by the driver, + * a driver typically only advertises features that it is capable of offloading + * to its device. + * + * The checksum related features are: + * + * NETIF_F_HW_CSUM - The driver (or its device) is able to compute one + * IP (one's complement) checksum for any combination + * of protocols or protocol layering. The checksum is + * computed and set in a packet per the CHECKSUM_PARTIAL + * interface (see below). + * + * NETIF_F_IP_CSUM - Driver (device) is only able to checksum plain + * TCP or UDP packets over IPv4. These are specifically + * unencapsulated packets of the form IPv4|TCP or + * IPv4|UDP where the Protocol field in the IPv4 header + * is TCP or UDP. The IPv4 header may contain IP options + * This feature cannot be set in features for a device + * with NETIF_F_HW_CSUM also set. This feature is being + * DEPRECATED (see below). + * + * NETIF_F_IPV6_CSUM - Driver (device) is only able to checksum plain + * TCP or UDP packets over IPv6. These are specifically + * unencapsulated packets of the form IPv6|TCP or + * IPv4|UDP where the Next Header field in the IPv6 + * header is either TCP or UDP. IPv6 extension headers + * are not supported with this feature. This feature + * cannot be set in features for a device with + * NETIF_F_HW_CSUM also set. This feature is being + * DEPRECATED (see below). + * + * NETIF_F_RXCSUM - Driver (device) performs receive checksum offload. + * This flag is used only used to disable the RX checksum + * feature for a device. The stack will accept receive + * checksum indication in packets received on a device + * regardless of whether NETIF_F_RXCSUM is set. + * + * B. Checksumming of received packets by device. Indication of checksum + * verification is in set skb->ip_summed. Possible values are: * * CHECKSUM_NONE: * - * Device failed to checksum this packet e.g. due to lack of capabilities. + * Device did not checksum this packet e.g. due to lack of capabilities. * The packet contains full (though not verified) checksum in packet but * not in skb->csum. Thus, skb->csum is undefined in this case. * @@ -53,9 +97,8 @@ * (as in CHECKSUM_COMPLETE), but it does parse headers and verify checksums * for specific protocols. For such packets it will set CHECKSUM_UNNECESSARY * if their checksums are okay. skb->csum is still undefined in this case - * though. It is a bad option, but, unfortunately, nowadays most vendors do - * this. Apparently with the secret goal to sell you new devices, when you - * will add new protocol to your host, f.e. IPv6 8) + * though. A driver or device must never modify the checksum field in the + * packet even if checksum is verified. * * CHECKSUM_UNNECESSARY is applicable to following protocols: * TCP: IPv6 and IPv4. @@ -96,40 +139,77 @@ * packet that are after the checksum being offloaded are not considered to * be verified. * - * B. Checksumming on output. - * - * CHECKSUM_NONE: - * - * The skb was already checksummed by the protocol, or a checksum is not - * required. + * C. Checksumming on transmit for non-GSO. The stack requests checksum offload + * in the skb->ip_summed for a packet. Values are: * * CHECKSUM_PARTIAL: * - * The device is required to checksum the packet as seen by hard_start_xmit() + * The driver is required to checksum the packet as seen by hard_start_xmit() * from skb->csum_start up to the end, and to record/write the checksum at - * offset skb->csum_start + skb->csum_offset. + * offset skb->csum_start + skb->csum_offset. A driver may verify that the + * csum_start and csum_offset values are valid values given the length and + * offset of the packet, however they should not attempt to validate that the + * checksum refers to a legitimate transport layer checksum-- it is the + * purview of the stack to validate that csum_start and csum_offset are set + * correctly. + * + * When the stack requests checksum offload for a packet, the driver MUST + * ensure that the checksum is set correctly. A driver can either offload the + * checksum calculation to the device, or call skb_checksum_help (in the case + * that the device does not support offload for a particular checksum). + * + * NETIF_F_IP_CSUM and NETIF_F_IPV6_CSUM are being deprecated in favor of + * NETIF_F_HW_CSUM. New devices should use NETIF_F_HW_CSUM to indicate + * checksum offload capability. If a device has limited checksum capabilities + * (for instance can only perform NETIF_F_IP_CSUM or NETIF_F_IPV6_CSUM as + * described above) a helper function can be called to resolve + * CHECKSUM_PARTIAL. The helper functions are skb_csum_off_chk*. The helper + * function takes a spec argument that describes the protocol layer that is + * supported for checksum offload and can be called for each packet. If a + * packet does not match the specification for offload, skb_checksum_help + * is called to resolve the checksum. * - * The device must show its capabilities in dev->features, set up at device - * setup time, e.g. netdev_features.h: + * CHECKSUM_NONE: * - * NETIF_F_HW_CSUM - It's a clever device, it's able to checksum everything. - * NETIF_F_IP_CSUM - Device is dumb, it's able to checksum only TCP/UDP over - * IPv4. Sigh. Vendors like this way for an unknown reason. - * Though, see comment above about CHECKSUM_UNNECESSARY. 8) - * NETIF_F_IPV6_CSUM - About as dumb as the last one but does IPv6 instead. - * NETIF_F_... - Well, you get the picture. + * The skb was already checksummed by the protocol, or a checksum is not + * required. * * CHECKSUM_UNNECESSARY: * - * Normally, the device will do per protocol specific checksumming. Protocol - * implementations that do not want the NIC to perform the checksum - * calculation should use this flag in their outgoing skbs. - * - * NETIF_F_FCOE_CRC - This indicates that the device can do FCoE FC CRC - * offload. Correspondingly, the FCoE protocol driver - * stack should use CHECKSUM_UNNECESSARY. + * This has the same meaning on as CHECKSUM_NONE for checksum offload on + * output. * - * Any questions? No questions, good. --ANK + * CHECKSUM_COMPLETE: + * Not used in checksum output. If a driver observes a packet with this value + * set in skbuff, if should treat as CHECKSUM_NONE being set. + * + * D. Non-IP checksum (CRC) offloads + * + * NETIF_F_SCTP_CRC - This feature indicates that a device is capable of + * offloading the SCTP CRC in a packet. To perform this offload the stack + * will set ip_summed to CHECKSUM_PARTIAL and set csum_start and csum_offset + * accordingly. Note the there is no indication in the skbuff that the + * CHECKSUM_PARTIAL refers to an SCTP checksum, a driver that supports + * both IP checksum offload and SCTP CRC offload must verify which offload + * is configured for a packet presumably by inspecting packet headers. + * + * NETIF_F_FCOE_CRC - This feature indicates that a device is capable of + * offloading the FCOE CRC in a packet. To perform this offload the stack + * will set ip_summed to CHECKSUM_PARTIAL and set csum_start and csum_offset + * accordingly. Note the there is no indication in the skbuff that the + * CHECKSUM_PARTIAL refers to an FCOE checksum, a driver that supports + * both IP checksum offload and FCOE CRC offload must verify which offload + * is configured for a packet presumably by inspecting packet headers. + * + * E. Checksumming on output with GSO. + * + * In the case of a GSO packet (skb_is_gso(skb) is true), checksum offload + * is implied by the SKB_GSO_* flags in gso_type. Most obviously, if the + * gso_type is SKB_GSO_TCPV4 or SKB_GSO_TCPV6, TCP checksum offload as + * part of the GSO operation is implied. If a checksum is being offloaded + * with GSO then ip_summed is CHECKSUM_PARTIAL, csum_start and csum_offset + * are set to refer to the outermost checksum being offload (two offloaded + * checksums are possible with UDP encapsulation). */ /* Don't change this without changing skb_csum_unnecessary! */ @@ -1939,6 +2019,11 @@ static inline unsigned char *skb_inner_transport_header(const struct sk_buff return skb->head + skb->inner_transport_header; } +static inline int skb_inner_transport_offset(const struct sk_buff *skb) +{ + return skb_inner_transport_header(skb) - skb->data; +} + static inline void skb_reset_inner_transport_header(struct sk_buff *skb) { skb->inner_transport_header = skb->data - skb->head; diff --git a/include/net/sock.h b/include/net/sock.h index 0ca22b014de1..ab0269f4b2cc 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1791,6 +1791,15 @@ static inline void sk_nocaps_add(struct sock *sk, netdev_features_t flags) sk->sk_route_caps &= ~flags; } +static inline bool sk_check_csum_caps(struct sock *sk) +{ + return (sk->sk_route_caps & NETIF_F_HW_CSUM) || + (sk->sk_family == PF_INET && + (sk->sk_route_caps & NETIF_F_IP_CSUM)) || + (sk->sk_family == PF_INET6 && + (sk->sk_route_caps & NETIF_F_IPV6_CSUM)); +} + static inline int skb_do_copy_data_nocache(struct sock *sk, struct sk_buff *skb, struct iov_iter *from, char *to, int copy, int offset) diff --git a/include/net/vxlan.h b/include/net/vxlan.h index c1c899c3a51b..b5a1aec1a167 100644 --- a/include/net/vxlan.h +++ b/include/net/vxlan.h @@ -232,7 +232,7 @@ static inline netdev_features_t vxlan_features_check(struct sk_buff *skb, skb->inner_protocol != htons(ETH_P_TEB) || (skb_inner_mac_header(skb) - skb_transport_header(skb) != sizeof(struct udphdr) + sizeof(struct vxlanhdr)))) - return features & ~(NETIF_F_ALL_CSUM | NETIF_F_GSO_MASK); + return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK); return features; } |