diff options
Diffstat (limited to 'include/net/udp.h')
| -rw-r--r-- | include/net/udp.h | 594 |
1 files changed, 498 insertions, 96 deletions
diff --git a/include/net/udp.h b/include/net/udp.h index 74c10ec5e74f..a061d1b22ddc 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket @@ -13,11 +14,6 @@ * Fixes: * Alan Cox : Turned on udp checksums. I don't want to * chase 'memory corruption' bugs that aren't! - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. */ #ifndef _UDP_H #define _UDP_H @@ -25,12 +21,14 @@ #include <linux/list.h> #include <linux/bug.h> #include <net/inet_sock.h> +#include <net/gso.h> #include <net/sock.h> #include <net/snmp.h> #include <net/ip.h> #include <linux/ipv6.h> #include <linux/seq_file.h> #include <linux/poll.h> +#include <linux/indirect_call_wrapper.h> /** * struct udp_skb_cb - UDP(-Lite) private variables @@ -52,39 +50,68 @@ struct udp_skb_cb { #define UDP_SKB_CB(__skb) ((struct udp_skb_cb *)((__skb)->cb)) /** - * struct udp_hslot - UDP hash slot + * struct udp_hslot - UDP hash slot used by udp_table.hash/hash4 * * @head: head of list of sockets + * @nulls_head: head of list of sockets, only used by hash4 * @count: number of sockets in 'head' list * @lock: spinlock protecting changes to head/count */ struct udp_hslot { - struct hlist_nulls_head head; + union { + struct hlist_head head; + /* hash4 uses hlist_nulls to avoid moving wrongly onto another + * hlist, because rehash() can happen with lookup(). + */ + struct hlist_nulls_head nulls_head; + }; int count; spinlock_t lock; -} __attribute__((aligned(2 * sizeof(long)))); +} __aligned(2 * sizeof(long)); + +/** + * struct udp_hslot_main - UDP hash slot used by udp_table.hash2 + * + * @hslot: basic hash slot + * @hash4_cnt: number of sockets in hslot4 of the same + * (local port, local address) + */ +struct udp_hslot_main { + struct udp_hslot hslot; /* must be the first member */ +#if !IS_ENABLED(CONFIG_BASE_SMALL) + u32 hash4_cnt; +#endif +} __aligned(2 * sizeof(long)); +#define UDP_HSLOT_MAIN(__hslot) ((struct udp_hslot_main *)(__hslot)) /** * struct udp_table - UDP table * * @hash: hash table, sockets are hashed on (local port) * @hash2: hash table, sockets are hashed on (local port, local address) + * @hash4: hash table, connected sockets are hashed on + * (local port, local address, remote port, remote address) * @mask: number of slots in hash tables, minus 1 * @log: log2(number of slots in hash table) */ struct udp_table { struct udp_hslot *hash; - struct udp_hslot *hash2; + struct udp_hslot_main *hash2; +#if !IS_ENABLED(CONFIG_BASE_SMALL) + struct udp_hslot *hash4; +#endif unsigned int mask; unsigned int log; }; extern struct udp_table udp_table; -extern void udp_table_init(struct udp_table *, const char *); +void udp_table_init(struct udp_table *, const char *); static inline struct udp_hslot *udp_hashslot(struct udp_table *table, - struct net *net, unsigned int num) + const struct net *net, + unsigned int num) { return &table->hash[udp_hashfn(net, num, table->mask)]; } + /* * For secondary hash, net_hash_mix() is performed before calling * udp_hashslot2(), this explains difference with udp_hashslot() @@ -92,21 +119,93 @@ static inline struct udp_hslot *udp_hashslot(struct udp_table *table, static inline struct udp_hslot *udp_hashslot2(struct udp_table *table, unsigned int hash) { - return &table->hash2[hash & table->mask]; + return &table->hash2[hash & table->mask].hslot; +} + +#if IS_ENABLED(CONFIG_BASE_SMALL) +static inline void udp_table_hash4_init(struct udp_table *table) +{ +} + +static inline struct udp_hslot *udp_hashslot4(struct udp_table *table, + unsigned int hash) +{ + BUILD_BUG(); + return NULL; +} + +static inline bool udp_hashed4(const struct sock *sk) +{ + return false; +} + +static inline unsigned int udp_hash4_slot_size(void) +{ + return 0; +} + +static inline bool udp_has_hash4(const struct udp_hslot *hslot2) +{ + return false; +} + +static inline void udp_hash4_inc(struct udp_hslot *hslot2) +{ +} + +static inline void udp_hash4_dec(struct udp_hslot *hslot2) +{ +} +#else /* !CONFIG_BASE_SMALL */ + +/* Must be called with table->hash2 initialized */ +static inline void udp_table_hash4_init(struct udp_table *table) +{ + table->hash4 = (void *)(table->hash2 + (table->mask + 1)); + for (int i = 0; i <= table->mask; i++) { + table->hash2[i].hash4_cnt = 0; + + INIT_HLIST_NULLS_HEAD(&table->hash4[i].nulls_head, i); + table->hash4[i].count = 0; + spin_lock_init(&table->hash4[i].lock); + } +} + +static inline struct udp_hslot *udp_hashslot4(struct udp_table *table, + unsigned int hash) +{ + return &table->hash4[hash & table->mask]; +} + +static inline bool udp_hashed4(const struct sock *sk) +{ + return !hlist_nulls_unhashed(&udp_sk(sk)->udp_lrpa_node); +} + +static inline unsigned int udp_hash4_slot_size(void) +{ + return sizeof(struct udp_hslot); } -/* Note: this must match 'valbool' in sock_setsockopt */ -#define UDP_CSUM_NOXMIT 1 +static inline bool udp_has_hash4(const struct udp_hslot *hslot2) +{ + return UDP_HSLOT_MAIN(hslot2)->hash4_cnt; +} -/* Used by SunRPC/xprt layer. */ -#define UDP_CSUM_NORCV 2 +static inline void udp_hash4_inc(struct udp_hslot *hslot2) +{ + UDP_HSLOT_MAIN(hslot2)->hash4_cnt++; +} -/* Default, as per the RFC, is to always do csums. */ -#define UDP_CSUM_DEFAULT 0 +static inline void udp_hash4_dec(struct udp_hslot *hslot2) +{ + UDP_HSLOT_MAIN(hslot2)->hash4_cnt--; +} +#endif /* CONFIG_BASE_SMALL */ extern struct proto udp_prot; -extern atomic_long_t udp_memory_allocated; +DECLARE_PER_CPU(int, udp_memory_per_cpu_fw_alloc); /* sysctl variables for udp */ extern long sysctl_udp_mem[3]; @@ -120,7 +219,9 @@ struct sk_buff; */ static inline __sum16 __udp_lib_checksum_complete(struct sk_buff *skb) { - return __skb_checksum_complete_head(skb, UDP_SKB_CB(skb)->cscov); + return (UDP_SKB_CB(skb)->cscov == skb->len ? + __skb_checksum_complete(skb) : + __skb_checksum_complete_head(skb, UDP_SKB_CB(skb)->cscov)); } static inline int udp_lib_checksum_complete(struct sk_buff *skb) @@ -156,121 +257,422 @@ static inline __wsum udp_csum(struct sk_buff *skb) return csum; } +static inline __sum16 udp_v4_check(int len, __be32 saddr, + __be32 daddr, __wsum base) +{ + return csum_tcpudp_magic(saddr, daddr, len, IPPROTO_UDP, base); +} + +void udp_set_csum(bool nocheck, struct sk_buff *skb, + __be32 saddr, __be32 daddr, int len); + +static inline void udp_csum_pull_header(struct sk_buff *skb) +{ + if (!skb->csum_valid && skb->ip_summed == CHECKSUM_NONE) + skb->csum = csum_partial(skb->data, sizeof(struct udphdr), + skb->csum); + skb_pull_rcsum(skb, sizeof(struct udphdr)); + UDP_SKB_CB(skb)->cscov -= sizeof(struct udphdr); +} + +typedef struct sock *(*udp_lookup_t)(const struct sk_buff *skb, __be16 sport, + __be16 dport); + +void udp_v6_early_demux(struct sk_buff *skb); +INDIRECT_CALLABLE_DECLARE(int udpv6_rcv(struct sk_buff *)); + +struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb, + netdev_features_t features, bool is_ipv6); + +static inline int udp_lib_init_sock(struct sock *sk) +{ + struct udp_sock *up = udp_sk(sk); + + sk->sk_drop_counters = &up->drop_counters; + skb_queue_head_init(&up->reader_queue); + INIT_HLIST_NODE(&up->tunnel_list); + up->forward_threshold = sk->sk_rcvbuf >> 2; + set_bit(SOCK_CUSTOM_SOCKOPT, &sk->sk_socket->flags); + + up->udp_prod_queue = kcalloc(nr_node_ids, sizeof(*up->udp_prod_queue), + GFP_KERNEL); + if (!up->udp_prod_queue) + return -ENOMEM; + for (int i = 0; i < nr_node_ids; i++) + init_llist_head(&up->udp_prod_queue[i].ll_root); + return 0; +} + +static inline void udp_drops_inc(struct sock *sk) +{ + numa_drop_add(&udp_sk(sk)->drop_counters, 1); +} + /* hash routines shared between UDPv4/6 and UDP-Litev4/6 */ -static inline void udp_lib_hash(struct sock *sk) +static inline int udp_lib_hash(struct sock *sk) { BUG(); + return 0; } -extern void udp_lib_unhash(struct sock *sk); -extern void udp_lib_rehash(struct sock *sk, u16 new_hash); +void udp_lib_unhash(struct sock *sk); +void udp_lib_rehash(struct sock *sk, u16 new_hash, u16 new_hash4); +u32 udp_ehashfn(const struct net *net, const __be32 laddr, const __u16 lport, + const __be32 faddr, const __be16 fport); static inline void udp_lib_close(struct sock *sk, long timeout) { sk_common_release(sk); } -extern int udp_lib_get_port(struct sock *sk, unsigned short snum, - int (*)(const struct sock *,const struct sock *), - unsigned int hash2_nulladdr); +/* hash4 routines shared between UDPv4/6 */ +#if IS_ENABLED(CONFIG_BASE_SMALL) +static inline void udp_lib_hash4(struct sock *sk, u16 hash) +{ +} + +static inline void udp4_hash4(struct sock *sk) +{ +} +#else /* !CONFIG_BASE_SMALL */ +void udp_lib_hash4(struct sock *sk, u16 hash); +void udp4_hash4(struct sock *sk); +#endif /* CONFIG_BASE_SMALL */ + +int udp_lib_get_port(struct sock *sk, unsigned short snum, + unsigned int hash2_nulladdr); + +u32 udp_flow_hashrnd(void); + +static inline __be16 udp_flow_src_port(struct net *net, struct sk_buff *skb, + int min, int max, bool use_eth) +{ + u32 hash; + + if (min >= max) { + /* Use default range */ + inet_get_local_port_range(net, &min, &max); + } + + hash = skb_get_hash(skb); + if (unlikely(!hash)) { + if (use_eth) { + /* Can't find a normal hash, caller has indicated an + * Ethernet packet so use that to compute a hash. + */ + hash = jhash(skb->data, 2 * ETH_ALEN, + (__force u32) skb->protocol); + } else { + /* Can't derive any sort of hash for the packet, set + * to some consistent random value. + */ + hash = udp_flow_hashrnd(); + } + } + + /* Since this is being sent on the wire obfuscate hash a bit + * to minimize possibility that any useful information to an + * attacker is leaked. Only upper 16 bits are relevant in the + * computation for 16 bit port value. + */ + hash ^= hash << 16; + + return htons((((u64) hash * (max - min)) >> 32) + min); +} + +static inline int udp_rqueue_get(struct sock *sk) +{ + return sk_rmem_alloc_get(sk) - READ_ONCE(udp_sk(sk)->forward_deficit); +} + +static inline bool udp_sk_bound_dev_eq(const struct net *net, int bound_dev_if, + int dif, int sdif) +{ +#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) + return inet_bound_dev_eq(!!READ_ONCE(net->ipv4.sysctl_udp_l3mdev_accept), + bound_dev_if, dif, sdif); +#else + return inet_bound_dev_eq(true, bound_dev_if, dif, sdif); +#endif +} /* net/ipv4/udp.c */ -extern int udp_get_port(struct sock *sk, unsigned short snum, - int (*saddr_cmp)(const struct sock *, - const struct sock *)); -extern void udp_err(struct sk_buff *, u32); -extern int udp_sendmsg(struct kiocb *iocb, struct sock *sk, - struct msghdr *msg, size_t len); -extern int udp_push_pending_frames(struct sock *sk); -extern void udp_flush_pending_frames(struct sock *sk); -extern int udp_rcv(struct sk_buff *skb); -extern int udp_ioctl(struct sock *sk, int cmd, unsigned long arg); -extern int udp_disconnect(struct sock *sk, int flags); -extern unsigned int udp_poll(struct file *file, struct socket *sock, - poll_table *wait); -extern struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb, - netdev_features_t features); -extern int udp_lib_getsockopt(struct sock *sk, int level, int optname, - char __user *optval, int __user *optlen); -extern int udp_lib_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, unsigned int optlen, - int (*push_pending_frames)(struct sock *)); -extern struct sock *udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport, - __be32 daddr, __be16 dport, - int dif); -extern struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport, - __be32 daddr, __be16 dport, - int dif, struct udp_table *tbl); -extern struct sock *udp6_lib_lookup(struct net *net, const struct in6_addr *saddr, __be16 sport, - const struct in6_addr *daddr, __be16 dport, - int dif); -extern struct sock *__udp6_lib_lookup(struct net *net, const struct in6_addr *saddr, __be16 sport, - const struct in6_addr *daddr, __be16 dport, - int dif, struct udp_table *tbl); +void udp_destruct_common(struct sock *sk); +void skb_consume_udp(struct sock *sk, struct sk_buff *skb, int len); +int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb); +void udp_skb_destructor(struct sock *sk, struct sk_buff *skb); +struct sk_buff *__skb_recv_udp(struct sock *sk, unsigned int flags, int *off, + int *err); +static inline struct sk_buff *skb_recv_udp(struct sock *sk, unsigned int flags, + int *err) +{ + int off = 0; + + return __skb_recv_udp(sk, flags, &off, err); +} + +enum skb_drop_reason udp_v4_early_demux(struct sk_buff *skb); +bool udp_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst); +int udp_err(struct sk_buff *, u32); +int udp_abort(struct sock *sk, int err); +int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len); +void udp_splice_eof(struct socket *sock); +int udp_push_pending_frames(struct sock *sk); +void udp_flush_pending_frames(struct sock *sk); +int udp_cmsg_send(struct sock *sk, struct msghdr *msg, u16 *gso_size); +void udp4_hwcsum(struct sk_buff *skb, __be32 src, __be32 dst); +int udp_rcv(struct sk_buff *skb); +int udp_ioctl(struct sock *sk, int cmd, int *karg); +int udp_init_sock(struct sock *sk); +int udp_pre_connect(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len); +int __udp_disconnect(struct sock *sk, int flags); +int udp_disconnect(struct sock *sk, int flags); +__poll_t udp_poll(struct file *file, struct socket *sock, poll_table *wait); +struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb, + netdev_features_t features, + bool is_ipv6); +int udp_lib_getsockopt(struct sock *sk, int level, int optname, + char __user *optval, int __user *optlen); +int udp_lib_setsockopt(struct sock *sk, int level, int optname, + sockptr_t optval, unsigned int optlen, + int (*push_pending_frames)(struct sock *)); +struct sock *udp4_lib_lookup(const struct net *net, __be32 saddr, __be16 sport, + __be32 daddr, __be16 dport, int dif); +struct sock *__udp4_lib_lookup(const struct net *net, __be32 saddr, + __be16 sport, + __be32 daddr, __be16 dport, int dif, int sdif, + struct udp_table *tbl, struct sk_buff *skb); +struct sock *udp4_lib_lookup_skb(const struct sk_buff *skb, + __be16 sport, __be16 dport); +struct sock *udp6_lib_lookup(const struct net *net, + const struct in6_addr *saddr, __be16 sport, + const struct in6_addr *daddr, __be16 dport, + int dif); +struct sock *__udp6_lib_lookup(const struct net *net, + const struct in6_addr *saddr, __be16 sport, + const struct in6_addr *daddr, __be16 dport, + int dif, int sdif, struct udp_table *tbl, + struct sk_buff *skb); +struct sock *udp6_lib_lookup_skb(const struct sk_buff *skb, + __be16 sport, __be16 dport); +int udp_read_skb(struct sock *sk, skb_read_actor_t recv_actor); + +/* UDP uses skb->dev_scratch to cache as much information as possible and avoid + * possibly multiple cache miss on dequeue() + */ +struct udp_dev_scratch { + /* skb->truesize and the stateless bit are embedded in a single field; + * do not use a bitfield since the compiler emits better/smaller code + * this way + */ + u32 _tsize_state; + +#if BITS_PER_LONG == 64 + /* len and the bit needed to compute skb_csum_unnecessary + * will be on cold cache lines at recvmsg time. + * skb->len can be stored on 16 bits since the udp header has been + * already validated and pulled. + */ + u16 len; + bool is_linear; + bool csum_unnecessary; +#endif +}; + +static inline struct udp_dev_scratch *udp_skb_scratch(struct sk_buff *skb) +{ + return (struct udp_dev_scratch *)&skb->dev_scratch; +} + +#if BITS_PER_LONG == 64 +static inline unsigned int udp_skb_len(struct sk_buff *skb) +{ + return udp_skb_scratch(skb)->len; +} + +static inline bool udp_skb_csum_unnecessary(struct sk_buff *skb) +{ + return udp_skb_scratch(skb)->csum_unnecessary; +} + +static inline bool udp_skb_is_linear(struct sk_buff *skb) +{ + return udp_skb_scratch(skb)->is_linear; +} + +#else +static inline unsigned int udp_skb_len(struct sk_buff *skb) +{ + return skb->len; +} + +static inline bool udp_skb_csum_unnecessary(struct sk_buff *skb) +{ + return skb_csum_unnecessary(skb); +} + +static inline bool udp_skb_is_linear(struct sk_buff *skb) +{ + return !skb_is_nonlinear(skb); +} +#endif + +static inline int copy_linear_skb(struct sk_buff *skb, int len, int off, + struct iov_iter *to) +{ + return copy_to_iter_full(skb->data + off, len, to) ? 0 : -EFAULT; +} /* * SNMP statistics for UDP and UDP-Lite */ -#define UDP_INC_STATS_USER(net, field, is_udplite) do { \ - if (is_udplite) SNMP_INC_STATS_USER((net)->mib.udplite_statistics, field); \ - else SNMP_INC_STATS_USER((net)->mib.udp_statistics, field); } while(0) -#define UDP_INC_STATS_BH(net, field, is_udplite) do { \ - if (is_udplite) SNMP_INC_STATS_BH((net)->mib.udplite_statistics, field); \ - else SNMP_INC_STATS_BH((net)->mib.udp_statistics, field); } while(0) - -#define UDP6_INC_STATS_BH(net, field, is_udplite) do { \ - if (is_udplite) SNMP_INC_STATS_BH((net)->mib.udplite_stats_in6, field);\ - else SNMP_INC_STATS_BH((net)->mib.udp_stats_in6, field); \ +#define UDP_INC_STATS(net, field, is_udplite) do { \ + if (is_udplite) SNMP_INC_STATS((net)->mib.udplite_statistics, field); \ + else SNMP_INC_STATS((net)->mib.udp_statistics, field); } while(0) +#define __UDP_INC_STATS(net, field, is_udplite) do { \ + if (is_udplite) __SNMP_INC_STATS((net)->mib.udplite_statistics, field); \ + else __SNMP_INC_STATS((net)->mib.udp_statistics, field); } while(0) + +#define __UDP6_INC_STATS(net, field, is_udplite) do { \ + if (is_udplite) __SNMP_INC_STATS((net)->mib.udplite_stats_in6, field);\ + else __SNMP_INC_STATS((net)->mib.udp_stats_in6, field); \ } while(0) -#define UDP6_INC_STATS_USER(net, field, __lite) do { \ - if (__lite) SNMP_INC_STATS_USER((net)->mib.udplite_stats_in6, field); \ - else SNMP_INC_STATS_USER((net)->mib.udp_stats_in6, field); \ +#define UDP6_INC_STATS(net, field, __lite) do { \ + if (__lite) SNMP_INC_STATS((net)->mib.udplite_stats_in6, field); \ + else SNMP_INC_STATS((net)->mib.udp_stats_in6, field); \ } while(0) #if IS_ENABLED(CONFIG_IPV6) -#define UDPX_INC_STATS_BH(sk, field) \ - do { \ - if ((sk)->sk_family == AF_INET) \ - UDP_INC_STATS_BH(sock_net(sk), field, 0); \ - else \ - UDP6_INC_STATS_BH(sock_net(sk), field, 0); \ - } while (0); +#define __UDPX_MIB(sk, ipv4) \ +({ \ + ipv4 ? (IS_UDPLITE(sk) ? sock_net(sk)->mib.udplite_statistics : \ + sock_net(sk)->mib.udp_statistics) : \ + (IS_UDPLITE(sk) ? sock_net(sk)->mib.udplite_stats_in6 : \ + sock_net(sk)->mib.udp_stats_in6); \ +}) #else -#define UDPX_INC_STATS_BH(sk, field) UDP_INC_STATS_BH(sock_net(sk), field, 0) +#define __UDPX_MIB(sk, ipv4) \ +({ \ + IS_UDPLITE(sk) ? sock_net(sk)->mib.udplite_statistics : \ + sock_net(sk)->mib.udp_statistics; \ +}) #endif -/* /proc */ -int udp_seq_open(struct inode *inode, struct file *file); +#define __UDPX_INC_STATS(sk, field) \ + __SNMP_INC_STATS(__UDPX_MIB(sk, (sk)->sk_family == AF_INET), field) +#ifdef CONFIG_PROC_FS struct udp_seq_afinfo { - char *name; sa_family_t family; struct udp_table *udp_table; - const struct file_operations *seq_fops; - struct seq_operations seq_ops; }; struct udp_iter_state { struct seq_net_private p; - sa_family_t family; int bucket; - struct udp_table *udp_table; }; -#ifdef CONFIG_PROC_FS -extern int udp_proc_register(struct net *net, struct udp_seq_afinfo *afinfo); -extern void udp_proc_unregister(struct net *net, struct udp_seq_afinfo *afinfo); +void *udp_seq_start(struct seq_file *seq, loff_t *pos); +void *udp_seq_next(struct seq_file *seq, void *v, loff_t *pos); +void udp_seq_stop(struct seq_file *seq, void *v); -extern int udp4_proc_init(void); -extern void udp4_proc_exit(void); -#endif +extern const struct seq_operations udp_seq_ops; +extern const struct seq_operations udp6_seq_ops; + +int udp4_proc_init(void); +void udp4_proc_exit(void); +#endif /* CONFIG_PROC_FS */ -extern int udpv4_offload_init(void); +int udpv4_offload_init(void); -extern void udp_init(void); +void udp_init(void); -extern void udp_encap_enable(void); +DECLARE_STATIC_KEY_FALSE(udp_encap_needed_key); +void udp_encap_enable(void); +void udp_encap_disable(void); #if IS_ENABLED(CONFIG_IPV6) -extern void udpv6_encap_enable(void); +DECLARE_STATIC_KEY_FALSE(udpv6_encap_needed_key); +void udpv6_encap_enable(void); #endif + +static inline struct sk_buff *udp_rcv_segment(struct sock *sk, + struct sk_buff *skb, bool ipv4) +{ + netdev_features_t features = NETIF_F_SG; + struct sk_buff *segs; + int drop_count; + + /* + * Segmentation in UDP receive path is only for UDP GRO, drop udp + * fragmentation offload (UFO) packets. + */ + if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP) { + drop_count = 1; + goto drop; + } + + /* Avoid csum recalculation by skb_segment unless userspace explicitly + * asks for the final checksum values + */ + if (!inet_get_convert_csum(sk)) + features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM; + + /* UDP segmentation expects packets of type CHECKSUM_PARTIAL or + * CHECKSUM_NONE in __udp_gso_segment. UDP GRO indeed builds partial + * packets in udp_gro_complete_segment. As does UDP GSO, verified by + * udp_send_skb. But when those packets are looped in dev_loopback_xmit + * their ip_summed CHECKSUM_NONE is changed to CHECKSUM_UNNECESSARY. + * Reset in this specific case, where PARTIAL is both correct and + * required. + */ + if (skb->pkt_type == PACKET_LOOPBACK) + skb->ip_summed = CHECKSUM_PARTIAL; + + /* the GSO CB lays after the UDP one, no need to save and restore any + * CB fragment + */ + segs = __skb_gso_segment(skb, features, false); + if (IS_ERR_OR_NULL(segs)) { + drop_count = skb_shinfo(skb)->gso_segs; + goto drop; + } + + consume_skb(skb); + return segs; + +drop: + sk_drops_add(sk, drop_count); + SNMP_ADD_STATS(__UDPX_MIB(sk, ipv4), UDP_MIB_INERRORS, drop_count); + kfree_skb(skb); + return NULL; +} + +static inline void udp_post_segment_fix_csum(struct sk_buff *skb) +{ + /* UDP-lite can't land here - no GRO */ + WARN_ON_ONCE(UDP_SKB_CB(skb)->partial_cov); + + /* UDP packets generated with UDP_SEGMENT and traversing: + * + * UDP tunnel(xmit) -> veth (segmentation) -> veth (gro) -> UDP tunnel (rx) + * + * can reach an UDP socket with CHECKSUM_NONE, because + * __iptunnel_pull_header() converts CHECKSUM_PARTIAL into NONE. + * SKB_GSO_UDP_L4 or SKB_GSO_FRAGLIST packets with no UDP tunnel will + * have a valid checksum, as the GRO engine validates the UDP csum + * before the aggregation and nobody strips such info in between. + * Instead of adding another check in the tunnel fastpath, we can force + * a valid csum after the segmentation. + * Additionally fixup the UDP CB. + */ + UDP_SKB_CB(skb)->cscov = skb->len; + if (skb->ip_summed == CHECKSUM_NONE && !skb->csum_valid) + skb->csum_valid = 1; +} + +#ifdef CONFIG_BPF_SYSCALL +struct sk_psock; +int udp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore); +#endif + #endif /* _UDP_H */ |