summaryrefslogtreecommitdiff
path: root/net/core
diff options
context:
space:
mode:
Diffstat (limited to 'net/core')
-rw-r--r--net/core/datagram.c13
-rw-r--r--net/core/dev.c21
-rw-r--r--net/core/dev_ioctl.c11
-rw-r--r--net/core/fib_rules.c80
-rw-r--r--net/core/filter.c268
-rw-r--r--net/core/gen_stats.c16
-rw-r--r--net/core/lwt_bpf.c2
-rw-r--r--net/core/page_pool.c2
-rw-r--r--net/core/rtnetlink.c9
-rw-r--r--net/core/skbuff.c14
-rw-r--r--net/core/sock.c13
-rw-r--r--net/core/xdp.c3
12 files changed, 327 insertions, 125 deletions
diff --git a/net/core/datagram.c b/net/core/datagram.c
index f19bf3dc2bd6..9938952c5c78 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -819,8 +819,9 @@ EXPORT_SYMBOL(skb_copy_and_csum_datagram_msg);
/**
* datagram_poll - generic datagram poll
+ * @file: file struct
* @sock: socket
- * @events to wait for
+ * @wait: poll table
*
* Datagram poll: Again totally generic. This also handles
* sequenced packet sockets providing the socket receive queue
@@ -830,10 +831,14 @@ EXPORT_SYMBOL(skb_copy_and_csum_datagram_msg);
* and you use a different write policy from sock_writeable()
* then please supply your own write_space callback.
*/
-__poll_t datagram_poll_mask(struct socket *sock, __poll_t events)
+__poll_t datagram_poll(struct file *file, struct socket *sock,
+ poll_table *wait)
{
struct sock *sk = sock->sk;
- __poll_t mask = 0;
+ __poll_t mask;
+
+ sock_poll_wait(file, sk_sleep(sk), wait);
+ mask = 0;
/* exceptional events? */
if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue))
@@ -866,4 +871,4 @@ __poll_t datagram_poll_mask(struct socket *sock, __poll_t events)
return mask;
}
-EXPORT_SYMBOL(datagram_poll_mask);
+EXPORT_SYMBOL(datagram_poll);
diff --git a/net/core/dev.c b/net/core/dev.c
index 57b7bab5f70b..559a91271f82 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -7149,16 +7149,19 @@ int dev_change_tx_queue_len(struct net_device *dev, unsigned long new_len)
dev->tx_queue_len = new_len;
res = call_netdevice_notifiers(NETDEV_CHANGE_TX_QUEUE_LEN, dev);
res = notifier_to_errno(res);
- if (res) {
- netdev_err(dev,
- "refused to change device tx_queue_len\n");
- dev->tx_queue_len = orig_len;
- return res;
- }
- return dev_qdisc_change_tx_queue_len(dev);
+ if (res)
+ goto err_rollback;
+ res = dev_qdisc_change_tx_queue_len(dev);
+ if (res)
+ goto err_rollback;
}
return 0;
+
+err_rollback:
+ netdev_err(dev, "refused to change device tx_queue_len\n");
+ dev->tx_queue_len = orig_len;
+ return res;
}
/**
@@ -8643,7 +8646,8 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char
/* We get here if we can't use the current device name */
if (!pat)
goto out;
- if (dev_get_valid_name(net, dev, pat) < 0)
+ err = dev_get_valid_name(net, dev, pat);
+ if (err < 0)
goto out;
}
@@ -8655,7 +8659,6 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char
dev_close(dev);
/* And unlink it from device chain */
- err = -ENODEV;
unlist_netdevice(dev);
synchronize_net();
diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c
index a04e1e88bf3a..50537ff961a7 100644
--- a/net/core/dev_ioctl.c
+++ b/net/core/dev_ioctl.c
@@ -285,16 +285,9 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, unsigned int cmd)
if (ifr->ifr_qlen < 0)
return -EINVAL;
if (dev->tx_queue_len ^ ifr->ifr_qlen) {
- unsigned int orig_len = dev->tx_queue_len;
-
- dev->tx_queue_len = ifr->ifr_qlen;
- err = call_netdevice_notifiers(
- NETDEV_CHANGE_TX_QUEUE_LEN, dev);
- err = notifier_to_errno(err);
- if (err) {
- dev->tx_queue_len = orig_len;
+ err = dev_change_tx_queue_len(dev, ifr->ifr_qlen);
+ if (err)
return err;
- }
}
return 0;
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index 126ffc5bc630..f64aa13811ea 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -416,6 +416,14 @@ static struct fib_rule *rule_find(struct fib_rules_ops *ops,
if (rule->mark && r->mark != rule->mark)
continue;
+ if (rule->suppress_ifgroup != -1 &&
+ r->suppress_ifgroup != rule->suppress_ifgroup)
+ continue;
+
+ if (rule->suppress_prefixlen != -1 &&
+ r->suppress_prefixlen != rule->suppress_prefixlen)
+ continue;
+
if (rule->mark_mask && r->mark_mask != rule->mark_mask)
continue;
@@ -436,6 +444,9 @@ static struct fib_rule *rule_find(struct fib_rules_ops *ops,
if (rule->ip_proto && r->ip_proto != rule->ip_proto)
continue;
+ if (rule->proto && r->proto != rule->proto)
+ continue;
+
if (fib_rule_port_range_set(&rule->sport_range) &&
!fib_rule_port_range_compare(&r->sport_range,
&rule->sport_range))
@@ -645,6 +656,73 @@ errout:
return err;
}
+static int rule_exists(struct fib_rules_ops *ops, struct fib_rule_hdr *frh,
+ struct nlattr **tb, struct fib_rule *rule)
+{
+ struct fib_rule *r;
+
+ list_for_each_entry(r, &ops->rules_list, list) {
+ if (r->action != rule->action)
+ continue;
+
+ if (r->table != rule->table)
+ continue;
+
+ if (r->pref != rule->pref)
+ continue;
+
+ if (memcmp(r->iifname, rule->iifname, IFNAMSIZ))
+ continue;
+
+ if (memcmp(r->oifname, rule->oifname, IFNAMSIZ))
+ continue;
+
+ if (r->mark != rule->mark)
+ continue;
+
+ if (r->suppress_ifgroup != rule->suppress_ifgroup)
+ continue;
+
+ if (r->suppress_prefixlen != rule->suppress_prefixlen)
+ continue;
+
+ if (r->mark_mask != rule->mark_mask)
+ continue;
+
+ if (r->tun_id != rule->tun_id)
+ continue;
+
+ if (r->fr_net != rule->fr_net)
+ continue;
+
+ if (r->l3mdev != rule->l3mdev)
+ continue;
+
+ if (!uid_eq(r->uid_range.start, rule->uid_range.start) ||
+ !uid_eq(r->uid_range.end, rule->uid_range.end))
+ continue;
+
+ if (r->ip_proto != rule->ip_proto)
+ continue;
+
+ if (r->proto != rule->proto)
+ continue;
+
+ if (!fib_rule_port_range_compare(&r->sport_range,
+ &rule->sport_range))
+ continue;
+
+ if (!fib_rule_port_range_compare(&r->dport_range,
+ &rule->dport_range))
+ continue;
+
+ if (!ops->compare(r, frh, tb))
+ continue;
+ return 1;
+ }
+ return 0;
+}
+
int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh,
struct netlink_ext_ack *extack)
{
@@ -679,7 +757,7 @@ int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh,
goto errout;
if ((nlh->nlmsg_flags & NLM_F_EXCL) &&
- rule_find(ops, frh, tb, rule, user_priority)) {
+ rule_exists(ops, frh, tb, rule)) {
err = -EEXIST;
goto errout_free;
}
diff --git a/net/core/filter.c b/net/core/filter.c
index 3d9ba7e5965a..9dfd145eedcc 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -459,11 +459,21 @@ static bool convert_bpf_ld_abs(struct sock_filter *fp, struct bpf_insn **insnp)
(!unaligned_ok && offset >= 0 &&
offset + ip_align >= 0 &&
offset + ip_align % size == 0))) {
+ bool ldx_off_ok = offset <= S16_MAX;
+
*insn++ = BPF_MOV64_REG(BPF_REG_TMP, BPF_REG_H);
*insn++ = BPF_ALU64_IMM(BPF_SUB, BPF_REG_TMP, offset);
- *insn++ = BPF_JMP_IMM(BPF_JSLT, BPF_REG_TMP, size, 2 + endian);
- *insn++ = BPF_LDX_MEM(BPF_SIZE(fp->code), BPF_REG_A, BPF_REG_D,
- offset);
+ *insn++ = BPF_JMP_IMM(BPF_JSLT, BPF_REG_TMP,
+ size, 2 + endian + (!ldx_off_ok * 2));
+ if (ldx_off_ok) {
+ *insn++ = BPF_LDX_MEM(BPF_SIZE(fp->code), BPF_REG_A,
+ BPF_REG_D, offset);
+ } else {
+ *insn++ = BPF_MOV64_REG(BPF_REG_TMP, BPF_REG_D);
+ *insn++ = BPF_ALU64_IMM(BPF_ADD, BPF_REG_TMP, offset);
+ *insn++ = BPF_LDX_MEM(BPF_SIZE(fp->code), BPF_REG_A,
+ BPF_REG_TMP, 0);
+ }
if (endian)
*insn++ = BPF_ENDIAN(BPF_FROM_BE, BPF_REG_A, size * 8);
*insn++ = BPF_JMP_A(8);
@@ -1702,24 +1712,26 @@ static const struct bpf_func_proto bpf_skb_load_bytes_proto = {
BPF_CALL_5(bpf_skb_load_bytes_relative, const struct sk_buff *, skb,
u32, offset, void *, to, u32, len, u32, start_header)
{
+ u8 *end = skb_tail_pointer(skb);
+ u8 *net = skb_network_header(skb);
+ u8 *mac = skb_mac_header(skb);
u8 *ptr;
- if (unlikely(offset > 0xffff || len > skb_headlen(skb)))
+ if (unlikely(offset > 0xffff || len > (end - mac)))
goto err_clear;
switch (start_header) {
case BPF_HDR_START_MAC:
- ptr = skb_mac_header(skb) + offset;
+ ptr = mac + offset;
break;
case BPF_HDR_START_NET:
- ptr = skb_network_header(skb) + offset;
+ ptr = net + offset;
break;
default:
goto err_clear;
}
- if (likely(ptr >= skb_mac_header(skb) &&
- ptr + len <= skb_tail_pointer(skb))) {
+ if (likely(ptr >= mac && ptr + len <= end)) {
memcpy(to, ptr, len);
return 0;
}
@@ -1762,6 +1774,37 @@ static const struct bpf_func_proto bpf_skb_pull_data_proto = {
.arg2_type = ARG_ANYTHING,
};
+static inline int sk_skb_try_make_writable(struct sk_buff *skb,
+ unsigned int write_len)
+{
+ int err = __bpf_try_make_writable(skb, write_len);
+
+ bpf_compute_data_end_sk_skb(skb);
+ return err;
+}
+
+BPF_CALL_2(sk_skb_pull_data, struct sk_buff *, skb, u32, len)
+{
+ /* Idea is the following: should the needed direct read/write
+ * test fail during runtime, we can pull in more data and redo
+ * again, since implicitly, we invalidate previous checks here.
+ *
+ * Or, since we know how much we need to make read/writeable,
+ * this can be done once at the program beginning for direct
+ * access case. By this we overcome limitations of only current
+ * headroom being accessible.
+ */
+ return sk_skb_try_make_writable(skb, len ? : skb_headlen(skb));
+}
+
+static const struct bpf_func_proto sk_skb_pull_data_proto = {
+ .func = sk_skb_pull_data,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_ANYTHING,
+};
+
BPF_CALL_5(bpf_l3_csum_replace, struct sk_buff *, skb, u32, offset,
u64, from, u64, to, u64, flags)
{
@@ -2779,7 +2822,8 @@ static int bpf_skb_net_shrink(struct sk_buff *skb, u32 len_diff)
static u32 __bpf_skb_max_len(const struct sk_buff *skb)
{
- return skb->dev->mtu + skb->dev->hard_header_len;
+ return skb->dev ? skb->dev->mtu + skb->dev->hard_header_len :
+ SKB_MAX_ALLOC;
}
static int bpf_skb_adjust_net(struct sk_buff *skb, s32 len_diff)
@@ -2863,8 +2907,8 @@ static int bpf_skb_trim_rcsum(struct sk_buff *skb, unsigned int new_len)
return __skb_trim_rcsum(skb, new_len);
}
-BPF_CALL_3(bpf_skb_change_tail, struct sk_buff *, skb, u32, new_len,
- u64, flags)
+static inline int __bpf_skb_change_tail(struct sk_buff *skb, u32 new_len,
+ u64 flags)
{
u32 max_len = __bpf_skb_max_len(skb);
u32 min_len = __bpf_skb_min_len(skb);
@@ -2900,6 +2944,13 @@ BPF_CALL_3(bpf_skb_change_tail, struct sk_buff *, skb, u32, new_len,
if (!ret && skb_is_gso(skb))
skb_gso_reset(skb);
}
+ return ret;
+}
+
+BPF_CALL_3(bpf_skb_change_tail, struct sk_buff *, skb, u32, new_len,
+ u64, flags)
+{
+ int ret = __bpf_skb_change_tail(skb, new_len, flags);
bpf_compute_data_pointers(skb);
return ret;
@@ -2914,9 +2965,27 @@ static const struct bpf_func_proto bpf_skb_change_tail_proto = {
.arg3_type = ARG_ANYTHING,
};
-BPF_CALL_3(bpf_skb_change_head, struct sk_buff *, skb, u32, head_room,
+BPF_CALL_3(sk_skb_change_tail, struct sk_buff *, skb, u32, new_len,
u64, flags)
{
+ int ret = __bpf_skb_change_tail(skb, new_len, flags);
+
+ bpf_compute_data_end_sk_skb(skb);
+ return ret;
+}
+
+static const struct bpf_func_proto sk_skb_change_tail_proto = {
+ .func = sk_skb_change_tail,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_ANYTHING,
+ .arg3_type = ARG_ANYTHING,
+};
+
+static inline int __bpf_skb_change_head(struct sk_buff *skb, u32 head_room,
+ u64 flags)
+{
u32 max_len = __bpf_skb_max_len(skb);
u32 new_len = skb->len + head_room;
int ret;
@@ -2941,8 +3010,16 @@ BPF_CALL_3(bpf_skb_change_head, struct sk_buff *, skb, u32, head_room,
skb_reset_mac_header(skb);
}
+ return ret;
+}
+
+BPF_CALL_3(bpf_skb_change_head, struct sk_buff *, skb, u32, head_room,
+ u64, flags)
+{
+ int ret = __bpf_skb_change_head(skb, head_room, flags);
+
bpf_compute_data_pointers(skb);
- return 0;
+ return ret;
}
static const struct bpf_func_proto bpf_skb_change_head_proto = {
@@ -2954,6 +3031,23 @@ static const struct bpf_func_proto bpf_skb_change_head_proto = {
.arg3_type = ARG_ANYTHING,
};
+BPF_CALL_3(sk_skb_change_head, struct sk_buff *, skb, u32, head_room,
+ u64, flags)
+{
+ int ret = __bpf_skb_change_head(skb, head_room, flags);
+
+ bpf_compute_data_end_sk_skb(skb);
+ return ret;
+}
+
+static const struct bpf_func_proto sk_skb_change_head_proto = {
+ .func = sk_skb_change_head,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_ANYTHING,
+ .arg3_type = ARG_ANYTHING,
+};
static unsigned long xdp_get_metalen(const struct xdp_buff *xdp)
{
return xdp_data_meta_unsupported(xdp) ? 0 :
@@ -3046,12 +3140,16 @@ static int __bpf_tx_xdp(struct net_device *dev,
u32 index)
{
struct xdp_frame *xdpf;
- int sent;
+ int err, sent;
if (!dev->netdev_ops->ndo_xdp_xmit) {
return -EOPNOTSUPP;
}
+ err = xdp_ok_fwd_dev(dev, xdp->data_end - xdp->data);
+ if (unlikely(err))
+ return err;
+
xdpf = convert_to_xdp_frame(xdp);
if (unlikely(!xdpf))
return -EOVERFLOW;
@@ -3214,20 +3312,6 @@ err:
}
EXPORT_SYMBOL_GPL(xdp_do_redirect);
-static int __xdp_generic_ok_fwd_dev(struct sk_buff *skb, struct net_device *fwd)
-{
- unsigned int len;
-
- if (unlikely(!(fwd->flags & IFF_UP)))
- return -ENETDOWN;
-
- len = fwd->mtu + fwd->hard_header_len + VLAN_HLEN;
- if (skb->len > len)
- return -EMSGSIZE;
-
- return 0;
-}
-
static int xdp_do_generic_redirect_map(struct net_device *dev,
struct sk_buff *skb,
struct xdp_buff *xdp,
@@ -3256,10 +3340,11 @@ static int xdp_do_generic_redirect_map(struct net_device *dev,
}
if (map->map_type == BPF_MAP_TYPE_DEVMAP) {
- if (unlikely((err = __xdp_generic_ok_fwd_dev(skb, fwd))))
+ struct bpf_dtab_netdev *dst = fwd;
+
+ err = dev_map_generic_redirect(dst, skb, xdp_prog);
+ if (unlikely(err))
goto err;
- skb->dev = fwd;
- generic_xdp_tx(skb, xdp_prog);
} else if (map->map_type == BPF_MAP_TYPE_XSKMAP) {
struct xdp_sock *xs = fwd;
@@ -3298,7 +3383,8 @@ int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb,
goto err;
}
- if (unlikely((err = __xdp_generic_ok_fwd_dev(skb, fwd))))
+ err = xdp_ok_fwd_dev(fwd, skb->len);
+ if (unlikely(err))
goto err;
skb->dev = fwd;
@@ -4086,8 +4172,9 @@ static int bpf_fib_set_fwd_params(struct bpf_fib_lookup *params,
memcpy(params->smac, dev->dev_addr, ETH_ALEN);
params->h_vlan_TCI = 0;
params->h_vlan_proto = 0;
+ params->ifindex = dev->ifindex;
- return dev->ifindex;
+ return 0;
}
#endif
@@ -4111,7 +4198,7 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
/* verify forwarding is enabled on this interface */
in_dev = __in_dev_get_rcu(dev);
if (unlikely(!in_dev || !IN_DEV_FORWARD(in_dev)))
- return 0;
+ return BPF_FIB_LKUP_RET_FWD_DISABLED;
if (flags & BPF_FIB_LOOKUP_OUTPUT) {
fl4.flowi4_iif = 1;
@@ -4136,7 +4223,7 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
tb = fib_get_table(net, tbid);
if (unlikely(!tb))
- return 0;
+ return BPF_FIB_LKUP_RET_NOT_FWDED;
err = fib_table_lookup(tb, &fl4, &res, FIB_LOOKUP_NOREF);
} else {
@@ -4148,8 +4235,20 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
err = fib_lookup(net, &fl4, &res, FIB_LOOKUP_NOREF);
}
- if (err || res.type != RTN_UNICAST)
- return 0;
+ if (err) {
+ /* map fib lookup errors to RTN_ type */
+ if (err == -EINVAL)
+ return BPF_FIB_LKUP_RET_BLACKHOLE;
+ if (err == -EHOSTUNREACH)
+ return BPF_FIB_LKUP_RET_UNREACHABLE;
+ if (err == -EACCES)
+ return BPF_FIB_LKUP_RET_PROHIBIT;
+
+ return BPF_FIB_LKUP_RET_NOT_FWDED;
+ }
+
+ if (res.type != RTN_UNICAST)
+ return BPF_FIB_LKUP_RET_NOT_FWDED;
if (res.fi->fib_nhs > 1)
fib_select_path(net, &res, &fl4, NULL);
@@ -4157,19 +4256,16 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
if (check_mtu) {
mtu = ip_mtu_from_fib_result(&res, params->ipv4_dst);
if (params->tot_len > mtu)
- return 0;
+ return BPF_FIB_LKUP_RET_FRAG_NEEDED;
}
nh = &res.fi->fib_nh[res.nh_sel];
/* do not handle lwt encaps right now */
if (nh->nh_lwtstate)
- return 0;
+ return BPF_FIB_LKUP_RET_UNSUPP_LWT;
dev = nh->nh_dev;
- if (unlikely(!dev))
- return 0;
-
if (nh->nh_gw)
params->ipv4_dst = nh->nh_gw;
@@ -4179,10 +4275,10 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
* rcu_read_lock_bh is not needed here
*/
neigh = __ipv4_neigh_lookup_noref(dev, (__force u32)params->ipv4_dst);
- if (neigh)
- return bpf_fib_set_fwd_params(params, neigh, dev);
+ if (!neigh)
+ return BPF_FIB_LKUP_RET_NO_NEIGH;
- return 0;
+ return bpf_fib_set_fwd_params(params, neigh, dev);
}
#endif
@@ -4203,7 +4299,7 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
/* link local addresses are never forwarded */
if (rt6_need_strict(dst) || rt6_need_strict(src))
- return 0;
+ return BPF_FIB_LKUP_RET_NOT_FWDED;
dev = dev_get_by_index_rcu(net, params->ifindex);
if (unlikely(!dev))
@@ -4211,7 +4307,7 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
idev = __in6_dev_get_safely(dev);
if (unlikely(!idev || !net->ipv6.devconf_all->forwarding))
- return 0;
+ return BPF_FIB_LKUP_RET_FWD_DISABLED;
if (flags & BPF_FIB_LOOKUP_OUTPUT) {
fl6.flowi6_iif = 1;
@@ -4238,7 +4334,7 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
tb = ipv6_stub->fib6_get_table(net, tbid);
if (unlikely(!tb))
- return 0;
+ return BPF_FIB_LKUP_RET_NOT_FWDED;
f6i = ipv6_stub->fib6_table_lookup(net, tb, oif, &fl6, strict);
} else {
@@ -4251,11 +4347,23 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
}
if (unlikely(IS_ERR_OR_NULL(f6i) || f6i == net->ipv6.fib6_null_entry))
- return 0;
+ return BPF_FIB_LKUP_RET_NOT_FWDED;
- if (unlikely(f6i->fib6_flags & RTF_REJECT ||
- f6i->fib6_type != RTN_UNICAST))
- return 0;
+ if (unlikely(f6i->fib6_flags & RTF_REJECT)) {
+ switch (f6i->fib6_type) {
+ case RTN_BLACKHOLE:
+ return BPF_FIB_LKUP_RET_BLACKHOLE;
+ case RTN_UNREACHABLE:
+ return BPF_FIB_LKUP_RET_UNREACHABLE;
+ case RTN_PROHIBIT:
+ return BPF_FIB_LKUP_RET_PROHIBIT;
+ default:
+ return BPF_FIB_LKUP_RET_NOT_FWDED;
+ }
+ }
+
+ if (f6i->fib6_type != RTN_UNICAST)
+ return BPF_FIB_LKUP_RET_NOT_FWDED;
if (f6i->fib6_nsiblings && fl6.flowi6_oif == 0)
f6i = ipv6_stub->fib6_multipath_select(net, f6i, &fl6,
@@ -4265,11 +4373,11 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
if (check_mtu) {
mtu = ipv6_stub->ip6_mtu_from_fib6(f6i, dst, src);
if (params->tot_len > mtu)
- return 0;
+ return BPF_FIB_LKUP_RET_FRAG_NEEDED;
}
if (f6i->fib6_nh.nh_lwtstate)
- return 0;
+ return BPF_FIB_LKUP_RET_UNSUPP_LWT;
if (f6i->fib6_flags & RTF_GATEWAY)
*dst = f6i->fib6_nh.nh_gw;
@@ -4283,10 +4391,10 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
*/
neigh = ___neigh_lookup_noref(ipv6_stub->nd_tbl, neigh_key_eq128,
ndisc_hashfn, dst, dev);
- if (neigh)
- return bpf_fib_set_fwd_params(params, neigh, dev);
+ if (!neigh)
+ return BPF_FIB_LKUP_RET_NO_NEIGH;
- return 0;
+ return bpf_fib_set_fwd_params(params, neigh, dev);
}
#endif
@@ -4328,7 +4436,7 @@ BPF_CALL_4(bpf_skb_fib_lookup, struct sk_buff *, skb,
struct bpf_fib_lookup *, params, int, plen, u32, flags)
{
struct net *net = dev_net(skb->dev);
- int index = -EAFNOSUPPORT;
+ int rc = -EAFNOSUPPORT;
if (plen < sizeof(*params))
return -EINVAL;
@@ -4339,25 +4447,25 @@ BPF_CALL_4(bpf_skb_fib_lookup, struct sk_buff *, skb,
switch (params->family) {
#if IS_ENABLED(CONFIG_INET)
case AF_INET:
- index = bpf_ipv4_fib_lookup(net, params, flags, false);
+ rc = bpf_ipv4_fib_lookup(net, params, flags, false);
break;
#endif
#if IS_ENABLED(CONFIG_IPV6)
case AF_INET6:
- index = bpf_ipv6_fib_lookup(net, params, flags, false);
+ rc = bpf_ipv6_fib_lookup(net, params, flags, false);
break;
#endif
}
- if (index > 0) {
+ if (!rc) {
struct net_device *dev;
- dev = dev_get_by_index_rcu(net, index);
+ dev = dev_get_by_index_rcu(net, params->ifindex);
if (!is_skb_forwardable(dev, skb))
- index = 0;
+ rc = BPF_FIB_LKUP_RET_FRAG_NEEDED;
}
- return index;
+ return rc;
}
static const struct bpf_func_proto bpf_skb_fib_lookup_proto = {
@@ -4430,10 +4538,10 @@ static const struct bpf_func_proto bpf_lwt_push_encap_proto = {
.arg4_type = ARG_CONST_SIZE
};
+#if IS_ENABLED(CONFIG_IPV6_SEG6_BPF)
BPF_CALL_4(bpf_lwt_seg6_store_bytes, struct sk_buff *, skb, u32, offset,
const void *, from, u32, len)
{
-#if IS_ENABLED(CONFIG_IPV6_SEG6_BPF)
struct seg6_bpf_srh_state *srh_state =
this_cpu_ptr(&seg6_bpf_srh_states);
void *srh_tlvs, *srh_end, *ptr;
@@ -4459,9 +4567,6 @@ BPF_CALL_4(bpf_lwt_seg6_store_bytes, struct sk_buff *, skb, u32, offset,
memcpy(skb->data + offset, from, len);
return 0;
-#else /* CONFIG_IPV6_SEG6_BPF */
- return -EOPNOTSUPP;
-#endif
}
static const struct bpf_func_proto bpf_lwt_seg6_store_bytes_proto = {
@@ -4477,7 +4582,6 @@ static const struct bpf_func_proto bpf_lwt_seg6_store_bytes_proto = {
BPF_CALL_4(bpf_lwt_seg6_action, struct sk_buff *, skb,
u32, action, void *, param, u32, param_len)
{
-#if IS_ENABLED(CONFIG_IPV6_SEG6_BPF)
struct seg6_bpf_srh_state *srh_state =
this_cpu_ptr(&seg6_bpf_srh_states);
struct ipv6_sr_hdr *srh;
@@ -4525,9 +4629,6 @@ BPF_CALL_4(bpf_lwt_seg6_action, struct sk_buff *, skb,
default:
return -EINVAL;
}
-#else /* CONFIG_IPV6_SEG6_BPF */
- return -EOPNOTSUPP;
-#endif
}
static const struct bpf_func_proto bpf_lwt_seg6_action_proto = {
@@ -4543,7 +4644,6 @@ static const struct bpf_func_proto bpf_lwt_seg6_action_proto = {
BPF_CALL_3(bpf_lwt_seg6_adjust_srh, struct sk_buff *, skb, u32, offset,
s32, len)
{
-#if IS_ENABLED(CONFIG_IPV6_SEG6_BPF)
struct seg6_bpf_srh_state *srh_state =
this_cpu_ptr(&seg6_bpf_srh_states);
void *srh_end, *srh_tlvs, *ptr;
@@ -4587,9 +4687,6 @@ BPF_CALL_3(bpf_lwt_seg6_adjust_srh, struct sk_buff *, skb, u32, offset,
srh_state->hdrlen += len;
srh_state->valid = 0;
return 0;
-#else /* CONFIG_IPV6_SEG6_BPF */
- return -EOPNOTSUPP;
-#endif
}
static const struct bpf_func_proto bpf_lwt_seg6_adjust_srh_proto = {
@@ -4600,6 +4697,7 @@ static const struct bpf_func_proto bpf_lwt_seg6_adjust_srh_proto = {
.arg2_type = ARG_ANYTHING,
.arg3_type = ARG_ANYTHING,
};
+#endif /* CONFIG_IPV6_SEG6_BPF */
bool bpf_helper_changes_pkt_data(void *func)
{
@@ -4608,9 +4706,12 @@ bool bpf_helper_changes_pkt_data(void *func)
func == bpf_skb_store_bytes ||
func == bpf_skb_change_proto ||
func == bpf_skb_change_head ||
+ func == sk_skb_change_head ||
func == bpf_skb_change_tail ||
+ func == sk_skb_change_tail ||
func == bpf_skb_adjust_room ||
func == bpf_skb_pull_data ||
+ func == sk_skb_pull_data ||
func == bpf_clone_redirect ||
func == bpf_l3_csum_replace ||
func == bpf_l4_csum_replace ||
@@ -4618,11 +4719,12 @@ bool bpf_helper_changes_pkt_data(void *func)
func == bpf_xdp_adjust_meta ||
func == bpf_msg_pull_data ||
func == bpf_xdp_adjust_tail ||
- func == bpf_lwt_push_encap ||
+#if IS_ENABLED(CONFIG_IPV6_SEG6_BPF)
func == bpf_lwt_seg6_store_bytes ||
func == bpf_lwt_seg6_adjust_srh ||
- func == bpf_lwt_seg6_action
- )
+ func == bpf_lwt_seg6_action ||
+#endif
+ func == bpf_lwt_push_encap)
return true;
return false;
@@ -4862,11 +4964,11 @@ sk_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
case BPF_FUNC_skb_load_bytes:
return &bpf_skb_load_bytes_proto;
case BPF_FUNC_skb_pull_data:
- return &bpf_skb_pull_data_proto;
+ return &sk_skb_pull_data_proto;
case BPF_FUNC_skb_change_tail:
- return &bpf_skb_change_tail_proto;
+ return &sk_skb_change_tail_proto;
case BPF_FUNC_skb_change_head:
- return &bpf_skb_change_head_proto;
+ return &sk_skb_change_head_proto;
case BPF_FUNC_get_socket_cookie:
return &bpf_get_socket_cookie_proto;
case BPF_FUNC_get_socket_uid:
@@ -4957,12 +5059,14 @@ static const struct bpf_func_proto *
lwt_seg6local_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
{
switch (func_id) {
+#if IS_ENABLED(CONFIG_IPV6_SEG6_BPF)
case BPF_FUNC_lwt_seg6_store_bytes:
return &bpf_lwt_seg6_store_bytes_proto;
case BPF_FUNC_lwt_seg6_action:
return &bpf_lwt_seg6_action_proto;
case BPF_FUNC_lwt_seg6_adjust_srh:
return &bpf_lwt_seg6_adjust_srh_proto;
+#endif
default:
return lwt_out_func_proto(func_id, prog);
}
diff --git a/net/core/gen_stats.c b/net/core/gen_stats.c
index b2b2323bdc84..188d693cb251 100644
--- a/net/core/gen_stats.c
+++ b/net/core/gen_stats.c
@@ -77,8 +77,20 @@ gnet_stats_start_copy_compat(struct sk_buff *skb, int type, int tc_stats_type,
d->lock = lock;
spin_lock_bh(lock);
}
- if (d->tail)
- return gnet_stats_copy(d, type, NULL, 0, padattr);
+ if (d->tail) {
+ int ret = gnet_stats_copy(d, type, NULL, 0, padattr);
+
+ /* The initial attribute added in gnet_stats_copy() may be
+ * preceded by a padding attribute, in which case d->tail will
+ * end up pointing at the padding instead of the real attribute.
+ * Fix this so gnet_stats_finish_copy() adjusts the length of
+ * the right attribute.
+ */
+ if (ret == 0 && d->tail->nla_type == padattr)
+ d->tail = (struct nlattr *)((char *)d->tail +
+ NLA_ALIGN(d->tail->nla_len));
+ return ret;
+ }
return 0;
}
diff --git a/net/core/lwt_bpf.c b/net/core/lwt_bpf.c
index e7e626fb87bb..e45098593dc0 100644
--- a/net/core/lwt_bpf.c
+++ b/net/core/lwt_bpf.c
@@ -217,7 +217,7 @@ static int bpf_parse_prog(struct nlattr *attr, struct bpf_lwt_prog *prog,
if (!tb[LWT_BPF_PROG_FD] || !tb[LWT_BPF_PROG_NAME])
return -EINVAL;
- prog->name = nla_memdup(tb[LWT_BPF_PROG_NAME], GFP_KERNEL);
+ prog->name = nla_memdup(tb[LWT_BPF_PROG_NAME], GFP_ATOMIC);
if (!prog->name)
return -ENOMEM;
diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index 68bf07206744..43a932cb609b 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -269,7 +269,7 @@ static void __page_pool_empty_ring(struct page_pool *pool)
struct page *page;
/* Empty recycle ring */
- while ((page = ptr_ring_consume(&pool->ring))) {
+ while ((page = ptr_ring_consume_bh(&pool->ring))) {
/* Verify the refcnt invariant of cached pages */
if (!(page_ref_count(page) == 1))
pr_crit("%s() page_pool refcnt %d violation\n",
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 5ef61222fdef..e3f743c141b3 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -2759,9 +2759,12 @@ int rtnl_configure_link(struct net_device *dev, const struct ifinfomsg *ifm)
return err;
}
- dev->rtnl_link_state = RTNL_LINK_INITIALIZED;
-
- __dev_notify_flags(dev, old_flags, ~0U);
+ if (dev->rtnl_link_state == RTNL_LINK_INITIALIZED) {
+ __dev_notify_flags(dev, old_flags, 0U);
+ } else {
+ dev->rtnl_link_state = RTNL_LINK_INITIALIZED;
+ __dev_notify_flags(dev, old_flags, ~0U);
+ }
return 0;
}
EXPORT_SYMBOL(rtnl_configure_link);
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index c642304f178c..fb35b62af272 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -858,6 +858,7 @@ static struct sk_buff *__skb_clone(struct sk_buff *n, struct sk_buff *skb)
n->cloned = 1;
n->nohdr = 0;
n->peeked = 0;
+ C(pfmemalloc);
n->destructor = NULL;
C(tail);
C(end);
@@ -3719,6 +3720,7 @@ normal:
net_warn_ratelimited(
"skb_segment: too many frags: %u %u\n",
pos, mss);
+ err = -EINVAL;
goto err;
}
@@ -3752,11 +3754,10 @@ skip_fraglist:
perform_csum_check:
if (!csum) {
- if (skb_has_shared_frag(nskb)) {
- err = __skb_linearize(nskb);
- if (err)
- goto err;
- }
+ if (skb_has_shared_frag(nskb) &&
+ __skb_linearize(nskb))
+ goto err;
+
if (!nskb->remcsum_offload)
nskb->ip_summed = CHECKSUM_NONE;
SKB_GSO_CB(nskb)->csum =
@@ -5276,8 +5277,7 @@ struct sk_buff *alloc_skb_with_frags(unsigned long header_len,
if (npages >= 1 << order) {
page = alloc_pages((gfp_mask & ~__GFP_DIRECT_RECLAIM) |
__GFP_COMP |
- __GFP_NOWARN |
- __GFP_NORETRY,
+ __GFP_NOWARN,
order);
if (page)
goto fill_page;
diff --git a/net/core/sock.c b/net/core/sock.c
index bcc41829a16d..bc2d7a37297f 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2277,9 +2277,9 @@ int sk_alloc_sg(struct sock *sk, int len, struct scatterlist *sg,
pfrag->offset += use;
sge = sg + sg_curr - 1;
- if (sg_curr > first_coalesce && sg_page(sg) == pfrag->page &&
- sg->offset + sg->length == orig_offset) {
- sg->length += use;
+ if (sg_curr > first_coalesce && sg_page(sge) == pfrag->page &&
+ sge->offset + sge->length == orig_offset) {
+ sge->length += use;
} else {
sge = sg + sg_curr;
sg_unmark_end(sge);
@@ -3243,7 +3243,8 @@ static int req_prot_init(const struct proto *prot)
rsk_prot->slab = kmem_cache_create(rsk_prot->slab_name,
rsk_prot->obj_size, 0,
- prot->slab_flags, NULL);
+ SLAB_ACCOUNT | prot->slab_flags,
+ NULL);
if (!rsk_prot->slab) {
pr_crit("%s: Can't create request sock SLAB cache!\n",
@@ -3258,7 +3259,8 @@ int proto_register(struct proto *prot, int alloc_slab)
if (alloc_slab) {
prot->slab = kmem_cache_create_usercopy(prot->name,
prot->obj_size, 0,
- SLAB_HWCACHE_ALIGN | prot->slab_flags,
+ SLAB_HWCACHE_ALIGN | SLAB_ACCOUNT |
+ prot->slab_flags,
prot->useroffset, prot->usersize,
NULL);
@@ -3281,6 +3283,7 @@ int proto_register(struct proto *prot, int alloc_slab)
kmem_cache_create(prot->twsk_prot->twsk_slab_name,
prot->twsk_prot->twsk_obj_size,
0,
+ SLAB_ACCOUNT |
prot->slab_flags,
NULL);
if (prot->twsk_prot->twsk_slab == NULL)
diff --git a/net/core/xdp.c b/net/core/xdp.c
index 9d1f22072d5d..6771f1855b96 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -345,7 +345,8 @@ static void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct,
rcu_read_lock();
/* mem->id is valid, checked in xdp_rxq_info_reg_mem_model() */
xa = rhashtable_lookup(mem_id_ht, &mem->id, mem_id_rht_params);
- xa->zc_alloc->free(xa->zc_alloc, handle);
+ if (!WARN_ON_ONCE(!xa))
+ xa->zc_alloc->free(xa->zc_alloc, handle);
rcu_read_unlock();
default:
/* Not possible, checked in xdp_rxq_info_reg_mem_model() */
generated by cgit v1.2.3-70-g09d2 (git 2.51.1) at 2025-11-04 01:54:20 +0000