aboutsummaryrefslogtreecommitdiffstats
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/cipso_ipv4.c6
-rw-r--r--net/ipv4/devinet.c1
-rw-r--r--net/ipv4/esp4_offload.c4
-rw-r--r--net/ipv4/fib_frontend.c22
-rw-r--r--net/ipv4/inet_connection_sock.c43
-rw-r--r--net/ipv4/ip_vti.c23
-rw-r--r--net/ipv4/ipip.c2
-rw-r--r--net/ipv4/ipmr.c2
-rw-r--r--net/ipv4/netfilter/nf_nat_pptp.c7
-rw-r--r--net/ipv4/nexthop.c105
-rw-r--r--net/ipv4/route.c16
-rw-r--r--net/ipv4/tcp.c27
-rw-r--r--net/ipv4/tcp_bpf.c10
-rw-r--r--net/ipv4/tcp_input.c3
14 files changed, 166 insertions, 105 deletions
diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c
index 0bd10a1f477f..a23094b050f8 100644
--- a/net/ipv4/cipso_ipv4.c
+++ b/net/ipv4/cipso_ipv4.c
@@ -1258,7 +1258,8 @@ static int cipso_v4_parsetag_rbm(const struct cipso_v4_doi *doi_def,
return ret_val;
}
- secattr->flags |= NETLBL_SECATTR_MLS_CAT;
+ if (secattr->attr.mls.cat)
+ secattr->flags |= NETLBL_SECATTR_MLS_CAT;
}
return 0;
@@ -1439,7 +1440,8 @@ static int cipso_v4_parsetag_rng(const struct cipso_v4_doi *doi_def,
return ret_val;
}
- secattr->flags |= NETLBL_SECATTR_MLS_CAT;
+ if (secattr->attr.mls.cat)
+ secattr->flags |= NETLBL_SECATTR_MLS_CAT;
}
return 0;
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 458dc6eb5a68..a27d034c85cc 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -276,6 +276,7 @@ static struct in_device *inetdev_init(struct net_device *dev)
err = devinet_sysctl_register(in_dev);
if (err) {
in_dev->dead = 1;
+ neigh_parms_release(&arp_tbl, in_dev->arp_parms);
in_dev_put(in_dev);
in_dev = NULL;
goto out;
diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c
index e2e219c7854a..25c8ba6732df 100644
--- a/net/ipv4/esp4_offload.c
+++ b/net/ipv4/esp4_offload.c
@@ -63,10 +63,8 @@ static struct sk_buff *esp4_gro_receive(struct list_head *head,
sp->olen++;
xo = xfrm_offload(skb);
- if (!xo) {
- xfrm_state_put(x);
+ if (!xo)
goto out_reset;
- }
}
xo->flags |= XFRM_GRO;
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 213be9c050ad..41079490a118 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -309,17 +309,18 @@ bool fib_info_nh_uses_dev(struct fib_info *fi, const struct net_device *dev)
{
bool dev_match = false;
#ifdef CONFIG_IP_ROUTE_MULTIPATH
- int ret;
+ if (unlikely(fi->nh)) {
+ dev_match = nexthop_uses_dev(fi->nh, dev);
+ } else {
+ int ret;
- for (ret = 0; ret < fib_info_num_path(fi); ret++) {
- const struct fib_nh_common *nhc = fib_info_nhc(fi, ret);
+ for (ret = 0; ret < fib_info_num_path(fi); ret++) {
+ const struct fib_nh_common *nhc = fib_info_nhc(fi, ret);
- if (nhc->nhc_dev == dev) {
- dev_match = true;
- break;
- } else if (l3mdev_master_ifindex_rcu(nhc->nhc_dev) == dev->ifindex) {
- dev_match = true;
- break;
+ if (nhc_l3mdev_matches_dev(nhc, dev)) {
+ dev_match = true;
+ break;
+ }
}
}
#else
@@ -918,7 +919,6 @@ int ip_valid_fib_dump_req(struct net *net, const struct nlmsghdr *nlh,
else
filter->dump_exceptions = false;
- filter->dump_all_families = (rtm->rtm_family == AF_UNSPEC);
filter->flags = rtm->rtm_flags;
filter->protocol = rtm->rtm_protocol;
filter->rt_type = rtm->rtm_type;
@@ -990,7 +990,7 @@ static int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb)
if (filter.table_id) {
tb = fib_get_table(net, filter.table_id);
if (!tb) {
- if (filter.dump_all_families)
+ if (rtnl_msg_family(cb->nlh) != PF_INET)
return skb->len;
NL_SET_ERR_MSG(cb->extack, "ipv4: FIB table does not exist");
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index d545fb99a8a1..76afe93904d5 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -24,17 +24,19 @@
#include <net/addrconf.h>
#if IS_ENABLED(CONFIG_IPV6)
-/* match_wildcard == true: IPV6_ADDR_ANY equals to any IPv6 addresses if IPv6
- * only, and any IPv4 addresses if not IPv6 only
- * match_wildcard == false: addresses must be exactly the same, i.e.
- * IPV6_ADDR_ANY only equals to IPV6_ADDR_ANY,
- * and 0.0.0.0 equals to 0.0.0.0 only
+/* match_sk*_wildcard == true: IPV6_ADDR_ANY equals to any IPv6 addresses
+ * if IPv6 only, and any IPv4 addresses
+ * if not IPv6 only
+ * match_sk*_wildcard == false: addresses must be exactly the same, i.e.
+ * IPV6_ADDR_ANY only equals to IPV6_ADDR_ANY,
+ * and 0.0.0.0 equals to 0.0.0.0 only
*/
static bool ipv6_rcv_saddr_equal(const struct in6_addr *sk1_rcv_saddr6,
const struct in6_addr *sk2_rcv_saddr6,
__be32 sk1_rcv_saddr, __be32 sk2_rcv_saddr,
bool sk1_ipv6only, bool sk2_ipv6only,
- bool match_wildcard)
+ bool match_sk1_wildcard,
+ bool match_sk2_wildcard)
{
int addr_type = ipv6_addr_type(sk1_rcv_saddr6);
int addr_type2 = sk2_rcv_saddr6 ? ipv6_addr_type(sk2_rcv_saddr6) : IPV6_ADDR_MAPPED;
@@ -44,8 +46,8 @@ static bool ipv6_rcv_saddr_equal(const struct in6_addr *sk1_rcv_saddr6,
if (!sk2_ipv6only) {
if (sk1_rcv_saddr == sk2_rcv_saddr)
return true;
- if (!sk1_rcv_saddr || !sk2_rcv_saddr)
- return match_wildcard;
+ return (match_sk1_wildcard && !sk1_rcv_saddr) ||
+ (match_sk2_wildcard && !sk2_rcv_saddr);
}
return false;
}
@@ -53,11 +55,11 @@ static bool ipv6_rcv_saddr_equal(const struct in6_addr *sk1_rcv_saddr6,
if (addr_type == IPV6_ADDR_ANY && addr_type2 == IPV6_ADDR_ANY)
return true;
- if (addr_type2 == IPV6_ADDR_ANY && match_wildcard &&
+ if (addr_type2 == IPV6_ADDR_ANY && match_sk2_wildcard &&
!(sk2_ipv6only && addr_type == IPV6_ADDR_MAPPED))
return true;
- if (addr_type == IPV6_ADDR_ANY && match_wildcard &&
+ if (addr_type == IPV6_ADDR_ANY && match_sk1_wildcard &&
!(sk1_ipv6only && addr_type2 == IPV6_ADDR_MAPPED))
return true;
@@ -69,18 +71,19 @@ static bool ipv6_rcv_saddr_equal(const struct in6_addr *sk1_rcv_saddr6,
}
#endif
-/* match_wildcard == true: 0.0.0.0 equals to any IPv4 addresses
- * match_wildcard == false: addresses must be exactly the same, i.e.
- * 0.0.0.0 only equals to 0.0.0.0
+/* match_sk*_wildcard == true: 0.0.0.0 equals to any IPv4 addresses
+ * match_sk*_wildcard == false: addresses must be exactly the same, i.e.
+ * 0.0.0.0 only equals to 0.0.0.0
*/
static bool ipv4_rcv_saddr_equal(__be32 sk1_rcv_saddr, __be32 sk2_rcv_saddr,
- bool sk2_ipv6only, bool match_wildcard)
+ bool sk2_ipv6only, bool match_sk1_wildcard,
+ bool match_sk2_wildcard)
{
if (!sk2_ipv6only) {
if (sk1_rcv_saddr == sk2_rcv_saddr)
return true;
- if (!sk1_rcv_saddr || !sk2_rcv_saddr)
- return match_wildcard;
+ return (match_sk1_wildcard && !sk1_rcv_saddr) ||
+ (match_sk2_wildcard && !sk2_rcv_saddr);
}
return false;
}
@@ -96,10 +99,12 @@ bool inet_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2,
sk2->sk_rcv_saddr,
ipv6_only_sock(sk),
ipv6_only_sock(sk2),
+ match_wildcard,
match_wildcard);
#endif
return ipv4_rcv_saddr_equal(sk->sk_rcv_saddr, sk2->sk_rcv_saddr,
- ipv6_only_sock(sk2), match_wildcard);
+ ipv6_only_sock(sk2), match_wildcard,
+ match_wildcard);
}
EXPORT_SYMBOL(inet_rcv_saddr_equal);
@@ -273,10 +278,10 @@ static inline int sk_reuseport_match(struct inet_bind_bucket *tb,
tb->fast_rcv_saddr,
sk->sk_rcv_saddr,
tb->fast_ipv6_only,
- ipv6_only_sock(sk), true);
+ ipv6_only_sock(sk), true, false);
#endif
return ipv4_rcv_saddr_equal(tb->fast_rcv_saddr, sk->sk_rcv_saddr,
- ipv6_only_sock(sk), true);
+ ipv6_only_sock(sk), true, false);
}
/* Obtain a reference to a local port for the given sock,
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index 1b4e6f298648..1dda7c155c48 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -93,7 +93,28 @@ static int vti_rcv_proto(struct sk_buff *skb)
static int vti_rcv_tunnel(struct sk_buff *skb)
{
- return vti_rcv(skb, ip_hdr(skb)->saddr, true);
+ struct ip_tunnel_net *itn = net_generic(dev_net(skb->dev), vti_net_id);
+ const struct iphdr *iph = ip_hdr(skb);
+ struct ip_tunnel *tunnel;
+
+ tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY,
+ iph->saddr, iph->daddr, 0);
+ if (tunnel) {
+ struct tnl_ptk_info tpi = {
+ .proto = htons(ETH_P_IP),
+ };
+
+ if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
+ goto drop;
+ if (iptunnel_pull_header(skb, 0, tpi.proto, false))
+ goto drop;
+ return ip_tunnel_rcv(tunnel, skb, &tpi, NULL, false);
+ }
+
+ return -EINVAL;
+drop:
+ kfree_skb(skb);
+ return 0;
}
static int vti_rcv_cb(struct sk_buff *skb, int err)
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index 2f01cf6fa0de..678575adaf3b 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -698,7 +698,7 @@ out:
rtnl_link_failed:
#if IS_ENABLED(CONFIG_MPLS)
- xfrm4_tunnel_deregister(&mplsip_handler, AF_INET);
+ xfrm4_tunnel_deregister(&mplsip_handler, AF_MPLS);
xfrm_tunnel_mplsip_failed:
#endif
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 6e68def66822..2508b4c37af3 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -2611,7 +2611,7 @@ static int ipmr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb)
mrt = ipmr_get_table(sock_net(skb->sk), filter.table_id);
if (!mrt) {
- if (filter.dump_all_families)
+ if (rtnl_msg_family(cb->nlh) != RTNL_FAMILY_IPMR)
return skb->len;
NL_SET_ERR_MSG(cb->extack, "ipv4: MR table does not exist");
diff --git a/net/ipv4/netfilter/nf_nat_pptp.c b/net/ipv4/netfilter/nf_nat_pptp.c
index b2aeb7bf5dac..2a1e10f4ae93 100644
--- a/net/ipv4/netfilter/nf_nat_pptp.c
+++ b/net/ipv4/netfilter/nf_nat_pptp.c
@@ -166,8 +166,7 @@ pptp_outbound_pkt(struct sk_buff *skb,
break;
default:
pr_debug("unknown outbound packet 0x%04x:%s\n", msg,
- msg <= PPTP_MSG_MAX ? pptp_msg_name[msg] :
- pptp_msg_name[0]);
+ pptp_msg_name(msg));
/* fall through */
case PPTP_SET_LINK_INFO:
/* only need to NAT in case PAC is behind NAT box */
@@ -268,9 +267,7 @@ pptp_inbound_pkt(struct sk_buff *skb,
pcid_off = offsetof(union pptp_ctrl_union, setlink.peersCallID);
break;
default:
- pr_debug("unknown inbound packet %s\n",
- msg <= PPTP_MSG_MAX ? pptp_msg_name[msg] :
- pptp_msg_name[0]);
+ pr_debug("unknown inbound packet %s\n", pptp_msg_name(msg));
/* fall through */
case PPTP_START_SESSION_REQUEST:
case PPTP_START_SESSION_REPLY:
diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c
index d072c326dd64..b6ecb30544f6 100644
--- a/net/ipv4/nexthop.c
+++ b/net/ipv4/nexthop.c
@@ -63,9 +63,16 @@ static void nexthop_free_mpath(struct nexthop *nh)
int i;
nhg = rcu_dereference_raw(nh->nh_grp);
- for (i = 0; i < nhg->num_nh; ++i)
- WARN_ON(nhg->nh_entries[i].nh);
+ for (i = 0; i < nhg->num_nh; ++i) {
+ struct nh_grp_entry *nhge = &nhg->nh_entries[i];
+
+ WARN_ON(!list_empty(&nhge->nh_list));
+ nexthop_put(nhge->nh);
+ }
+
+ WARN_ON(nhg->spare == nhg);
+ kfree(nhg->spare);
kfree(nhg);
}
@@ -276,6 +283,7 @@ out:
return 0;
nla_put_failure:
+ nlmsg_cancel(skb, nlh);
return -EMSGSIZE;
}
@@ -433,7 +441,7 @@ static int nh_check_attr_group(struct net *net, struct nlattr *tb[],
if (!valid_group_nh(nh, len, extack))
return -EINVAL;
}
- for (i = NHA_GROUP + 1; i < __NHA_MAX; ++i) {
+ for (i = NHA_GROUP_TYPE + 1; i < __NHA_MAX; ++i) {
if (!tb[i])
continue;
@@ -693,41 +701,56 @@ static void nh_group_rebalance(struct nh_group *nhg)
}
}
-static void remove_nh_grp_entry(struct nh_grp_entry *nhge,
- struct nh_group *nhg,
+static void remove_nh_grp_entry(struct net *net, struct nh_grp_entry *nhge,
struct nl_info *nlinfo)
{
+ struct nh_grp_entry *nhges, *new_nhges;
+ struct nexthop *nhp = nhge->nh_parent;
struct nexthop *nh = nhge->nh;
- struct nh_grp_entry *nhges;
- bool found = false;
- int i;
+ struct nh_group *nhg, *newg;
+ int i, j;
WARN_ON(!nh);
- nhges = nhg->nh_entries;
- for (i = 0; i < nhg->num_nh; ++i) {
- if (found) {
- nhges[i-1].nh = nhges[i].nh;
- nhges[i-1].weight = nhges[i].weight;
- list_del(&nhges[i].nh_list);
- list_add(&nhges[i-1].nh_list, &nhges[i-1].nh->grp_list);
- } else if (nhg->nh_entries[i].nh == nh) {
- found = true;
- }
- }
+ nhg = rtnl_dereference(nhp->nh_grp);
+ newg = nhg->spare;
- if (WARN_ON(!found))
+ /* last entry, keep it visible and remove the parent */
+ if (nhg->num_nh == 1) {
+ remove_nexthop(net, nhp, nlinfo);
return;
+ }
+
+ newg->has_v4 = nhg->has_v4;
+ newg->mpath = nhg->mpath;
+ newg->num_nh = nhg->num_nh;
- nhg->num_nh--;
- nhg->nh_entries[nhg->num_nh].nh = NULL;
+ /* copy old entries to new except the one getting removed */
+ nhges = nhg->nh_entries;
+ new_nhges = newg->nh_entries;
+ for (i = 0, j = 0; i < nhg->num_nh; ++i) {
+ /* current nexthop getting removed */
+ if (nhg->nh_entries[i].nh == nh) {
+ newg->num_nh--;
+ continue;
+ }
- nh_group_rebalance(nhg);
+ list_del(&nhges[i].nh_list);
+ new_nhges[j].nh_parent = nhges[i].nh_parent;
+ new_nhges[j].nh = nhges[i].nh;
+ new_nhges[j].weight = nhges[i].weight;
+ list_add(&new_nhges[j].nh_list, &new_nhges[j].nh->grp_list);
+ j++;
+ }
- nexthop_put(nh);
+ nh_group_rebalance(newg);
+ rcu_assign_pointer(nhp->nh_grp, newg);
+
+ list_del(&nhge->nh_list);
+ nexthop_put(nhge->nh);
if (nlinfo)
- nexthop_notify(RTM_NEWNEXTHOP, nhge->nh_parent, nlinfo);
+ nexthop_notify(RTM_NEWNEXTHOP, nhp, nlinfo);
}
static void remove_nexthop_from_groups(struct net *net, struct nexthop *nh,
@@ -735,17 +758,11 @@ static void remove_nexthop_from_groups(struct net *net, struct nexthop *nh,
{
struct nh_grp_entry *nhge, *tmp;
- list_for_each_entry_safe(nhge, tmp, &nh->grp_list, nh_list) {
- struct nh_group *nhg;
-
- list_del(&nhge->nh_list);
- nhg = rtnl_dereference(nhge->nh_parent->nh_grp);
- remove_nh_grp_entry(nhge, nhg, nlinfo);
+ list_for_each_entry_safe(nhge, tmp, &nh->grp_list, nh_list)
+ remove_nh_grp_entry(net, nhge, nlinfo);
- /* if this group has no more entries then remove it */
- if (!nhg->num_nh)
- remove_nexthop(net, nhge->nh_parent, nlinfo);
- }
+ /* make sure all see the newly published array before releasing rtnl */
+ synchronize_rcu();
}
static void remove_nexthop_group(struct nexthop *nh, struct nl_info *nlinfo)
@@ -759,10 +776,7 @@ static void remove_nexthop_group(struct nexthop *nh, struct nl_info *nlinfo)
if (WARN_ON(!nhge->nh))
continue;
- list_del(&nhge->nh_list);
- nexthop_put(nhge->nh);
- nhge->nh = NULL;
- nhg->num_nh--;
+ list_del_init(&nhge->nh_list);
}
}
@@ -1085,6 +1099,7 @@ static struct nexthop *nexthop_create_group(struct net *net,
{
struct nlattr *grps_attr = cfg->nh_grp;
struct nexthop_grp *entry = nla_data(grps_attr);
+ u16 num_nh = nla_len(grps_attr) / sizeof(*entry);
struct nh_group *nhg;
struct nexthop *nh;
int i;
@@ -1095,12 +1110,21 @@ static struct nexthop *nexthop_create_group(struct net *net,
nh->is_group = 1;
- nhg = nexthop_grp_alloc(nla_len(grps_attr) / sizeof(*entry));
+ nhg = nexthop_grp_alloc(num_nh);
if (!nhg) {
kfree(nh);
return ERR_PTR(-ENOMEM);
}
+ /* spare group used for removals */
+ nhg->spare = nexthop_grp_alloc(num_nh);
+ if (!nhg) {
+ kfree(nhg);
+ kfree(nh);
+ return NULL;
+ }
+ nhg->spare->spare = nhg;
+
for (i = 0; i < nhg->num_nh; ++i) {
struct nexthop *nhe;
struct nh_info *nhi;
@@ -1132,6 +1156,7 @@ out_no_nh:
for (; i >= 0; --i)
nexthop_put(nhg->nh_entries[i].nh);
+ kfree(nhg->spare);
kfree(nhg);
kfree(nh);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index ebe7060d0fc9..fea6a8a11183 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -491,18 +491,16 @@ u32 ip_idents_reserve(u32 hash, int segs)
atomic_t *p_id = ip_idents + hash % IP_IDENTS_SZ;
u32 old = READ_ONCE(*p_tstamp);
u32 now = (u32)jiffies;
- u32 new, delta = 0;
+ u32 delta = 0;
if (old != now && cmpxchg(p_tstamp, old, now) == old)
delta = prandom_u32_max(now - old);
- /* Do not use atomic_add_return() as it makes UBSAN unhappy */
- do {
- old = (u32)atomic_read(p_id);
- new = old + delta + segs;
- } while (atomic_cmpxchg(p_id, old, new) != old);
-
- return new - segs;
+ /* If UBSAN reports an error there, please make sure your compiler
+ * supports -fno-strict-overflow before reporting it that was a bug
+ * in UBSAN, and it has been fixed in GCC-8.
+ */
+ return atomic_add_return(segs + delta, p_id) - segs;
}
EXPORT_SYMBOL(ip_idents_reserve);
@@ -915,7 +913,7 @@ void ip_rt_send_redirect(struct sk_buff *skb)
/* Check for load limit; set rate_last to the latest sent
* redirect.
*/
- if (peer->rate_tokens == 0 ||
+ if (peer->n_redirects == 0 ||
time_after(jiffies,
(peer->rate_last +
(ip_rt_redirect_load << peer->n_redirects)))) {
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index dc77c303e6f7..06aad5e09459 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -476,9 +476,17 @@ static void tcp_tx_timestamp(struct sock *sk, u16 tsflags)
static inline bool tcp_stream_is_readable(const struct tcp_sock *tp,
int target, struct sock *sk)
{
- return (READ_ONCE(tp->rcv_nxt) - READ_ONCE(tp->copied_seq) >= target) ||
- (sk->sk_prot->stream_memory_read ?
- sk->sk_prot->stream_memory_read(sk) : false);
+ int avail = READ_ONCE(tp->rcv_nxt) - READ_ONCE(tp->copied_seq);
+
+ if (avail > 0) {
+ if (avail >= target)
+ return true;
+ if (tcp_rmem_pressure(sk))
+ return true;
+ }
+ if (sk->sk_prot->stream_memory_read)
+ return sk->sk_prot->stream_memory_read(sk);
+ return false;
}
/*
@@ -1756,10 +1764,11 @@ static int tcp_zerocopy_receive(struct sock *sk,
down_read(&current->mm->mmap_sem);
- ret = -EINVAL;
vma = find_vma(current->mm, address);
- if (!vma || vma->vm_start > address || vma->vm_ops != &tcp_vm_ops)
- goto out;
+ if (!vma || vma->vm_start > address || vma->vm_ops != &tcp_vm_ops) {
+ up_read(&current->mm->mmap_sem);
+ return -EINVAL;
+ }
zc->length = min_t(unsigned long, zc->length, vma->vm_end - address);
tp = tcp_sk(sk);
@@ -2154,13 +2163,15 @@ skip_copy:
tp->urg_data = 0;
tcp_fast_path_check(sk);
}
- if (used + offset < skb->len)
- continue;
if (TCP_SKB_CB(skb)->has_rxtstamp) {
tcp_update_recv_tstamps(skb, &tss);
cmsg_flags |= 2;
}
+
+ if (used + offset < skb->len)
+ continue;
+
if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
goto found_fin_ok;
if (!(flags & MSG_PEEK))
diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index 8a01428f80c1..69b025408390 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -121,14 +121,17 @@ int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
struct sk_psock *psock;
int copied, ret;
+ if (unlikely(flags & MSG_ERRQUEUE))
+ return inet_recv_error(sk, msg, len, addr_len);
+
psock = sk_psock_get(sk);
if (unlikely(!psock))
return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
- if (unlikely(flags & MSG_ERRQUEUE))
- return inet_recv_error(sk, msg, len, addr_len);
if (!skb_queue_empty(&sk->sk_receive_queue) &&
- sk_psock_queue_empty(psock))
+ sk_psock_queue_empty(psock)) {
+ sk_psock_put(sk, psock);
return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
+ }
lock_sock(sk);
msg_bytes_ready:
copied = __tcp_bpf_recvmsg(sk, psock, msg, len, flags);
@@ -200,7 +203,6 @@ static int bpf_tcp_ingress(struct sock *sk, struct sk_psock *psock,
if (!ret) {
msg->sg.start = i;
- msg->sg.size -= apply_bytes;
sk_psock_queue_msg(psock, tmp);
sk_psock_data_ready(sk, psock);
} else {
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 6b6b57000dad..e17d396102ce 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4761,7 +4761,8 @@ void tcp_data_ready(struct sock *sk)
const struct tcp_sock *tp = tcp_sk(sk);
int avail = tp->rcv_nxt - tp->copied_seq;
- if (avail < sk->sk_rcvlowat && !sock_flag(sk, SOCK_DONE))
+ if (avail < sk->sk_rcvlowat && !tcp_rmem_pressure(sk) &&
+ !sock_flag(sk, SOCK_DONE))
return;
sk->sk_data_ready(sk);
generated by cgit 1.2.3-korg (git 2.39.0) at 2024-04-27 17:52:58 +0000