summaryrefslogtreecommitdiff
path: root/net
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2023-08-03 14:00:02 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2023-08-03 14:00:02 -0700
commit999f6631866e9ea81add935b9c6ebaab0579d259 (patch)
treeaae62c1a7398a9a58fc0099979828062fd1ac540 /net
parent7bafbd4027ae86572f308c4ddf93120c90126332 (diff)
parent0765c5f293357ee43eca72e27c3547f9d99ac355 (diff)
Merge tag 'net-6.5-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
Pull networking fixes from Jakub Kicinski: "Including fixes from bpf and wireless. Nothing scary here. Feels like the first wave of regressions from v6.5 is addressed - one outstanding fix still to come in TLS for the sendpage rework. Current release - regressions: - udp: fix __ip_append_data()'s handling of MSG_SPLICE_PAGES - dsa: fix older DSA drivers using phylink Previous releases - regressions: - gro: fix misuse of CB in udp socket lookup - mlx5: unregister devlink params in case interface is down - Revert "wifi: ath11k: Enable threaded NAPI" Previous releases - always broken: - sched: cls_u32: fix match key mis-addressing - sched: bind logic fixes for cls_fw, cls_u32 and cls_route - add bound checks to a number of places which hand-parse netlink - bpf: disable preemption in perf_event_output helpers code - qed: fix scheduling in a tasklet while getting stats - avoid using APIs which are not hardirq-safe in couple of drivers, when we may be in a hard IRQ (netconsole) - wifi: cfg80211: fix return value in scan logic, avoid page allocator warning - wifi: mt76: mt7615: do not advertise 5 GHz on first PHY of MT7615D (DBDC) Misc: - drop handful of inactive maintainers, put some new in place" * tag 'net-6.5-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (98 commits) MAINTAINERS: update TUN/TAP maintainers test/vsock: remove vsock_perf executable on `make clean` tcp_metrics: fix data-race in tcpm_suck_dst() vs fastopen tcp_metrics: annotate data-races around tm->tcpm_net tcp_metrics: annotate data-races around tm->tcpm_vals[] tcp_metrics: annotate data-races around tm->tcpm_lock tcp_metrics: annotate data-races around tm->tcpm_stamp tcp_metrics: fix addr_same() helper prestera: fix fallback to previous version on same major version udp: Fix __ip_append_data()'s handling of MSG_SPLICE_PAGES net/mlx5e: Set proper IPsec source port in L4 selector net/mlx5: fs_core: Skip the FTs in the same FS_TYPE_PRIO_CHAINS fs_prio net/mlx5: fs_core: Make find_closest_ft more generic wifi: brcmfmac: Fix field-spanning write in brcmf_scan_params_v2_to_v1() vxlan: Fix nexthop hash size ip6mr: Fix skb_under_panic in ip6mr_cache_report() s390/qeth: Don't call dev_close/dev_open (DOWN/UP) net: tap_open(): set sk_uid from current_fsuid() net: tun_chr_open(): set sk_uid from current_fsuid() net: dcb: choose correct policy to parse DCB_ATTR_BCN ...
Diffstat (limited to 'net')
-rw-r--r--net/can/raw.c2
-rw-r--r--net/core/bpf_sk_storage.c5
-rw-r--r--net/core/rtnetlink.c8
-rw-r--r--net/core/sock.c69
-rw-r--r--net/core/sock_map.c2
-rw-r--r--net/dcb/dcbnl.c2
-rw-r--r--net/dccp/ipv6.c4
-rw-r--r--net/dsa/port.c9
-rw-r--r--net/ipv4/inet_diag.c4
-rw-r--r--net/ipv4/ip_output.c17
-rw-r--r--net/ipv4/ip_sockglue.c2
-rw-r--r--net/ipv4/raw.c2
-rw-r--r--net/ipv4/route.c4
-rw-r--r--net/ipv4/tcp_ipv4.c4
-rw-r--r--net/ipv4/tcp_metrics.c70
-rw-r--r--net/ipv4/udp.c8
-rw-r--r--net/ipv4/udp_offload.c7
-rw-r--r--net/ipv6/ip6mr.c2
-rw-r--r--net/ipv6/ping.c2
-rw-r--r--net/ipv6/raw.c6
-rw-r--r--net/ipv6/route.c7
-rw-r--r--net/ipv6/tcp_ipv6.c9
-rw-r--r--net/ipv6/udp.c12
-rw-r--r--net/ipv6/udp_offload.c7
-rw-r--r--net/l2tp/l2tp_ip6.c2
-rw-r--r--net/mptcp/sockopt.c2
-rw-r--r--net/netfilter/nft_socket.c2
-rw-r--r--net/netfilter/xt_socket.c4
-rw-r--r--net/packet/af_packet.c12
-rw-r--r--net/sched/cls_flower.c5
-rw-r--r--net/sched/cls_fw.c1
-rw-r--r--net/sched/cls_route.c1
-rw-r--r--net/sched/cls_u32.c57
-rw-r--r--net/sched/em_meta.c4
-rw-r--r--net/sched/sch_taprio.c15
-rw-r--r--net/smc/af_smc.c2
-rw-r--r--net/unix/af_unix.c2
-rw-r--r--net/wireless/scan.c2
-rw-r--r--net/xdp/xsk.c2
-rw-r--r--net/xfrm/xfrm_policy.c2
40 files changed, 249 insertions, 130 deletions
diff --git a/net/can/raw.c b/net/can/raw.c
index ba6b52b1d776..e10f59375659 100644
--- a/net/can/raw.c
+++ b/net/can/raw.c
@@ -865,7 +865,7 @@ static int raw_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
skb->dev = dev;
skb->priority = sk->sk_priority;
- skb->mark = sk->sk_mark;
+ skb->mark = READ_ONCE(sk->sk_mark);
skb->tstamp = sockc.transmit_time;
skb_setup_tx_timestamp(skb, sockc.tsflags);
diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c
index d4172534dfa8..cca7594be92e 100644
--- a/net/core/bpf_sk_storage.c
+++ b/net/core/bpf_sk_storage.c
@@ -496,8 +496,11 @@ bpf_sk_storage_diag_alloc(const struct nlattr *nla_stgs)
return ERR_PTR(-EPERM);
nla_for_each_nested(nla, nla_stgs, rem) {
- if (nla_type(nla) == SK_DIAG_BPF_STORAGE_REQ_MAP_FD)
+ if (nla_type(nla) == SK_DIAG_BPF_STORAGE_REQ_MAP_FD) {
+ if (nla_len(nla) != sizeof(u32))
+ return ERR_PTR(-EINVAL);
nr_maps++;
+ }
}
diag = kzalloc(struct_size(diag, maps, nr_maps), GFP_KERNEL);
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 3ad4e030846d..aef25aa5cf1d 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -5140,13 +5140,17 @@ static int rtnl_bridge_setlink(struct sk_buff *skb, struct nlmsghdr *nlh,
br_spec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC);
if (br_spec) {
nla_for_each_nested(attr, br_spec, rem) {
- if (nla_type(attr) == IFLA_BRIDGE_FLAGS) {
+ if (nla_type(attr) == IFLA_BRIDGE_FLAGS && !have_flags) {
if (nla_len(attr) < sizeof(flags))
return -EINVAL;
have_flags = true;
flags = nla_get_u16(attr);
- break;
+ }
+
+ if (nla_type(attr) == IFLA_BRIDGE_MODE) {
+ if (nla_len(attr) < sizeof(u16))
+ return -EINVAL;
}
}
}
diff --git a/net/core/sock.c b/net/core/sock.c
index 9370fd50aa2c..6d4f28efe29a 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -429,6 +429,7 @@ static int sock_set_timeout(long *timeo_p, sockptr_t optval, int optlen,
{
struct __kernel_sock_timeval tv;
int err = sock_copy_user_timeval(&tv, optval, optlen, old_timeval);
+ long val;
if (err)
return err;
@@ -439,7 +440,7 @@ static int sock_set_timeout(long *timeo_p, sockptr_t optval, int optlen,
if (tv.tv_sec < 0) {
static int warned __read_mostly;
- *timeo_p = 0;
+ WRITE_ONCE(*timeo_p, 0);
if (warned < 10 && net_ratelimit()) {
warned++;
pr_info("%s: `%s' (pid %d) tries to set negative timeout\n",
@@ -447,11 +448,12 @@ static int sock_set_timeout(long *timeo_p, sockptr_t optval, int optlen,
}
return 0;
}
- *timeo_p = MAX_SCHEDULE_TIMEOUT;
- if (tv.tv_sec == 0 && tv.tv_usec == 0)
- return 0;
- if (tv.tv_sec < (MAX_SCHEDULE_TIMEOUT / HZ - 1))
- *timeo_p = tv.tv_sec * HZ + DIV_ROUND_UP((unsigned long)tv.tv_usec, USEC_PER_SEC / HZ);
+ val = MAX_SCHEDULE_TIMEOUT;
+ if ((tv.tv_sec || tv.tv_usec) &&
+ (tv.tv_sec < (MAX_SCHEDULE_TIMEOUT / HZ - 1)))
+ val = tv.tv_sec * HZ + DIV_ROUND_UP((unsigned long)tv.tv_usec,
+ USEC_PER_SEC / HZ);
+ WRITE_ONCE(*timeo_p, val);
return 0;
}
@@ -804,7 +806,7 @@ EXPORT_SYMBOL(sock_no_linger);
void sock_set_priority(struct sock *sk, u32 priority)
{
lock_sock(sk);
- sk->sk_priority = priority;
+ WRITE_ONCE(sk->sk_priority, priority);
release_sock(sk);
}
EXPORT_SYMBOL(sock_set_priority);
@@ -813,9 +815,9 @@ void sock_set_sndtimeo(struct sock *sk, s64 secs)
{
lock_sock(sk);
if (secs && secs < MAX_SCHEDULE_TIMEOUT / HZ - 1)
- sk->sk_sndtimeo = secs * HZ;
+ WRITE_ONCE(sk->sk_sndtimeo, secs * HZ);
else
- sk->sk_sndtimeo = MAX_SCHEDULE_TIMEOUT;
+ WRITE_ONCE(sk->sk_sndtimeo, MAX_SCHEDULE_TIMEOUT);
release_sock(sk);
}
EXPORT_SYMBOL(sock_set_sndtimeo);
@@ -988,7 +990,7 @@ EXPORT_SYMBOL(sock_set_rcvbuf);
static void __sock_set_mark(struct sock *sk, u32 val)
{
if (val != sk->sk_mark) {
- sk->sk_mark = val;
+ WRITE_ONCE(sk->sk_mark, val);
sk_dst_reset(sk);
}
}
@@ -1007,7 +1009,7 @@ static void sock_release_reserved_memory(struct sock *sk, int bytes)
bytes = round_down(bytes, PAGE_SIZE);
WARN_ON(bytes > sk->sk_reserved_mem);
- sk->sk_reserved_mem -= bytes;
+ WRITE_ONCE(sk->sk_reserved_mem, sk->sk_reserved_mem - bytes);
sk_mem_reclaim(sk);
}
@@ -1044,7 +1046,8 @@ static int sock_reserve_memory(struct sock *sk, int bytes)
}
sk->sk_forward_alloc += pages << PAGE_SHIFT;
- sk->sk_reserved_mem += pages << PAGE_SHIFT;
+ WRITE_ONCE(sk->sk_reserved_mem,
+ sk->sk_reserved_mem + (pages << PAGE_SHIFT));
return 0;
}
@@ -1213,7 +1216,7 @@ set_sndbuf:
if ((val >= 0 && val <= 6) ||
sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) ||
sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))
- sk->sk_priority = val;
+ WRITE_ONCE(sk->sk_priority, val);
else
ret = -EPERM;
break;
@@ -1438,7 +1441,8 @@ set_sndbuf:
cmpxchg(&sk->sk_pacing_status,
SK_PACING_NONE,
SK_PACING_NEEDED);
- sk->sk_max_pacing_rate = ulval;
+ /* Pairs with READ_ONCE() from sk_getsockopt() */
+ WRITE_ONCE(sk->sk_max_pacing_rate, ulval);
sk->sk_pacing_rate = min(sk->sk_pacing_rate, ulval);
break;
}
@@ -1533,7 +1537,9 @@ set_sndbuf:
}
if ((u8)val == SOCK_TXREHASH_DEFAULT)
val = READ_ONCE(sock_net(sk)->core.sysctl_txrehash);
- /* Paired with READ_ONCE() in tcp_rtx_synack() */
+ /* Paired with READ_ONCE() in tcp_rtx_synack()
+ * and sk_getsockopt().
+ */
WRITE_ONCE(sk->sk_txrehash, (u8)val);
break;
@@ -1633,11 +1639,11 @@ int sk_getsockopt(struct sock *sk, int level, int optname,
break;
case SO_SNDBUF:
- v.val = sk->sk_sndbuf;
+ v.val = READ_ONCE(sk->sk_sndbuf);
break;
case SO_RCVBUF:
- v.val = sk->sk_rcvbuf;
+ v.val = READ_ONCE(sk->sk_rcvbuf);
break;
case SO_REUSEADDR:
@@ -1679,7 +1685,7 @@ int sk_getsockopt(struct sock *sk, int level, int optname,
break;
case SO_PRIORITY:
- v.val = sk->sk_priority;
+ v.val = READ_ONCE(sk->sk_priority);
break;
case SO_LINGER:
@@ -1717,16 +1723,18 @@ int sk_getsockopt(struct sock *sk, int level, int optname,
case SO_RCVTIMEO_OLD:
case SO_RCVTIMEO_NEW:
- lv = sock_get_timeout(sk->sk_rcvtimeo, &v, SO_RCVTIMEO_OLD == optname);
+ lv = sock_get_timeout(READ_ONCE(sk->sk_rcvtimeo), &v,
+ SO_RCVTIMEO_OLD == optname);
break;
case SO_SNDTIMEO_OLD:
case SO_SNDTIMEO_NEW:
- lv = sock_get_timeout(sk->sk_sndtimeo, &v, SO_SNDTIMEO_OLD == optname);
+ lv = sock_get_timeout(READ_ONCE(sk->sk_sndtimeo), &v,
+ SO_SNDTIMEO_OLD == optname);
break;
case SO_RCVLOWAT:
- v.val = sk->sk_rcvlowat;
+ v.val = READ_ONCE(sk->sk_rcvlowat);
break;
case SO_SNDLOWAT:
@@ -1843,7 +1851,7 @@ int sk_getsockopt(struct sock *sk, int level, int optname,
optval, optlen, len);
case SO_MARK:
- v.val = sk->sk_mark;
+ v.val = READ_ONCE(sk->sk_mark);
break;
case SO_RCVMARK:
@@ -1862,7 +1870,7 @@ int sk_getsockopt(struct sock *sk, int level, int optname,
if (!sock->ops->set_peek_off)
return -EOPNOTSUPP;
- v.val = sk->sk_peek_off;
+ v.val = READ_ONCE(sk->sk_peek_off);
break;
case SO_NOFCS:
v.val = sock_flag(sk, SOCK_NOFCS);
@@ -1892,7 +1900,7 @@ int sk_getsockopt(struct sock *sk, int level, int optname,
#ifdef CONFIG_NET_RX_BUSY_POLL
case SO_BUSY_POLL:
- v.val = sk->sk_ll_usec;
+ v.val = READ_ONCE(sk->sk_ll_usec);
break;
case SO_PREFER_BUSY_POLL:
v.val = READ_ONCE(sk->sk_prefer_busy_poll);
@@ -1900,12 +1908,14 @@ int sk_getsockopt(struct sock *sk, int level, int optname,
#endif
case SO_MAX_PACING_RATE:
+ /* The READ_ONCE() pair with the WRITE_ONCE() in sk_setsockopt() */
if (sizeof(v.ulval) != sizeof(v.val) && len >= sizeof(v.ulval)) {
lv = sizeof(v.ulval);
- v.ulval = sk->sk_max_pacing_rate;
+ v.ulval = READ_ONCE(sk->sk_max_pacing_rate);
} else {
/* 32bit version */
- v.val = min_t(unsigned long, sk->sk_max_pacing_rate, ~0U);
+ v.val = min_t(unsigned long, ~0U,
+ READ_ONCE(sk->sk_max_pacing_rate));
}
break;
@@ -1973,11 +1983,12 @@ int sk_getsockopt(struct sock *sk, int level, int optname,
break;
case SO_RESERVE_MEM:
- v.val = sk->sk_reserved_mem;
+ v.val = READ_ONCE(sk->sk_reserved_mem);
break;
case SO_TXREHASH:
- v.val = sk->sk_txrehash;
+ /* Paired with WRITE_ONCE() in sk_setsockopt() */
+ v.val = READ_ONCE(sk->sk_txrehash);
break;
default:
@@ -3168,7 +3179,7 @@ EXPORT_SYMBOL(__sk_mem_reclaim);
int sk_set_peek_off(struct sock *sk, int val)
{
- sk->sk_peek_off = val;
+ WRITE_ONCE(sk->sk_peek_off, val);
return 0;
}
EXPORT_SYMBOL_GPL(sk_set_peek_off);
diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index 19538d628714..08ab108206bf 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -115,7 +115,6 @@ static void sock_map_sk_acquire(struct sock *sk)
__acquires(&sk->sk_lock.slock)
{
lock_sock(sk);
- preempt_disable();
rcu_read_lock();
}
@@ -123,7 +122,6 @@ static void sock_map_sk_release(struct sock *sk)
__releases(&sk->sk_lock.slock)
{
rcu_read_unlock();
- preempt_enable();
release_sock(sk);
}
diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c
index c0c438128575..2e6b8c8fd2de 100644
--- a/net/dcb/dcbnl.c
+++ b/net/dcb/dcbnl.c
@@ -980,7 +980,7 @@ static int dcbnl_bcn_setcfg(struct net_device *netdev, struct nlmsghdr *nlh,
return -EOPNOTSUPP;
ret = nla_parse_nested_deprecated(data, DCB_BCN_ATTR_MAX,
- tb[DCB_ATTR_BCN], dcbnl_pfc_up_nest,
+ tb[DCB_ATTR_BCN], dcbnl_bcn_nest,
NULL);
if (ret)
return ret;
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 7249ef218178..d29d1163203d 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -238,8 +238,8 @@ static int dccp_v6_send_response(const struct sock *sk, struct request_sock *req
opt = ireq->ipv6_opt;
if (!opt)
opt = rcu_dereference(np->opt);
- err = ip6_xmit(sk, skb, &fl6, sk->sk_mark, opt, np->tclass,
- sk->sk_priority);
+ err = ip6_xmit(sk, skb, &fl6, READ_ONCE(sk->sk_mark), opt,
+ np->tclass, sk->sk_priority);
rcu_read_unlock();
err = net_xmit_eval(err);
}
diff --git a/net/dsa/port.c b/net/dsa/port.c
index 0ce8fd311c78..2f6195d7b741 100644
--- a/net/dsa/port.c
+++ b/net/dsa/port.c
@@ -1727,8 +1727,15 @@ int dsa_port_phylink_create(struct dsa_port *dp)
ds->ops->phylink_mac_an_restart)
dp->pl_config.legacy_pre_march2020 = true;
- if (ds->ops->phylink_get_caps)
+ if (ds->ops->phylink_get_caps) {
ds->ops->phylink_get_caps(ds, dp->index, &dp->pl_config);
+ } else {
+ /* For legacy drivers */
+ __set_bit(PHY_INTERFACE_MODE_INTERNAL,
+ dp->pl_config.supported_interfaces);
+ __set_bit(PHY_INTERFACE_MODE_GMII,
+ dp->pl_config.supported_interfaces);
+ }
pl = phylink_create(&dp->pl_config, of_fwnode_handle(dp->dn),
mode, &dsa_port_phylink_mac_ops);
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index b812eb36f0e3..f7426926a104 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -150,7 +150,7 @@ int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb,
}
#endif
- if (net_admin && nla_put_u32(skb, INET_DIAG_MARK, sk->sk_mark))
+ if (net_admin && nla_put_u32(skb, INET_DIAG_MARK, READ_ONCE(sk->sk_mark)))
goto errout;
if (ext & (1 << (INET_DIAG_CLASS_ID - 1)) ||
@@ -799,7 +799,7 @@ int inet_diag_bc_sk(const struct nlattr *bc, struct sock *sk)
entry.ifindex = sk->sk_bound_dev_if;
entry.userlocks = sk_fullsock(sk) ? sk->sk_userlocks : 0;
if (sk_fullsock(sk))
- entry.mark = sk->sk_mark;
+ entry.mark = READ_ONCE(sk->sk_mark);
else if (sk->sk_state == TCP_NEW_SYN_RECV)
entry.mark = inet_rsk(inet_reqsk(sk))->ir_mark;
else if (sk->sk_state == TCP_TIME_WAIT)
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 6e70839257f7..6ba1a0fafbaa 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -184,9 +184,9 @@ int ip_build_and_send_pkt(struct sk_buff *skb, const struct sock *sk,
ip_options_build(skb, &opt->opt, daddr, rt);
}
- skb->priority = sk->sk_priority;
+ skb->priority = READ_ONCE(sk->sk_priority);
if (!skb->mark)
- skb->mark = sk->sk_mark;
+ skb->mark = READ_ONCE(sk->sk_mark);
/* Send it out. */
return ip_local_out(net, skb->sk, skb);
@@ -528,8 +528,8 @@ packet_routed:
skb_shinfo(skb)->gso_segs ?: 1);
/* TODO : should we use skb->sk here instead of sk ? */
- skb->priority = sk->sk_priority;
- skb->mark = sk->sk_mark;
+ skb->priority = READ_ONCE(sk->sk_priority);
+ skb->mark = READ_ONCE(sk->sk_mark);
res = ip_local_out(net, sk, skb);
rcu_read_unlock();
@@ -1158,10 +1158,15 @@ alloc_new_skb:
}
copy = datalen - transhdrlen - fraggap - pagedlen;
+ /* [!] NOTE: copy will be negative if pagedlen>0
+ * because then the equation reduces to -fraggap.
+ */
if (copy > 0 && getfrag(from, data + transhdrlen, offset, copy, fraggap, skb) < 0) {
err = -EFAULT;
kfree_skb(skb);
goto error;
+ } else if (flags & MSG_SPLICE_PAGES) {
+ copy = 0;
}
offset += copy;
@@ -1209,6 +1214,10 @@ alloc_new_skb:
} else if (flags & MSG_SPLICE_PAGES) {
struct msghdr *msg = from;
+ err = -EIO;
+ if (WARN_ON_ONCE(copy > msg->msg_iter.count))
+ goto error;
+
err = skb_splice_from_iter(skb, &msg->msg_iter, copy,
sk->sk_allocation);
if (err < 0)
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 8e97d8d4cc9d..d41bce8927b2 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -592,7 +592,7 @@ void __ip_sock_set_tos(struct sock *sk, int val)
}
if (inet_sk(sk)->tos != val) {
inet_sk(sk)->tos = val;
- sk->sk_priority = rt_tos2priority(val);
+ WRITE_ONCE(sk->sk_priority, rt_tos2priority(val));
sk_dst_reset(sk);
}
}
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 7782ff5e6539..cb381f5aa464 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -348,7 +348,7 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4,
goto error;
skb_reserve(skb, hlen);
- skb->priority = sk->sk_priority;
+ skb->priority = READ_ONCE(sk->sk_priority);
skb->mark = sockc->mark;
skb->tstamp = sockc->transmit_time;
skb_dst_set(skb, &rt->dst);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 98d7e6ba7493..92fede388d52 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -518,7 +518,7 @@ static void __build_flow_key(const struct net *net, struct flowi4 *fl4,
const struct inet_sock *inet = inet_sk(sk);
oif = sk->sk_bound_dev_if;
- mark = sk->sk_mark;
+ mark = READ_ONCE(sk->sk_mark);
tos = ip_sock_rt_tos(sk);
scope = ip_sock_rt_scope(sk);
prot = inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol;
@@ -552,7 +552,7 @@ static void build_sk_flow_key(struct flowi4 *fl4, const struct sock *sk)
inet_opt = rcu_dereference(inet->inet_opt);
if (inet_opt && inet_opt->opt.srr)
daddr = inet_opt->opt.faddr;
- flowi4_init_output(fl4, sk->sk_bound_dev_if, sk->sk_mark,
+ flowi4_init_output(fl4, sk->sk_bound_dev_if, READ_ONCE(sk->sk_mark),
ip_sock_rt_tos(sk) & IPTOS_RT_MASK,
ip_sock_rt_scope(sk),
inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol,
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 069642014636..a59cc4b83861 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -931,9 +931,9 @@ static void tcp_v4_send_ack(const struct sock *sk,
ctl_sk = this_cpu_read(ipv4_tcp_sk);
sock_net_set(ctl_sk, net);
ctl_sk->sk_mark = (sk->sk_state == TCP_TIME_WAIT) ?
- inet_twsk(sk)->tw_mark : sk->sk_mark;
+ inet_twsk(sk)->tw_mark : READ_ONCE(sk->sk_mark);
ctl_sk->sk_priority = (sk->sk_state == TCP_TIME_WAIT) ?
- inet_twsk(sk)->tw_priority : sk->sk_priority;
+ inet_twsk(sk)->tw_priority : READ_ONCE(sk->sk_priority);
transmit_time = tcp_transmit_time(sk);
ip_send_unicast_reply(ctl_sk,
skb, &TCP_SKB_CB(skb)->header.h4.opt,
diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
index 82f4575f9cd9..99ac5efe244d 100644
--- a/net/ipv4/tcp_metrics.c
+++ b/net/ipv4/tcp_metrics.c
@@ -40,7 +40,7 @@ struct tcp_fastopen_metrics {
struct tcp_metrics_block {
struct tcp_metrics_block __rcu *tcpm_next;
- possible_net_t tcpm_net;
+ struct net *tcpm_net;
struct inetpeer_addr tcpm_saddr;
struct inetpeer_addr tcpm_daddr;
unsigned long tcpm_stamp;
@@ -51,34 +51,38 @@ struct tcp_metrics_block {
struct rcu_head rcu_head;
};
-static inline struct net *tm_net(struct tcp_metrics_block *tm)
+static inline struct net *tm_net(const struct tcp_metrics_block *tm)
{
- return read_pnet(&tm->tcpm_net);
+ /* Paired with the WRITE_ONCE() in tcpm_new() */
+ return READ_ONCE(tm->tcpm_net);
}
static bool tcp_metric_locked(struct tcp_metrics_block *tm,
enum tcp_metric_index idx)
{
- return tm->tcpm_lock & (1 << idx);
+ /* Paired with WRITE_ONCE() in tcpm_suck_dst() */
+ return READ_ONCE(tm->tcpm_lock) & (1 << idx);
}
-static u32 tcp_metric_get(struct tcp_metrics_block *tm,
+static u32 tcp_metric_get(const struct tcp_metrics_block *tm,
enum tcp_metric_index idx)
{
- return tm->tcpm_vals[idx];
+ /* Paired with WRITE_ONCE() in tcp_metric_set() */
+ return READ_ONCE(tm->tcpm_vals[idx]);
}
static void tcp_metric_set(struct tcp_metrics_block *tm,
enum tcp_metric_index idx,
u32 val)
{
- tm->tcpm_vals[idx] = val;
+ /* Paired with READ_ONCE() in tcp_metric_get() */
+ WRITE_ONCE(tm->tcpm_vals[idx], val);
}
static bool addr_same(const struct inetpeer_addr *a,
const struct inetpeer_addr *b)
{
- return inetpeer_addr_cmp(a, b) == 0;
+ return (a->family == b->family) && !inetpeer_addr_cmp(a, b);
}
struct tcpm_hash_bucket {
@@ -89,6 +93,7 @@ static struct tcpm_hash_bucket *tcp_metrics_hash __read_mostly;
static unsigned int tcp_metrics_hash_log __read_mostly;
static DEFINE_SPINLOCK(tcp_metrics_lock);
+static DEFINE_SEQLOCK(fastopen_seqlock);
static void tcpm_suck_dst(struct tcp_metrics_block *tm,
const struct dst_entry *dst,
@@ -97,7 +102,7 @@ static void tcpm_suck_dst(struct tcp_metrics_block *tm,
u32 msval;
u32 val;
- tm->tcpm_stamp = jiffies;
+ WRITE_ONCE(tm->tcpm_stamp, jiffies);
val = 0;
if (dst_metric_locked(dst, RTAX_RTT))
@@ -110,30 +115,42 @@ static void tcpm_suck_dst(struct tcp_metrics_block *tm,
val |= 1 << TCP_METRIC_CWND;
if (dst_metric_locked(dst, RTAX_REORDERING))
val |= 1 << TCP_METRIC_REORDERING;
- tm->tcpm_lock = val;
+ /* Paired with READ_ONCE() in tcp_metric_locked() */
+ WRITE_ONCE(tm->tcpm_lock, val);
msval = dst_metric_raw(dst, RTAX_RTT);
- tm->tcpm_vals[TCP_METRIC_RTT] = msval * USEC_PER_MSEC;
+ tcp_metric_set(tm, TCP_METRIC_RTT, msval * USEC_PER_MSEC);
msval = dst_metric_raw(dst, RTAX_RTTVAR);
- tm->tcpm_vals[TCP_METRIC_RTTVAR] = msval * USEC_PER_MSEC;
- tm->tcpm_vals[TCP_METRIC_SSTHRESH] = dst_metric_raw(dst, RTAX_SSTHRESH);
- tm->tcpm_vals[TCP_METRIC_CWND] = dst_metric_raw(dst, RTAX_CWND);
- tm->tcpm_vals[TCP_METRIC_REORDERING] = dst_metric_raw(dst, RTAX_REORDERING);
+ tcp_metric_set(tm, TCP_METRIC_RTTVAR, msval * USEC_PER_MSEC);
+ tcp_metric_set(tm, TCP_METRIC_SSTHRESH,
+ dst_metric_raw(dst, RTAX_SSTHRESH));
+ tcp_metric_set(tm, TCP_METRIC_CWND,
+ dst_metric_raw(dst, RTAX_CWND));
+ tcp_metric_set(tm, TCP_METRIC_REORDERING,
+ dst_metric_raw(dst, RTAX_REORDERING));
if (fastopen_clear) {
+ write_seqlock(&fastopen_seqlock);
tm->tcpm_fastopen.mss = 0;
tm->tcpm_fastopen.syn_loss = 0;
tm->tcpm_fastopen.try_exp = 0;
tm->tcpm_fastopen.cookie.exp = false;
tm->tcpm_fastopen.cookie.len = 0;
+ write_sequnlock(&fastopen_seqlock);
}
}
#define TCP_METRICS_TIMEOUT (60 * 60 * HZ)
-static void tcpm_check_stamp(struct tcp_metrics_block *tm, struct dst_entry *dst)
+static void tcpm_check_stamp(struct tcp_metrics_block *tm,
+ const struct dst_entry *dst)
{
- if (tm && unlikely(time_after(jiffies, tm->tcpm_stamp + TCP_METRICS_TIMEOUT)))
+ unsigned long limit;
+
+ if (!tm)
+ return;
+ limit = READ_ONCE(tm->tcpm_stamp) + TCP_METRICS_TIMEOUT;
+ if (unlikely(time_after(jiffies, limit)))
tcpm_suck_dst(tm, dst, false);
}
@@ -174,20 +191,23 @@ static struct tcp_metrics_block *tcpm_new(struct dst_entry *dst,
oldest = deref_locked(tcp_metrics_hash[hash].chain);
for (tm = deref_locked(oldest->tcpm_next); tm;
tm = deref_locked(tm->tcpm_next)) {
- if (time_before(tm->tcpm_stamp, oldest->tcpm_stamp))
+ if (time_before(READ_ONCE(tm->tcpm_stamp),
+ READ_ONCE(oldest->tcpm_stamp)))
oldest = tm;
}
tm = oldest;
} else {
- tm = kmalloc(sizeof(*tm), GFP_ATOMIC);
+ tm = kzalloc(sizeof(*tm), GFP_ATOMIC);
if (!tm)
goto out_unlock;
}
- write_pnet(&tm->tcpm_net, net);
+ /* Paired with the READ_ONCE() in tm_net() */
+ WRITE_ONCE(tm->tcpm_net, net);
+
tm->tcpm_saddr = *saddr;
tm->tcpm_daddr = *daddr;
- tcpm_suck_dst(tm, dst, true);
+ tcpm_suck_dst(tm, dst, reclaim);
if (likely(!reclaim)) {
tm->tcpm_next = tcp_metrics_hash[hash].chain;
@@ -434,7 +454,7 @@ void tcp_update_metrics(struct sock *sk)
tp->reordering);
}
}
- tm->tcpm_stamp = jiffies;
+ WRITE_ONCE(tm->tcpm_stamp, jiffies);
out_unlock:
rcu_read_unlock();
}
@@ -539,8 +559,6 @@ bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst)
return ret;
}
-static DEFINE_SEQLOCK(fastopen_seqlock);
-
void tcp_fastopen_cache_get(struct sock *sk, u16 *mss,
struct tcp_fastopen_cookie *cookie)
{
@@ -647,7 +665,7 @@ static int tcp_metrics_fill_info(struct sk_buff *msg,
}
if (nla_put_msecs(msg, TCP_METRICS_ATTR_AGE,
- jiffies - tm->tcpm_stamp,
+ jiffies - READ_ONCE(tm->tcpm_stamp),
TCP_METRICS_ATTR_PAD) < 0)
goto nla_put_failure;
@@ -658,7 +676,7 @@ static int tcp_metrics_fill_info(struct sk_buff *msg,
if (!nest)
goto nla_put_failure;
for (i = 0; i < TCP_METRIC_MAX_KERNEL + 1; i++) {
- u32 val = tm->tcpm_vals[i];
+ u32 val = tcp_metric_get(tm, i);
if (!val)
continue;
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 42a96b3547c9..abfa860367aa 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -114,6 +114,7 @@
#include <net/sock_reuseport.h>
#include <net/addrconf.h>
#include <net/udp_tunnel.h>
+#include <net/gro.h>
#if IS_ENABLED(CONFIG_IPV6)
#include <net/ipv6_stubs.h>
#endif
@@ -555,10 +556,13 @@ struct sock *udp4_lib_lookup_skb(const struct sk_buff *skb,
{
const struct iphdr *iph = ip_hdr(skb);
struct net *net = dev_net(skb->dev);
+ int iif, sdif;
+
+ inet_get_iif_sdif(skb, &iif, &sdif);
return __udp4_lib_lookup(net, iph->saddr, sport,
- iph->daddr, dport, inet_iif(skb),
- inet_sdif(skb), net->ipv4.udp_table, NULL);
+ iph->daddr, dport, iif,
+ sdif, net->ipv4.udp_table, NULL);
}
/* Must be called under rcu_read_lock().
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index f402946da344..0f46b3c2e4ac 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -609,10 +609,13 @@ static struct sock *udp4_gro_lookup_skb(struct sk_buff *skb, __be16 sport,
{
const struct iphdr *iph = skb_gro_network_header(skb);
struct net *net = dev_net(skb->dev);
+ int iif, sdif;
+
+ inet_get_iif_sdif(skb, &iif, &sdif);
return __udp4_lib_lookup(net, iph->saddr, sport,
- iph->daddr, dport, inet_iif(skb),
- inet_sdif(skb), net->ipv4.udp_table, NULL);
+ iph->daddr, dport, iif,
+ sdif, net->ipv4.udp_table, NULL);
}
INDIRECT_CALLABLE_SCOPE
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index cc3d5ad17257..67a3b8f6e72b 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -1073,7 +1073,7 @@ static int ip6mr_cache_report(const struct mr_table *mrt, struct sk_buff *pkt,
And all this only to mangle msg->im6_msgtype and
to set msg->im6_mbz to "mbz" :-)
*/
- skb_push(skb, -skb_network_offset(pkt));
+ __skb_pull(skb, skb_network_offset(pkt));
skb_push(skb, sizeof(*msg));
skb_reset_transport_header(skb);
diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c
index f804c11e2146..c2c291827a2c 100644
--- a/net/ipv6/ping.c
+++ b/net/ipv6/ping.c
@@ -120,7 +120,7 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
ipcm6_init_sk(&ipc6, np);
ipc6.sockc.tsflags = sk->sk_tsflags;
- ipc6.sockc.mark = sk->sk_mark;
+ ipc6.sockc.mark = READ_ONCE(sk->sk_mark);
fl6.flowi6_oif = oif;
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index ac1cef094c5f..49381f35b623 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -614,7 +614,7 @@ static int rawv6_send_hdrinc(struct sock *sk, struct msghdr *msg, int length,
skb_reserve(skb, hlen);
skb->protocol = htons(ETH_P_IPV6);
- skb->priority = sk->sk_priority;
+ skb->priority = READ_ONCE(sk->sk_priority);
skb->mark = sockc->mark;
skb->tstamp = sockc->transmit_time;
@@ -774,12 +774,12 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
*/
memset(&fl6, 0, sizeof(fl6));
- fl6.flowi6_mark = sk->sk_mark;
+ fl6.flowi6_mark = READ_ONCE(sk->sk_mark);
fl6.flowi6_uid = sk->sk_uid;
ipcm6_init(&ipc6);
ipc6.sockc.tsflags = sk->sk_tsflags;
- ipc6.sockc.mark = sk->sk_mark;
+ ipc6.sockc.mark = fl6.flowi6_mark;
if (sin6) {
if (addr_len < SIN6_LEN_RFC2133)
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 64e873f5895f..56a55585eb79 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -2951,7 +2951,8 @@ void ip6_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, __be32 mtu)
if (!oif && skb->dev)
oif = l3mdev_master_ifindex(skb->dev);
- ip6_update_pmtu(skb, sock_net(sk), mtu, oif, sk->sk_mark, sk->sk_uid);
+ ip6_update_pmtu(skb, sock_net(sk), mtu, oif, READ_ONCE(sk->sk_mark),
+ sk->sk_uid);
dst = __sk_dst_get(sk);
if (!dst || !dst->obsolete ||
@@ -3172,8 +3173,8 @@ void ip6_redirect_no_header(struct sk_buff *skb, struct net *net, int oif)
void ip6_sk_redirect(struct sk_buff *skb, struct sock *sk)
{
- ip6_redirect(skb, sock_net(sk), sk->sk_bound_dev_if, sk->sk_mark,
- sk->sk_uid);
+ ip6_redirect(skb, sock_net(sk), sk->sk_bound_dev_if,
+ READ_ONCE(sk->sk_mark), sk->sk_uid);
}
EXPORT_SYMBOL_GPL(ip6_sk_redirect);
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 4714eb695913..6e86721e1cdb 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -564,8 +564,8 @@ static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst,
opt = ireq->ipv6_opt;
if (!opt)
opt = rcu_dereference(np->opt);
- err = ip6_xmit(sk, skb, fl6, skb->mark ? : sk->sk_mark, opt,
- tclass, sk->sk_priority);
+ err = ip6_xmit(sk, skb, fl6, skb->mark ? : READ_ONCE(sk->sk_mark),
+ opt, tclass, sk->sk_priority);
rcu_read_unlock();
err = net_xmit_eval(err);
}
@@ -939,7 +939,7 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32
if (sk->sk_state == TCP_TIME_WAIT)
mark = inet_twsk(sk)->tw_mark;
else
- mark = sk->sk_mark;
+ mark = READ_ONCE(sk->sk_mark);
skb_set_delivery_time(buff, tcp_transmit_time(sk), true);
}
if (txhash) {
@@ -1128,7 +1128,8 @@ static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb,
tcp_time_stamp_raw() + tcp_rsk(req)->ts_off,
READ_ONCE(req->ts_recent), sk->sk_bound_dev_if,
tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->saddr, l3index),
- ipv6_get_dsfield(ipv6_hdr(skb)), 0, sk->sk_priority,
+ ipv6_get_dsfield(ipv6_hdr(skb)), 0,
+ READ_ONCE(sk->sk_priority),
READ_ONCE(tcp_rsk(req)->txhash));
}
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index b7c972aa09a7..f787e6b8424c 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -51,6 +51,7 @@
#include <net/inet6_hashtables.h>
#include <net/busy_poll.h>
#include <net/sock_reuseport.h>
+#include <net/gro.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
@@ -300,10 +301,13 @@ struct sock *udp6_lib_lookup_skb(const struct sk_buff *skb,
{
const struct ipv6hdr *iph = ipv6_hdr(skb);
struct net *net = dev_net(skb->dev);
+ int iif, sdif;
+
+ inet6_get_iif_sdif(skb, &iif, &sdif);
return __udp6_lib_lookup(net, &iph->saddr, sport,
- &iph->daddr, dport, inet6_iif(skb),
- inet6_sdif(skb), net->ipv4.udp_table, NULL);
+ &iph->daddr, dport, iif,
+ sdif, net->ipv4.udp_table, NULL);
}
/* Must be called under rcu_read_lock().
@@ -624,7 +628,7 @@ int __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
if (type == NDISC_REDIRECT) {
if (tunnel) {
ip6_redirect(skb, sock_net(sk), inet6_iif(skb),
- sk->sk_mark, sk->sk_uid);
+ READ_ONCE(sk->sk_mark), sk->sk_uid);
} else {
ip6_sk_redirect(skb, sk);
}
@@ -1356,7 +1360,7 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
ipcm6_init(&ipc6);
ipc6.gso_size = READ_ONCE(up->gso_size);
ipc6.sockc.tsflags = sk->sk_tsflags;
- ipc6.sockc.mark = sk->sk_mark;
+ ipc6.sockc.mark = READ_ONCE(sk->sk_mark);
/* destination address check */
if (sin6) {
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index 09fa7a42cb93..6b95ba241ebe 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -118,10 +118,13 @@ static struct sock *udp6_gro_lookup_skb(struct sk_buff *skb, __be16 sport,
{
const struct ipv6hdr *iph = skb_gro_network_header(skb);
struct net *net = dev_net(skb->dev);
+ int iif, sdif;
+
+ inet6_get_iif_sdif(skb, &iif, &sdif);
return __udp6_lib_lookup(net, &iph->saddr, sport,
- &iph->daddr, dport, inet6_iif(skb),
- inet6_sdif(skb), net->ipv4.udp_table, NULL);
+ &iph->daddr, dport, iif,
+ sdif, net->ipv4.udp_table, NULL);
}
INDIRECT_CALLABLE_SCOPE
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index b1623f9c4f92..ff78217f0cb1 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -519,7 +519,7 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
/* Get and verify the address */
memset(&fl6, 0, sizeof(fl6));
- fl6.flowi6_mark = sk->sk_mark;
+ fl6.flowi6_mark = READ_ONCE(sk->sk_mark);
fl6.flowi6_uid = sk->sk_uid;
ipcm6_init(&ipc6);
diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c
index 63f7a09335c5..a3f1fe810cc9 100644
--- a/net/mptcp/sockopt.c
+++ b/net/mptcp/sockopt.c
@@ -103,7 +103,7 @@ static void mptcp_sol_socket_sync_intval(struct mptcp_sock *msk, int optname, in
break;
case SO_MARK:
if (READ_ONCE(ssk->sk_mark) != sk->sk_mark) {
- ssk->sk_mark = sk->sk_mark;
+ WRITE_ONCE(ssk->sk_mark, sk->sk_mark);
sk_dst_reset(ssk);
}
break;
diff --git a/net/netfilter/nft_socket.c b/net/netfilter/nft_socket.c
index 84def74698b7..9ed85be79452 100644
--- a/net/netfilter/nft_socket.c
+++ b/net/netfilter/nft_socket.c
@@ -107,7 +107,7 @@ static void nft_socket_eval(const struct nft_expr *expr,
break;
case NFT_SOCKET_MARK:
if (sk_fullsock(sk)) {
- *dest = sk->sk_mark;
+ *dest = READ_ONCE(sk->sk_mark);
} else {
regs->verdict.code = NFT_BREAK;
return;
diff --git a/net/netfilter/xt_socket.c b/net/netfilter/xt_socket.c
index 7013f55f05d1..76e01f292aaf 100644
--- a/net/netfilter/xt_socket.c
+++ b/net/netfilter/xt_socket.c
@@ -77,7 +77,7 @@ socket_match(const struct sk_buff *skb, struct xt_action_param *par,
if (info->flags & XT_SOCKET_RESTORESKMARK && !wildcard &&
transparent && sk_fullsock(sk))
- pskb->mark = sk->sk_mark;
+ pskb->mark = READ_ONCE(sk->sk_mark);
if (sk != skb->sk)
sock_gen_put(sk);
@@ -138,7 +138,7 @@ socket_mt6_v1_v2_v3(const struct sk_buff *skb, struct xt_action_param *par)
if (info->flags & XT_SOCKET_RESTORESKMARK && !wildcard &&
transparent && sk_fullsock(sk))
- pskb->mark = sk->sk_mark;
+ pskb->mark = READ_ONCE(sk->sk_mark);
if (sk != skb->sk)
sock_gen_put(sk);
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 8e3ddec4c3d5..a4631cb457a9 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2050,8 +2050,8 @@ retry:
skb->protocol = proto;
skb->dev = dev;
- skb->priority = sk->sk_priority;
- skb->mark = sk->sk_mark;
+ skb->priority = READ_ONCE(sk->sk_priority);
+ skb->mark = READ_ONCE(sk->sk_mark);
skb->tstamp = sockc.transmit_time;
skb_setup_tx_timestamp(skb, sockc.tsflags);
@@ -2585,8 +2585,8 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb,
skb->protocol = proto;
skb->dev = dev;
- skb->priority = po->sk.sk_priority;
- skb->mark = po->sk.sk_mark;
+ skb->priority = READ_ONCE(po->sk.sk_priority);
+ skb->mark = READ_ONCE(po->sk.sk_mark);
skb->tstamp = sockc->transmit_time;
skb_setup_tx_timestamp(skb, sockc->tsflags);
skb_zcopy_set_nouarg(skb, ph.raw);
@@ -2988,7 +2988,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
goto out_unlock;
sockcm_init(&sockc, sk);
- sockc.mark = sk->sk_mark;
+ sockc.mark = READ_ONCE(sk->sk_mark);
if (msg->msg_controllen) {
err = sock_cmsg_send(sk, msg, &sockc);
if (unlikely(err))
@@ -3061,7 +3061,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
skb->protocol = proto;
skb->dev = dev;
- skb->priority = sk->sk_priority;
+ skb->priority = READ_ONCE(sk->sk_priority);
skb->mark = sockc.mark;
skb->tstamp = sockc.transmit_time;
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index 8da9d039d964..9f0711da9c95 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -776,7 +776,8 @@ mpls_stack_entry_policy[TCA_FLOWER_KEY_MPLS_OPT_LSE_MAX + 1] = {
[TCA_FLOWER_KEY_MPLS_OPT_LSE_LABEL] = { .type = NLA_U32 },
};
-static const struct nla_policy cfm_opt_policy[TCA_FLOWER_KEY_CFM_OPT_MAX] = {
+static const struct nla_policy
+cfm_opt_policy[TCA_FLOWER_KEY_CFM_OPT_MAX + 1] = {
[TCA_FLOWER_KEY_CFM_MD_LEVEL] = NLA_POLICY_MAX(NLA_U8,
FLOW_DIS_CFM_MDL_MAX),
[TCA_FLOWER_KEY_CFM_OPCODE] = { .type = NLA_U8 },
@@ -1709,7 +1710,7 @@ static int fl_set_key_cfm(struct nlattr **tb,
struct fl_flow_key *mask,
struct netlink_ext_ack *extack)
{
- struct nlattr *nla_cfm_opt[TCA_FLOWER_KEY_CFM_OPT_MAX];
+ struct nlattr *nla_cfm_opt[TCA_FLOWER_KEY_CFM_OPT_MAX + 1];
int err;
if (!tb[TCA_FLOWER_KEY_CFM])
diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c
index 8641f8059317..c49d6af0e048 100644
--- a/net/sched/cls_fw.c
+++ b/net/sched/cls_fw.c
@@ -267,7 +267,6 @@ static int fw_change(struct net *net, struct sk_buff *in_skb,
return -ENOBUFS;
fnew->id = f->id;
- fnew->res = f->res;
fnew->ifindex = f->ifindex;
fnew->tp = f->tp;
diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c
index d0c53724d3e8..1e20bbd687f1 100644
--- a/net/sched/cls_route.c
+++ b/net/sched/cls_route.c
@@ -513,7 +513,6 @@ static int route4_change(struct net *net, struct sk_buff *in_skb,
if (fold) {
f->id = fold->id;
f->iif = fold->iif;
- f->res = fold->res;
f->handle = fold->handle;
f->tp = fold->tp;
diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index 5abf31e432ca..da4c179a4d41 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -826,7 +826,6 @@ static struct tc_u_knode *u32_init_knode(struct net *net, struct tcf_proto *tp,
new->ifindex = n->ifindex;
new->fshift = n->fshift;
- new->res = n->res;
new->flags = n->flags;
RCU_INIT_POINTER(new->ht_down, ht);
@@ -1024,18 +1023,62 @@ static int u32_change(struct net *net, struct sk_buff *in_skb,
return -EINVAL;
}
+ /* At this point, we need to derive the new handle that will be used to
+ * uniquely map the identity of this table match entry. The
+ * identity of the entry that we need to construct is 32 bits made of:
+ * htid(12b):bucketid(8b):node/entryid(12b)
+ *
+ * At this point _we have the table(ht)_ in which we will insert this
+ * entry. We carry the table's id in variable "htid".
+ * Note that earlier code picked the ht selection either by a) the user
+ * providing the htid specified via TCA_U32_HASH attribute or b) when
+ * no such attribute is passed then the root ht, is default to at ID
+ * 0x[800][00][000]. Rule: the root table has a single bucket with ID 0.
+ * If OTOH the user passed us the htid, they may also pass a bucketid of
+ * choice. 0 is fine. For example a user htid is 0x[600][01][000] it is
+ * indicating hash bucketid of 1. Rule: the entry/node ID _cannot_ be
+ * passed via the htid, so even if it was non-zero it will be ignored.
+ *
+ * We may also have a handle, if the user passed one. The handle also
+ * carries the same addressing of htid(12b):bucketid(8b):node/entryid(12b).
+ * Rule: the bucketid on the handle is ignored even if one was passed;
+ * rather the value on "htid" is always assumed to be the bucketid.
+ */
if (handle) {
+ /* Rule: The htid from handle and tableid from htid must match */
if (TC_U32_HTID(handle) && TC_U32_HTID(handle ^ htid)) {
NL_SET_ERR_MSG_MOD(extack, "Handle specified hash table address mismatch");
return -EINVAL;
}
- handle = htid | TC_U32_NODE(handle);
- err = idr_alloc_u32(&ht->handle_idr, NULL, &handle, handle,
- GFP_KERNEL);
- if (err)
- return err;
- } else
+ /* Ok, so far we have a valid htid(12b):bucketid(8b) but we
+ * need to finalize the table entry identification with the last
+ * part - the node/entryid(12b)). Rule: Nodeid _cannot be 0_ for
+ * entries. Rule: nodeid of 0 is reserved only for tables(see
+ * earlier code which processes TC_U32_DIVISOR attribute).
+ * Rule: The nodeid can only be derived from the handle (and not
+ * htid).
+ * Rule: if the handle specified zero for the node id example
+ * 0x60000000, then pick a new nodeid from the pool of IDs
+ * this hash table has been allocating from.
+ * If OTOH it is specified (i.e for example the user passed a
+ * handle such as 0x60000123), then we use it generate our final
+ * handle which is used to uniquely identify the match entry.
+ */
+ if (!TC_U32_NODE(handle)) {
+ handle = gen_new_kid(ht, htid);
+ } else {
+ handle = htid | TC_U32_NODE(handle);
+ err = idr_alloc_u32(&ht->handle_idr, NULL, &handle,
+ handle, GFP_KERNEL);
+ if (err)
+ return err;
+ }
+ } else {
+ /* The user did not give us a handle; lets just generate one
+ * from the table's pool of nodeids.
+ */
handle = gen_new_kid(ht, htid);
+ }
if (tb[TCA_U32_SEL] == NULL) {
NL_SET_ERR_MSG_MOD(extack, "Selector not specified");
diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c
index af85a73c4c54..6fdba069f6bf 100644
--- a/net/sched/em_meta.c
+++ b/net/sched/em_meta.c
@@ -568,7 +568,7 @@ META_COLLECTOR(int_sk_rcvtimeo)
*err = -1;
return;
}
- dst->value = sk->sk_rcvtimeo / HZ;
+ dst->value = READ_ONCE(sk->sk_rcvtimeo) / HZ;
}
META_COLLECTOR(int_sk_sndtimeo)
@@ -579,7 +579,7 @@ META_COLLECTOR(int_sk_sndtimeo)
*err = -1;
return;
}
- dst->value = sk->sk_sndtimeo / HZ;
+ dst->value = READ_ONCE(sk->sk_sndtimeo) / HZ;
}
META_COLLECTOR(int_sk_sendmsg_off)
diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index 717ae51d94a0..8c9cfff7fd05 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -1015,6 +1015,11 @@ static const struct nla_policy taprio_tc_policy[TCA_TAPRIO_TC_ENTRY_MAX + 1] = {
TC_FP_PREEMPTIBLE),
};
+static struct netlink_range_validation_signed taprio_cycle_time_range = {
+ .min = 0,
+ .max = INT_MAX,
+};
+
static const struct nla_policy taprio_policy[TCA_TAPRIO_ATTR_MAX + 1] = {
[TCA_TAPRIO_ATTR_PRIOMAP] = {
.len = sizeof(struct tc_mqprio_qopt)
@@ -1023,7 +1028,8 @@ static const struct nla_policy taprio_policy[TCA_TAPRIO_ATTR_MAX + 1] = {
[TCA_TAPRIO_ATTR_SCHED_BASE_TIME] = { .type = NLA_S64 },
[TCA_TAPRIO_ATTR_SCHED_SINGLE_ENTRY] = { .type = NLA_NESTED },
[TCA_TAPRIO_ATTR_SCHED_CLOCKID] = { .type = NLA_S32 },
- [TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME] = { .type = NLA_S64 },
+ [TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME] =
+ NLA_POLICY_FULL_RANGE_SIGNED(NLA_S64, &taprio_cycle_time_range),
[TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME_EXTENSION] = { .type = NLA_S64 },
[TCA_TAPRIO_ATTR_FLAGS] = { .type = NLA_U32 },
[TCA_TAPRIO_ATTR_TXTIME_DELAY] = { .type = NLA_U32 },
@@ -1159,6 +1165,11 @@ static int parse_taprio_schedule(struct taprio_sched *q, struct nlattr **tb,
return -EINVAL;
}
+ if (cycle < 0 || cycle > INT_MAX) {
+ NL_SET_ERR_MSG(extack, "'cycle_time' is too big");
+ return -EINVAL;
+ }
+
new->cycle_time = cycle;
}
@@ -1347,7 +1358,7 @@ static void setup_txtime(struct taprio_sched *q,
struct sched_gate_list *sched, ktime_t base)
{
struct sched_entry *entry;
- u32 interval = 0;
+ u64 interval = 0;
list_for_each_entry(entry, &sched->entries, list) {
entry->next_txtime = ktime_add_ns(base, interval);
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index a7f887d91d89..0c013d2b5d8f 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -445,7 +445,7 @@ static void smc_copy_sock_settings(struct sock *nsk, struct sock *osk,
nsk->sk_rcvbuf = osk->sk_rcvbuf;
nsk->sk_sndtimeo = osk->sk_sndtimeo;
nsk->sk_rcvtimeo = osk->sk_rcvtimeo;
- nsk->sk_mark = osk->sk_mark;
+ nsk->sk_mark = READ_ONCE(osk->sk_mark);
nsk->sk_priority = osk->sk_priority;
nsk->sk_rcvlowat = osk->sk_rcvlowat;
nsk->sk_bound_dev_if = osk->sk_bound_dev_if;
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 78585217f61a..86930a8ed012 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -790,7 +790,7 @@ static int unix_set_peek_off(struct sock *sk, int val)
if (mutex_lock_interruptible(&u->iolock))
return -EINTR;
- sk->sk_peek_off = val;
+ WRITE_ONCE(sk->sk_peek_off, val);
mutex_unlock(&u->iolock);
return 0;
diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index 8bf00caf5d29..0cf1ce7b6934 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -657,7 +657,7 @@ static int cfg80211_parse_colocated_ap(const struct cfg80211_bss_ies *ies,
ret = cfg80211_calc_short_ssid(ies, &ssid_elem, &s_ssid_tmp);
if (ret)
- return ret;
+ return 0;
for_each_element_id(elem, WLAN_EID_REDUCED_NEIGHBOR_REPORT,
ies->data, ies->len) {
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index 31dca4ecb2c5..b89adb52a977 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -505,7 +505,7 @@ static struct sk_buff *xsk_build_skb(struct xdp_sock *xs,
skb->dev = dev;
skb->priority = xs->sk.sk_priority;
- skb->mark = xs->sk.sk_mark;
+ skb->mark = READ_ONCE(xs->sk.sk_mark);
skb_shinfo(skb)->destructor_arg = (void *)(long)desc->addr;
skb->destructor = xsk_destruct_skb;
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index e7617c9959c3..d6b405782b63 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -2250,7 +2250,7 @@ static struct xfrm_policy *xfrm_sk_policy_lookup(const struct sock *sk, int dir,
match = xfrm_selector_match(&pol->selector, fl, family);
if (match) {
- if ((sk->sk_mark & pol->mark.m) != pol->mark.v ||
+ if ((READ_ONCE(sk->sk_mark) & pol->mark.m) != pol->mark.v ||
pol->if_id != if_id) {
pol = NULL;
goto out;