diff options
Diffstat (limited to 'net/core')
-rw-r--r-- | net/core/Makefile | 1 | ||||
-rw-r--r-- | net/core/datagram.c | 9 | ||||
-rw-r--r-- | net/core/dev.c | 5 | ||||
-rw-r--r-- | net/core/dst_cache.c | 8 | ||||
-rw-r--r-- | net/core/ethtool.c | 2 | ||||
-rw-r--r-- | net/core/filter.c | 187 | ||||
-rw-r--r-- | net/core/flow_dissector.c | 13 | ||||
-rw-r--r-- | net/core/gen_estimator.c | 2 | ||||
-rw-r--r-- | net/core/gen_stats.c | 1 | ||||
-rw-r--r-- | net/core/hwbm.c | 87 | ||||
-rw-r--r-- | net/core/netpoll.c | 3 | ||||
-rw-r--r-- | net/core/rtnetlink.c | 47 | ||||
-rw-r--r-- | net/core/skbuff.c | 67 | ||||
-rw-r--r-- | net/core/sock.c | 94 | ||||
-rw-r--r-- | net/core/sock_diag.c | 1 |
15 files changed, 410 insertions, 117 deletions
diff --git a/net/core/Makefile b/net/core/Makefile index 014422e2561f..d6508c2ddca5 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -25,4 +25,5 @@ obj-$(CONFIG_CGROUP_NET_PRIO) += netprio_cgroup.o obj-$(CONFIG_CGROUP_NET_CLASSID) += netclassid_cgroup.o obj-$(CONFIG_LWTUNNEL) += lwtunnel.o obj-$(CONFIG_DST_CACHE) += dst_cache.o +obj-$(CONFIG_HWBM) += hwbm.o obj-$(CONFIG_NET_DEVLINK) += devlink.o diff --git a/net/core/datagram.c b/net/core/datagram.c index fa9dc6450b08..b7de71f8d5d3 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -301,16 +301,19 @@ void skb_free_datagram(struct sock *sk, struct sk_buff *skb) } EXPORT_SYMBOL(skb_free_datagram); -void skb_free_datagram_locked(struct sock *sk, struct sk_buff *skb) +void __skb_free_datagram_locked(struct sock *sk, struct sk_buff *skb, int len) { bool slow; if (likely(atomic_read(&skb->users) == 1)) smp_rmb(); - else if (likely(!atomic_dec_and_test(&skb->users))) + else if (likely(!atomic_dec_and_test(&skb->users))) { + sk_peek_offset_bwd(sk, len); return; + } slow = lock_sock_fast(sk); + sk_peek_offset_bwd(sk, len); skb_orphan(skb); sk_mem_reclaim_partial(sk); unlock_sock_fast(sk, slow); @@ -318,7 +321,7 @@ void skb_free_datagram_locked(struct sock *sk, struct sk_buff *skb) /* skb is now orphaned, can be freed outside of locked section */ __kfree_skb(skb); } -EXPORT_SYMBOL(skb_free_datagram_locked); +EXPORT_SYMBOL(__skb_free_datagram_locked); /** * skb_kill_datagram - Free a datagram skbuff forcibly diff --git a/net/core/dev.c b/net/core/dev.c index edb7179bc051..273f10d1e306 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4438,7 +4438,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff NAPI_GRO_CB(skb)->same_flow = 0; NAPI_GRO_CB(skb)->flush = 0; NAPI_GRO_CB(skb)->free = 0; - NAPI_GRO_CB(skb)->udp_mark = 0; + NAPI_GRO_CB(skb)->encap_mark = 0; NAPI_GRO_CB(skb)->gro_remcsum_start = 0; /* Setup for GRO checksum validation */ @@ -4663,6 +4663,8 @@ static struct sk_buff *napi_frags_skb(struct napi_struct *napi) 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; } @@ -6445,6 +6447,7 @@ EXPORT_SYMBOL(dev_get_phys_port_id); * dev_get_phys_port_name - Get device physical port name * @dev: device * @name: port name + * @len: limit of bytes to copy to name * * Get device physical port name */ diff --git a/net/core/dst_cache.c b/net/core/dst_cache.c index 3938f3f38d69..554d36449231 100644 --- a/net/core/dst_cache.c +++ b/net/core/dst_cache.c @@ -28,8 +28,8 @@ struct dst_cache_pcpu { }; }; -void dst_cache_per_cpu_dst_set(struct dst_cache_pcpu *dst_cache, - struct dst_entry *dst, u32 cookie) +static void dst_cache_per_cpu_dst_set(struct dst_cache_pcpu *dst_cache, + struct dst_entry *dst, u32 cookie) { dst_release(dst_cache->dst); if (dst) @@ -39,8 +39,8 @@ void dst_cache_per_cpu_dst_set(struct dst_cache_pcpu *dst_cache, dst_cache->dst = dst; } -struct dst_entry *dst_cache_per_cpu_get(struct dst_cache *dst_cache, - struct dst_cache_pcpu *idst) +static struct dst_entry *dst_cache_per_cpu_get(struct dst_cache *dst_cache, + struct dst_cache_pcpu *idst) { struct dst_entry *dst; diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 2966cd0d7c93..f426c5ad6149 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -655,7 +655,7 @@ static int ethtool_get_link_ksettings(struct net_device *dev, != link_ksettings.base.link_mode_masks_nwords) { /* wrong link mode nbits requested */ memset(&link_ksettings, 0, sizeof(link_ksettings)); - /* keep cmd field reset to 0 */ + link_ksettings.base.cmd = ETHTOOL_GLINKSETTINGS; /* send back number of words required as negative val */ compiletime_assert(__ETHTOOL_LINK_MODE_MASK_NU32 <= S8_MAX, "need too many bits for link modes!"); diff --git a/net/core/filter.c b/net/core/filter.c index 5e2a3b5e5196..ca7f832b2980 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1149,7 +1149,8 @@ void bpf_prog_destroy(struct bpf_prog *fp) } EXPORT_SYMBOL_GPL(bpf_prog_destroy); -static int __sk_attach_prog(struct bpf_prog *prog, struct sock *sk) +static int __sk_attach_prog(struct bpf_prog *prog, struct sock *sk, + bool locked) { struct sk_filter *fp, *old_fp; @@ -1165,10 +1166,8 @@ static int __sk_attach_prog(struct bpf_prog *prog, struct sock *sk) return -ENOMEM; } - old_fp = rcu_dereference_protected(sk->sk_filter, - sock_owned_by_user(sk)); + old_fp = rcu_dereference_protected(sk->sk_filter, locked); rcu_assign_pointer(sk->sk_filter, fp); - if (old_fp) sk_filter_uncharge(sk, old_fp); @@ -1247,7 +1246,8 @@ struct bpf_prog *__get_filter(struct sock_fprog *fprog, struct sock *sk) * occurs or there is insufficient memory for the filter a negative * errno code is returned. On success the return is zero. */ -int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk) +int __sk_attach_filter(struct sock_fprog *fprog, struct sock *sk, + bool locked) { struct bpf_prog *prog = __get_filter(fprog, sk); int err; @@ -1255,7 +1255,7 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk) if (IS_ERR(prog)) return PTR_ERR(prog); - err = __sk_attach_prog(prog, sk); + err = __sk_attach_prog(prog, sk, locked); if (err < 0) { __bpf_prog_release(prog); return err; @@ -1263,7 +1263,12 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk) return 0; } -EXPORT_SYMBOL_GPL(sk_attach_filter); +EXPORT_SYMBOL_GPL(__sk_attach_filter); + +int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk) +{ + return __sk_attach_filter(fprog, sk, sock_owned_by_user(sk)); +} int sk_reuseport_attach_filter(struct sock_fprog *fprog, struct sock *sk) { @@ -1309,7 +1314,7 @@ int sk_attach_bpf(u32 ufd, struct sock *sk) if (IS_ERR(prog)) return PTR_ERR(prog); - err = __sk_attach_prog(prog, sk); + err = __sk_attach_prog(prog, sk, sock_owned_by_user(sk)); if (err < 0) { bpf_prog_put(prog); return err; @@ -1353,7 +1358,7 @@ static u64 bpf_skb_store_bytes(u64 r1, u64 r2, u64 r3, u64 r4, u64 flags) unsigned int len = (unsigned int) r4; void *ptr; - if (unlikely(flags & ~(BPF_F_RECOMPUTE_CSUM))) + if (unlikely(flags & ~(BPF_F_RECOMPUTE_CSUM | BPF_F_INVALIDATE_HASH))) return -EINVAL; /* bpf verifier guarantees that: @@ -1384,11 +1389,13 @@ static u64 bpf_skb_store_bytes(u64 r1, u64 r2, u64 r3, u64 r4, u64 flags) if (flags & BPF_F_RECOMPUTE_CSUM) skb_postpush_rcsum(skb, ptr, len); + if (flags & BPF_F_INVALIDATE_HASH) + skb_clear_hash(skb); return 0; } -const struct bpf_func_proto bpf_skb_store_bytes_proto = { +static const struct bpf_func_proto bpf_skb_store_bytes_proto = { .func = bpf_skb_store_bytes, .gpl_only = false, .ret_type = RET_INTEGER, @@ -1419,7 +1426,7 @@ static u64 bpf_skb_load_bytes(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) return 0; } -const struct bpf_func_proto bpf_skb_load_bytes_proto = { +static const struct bpf_func_proto bpf_skb_load_bytes_proto = { .func = bpf_skb_load_bytes, .gpl_only = false, .ret_type = RET_INTEGER, @@ -1447,6 +1454,12 @@ static u64 bpf_l3_csum_replace(u64 r1, u64 r2, u64 from, u64 to, u64 flags) return -EFAULT; switch (flags & BPF_F_HDR_FIELD_MASK) { + case 0: + if (unlikely(from != 0)) + return -EINVAL; + + csum_replace_by_diff(ptr, to); + break; case 2: csum_replace2(ptr, from, to); break; @@ -1464,7 +1477,7 @@ static u64 bpf_l3_csum_replace(u64 r1, u64 r2, u64 from, u64 to, u64 flags) return 0; } -const struct bpf_func_proto bpf_l3_csum_replace_proto = { +static const struct bpf_func_proto bpf_l3_csum_replace_proto = { .func = bpf_l3_csum_replace, .gpl_only = false, .ret_type = RET_INTEGER, @@ -1523,7 +1536,7 @@ static u64 bpf_l4_csum_replace(u64 r1, u64 r2, u64 from, u64 to, u64 flags) return 0; } -const struct bpf_func_proto bpf_l4_csum_replace_proto = { +static const struct bpf_func_proto bpf_l4_csum_replace_proto = { .func = bpf_l4_csum_replace, .gpl_only = false, .ret_type = RET_INTEGER, @@ -1562,7 +1575,7 @@ static u64 bpf_csum_diff(u64 r1, u64 from_size, u64 r3, u64 to_size, u64 seed) return csum_partial(sp->diff, diff_size, seed); } -const struct bpf_func_proto bpf_csum_diff_proto = { +static const struct bpf_func_proto bpf_csum_diff_proto = { .func = bpf_csum_diff, .gpl_only = false, .ret_type = RET_INTEGER, @@ -1600,7 +1613,7 @@ static u64 bpf_clone_redirect(u64 r1, u64 ifindex, u64 flags, u64 r4, u64 r5) return dev_queue_xmit(skb2); } -const struct bpf_func_proto bpf_clone_redirect_proto = { +static const struct bpf_func_proto bpf_clone_redirect_proto = { .func = bpf_clone_redirect, .gpl_only = false, .ret_type = RET_INTEGER, @@ -1652,7 +1665,7 @@ int skb_do_redirect(struct sk_buff *skb) return dev_queue_xmit(skb); } -const struct bpf_func_proto bpf_redirect_proto = { +static const struct bpf_func_proto bpf_redirect_proto = { .func = bpf_redirect, .gpl_only = false, .ret_type = RET_INTEGER, @@ -1674,14 +1687,7 @@ static const struct bpf_func_proto bpf_get_cgroup_classid_proto = { static u64 bpf_get_route_realm(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) { -#ifdef CONFIG_IP_ROUTE_CLASSID - const struct dst_entry *dst; - - dst = skb_dst((struct sk_buff *) (unsigned long) r1); - if (dst) - return dst->tclassid; -#endif - return 0; + return dst_tclassid((struct sk_buff *) (unsigned long) r1); } static const struct bpf_func_proto bpf_get_route_realm_proto = { @@ -1762,12 +1768,16 @@ static u64 bpf_skb_get_tunnel_key(u64 r1, u64 r2, u64 size, u64 flags, u64 r5) return -EPROTO; if (unlikely(size != sizeof(struct bpf_tunnel_key))) { switch (size) { + case offsetof(struct bpf_tunnel_key, tunnel_label): + case offsetof(struct bpf_tunnel_key, tunnel_ext): + goto set_compat; case offsetof(struct bpf_tunnel_key, remote_ipv6[1]): /* Fixup deprecated structure layouts here, so we have * a common path later on. */ if (ip_tunnel_info_af(info) != AF_INET) return -EINVAL; +set_compat: to = (struct bpf_tunnel_key *)compat; break; default: @@ -1779,11 +1789,13 @@ static u64 bpf_skb_get_tunnel_key(u64 r1, u64 r2, u64 size, u64 flags, u64 r5) to->tunnel_tos = info->key.tos; to->tunnel_ttl = info->key.ttl; - if (flags & BPF_F_TUNINFO_IPV6) + if (flags & BPF_F_TUNINFO_IPV6) { memcpy(to->remote_ipv6, &info->key.u.ipv6.src, sizeof(to->remote_ipv6)); - else + to->tunnel_label = be32_to_cpu(info->key.label); + } else { to->remote_ipv4 = be32_to_cpu(info->key.u.ipv4.src); + } if (unlikely(size != sizeof(struct bpf_tunnel_key))) memcpy((void *)(long) r2, to, size); @@ -1791,7 +1803,7 @@ static u64 bpf_skb_get_tunnel_key(u64 r1, u64 r2, u64 size, u64 flags, u64 r5) return 0; } -const struct bpf_func_proto bpf_skb_get_tunnel_key_proto = { +static const struct bpf_func_proto bpf_skb_get_tunnel_key_proto = { .func = bpf_skb_get_tunnel_key, .gpl_only = false, .ret_type = RET_INTEGER, @@ -1801,6 +1813,32 @@ const struct bpf_func_proto bpf_skb_get_tunnel_key_proto = { .arg4_type = ARG_ANYTHING, }; +static u64 bpf_skb_get_tunnel_opt(u64 r1, u64 r2, u64 size, u64 r4, u64 r5) +{ + struct sk_buff *skb = (struct sk_buff *) (long) r1; + u8 *to = (u8 *) (long) r2; + const struct ip_tunnel_info *info = skb_tunnel_info(skb); + + if (unlikely(!info || + !(info->key.tun_flags & TUNNEL_OPTIONS_PRESENT))) + return -ENOENT; + if (unlikely(size < info->options_len)) + return -ENOMEM; + + ip_tunnel_info_opts_get(to, info); + + return info->options_len; +} + +static const struct bpf_func_proto bpf_skb_get_tunnel_opt_proto = { + .func = bpf_skb_get_tunnel_opt, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_PTR_TO_STACK, + .arg3_type = ARG_CONST_STACK_SIZE, +}; + static struct metadata_dst __percpu *md_dst; static u64 bpf_skb_set_tunnel_key(u64 r1, u64 r2, u64 size, u64 flags, u64 r5) @@ -1811,10 +1849,13 @@ static u64 bpf_skb_set_tunnel_key(u64 r1, u64 r2, u64 size, u64 flags, u64 r5) u8 compat[sizeof(struct bpf_tunnel_key)]; struct ip_tunnel_info *info; - if (unlikely(flags & ~(BPF_F_TUNINFO_IPV6))) + if (unlikely(flags & ~(BPF_F_TUNINFO_IPV6 | BPF_F_ZERO_CSUM_TX | + BPF_F_DONT_FRAGMENT))) return -EINVAL; if (unlikely(size != sizeof(struct bpf_tunnel_key))) { switch (size) { + case offsetof(struct bpf_tunnel_key, tunnel_label): + case offsetof(struct bpf_tunnel_key, tunnel_ext): case offsetof(struct bpf_tunnel_key, remote_ipv6[1]): /* Fixup deprecated structure layouts here, so we have * a common path later on. @@ -1827,6 +1868,9 @@ static u64 bpf_skb_set_tunnel_key(u64 r1, u64 r2, u64 size, u64 flags, u64 r5) return -EINVAL; } } + if (unlikely((!(flags & BPF_F_TUNINFO_IPV6) && from->tunnel_label) || + from->tunnel_ext)) + return -EINVAL; skb_dst_drop(skb); dst_hold((struct dst_entry *) md); @@ -1835,7 +1879,10 @@ static u64 bpf_skb_set_tunnel_key(u64 r1, u64 r2, u64 size, u64 flags, u64 r5) info = &md->u.tun_info; info->mode = IP_TUNNEL_INFO_TX; - info->key.tun_flags = TUNNEL_KEY; + info->key.tun_flags = TUNNEL_KEY | TUNNEL_CSUM | TUNNEL_NOCACHE; + if (flags & BPF_F_DONT_FRAGMENT) + info->key.tun_flags |= TUNNEL_DONT_FRAGMENT; + info->key.tun_id = cpu_to_be64(from->tunnel_id); info->key.tos = from->tunnel_tos; info->key.ttl = from->tunnel_ttl; @@ -1844,14 +1891,18 @@ static u64 bpf_skb_set_tunnel_key(u64 r1, u64 r2, u64 size, u64 flags, u64 r5) info->mode |= IP_TUNNEL_INFO_IPV6; memcpy(&info->key.u.ipv6.dst, from->remote_ipv6, sizeof(from->remote_ipv6)); + info->key.label = cpu_to_be32(from->tunnel_label) & + IPV6_FLOWLABEL_MASK; } else { info->key.u.ipv4.dst = cpu_to_be32(from->remote_ipv4); + if (flags & BPF_F_ZERO_CSUM_TX) + info->key.tun_flags &= ~TUNNEL_CSUM; } return 0; } -const struct bpf_func_proto bpf_skb_set_tunnel_key_proto = { +static const struct bpf_func_proto bpf_skb_set_tunnel_key_proto = { .func = bpf_skb_set_tunnel_key, .gpl_only = false, .ret_type = RET_INTEGER, @@ -1861,17 +1912,53 @@ const struct bpf_func_proto bpf_skb_set_tunnel_key_proto = { .arg4_type = ARG_ANYTHING, }; -static const struct bpf_func_proto *bpf_get_skb_set_tunnel_key_proto(void) +static u64 bpf_skb_set_tunnel_opt(u64 r1, u64 r2, u64 size, u64 r4, u64 r5) +{ + struct sk_buff *skb = (struct sk_buff *) (long) r1; + u8 *from = (u8 *) (long) r2; + struct ip_tunnel_info *info = skb_tunnel_info(skb); + const struct metadata_dst *md = this_cpu_ptr(md_dst); + + if (unlikely(info != &md->u.tun_info || (size & (sizeof(u32) - 1)))) + return -EINVAL; + if (unlikely(size > IP_TUNNEL_OPTS_MAX)) + return -ENOMEM; + + ip_tunnel_info_opts_set(info, from, size); + + return 0; +} + +static const struct bpf_func_proto bpf_skb_set_tunnel_opt_proto = { + .func = bpf_skb_set_tunnel_opt, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_PTR_TO_STACK, + .arg3_type = ARG_CONST_STACK_SIZE, +}; + +static const struct bpf_func_proto * +bpf_get_skb_set_tunnel_proto(enum bpf_func_id which) { if (!md_dst) { - /* race is not possible, since it's called from - * verifier that is holding verifier mutex + /* Race is not possible, since it's called from verifier + * that is holding verifier mutex. */ - md_dst = metadata_dst_alloc_percpu(0, GFP_KERNEL); + md_dst = metadata_dst_alloc_percpu(IP_TUNNEL_OPTS_MAX, + GFP_KERNEL); if (!md_dst) return NULL; } - return &bpf_skb_set_tunnel_key_proto; + + switch (which) { + case BPF_FUNC_skb_set_tunnel_key: + return &bpf_skb_set_tunnel_key_proto; + case BPF_FUNC_skb_set_tunnel_opt: + return &bpf_skb_set_tunnel_opt_proto; + default: + return NULL; + } } static const struct bpf_func_proto * @@ -1925,7 +2012,11 @@ tc_cls_act_func_proto(enum bpf_func_id func_id) case BPF_FUNC_skb_get_tunnel_key: return &bpf_skb_get_tunnel_key_proto; case BPF_FUNC_skb_set_tunnel_key: - return bpf_get_skb_set_tunnel_key_proto(); + return bpf_get_skb_set_tunnel_proto(func_id); + case BPF_FUNC_skb_get_tunnel_opt: + return &bpf_skb_get_tunnel_opt_proto; + case BPF_FUNC_skb_set_tunnel_opt: + return bpf_get_skb_set_tunnel_proto(func_id); case BPF_FUNC_redirect: return &bpf_redirect_proto; case BPF_FUNC_get_route_realm: @@ -1974,16 +2065,14 @@ static bool sk_filter_is_valid_access(int off, int size, static bool tc_cls_act_is_valid_access(int off, int size, enum bpf_access_type type) { - if (off == offsetof(struct __sk_buff, tc_classid)) - return type == BPF_WRITE ? true : false; - if (type == BPF_WRITE) { switch (off) { case offsetof(struct __sk_buff, mark): case offsetof(struct __sk_buff, tc_index): case offsetof(struct __sk_buff, priority): case offsetof(struct __sk_buff, cb[0]) ... - offsetof(struct __sk_buff, cb[4]): + offsetof(struct __sk_buff, cb[4]): + case offsetof(struct __sk_buff, tc_classid): break; default: return false; @@ -2100,8 +2189,10 @@ static u32 bpf_net_convert_ctx_access(enum bpf_access_type type, int dst_reg, ctx_off -= offsetof(struct __sk_buff, tc_classid); ctx_off += offsetof(struct sk_buff, cb); ctx_off += offsetof(struct qdisc_skb_cb, tc_classid); - WARN_ON(type != BPF_WRITE); - *insn++ = BPF_STX_MEM(BPF_H, dst_reg, src_reg, ctx_off); + if (type == BPF_WRITE) + *insn++ = BPF_STX_MEM(BPF_H, dst_reg, src_reg, ctx_off); + else + *insn++ = BPF_LDX_MEM(BPF_H, dst_reg, src_reg, ctx_off); break; case offsetof(struct __sk_buff, tc_index): @@ -2164,7 +2255,7 @@ static int __init register_sk_filter_ops(void) } late_initcall(register_sk_filter_ops); -int sk_detach_filter(struct sock *sk) +int __sk_detach_filter(struct sock *sk, bool locked) { int ret = -ENOENT; struct sk_filter *filter; @@ -2172,8 +2263,7 @@ int sk_detach_filter(struct sock *sk) if (sock_flag(sk, SOCK_FILTER_LOCKED)) return -EPERM; - filter = rcu_dereference_protected(sk->sk_filter, - sock_owned_by_user(sk)); + filter = rcu_dereference_protected(sk->sk_filter, locked); if (filter) { RCU_INIT_POINTER(sk->sk_filter, NULL); sk_filter_uncharge(sk, filter); @@ -2182,7 +2272,12 @@ int sk_detach_filter(struct sock *sk) return ret; } -EXPORT_SYMBOL_GPL(sk_detach_filter); +EXPORT_SYMBOL_GPL(__sk_detach_filter); + +int sk_detach_filter(struct sock *sk) +{ + return __sk_detach_filter(sk, sock_owned_by_user(sk)); +} int sk_get_filter(struct sock *sk, struct sock_filter __user *ubuf, unsigned int len) diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 7c7b8739b8b8..a669dea146c6 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -19,25 +19,12 @@ #include <net/flow_dissector.h> #include <scsi/fc/fc_fcoe.h> -static bool dissector_uses_key(const struct flow_dissector *flow_dissector, - enum flow_dissector_key_id key_id) -{ - return flow_dissector->used_keys & (1 << key_id); -} - static void dissector_set_key(struct flow_dissector *flow_dissector, enum flow_dissector_key_id key_id) { flow_dissector->used_keys |= (1 << key_id); } -static void *skb_flow_dissector_target(struct flow_dissector *flow_dissector, - enum flow_dissector_key_id key_id, - void *target_container) -{ - return ((char *) target_container) + flow_dissector->offset[key_id]; -} - void skb_flow_dissector_init(struct flow_dissector *flow_dissector, const struct flow_dissector_key *key, unsigned int key_count) diff --git a/net/core/gen_estimator.c b/net/core/gen_estimator.c index 92d886f4adcb..4573d81093fe 100644 --- a/net/core/gen_estimator.c +++ b/net/core/gen_estimator.c @@ -191,6 +191,7 @@ struct gen_estimator *gen_find_node(const struct gnet_stats_basic_packed *bstats /** * gen_new_estimator - create a new rate estimator * @bstats: basic statistics + * @cpu_bstats: bstats per cpu * @rate_est: rate estimator statistics * @stats_lock: statistics lock * @opt: rate estimator configuration TLV @@ -287,6 +288,7 @@ EXPORT_SYMBOL(gen_kill_estimator); /** * gen_replace_estimator - replace rate estimator configuration * @bstats: basic statistics + * @cpu_bstats: bstats per cpu * @rate_est: rate estimator statistics * @stats_lock: statistics lock * @opt: rate estimator configuration TLV diff --git a/net/core/gen_stats.c b/net/core/gen_stats.c index 1e2f46a69d50..e640462ea8bf 100644 --- a/net/core/gen_stats.c +++ b/net/core/gen_stats.c @@ -140,6 +140,7 @@ EXPORT_SYMBOL(__gnet_stats_copy_basic); /** * gnet_stats_copy_basic - copy basic statistics into statistic TLV * @d: dumping handle + * @cpu: copy statistic per cpu * @b: basic statistics * * Appends the basic statistics to the top level TLV created by diff --git a/net/core/hwbm.c b/net/core/hwbm.c new file mode 100644 index 000000000000..941c28486896 --- /dev/null +++ b/net/core/hwbm.c @@ -0,0 +1,87 @@ +/* Support for hardware buffer manager. + * + * Copyright (C) 2016 Marvell + * + * Gregory CLEMENT <gregory.clement@free-electrons.com> + * + * 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. + */ +#include <linux/kernel.h> +#include <linux/printk.h> +#include <linux/skbuff.h> +#include <net/hwbm.h> + +void hwbm_buf_free(struct hwbm_pool *bm_pool, void *buf) +{ + if (likely(bm_pool->frag_size <= PAGE_SIZE)) + skb_free_frag(buf); + else + kfree(buf); +} +EXPORT_SYMBOL_GPL(hwbm_buf_free); + +/* Refill processing for HW buffer management */ +int hwbm_pool_refill(struct hwbm_pool *bm_pool, gfp_t gfp) +{ + int frag_size = bm_pool->frag_size; + void *buf; + + if (likely(frag_size <= PAGE_SIZE)) + buf = netdev_alloc_frag(frag_size); + else + buf = kmalloc(frag_size, gfp); + + if (!buf) + return -ENOMEM; + + if (bm_pool->construct) + if (bm_pool->construct(bm_pool, buf)) { + hwbm_buf_free(bm_pool, buf); + return -ENOMEM; + } + + return 0; +} +EXPORT_SYMBOL_GPL(hwbm_pool_refill); + +int hwbm_pool_add(struct hwbm_pool *bm_pool, unsigned int buf_num, gfp_t gfp) +{ + int err, i; + unsigned long flags; + + spin_lock_irqsave(&bm_pool->lock, flags); + if (bm_pool->buf_num == bm_pool->size) { + pr_warn("pool already filled\n"); + return bm_pool->buf_num; + } + + if (buf_num + bm_pool->buf_num > bm_pool->size) { + pr_warn("cannot allocate %d buffers for pool\n", + buf_num); + return 0; + } + + if ((buf_num + bm_pool->buf_num) < bm_pool->buf_num) { + pr_warn("Adding %d buffers to the %d current buffers will overflow\n", + buf_num, bm_pool->buf_num); + return 0; + } + + for (i = 0; i < buf_num; i++) { + err = hwbm_pool_refill(bm_pool, gfp); + if (err < 0) + break; + } + + /* Update BM driver with number of buffers added to pool */ + bm_pool->buf_num += i; + + pr_debug("hwpm pool: %d of %d buffers added\n", i, buf_num); + spin_unlock_irqrestore(&bm_pool->lock, flags); + + return i; +} +EXPORT_SYMBOL_GPL(hwbm_pool_add); diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 94acfc89ad97..a57bd17805b4 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -603,7 +603,6 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev) const struct net_device_ops *ops; int err; - np->dev = ndev; strlcpy(np->dev_name, ndev->name, IFNAMSIZ); INIT_WORK(&np->cleanup_work, netpoll_async_cleanup); @@ -670,6 +669,7 @@ int netpoll_setup(struct netpoll *np) goto unlock; } dev_hold(ndev); + np->dev = ndev; if (netdev_master_upper_dev_get(ndev)) { np_err(np, "%s is a slave device, aborting\n", np->dev_name); @@ -770,6 +770,7 @@ int netpoll_setup(struct netpoll *np) return 0; put: + np->dev = NULL; dev_put(ndev); unlock: rtnl_unlock(); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 6128aac01b11..a75f7e94b445 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -895,6 +895,8 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev, + nla_total_size(4) /* IFLA_PROMISCUITY */ + nla_total_size(4) /* IFLA_NUM_TX_QUEUES */ + nla_total_size(4) /* IFLA_NUM_RX_QUEUES */ + + nla_total_size(4) /* IFLA_MAX_GSO_SEGS */ + + nla_total_size(4) /* IFLA_MAX_GSO_SIZE */ + nla_total_size(1) /* IFLA_OPERSTATE */ + nla_total_size(1) /* IFLA_LINKMODE */ + nla_total_size(4) /* IFLA_CARRIER_CHANGES */ @@ -907,6 +909,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev, + rtnl_link_get_af_size(dev, ext_filter_mask) /* IFLA_AF_SPEC */ + nla_total_size(MAX_PHYS_ITEM_ID_LEN) /* IFLA_PHYS_PORT_ID */ + nla_total_size(MAX_PHYS_ITEM_ID_LEN) /* IFLA_PHYS_SWITCH_ID */ + + nla_total_size(IFNAMSIZ) /* IFLA_PHYS_PORT_NAME */ + nla_total_size(1); /* IFLA_PROTO_DOWN */ } @@ -1223,6 +1226,8 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, nla_put_u32(skb, IFLA_GROUP, dev->group) || nla_put_u32(skb, IFLA_PROMISCUITY, dev->promiscuity) || nla_put_u32(skb, IFLA_NUM_TX_QUEUES, dev->num_tx_queues) || + nla_put_u32(skb, IFLA_GSO_MAX_SEGS, dev->gso_max_segs) || + nla_put_u32(skb, IFLA_GSO_MAX_SIZE, dev->gso_max_size) || #ifdef CONFIG_RPS nla_put_u32(skb, IFLA_NUM_RX_QUEUES, dev->num_rx_queues) || #endif @@ -1389,6 +1394,8 @@ static const struct nla_policy ifla_vf_policy[IFLA_VF_MAX+1] = { [IFLA_VF_RSS_QUERY_EN] = { .len = sizeof(struct ifla_vf_rss_query_en) }, [IFLA_VF_STATS] = { .type = NLA_NESTED }, [IFLA_VF_TRUST] = { .len = sizeof(struct ifla_vf_trust) }, + [IFLA_VF_IB_NODE_GUID] = { .len = sizeof(struct ifla_vf_guid) }, + [IFLA_VF_IB_PORT_GUID] = { .len = sizeof(struct ifla_vf_guid) }, }; static const struct nla_policy ifla_port_policy[IFLA_PORT_MAX+1] = { @@ -1593,6 +1600,22 @@ static int validate_linkmsg(struct net_device *dev, struct nlattr *tb[]) return 0; } +static int handle_infiniband_guid(struct net_device *dev, struct ifla_vf_guid *ivt, + int guid_type) +{ + const struct net_device_ops *ops = dev->netdev_ops; + + return ops->ndo_set_vf_guid(dev, ivt->vf, ivt->guid, guid_type); +} + +static int handle_vf_guid(struct net_device *dev, struct ifla_vf_guid *ivt, int guid_type) +{ + if (dev->type != ARPHRD_INFINIBAND) + return -EOPNOTSUPP; + + return handle_infiniband_guid(dev, ivt, guid_type); +} + static int do_setvfinfo(struct net_device *dev, struct nlattr **tb) { const struct net_device_ops *ops = dev->netdev_ops; @@ -1695,6 +1718,24 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb) return err; } + if (tb[IFLA_VF_IB_NODE_GUID]) { + struct ifla_vf_guid *ivt = nla_data(tb[IFLA_VF_IB_NODE_GUID]); + + if (!ops->ndo_set_vf_guid) + return -EOPNOTSUPP; + + return handle_vf_guid(dev, ivt, IFLA_VF_IB_NODE_GUID); + } + + if (tb[IFLA_VF_IB_PORT_GUID]) { + struct ifla_vf_guid *ivt = nla_data(tb[IFLA_VF_IB_PORT_GUID]); + + if (!ops->ndo_set_vf_guid) + return -EOPNOTSUPP; + + return handle_vf_guid(dev, ivt, IFLA_VF_IB_PORT_GUID); + } + return err; } @@ -2970,6 +3011,7 @@ int ndo_dflt_fdb_dump(struct sk_buff *skb, nlmsg_populate_fdb(skb, cb, dev, &idx, &dev->mc); out: netif_addr_unlock_bh(dev); + cb->args[1] = err; return idx; } EXPORT_SYMBOL(ndo_dflt_fdb_dump); @@ -3003,6 +3045,7 @@ static int rtnl_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb) ops = br_dev->netdev_ops; } + cb->args[1] = 0; for_each_netdev(net, dev) { if (brport_idx && (dev->ifindex != brport_idx)) continue; @@ -3030,12 +3073,16 @@ static int rtnl_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb) idx = cops->ndo_fdb_dump(skb, cb, br_dev, dev, idx); } + if (cb->args[1] == -EMSGSIZE) + break; if (dev->netdev_ops->ndo_fdb_dump) idx = dev->netdev_ops->ndo_fdb_dump(skb, cb, dev, NULL, idx); else idx = ndo_dflt_fdb_dump(skb, cb, dev, NULL, idx); + if (cb->args[1] == -EMSGSIZE) + break; cops = NULL; } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 7af7ec635d90..d04c2d1c8c87 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -801,9 +801,9 @@ void napi_consume_skb(struct sk_buff *skb, int budget) if (unlikely(!skb)) return; - /* if budget is 0 assume netpoll w/ IRQs disabled */ + /* Zero budget indicate non-NAPI context called us, like netpoll */ if (unlikely(!budget)) { - dev_consume_skb_irq(skb); + dev_consume_skb_any(skb); return; } @@ -815,7 +815,7 @@ void napi_consume_skb(struct sk_buff *skb, int budget) trace_consume_skb(skb); /* if SKB is a clone, don't handle this case */ - if (unlikely(skb->fclone != SKB_FCLONE_UNAVAILABLE)) { + if (skb->fclone != SKB_FCLONE_UNAVAILABLE) { __kfree_skb(skb); return; } @@ -1918,6 +1918,7 @@ static bool __skb_splice_bits(struct sk_buff *skb, struct pipe_inode_info *pipe, struct splice_pipe_desc *spd, struct sock *sk) { int seg; + struct sk_buff *iter; /* map the linear part : * If skb->head_frag is set, this 'linear' part is backed by a @@ -1944,6 +1945,19 @@ static bool __skb_splice_bits(struct sk_buff *skb, struct pipe_inode_info *pipe, return true; } + skb_walk_frags(skb, iter) { + if (*offset >= iter->len) { + *offset -= iter->len; + continue; + } + /* __skb_splice_bits() only fails if the output has no room + * left, so no point in going over the frag_list for the error + * case. + */ + if (__skb_splice_bits(iter, pipe, offset, len, spd, sk)) + return true; + } + return false; } @@ -1970,9 +1984,7 @@ ssize_t skb_socket_splice(struct sock *sk, /* * Map data from the skb to a pipe. Should handle both the linear part, - * the fragments, and the frag list. It does NOT handle frag lists within - * the frag list, if such a thing exists. We'd probably need to recurse to - * handle that cleanly. + * the fragments, and the frag list. */ int skb_splice_bits(struct sk_buff *skb, struct sock *sk, unsigned int offset, struct pipe_inode_info *pipe, unsigned int tlen, @@ -1991,29 +2003,10 @@ int skb_splice_bits(struct sk_buff *skb, struct sock *sk, unsigned int offset, .ops = &nosteal_pipe_buf_ops, .spd_release = sock_spd_release, }; - struct sk_buff *frag_iter; int ret = 0; - /* - * __skb_splice_bits() only fails if the output has no room left, - * so no point in going over the frag_list for the error case. - */ - if (__skb_splice_bits(skb, pipe, &offset, &tlen, &spd, sk)) - goto done; - else if (!tlen) - goto done; + __skb_splice_bits(skb, pipe, &offset, &tlen, &spd, sk); - /* - * now see if we have a frag_list to map - */ - skb_walk_frags(skb, frag_iter) { - if (!tlen) - break; - if (__skb_splice_bits(frag_iter, pipe, &offset, &tlen, &spd, sk)) - break; - } - -done: if (spd.nr_pages) ret = splice_cb(sk, pipe, &spd); @@ -3023,6 +3016,24 @@ int skb_append_pagefrags(struct sk_buff *skb, struct page *page, EXPORT_SYMBOL_GPL(skb_append_pagefrags); /** + * skb_push_rcsum - push skb and update receive checksum + * @skb: buffer to update + * @len: length of data pulled + * + * This function performs an skb_push on the packet and updates + * the CHECKSUM_COMPLETE checksum. It should be used on + * receive path processing instead of skb_push unless you know + * that the checksum difference is zero (e.g., a valid IP header) + * or you are setting ip_summed to CHECKSUM_NONE. + */ +static unsigned char *skb_push_rcsum(struct sk_buff *skb, unsigned len) +{ + skb_push(skb, len); + skb_postpush_rcsum(skb, skb->data, len); + return skb->data; +} + +/** * skb_pull_rcsum - pull skb and update receive checksum * @skb: buffer to update * @len: length of data pulled @@ -4167,9 +4178,9 @@ struct sk_buff *skb_checksum_trimmed(struct sk_buff *skb, if (!pskb_may_pull(skb_chk, offset)) goto err; - __skb_pull(skb_chk, offset); + skb_pull_rcsum(skb_chk, offset); ret = skb_chkf(skb_chk); - __skb_push(skb_chk, offset); + skb_push_rcsum(skb_chk, offset); if (ret) goto err; diff --git a/net/core/sock.c b/net/core/sock.c index 4493ff820c2c..2ce76e82857f 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -402,9 +402,8 @@ static void sock_disable_timestamp(struct sock *sk, unsigned long flags) } -int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) +int __sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) { - int err; unsigned long flags; struct sk_buff_head *list = &sk->sk_receive_queue; @@ -414,10 +413,6 @@ int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) return -ENOMEM; } - err = sk_filter(sk, skb); - if (err) - return err; - if (!sk_rmem_schedule(sk, skb, skb->truesize)) { atomic_inc(&sk->sk_drops); return -ENOBUFS; @@ -440,6 +435,18 @@ int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) sk->sk_data_ready(sk); return 0; } +EXPORT_SYMBOL(__sock_queue_rcv_skb); + +int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) +{ + int err; + + err = sk_filter(sk, skb); + if (err) + return err; + + return __sock_queue_rcv_skb(sk, skb); +} EXPORT_SYMBOL(sock_queue_rcv_skb); int sk_receive_skb(struct sock *sk, struct sk_buff *skb, const int nested) @@ -832,7 +839,8 @@ set_rcvbuf: !(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID)) { if (sk->sk_protocol == IPPROTO_TCP && sk->sk_type == SOCK_STREAM) { - if (sk->sk_state != TCP_ESTABLISHED) { + if ((1 << sk->sk_state) & + (TCPF_CLOSE | TCPF_LISTEN)) { ret = -EINVAL; break; } @@ -1418,8 +1426,12 @@ struct sock *sk_alloc(struct net *net, int family, gfp_t priority, } EXPORT_SYMBOL(sk_alloc); -void sk_destruct(struct sock *sk) +/* Sockets having SOCK_RCU_FREE will call this function after one RCU + * grace period. This is the case for UDP sockets and TCP listeners. + */ +static void __sk_destruct(struct rcu_head *head) { + struct sock *sk = container_of(head, struct sock, sk_rcu); struct sk_filter *filter; if (sk->sk_destruct) @@ -1448,6 +1460,14 @@ void sk_destruct(struct sock *sk) sk_prot_free(sk->sk_prot_creator, sk); } +void sk_destruct(struct sock *sk) +{ + if (sock_flag(sk, SOCK_RCU_FREE)) + call_rcu(&sk->sk_rcu, __sk_destruct); + else + __sk_destruct(&sk->sk_rcu); +} + static void __sk_free(struct sock *sk) { if (unlikely(sock_diag_has_destroy_listeners(sk) && sk->sk_net_refcnt)) @@ -1512,6 +1532,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) newsk->sk_dst_cache = NULL; newsk->sk_wmem_queued = 0; newsk->sk_forward_alloc = 0; + atomic_set(&newsk->sk_drops, 0); newsk->sk_send_head = NULL; newsk->sk_userlocks = sk->sk_userlocks & ~SOCK_BINDPORT_LOCK; @@ -1866,27 +1887,51 @@ struct sk_buff *sock_alloc_send_skb(struct sock *sk, unsigned long size, } EXPORT_SYMBOL(sock_alloc_send_skb); +int __sock_cmsg_send(struct sock *sk, struct msghdr *msg, struct cmsghdr *cmsg, + struct sockcm_cookie *sockc) +{ + u32 tsflags; + + switch (cmsg->cmsg_type) { + case SO_MARK: + if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) + return -EPERM; + if (cmsg->cmsg_len != CMSG_LEN(sizeof(u32))) + return -EINVAL; + sockc->mark = *(u32 *)CMSG_DATA(cmsg); + break; + case SO_TIMESTAMPING: + if (cmsg->cmsg_len != CMSG_LEN(sizeof(u32))) + return -EINVAL; + + tsflags = *(u32 *)CMSG_DATA(cmsg); + if (tsflags & ~SOF_TIMESTAMPING_TX_RECORD_MASK) + return -EINVAL; + + sockc->tsflags &= ~SOF_TIMESTAMPING_TX_RECORD_MASK; + sockc->tsflags |= tsflags; + break; + default: + return -EINVAL; + } + return 0; +} +EXPORT_SYMBOL(__sock_cmsg_send); + int sock_cmsg_send(struct sock *sk, struct msghdr *msg, struct sockcm_cookie *sockc) { struct cmsghdr *cmsg; + int ret; for_each_cmsghdr(cmsg, msg) { if (!CMSG_OK(msg, cmsg)) return -EINVAL; if (cmsg->cmsg_level != SOL_SOCKET) continue; - switch (cmsg->cmsg_type) { - case SO_MARK: - if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) - return -EPERM; - if (cmsg->cmsg_len != CMSG_LEN(sizeof(u32))) - return -EINVAL; - sockc->mark = *(u32 *)CMSG_DATA(cmsg); - break; - default: - return -EINVAL; - } + ret = __sock_cmsg_send(sk, msg, cmsg, sockc); + if (ret) + return ret; } return 0; } @@ -1908,7 +1953,7 @@ EXPORT_SYMBOL(sock_cmsg_send); bool skb_page_frag_refill(unsigned int sz, struct page_frag *pfrag, gfp_t gfp) { if (pfrag->page) { - if (atomic_read(&pfrag->page->_count) == 1) { + if (page_ref_count(pfrag->page) == 1) { pfrag->offset = 0; return true; } @@ -2142,6 +2187,15 @@ void __sk_mem_reclaim(struct sock *sk, int amount) } EXPORT_SYMBOL(__sk_mem_reclaim); +int sk_set_peek_off(struct sock *sk, int val) +{ + if (val < 0) + return -EINVAL; + + sk->sk_peek_off = val; + return 0; +} +EXPORT_SYMBOL_GPL(sk_set_peek_off); /* * Set of default routines for initialising struct proto_ops when diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c index a996ce8c8fb2..ca9e35bbe13c 100644 --- a/net/core/sock_diag.c +++ b/net/core/sock_diag.c @@ -67,6 +67,7 @@ int sock_diag_put_meminfo(struct sock *sk, struct sk_buff *skb, int attrtype) mem[SK_MEMINFO_WMEM_QUEUED] = sk->sk_wmem_queued; mem[SK_MEMINFO_OPTMEM] = atomic_read(&sk->sk_omem_alloc); mem[SK_MEMINFO_BACKLOG] = sk->sk_backlog.len; + mem[SK_MEMINFO_DROPS] = atomic_read(&sk->sk_drops); return nla_put(skb, attrtype, sizeof(mem), &mem); } |