aboutsummaryrefslogtreecommitdiff
path: root/net/core
diff options
context:
space:
mode:
Diffstat (limited to 'net/core')
-rw-r--r--net/core/dev.c4
-rw-r--r--net/core/filter.c52
-rw-r--r--net/core/net_namespace.c10
-rw-r--r--net/core/rtnetlink.c4
-rw-r--r--net/core/sock.c42
-rw-r--r--net/core/sock_map.c12
6 files changed, 67 insertions, 57 deletions
diff --git a/net/core/dev.c b/net/core/dev.c
index ea5fbcd133ae..8453e14d301b 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3639,6 +3639,9 @@ int skb_csum_hwoffload_help(struct sk_buff *skb,
return 0;
if (features & (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM)) {
+ if (vlan_get_protocol(skb) == htons(ETH_P_IPV6) &&
+ skb_network_header_len(skb) != sizeof(struct ipv6hdr))
+ goto sw_checksum;
switch (skb->csum_offset) {
case offsetof(struct tcphdr, check):
case offsetof(struct udphdr, check):
@@ -3646,6 +3649,7 @@ int skb_csum_hwoffload_help(struct sk_buff *skb,
}
}
+sw_checksum:
return skb_checksum_help(skb);
}
EXPORT_SYMBOL(skb_csum_hwoffload_help);
diff --git a/net/core/filter.c b/net/core/filter.c
index bd0d08bf76bb..fb56567c551e 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2249,7 +2249,7 @@ static int bpf_out_neigh_v6(struct net *net, struct sk_buff *skb,
rcu_read_unlock();
return ret;
}
- rcu_read_unlock_bh();
+ rcu_read_unlock();
if (dst)
IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES);
out_drop:
@@ -2438,9 +2438,9 @@ out:
/* Internal, non-exposed redirect flags. */
enum {
- BPF_F_NEIGH = (1ULL << 1),
- BPF_F_PEER = (1ULL << 2),
- BPF_F_NEXTHOP = (1ULL << 3),
+ BPF_F_NEIGH = (1ULL << 16),
+ BPF_F_PEER = (1ULL << 17),
+ BPF_F_NEXTHOP = (1ULL << 18),
#define BPF_F_REDIRECT_INTERNAL (BPF_F_NEIGH | BPF_F_PEER | BPF_F_NEXTHOP)
};
@@ -2450,6 +2450,8 @@ BPF_CALL_3(bpf_clone_redirect, struct sk_buff *, skb, u32, ifindex, u64, flags)
struct sk_buff *clone;
int ret;
+ BUILD_BUG_ON(BPF_F_REDIRECT_INTERNAL & BPF_F_REDIRECT_FLAGS);
+
if (unlikely(flags & (~(BPF_F_INGRESS) | BPF_F_REDIRECT_INTERNAL)))
return -EINVAL;
@@ -6279,24 +6281,16 @@ BPF_CALL_5(bpf_skb_check_mtu, struct sk_buff *, skb,
{
int ret = BPF_MTU_CHK_RET_FRAG_NEEDED;
struct net_device *dev = skb->dev;
- int skb_len, dev_len;
- int mtu = 0;
-
- if (unlikely(flags & ~(BPF_MTU_CHK_SEGS))) {
- ret = -EINVAL;
- goto out;
- }
+ int mtu, dev_len, skb_len;
- if (unlikely(flags & BPF_MTU_CHK_SEGS && (len_diff || *mtu_len))) {
- ret = -EINVAL;
- goto out;
- }
+ if (unlikely(flags & ~(BPF_MTU_CHK_SEGS)))
+ return -EINVAL;
+ if (unlikely(flags & BPF_MTU_CHK_SEGS && (len_diff || *mtu_len)))
+ return -EINVAL;
dev = __dev_via_ifindex(dev, ifindex);
- if (unlikely(!dev)) {
- ret = -ENODEV;
- goto out;
- }
+ if (unlikely(!dev))
+ return -ENODEV;
mtu = READ_ONCE(dev->mtu);
dev_len = mtu + dev->hard_header_len;
@@ -6331,19 +6325,15 @@ BPF_CALL_5(bpf_xdp_check_mtu, struct xdp_buff *, xdp,
struct net_device *dev = xdp->rxq->dev;
int xdp_len = xdp->data_end - xdp->data;
int ret = BPF_MTU_CHK_RET_SUCCESS;
- int mtu = 0, dev_len;
+ int mtu, dev_len;
/* XDP variant doesn't support multi-buffer segment check (yet) */
- if (unlikely(flags)) {
- ret = -EINVAL;
- goto out;
- }
+ if (unlikely(flags))
+ return -EINVAL;
dev = __dev_via_ifindex(dev, ifindex);
- if (unlikely(!dev)) {
- ret = -ENODEV;
- goto out;
- }
+ if (unlikely(!dev))
+ return -ENODEV;
mtu = READ_ONCE(dev->mtu);
dev_len = mtu + dev->hard_header_len;
@@ -6355,7 +6345,7 @@ BPF_CALL_5(bpf_xdp_check_mtu, struct xdp_buff *, xdp,
xdp_len += len_diff; /* minus result pass check */
if (xdp_len > dev_len)
ret = BPF_MTU_CHK_RET_FRAG_NEEDED;
-out:
+
*mtu_len = mtu;
return ret;
}
@@ -6366,7 +6356,7 @@ static const struct bpf_func_proto bpf_skb_check_mtu_proto = {
.ret_type = RET_INTEGER,
.arg1_type = ARG_PTR_TO_CTX,
.arg2_type = ARG_ANYTHING,
- .arg3_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_ALIGNED,
+ .arg3_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_WRITE | MEM_ALIGNED,
.arg3_size = sizeof(u32),
.arg4_type = ARG_ANYTHING,
.arg5_type = ARG_ANYTHING,
@@ -6378,7 +6368,7 @@ static const struct bpf_func_proto bpf_xdp_check_mtu_proto = {
.ret_type = RET_INTEGER,
.arg1_type = ARG_PTR_TO_CTX,
.arg2_type = ARG_ANYTHING,
- .arg3_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_ALIGNED,
+ .arg3_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_WRITE | MEM_ALIGNED,
.arg3_size = sizeof(u32),
.arg4_type = ARG_ANYTHING,
.arg5_type = ARG_ANYTHING,
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index e39479f1c9a4..b231b27d8268 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -694,20 +694,18 @@ EXPORT_SYMBOL_GPL(get_net_ns);
struct net *get_net_ns_by_fd(int fd)
{
- struct fd f = fdget(fd);
- struct net *net = ERR_PTR(-EINVAL);
+ CLASS(fd, f)(fd);
- if (!fd_file(f))
+ if (fd_empty(f))
return ERR_PTR(-EBADF);
if (proc_ns_file(fd_file(f))) {
struct ns_common *ns = get_proc_ns(file_inode(fd_file(f)));
if (ns->ops == &netns_operations)
- net = get_net(container_of(ns, struct net, ns));
+ return get_net(container_of(ns, struct net, ns));
}
- fdput(f);
- return net;
+ return ERR_PTR(-EINVAL);
}
EXPORT_SYMBOL_GPL(get_net_ns_by_fd);
#endif
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index e30e7ea0207d..2ba5cd965d3f 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -2032,7 +2032,7 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = {
[IFLA_NUM_TX_QUEUES] = { .type = NLA_U32 },
[IFLA_NUM_RX_QUEUES] = { .type = NLA_U32 },
[IFLA_GSO_MAX_SEGS] = { .type = NLA_U32 },
- [IFLA_GSO_MAX_SIZE] = { .type = NLA_U32 },
+ [IFLA_GSO_MAX_SIZE] = NLA_POLICY_MIN(NLA_U32, MAX_TCP_HEADER + 1),
[IFLA_PHYS_PORT_ID] = { .type = NLA_BINARY, .len = MAX_PHYS_ITEM_ID_LEN },
[IFLA_CARRIER_CHANGES] = { .type = NLA_U32 }, /* ignored */
[IFLA_PHYS_SWITCH_ID] = { .type = NLA_BINARY, .len = MAX_PHYS_ITEM_ID_LEN },
@@ -2057,7 +2057,7 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = {
[IFLA_TSO_MAX_SIZE] = { .type = NLA_REJECT },
[IFLA_TSO_MAX_SEGS] = { .type = NLA_REJECT },
[IFLA_ALLMULTI] = { .type = NLA_REJECT },
- [IFLA_GSO_IPV4_MAX_SIZE] = { .type = NLA_U32 },
+ [IFLA_GSO_IPV4_MAX_SIZE] = NLA_POLICY_MIN(NLA_U32, MAX_TCP_HEADER + 1),
[IFLA_GRO_IPV4_MAX_SIZE] = { .type = NLA_U32 },
};
diff --git a/net/core/sock.c b/net/core/sock.c
index 039be95c40cf..da50df485090 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1052,32 +1052,34 @@ static int sock_reserve_memory(struct sock *sk, int bytes)
#ifdef CONFIG_PAGE_POOL
-/* This is the number of tokens that the user can SO_DEVMEM_DONTNEED in
- * 1 syscall. The limit exists to limit the amount of memory the kernel
- * allocates to copy these tokens.
+/* This is the number of tokens and frags that the user can SO_DEVMEM_DONTNEED
+ * in 1 syscall. The limit exists to limit the amount of memory the kernel
+ * allocates to copy these tokens, and to prevent looping over the frags for
+ * too long.
*/
#define MAX_DONTNEED_TOKENS 128
+#define MAX_DONTNEED_FRAGS 1024
static noinline_for_stack int
sock_devmem_dontneed(struct sock *sk, sockptr_t optval, unsigned int optlen)
{
unsigned int num_tokens, i, j, k, netmem_num = 0;
struct dmabuf_token *tokens;
+ int ret = 0, num_frags = 0;
netmem_ref netmems[16];
- int ret = 0;
if (!sk_is_tcp(sk))
return -EBADF;
- if (optlen % sizeof(struct dmabuf_token) ||
+ if (optlen % sizeof(*tokens) ||
optlen > sizeof(*tokens) * MAX_DONTNEED_TOKENS)
return -EINVAL;
- tokens = kvmalloc_array(optlen, sizeof(*tokens), GFP_KERNEL);
+ num_tokens = optlen / sizeof(*tokens);
+ tokens = kvmalloc_array(num_tokens, sizeof(*tokens), GFP_KERNEL);
if (!tokens)
return -ENOMEM;
- num_tokens = optlen / sizeof(struct dmabuf_token);
if (copy_from_sockptr(tokens, optval, optlen)) {
kvfree(tokens);
return -EFAULT;
@@ -1086,24 +1088,28 @@ sock_devmem_dontneed(struct sock *sk, sockptr_t optval, unsigned int optlen)
xa_lock_bh(&sk->sk_user_frags);
for (i = 0; i < num_tokens; i++) {
for (j = 0; j < tokens[i].token_count; j++) {
+ if (++num_frags > MAX_DONTNEED_FRAGS)
+ goto frag_limit_reached;
+
netmem_ref netmem = (__force netmem_ref)__xa_erase(
&sk->sk_user_frags, tokens[i].token_start + j);
- if (netmem &&
- !WARN_ON_ONCE(!netmem_is_net_iov(netmem))) {
- netmems[netmem_num++] = netmem;
- if (netmem_num == ARRAY_SIZE(netmems)) {
- xa_unlock_bh(&sk->sk_user_frags);
- for (k = 0; k < netmem_num; k++)
- WARN_ON_ONCE(!napi_pp_put_page(netmems[k]));
- netmem_num = 0;
- xa_lock_bh(&sk->sk_user_frags);
- }
- ret++;
+ if (!netmem || WARN_ON_ONCE(!netmem_is_net_iov(netmem)))
+ continue;
+
+ netmems[netmem_num++] = netmem;
+ if (netmem_num == ARRAY_SIZE(netmems)) {
+ xa_unlock_bh(&sk->sk_user_frags);
+ for (k = 0; k < netmem_num; k++)
+ WARN_ON_ONCE(!napi_pp_put_page(netmems[k]));
+ netmem_num = 0;
+ xa_lock_bh(&sk->sk_user_frags);
}
+ ret++;
}
}
+frag_limit_reached:
xa_unlock_bh(&sk->sk_user_frags);
for (k = 0; k < netmem_num; k++)
WARN_ON_ONCE(!napi_pp_put_page(netmems[k]));
diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index 242c91a6e3d3..78347d7d25ef 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -647,6 +647,8 @@ BPF_CALL_4(bpf_sk_redirect_map, struct sk_buff *, skb,
sk = __sock_map_lookup_elem(map, key);
if (unlikely(!sk || !sock_map_redirect_allowed(sk)))
return SK_DROP;
+ if ((flags & BPF_F_INGRESS) && sk_is_vsock(sk))
+ return SK_DROP;
skb_bpf_set_redir(skb, sk, flags & BPF_F_INGRESS);
return SK_PASS;
@@ -675,6 +677,8 @@ BPF_CALL_4(bpf_msg_redirect_map, struct sk_msg *, msg,
return SK_DROP;
if (!(flags & BPF_F_INGRESS) && !sk_is_tcp(sk))
return SK_DROP;
+ if (sk_is_vsock(sk))
+ return SK_DROP;
msg->flags = flags;
msg->sk_redir = sk;
@@ -1249,6 +1253,8 @@ BPF_CALL_4(bpf_sk_redirect_hash, struct sk_buff *, skb,
sk = __sock_hash_lookup_elem(map, key);
if (unlikely(!sk || !sock_map_redirect_allowed(sk)))
return SK_DROP;
+ if ((flags & BPF_F_INGRESS) && sk_is_vsock(sk))
+ return SK_DROP;
skb_bpf_set_redir(skb, sk, flags & BPF_F_INGRESS);
return SK_PASS;
@@ -1277,6 +1283,8 @@ BPF_CALL_4(bpf_msg_redirect_hash, struct sk_msg *, msg,
return SK_DROP;
if (!(flags & BPF_F_INGRESS) && !sk_is_tcp(sk))
return SK_DROP;
+ if (sk_is_vsock(sk))
+ return SK_DROP;
msg->flags = flags;
msg->sk_redir = sk;
@@ -1752,6 +1760,10 @@ static int sock_map_link_update_prog(struct bpf_link *link,
ret = -EINVAL;
goto out;
}
+ if (!sockmap_link->map) {
+ ret = -ENOLINK;
+ goto out;
+ }
ret = sock_map_prog_link_lookup(sockmap_link->map, &pprog, &plink,
sockmap_link->attach_type);
generated by cgit (git 2.34.1) at 2025-05-30 12:17:48 +0000