aboutsummaryrefslogtreecommitdiff
path: root/net/core
diff options
context:
space:
mode:
Diffstat (limited to 'net/core')
-rw-r--r--net/core/dev.c19
-rw-r--r--net/core/filter.c14
-rw-r--r--net/core/flow_dissector.c2
-rw-r--r--net/core/flow_offload.c22
-rw-r--r--net/core/netpoll.c6
-rw-r--r--net/core/skbuff.c19
-rw-r--r--net/core/skmsg.c4
-rw-r--r--net/core/sock.c50
-rw-r--r--net/core/sock_diag.c3
-rw-r--r--net/core/sock_map.c22
-rw-r--r--net/core/stream.c16
11 files changed, 119 insertions, 58 deletions
diff --git a/net/core/dev.c b/net/core/dev.c
index fc676b2610e3..5156c0edebe8 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4374,12 +4374,17 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb,
act = bpf_prog_run_xdp(xdp_prog, xdp);
+ /* check if bpf_xdp_adjust_head was used */
off = xdp->data - orig_data;
- if (off > 0)
- __skb_pull(skb, off);
- else if (off < 0)
- __skb_push(skb, -off);
- skb->mac_header += off;
+ if (off) {
+ if (off > 0)
+ __skb_pull(skb, off);
+ else if (off < 0)
+ __skb_push(skb, -off);
+
+ skb->mac_header += off;
+ skb_reset_network_header(skb);
+ }
/* check if bpf_xdp_adjust_tail was used. it can only "shrink"
* pckt.
@@ -8753,6 +8758,8 @@ int register_netdevice(struct net_device *dev)
ret = notifier_to_errno(ret);
if (ret) {
rollback_registered(dev);
+ rcu_barrier();
+
dev->reg_state = NETREG_UNREGISTERED;
}
/*
@@ -9701,6 +9708,8 @@ static void __net_exit default_device_exit(struct net *net)
/* Push remaining network devices to init_net */
snprintf(fb_name, IFNAMSIZ, "dev%d", dev->ifindex);
+ if (__dev_get_by_name(&init_net, fb_name))
+ snprintf(fb_name, IFNAMSIZ, "dev%%d");
err = dev_change_net_namespace(dev, &init_net, fb_name);
if (err) {
pr_emerg("%s: failed to move %s to init_net: %d\n",
diff --git a/net/core/filter.c b/net/core/filter.c
index 4e2a79b2fd77..4c6a252d4212 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -7455,12 +7455,12 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type,
case offsetof(struct __sk_buff, gso_segs):
/* si->dst_reg = skb_shinfo(SKB); */
#ifdef NET_SKBUFF_DATA_USES_OFFSET
- *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, head),
- si->dst_reg, si->src_reg,
- offsetof(struct sk_buff, head));
*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, end),
BPF_REG_AX, si->src_reg,
offsetof(struct sk_buff, end));
+ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, head),
+ si->dst_reg, si->src_reg,
+ offsetof(struct sk_buff, head));
*insn++ = BPF_ALU64_REG(BPF_ADD, si->dst_reg, BPF_REG_AX);
#else
*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, end),
@@ -8757,13 +8757,13 @@ sk_reuseport_is_valid_access(int off, int size,
return size == size_default;
/* Fields that allow narrowing */
- case offsetof(struct sk_reuseport_md, eth_protocol):
+ case bpf_ctx_range(struct sk_reuseport_md, eth_protocol):
if (size < FIELD_SIZEOF(struct sk_buff, protocol))
return false;
/* fall through */
- case offsetof(struct sk_reuseport_md, ip_protocol):
- case offsetof(struct sk_reuseport_md, bind_inany):
- case offsetof(struct sk_reuseport_md, len):
+ case bpf_ctx_range(struct sk_reuseport_md, ip_protocol):
+ case bpf_ctx_range(struct sk_reuseport_md, bind_inany):
+ case bpf_ctx_range(struct sk_reuseport_md, len):
bpf_ctx_record_field_size(info, size_default);
return bpf_ctx_narrow_access_ok(off, size, size_default);
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 3e6fedb57bc1..2470b4b404e6 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -142,8 +142,8 @@ int skb_flow_dissector_bpf_prog_detach(const union bpf_attr *attr)
mutex_unlock(&flow_dissector_mutex);
return -ENOENT;
}
- bpf_prog_put(attached);
RCU_INIT_POINTER(net->flow_dissector_prog, NULL);
+ bpf_prog_put(attached);
mutex_unlock(&flow_dissector_mutex);
return 0;
}
diff --git a/net/core/flow_offload.c b/net/core/flow_offload.c
index 76f8db3841d7..d63b970784dc 100644
--- a/net/core/flow_offload.c
+++ b/net/core/flow_offload.c
@@ -165,7 +165,7 @@ void flow_rule_match_enc_opts(const struct flow_rule *rule,
}
EXPORT_SYMBOL(flow_rule_match_enc_opts);
-struct flow_block_cb *flow_block_cb_alloc(struct net *net, tc_setup_cb_t *cb,
+struct flow_block_cb *flow_block_cb_alloc(flow_setup_cb_t *cb,
void *cb_ident, void *cb_priv,
void (*release)(void *cb_priv))
{
@@ -175,7 +175,6 @@ struct flow_block_cb *flow_block_cb_alloc(struct net *net, tc_setup_cb_t *cb,
if (!block_cb)
return ERR_PTR(-ENOMEM);
- block_cb->net = net;
block_cb->cb = cb;
block_cb->cb_ident = cb_ident;
block_cb->cb_priv = cb_priv;
@@ -194,14 +193,13 @@ void flow_block_cb_free(struct flow_block_cb *block_cb)
}
EXPORT_SYMBOL(flow_block_cb_free);
-struct flow_block_cb *flow_block_cb_lookup(struct flow_block_offload *f,
- tc_setup_cb_t *cb, void *cb_ident)
+struct flow_block_cb *flow_block_cb_lookup(struct flow_block *block,
+ flow_setup_cb_t *cb, void *cb_ident)
{
struct flow_block_cb *block_cb;
- list_for_each_entry(block_cb, f->driver_block_list, driver_list) {
- if (block_cb->net == f->net &&
- block_cb->cb == cb &&
+ list_for_each_entry(block_cb, &block->cb_list, list) {
+ if (block_cb->cb == cb &&
block_cb->cb_ident == cb_ident)
return block_cb;
}
@@ -228,7 +226,7 @@ unsigned int flow_block_cb_decref(struct flow_block_cb *block_cb)
}
EXPORT_SYMBOL(flow_block_cb_decref);
-bool flow_block_cb_is_busy(tc_setup_cb_t *cb, void *cb_ident,
+bool flow_block_cb_is_busy(flow_setup_cb_t *cb, void *cb_ident,
struct list_head *driver_block_list)
{
struct flow_block_cb *block_cb;
@@ -245,7 +243,8 @@ EXPORT_SYMBOL(flow_block_cb_is_busy);
int flow_block_cb_setup_simple(struct flow_block_offload *f,
struct list_head *driver_block_list,
- tc_setup_cb_t *cb, void *cb_ident, void *cb_priv,
+ flow_setup_cb_t *cb,
+ void *cb_ident, void *cb_priv,
bool ingress_only)
{
struct flow_block_cb *block_cb;
@@ -261,8 +260,7 @@ int flow_block_cb_setup_simple(struct flow_block_offload *f,
if (flow_block_cb_is_busy(cb, cb_ident, driver_block_list))
return -EBUSY;
- block_cb = flow_block_cb_alloc(f->net, cb, cb_ident,
- cb_priv, NULL);
+ block_cb = flow_block_cb_alloc(cb, cb_ident, cb_priv, NULL);
if (IS_ERR(block_cb))
return PTR_ERR(block_cb);
@@ -270,7 +268,7 @@ int flow_block_cb_setup_simple(struct flow_block_offload *f,
list_add_tail(&block_cb->driver_list, driver_block_list);
return 0;
case FLOW_BLOCK_UNBIND:
- block_cb = flow_block_cb_lookup(f, cb, cb_ident);
+ block_cb = flow_block_cb_lookup(f->block, cb, cb_ident);
if (!block_cb)
return -ENOENT;
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index 2cf27da1baeb..849380a622ef 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -122,7 +122,7 @@ static void queue_process(struct work_struct *work)
txq = netdev_get_tx_queue(dev, q_index);
HARD_TX_LOCK(dev, txq, smp_processor_id());
if (netif_xmit_frozen_or_stopped(txq) ||
- netpoll_start_xmit(skb, dev, txq) != NETDEV_TX_OK) {
+ !dev_xmit_complete(netpoll_start_xmit(skb, dev, txq))) {
skb_queue_head(&npinfo->txq, skb);
HARD_TX_UNLOCK(dev, txq);
local_irq_restore(flags);
@@ -335,7 +335,7 @@ void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb,
HARD_TX_UNLOCK(dev, txq);
- if (status == NETDEV_TX_OK)
+ if (dev_xmit_complete(status))
break;
}
@@ -352,7 +352,7 @@ void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb,
}
- if (status != NETDEV_TX_OK) {
+ if (!dev_xmit_complete(status)) {
skb_queue_tail(&npinfo->txq, skb);
schedule_delayed_work(&npinfo->tx_work,0);
}
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 0338820ee0ec..982d8d12830e 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3664,6 +3664,25 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb,
int pos;
int dummy;
+ if (list_skb && !list_skb->head_frag && skb_headlen(list_skb) &&
+ (skb_shinfo(head_skb)->gso_type & SKB_GSO_DODGY)) {
+ /* gso_size is untrusted, and we have a frag_list with a linear
+ * non head_frag head.
+ *
+ * (we assume checking the first list_skb member suffices;
+ * i.e if either of the list_skb members have non head_frag
+ * head, then the first one has too).
+ *
+ * If head_skb's headlen does not fit requested gso_size, it
+ * means that the frag_list members do NOT terminate on exact
+ * gso_size boundaries. Hence we cannot perform skb_frag_t page
+ * sharing. Therefore we must fallback to copying the frag_list
+ * skbs; we do so by disabling SG.
+ */
+ if (mss != GSO_BY_FRAGS && mss != skb_headlen(head_skb))
+ features &= ~NETIF_F_SG;
+ }
+
__skb_push(head_skb, doffset);
proto = skb_network_protocol(head_skb, &dummy);
if (unlikely(!proto))
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 93bffaad2135..6832eeb4b785 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -585,12 +585,12 @@ EXPORT_SYMBOL_GPL(sk_psock_destroy);
void sk_psock_drop(struct sock *sk, struct sk_psock *psock)
{
- rcu_assign_sk_user_data(sk, NULL);
sk_psock_cork_free(psock);
sk_psock_zap_ingress(psock);
- sk_psock_restore_proto(sk, psock);
write_lock_bh(&sk->sk_callback_lock);
+ sk_psock_restore_proto(sk, psock);
+ rcu_assign_sk_user_data(sk, NULL);
if (psock->progs.skb_parser)
sk_psock_stop_strp(sk, psock);
write_unlock_bh(&sk->sk_callback_lock);
diff --git a/net/core/sock.c b/net/core/sock.c
index d57b0cc995a0..545fac19a711 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1992,6 +1992,19 @@ void skb_set_owner_w(struct sk_buff *skb, struct sock *sk)
}
EXPORT_SYMBOL(skb_set_owner_w);
+static bool can_skb_orphan_partial(const struct sk_buff *skb)
+{
+#ifdef CONFIG_TLS_DEVICE
+ /* Drivers depend on in-order delivery for crypto offload,
+ * partial orphan breaks out-of-order-OK logic.
+ */
+ if (skb->decrypted)
+ return false;
+#endif
+ return (skb->destructor == sock_wfree ||
+ (IS_ENABLED(CONFIG_INET) && skb->destructor == tcp_wfree));
+}
+
/* This helper is used by netem, as it can hold packets in its
* delay queue. We want to allow the owner socket to send more
* packets, as if they were already TX completed by a typical driver.
@@ -2003,11 +2016,7 @@ void skb_orphan_partial(struct sk_buff *skb)
if (skb_is_tcp_pure_ack(skb))
return;
- if (skb->destructor == sock_wfree
-#ifdef CONFIG_INET
- || skb->destructor == tcp_wfree
-#endif
- ) {
+ if (can_skb_orphan_partial(skb)) {
struct sock *sk = skb->sk;
if (refcount_inc_not_zero(&sk->sk_refcnt)) {
@@ -3278,16 +3287,17 @@ static __init int net_inuse_init(void)
core_initcall(net_inuse_init);
-static void assign_proto_idx(struct proto *prot)
+static int assign_proto_idx(struct proto *prot)
{
prot->inuse_idx = find_first_zero_bit(proto_inuse_idx, PROTO_INUSE_NR);
if (unlikely(prot->inuse_idx == PROTO_INUSE_NR - 1)) {
pr_err("PROTO_INUSE_NR exhausted\n");
- return;
+ return -ENOSPC;
}
set_bit(prot->inuse_idx, proto_inuse_idx);
+ return 0;
}
static void release_proto_idx(struct proto *prot)
@@ -3296,8 +3306,9 @@ static void release_proto_idx(struct proto *prot)
clear_bit(prot->inuse_idx, proto_inuse_idx);
}
#else
-static inline void assign_proto_idx(struct proto *prot)
+static inline int assign_proto_idx(struct proto *prot)
{
+ return 0;
}
static inline void release_proto_idx(struct proto *prot)
@@ -3346,6 +3357,8 @@ static int req_prot_init(const struct proto *prot)
int proto_register(struct proto *prot, int alloc_slab)
{
+ int ret = -ENOBUFS;
+
if (alloc_slab) {
prot->slab = kmem_cache_create_usercopy(prot->name,
prot->obj_size, 0,
@@ -3382,20 +3395,27 @@ int proto_register(struct proto *prot, int alloc_slab)
}
mutex_lock(&proto_list_mutex);
+ ret = assign_proto_idx(prot);
+ if (ret) {
+ mutex_unlock(&proto_list_mutex);
+ goto out_free_timewait_sock_slab_name;
+ }
list_add(&prot->node, &proto_list);
- assign_proto_idx(prot);
mutex_unlock(&proto_list_mutex);
- return 0;
+ return ret;
out_free_timewait_sock_slab_name:
- kfree(prot->twsk_prot->twsk_slab_name);
+ if (alloc_slab && prot->twsk_prot)
+ kfree(prot->twsk_prot->twsk_slab_name);
out_free_request_sock_slab:
- req_prot_cleanup(prot->rsk_prot);
+ if (alloc_slab) {
+ req_prot_cleanup(prot->rsk_prot);
- kmem_cache_destroy(prot->slab);
- prot->slab = NULL;
+ kmem_cache_destroy(prot->slab);
+ prot->slab = NULL;
+ }
out:
- return -ENOBUFS;
+ return ret;
}
EXPORT_SYMBOL(proto_register);
diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c
index 3312a5849a97..c13ffbd33d8d 100644
--- a/net/core/sock_diag.c
+++ b/net/core/sock_diag.c
@@ -19,6 +19,7 @@ static const struct sock_diag_handler *sock_diag_handlers[AF_MAX];
static int (*inet_rcv_compat)(struct sk_buff *skb, struct nlmsghdr *nlh);
static DEFINE_MUTEX(sock_diag_table_mutex);
static struct workqueue_struct *broadcast_wq;
+static atomic64_t cookie_gen;
u64 sock_gen_cookie(struct sock *sk)
{
@@ -27,7 +28,7 @@ u64 sock_gen_cookie(struct sock *sk)
if (res)
return res;
- res = atomic64_inc_return(&sock_net(sk)->cookie_gen);
+ res = atomic64_inc_return(&cookie_gen);
atomic64_cmpxchg(&sk->sk_cookie, 0, res);
}
}
diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index 52d4faeee18b..50916f9bc4f2 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -247,6 +247,8 @@ static void sock_map_free(struct bpf_map *map)
raw_spin_unlock_bh(&stab->lock);
rcu_read_unlock();
+ synchronize_rcu();
+
bpf_map_area_free(stab->sks);
kfree(stab);
}
@@ -276,16 +278,20 @@ static int __sock_map_delete(struct bpf_stab *stab, struct sock *sk_test,
struct sock **psk)
{
struct sock *sk;
+ int err = 0;
raw_spin_lock_bh(&stab->lock);
sk = *psk;
if (!sk_test || sk_test == sk)
- *psk = NULL;
+ sk = xchg(psk, NULL);
+
+ if (likely(sk))
+ sock_map_unref(sk, psk);
+ else
+ err = -EINVAL;
+
raw_spin_unlock_bh(&stab->lock);
- if (unlikely(!sk))
- return -EINVAL;
- sock_map_unref(sk, psk);
- return 0;
+ return err;
}
static void sock_map_delete_from_link(struct bpf_map *map, struct sock *sk,
@@ -328,6 +334,7 @@ static int sock_map_update_common(struct bpf_map *map, u32 idx,
struct sock *sk, u64 flags)
{
struct bpf_stab *stab = container_of(map, struct bpf_stab, map);
+ struct inet_connection_sock *icsk = inet_csk(sk);
struct sk_psock_link *link;
struct sk_psock *psock;
struct sock *osk;
@@ -338,6 +345,8 @@ static int sock_map_update_common(struct bpf_map *map, u32 idx,
return -EINVAL;
if (unlikely(idx >= map->max_entries))
return -E2BIG;
+ if (unlikely(icsk->icsk_ulp_data))
+ return -EINVAL;
link = sk_psock_init_link();
if (!link)
@@ -647,6 +656,7 @@ static int sock_hash_update_common(struct bpf_map *map, void *key,
struct sock *sk, u64 flags)
{
struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
+ struct inet_connection_sock *icsk = inet_csk(sk);
u32 key_size = map->key_size, hash;
struct bpf_htab_elem *elem, *elem_new;
struct bpf_htab_bucket *bucket;
@@ -657,6 +667,8 @@ static int sock_hash_update_common(struct bpf_map *map, void *key,
WARN_ON_ONCE(!rcu_read_lock_held());
if (unlikely(flags > BPF_EXIST))
return -EINVAL;
+ if (unlikely(icsk->icsk_ulp_data))
+ return -EINVAL;
link = sk_psock_init_link();
if (!link)
diff --git a/net/core/stream.c b/net/core/stream.c
index e94bb02a5629..4f1d4aa5fb38 100644
--- a/net/core/stream.c
+++ b/net/core/stream.c
@@ -120,7 +120,6 @@ int sk_stream_wait_memory(struct sock *sk, long *timeo_p)
int err = 0;
long vm_wait = 0;
long current_timeo = *timeo_p;
- bool noblock = (*timeo_p ? false : true);
DEFINE_WAIT_FUNC(wait, woken_wake_function);
if (sk_stream_memory_free(sk))
@@ -133,11 +132,8 @@ int sk_stream_wait_memory(struct sock *sk, long *timeo_p)
if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN))
goto do_error;
- if (!*timeo_p) {
- if (noblock)
- set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
- goto do_nonblock;
- }
+ if (!*timeo_p)
+ goto do_eagain;
if (signal_pending(current))
goto do_interrupted;
sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk);
@@ -169,7 +165,13 @@ out:
do_error:
err = -EPIPE;
goto out;
-do_nonblock:
+do_eagain:
+ /* Make sure that whenever EAGAIN is returned, EPOLLOUT event can
+ * be generated later.
+ * When TCP receives ACK packets that make room, tcp_check_space()
+ * only calls tcp_new_space() if SOCK_NOSPACE is set.
+ */
+ set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
err = -EAGAIN;
goto out;
do_interrupted:
Powered by cgit, Gruvboxed by Blaster4385.