diff options
Diffstat (limited to 'net/core')
| -rw-r--r-- | net/core/datagram.c | 3 | ||||
| -rw-r--r-- | net/core/dev.c | 12 | ||||
| -rw-r--r-- | net/core/devlink.c | 22 | ||||
| -rw-r--r-- | net/core/dst_cache.c | 19 | ||||
| -rw-r--r-- | net/core/fib_rules.c | 2 | ||||
| -rw-r--r-- | net/core/filter.c | 70 | ||||
| -rw-r--r-- | net/core/neighbour.c | 4 | ||||
| -rw-r--r-- | net/core/page_pool.c | 10 | ||||
| -rw-r--r-- | net/core/skbuff.c | 19 | ||||
| -rw-r--r-- | net/core/skmsg.c | 5 | ||||
| -rw-r--r-- | net/core/sock.c | 8 | ||||
| -rw-r--r-- | net/core/sock_map.c | 21 |
12 files changed, 134 insertions, 61 deletions
diff --git a/net/core/datagram.c b/net/core/datagram.c index 15ab9ffb27fe..ee290776c661 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -646,7 +646,8 @@ int __zerocopy_sg_from_iter(struct sock *sk, struct sk_buff *skb, skb->truesize += truesize; if (sk && sk->sk_type == SOCK_STREAM) { sk_wmem_queued_add(sk, truesize); - sk_mem_charge(sk, truesize); + if (!skb_zcopy_pure(skb)) + sk_mem_charge(sk, truesize); } else { refcount_add(truesize, &skb->sk->sk_wmem_alloc); } diff --git a/net/core/dev.c b/net/core/dev.c index edeb811c454e..2a352e668d10 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4210,7 +4210,10 @@ static int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev) if (dev->flags & IFF_UP) { int cpu = smp_processor_id(); /* ok because BHs are off */ - if (txq->xmit_lock_owner != cpu) { + /* Other cpus might concurrently change txq->xmit_lock_owner + * to -1 or to their cpu id, but not to our id. + */ + if (READ_ONCE(txq->xmit_lock_owner) != cpu) { if (dev_xmit_recursion()) goto recursion_alert; @@ -6928,7 +6931,7 @@ void napi_disable(struct napi_struct *n) might_sleep(); set_bit(NAPI_STATE_DISABLE, &n->state); - do { + for ( ; ; ) { val = READ_ONCE(n->state); if (val & (NAPIF_STATE_SCHED | NAPIF_STATE_NPSVC)) { usleep_range(20, 200); @@ -6937,7 +6940,10 @@ void napi_disable(struct napi_struct *n) new = val | NAPIF_STATE_SCHED | NAPIF_STATE_NPSVC; new &= ~(NAPIF_STATE_THREADED | NAPIF_STATE_PREFER_BUSY_POLL); - } while (cmpxchg(&n->state, val, new) != val); + + if (cmpxchg(&n->state, val, new) == val) + break; + } hrtimer_cancel(&n->timer); diff --git a/net/core/devlink.c b/net/core/devlink.c index 6b5ee862429e..c06c9ba6e8c5 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -66,7 +66,7 @@ struct devlink { u8 reload_failed:1; refcount_t refcount; struct completion comp; - char priv[0] __aligned(NETDEV_ALIGN); + char priv[] __aligned(NETDEV_ALIGN); }; void *devlink_priv(struct devlink *devlink) @@ -4110,14 +4110,6 @@ static int devlink_nl_cmd_reload(struct sk_buff *skb, struct genl_info *info) return err; } - if (info->attrs[DEVLINK_ATTR_NETNS_PID] || - info->attrs[DEVLINK_ATTR_NETNS_FD] || - info->attrs[DEVLINK_ATTR_NETNS_ID]) { - dest_net = devlink_netns_get(skb, info); - if (IS_ERR(dest_net)) - return PTR_ERR(dest_net); - } - if (info->attrs[DEVLINK_ATTR_RELOAD_ACTION]) action = nla_get_u8(info->attrs[DEVLINK_ATTR_RELOAD_ACTION]); else @@ -4160,6 +4152,14 @@ static int devlink_nl_cmd_reload(struct sk_buff *skb, struct genl_info *info) return -EINVAL; } } + if (info->attrs[DEVLINK_ATTR_NETNS_PID] || + info->attrs[DEVLINK_ATTR_NETNS_FD] || + info->attrs[DEVLINK_ATTR_NETNS_ID]) { + dest_net = devlink_netns_get(skb, info); + if (IS_ERR(dest_net)) + return PTR_ERR(dest_net); + } + err = devlink_reload(devlink, dest_net, action, limit, &actions_performed, info->extack); if (dest_net) @@ -4229,7 +4229,9 @@ static void __devlink_flash_update_notify(struct devlink *devlink, WARN_ON(cmd != DEVLINK_CMD_FLASH_UPDATE && cmd != DEVLINK_CMD_FLASH_UPDATE_END && cmd != DEVLINK_CMD_FLASH_UPDATE_STATUS); - WARN_ON(!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED)); + + if (!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED)) + return; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) diff --git a/net/core/dst_cache.c b/net/core/dst_cache.c index be74ab4551c2..0ccfd5fa5cb9 100644 --- a/net/core/dst_cache.c +++ b/net/core/dst_cache.c @@ -162,3 +162,22 @@ void dst_cache_destroy(struct dst_cache *dst_cache) free_percpu(dst_cache->cache); } EXPORT_SYMBOL_GPL(dst_cache_destroy); + +void dst_cache_reset_now(struct dst_cache *dst_cache) +{ + int i; + + if (!dst_cache->cache) + return; + + dst_cache->reset_ts = jiffies; + for_each_possible_cpu(i) { + struct dst_cache_pcpu *idst = per_cpu_ptr(dst_cache->cache, i); + struct dst_entry *dst = idst->dst; + + idst->cookie = 0; + idst->dst = NULL; + dst_release(dst); + } +} +EXPORT_SYMBOL_GPL(dst_cache_reset_now); diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index 79df7cd9dbc1..1bb567a3b329 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -323,7 +323,7 @@ jumped: if (!err && ops->suppress && INDIRECT_CALL_MT(ops->suppress, fib6_rule_suppress, fib4_rule_suppress, - rule, arg)) + rule, flags, arg)) continue; if (err != -EAGAIN) { diff --git a/net/core/filter.c b/net/core/filter.c index 8e8d3b49c297..6102f093d59a 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -7162,6 +7162,8 @@ sock_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) #endif case BPF_FUNC_sk_storage_get: return &bpf_sk_storage_get_cg_sock_proto; + case BPF_FUNC_ktime_get_coarse_ns: + return &bpf_ktime_get_coarse_ns_proto; default: return bpf_base_func_proto(func_id); } @@ -9756,22 +9758,46 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, static struct bpf_insn *bpf_convert_data_end_access(const struct bpf_insn *si, struct bpf_insn *insn) { - /* si->dst_reg = skb->data */ + int reg; + int temp_reg_off = offsetof(struct sk_buff, cb) + + offsetof(struct sk_skb_cb, temp_reg); + + if (si->src_reg == si->dst_reg) { + /* We need an extra register, choose and save a register. */ + reg = BPF_REG_9; + if (si->src_reg == reg || si->dst_reg == reg) + reg--; + if (si->src_reg == reg || si->dst_reg == reg) + reg--; + *insn++ = BPF_STX_MEM(BPF_DW, si->src_reg, reg, temp_reg_off); + } else { + reg = si->dst_reg; + } + + /* reg = skb->data */ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, data), - si->dst_reg, si->src_reg, + reg, si->src_reg, offsetof(struct sk_buff, data)); /* AX = skb->len */ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, len), BPF_REG_AX, si->src_reg, offsetof(struct sk_buff, len)); - /* si->dst_reg = skb->data + skb->len */ - *insn++ = BPF_ALU64_REG(BPF_ADD, si->dst_reg, BPF_REG_AX); + /* reg = skb->data + skb->len */ + *insn++ = BPF_ALU64_REG(BPF_ADD, reg, BPF_REG_AX); /* AX = skb->data_len */ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, data_len), BPF_REG_AX, si->src_reg, offsetof(struct sk_buff, data_len)); - /* si->dst_reg = skb->data + skb->len - skb->data_len */ - *insn++ = BPF_ALU64_REG(BPF_SUB, si->dst_reg, BPF_REG_AX); + + /* reg = skb->data + skb->len - skb->data_len */ + *insn++ = BPF_ALU64_REG(BPF_SUB, reg, BPF_REG_AX); + + if (si->src_reg == si->dst_reg) { + /* Restore the saved register */ + *insn++ = BPF_MOV64_REG(BPF_REG_AX, si->src_reg); + *insn++ = BPF_MOV64_REG(si->dst_reg, reg); + *insn++ = BPF_LDX_MEM(BPF_DW, reg, BPF_REG_AX, temp_reg_off); + } return insn; } @@ -9782,11 +9808,33 @@ static u32 sk_skb_convert_ctx_access(enum bpf_access_type type, struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; + int off; switch (si->off) { case offsetof(struct __sk_buff, data_end): insn = bpf_convert_data_end_access(si, insn); break; + case offsetof(struct __sk_buff, cb[0]) ... + offsetofend(struct __sk_buff, cb[4]) - 1: + BUILD_BUG_ON(sizeof_field(struct sk_skb_cb, data) < 20); + BUILD_BUG_ON((offsetof(struct sk_buff, cb) + + offsetof(struct sk_skb_cb, data)) % + sizeof(__u64)); + + prog->cb_access = 1; + off = si->off; + off -= offsetof(struct __sk_buff, cb[0]); + off += offsetof(struct sk_buff, cb); + off += offsetof(struct sk_skb_cb, data); + if (type == BPF_WRITE) + *insn++ = BPF_STX_MEM(BPF_SIZE(si->code), si->dst_reg, + si->src_reg, off); + else + *insn++ = BPF_LDX_MEM(BPF_SIZE(si->code), si->dst_reg, + si->src_reg, off); + break; + + default: return bpf_convert_ctx_access(type, si, insn_buf, prog, target_size); @@ -10281,6 +10329,8 @@ sk_reuseport_func_proto(enum bpf_func_id func_id, return &sk_reuseport_load_bytes_relative_proto; case BPF_FUNC_get_socket_cookie: return &bpf_get_socket_ptr_cookie_proto; + case BPF_FUNC_ktime_get_coarse_ns: + return &bpf_ktime_get_coarse_ns_proto; default: return bpf_base_func_proto(func_id); } @@ -10423,8 +10473,10 @@ BPF_CALL_3(bpf_sk_lookup_assign, struct bpf_sk_lookup_kern *, ctx, return -EINVAL; if (unlikely(sk && sk_is_refcounted(sk))) return -ESOCKTNOSUPPORT; /* reject non-RCU freed sockets */ - if (unlikely(sk && sk->sk_state == TCP_ESTABLISHED)) - return -ESOCKTNOSUPPORT; /* reject connected sockets */ + if (unlikely(sk && sk_is_tcp(sk) && sk->sk_state != TCP_LISTEN)) + return -ESOCKTNOSUPPORT; /* only accept TCP socket in LISTEN */ + if (unlikely(sk && sk_is_udp(sk) && sk->sk_state != TCP_CLOSE)) + return -ESOCKTNOSUPPORT; /* only accept UDP socket in CLOSE */ /* Check if socket is suitable for packet L3/L4 protocol */ if (sk && sk->sk_protocol != ctx->protocol) @@ -10785,6 +10837,8 @@ bpf_sk_base_func_proto(enum bpf_func_id func_id) case BPF_FUNC_skc_to_unix_sock: func = &bpf_skc_to_unix_sock_proto; break; + case BPF_FUNC_ktime_get_coarse_ns: + return &bpf_ktime_get_coarse_ns_proto; default: return bpf_base_func_proto(func_id); } diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 47931c8be04b..dda12fbd177b 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -763,11 +763,10 @@ struct pneigh_entry * pneigh_lookup(struct neigh_table *tbl, ASSERT_RTNL(); - n = kmalloc(sizeof(*n) + key_len, GFP_KERNEL); + n = kzalloc(sizeof(*n) + key_len, GFP_KERNEL); if (!n) goto out; - n->protocol = 0; write_pnet(&n->net, net); memcpy(n->key, pkey, key_len); n->dev = dev; @@ -1779,6 +1778,7 @@ int neigh_table_clear(int index, struct neigh_table *tbl) { neigh_tables[index] = NULL; /* It is not clean... Fix it to unload IPv6 module safely */ + cancel_delayed_work_sync(&tbl->managed_work); cancel_delayed_work_sync(&tbl->gc_work); del_timer_sync(&tbl->proxy_timer); pneigh_queue_purge(&tbl->proxy_queue); diff --git a/net/core/page_pool.c b/net/core/page_pool.c index 9b60e4301a44..1a6978427d6c 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -49,12 +49,6 @@ static int page_pool_init(struct page_pool *pool, * which is the XDP_TX use-case. */ if (pool->p.flags & PP_FLAG_DMA_MAP) { - /* DMA-mapping is not supported on 32-bit systems with - * 64-bit DMA mapping. - */ - if (sizeof(dma_addr_t) > sizeof(unsigned long)) - return -EOPNOTSUPP; - if ((pool->p.dma_dir != DMA_FROM_DEVICE) && (pool->p.dma_dir != DMA_BIDIRECTIONAL)) return -EINVAL; @@ -75,6 +69,10 @@ static int page_pool_init(struct page_pool *pool, */ } + if (PAGE_POOL_DMA_USE_PP_FRAG_COUNT && + pool->p.flags & PP_FLAG_PAGE_FRAG) + return -EINVAL; + if (ptr_ring_init(&pool->ring, ring_qsize, GFP_KERNEL) < 0) return -ENOMEM; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 67a9188d8a49..909db87d7383 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -832,7 +832,7 @@ void skb_dump(const char *level, const struct sk_buff *skb, bool full_pkt) ntohs(skb->protocol), skb->pkt_type, skb->skb_iif); if (dev) - printk("%sdev name=%s feat=0x%pNF\n", + printk("%sdev name=%s feat=%pNF\n", level, dev->name, &dev->features); if (sk) printk("%ssk family=%hu type=%u proto=%u\n", @@ -3433,8 +3433,9 @@ static inline void skb_split_no_header(struct sk_buff *skb, void skb_split(struct sk_buff *skb, struct sk_buff *skb1, const u32 len) { int pos = skb_headlen(skb); + const int zc_flags = SKBFL_SHARED_FRAG | SKBFL_PURE_ZEROCOPY; - skb_shinfo(skb1)->flags |= skb_shinfo(skb)->flags & SKBFL_SHARED_FRAG; + skb_shinfo(skb1)->flags |= skb_shinfo(skb)->flags & zc_flags; skb_zerocopy_clone(skb1, skb, 0); if (len < pos) /* Split line is inside header. */ skb_split_inside_header(skb, skb1, len, pos); @@ -3449,19 +3450,7 @@ EXPORT_SYMBOL(skb_split); */ static int skb_prepare_for_shift(struct sk_buff *skb) { - int ret = 0; - - if (skb_cloned(skb)) { - /* Save and restore truesize: pskb_expand_head() may reallocate - * memory where ksize(kmalloc(S)) != ksize(kmalloc(S)), but we - * cannot change truesize at this point. - */ - unsigned int save_truesize = skb->truesize; - - ret = pskb_expand_head(skb, 0, 0, GFP_ATOMIC); - skb->truesize = save_truesize; - } - return ret; + return skb_unclone_keeptruesize(skb, GFP_ATOMIC); } /** diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 1ae52ac943f6..8eb671c827f9 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -1124,6 +1124,8 @@ void sk_psock_start_strp(struct sock *sk, struct sk_psock *psock) void sk_psock_stop_strp(struct sock *sk, struct sk_psock *psock) { + psock_set_prog(&psock->progs.stream_parser, NULL); + if (!psock->saved_data_ready) return; @@ -1212,6 +1214,9 @@ void sk_psock_start_verdict(struct sock *sk, struct sk_psock *psock) void sk_psock_stop_verdict(struct sock *sk, struct sk_psock *psock) { + psock_set_prog(&psock->progs.stream_verdict, NULL); + psock_set_prog(&psock->progs.skb_verdict, NULL); + if (!psock->saved_data_ready) return; diff --git a/net/core/sock.c b/net/core/sock.c index 9862eefce21e..41e91d0f7061 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -976,7 +976,7 @@ static int sock_reserve_memory(struct sock *sk, int bytes) bool charged; int pages; - if (!mem_cgroup_sockets_enabled || !sk->sk_memcg) + if (!mem_cgroup_sockets_enabled || !sk->sk_memcg || !sk_has_account(sk)) return -EOPNOTSUPP; if (!bytes) @@ -2124,8 +2124,10 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) newsk->sk_prot_creator = prot; /* SANITY */ - if (likely(newsk->sk_net_refcnt)) + if (likely(newsk->sk_net_refcnt)) { get_net(sock_net(newsk)); + sock_inuse_add(sock_net(newsk), 1); + } sk_node_init(&newsk->sk_node); sock_lock_init(newsk); bh_lock_sock(newsk); @@ -2197,8 +2199,6 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) newsk->sk_err_soft = 0; newsk->sk_priority = 0; newsk->sk_incoming_cpu = raw_smp_processor_id(); - if (likely(newsk->sk_net_refcnt)) - sock_inuse_add(sock_net(newsk), 1); /* Before updating sk_refcnt, we must commit prior changes to memory * (Documentation/RCU/rculist_nulls.rst for details) diff --git a/net/core/sock_map.c b/net/core/sock_map.c index e252b8ec2b85..4ca4b11f4e5f 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -167,8 +167,11 @@ static void sock_map_del_link(struct sock *sk, write_lock_bh(&sk->sk_callback_lock); if (strp_stop) sk_psock_stop_strp(sk, psock); - else + if (verdict_stop) sk_psock_stop_verdict(sk, psock); + + if (psock->psock_update_sk_prot) + psock->psock_update_sk_prot(sk, psock, false); write_unlock_bh(&sk->sk_callback_lock); } } @@ -282,6 +285,12 @@ static int sock_map_link(struct bpf_map *map, struct sock *sk) if (msg_parser) psock_set_prog(&psock->progs.msg_parser, msg_parser); + if (stream_parser) + psock_set_prog(&psock->progs.stream_parser, stream_parser); + if (stream_verdict) + psock_set_prog(&psock->progs.stream_verdict, stream_verdict); + if (skb_verdict) + psock_set_prog(&psock->progs.skb_verdict, skb_verdict); ret = sock_map_init_proto(sk, psock); if (ret < 0) @@ -292,14 +301,10 @@ static int sock_map_link(struct bpf_map *map, struct sock *sk) ret = sk_psock_init_strp(sk, psock); if (ret) goto out_unlock_drop; - psock_set_prog(&psock->progs.stream_verdict, stream_verdict); - psock_set_prog(&psock->progs.stream_parser, stream_parser); sk_psock_start_strp(sk, psock); } else if (!stream_parser && stream_verdict && !psock->saved_data_ready) { - psock_set_prog(&psock->progs.stream_verdict, stream_verdict); sk_psock_start_verdict(sk,psock); } else if (!stream_verdict && skb_verdict && !psock->saved_data_ready) { - psock_set_prog(&psock->progs.skb_verdict, skb_verdict); sk_psock_start_verdict(sk, psock); } write_unlock_bh(&sk->sk_callback_lock); @@ -511,12 +516,6 @@ static bool sock_map_op_okay(const struct bpf_sock_ops_kern *ops) ops->op == BPF_SOCK_OPS_TCP_LISTEN_CB; } -static bool sk_is_tcp(const struct sock *sk) -{ - return sk->sk_type == SOCK_STREAM && - sk->sk_protocol == IPPROTO_TCP; -} - static bool sock_map_redirect_allowed(const struct sock *sk) { if (sk_is_tcp(sk)) |