diff --git a/Documentation/networking/checksum-offloads.txt b/Documentation/networking/checksum-offloads.txt index 56e36861245f108595bb340123b2dece1ea2bead..d52d191bbb0c4c7a4ba5de9a5c6fad6683c6ac12 100644 --- a/Documentation/networking/checksum-offloads.txt +++ b/Documentation/networking/checksum-offloads.txt @@ -35,6 +35,9 @@ This interface only allows a single checksum to be offloaded. Where encapsulation is used, the packet may have multiple checksum fields in different header layers, and the rest will have to be handled by another mechanism such as LCO or RCO. +CRC32c can also be offloaded using this interface, by means of filling + skb->csum_start and skb->csum_offset as described above, and setting + skb->csum_not_inet: see skbuff.h comment (section 'D') for more details. No offloading of the IP header checksum is performed; it is always done in software. This is OK because when we build the IP header, we obviously have it in cache, so summing it isn't expensive. It's also rather short. @@ -49,9 +52,9 @@ A driver declares its offload capabilities in netdev->hw_features; see and csum_offset given in the SKB; if it tries to deduce these itself in hardware (as some NICs do) the driver should check that the values in the SKB match those which the hardware will deduce, and if not, fall back to - checksumming in software instead (with skb_checksum_help or one of the - skb_csum_off_chk* functions as mentioned in include/linux/skbuff.h). This - is a pain, but that's what you get when hardware tries to be clever. + checksumming in software instead (with skb_csum_hwoffload_help() or one of + the skb_checksum_help() / skb_crc32c_csum_help functions, as mentioned in + include/linux/skbuff.h). The stack should, for the most part, assume that checksum offload is supported by the underlying device. The only place that should check is @@ -60,7 +63,7 @@ The stack should, for the most part, assume that checksum offload is may include other offloads besides TX Checksum Offload) and, if they are not supported or enabled on the device (determined by netdev->features), performs the corresponding offload in software. In the case of TX - Checksum Offload, that means calling skb_checksum_help(skb). + Checksum Offload, that means calling skb_csum_hwoffload_help(skb, features). LCO: Local Checksum Offload diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c index 3a8a4aa13687ff42510e7a260b1de6715a55d8d5..9a0817938eca38526e4c746680efe2845e9b1e51 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c @@ -223,7 +223,7 @@ int aq_ring_rx_clean(struct aq_ring_s *self, int *work_done, int budget) skb->protocol = eth_type_trans(skb, ndev); if (unlikely(buff->is_cso_err)) { ++self->stats.rx.errors; - __skb_mark_checksum_bad(skb); + skb->ip_summed = CHECKSUM_NONE; } else { if (buff->is_ip_cso) { __skb_incr_checksum_unnecessary(skb); diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 0150b2dd3031d6514b783493bd698d2a375b3ab4..f8f7cd52a0a0946b44dbbc9fb74de1f6c4db9ac0 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2573,9 +2573,7 @@ static inline void skb_gro_incr_csum_unnecessary(struct sk_buff *skb) if (__skb_gro_checksum_validate_needed(skb, zero_okay, check)) \ __ret = __skb_gro_checksum_validate_complete(skb, \ compute_pseudo(skb, proto)); \ - if (__ret) \ - __skb_mark_checksum_bad(skb); \ - else \ + if (!__ret) \ skb_gro_incr_csum_unnecessary(skb); \ __ret; \ }) @@ -3931,6 +3929,10 @@ void netdev_rss_key_fill(void *buffer, size_t len); int dev_get_nest_level(struct net_device *dev); int skb_checksum_help(struct sk_buff *skb); +int skb_crc32c_csum_help(struct sk_buff *skb); +int skb_csum_hwoffload_help(struct sk_buff *skb, + const netdev_features_t features); + struct sk_buff *__skb_gso_segment(struct sk_buff *skb, netdev_features_t features, bool tx_path); struct sk_buff *skb_mac_gso_segment(struct sk_buff *skb, diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 7c0cb2ce8b01a9be366d8cdb7e3661f65ebff3c9..1713e4b7ea9f1c5f47e5da6dc398a94fa8a4eadb 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -109,6 +109,7 @@ * may perform further validation in this case. * GRE: only if the checksum is present in the header. * SCTP: indicates the CRC in SCTP header has been validated. + * FCOE: indicates the CRC in FC frame has been validated. * * skb->csum_level indicates the number of consecutive checksums found in * the packet minus one that have been verified as CHECKSUM_UNNECESSARY. @@ -126,8 +127,10 @@ * packet as seen by netif_rx() and fills out in skb->csum. Meaning, the * hardware doesn't need to parse L3/L4 headers to implement this. * - * Note: Even if device supports only some protocols, but is able to produce - * skb->csum, it MUST use CHECKSUM_COMPLETE, not CHECKSUM_UNNECESSARY. + * Notes: + * - Even if device supports only some protocols, but is able to produce + * skb->csum, it MUST use CHECKSUM_COMPLETE, not CHECKSUM_UNNECESSARY. + * - CHECKSUM_COMPLETE is not applicable to SCTP and FCoE protocols. * * CHECKSUM_PARTIAL: * @@ -162,14 +165,11 @@ * * 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. + * checksum offload capability. + * skb_csum_hwoffload_help() can be called to resolve CHECKSUM_PARTIAL based + * on network device checksumming capabilities: if a packet does not match + * them, skb_checksum_help or skb_crc32c_help (depending on the value of + * csum_not_inet, see item D.) is called to resolve the checksum. * * CHECKSUM_NONE: * @@ -189,11 +189,13 @@ * * 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. + * will set set csum_start and csum_offset accordingly, set ip_summed to + * CHECKSUM_PARTIAL and set csum_not_inet to 1, to provide an indication in + * the skbuff that the CHECKSUM_PARTIAL refers to CRC32c. + * A driver that supports both IP checksum offload and SCTP CRC32c offload + * must verify which offload is configured for a packet by testing the + * value of skb->csum_not_inet; skb_crc32c_csum_help is provided to resolve + * CHECKSUM_PARTIAL on skbs where csum_not_inet is set to 1. * * 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 @@ -556,6 +558,7 @@ typedef unsigned char *sk_buff_data_t; * @wifi_acked_valid: wifi_acked was set * @wifi_acked: whether frame was acked on wifi or not * @no_fcs: Request NIC to treat last 4 bytes as Ethernet FCS + * @csum_not_inet: use CRC32c to resolve CHECKSUM_PARTIAL * @dst_pending_confirm: need to confirm neighbour * @napi_id: id of the NAPI struct this skb came from * @secmark: security marking @@ -684,7 +687,7 @@ struct sk_buff { __u8 csum_valid:1; __u8 csum_complete_sw:1; __u8 csum_level:2; - __u8 csum_bad:1; + __u8 csum_not_inet:1; __u8 dst_pending_confirm:1; #ifdef CONFIG_IPV6_NDISC_NODETYPE @@ -3076,6 +3079,8 @@ struct skb_checksum_ops { __wsum (*combine)(__wsum csum, __wsum csum2, int offset, int len); }; +extern const struct skb_checksum_ops *crc32c_csum_stub __read_mostly; + __wsum __skb_checksum(const struct sk_buff *skb, int offset, int len, __wsum csum, const struct skb_checksum_ops *ops); __wsum skb_checksum(const struct sk_buff *skb, int offset, int len, @@ -3333,21 +3338,6 @@ static inline void __skb_incr_checksum_unnecessary(struct sk_buff *skb) } } -static inline void __skb_mark_checksum_bad(struct sk_buff *skb) -{ - /* Mark current checksum as bad (typically called from GRO - * path). In the case that ip_summed is CHECKSUM_NONE - * this must be the first checksum encountered in the packet. - * When ip_summed is CHECKSUM_UNNECESSARY, this is the first - * checksum after the last one validated. For UDP, a zero - * checksum can not be marked as bad. - */ - - if (skb->ip_summed == CHECKSUM_NONE || - skb->ip_summed == CHECKSUM_UNNECESSARY) - skb->csum_bad = 1; -} - /* Check if we need to perform checksum complete validation. * * Returns true if checksum complete is needed, false otherwise @@ -3401,9 +3391,6 @@ static inline __sum16 __skb_checksum_validate_complete(struct sk_buff *skb, skb->csum_valid = 1; return 0; } - } else if (skb->csum_bad) { - /* ip_summed == CHECKSUM_NONE in this case */ - return (__force __sum16)1; } skb->csum = psum; @@ -3463,8 +3450,7 @@ static inline __wsum null_compute_pseudo(struct sk_buff *skb, int proto) static inline bool __skb_checksum_convert_check(struct sk_buff *skb) { - return (skb->ip_summed == CHECKSUM_NONE && - skb->csum_valid && !skb->csum_bad); + return (skb->ip_summed == CHECKSUM_NONE && skb->csum_valid); } static inline void __skb_checksum_convert(struct sk_buff *skb, diff --git a/net/bridge/netfilter/nft_reject_bridge.c b/net/bridge/netfilter/nft_reject_bridge.c index 346ef6b00b8f05b62edc911d06c01692624596d9..c16dd3a47fc677fb2e6d2740c20b8ddbf11b3a1a 100644 --- a/net/bridge/netfilter/nft_reject_bridge.c +++ b/net/bridge/netfilter/nft_reject_bridge.c @@ -111,7 +111,7 @@ static void nft_reject_br_send_v4_unreach(struct net *net, __wsum csum; u8 proto; - if (oldskb->csum_bad || !nft_bridge_iphdr_validate(oldskb)) + if (!nft_bridge_iphdr_validate(oldskb)) return; /* IP header checks: fragment. */ @@ -226,9 +226,6 @@ static bool reject6_br_csum_ok(struct sk_buff *skb, int hook) __be16 fo; u8 proto = ip6h->nexthdr; - if (skb->csum_bad) - return false; - if (skb_csum_unnecessary(skb)) return true; diff --git a/net/core/dev.c b/net/core/dev.c index acd594c56f0ab846ed9ad895bd27abbe73411b82..bb136f726890331d02e69236dd5730eb09a1873c 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -143,6 +143,7 @@ #include #include #include +#include #include "net-sysfs.h" @@ -2612,6 +2613,47 @@ int skb_checksum_help(struct sk_buff *skb) } EXPORT_SYMBOL(skb_checksum_help); +int skb_crc32c_csum_help(struct sk_buff *skb) +{ + __le32 crc32c_csum; + int ret = 0, offset, start; + + if (skb->ip_summed != CHECKSUM_PARTIAL) + goto out; + + if (unlikely(skb_is_gso(skb))) + goto out; + + /* Before computing a checksum, we should make sure no frag could + * be modified by an external entity : checksum could be wrong. + */ + if (unlikely(skb_has_shared_frag(skb))) { + ret = __skb_linearize(skb); + if (ret) + goto out; + } + start = skb_checksum_start_offset(skb); + offset = start + offsetof(struct sctphdr, checksum); + if (WARN_ON_ONCE(offset >= skb_headlen(skb))) { + ret = -EINVAL; + goto out; + } + if (skb_cloned(skb) && + !skb_clone_writable(skb, offset + sizeof(__le32))) { + ret = pskb_expand_head(skb, 0, 0, GFP_ATOMIC); + if (ret) + goto out; + } + crc32c_csum = cpu_to_le32(~__skb_checksum(skb, start, + skb->len - start, ~(__u32)0, + crc32c_csum_stub)); + *(__le32 *)(skb->data + offset) = crc32c_csum; + skb->ip_summed = CHECKSUM_NONE; + skb->csum_not_inet = 0; +out: + return ret; +} + __be16 skb_network_protocol(struct sk_buff *skb, int *depth) { __be16 type = skb->protocol; @@ -2954,6 +2996,17 @@ static struct sk_buff *validate_xmit_vlan(struct sk_buff *skb, return skb; } +int skb_csum_hwoffload_help(struct sk_buff *skb, + const netdev_features_t features) +{ + if (unlikely(skb->csum_not_inet)) + return !!(features & NETIF_F_SCTP_CRC) ? 0 : + skb_crc32c_csum_help(skb); + + return !!(features & NETIF_F_CSUM_MASK) ? 0 : skb_checksum_help(skb); +} +EXPORT_SYMBOL(skb_csum_hwoffload_help); + static struct sk_buff *validate_xmit_skb(struct sk_buff *skb, struct net_device *dev) { netdev_features_t features; @@ -2992,8 +3045,7 @@ static struct sk_buff *validate_xmit_skb(struct sk_buff *skb, struct net_device else skb_set_transport_header(skb, skb_checksum_start_offset(skb)); - if (!(features & NETIF_F_CSUM_MASK) && - skb_checksum_help(skb)) + if (skb_csum_hwoffload_help(skb, features)) goto out_kfree_skb; } } @@ -4637,9 +4689,6 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff if (netif_elide_gro(skb->dev)) goto normal; - if (skb->csum_bad) - goto normal; - gro_list_prepare(napi, skb); rcu_read_lock(); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 346d3e85dfbc2eca1ded0442ecb78d31e1768523..d5c98117cbcecd4fef21d3f75d7ea441bcf66c60 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -2243,6 +2243,32 @@ __wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset, } EXPORT_SYMBOL(skb_copy_and_csum_bits); +static __wsum warn_crc32c_csum_update(const void *buff, int len, __wsum sum) +{ + net_warn_ratelimited( + "%s: attempt to compute crc32c without libcrc32c.ko\n", + __func__); + return 0; +} + +static __wsum warn_crc32c_csum_combine(__wsum csum, __wsum csum2, + int offset, int len) +{ + net_warn_ratelimited( + "%s: attempt to compute crc32c without libcrc32c.ko\n", + __func__); + return 0; +} + +static const struct skb_checksum_ops default_crc32c_ops = { + .update = warn_crc32c_csum_update, + .combine = warn_crc32c_csum_combine, +}; + +const struct skb_checksum_ops *crc32c_csum_stub __read_mostly = + &default_crc32c_ops; +EXPORT_SYMBOL(crc32c_csum_stub); + /** * skb_zerocopy_headlen - Calculate headroom needed for skb_zerocopy() * @from: source buffer diff --git a/net/ipv4/netfilter/nf_reject_ipv4.c b/net/ipv4/netfilter/nf_reject_ipv4.c index 7cd8d0d918f82e275e0ecd31c1cea8ec8fcf345d..6f8d9e5e062bca9679bf8a01feaebcb80925e01f 100644 --- a/net/ipv4/netfilter/nf_reject_ipv4.c +++ b/net/ipv4/netfilter/nf_reject_ipv4.c @@ -172,7 +172,7 @@ void nf_send_unreach(struct sk_buff *skb_in, int code, int hook) struct iphdr *iph = ip_hdr(skb_in); u8 proto; - if (skb_in->csum_bad || iph->frag_off & htons(IP_OFFSET)) + if (iph->frag_off & htons(IP_OFFSET)) return; if (skb_csum_unnecessary(skb_in)) { diff --git a/net/ipv6/netfilter/nf_reject_ipv6.c b/net/ipv6/netfilter/nf_reject_ipv6.c index eedee5d108d98422eab5753d7c619b269e07685e..f63b18e05c69e23bd3aef4c0d87a4eedb1823a23 100644 --- a/net/ipv6/netfilter/nf_reject_ipv6.c +++ b/net/ipv6/netfilter/nf_reject_ipv6.c @@ -220,9 +220,6 @@ static bool reject6_csum_ok(struct sk_buff *skb, int hook) __be16 fo; u8 proto; - if (skb->csum_bad) - return false; - if (skb_csum_unnecessary(skb)) return true; diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 7b17da9a94a0c15ab8ec28205e025d9554c798fb..9ddc9f8412a277badcba160d89b5343c2c80780a 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -453,7 +453,7 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb, /* Complete checksum if needed */ if (skb->ip_summed == CHECKSUM_PARTIAL && - (err = skb_checksum_help(skb))) + (err = skb_csum_hwoffload_help(skb, 0))) goto out; /* Older versions of OVS user space enforce alignment of the last diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c index ab6fdbd34db774bdb9d8a958ead2c808a3405d13..3317a2f579da7dfa764f7d5d7665460ffe06438b 100644 --- a/net/sched/act_csum.c +++ b/net/sched/act_csum.c @@ -350,6 +350,7 @@ static int tcf_csum_sctp(struct sk_buff *skb, unsigned int ihl, sctph->checksum = sctp_compute_cksum(skb, skb_network_offset(skb) + ihl); skb->ip_summed = CHECKSUM_NONE; + skb->csum_not_inet = 0; return 1; } diff --git a/net/sctp/offload.c b/net/sctp/offload.c index 4f5a2b580aa52deb75e00c92d8b60992cf5bdaa6..275925b93b2909a32e9a5ab83a16e9b0f5717e24 100644 --- a/net/sctp/offload.c +++ b/net/sctp/offload.c @@ -35,6 +35,7 @@ static __le32 sctp_gso_make_checksum(struct sk_buff *skb) { skb->ip_summed = CHECKSUM_NONE; + skb->csum_not_inet = 0; return sctp_compute_cksum(skb, skb_transport_offset(skb)); } @@ -98,6 +99,11 @@ static const struct net_offload sctp6_offload = { }, }; +static const struct skb_checksum_ops crc32c_csum_ops = { + .update = sctp_csum_update, + .combine = sctp_csum_combine, +}; + int __init sctp_offload_init(void) { int ret; @@ -110,6 +116,7 @@ int __init sctp_offload_init(void) if (ret) goto ipv4; + crc32c_csum_stub = &crc32c_csum_ops; return ret; ipv4: diff --git a/net/sctp/output.c b/net/sctp/output.c index 1409a875ad8e22172a4b6ec08ce339da3c8b80ab..e2edf2ebbadecd81adab46e2afc385314336e9ed 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -538,6 +538,7 @@ static int sctp_packet_pack(struct sctp_packet *packet, } else { chksum: head->ip_summed = CHECKSUM_PARTIAL; + head->csum_not_inet = 1; head->csum_start = skb_transport_header(head) - head->head; head->csum_offset = offsetof(struct sctphdr, checksum); }