diff options
| -rw-r--r-- | drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c | 1 | ||||
| -rw-r--r-- | drivers/net/ethernet/broadcom/bnxt/bnxt.c | 1 | ||||
| -rw-r--r-- | drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 1 | ||||
| -rw-r--r-- | drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 1 | ||||
| -rw-r--r-- | drivers/net/ethernet/qlogic/qede/qede_fp.c | 1 | ||||
| -rw-r--r-- | drivers/net/geneve.c | 1 | ||||
| -rw-r--r-- | drivers/net/vxlan.c | 1 | ||||
| -rw-r--r-- | include/linux/netdevice.h | 351 | ||||
| -rw-r--r-- | include/net/gro.h | 420 | ||||
| -rw-r--r-- | include/net/ip.h | 8 | ||||
| -rw-r--r-- | include/net/ip6_checksum.h | 8 | ||||
| -rw-r--r-- | include/net/udp.h | 24 | ||||
| -rw-r--r-- | net/core/Makefile | 2 | ||||
| -rw-r--r-- | net/core/dev.c | 668 | ||||
| -rw-r--r-- | net/core/gro.c | 766 | ||||
| -rw-r--r-- | net/core/skbuff.c | 142 | ||||
| -rw-r--r-- | net/ipv4/af_inet.c | 1 | ||||
| -rw-r--r-- | net/ipv4/esp4_offload.c | 1 | ||||
| -rw-r--r-- | net/ipv4/fou.c | 1 | ||||
| -rw-r--r-- | net/ipv4/gre_offload.c | 1 | ||||
| -rw-r--r-- | net/ipv4/tcp_offload.c | 1 | ||||
| -rw-r--r-- | net/ipv4/udp_offload.c | 28 | ||||
| -rw-r--r-- | net/ipv6/esp6_offload.c | 1 | ||||
| -rw-r--r-- | net/ipv6/tcpv6_offload.c | 1 | ||||
| -rw-r--r-- | net/ipv6/udp_offload.c | 1 |
25 files changed, 1230 insertions, 1202 deletions
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c index e8e8c2d593c5..54a2334dee56 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c @@ -25,6 +25,7 @@ #include <linux/ip.h> #include <linux/crash_dump.h> #include <net/tcp.h> +#include <net/gro.h> #include <net/ipv6.h> #include <net/ip6_checksum.h> #include <linux/prefetch.h> diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index c04ea83188e2..c057b1df86a9 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -37,6 +37,7 @@ #include <linux/if_bridge.h> #include <linux/rtc.h> #include <linux/bpf.h> +#include <net/gro.h> #include <net/ip.h> #include <net/tcp.h> #include <net/udp.h> diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index 9ccebbaa0d69..13835a37b3a2 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -17,6 +17,7 @@ #include <linux/skbuff.h> #include <linux/sctp.h> #include <net/gre.h> +#include <net/gro.h> #include <net/ip6_checksum.h> #include <net/pkt_cls.h> #include <net/tcp.h> diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 96967b0a2441..e384f6458c06 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -37,6 +37,7 @@ #include <net/ip6_checksum.h> #include <net/page_pool.h> #include <net/inet_ecn.h> +#include <net/gro.h> #include <net/udp.h> #include <net/tcp.h> #include "en.h" diff --git a/drivers/net/ethernet/qlogic/qede/qede_fp.c b/drivers/net/ethernet/qlogic/qede/qede_fp.c index 065e9004598e..e113fbd56e86 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_fp.c +++ b/drivers/net/ethernet/qlogic/qede/qede_fp.c @@ -10,6 +10,7 @@ #include <linux/bpf_trace.h> #include <net/udp_tunnel.h> #include <linux/ip.h> +#include <net/gro.h> #include <net/ipv6.h> #include <net/tcp.h> #include <linux/if_ether.h> diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index 1ab94b5f9bbf..9d26d1b965d2 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -17,6 +17,7 @@ #include <net/gro_cells.h> #include <net/rtnetlink.h> #include <net/geneve.h> +#include <net/gro.h> #include <net/protocol.h> #define GENEVE_NETDEV_VER "0.6" diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 141635a35c28..563f86de0e0d 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -17,6 +17,7 @@ #include <linux/ethtool.h> #include <net/arp.h> #include <net/ndisc.h> +#include <net/gro.h> #include <net/ipv6_stubs.h> #include <net/ip.h> #include <net/icmp.h> diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 3ec42495a43a..31a7e6b27681 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2520,109 +2520,6 @@ static inline void netif_napi_del(struct napi_struct *napi) synchronize_net(); } -struct napi_gro_cb { - /* Virtual address of skb_shinfo(skb)->frags[0].page + offset. */ - void *frag0; - - /* Length of frag0. */ - unsigned int frag0_len; - - /* This indicates where we are processing relative to skb->data. */ - int data_offset; - - /* This is non-zero if the packet cannot be merged with the new skb. */ - u16 flush; - - /* Save the IP ID here and check when we get to the transport layer */ - u16 flush_id; - - /* Number of segments aggregated. */ - u16 count; - - /* Start offset for remote checksum offload */ - u16 gro_remcsum_start; - - /* jiffies when first packet was created/queued */ - unsigned long age; - - /* Used in ipv6_gro_receive() and foo-over-udp */ - u16 proto; - - /* This is non-zero if the packet may be of the same flow. */ - u8 same_flow:1; - - /* Used in tunnel GRO receive */ - u8 encap_mark:1; - - /* GRO checksum is valid */ - u8 csum_valid:1; - - /* Number of checksums via CHECKSUM_UNNECESSARY */ - u8 csum_cnt:3; - - /* Free the skb? */ - u8 free:2; -#define NAPI_GRO_FREE 1 -#define NAPI_GRO_FREE_STOLEN_HEAD 2 - - /* Used in foo-over-udp, set in udp[46]_gro_receive */ - u8 is_ipv6:1; - - /* Used in GRE, set in fou/gue_gro_receive */ - u8 is_fou:1; - - /* Used to determine if flush_id can be ignored */ - u8 is_atomic:1; - - /* Number of gro_receive callbacks this packet already went through */ - u8 recursion_counter:4; - - /* GRO is done by frag_list pointer chaining. */ - u8 is_flist:1; - - /* used to support CHECKSUM_COMPLETE for tunneling protocols */ - __wsum csum; - - /* used in skb_gro_receive() slow path */ - struct sk_buff *last; -}; - -#define NAPI_GRO_CB(skb) ((struct napi_gro_cb *)(skb)->cb) - -#define GRO_RECURSION_LIMIT 15 -static inline int gro_recursion_inc_test(struct sk_buff *skb) -{ - return ++NAPI_GRO_CB(skb)->recursion_counter == GRO_RECURSION_LIMIT; -} - -typedef struct sk_buff *(*gro_receive_t)(struct list_head *, struct sk_buff *); -static inline struct sk_buff *call_gro_receive(gro_receive_t cb, - struct list_head *head, - struct sk_buff *skb) -{ - if (unlikely(gro_recursion_inc_test(skb))) { - NAPI_GRO_CB(skb)->flush |= 1; - return NULL; - } - - return cb(head, skb); -} - -typedef struct sk_buff *(*gro_receive_sk_t)(struct sock *, struct list_head *, - struct sk_buff *); -static inline struct sk_buff *call_gro_receive_sk(gro_receive_sk_t cb, - struct sock *sk, - struct list_head *head, - struct sk_buff *skb) -{ - if (unlikely(gro_recursion_inc_test(skb))) { - NAPI_GRO_CB(skb)->flush |= 1; - return NULL; - } - - return cb(sk, head, skb); -} - struct packet_type { __be16 type; /* This is really htons(ether_type). */ bool ignore_outgoing; @@ -3005,254 +2902,7 @@ struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex); struct net_device *dev_get_by_napi_id(unsigned int napi_id); int netdev_get_name(struct net *net, char *name, int ifindex); int dev_restart(struct net_device *dev); -int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb); -int skb_gro_receive_list(struct sk_buff *p, struct sk_buff *skb); - -static inline unsigned int skb_gro_offset(const struct sk_buff *skb) -{ - return NAPI_GRO_CB(skb)->data_offset; -} - -static inline unsigned int skb_gro_len(const struct sk_buff *skb) -{ - return skb->len - NAPI_GRO_CB(skb)->data_offset; -} - -static inline void skb_gro_pull(struct sk_buff *skb, unsigned int len) -{ - NAPI_GRO_CB(skb)->data_offset += len; -} - -static inline void *skb_gro_header_fast(struct sk_buff *skb, - unsigned int offset) -{ - return NAPI_GRO_CB(skb)->frag0 + offset; -} - -static inline int skb_gro_header_hard(struct sk_buff *skb, unsigned int hlen) -{ - return NAPI_GRO_CB(skb)->frag0_len < hlen; -} - -static inline void skb_gro_frag0_invalidate(struct sk_buff *skb) -{ - NAPI_GRO_CB(skb)->frag0 = NULL; - NAPI_GRO_CB(skb)->frag0_len = 0; -} - -static inline void *skb_gro_header_slow(struct sk_buff *skb, unsigned int hlen, - unsigned int offset) -{ - if (!pskb_may_pull(skb, hlen)) - return NULL; - - skb_gro_frag0_invalidate(skb); - return skb->data + offset; -} - -static inline void *skb_gro_network_header(struct sk_buff *skb) -{ - return (NAPI_GRO_CB(skb)->frag0 ?: skb->data) + - skb_network_offset(skb); -} - -static inline void skb_gro_postpull_rcsum(struct sk_buff *skb, - const void *start, unsigned int len) -{ - if (NAPI_GRO_CB(skb)->csum_valid) - NAPI_GRO_CB(skb)->csum = csum_sub(NAPI_GRO_CB(skb)->csum, - csum_partial(start, len, 0)); -} - -/* GRO checksum functions. These are logical equivalents of the normal - * checksum functions (in skbuff.h) except that they operate on the GRO - * offsets and fields in sk_buff. - */ -__sum16 __skb_gro_checksum_complete(struct sk_buff *skb); - -static inline bool skb_at_gro_remcsum_start(struct sk_buff *skb) -{ - return (NAPI_GRO_CB(skb)->gro_remcsum_start == skb_gro_offset(skb)); -} - -static inline bool __skb_gro_checksum_validate_needed(struct sk_buff *skb, - bool zero_okay, - __sum16 check) -{ - return ((skb->ip_summed != CHECKSUM_PARTIAL || - skb_checksum_start_offset(skb) < - skb_gro_offset(skb)) && - !skb_at_gro_remcsum_start(skb) && - NAPI_GRO_CB(skb)->csum_cnt == 0 && - (!zero_okay || check)); -} - -static inline __sum16 __skb_gro_checksum_validate_complete(struct sk_buff *skb, - __wsum psum) -{ - if (NAPI_GRO_CB(skb)->csum_valid && - !csum_fold(csum_add(psum, NAPI_GRO_CB(skb)->csum))) - return 0; - - NAPI_GRO_CB(skb)->csum = psum; - - return __skb_gro_checksum_complete(skb); -} - -static inline void skb_gro_incr_csum_unnecessary(struct sk_buff *skb) -{ - if (NAPI_GRO_CB(skb)->csum_cnt > 0) { - /* Consume a checksum from CHECKSUM_UNNECESSARY */ - NAPI_GRO_CB(skb)->csum_cnt--; - } else { - /* Update skb for CHECKSUM_UNNECESSARY and csum_level when we - * verified a new top level checksum or an encapsulated one - * during GRO. This saves work if we fallback to normal path. - */ - __skb_incr_checksum_unnecessary(skb); - } -} - -#define __skb_gro_checksum_validate(skb, proto, zero_okay, check, \ - compute_pseudo) \ -({ \ - __sum16 __ret = 0; \ - if (__skb_gro_checksum_validate_needed(skb, zero_okay, check)) \ - __ret = __skb_gro_checksum_validate_complete(skb, \ - compute_pseudo(skb, proto)); \ - if (!__ret) \ - skb_gro_incr_csum_unnecessary(skb); \ - __ret; \ -}) - -#define skb_gro_checksum_validate(skb, proto, compute_pseudo) \ - __skb_gro_checksum_validate(skb, proto, false, 0, compute_pseudo) - -#define skb_gro_checksum_validate_zero_check(skb, proto, check, \ - compute_pseudo) \ - __skb_gro_checksum_validate(skb, proto, true, check, compute_pseudo) - -#define skb_gro_checksum_simple_validate(skb) \ - __skb_gro_checksum_validate(skb, 0, false, 0, null_compute_pseudo) - -static inline bool __skb_gro_checksum_convert_check(struct sk_buff *skb) -{ - return (NAPI_GRO_CB(skb)->csum_cnt == 0 && - !NAPI_GRO_CB(skb)->csum_valid); -} - -static inline void __skb_gro_checksum_convert(struct sk_buff *skb, - __wsum pseudo) -{ - NAPI_GRO_CB(skb)->csum = ~pseudo; - NAPI_GRO_CB(skb)->csum_valid = 1; -} - -#define skb_gro_checksum_try_convert(skb, proto, compute_pseudo) \ -do { \ - if (__skb_gro_checksum_convert_check(skb)) \ - __skb_gro_checksum_convert(skb, \ - compute_pseudo(skb, proto)); \ -} while (0) - -struct gro_remcsum { - int offset; - __wsum delta; -}; - -static inline void skb_gro_remcsum_init(struct gro_remcsum *grc) -{ - grc->offset = 0; - grc->delta = 0; -} - -static inline void *skb_gro_remcsum_process(struct sk_buff *skb, void *ptr, - unsigned int off, size_t hdrlen, - int start, int offset, - struct gro_remcsum *grc, - bool nopartial) -{ - __wsum delta; - size_t plen = hdrlen + max_t(size_t, offset + sizeof(u16), start); - - BUG_ON(!NAPI_GRO_CB(skb)->csum_valid); - - if (!nopartial) { - NAPI_GRO_CB(skb)->gro_remcsum_start = off + hdrlen + start; - return ptr; - } - - ptr = skb_gro_header_fast(skb, off); - if (skb_gro_header_hard(skb, off + plen)) { - ptr = skb_gro_header_slow(skb, off + plen, off); - if (!ptr) - return NULL; - } - - delta = remcsum_adjust(ptr + hdrlen, NAPI_GRO_CB(skb)->csum, - start, offset); - - /* Adjust skb->csum since we changed the packet */ - NAPI_GRO_CB(skb)->csum = csum_add(NAPI_GRO_CB(skb)->csum, delta); - - grc->offset = off + hdrlen + offset; - grc->delta = delta; - - return ptr; -} - -static inline void skb_gro_remcsum_cleanup(struct sk_buff *skb, - struct gro_remcsum *grc) -{ - void *ptr; - size_t plen = grc->offset + sizeof(u16); - - if (!grc->delta) - return; - - ptr = skb_gro_header_fast(skb, grc->offset); - if (skb_gro_header_hard(skb, grc->offset + sizeof(u16))) { - ptr = skb_gro_header_slow(skb, plen, grc->offset); - if (!ptr) - return; - } - - remcsum_unadjust((__sum16 *)ptr, grc->delta); -} - -#ifdef CONFIG_XFRM_OFFLOAD -static inline void skb_gro_flush_final(struct sk_buff *skb, struct sk_buff *pp, int flush) -{ - if (PTR_ERR(pp) != -EINPROGRESS) - NAPI_GRO_CB(skb)->flush |= flush; -} -static inline void skb_gro_flush_final_remcsum(struct sk_buff *skb, - struct sk_buff *pp, - int flush, - struct gro_remcsum *grc) -{ - if (PTR_ERR(pp) != -EINPROGRESS) { - NAPI_GRO_CB(skb)->flush |= flush; - skb_gro_remcsum_cleanup(skb, grc); - skb->remcsum_offload = 0; - } -} -#else -static inline void skb_gro_flush_final(struct sk_buff *skb, struct sk_buff *pp, int flush) -{ - NAPI_GRO_CB(skb)->flush |= flush; -} -static inline void skb_gro_flush_final_remcsum(struct sk_buff *skb, - struct sk_buff *pp, - int flush, - struct gro_remcsum *grc) -{ - NAPI_GRO_CB(skb)->flush |= flush; - skb_gro_remcsum_cleanup(skb, grc); - skb->remcsum_offload = 0; -} -#endif static inline int dev_hard_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, @@ -4007,6 +3657,7 @@ int netif_rx_ni(struct sk_buff *skb); int netif_rx_any_context(struct sk_buff *skb); int netif_receive_skb(struct sk_buff *skb); int netif_receive_skb_core(struct sk_buff *skb); +void netif_receive_skb_list_internal(struct list_head *head); void netif_receive_skb_list(struct list_head *head); gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb); void napi_gro_flush(struct napi_struct *napi, bool flush_old); diff --git a/include/net/gro.h b/include/net/gro.h index 01edaf3fdda0..d0e7df691a80 100644 --- a/include/net/gro.h +++ b/include/net/gro.h @@ -4,9 +4,367 @@ #define _NET_IPV6_GRO_H #include <linux/indirect_call_wrapper.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/skbuff.h> +#include <net/udp.h> -struct list_head; -struct sk_buff; +struct napi_gro_cb { + /* Virtual address of skb_shinfo(skb)->frags[0].page + offset. */ + void *frag0; + + /* Length of frag0. */ + unsigned int frag0_len; + + /* This indicates where we are processing relative to skb->data. */ + int data_offset; + + /* This is non-zero if the packet cannot be merged with the new skb. */ + u16 flush; + + /* Save the IP ID here and check when we get to the transport layer */ + u16 flush_id; + + /* Number of segments aggregated. */ + u16 count; + + /* Start offset for remote checksum offload */ + u16 gro_remcsum_start; + + /* jiffies when first packet was created/queued */ + unsigned long age; + + /* Used in ipv6_gro_receive() and foo-over-udp */ + u16 proto; + + /* This is non-zero if the packet may be of the same flow. */ + u8 same_flow:1; + + /* Used in tunnel GRO receive */ + u8 encap_mark:1; + + /* GRO checksum is valid */ + u8 csum_valid:1; + + /* Number of checksums via CHECKSUM_UNNECESSARY */ + u8 csum_cnt:3; + + /* Free the skb? */ + u8 free:2; +#define NAPI_GRO_FREE 1 +#define NAPI_GRO_FREE_STOLEN_HEAD 2 + + /* Used in foo-over-udp, set in udp[46]_gro_receive */ + u8 is_ipv6:1; + + /* Used in GRE, set in fou/gue_gro_receive */ + u8 is_fou:1; + + /* Used to determine if flush_id can be ignored */ + u8 is_atomic:1; + + /* Number of gro_receive callbacks this packet already went through */ + u8 recursion_counter:4; + + /* GRO is done by frag_list pointer chaining. */ + u8 is_flist:1; + + /* used to support CHECKSUM_COMPLETE for tunneling protocols */ + __wsum csum; + + /* used in skb_gro_receive() slow path */ + struct sk_buff *last; +}; + +#define NAPI_GRO_CB(skb) ((struct napi_gro_cb *)(skb)->cb) + +#define GRO_RECURSION_LIMIT 15 +static inline int gro_recursion_inc_test(struct sk_buff *skb) +{ + return ++NAPI_GRO_CB(skb)->recursion_counter == GRO_RECURSION_LIMIT; +} + +typedef struct sk_buff *(*gro_receive_t)(struct list_head *, struct sk_buff *); +static inline struct sk_buff *call_gro_receive(gro_receive_t cb, + struct list_head *head, + struct sk_buff *skb) +{ + if (unlikely(gro_recursion_inc_test(skb))) { + NAPI_GRO_CB(skb)->flush |= 1; + return NULL; + } + + return cb(head, skb); +} + +typedef struct sk_buff *(*gro_receive_sk_t)(struct sock *, struct list_head *, + struct sk_buff *); +static inline struct sk_buff *call_gro_receive_sk(gro_receive_sk_t cb, + struct sock *sk, + struct list_head *head, + struct sk_buff *skb) +{ + if (unlikely(gro_recursion_inc_test(skb))) { + NAPI_GRO_CB(skb)->flush |= 1; + return NULL; + } + + return cb(sk, head, skb); +} + +static inline unsigned int skb_gro_offset(const struct sk_buff *skb) +{ + return NAPI_GRO_CB(skb)->data_offset; +} + +static inline unsigned int skb_gro_len(const struct sk_buff *skb) +{ + return skb->len - NAPI_GRO_CB(skb)->data_offset; +} + +static inline void skb_gro_pull(struct sk_buff *skb, unsigned int len) +{ + NAPI_GRO_CB(skb)->data_offset += len; +} + +static inline void *skb_gro_header_fast(struct sk_buff *skb, + unsigned int offset) +{ + return NAPI_GRO_CB(skb)->frag0 + offset; +} + +static inline int skb_gro_header_hard(struct sk_buff *skb, unsigned int hlen) +{ + return NAPI_GRO_CB(skb)->frag0_len < hlen; +} + +static inline void skb_gro_frag0_invalidate(struct sk_buff *skb) +{ + NAPI_GRO_CB(skb)->frag0 = NULL; + NAPI_GRO_CB(skb)->frag0_len = 0; +} + +static inline void *skb_gro_header_slow(struct sk_buff *skb, unsigned int hlen, + unsigned int offset) +{ + if (!pskb_may_pull(skb, hlen)) + return NULL; + + skb_gro_frag0_invalidate(skb); + return skb->data + offset; +} + +static inline void *skb_gro_network_header(struct sk_buff *skb) +{ + return (NAPI_GRO_CB(skb)->frag0 ?: skb->data) + + skb_network_offset(skb); +} + +static inline __wsum inet_gro_compute_pseudo(struct sk_buff *skb, int proto) +{ + const struct iphdr *iph = skb_gro_network_header(skb); + + return csum_tcpudp_nofold(iph->saddr, iph->daddr, + skb_gro_len(skb), proto, 0); +} + +static inline void skb_gro_postpull_rcsum(struct sk_buff *skb, + const void *start, unsigned int len) +{ + if (NAPI_GRO_CB(skb)->csum_valid) + NAPI_GRO_CB(skb)->csum = csum_sub(NAPI_GRO_CB(skb)->csum, + csum_partial(start, len, 0)); +} + +/* GRO checksum functions. These are logical equivalents of the normal + * checksum functions (in skbuff.h) except that they operate on the GRO + * offsets and fields in sk_buff. + */ + +__sum16 __skb_gro_checksum_complete(struct sk_buff *skb); + +static inline bool skb_at_gro_remcsum_start(struct sk_buff *skb) +{ + return (NAPI_GRO_CB(skb)->gro_remcsum_start == skb_gro_offset(skb)); +} + +static inline bool __skb_gro_checksum_validate_needed(struct sk_buff *skb, + bool zero_okay, + __sum16 check) +{ + return ((skb->ip_summed != CHECKSUM_PARTIAL || + skb_checksum_start_offset(skb) < + skb_gro_offset(skb)) && + !skb_at_gro_remcsum_start(skb) && + NAPI_GRO_CB(skb)->csum_cnt == 0 && + (!zero_okay || check)); +} + +static inline __sum16 __skb_gro_checksum_validate_complete(struct sk_buff *skb, + __wsum psum) +{ + if (NAPI_GRO_CB(skb)->csum_valid && + !csum_fold(csum_add(psum, NAPI_GRO_CB(skb)->csum))) + return 0; + + NAPI_GRO_CB(skb)->csum = psum; + + return __skb_gro_checksum_complete(skb); +} + +static inline void skb_gro_incr_csum_unnecessary(struct sk_buff *skb) +{ + if (NAPI_GRO_CB(skb)->csum_cnt > 0) { + /* Consume a checksum from CHECKSUM_UNNECESSARY */ + NAPI_GRO_CB(skb)->csum_cnt--; + } else { + /* Update skb for CHECKSUM_UNNECESSARY and csum_level when we + * verified a new top level checksum or an encapsulated one + * during GRO. This saves work if we fallback to normal path. + */ + __skb_incr_checksum_unnecessary(skb); + } +} + +#define __skb_gro_checksum_validate(skb, proto, zero_okay, check, \ + compute_pseudo) \ +({ \ + __sum16 __ret = 0; \ + if (__skb_gro_checksum_validate_needed(skb, zero_okay, check)) \ + __ret = __skb_gro_checksum_validate_complete(skb, \ + compute_pseudo(skb, proto)); \ + if (!__ret) \ + skb_gro_incr_csum_unnecessary(skb); \ + __ret; \ +}) + +#define skb_gro_checksum_validate(skb, proto, compute_pseudo) \ + __skb_gro_checksum_validate(skb, proto, false, 0, compute_pseudo) + +#define skb_gro_checksum_validate_zero_check(skb, proto, check, \ + compute_pseudo) \ + __skb_gro_checksum_validate(skb, proto, true, check, compute_pseudo) + +#define skb_gro_checksum_simple_validate(skb) \ + __skb_gro_checksum_validate(skb, 0, false, 0, null_compute_pseudo) + +static inline bool __skb_gro_checksum_convert_check(struct sk_buff *skb) +{ + return (NAPI_GRO_CB(skb)->csum_cnt == 0 && + !NAPI_GRO_CB(skb)->csum_valid); +} + +static inline void __skb_gro_checksum_convert(struct sk_buff *skb, + __wsum pseudo) +{ + NAPI_GRO_CB(skb)->csum = ~pseudo; + NAPI_GRO_CB(skb)->csum_valid = 1; +} + +#define skb_gro_checksum_try_convert(skb, proto, compute_pseudo) \ +do { \ + if (__skb_gro_checksum_convert_check(skb)) \ + __skb_gro_checksum_convert(skb, \ + compute_pseudo(skb, proto)); \ +} while (0) + +struct gro_remcsum { + int offset; + __wsum delta; +}; + +static inline void skb_gro_remcsum_init(struct gro_remcsum *grc) +{ + grc->offset = 0; + grc->delta = 0; +} + +static inline void *skb_gro_remcsum_process(struct sk_buff *skb, void *ptr, + unsigned int off, size_t hdrlen, + int start, int offset, + struct gro_remcsum *grc, + bool nopartial) +{ + __wsum delta; + size_t plen = hdrlen + max_t(size_t, offset + sizeof(u16), start); + + BUG_ON(!NAPI_GRO_CB(skb)->csum_valid); + + if (!nopartial) { + NAPI_GRO_CB(skb)->gro_remcsum_start = off + hdrlen + start; + return ptr; + } + + ptr = skb_gro_header_fast(skb, off); + if (skb_gro_header_hard(skb, off + plen)) { + ptr = skb_gro_header_slow(skb, off + plen, off); + if (!ptr) + return NULL; + } + + delta = remcsum_adjust(ptr + hdrlen, NAPI_GRO_CB(skb)->csum, + start, offset); + + /* Adjust skb->csum since we changed the packet */ + NAPI_GRO_CB(skb)->csum = csum_add(NAPI_GRO_CB(skb)->csum, delta); + + grc->offset = off + hdrlen + offset; + grc->delta = delta; + + return ptr; +} + +static inline void skb_gro_remcsum_cleanup(struct sk_buff *skb, + struct gro_remcsum *grc) +{ + void *ptr; + size_t plen = grc->offset + sizeof(u16); + + if (!grc->delta) + return; + + ptr = skb_gro_header_fast(skb, grc->offset); + if (skb_gro_header_hard(skb, grc->offset + sizeof(u16))) { + ptr = skb_gro_header_slow(skb, plen, grc->offset); + if (!ptr) + return; + } + + remcsum_unadjust((__sum16 *)ptr, grc->delta); +} + +#ifdef CONFIG_XFRM_OFFLOAD +static inline void skb_gro_flush_final(struct sk_buff *skb, struct sk_buff *pp, int flush) +{ + if (PTR_ERR(pp) != -EINPROGRESS) + NAPI_GRO_CB(skb)->flush |= flush; +} +static inline void skb_gro_flush_final_remcsum(struct sk_buff *skb, + struct sk_buff *pp, + int flush, + struct gro_remcsum *grc) +{ + if (PTR_ERR(pp) != -EINPROGRESS) { + NAPI_GRO_CB(skb)->flush |= flush; + skb_gro_remcsum_cleanup(skb, grc); + skb->remcsum_offload = 0; + } +} +#else +static inline void skb_gro_flush_final(struct sk_buff *skb, struct sk_buff *pp, int flush) +{ + NAPI_GRO_CB(skb)->flush |= flush; +} +static inline void skb_gro_flush_final_remcsum(struct sk_buff *skb, + struct sk_buff *pp, + int flush, + struct gro_remcsum *grc) +{ + NAPI_GRO_CB(skb)->flush |= flush; + skb_gro_remcsum_cleanup(skb, grc); + skb->remcsum_offload = 0; +} +#endif INDIRECT_CALLABLE_DECLARE(struct sk_buff *ipv6_gro_receive(struct list_head *, struct sk_buff *)); @@ -15,6 +373,14 @@ INDIRECT_CALLABLE_DECLARE(struct sk_buff *inet_gro_receive(struct list_head *, struct sk_buff *)); INDIRECT_CALLABLE_DECLARE(int inet_gro_complete(struct sk_buff *, int)); +INDIRECT_CALLABLE_DECLARE(struct sk_buff *udp4_gro_receive(struct list_head *, + struct sk_buff *)); +INDIRECT_CALLABLE_DECLARE(int udp4_gro_complete(struct sk_buff *, int)); + +INDIRECT_CALLABLE_DECLARE(struct sk_buff *udp6_gro_receive(struct list_head *, + struct sk_buff *)); +INDIRECT_CALLABLE_DECLARE(int udp6_gro_complete(struct sk_buff *, int)); + #define indirect_call_gro_receive_inet(cb, f2, f1, head, skb) \ ({ \ unlikely(gro_recursion_inc_test(skb)) ? \ @@ -22,4 +388,54 @@ INDIRECT_CALLABLE_DECLARE(int inet_gro_complete(struct sk_buff *, int)); INDIRECT_CALL_INET(cb, f2, f1, head, skb); \ }) +struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb, + struct udphdr *uh, struct sock *sk); +int udp_gro_complete(struct sk_buff *skb, int nhoff, udp_lookup_t lookup); + +static inline struct udphdr *udp_gro_udphdr(struct sk_buff *skb) +{ + struct udphdr *uh; + unsigned int hlen, off; + + off = skb_gro_offset(skb); + hlen = off + sizeof(*uh); + uh = skb_gro_header_fast(skb, off); + if (skb_gro_header_hard(skb, hlen)) + uh = skb_gro_header_slow(skb, hlen, off); + + return uh; +} + +static inline __wsum ip6_gro_compute_pseudo(struct sk_buff *skb, int proto) +{ + const struct ipv6hdr *iph = skb_gro_network_header(skb); + + return ~csum_unfold(csum_ipv6_magic(&iph->saddr, &iph->daddr, + skb_gro_len(skb), proto, 0)); +} + +int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb); + +/* Pass the currently batched GRO_NORMAL SKBs up to the stack. */ +static inline void gro_normal_list(struct napi_struct *napi) +{ + if (!napi->rx_count) + return; + netif_receive_skb_list_internal(&napi->rx_list); + INIT_LIST_HEAD(&napi->rx_list); + napi->rx_count = 0; +} + +/* Queue one GRO_NORMAL SKB up for list processing. If batch size exceeded, + * pass the whole batch up to the stack. + */ +static inline void gro_normal_one(struct napi_struct *napi, struct sk_buff *skb, int segs) +{ + list_add_tail(&skb->list, &napi->rx_list); + napi->rx_count += segs; + if (napi->rx_count >= gro_normal_batch) + gro_normal_list(napi); +} + + #endif /* _NET_IPV6_GRO_H */ diff --git a/include/net/ip.h b/include/net/ip.h index b71e88507c4a..7d1088888c10 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -568,14 +568,6 @@ static inline void iph_to_flow_copy_v4addrs(struct flow_keys *flow, flow->control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; } -static inline __wsum inet_gro_compute_pseudo(struct sk_buff *skb, int proto) -{ - const struct iphdr *iph = skb_gro_network_header(skb); - - return csum_tcpudp_nofold(iph->saddr, iph->daddr, - skb_gro_len(skb), proto, 0); -} - /* * Map a multicast IP onto multicast MAC for type ethernet. */ diff --git a/include/net/ip6_checksum.h b/include/net/ip6_checksum.h index ea681910b7a3..c8a96b888277 100644 --- a/include/net/ip6_checksum.h +++ b/include/net/ip6_checksum.h @@ -43,14 +43,6 @@ static inline __wsum ip6_compute_pseudo(struct sk_buff *skb, int proto) skb->len, proto, 0)); } -static inline __wsum ip6_gro_compute_pseudo(struct sk_buff *skb, int proto) -{ - const struct ipv6hdr *iph = skb_gro_network_header(skb); - - return ~csum_unfold(csum_ipv6_magic(&iph->saddr, &iph->daddr, - skb_gro_len(skb), proto, 0)); -} - static __inline__ __sum16 tcp_v6_check(int len, const struct in6_addr *saddr, const struct in6_addr *daddr, diff --git a/include/net/udp.h b/include/net/udp.h index 909ecf447e0f..f1c2a88c9005 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -167,36 +167,12 @@ static inline void udp_csum_pull_header(struct sk_buff *skb) typedef struct sock *(*udp_lookup_t)(const struct sk_buff *skb, __be16 sport, __be16 dport); -INDIRECT_CALLABLE_DECLARE(struct sk_buff *udp4_gro_receive(struct list_head *, - struct sk_buff *)); -INDIRECT_CALLABLE_DECLARE(int udp4_gro_complete(struct sk_buff *, int)); -INDIRECT_CALLABLE_DECLARE(struct sk_buff *udp6_gro_receive(struct list_head *, - struct sk_buff *)); -INDIRECT_CALLABLE_DECLARE(int udp6_gro_complete(struct sk_buff *, int)); INDIRECT_CALLABLE_DECLARE(void udp_v6_early_demux(struct sk_buff *)); INDIRECT_CALLABLE_DECLARE(int udpv6_rcv(struct sk_buff *)); -struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb, - struct udphdr *uh, struct sock *sk); -int udp_gro_complete(struct sk_buff *skb, int nhoff, udp_lookup_t lookup); - struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb, netdev_features_t features, bool is_ipv6); -static inline struct udphdr *udp_gro_udphdr(struct sk_buff *skb) -{ - struct udphdr *uh; - unsigned int hlen, off; - - off = skb_gro_offset(skb); - hlen = off + sizeof(*uh); - uh = skb_gro_header_fast(skb, off); - if (skb_gro_header_hard(skb, hlen)) - uh = skb_gro_header_slow(skb, hlen, off); - - return uh; -} - /* hash routines shared between UDPv4/6 and UDP-Litev4/6 */ static inline int udp_lib_hash(struct sock *sk) { diff --git a/net/core/Makefile b/net/core/Makefile index 4268846f2f47..6bdcb2cafed8 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -11,7 +11,7 @@ obj-$(CONFIG_SYSCTL) += sysctl_net_core.o obj-y += dev.o dev_addr_lists.o dst.o netevent.o \ neighbour.o rtnetlink.o utils.o link_watch.o filter.o \ sock_diag.o dev_ioctl.o tso.o sock_reuseport.o \ - fib_notifier.o xdp.o flow_offload.o + fib_notifier.o xdp.o flow_offload.o gro.o obj-y += net-sysfs.o obj-$(CONFIG_PAGE_POOL) += page_pool.o diff --git a/net/core/dev.c b/net/core/dev.c index 15ac064b5562..92c9258cbf28 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -153,16 +153,10 @@ #include "net-sysfs.h" -#define MAX_GRO_SKBS 8 - -/* This should be increased if a protocol with a bigger head is added. */ -#define GRO_MAX_HEAD (MAX_HEADER + 128) static DEFINE_SPINLOCK(ptype_lock); -static DEFINE_SPINLOCK(offload_lock); struct list_head ptype_base[PTYPE_HASH_SIZE] __read_mostly; struct list_head ptype_all __read_mostly; /* Taps */ -static struct list_head offload_base __read_mostly; static int netif_rx_internal(struct sk_buff *skb); static int call_netdevice_notifiers_info(unsigned long val, @@ -604,84 +598,6 @@ void dev_remove_pack(struct packet_type *pt) EXPORT_SYMBOL(dev_remove_pack); -/** - * dev_add_offload - register offload handlers - * @po: protocol offload declaration - * - * Add protocol offload handlers to the networking stack. The passed - * &proto_offload is linked into kernel lists and may not be freed until - * it has been removed from the kernel lists. - * - * This call does not sleep therefore it can not - * guarantee all CPU's that are in middle of receiving packets - * will see the new offload handlers (until the next received packet). - */ -void dev_add_offload(struct packet_offload *po) -{ - struct packet_offload *elem; - - spin_lock(&offload_lock); - list_for_each_entry(elem, &offload_base, list) { - if (po->priority < elem->priority) - break; - } - list_add_rcu(&po->list, elem->list.prev); - spin_unlock(&offload_lock); -} -EXPORT_SYMBOL(dev_add_offload); - -/** - * __dev_remove_offload - remove offload handler - * @po: packet offload declaration - * - * Remove a protocol offload handler that was previously added to the - * kernel offload handlers by dev_add_offload(). The passed &offload_type - * is removed from the kernel lists and can be freed or reused once this - * function returns. - * - * The packet type might still be in use by receivers - * and must not be freed until after all the CPU's have gone - * through a quiescent state. - */ -static void __dev_remove_offload(struct packet_offload *po) -{ - struct list_head *head = &offload_base; - struct packet_offload *po1; - - spin_lock(&offload_lock); - - list_for_each_entry(po1, head, list) { - if (po == po1) { - list_del_rcu(&po->list); - goto out; - } - } - - pr_warn("dev_remove_offload: %p not found\n", po); -out: - spin_unlock(&offload_lock); -} - -/** - * dev_remove_offload - remove packet offload handler - * @po: packet offload declaration - * - * Remove a packet offload handler that was previously added to the kernel - * offload handlers by dev_add_offload(). The passed &offload_type is - * removed from the kernel lists and can be freed or reused once this - * function returns. - * - * This call sleeps to guarantee that no CPU is looking at the packet - * type after return. - */ -void dev_remove_offload(struct packet_offload *po) -{ - __dev_remove_offload(po); - - synchronize_net(); -} -EXPORT_SYMBOL(dev_remove_offload); - /******************************************************************************* * * Device Interface Subroutines @@ -3315,40 +3231,6 @@ __be16 skb_network_protocol(struct sk_buff *skb, int *depth) return __vlan_get_protocol(skb, type, depth); } -/** - * skb_mac_gso_segment - mac layer segmentation handler. - * @skb: buffer to segment - * @features: features for the output path (see dev->features) - */ -struct sk_buff *skb_mac_gso_segment(struct sk_buff *skb, - netdev_features_t features) -{ - struct sk_buff *segs = ERR_PTR(-EPROTONOSUPPORT); - struct packet_offload *ptype; - int vlan_depth = skb->mac_len; - __be16 type = skb_network_protocol(skb, &vlan_depth); - - if (unlikely(!type)) - return ERR_PTR(-EINVAL); - - __skb_pull(skb, vlan_depth); - - rcu_read_lock(); - list_for_each_entry_rcu(ptype, &offload_base, list) { - if (ptype->type == type && ptype->callbacks.gso_segment) { - segs = ptype->callbacks.gso_segment(skb, features); - break; - } - } - rcu_read_unlock(); - - __skb_push(skb, skb->data - skb_mac_header(skb)); - - return segs; -} -EXPORT_SYMBOL(skb_mac_gso_segment); - - /* openvswitch calls this on rx path, so we need a different check. */ static inline bool skb_needs_check(struct sk_buff *skb, bool tx_path) @@ -4320,8 +4202,6 @@ int dev_weight_rx_bias __read_mostly = 1; /* bias for backlog weight */ int dev_weight_tx_bias __read_mostly = 1; /* bias for output_queue quota */ int dev_rx_weight __read_mostly = 64; int dev_tx_weight __read_mostly = 64; -/* Maximum number of GRO_NORMAL skbs to batch up for list-RX */ -int gro_normal_batch __read_mostly = 8; /* Called with irq disabled */ static inline void ____napi_schedule(struct softnet_data *sd, @@ -5664,7 +5544,7 @@ static int netif_receive_skb_internal(struct sk_buff *skb) return ret; } -static void netif_receive_skb_list_internal(struct list_head *head) +void netif_receive_skb_list_internal(struct list_head *head) { struct sk_buff *skb, *next; struct list_head sublist; @@ -5842,550 +5722,6 @@ static void flush_all_backlogs(void) cpus_read_unlock(); } -/* Pass the currently batched GRO_NORMAL SKBs up to the stack. */ -static void gro_normal_list(struct napi_struct *napi) -{ - if (!napi->rx_count) - return; - netif_receive_skb_list_internal(&napi->rx_list); - INIT_LIST_HEAD(&napi->rx_list); - napi->rx_count = 0; -} - -/* Queue one GRO_NORMAL SKB up for list processing. If batch size exceeded, - * pass the whole batch up to the stack. - */ -static void gro_normal_one(struct napi_struct *napi, struct sk_buff *skb, int segs) -{ - list_add_tail(&skb->list, &napi->rx_list); - napi->rx_count += segs; - if (napi->rx_count >= gro_normal_batch) - gro_normal_list(napi); -} - -static void napi_gro_complete(struct napi_struct *napi, struct sk_buff *skb) -{ - struct packet_offload *ptype; - __be16 type = skb->protocol; - struct list_head *head = &offload_base; - int err = -ENOENT; - - BUILD_BUG_ON(sizeof(struct napi_gro_cb) > sizeof(skb->cb)); - - if (NAPI_GRO_CB(skb)->count == 1) { - skb_shinfo(skb)->gso_size = 0; - goto out; - } - - rcu_read_lock(); - list_for_each_entry_rcu(ptype, head, list) { - if (ptype->type != type || !ptype->callbacks.gro_complete) - continue; - - err = INDIRECT_CALL_INET(ptype->callbacks.gro_complete, - ipv6_gro_complete, inet_gro_complete, - skb, 0); - break; - } - rcu_read_unlock(); - - if (err) { - WARN_ON(&ptype->list == head); - kfree_skb(skb); - return; - } - -out: - gro_normal_one(napi, skb, NAPI_GRO_CB(skb)->count); -} - -static void __napi_gro_flush_chain(struct napi_struct *napi, u32 index, - bool flush_old) -{ - struct list_head *head = &napi->gro_hash[index].list; - struct sk_buff *skb, *p; - - list_for_each_entry_safe_reverse(skb, p, head, list) { - if (flush_old && NAPI_GRO_CB(skb)->age == jiffies) - return; - skb_list_del_init(skb); - napi_gro_complete(napi, skb); - napi->gro_hash[index].count--; - } - - if (!napi->gro_hash[index].count) - __clear_bit(index, &napi->gro_bitmask); -} - -/* napi->gro_hash[].list contains packets ordered by age. - * youngest packets at the head of it. - * Complete skbs in reverse order to reduce latencies. - */ -void napi_gro_flush(struct napi_struct *napi, bool flush_old) -{ - unsigned long bitmask = napi->gro_bitmask; - unsigned int i, base = ~0U; - - while ((i = ffs(bitmask)) != 0) { - bitmask >>= i; - base += i; - __napi_gro_flush_chain(napi, base, flush_old); - } -} -EXPORT_SYMBOL(napi_gro_flush); - -static void gro_list_prepare(const struct list_head *head, - const struct sk_buff *skb) -{ - unsigned int maclen = skb->dev->hard_header_len; - u32 hash = skb_get_hash_raw(skb); - struct sk_buff *p; - - list_for_each_entry(p, head, list) { - unsigned long diffs; - - NAPI_GRO_CB(p)->flush = 0; - - if (hash != skb_get_hash_raw(p)) { - NAPI_GRO_CB(p)->same_flow = 0; - continue; - } - - diffs = (unsigned long)p->dev ^ (unsigned long)skb->dev; - diffs |= skb_vlan_tag_present(p) ^ skb_vlan_tag_present(skb); - if (skb_vlan_tag_present(p)) - diffs |= skb_vlan_tag_get(p) ^ skb_vlan_tag_get(skb); - diffs |= skb_metadata_differs(p, skb); - if (maclen == ETH_HLEN) - diffs |= compare_ether_header(skb_mac_header(p), - skb_mac_header(skb)); - else if (!diffs) - diffs = memcmp(skb_mac_header(p), - skb_mac_header(skb), - maclen); - - /* in most common scenarions 'slow_gro' is 0 - * otherwise we are already on some slower paths - * either skip all the infrequent tests altogether or - * avoid trying too hard to skip each of them individually - */ - if (!diffs && unlikely(skb->slow_gro | p->slow_gro)) { -#if IS_ENABLED(CONFIG_SKB_EXTENSIONS) && IS_ENABLED(CONFIG_NET_TC_SKB_EXT) - struct tc_skb_ext *skb_ext; - struct tc_skb_ext *p_ext; -#endif - - diffs |= p->sk != skb->sk; - diffs |= skb_metadata_dst_cmp(p, skb); - diffs |= skb_get_nfct(p) ^ skb_get_nfct(skb); - -#if IS_ENABLED(CONFIG_SKB_EXTENSIONS) && IS_ENABLED(CONFIG_NET_TC_SKB_EXT) - skb_ext = skb_ext_find(skb, TC_SKB_EXT); - p_ext = skb_ext_find(p, TC_SKB_EXT); - - diffs |= (!!p_ext) ^ (!!skb_ext); - if (!diffs && unlikely(skb_ext)) - diffs |= p_ext->chain ^ skb_ext->chain; -#endif - } - - NAPI_GRO_CB(p)->same_flow = !diffs; - } -} - -static inline void skb_gro_reset_offset(struct sk_buff *skb, u32 nhoff) -{ - const struct skb_shared_info *pinfo = skb_shinfo(skb); - const skb_frag_t *frag0 = &pinfo->frags[0]; - - NAPI_GRO_CB(skb)->data_offset = 0; - NAPI_GRO_CB(skb)->frag0 = NULL; - NAPI_GRO_CB(skb)->frag0_len = 0; - - if (!skb_headlen(skb) && pinfo->nr_frags && - !PageHighMem(skb_frag_page(frag0)) && - (!NET_IP_ALIGN || !((skb_frag_off(frag0) + nhoff) & 3))) { - NAPI_GRO_CB(skb)->frag0 = skb_frag_address(frag0); - NAPI_GRO_CB(skb)->frag0_len = min_t(unsigned int, - skb_frag_size(frag0), - skb->end - skb->tail); - } -} - -static void gro_pull_from_frag0(struct sk_buff *skb, int grow) -{ - struct skb_shared_info *pinfo = skb_shinfo(skb); - - BUG_ON(skb->end - skb->tail < grow); - - memcpy(skb_tail_pointer(skb), NAPI_GRO_CB(skb)->frag0, grow); - - skb->data_len -= grow; - skb->tail += grow; - - skb_frag_off_add(&pinfo->frags[0], grow); - skb_frag_size_sub(&pinfo->frags[0], grow); - - if (unlikely(!skb_frag_size(&pinfo->frags[0]))) { - skb_frag_unref(skb, 0); - memmove(pinfo->frags, pinfo->frags + 1, - --pinfo->nr_frags * sizeof(pinfo->frags[0])); - } -} - -static void gro_flush_oldest(struct napi_struct *napi, struct list_head *head) -{ - struct sk_buff *oldest; - - oldest = list_last_entry(head, struct sk_buff, list); - - /* We are called with head length >= MAX_GRO_SKBS, so this is - * impossible. - */ - if (WARN_ON_ONCE(!oldest)) - return; - - /* Do not adjust napi->gro_hash[].count, caller is adding a new - * SKB to the chain. - */ - skb_list_del_init(oldest); - napi_gro_complete(napi, oldest); -} - -static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb) -{ - u32 bucket = skb_get_hash_raw(skb) & (GRO_HASH_BUCKETS - 1); - struct gro_list *gro_list = &napi->gro_hash[bucket]; - struct list_head *head = &offload_base; - struct packet_offload *ptype; - __be16 type = skb->protocol; - struct sk_buff *pp = NULL; - enum gro_result ret; - int same_flow; - int grow; - - if (netif_elide_gro(skb->dev)) - goto normal; - - gro_list_prepare(&gro_list->list, skb); - - rcu_read_lock(); - list_for_each_entry_rcu(ptype, head, list) { - if (ptype->type != type || !ptype->callbacks.gro_receive) - continue; - - skb_set_network_header(skb, skb_gro_offset(skb)); - skb_reset_mac_len(skb); - NAPI_GRO_CB(skb)->same_flow = 0; - NAPI_GRO_CB(skb)->flush = skb_is_gso(skb) || skb_has_frag_list(skb); - NAPI_GRO_CB(skb)->free = 0; - NAPI_GRO_CB(skb)->encap_mark = 0; - NAPI_GRO_CB(skb)->recursion_counter = 0; - NAPI_GRO_CB(skb)->is_fou = 0; - NAPI_GRO_CB(skb)->is_atomic = 1; - NAPI_GRO_CB(skb)->gro_remcsum_start = 0; - - /* Setup for GRO checksum validation */ - switch (skb->ip_summed) { - case CHECKSUM_COMPLETE: - NAPI_GRO_CB(skb)->csum = skb->csum; - NAPI_GRO_CB(skb)->csum_valid = 1; - NAPI_GRO_CB(skb)->csum_cnt = 0; - break; - case CHECKSUM_UNNECESSARY: - NAPI_GRO_CB(skb)->csum_cnt = skb->csum_level + 1; - NAPI_GRO_CB(skb)->csum_valid = 0; - break; - default: - NAPI_GRO_CB(skb)->csum_cnt = 0; - NAPI_GRO_CB(skb)->csum_valid = 0; - } - - pp = INDIRECT_CALL_INET(ptype->callbacks.gro_receive, - ipv6_gro_receive, inet_gro_receive, - &gro_list->list, skb); - break; - } - rcu_read_unlock(); - - if (&ptype->list == head) - goto normal; - - if (PTR_ERR(pp) == -EINPROGRESS) { - ret = GRO_CONSUMED; - goto ok; - } - - same_flow = NAPI_GRO_CB(skb)->same_flow; - ret = NAPI_GRO_CB(skb)->free ? GRO_MERGED_FREE : GRO_MERGED; - - if (pp) { - skb_list_del_init(pp); - napi_gro_complete(napi, pp); - gro_list->count--; - } - - if (same_flow) - goto ok; - - if (NAPI_GRO_CB(skb)->flush) - goto normal; - - if (unlikely(gro_list->count >= MAX_GRO_SKBS)) - gro_flush_oldest(napi, &gro_list->list); - else - gro_list->count++; - - NAPI_GRO_CB(skb)->count = 1; - NAPI_GRO_CB(skb)->age = jiffies; - NAPI_GRO_CB(skb)->last = skb; - skb_shinfo(skb)->gso_size = skb_gro_len(skb); - list_add(&skb->list, &gro_list->list); - ret = GRO_HELD; - -pull: - grow = skb_gro_offset(skb) - skb_headlen(skb); - if (grow > 0) - gro_pull_from_frag0(skb, grow); -ok: - if (gro_list->count) { - if (!test_bit(bucket, &napi->gro_bitmask)) - __set_bit(bucket, &napi->gro_bitmask); - } else if (test_bit(bucket, &napi->gro_bitmask)) { - __clear_bit(bucket, &napi->gro_bitmask); - } - - return ret; - -normal: - ret = GRO_NORMAL; - goto pull; -} - -struct packet_offload *gro_find_receive_by_type(__be16 type) -{ - struct list_head *offload_head = &offload_base; - struct packet_offload *ptype; - - list_for_each_entry_rcu(ptype, offload_head, list) { - if (ptype->type != type || !ptype->callbacks.gro_receive) - continue; - return ptype; - } - return NULL; -} -EXPORT_SYMBOL(gro_find_receive_by_type); - -struct packet_offload *gro_find_complete_by_type(__be16 type) -{ - struct list_head *offload_head = &offload_base; - struct packet_offload *ptype; - - list_for_each_entry_rcu(ptype, offload_head, list) { - if (ptype->type != type || !ptype->callbacks.gro_complete) - continue; - return ptype; - } - return NULL; -} -EXPORT_SYMBOL(gro_find_complete_by_type); - -static gro_result_t napi_skb_finish(struct napi_struct *napi, - struct sk_buff *skb, - gro_result_t ret) -{ - switch (ret) { - case GRO_NORMAL: - gro_normal_one(napi, skb, 1); - break; - - case GRO_MERGED_FREE: - if (NAPI_GRO_CB(skb)->free == NAPI_GRO_FREE_STOLEN_HEAD) - napi_skb_free_stolen_head(skb); - else if (skb->fclone != SKB_FCLONE_UNAVAILABLE) - __kfree_skb(skb); - else - __kfree_skb_defer(skb); - break; - - case GRO_HELD: - case GRO_MERGED: - case GRO_CONSUMED: - break; - } - - return ret; -} - -gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb) -{ - gro_result_t ret; - - skb_mark_napi_id(skb, napi); - trace_napi_gro_receive_entry(skb); - - skb_gro_reset_offset(skb, 0); - - ret = napi_skb_finish(napi, skb, dev_gro_receive(napi, skb)); - trace_napi_gro_receive_exit(ret); - - return ret; -} -EXPORT_SYMBOL(napi_gro_receive); - -static void napi_reuse_skb(struct napi_struct *napi, struct sk_buff *skb) -{ - if (unlikely(skb->pfmemalloc)) { - consume_skb(skb); - return; - } - __skb_pull(skb, skb_headlen(skb)); - /* restore the reserve we had after netdev_alloc_skb_ip_align() */ - skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN - skb_headroom(skb)); - __vlan_hwaccel_clear_tag(skb); - skb->dev = napi->dev; - skb->skb_iif = 0; - - /* eth_type_trans() assumes pkt_type is PACKET_HOST */ - skb->pkt_type = PACKET_HOST; - - skb->encapsulation = 0; - skb_shinfo(skb)->gso_type = 0; - skb->truesize = SKB_TRUESIZE(skb_end_offset(skb)); - if (unlikely(skb->slow_gro)) { - skb_orphan(skb); - skb_ext_reset(skb); - nf_reset_ct(skb); - skb->slow_gro = 0; - } - - napi->skb = skb; -} - -struct sk_buff *napi_get_frags(struct napi_struct *napi) -{ - struct sk_buff *skb = napi->skb; - - if (!skb) { - skb = napi_alloc_skb(napi, GRO_MAX_HEAD); - if (skb) { - napi->skb = skb; - skb_mark_napi_id(skb, napi); - } - } - return skb; -} -EXPORT_SYMBOL(napi_get_frags); - -static gro_result_t napi_frags_finish(struct napi_struct *napi, - struct sk_buff *skb, - gro_result_t ret) -{ - switch (ret) { - case GRO_NORMAL: - case GRO_HELD: - __skb_push(skb, ETH_HLEN); - skb->protocol = eth_type_trans(skb, skb->dev); - if (ret == GRO_NORMAL) - gro_normal_one(napi, skb, 1); - break; - - case GRO_MERGED_FREE: - if (NAPI_GRO_CB(skb)->free == NAPI_GRO_FREE_STOLEN_HEAD) - napi_skb_free_stolen_head(skb); - else - napi_reuse_skb(napi, skb); - break; - - case GRO_MERGED: - case GRO_CONSUMED: - break; - } - - return ret; -} - -/* Upper GRO stack assumes network header starts at gro_offset=0 - * Drivers could call both napi_gro_frags() and napi_gro_receive() - * We copy ethernet header into skb->data to have a common layout. - */ -static struct sk_buff *napi_frags_skb(struct napi_struct *napi) -{ - struct sk_buff *skb = napi->skb; - const struct ethhdr *eth; - unsigned int hlen = sizeof(*eth); - - napi->skb = NULL; - - skb_reset_mac_header(skb); - skb_gro_reset_offset(skb, hlen); - - if (unlikely(skb_gro_header_hard(skb, hlen))) { - eth = skb_gro_header_slow(skb, hlen, 0); - if (unlikely(!eth)) { - net_warn_ratelimited("%s: dropping impossible skb from %s\n", - __func__, napi->dev->name); - napi_reuse_skb(napi, skb); - return NULL; - } - } else { - eth = (const struct ethhdr *)skb->data; - gro_pull_from_frag0(skb, hlen); - NAPI_GRO_CB(skb)->frag0 += hlen; - NAPI_GRO_CB(skb)->frag0_len -= hlen; - } - __skb_pull(skb, hlen); - - /* - * This works because the only protocols we care about don't require - * special handling. - * We'll fix it up properly in napi_frags_finish() - */ - skb->protocol = eth->h_proto; - - return skb; -} - -gro_result_t napi_gro_frags(struct napi_struct *napi) -{ - gro_result_t ret; - struct sk_buff *skb = napi_frags_skb(napi); - - trace_napi_gro_frags_entry(skb); - - ret = napi_frags_finish(napi, skb, dev_gro_receive(napi, skb)); - trace_napi_gro_frags_exit(ret); - - return ret; -} -EXPORT_SYMBOL(napi_gro_frags); - -/* Compute the checksum from gro_offset and return the folded value - * after adding in any pseudo checksum. - */ -__sum16 __skb_gro_checksum_complete(struct sk_buff *skb) -{ - __wsum wsum; - __sum16 sum; - - wsum = skb_checksum(skb, skb_gro_offset(skb), skb_gro_len(skb), 0); - - /* NAPI_GRO_CB(skb)->csum holds pseudo checksum */ - sum = csum_fold(csum_add(NAPI_GRO_CB(skb)->csum, wsum)); - /* See comments in __skb_checksum_complete(). */ - if (likely(!sum)) { - if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE) && - !skb->csum_complete_sw) - netdev_rx_csum_fault(skb->dev, skb); - } - - NAPI_GRO_CB(skb)->csum = wsum; - NAPI_GRO_CB(skb)->csum_valid = 1; - - return sum; -} -EXPORT_SYMBOL(__skb_gro_checksum_complete); - static void net_rps_send_ipi(struct softnet_data *remsd) { #ifdef CONFIG_RPS @@ -11640,8 +10976,6 @@ static int __init net_dev_init(void) for (i = 0; i < PTYPE_HASH_SIZE; i++) INIT_LIST_HEAD(&ptype_base[i]); - INIT_LIST_HEAD(&offload_base); - if (register_pernet_subsys(&netdev_net_ops)) goto out; diff --git a/net/core/gro.c b/net/core/gro.c new file mode 100644 index 000000000000..8ec8b44596da --- /dev/null +++ b/net/core/gro.c @@ -0,0 +1,766 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +#include <net/gro.h> +#include <net/dst_metadata.h> +#include <net/busy_poll.h> +#include <trace/events/net.h> + +#define MAX_GRO_SKBS 8 + +/* This should be increased if a protocol with a bigger head is added. */ +#define GRO_MAX_HEAD (MAX_HEADER + 128) + +static DEFINE_SPINLOCK(offload_lock); +static struct list_head offload_base __read_mostly = LIST_HEAD_INIT(offload_base); +/* Maximum number of GRO_NORMAL skbs to batch up for list-RX */ +int gro_normal_batch __read_mostly = 8; + +/** + * dev_add_offload - register offload handlers + * @po: protocol offload declaration + * + * Add protocol offload handlers to the networking stack. The passed + * &proto_offload is linked into kernel lists and may not be freed until + * it has been removed from the kernel lists. + * + * This call does not sleep therefore it can not + * guarantee all CPU's that are in middle of receiving packets + * will see the new offload handlers (until the next received packet). + */ +void dev_add_offload(struct packet_offload *po) +{ + struct packet_offload *elem; + + spin_lock(&offload_lock); + list_for_each_entry(elem, &offload_base, list) { + if (po->priority < elem->priority) + break; + } + list_add_rcu(&po->list, elem->list.prev); + spin_unlock(&offload_lock); +} +EXPORT_SYMBOL(dev_add_offload); + +/** + * __dev_remove_offload - remove offload handler + * @po: packet offload declaration + * + * Remove a protocol offload handler that was previously added to the + * kernel offload handlers by dev_add_offload(). The passed &offload_type + * is removed from the kernel lists and can be freed or reused once this + * function returns. + * + * The packet type might still be in use by receivers + * and must not be freed until after all the CPU's have gone + * through a quiescent state. + */ +static void __dev_remove_offload(struct packet_offload *po) +{ + struct list_head *head = &offload_base; + struct packet_offload *po1; + + spin_lock(&offload_lock); + + list_for_each_entry(po1, head, list) { + if (po == po1) { + list_del_rcu(&po->list); + goto out; + } + } + + pr_warn("dev_remove_offload: %p not found\n", po); +out: + spin_unlock(&offload_lock); +} + +/** + * dev_remove_offload - remove packet offload handler + * @po: packet offload declaration + * + * Remove a packet offload handler that was previously added to the kernel + * offload handlers by dev_add_offload(). The passed &offload_type is + * removed from the kernel lists and can be freed or reused once this + * function returns. + * + * This call sleeps to guarantee that no CPU is looking at the packet + * type after return. + */ +void dev_remove_offload(struct packet_offload *po) +{ + __dev_remove_offload(po); + + synchronize_net(); +} +EXPORT_SYMBOL(dev_remove_offload); + +/** + * skb_mac_gso_segment - mac layer segmentation handler. + * @skb: buffer to segment + * @features: features for the output path (see dev->features) + */ +struct sk_buff *skb_mac_gso_segment(struct sk_buff *skb, + netdev_features_t features) +{ + struct sk_buff *segs = ERR_PTR(-EPROTONOSUPPORT); + struct packet_offload *ptype; + int vlan_depth = skb->mac_len; + __be16 type = skb_network_protocol(skb, &vlan_depth); + + if (unlikely(!type)) + return ERR_PTR(-EINVAL); + + __skb_pull(skb, vlan_depth); + + rcu_read_lock(); + list_for_each_entry_rcu(ptype, &offload_base, list) { + if (ptype->type == type && ptype->callbacks.gso_segment) { + segs = ptype->callbacks.gso_segment(skb, features); + break; + } + } + rcu_read_unlock(); + + __skb_push(skb, skb->data - skb_mac_header(skb)); + + return segs; +} +EXPORT_SYMBOL(skb_mac_gso_segment); + +int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb) +{ + struct skb_shared_info *pinfo, *skbinfo = skb_shinfo(skb); + unsigned int offset = skb_gro_offset(skb); + unsigned int headlen = skb_headlen(skb); + unsigned int len = skb_gro_len(skb); + unsigned int delta_truesize; + unsigned int new_truesize; + struct sk_buff *lp; + + if (unlikely(p->len + len >= 65536 || NAPI_GRO_CB(skb)->flush)) + return -E2BIG; + + lp = NAPI_GRO_CB(p)->last; + pinfo = skb_shinfo(lp); + + if (headlen <= offset) { + skb_frag_t *frag; + skb_frag_t *frag2; + int i = skbinfo->nr_frags; + int nr_frags = pinfo->nr_frags + i; + + if (nr_frags > MAX_SKB_FRAGS) + goto merge; + + offset -= headlen; + pinfo->nr_frags = nr_frags; + skbinfo->nr_frags = 0; + + frag = pinfo->frags + nr_frags; + frag2 = skbinfo->frags + i; + do { + *--frag = *--frag2; + } while (--i); + + skb_frag_off_add(frag, offset); + skb_frag_size_sub(frag, offset); + + /* all fragments truesize : remove (head size + sk_buff) */ + new_truesize = SKB_TRUESIZE(skb_end_offset(skb)); + delta_truesize = skb->truesize - new_truesize; + + skb->truesize = new_truesize; + skb->len -= skb->data_len; + skb->data_len = 0; + + NAPI_GRO_CB(skb)->free = NAPI_GRO_FREE; + goto done; + } else if (skb->head_frag) { + int nr_frags = pinfo->nr_frags; + skb_frag_t *frag = pinfo->frags + nr_frags; + struct page *page = virt_to_head_page(skb->head); + unsigned int first_size = headlen - offset; + unsigned int first_offset; + + if (nr_frags + 1 + skbinfo->nr_frags > MAX_SKB_FRAGS) + goto merge; + + first_offset = skb->data - + (unsigned char *)page_address(page) + + offset; + + pinfo->nr_frags = nr_frags + 1 + skbinfo->nr_frags; + + __skb_frag_set_page(frag, page); + skb_frag_off_set(frag, first_offset); + skb_frag_size_set(frag, first_size); + + memcpy(frag + 1, skbinfo->frags, sizeof(*frag) * skbinfo->nr_frags); + /* We dont need to clear skbinfo->nr_frags here */ + + new_truesize = SKB_DATA_ALIGN(sizeof(struct sk_buff)); + delta_truesize = skb->truesize - new_truesize; + skb->truesize = new_truesize; + NAPI_GRO_CB(skb)->free = NAPI_GRO_FREE_STOLEN_HEAD; + goto done; + } + +merge: + /* sk owenrship - if any - completely transferred to the aggregated packet */ + skb->destructor = NULL; + delta_truesize = skb->truesize; + if (offset > headlen) { + unsigned int eat = offset - headlen; + + skb_frag_off_add(&skbinfo->frags[0], eat); + skb_frag_size_sub(&skbinfo->frags[0], eat); + skb->data_len -= eat; + skb->len -= eat; + offset = headlen; + } + + __skb_pull(skb, offset); + + if (NAPI_GRO_CB(p)->last == p) + skb_shinfo(p)->frag_list = skb; + else + NAPI_GRO_CB(p)->last->next = skb; + NAPI_GRO_CB(p)->last = skb; + __skb_header_release(skb); + lp = p; + +done: + NAPI_GRO_CB(p)->count++; + p->data_len += len; + p->truesize += delta_truesize; + p->len += len; + if (lp != p) { + lp->data_len += len; + lp->truesize += delta_truesize; + lp->len += len; + } + NAPI_GRO_CB(skb)->same_flow = 1; + return 0; +} + + +static void napi_gro_complete(struct napi_struct *napi, struct sk_buff *skb) +{ + struct packet_offload *ptype; + __be16 type = skb->protocol; + struct list_head *head = &offload_base; + int err = -ENOENT; + + BUILD_BUG_ON(sizeof(struct napi_gro_cb) > sizeof(skb->cb)); + + if (NAPI_GRO_CB(skb)->count == 1) { + skb_shinfo(skb)->gso_size = 0; + goto out; + } + + rcu_read_lock(); + list_for_each_entry_rcu(ptype, head, list) { + if (ptype->type != type || !ptype->callbacks.gro_complete) + continue; + + err = INDIRECT_CALL_INET(ptype->callbacks.gro_complete, + ipv6_gro_complete, inet_gro_complete, + skb, 0); + break; + } + rcu_read_unlock(); + + if (err) { + WARN_ON(&ptype->list == head); + kfree_skb(skb); + return; + } + +out: + gro_normal_one(napi, skb, NAPI_GRO_CB(skb)->count); +} + +static void __napi_gro_flush_chain(struct napi_struct *napi, u32 index, + bool flush_old) +{ + struct list_head *head = &napi->gro_hash[index].list; + struct sk_buff *skb, *p; + + list_for_each_entry_safe_reverse(skb, p, head, list) { + if (flush_old && NAPI_GRO_CB(skb)->age == jiffies) + return; + skb_list_del_init(skb); + napi_gro_complete(napi, skb); + napi->gro_hash[index].count--; + } + + if (!napi->gro_hash[index].count) + __clear_bit(index, &napi->gro_bitmask); +} + +/* napi->gro_hash[].list contains packets ordered by age. + * youngest packets at the head of it. + * Complete skbs in reverse order to reduce latencies. + */ +void napi_gro_flush(struct napi_struct *napi, bool flush_old) +{ + unsigned long bitmask = napi->gro_bitmask; + unsigned int i, base = ~0U; + + while ((i = ffs(bitmask)) != 0) { + bitmask >>= i; + base += i; + __napi_gro_flush_chain(napi, base, flush_old); + } +} +EXPORT_SYMBOL(napi_gro_flush); + +static void gro_list_prepare(const struct list_head *head, + const struct sk_buff *skb) +{ + unsigned int maclen = skb->dev->hard_header_len; + u32 hash = skb_get_hash_raw(skb); + struct sk_buff *p; + + list_for_each_entry(p, head, list) { + unsigned long diffs; + + NAPI_GRO_CB(p)->flush = 0; + + if (hash != skb_get_hash_raw(p)) { + NAPI_GRO_CB(p)->same_flow = 0; + continue; + } + + diffs = (unsigned long)p->dev ^ (unsigned long)skb->dev; + diffs |= skb_vlan_tag_present(p) ^ skb_vlan_tag_present(skb); + if (skb_vlan_tag_present(p)) + diffs |= skb_vlan_tag_get(p) ^ skb_vlan_tag_get(skb); + diffs |= skb_metadata_differs(p, skb); + if (maclen == ETH_HLEN) + diffs |= compare_ether_header(skb_mac_header(p), + skb_mac_header(skb)); + else if (!diffs) + diffs = memcmp(skb_mac_header(p), + skb_mac_header(skb), + maclen); + + /* in most common scenarions 'slow_gro' is 0 + * otherwise we are already on some slower paths + * either skip all the infrequent tests altogether or + * avoid trying too hard to skip each of them individually + */ + if (!diffs && unlikely(skb->slow_gro | p->slow_gro)) { +#if IS_ENABLED(CONFIG_SKB_EXTENSIONS) && IS_ENABLED(CONFIG_NET_TC_SKB_EXT) + struct tc_skb_ext *skb_ext; + struct tc_skb_ext *p_ext; +#endif + + diffs |= p->sk != skb->sk; + diffs |= skb_metadata_dst_cmp(p, skb); + diffs |= skb_get_nfct(p) ^ skb_get_nfct(skb); + +#if IS_ENABLED(CONFIG_SKB_EXTENSIONS) && IS_ENABLED(CONFIG_NET_TC_SKB_EXT) + skb_ext = skb_ext_find(skb, TC_SKB_EXT); + p_ext = skb_ext_find(p, TC_SKB_EXT); + + diffs |= (!!p_ext) ^ (!!skb_ext); + if (!diffs && unlikely(skb_ext)) + diffs |= p_ext->chain ^ skb_ext->chain; +#endif + } + + NAPI_GRO_CB(p)->same_flow = !diffs; + } +} + +static inline void skb_gro_reset_offset(struct sk_buff *skb, u32 nhoff) +{ + const struct skb_shared_info *pinfo = skb_shinfo(skb); + const skb_frag_t *frag0 = &pinfo->frags[0]; + + NAPI_GRO_CB(skb)->data_offset = 0; + NAPI_GRO_CB(skb)->frag0 = NULL; + NAPI_GRO_CB(skb)->frag0_len = 0; + + if (!skb_headlen(skb) && pinfo->nr_frags && + !PageHighMem(skb_frag_page(frag0)) && + (!NET_IP_ALIGN || !((skb_frag_off(frag0) + nhoff) & 3))) { + NAPI_GRO_CB(skb)->frag0 = skb_frag_address(frag0); + NAPI_GRO_CB(skb)->frag0_len = min_t(unsigned int, + skb_frag_size(frag0), + skb->end - skb->tail); + } +} + +static void gro_pull_from_frag0(struct sk_buff *skb, int grow) +{ + struct skb_shared_info *pinfo = skb_shinfo(skb); + + BUG_ON(skb->end - skb->tail < grow); + + memcpy(skb_tail_pointer(skb), NAPI_GRO_CB(skb)->frag0, grow); + + skb->data_len -= grow; + skb->tail += grow; + + skb_frag_off_add(&pinfo->frags[0], grow); + skb_frag_size_sub(&pinfo->frags[0], grow); + + if (unlikely(!skb_frag_size(&pinfo->frags[0]))) { + skb_frag_unref(skb, 0); + memmove(pinfo->frags, pinfo->frags + 1, + --pinfo->nr_frags * sizeof(pinfo->frags[0])); + } +} + +static void gro_flush_oldest(struct napi_struct *napi, struct list_head *head) +{ + struct sk_buff *oldest; + + oldest = list_last_entry(head, struct sk_buff, list); + + /* We are called with head length >= MAX_GRO_SKBS, so this is + * impossible. + */ + if (WARN_ON_ONCE(!oldest)) + return; + + /* Do not adjust napi->gro_hash[].count, caller is adding a new + * SKB to the chain. + */ + skb_list_del_init(oldest); + napi_gro_complete(napi, oldest); +} + +static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb) +{ + u32 bucket = skb_get_hash_raw(skb) & (GRO_HASH_BUCKETS - 1); + struct gro_list *gro_list = &napi->gro_hash[bucket]; + struct list_head *head = &offload_base; + struct packet_offload *ptype; + __be16 type = skb->protocol; + struct sk_buff *pp = NULL; + enum gro_result ret; + int same_flow; + int grow; + + if (netif_elide_gro(skb->dev)) + goto normal; + + gro_list_prepare(&gro_list->list, skb); + + rcu_read_lock(); + list_for_each_entry_rcu(ptype, head, list) { + if (ptype->type != type || !ptype->callbacks.gro_receive) + continue; + + skb_set_network_header(skb, skb_gro_offset(skb)); + skb_reset_mac_len(skb); + NAPI_GRO_CB(skb)->same_flow = 0; + NAPI_GRO_CB(skb)->flush = skb_is_gso(skb) || skb_has_frag_list(skb); + NAPI_GRO_CB(skb)->free = 0; + NAPI_GRO_CB(skb)->encap_mark = 0; + NAPI_GRO_CB(skb)->recursion_counter = 0; + NAPI_GRO_CB(skb)->is_fou = 0; + NAPI_GRO_CB(skb)->is_atomic = 1; + NAPI_GRO_CB(skb)->gro_remcsum_start = 0; + + /* Setup for GRO checksum validation */ + switch (skb->ip_summed) { + case CHECKSUM_COMPLETE: + NAPI_GRO_CB(skb)->csum = skb->csum; + NAPI_GRO_CB(skb)->csum_valid = 1; + NAPI_GRO_CB(skb)->csum_cnt = 0; + break; + case CHECKSUM_UNNECESSARY: + NAPI_GRO_CB(skb)->csum_cnt = skb->csum_level + 1; + NAPI_GRO_CB(skb)->csum_valid = 0; + break; + default: + NAPI_GRO_CB(skb)->csum_cnt = 0; + NAPI_GRO_CB(skb)->csum_valid = 0; + } + + pp = INDIRECT_CALL_INET(ptype->callbacks.gro_receive, + ipv6_gro_receive, inet_gro_receive, + &gro_list->list, skb); + break; + } + rcu_read_unlock(); + + if (&ptype->list == head) + goto normal; + + if (PTR_ERR(pp) == -EINPROGRESS) { + ret = GRO_CONSUMED; + goto ok; + } + + same_flow = NAPI_GRO_CB(skb)->same_flow; + ret = NAPI_GRO_CB(skb)->free ? GRO_MERGED_FREE : GRO_MERGED; + + if (pp) { + skb_list_del_init(pp); + napi_gro_complete(napi, pp); + gro_list->count--; + } + + if (same_flow) + goto ok; + + if (NAPI_GRO_CB(skb)->flush) + goto normal; + + if (unlikely(gro_list->count >= MAX_GRO_SKBS)) + gro_flush_oldest(napi, &gro_list->list); + else + gro_list->count++; + + NAPI_GRO_CB(skb)->count = 1; + NAPI_GRO_CB(skb)->age = jiffies; + NAPI_GRO_CB(skb)->last = skb; + skb_shinfo(skb)->gso_size = skb_gro_len(skb); + list_add(&skb->list, &gro_list->list); + ret = GRO_HELD; + +pull: + grow = skb_gro_offset(skb) - skb_headlen(skb); + if (grow > 0) + gro_pull_from_frag0(skb, grow); +ok: + if (gro_list->count) { + if (!test_bit(bucket, &napi->gro_bitmask)) + __set_bit(bucket, &napi->gro_bitmask); + } else if (test_bit(bucket, &napi->gro_bitmask)) { + __clear_bit(bucket, &napi->gro_bitmask); + } + + return ret; + +normal: + ret = GRO_NORMAL; + goto pull; +} + +struct packet_offload *gro_find_receive_by_type(__be16 type) +{ + struct list_head *offload_head = &offload_base; + struct packet_offload *ptype; + + list_for_each_entry_rcu(ptype, offload_head, list) { + if (ptype->type != type || !ptype->callbacks.gro_receive) + continue; + return ptype; + } + return NULL; +} +EXPORT_SYMBOL(gro_find_receive_by_type); + +struct packet_offload *gro_find_complete_by_type(__be16 type) +{ + struct list_head *offload_head = &offload_base; + struct packet_offload *ptype; + + list_for_each_entry_rcu(ptype, offload_head, list) { + if (ptype->type != type || !ptype->callbacks.gro_complete) + continue; + return ptype; + } + return NULL; +} +EXPORT_SYMBOL(gro_find_complete_by_type); + +static gro_result_t napi_skb_finish(struct napi_struct *napi, + struct sk_buff *skb, + gro_result_t ret) +{ + switch (ret) { + case GRO_NORMAL: + gro_normal_one(napi, skb, 1); + break; + + case GRO_MERGED_FREE: + if (NAPI_GRO_CB(skb)->free == NAPI_GRO_FREE_STOLEN_HEAD) + napi_skb_free_stolen_head(skb); + else if (skb->fclone != SKB_FCLONE_UNAVAILABLE) + __kfree_skb(skb); + else + __kfree_skb_defer(skb); + break; + + case GRO_HELD: + case GRO_MERGED: + case GRO_CONSUMED: + break; + } + + return ret; +} + +gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb) +{ + gro_result_t ret; + + skb_mark_napi_id(skb, napi); + trace_napi_gro_receive_entry(skb); + + skb_gro_reset_offset(skb, 0); + + ret = napi_skb_finish(napi, skb, dev_gro_receive(napi, skb)); + trace_napi_gro_receive_exit(ret); + + return ret; +} +EXPORT_SYMBOL(napi_gro_receive); + +static void napi_reuse_skb(struct napi_struct *napi, struct sk_buff *skb) +{ + if (unlikely(skb->pfmemalloc)) { + consume_skb(skb); + return; + } + __skb_pull(skb, skb_headlen(skb)); + /* restore the reserve we had after netdev_alloc_skb_ip_align() */ + skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN - skb_headroom(skb)); + __vlan_hwaccel_clear_tag(skb); + skb->dev = napi->dev; + skb->skb_iif = 0; + + /* eth_type_trans() assumes pkt_type is PACKET_HOST */ + skb->pkt_type = PACKET_HOST; + + skb->encapsulation = 0; + skb_shinfo(skb)->gso_type = 0; + skb->truesize = SKB_TRUESIZE(skb_end_offset(skb)); + if (unlikely(skb->slow_gro)) { + skb_orphan(skb); + skb_ext_reset(skb); + nf_reset_ct(skb); + skb->slow_gro = 0; + } + + napi->skb = skb; +} + +struct sk_buff *napi_get_frags(struct napi_struct *napi) +{ + struct sk_buff *skb = napi->skb; + + if (!skb) { + skb = napi_alloc_skb(napi, GRO_MAX_HEAD); + if (skb) { + napi->skb = skb; + skb_mark_napi_id(skb, napi); + } + } + return skb; +} +EXPORT_SYMBOL(napi_get_frags); + +static gro_result_t napi_frags_finish(struct napi_struct *napi, + struct sk_buff *skb, + gro_result_t ret) +{ + switch (ret) { + case GRO_NORMAL: + case GRO_HELD: + __skb_push(skb, ETH_HLEN); + skb->protocol = eth_type_trans(skb, skb->dev); + if (ret == GRO_NORMAL) + gro_normal_one(napi, skb, 1); + break; + + case GRO_MERGED_FREE: + if (NAPI_GRO_CB(skb)->free == NAPI_GRO_FREE_STOLEN_HEAD) + napi_skb_free_stolen_head(skb); + else + napi_reuse_skb(napi, skb); + break; + + case GRO_MERGED: + case GRO_CONSUMED: + break; + } + + return ret; +} + +/* Upper GRO stack assumes network header starts at gro_offset=0 + * Drivers could call both napi_gro_frags() and napi_gro_receive() + * We copy ethernet header into skb->data to have a common layout. + */ +static struct sk_buff *napi_frags_skb(struct napi_struct *napi) +{ + struct sk_buff *skb = napi->skb; + const struct ethhdr *eth; + unsigned int hlen = sizeof(*eth); + + napi->skb = NULL; + + skb_reset_mac_header(skb); + skb_gro_reset_offset(skb, hlen); + + if (unlikely(skb_gro_header_hard(skb, hlen))) { + eth = skb_gro_header_slow(skb, hlen, 0); + if (unlikely(!eth)) { + net_warn_ratelimited("%s: dropping impossible skb from %s\n", + __func__, napi->dev->name); + napi_reuse_skb(napi, skb); + return NULL; + } + } else { + eth = (const struct ethhdr *)skb->data; + gro_pull_from_frag0(skb, hlen); + NAPI_GRO_CB(skb)->frag0 += hlen; + NAPI_GRO_CB(skb)->frag0_len -= hlen; + } + __skb_pull(skb, hlen); + + /* + * This works because the only protocols we care about don't require + * special handling. + * We'll fix it up properly in napi_frags_finish() + */ + skb->protocol = eth->h_proto; + + return skb; +} + +gro_result_t napi_gro_frags(struct napi_struct *napi) +{ + gro_result_t ret; + struct sk_buff *skb = napi_frags_skb(napi); + + trace_napi_gro_frags_entry(skb); + + ret = napi_frags_finish(napi, skb, dev_gro_receive(napi, skb)); + trace_napi_gro_frags_exit(ret); + + return ret; +} +EXPORT_SYMBOL(napi_gro_frags); + +/* Compute the checksum from gro_offset and return the folded value + * after adding in any pseudo checksum. + */ +__sum16 __skb_gro_checksum_complete(struct sk_buff *skb) +{ + __wsum wsum; + __sum16 sum; + + wsum = skb_checksum(skb, skb_gro_offset(skb), skb_gro_len(skb), 0); + + /* NAPI_GRO_CB(skb)->csum holds pseudo checksum */ + sum = csum_fold(csum_add(NAPI_GRO_CB(skb)->csum, wsum)); + /* See comments in __skb_checksum_complete(). */ + if (likely(!sum)) { + if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE) && + !skb->csum_complete_sw) + netdev_rx_csum_fault(skb->dev, skb); + } + + NAPI_GRO_CB(skb)->csum = wsum; + NAPI_GRO_CB(skb)->csum_valid = 1; + + return sum; +} +EXPORT_SYMBOL(__skb_gro_checksum_complete); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index d57796f38a0b..73720bc1daa3 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -3919,32 +3919,6 @@ err_linearize: } EXPORT_SYMBOL_GPL(skb_segment_list); -int skb_gro_receive_list(struct sk_buff *p, struct sk_buff *skb) -{ - if (unlikely(p->len + skb->len >= 65536)) - return -E2BIG; - - if (NAPI_GRO_CB(p)->last == p) - skb_shinfo(p)->frag_list = skb; - else - NAPI_GRO_CB(p)->last->next = skb; - - skb_pull(skb, skb_gro_offset(skb)); - - NAPI_GRO_CB(p)->last = skb; - NAPI_GRO_CB(p)->count++; - p->data_len += skb->len; - - /* sk owenrship - if any - completely transferred to the aggregated packet */ - skb->destructor = NULL; - p->truesize += skb->truesize; - p->len += skb->len; - - NAPI_GRO_CB(skb)->same_flow = 1; - - return 0; -} - /** * skb_segment - Perform protocol segmentation on skb. * @head_skb: buffer to segment @@ -4297,122 +4271,6 @@ err: } EXPORT_SYMBOL_GPL(skb_segment); -int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb) -{ - struct skb_shared_info *pinfo, *skbinfo = skb_shinfo(skb); - unsigned int offset = skb_gro_offset(skb); - unsigned int headlen = skb_headlen(skb); - unsigned int len = skb_gro_len(skb); - unsigned int delta_truesize; - unsigned int new_truesize; - struct sk_buff *lp; - - if (unlikely(p->len + len >= 65536 || NAPI_GRO_CB(skb)->flush)) - return -E2BIG; - - lp = NAPI_GRO_CB(p)->last; - pinfo = skb_shinfo(lp); - - if (headlen <= offset) { - skb_frag_t *frag; - skb_frag_t *frag2; - int i = skbinfo->nr_frags; - int nr_frags = pinfo->nr_frags + i; - - if (nr_frags > MAX_SKB_FRAGS) - goto merge; - - offset -= headlen; - pinfo->nr_frags = nr_frags; - skbinfo->nr_frags = 0; - - frag = pinfo->frags + nr_frags; - frag2 = skbinfo->frags + i; - do { - *--frag = *--frag2; - } while (--i); - - skb_frag_off_add(frag, offset); - skb_frag_size_sub(frag, offset); - - /* all fragments truesize : remove (head size + sk_buff) */ - new_truesize = SKB_TRUESIZE(skb_end_offset(skb)); - delta_truesize = skb->truesize - new_truesize; - - skb->truesize = new_truesize; - skb->len -= skb->data_len; - skb->data_len = 0; - - NAPI_GRO_CB(skb)->free = NAPI_GRO_FREE; - goto done; - } else if (skb->head_frag) { - int nr_frags = pinfo->nr_frags; - skb_frag_t *frag = pinfo->frags + nr_frags; - struct page *page = virt_to_head_page(skb->head); - unsigned int first_size = headlen - offset; - unsigned int first_offset; - - if (nr_frags + 1 + skbinfo->nr_frags > MAX_SKB_FRAGS) - goto merge; - - first_offset = skb->data - - (unsigned char *)page_address(page) + - offset; - - pinfo->nr_frags = nr_frags + 1 + skbinfo->nr_frags; - - __skb_frag_set_page(frag, page); - skb_frag_off_set(frag, first_offset); - skb_frag_size_set(frag, first_size); - - memcpy(frag + 1, skbinfo->frags, sizeof(*frag) * skbinfo->nr_frags); - /* We dont need to clear skbinfo->nr_frags here */ - - new_truesize = SKB_DATA_ALIGN(sizeof(struct sk_buff)); - delta_truesize = skb->truesize - new_truesize; - skb->truesize = new_truesize; - NAPI_GRO_CB(skb)->free = NAPI_GRO_FREE_STOLEN_HEAD; - goto done; - } - -merge: - /* sk owenrship - if any - completely transferred to the aggregated packet */ - skb->destructor = NULL; - delta_truesize = skb->truesize; - if (offset > headlen) { - unsigned int eat = offset - headlen; - - skb_frag_off_add(&skbinfo->frags[0], eat); - skb_frag_size_sub(&skbinfo->frags[0], eat); - skb->data_len -= eat; - skb->len -= eat; - offset = headlen; - } - - __skb_pull(skb, offset); - - if (NAPI_GRO_CB(p)->last == p) - skb_shinfo(p)->frag_list = skb; - else - NAPI_GRO_CB(p)->last->next = skb; - NAPI_GRO_CB(p)->last = skb; - __skb_header_release(skb); - lp = p; - -done: - NAPI_GRO_CB(p)->count++; - p->data_len += len; - p->truesize += delta_truesize; - p->len += len; - if (lp != p) { - lp->data_len += len; - lp->truesize += delta_truesize; - lp->len += len; - } - NAPI_GRO_CB(skb)->same_flow = 1; - return 0; -} - #ifdef CONFIG_SKB_EXTENSIONS #define SKB_EXT_ALIGN_VALUE 8 #define SKB_EXT_CHUNKSIZEOF(x) (ALIGN((sizeof(x)), SKB_EXT_ALIGN_VALUE) / SKB_EXT_ALIGN_VALUE) diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 0189e3cd4a7d..6d52b6491255 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -99,6 +99,7 @@ #include <net/route.h> #include <net/ip_fib.h> #include <net/inet_connection_sock.h> +#include <net/gro.h> #include <net/tcp.h> #include <net/udp.h> #include <net/udplite.h> diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c index 8e4e9aa12130..d87f02a6e934 100644 --- a/net/ipv4/esp4_offload.c +++ b/net/ipv4/esp4_offload.c @@ -16,6 +16,7 @@ #include <crypto/authenc.h> #include <linux/err.h> #include <linux/module.h> +#include <net/gro.h> #include <net/ip.h> #include <net/xfrm.h> #include <net/esp.h> diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c index 8fcbc6258ec5..b56d6b40c0a2 100644 --- a/net/ipv4/fou.c +++ b/net/ipv4/fou.c @@ -9,6 +9,7 @@ #include <linux/types.h> #include <linux/kernel.h> #include <net/genetlink.h> +#include <net/gro.h> #include <net/gue.h> #include <net/fou.h> #include <net/ip.h> diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c index 1121a9d5fed9..740298dac7d3 100644 --- a/net/ipv4/gre_offload.c +++ b/net/ipv4/gre_offload.c @@ -10,6 +10,7 @@ #include <linux/init.h> #include <net/protocol.h> #include <net/gre.h> +#include <net/gro.h> static struct sk_buff *gre_gso_segment(struct sk_buff *skb, netdev_features_t features) diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c index fc61cd3fea65..30abde86db45 100644 --- a/net/ipv4/tcp_offload.c +++ b/net/ipv4/tcp_offload.c @@ -8,6 +8,7 @@ #include <linux/indirect_call_wrapper.h> #include <linux/skbuff.h> +#include <net/gro.h> #include <net/tcp.h> #include <net/protocol.h> diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index 86d32a1e62ac..cbeb8965d1b7 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -7,6 +7,7 @@ */ #include <linux/skbuff.h> +#include <net/gro.h> #include <net/udp.h> #include <net/protocol.h> #include <net/inet_common.h> @@ -424,6 +425,33 @@ out: return segs; } +static int skb_gro_receive_list(struct sk_buff *p, struct sk_buff *skb) +{ + if (unlikely(p->len + skb->len >= 65536)) + return -E2BIG; + + if (NAPI_GRO_CB(p)->last == p) + skb_shinfo(p)->frag_list = skb; + else + NAPI_GRO_CB(p)->last->next = skb; + + skb_pull(skb, skb_gro_offset(skb)); + + NAPI_GRO_CB(p)->last = skb; + NAPI_GRO_CB(p)->count++; + p->data_len += skb->len; + + /* sk owenrship - if any - completely transferred to the aggregated packet */ + skb->destructor = NULL; + p->truesize += skb->truesize; + p->len += skb->len; + + NAPI_GRO_CB(skb)->same_flow = 1; + + return 0; +} + + #define UDP_GRO_CNT_MAX 64 static struct sk_buff *udp_gro_receive_segment(struct list_head *head, struct sk_buff *skb) diff --git a/net/ipv6/esp6_offload.c b/net/ipv6/esp6_offload.c index a349d4798077..ba5e81cd569c 100644 --- a/net/ipv6/esp6_offload.c +++ b/net/ipv6/esp6_offload.c @@ -16,6 +16,7 @@ #include <crypto/authenc.h> #include <linux/err.h> #include <linux/module.h> +#include <net/gro.h> #include <net/ip.h> #include <net/xfrm.h> #include <net/esp.h> diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c index 1796856bc24f..39db5a226855 100644 --- a/net/ipv6/tcpv6_offload.c +++ b/net/ipv6/tcpv6_offload.c @@ -7,6 +7,7 @@ */ #include <linux/indirect_call_wrapper.h> #include <linux/skbuff.h> +#include <net/gro.h> #include <net/protocol.h> #include <net/tcp.h> #include <net/ip6_checksum.h> diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c index b3d9ed96e5ea..50a8a65fad23 100644 --- a/net/ipv6/udp_offload.c +++ b/net/ipv6/udp_offload.c @@ -13,6 +13,7 @@ #include <net/udp.h> #include <net/ip6_checksum.h> #include "ip6_offload.h" +#include <net/gro.h> static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, netdev_features_t features) |