aboutsummaryrefslogtreecommitdiffstats
path: root/net/core
diff options
context:
space:
mode:
Diffstat (limited to 'net/core')
-rw-r--r--net/core/datagram.c15
-rw-r--r--net/core/dev.c38
-rw-r--r--net/core/drop_monitor.c4
-rw-r--r--net/core/dst.c8
-rw-r--r--net/core/ethtool.c3
-rw-r--r--net/core/filter.c14
-rw-r--r--net/core/neighbour.c34
-rw-r--r--net/core/net_namespace.c2
-rw-r--r--net/core/netpoll.c19
-rw-r--r--net/core/pktgen.c14
-rw-r--r--net/core/rtnetlink.c15
-rw-r--r--net/core/skbuff.c42
-rw-r--r--net/core/sock.c38
-rw-r--r--net/core/stream.c9
14 files changed, 146 insertions, 109 deletions
diff --git a/net/core/datagram.c b/net/core/datagram.c
index 865a8cb7b0bd..6ba82eb14b46 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -837,18 +837,21 @@ __poll_t datagram_poll(struct file *file, struct socket *sock,
{
struct sock *sk = sock->sk;
__poll_t mask;
+ u8 shutdown;
sock_poll_wait(file, sock, wait);
mask = 0;
/* exceptional events? */
- if (sk->sk_err || !skb_queue_empty_lockless(&sk->sk_error_queue))
+ if (READ_ONCE(sk->sk_err) ||
+ !skb_queue_empty_lockless(&sk->sk_error_queue))
mask |= EPOLLERR |
(sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? EPOLLPRI : 0);
- if (sk->sk_shutdown & RCV_SHUTDOWN)
+ shutdown = READ_ONCE(sk->sk_shutdown);
+ if (shutdown & RCV_SHUTDOWN)
mask |= EPOLLRDHUP | EPOLLIN | EPOLLRDNORM;
- if (sk->sk_shutdown == SHUTDOWN_MASK)
+ if (shutdown == SHUTDOWN_MASK)
mask |= EPOLLHUP;
/* readable? */
@@ -857,10 +860,12 @@ __poll_t datagram_poll(struct file *file, struct socket *sock,
/* Connection-based need to check for termination and startup */
if (connection_based(sk)) {
- if (sk->sk_state == TCP_CLOSE)
+ int state = READ_ONCE(sk->sk_state);
+
+ if (state == TCP_CLOSE)
mask |= EPOLLHUP;
/* connection hasn't started yet? */
- if (sk->sk_state == TCP_SYN_SENT)
+ if (state == TCP_SYN_SENT)
return mask;
}
diff --git a/net/core/dev.c b/net/core/dev.c
index 880b096eef8a..b5c9648c2192 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2303,6 +2303,8 @@ int __netif_set_xps_queue(struct net_device *dev, const unsigned long *mask,
bool active = false;
unsigned int nr_ids;
+ WARN_ON_ONCE(index >= dev->num_tx_queues);
+
if (dev->num_tc) {
/* Do not allow XPS on subordinate device directly */
num_tc = dev->num_tc;
@@ -2794,8 +2796,10 @@ void __dev_kfree_skb_any(struct sk_buff *skb, enum skb_free_reason reason)
{
if (in_irq() || irqs_disabled())
__dev_kfree_skb_irq(skb, reason);
+ else if (unlikely(reason == SKB_REASON_DROPPED))
+ kfree_skb(skb);
else
- dev_kfree_skb(skb);
+ consume_skb(skb);
}
EXPORT_SYMBOL(__dev_kfree_skb_any);
@@ -3196,6 +3200,14 @@ static netdev_features_t gso_features_check(const struct sk_buff *skb,
if (gso_segs > dev->gso_max_segs)
return features & ~NETIF_F_GSO_MASK;
+ if (unlikely(skb->len >= READ_ONCE(dev->gso_max_size)))
+ return features & ~NETIF_F_GSO_MASK;
+
+ if (!skb_shinfo(skb)->gso_type) {
+ skb_warn_bad_offload(skb);
+ return features & ~NETIF_F_GSO_MASK;
+ }
+
/* Support for GSO partial features requires software
* intervention before we can actually process the packets
* so we need to strip support for any partial features now
@@ -4060,8 +4072,10 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb,
u32 next_cpu;
u32 ident;
- /* First check into global flow table if there is a match */
- ident = sock_flow_table->ents[hash & sock_flow_table->mask];
+ /* First check into global flow table if there is a match.
+ * This READ_ONCE() pairs with WRITE_ONCE() from rps_record_sock_flow().
+ */
+ ident = READ_ONCE(sock_flow_table->ents[hash & sock_flow_table->mask]);
if ((ident ^ hash) & ~rps_cpu_mask)
goto try_rps;
@@ -9004,9 +9018,7 @@ void netdev_run_todo(void)
BUG_ON(!list_empty(&dev->ptype_specific));
WARN_ON(rcu_access_pointer(dev->ip_ptr));
WARN_ON(rcu_access_pointer(dev->ip6_ptr));
-#if IS_ENABLED(CONFIG_DECNET)
- WARN_ON(dev->dn_ptr);
-#endif
+
if (dev->priv_destructor)
dev->priv_destructor(dev);
if (dev->needs_free_netdev)
@@ -9031,24 +9043,16 @@ void netdev_run_todo(void)
void netdev_stats_to_stats64(struct rtnl_link_stats64 *stats64,
const struct net_device_stats *netdev_stats)
{
-#if BITS_PER_LONG == 64
- BUILD_BUG_ON(sizeof(*stats64) < sizeof(*netdev_stats));
- memcpy(stats64, netdev_stats, sizeof(*netdev_stats));
- /* zero out counters that only exist in rtnl_link_stats64 */
- memset((char *)stats64 + sizeof(*netdev_stats), 0,
- sizeof(*stats64) - sizeof(*netdev_stats));
-#else
- size_t i, n = sizeof(*netdev_stats) / sizeof(unsigned long);
- const unsigned long *src = (const unsigned long *)netdev_stats;
+ size_t i, n = sizeof(*netdev_stats) / sizeof(atomic_long_t);
+ const atomic_long_t *src = (atomic_long_t *)netdev_stats;
u64 *dst = (u64 *)stats64;
BUILD_BUG_ON(n > sizeof(*stats64) / sizeof(u64));
for (i = 0; i < n; i++)
- dst[i] = src[i];
+ dst[i] = (unsigned long)atomic_long_read(&src[i]);
/* zero out counters that only exist in rtnl_link_stats64 */
memset((char *)stats64 + n * sizeof(u64), 0,
sizeof(*stats64) - n * sizeof(u64));
-#endif
}
EXPORT_SYMBOL(netdev_stats_to_stats64);
diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c
index 2ed600012640..52e559252a9e 100644
--- a/net/core/drop_monitor.c
+++ b/net/core/drop_monitor.c
@@ -122,7 +122,7 @@ out:
}
static const struct genl_multicast_group dropmon_mcgrps[] = {
- { .name = "events", },
+ { .name = "events", .cap_sys_admin = 1 },
};
static void send_dm_alert(struct work_struct *work)
@@ -370,10 +370,12 @@ static const struct genl_ops dropmon_ops[] = {
{
.cmd = NET_DM_CMD_START,
.doit = net_dm_cmd_trace,
+ .flags = GENL_ADMIN_PERM,
},
{
.cmd = NET_DM_CMD_STOP,
.doit = net_dm_cmd_trace,
+ .flags = GENL_ADMIN_PERM,
},
};
diff --git a/net/core/dst.c b/net/core/dst.c
index 81ccf20e2826..1b1677683b97 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -97,10 +97,10 @@ void *dst_alloc(struct dst_ops *ops, struct net_device *dev,
{
struct dst_entry *dst;
- if (ops->gc && dst_entries_get_fast(ops) > ops->gc_thresh) {
- if (ops->gc(ops))
- return NULL;
- }
+ if (ops->gc &&
+ !(flags & DST_NOCOUNT) &&
+ dst_entries_get_fast(ops) > ops->gc_thresh)
+ ops->gc(ops);
dst = kmem_cache_alloc(ops->kmem_cachep, GFP_ATOMIC);
if (!dst)
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index 4db9512feba8..d007f1cca64c 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -2023,7 +2023,8 @@ static int ethtool_get_phy_stats(struct net_device *dev, void __user *useraddr)
return n_stats;
if (n_stats > S32_MAX / sizeof(u64))
return -ENOMEM;
- WARN_ON_ONCE(!n_stats);
+ if (WARN_ON_ONCE(!n_stats))
+ return -EOPNOTSUPP;
if (copy_from_user(&stats, useraddr, sizeof(stats)))
return -EFAULT;
diff --git a/net/core/filter.c b/net/core/filter.c
index 5129e89f52bb..dea7132f3813 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2025,6 +2025,10 @@ static int __bpf_redirect_no_mac(struct sk_buff *skb, struct net_device *dev,
if (mlen) {
__skb_pull(skb, mlen);
+ if (unlikely(!skb->len)) {
+ kfree_skb(skb);
+ return -ERANGE;
+ }
/* At ingress, the mac header has already been pulled once.
* At egress, skb_pospull_rcsum has to be done in case that
@@ -2561,15 +2565,18 @@ static int bpf_skb_generic_push(struct sk_buff *skb, u32 off, u32 len)
static int bpf_skb_generic_pop(struct sk_buff *skb, u32 off, u32 len)
{
+ void *old_data;
+
/* skb_ensure_writable() is not needed here, as we're
* already working on an uncloned skb.
*/
if (unlikely(!pskb_may_pull(skb, off + len)))
return -ENOMEM;
- skb_postpull_rcsum(skb, skb->data + off, len);
- memmove(skb->data + len, skb->data, off);
+ old_data = skb->data;
__skb_pull(skb, len);
+ skb_postpull_rcsum(skb, old_data + off, len);
+ memmove(skb->data, old_data, off);
return 0;
}
@@ -4228,7 +4235,6 @@ 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 0;
}
@@ -4326,6 +4332,7 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
params->ipv4_dst = nh->nh_gw;
params->rt_metric = res.fi->fib_priority;
+ params->ifindex = dev->ifindex;
/* xdp and cls_bpf programs are run in RCU-bh so
* rcu_read_lock_bh is not needed here
@@ -4440,6 +4447,7 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
dev = f6i->fib6_nh.nh_dev;
params->rt_metric = f6i->fib6_metric;
+ params->ifindex = dev->ifindex;
/* xdp and cls_bpf programs are run in RCU-bh so rcu_read_lock_bh is
* not needed here. Can not use __ipv6_neigh_lookup_noref here
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 2b96e9a7fc59..5b6f3175d55b 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -476,37 +476,6 @@ struct neighbour *neigh_lookup(struct neigh_table *tbl, const void *pkey,
}
EXPORT_SYMBOL(neigh_lookup);
-struct neighbour *neigh_lookup_nodev(struct neigh_table *tbl, struct net *net,
- const void *pkey)
-{
- struct neighbour *n;
- unsigned int key_len = tbl->key_len;
- u32 hash_val;
- struct neigh_hash_table *nht;
-
- NEIGH_CACHE_STAT_INC(tbl, lookups);
-
- rcu_read_lock_bh();
- nht = rcu_dereference_bh(tbl->nht);
- hash_val = tbl->hash(pkey, NULL, nht->hash_rnd) >> (32 - nht->hash_shift);
-
- for (n = rcu_dereference_bh(nht->hash_buckets[hash_val]);
- n != NULL;
- n = rcu_dereference_bh(n->next)) {
- if (!memcmp(n->primary_key, pkey, key_len) &&
- net_eq(dev_net(n->dev), net)) {
- if (!refcount_inc_not_zero(&n->refcnt))
- n = NULL;
- NEIGH_CACHE_STAT_INC(tbl, hits);
- break;
- }
- }
-
- rcu_read_unlock_bh();
- return n;
-}
-EXPORT_SYMBOL(neigh_lookup_nodev);
-
struct neighbour *__neigh_create(struct neigh_table *tbl, const void *pkey,
struct net_device *dev, bool want_ref)
{
@@ -1661,9 +1630,6 @@ static struct neigh_table *neigh_find_table(int family)
case AF_INET6:
tbl = neigh_tables[NEIGH_ND_TABLE];
break;
- case AF_DECnet:
- tbl = neigh_tables[NEIGH_DN_TABLE];
- break;
}
return tbl;
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 56c240c98a56..a87774424829 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -132,12 +132,12 @@ static int ops_init(const struct pernet_operations *ops, struct net *net)
return 0;
if (ops->id && ops->size) {
-cleanup:
ng = rcu_dereference_protected(net->gen,
lockdep_is_held(&pernet_ops_rwsem));
ng->ptr[*ops->id] = NULL;
}
+cleanup:
kfree(data);
out:
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index 41e32a958d08..08f0da9e6a80 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -136,6 +136,20 @@ static void queue_process(struct work_struct *work)
}
}
+static int netif_local_xmit_active(struct net_device *dev)
+{
+ int i;
+
+ for (i = 0; i < dev->num_tx_queues; i++) {
+ struct netdev_queue *txq = netdev_get_tx_queue(dev, i);
+
+ if (READ_ONCE(txq->xmit_lock_owner) == smp_processor_id())
+ return 1;
+ }
+
+ return 0;
+}
+
static void poll_one_napi(struct napi_struct *napi)
{
int work;
@@ -182,7 +196,10 @@ void netpoll_poll_dev(struct net_device *dev)
if (!ni || down_trylock(&ni->dev_lock))
return;
- if (!netif_running(dev)) {
+ /* Some drivers will take the same locks in poll and xmit,
+ * we can't poll if local CPU is already in xmit.
+ */
+ if (!netif_running(dev) || netif_local_xmit_active(dev)) {
up(&ni->dev_lock);
return;
}
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 3714cd9e3111..3ade60ec4512 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -651,19 +651,19 @@ static int pktgen_if_show(struct seq_file *seq, void *v)
seq_puts(seq, " Flags: ");
for (i = 0; i < NR_PKT_FLAGS; i++) {
- if (i == F_FLOW_SEQ)
+ if (i == FLOW_SEQ_SHIFT)
if (!pkt_dev->cflows)
continue;
- if (pkt_dev->flags & (1 << i))
+ if (pkt_dev->flags & (1 << i)) {
seq_printf(seq, "%s ", pkt_flag_names[i]);
- else if (i == F_FLOW_SEQ)
- seq_puts(seq, "FLOW_RND ");
-
#ifdef CONFIG_XFRM
- if (i == F_IPSEC && pkt_dev->spi)
- seq_printf(seq, "spi:%u", pkt_dev->spi);
+ if (i == IPSEC_SHIFT && pkt_dev->spi)
+ seq_printf(seq, "spi:%u ", pkt_dev->spi);
#endif
+ } else if (i == FLOW_SEQ_SHIFT) {
+ seq_puts(seq, "FLOW_RND ");
+ }
}
seq_puts(seq, "\n");
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 2837cc03f69e..0d3f724da78b 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -2970,9 +2970,12 @@ replay:
ifname[0] = '\0';
ifm = nlmsg_data(nlh);
- if (ifm->ifi_index > 0)
+ if (ifm->ifi_index > 0) {
dev = __dev_get_by_index(net, ifm->ifi_index);
- else {
+ } else if (ifm->ifi_index < 0) {
+ NL_SET_ERR_MSG(extack, "ifindex can't be negative");
+ return -EINVAL;
+ } else {
if (ifname[0])
dev = __dev_get_by_name(net, ifname);
else
@@ -3436,7 +3439,7 @@ static int nlmsg_populate_fdb_fill(struct sk_buff *skb,
ndm->ndm_ifindex = dev->ifindex;
ndm->ndm_state = ndm_state;
- if (nla_put(skb, NDA_LLADDR, ETH_ALEN, addr))
+ if (nla_put(skb, NDA_LLADDR, dev->addr_len, addr))
goto nla_put_failure;
if (vid)
if (nla_put(skb, NDA_VLAN, sizeof(u16), &vid))
@@ -3450,10 +3453,10 @@ nla_put_failure:
return -EMSGSIZE;
}
-static inline size_t rtnl_fdb_nlmsg_size(void)
+static inline size_t rtnl_fdb_nlmsg_size(const struct net_device *dev)
{
return NLMSG_ALIGN(sizeof(struct ndmsg)) +
- nla_total_size(ETH_ALEN) + /* NDA_LLADDR */
+ nla_total_size(dev->addr_len) + /* NDA_LLADDR */
nla_total_size(sizeof(u16)) + /* NDA_VLAN */
0;
}
@@ -3465,7 +3468,7 @@ static void rtnl_fdb_notify(struct net_device *dev, u8 *addr, u16 vid, int type,
struct sk_buff *skb;
int err = -ENOBUFS;
- skb = nlmsg_new(rtnl_fdb_nlmsg_size(), GFP_ATOMIC);
+ skb = nlmsg_new(rtnl_fdb_nlmsg_size(dev), GFP_ATOMIC);
if (!skb)
goto errout;
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 4178fc28c277..e03cd719b86b 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -1953,6 +1953,9 @@ void *__pskb_pull_tail(struct sk_buff *skb, int delta)
insp = list;
} else {
/* Eaten partially. */
+ if (skb_is_gso(skb) && !list->head_frag &&
+ skb_headlen(list))
+ skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY;
if (skb_shared(list)) {
/* Sucks! We need to fork list. :-( */
@@ -3543,21 +3546,20 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb,
struct sk_buff *segs = NULL;
struct sk_buff *tail = NULL;
struct sk_buff *list_skb = skb_shinfo(head_skb)->frag_list;
- skb_frag_t *frag = skb_shinfo(head_skb)->frags;
unsigned int mss = skb_shinfo(head_skb)->gso_size;
unsigned int doffset = head_skb->data - skb_mac_header(head_skb);
- struct sk_buff *frag_skb = head_skb;
unsigned int offset = doffset;
unsigned int tnl_hlen = skb_tnl_header_len(head_skb);
unsigned int partial_segs = 0;
unsigned int headroom;
unsigned int len = head_skb->len;
+ struct sk_buff *frag_skb;
+ skb_frag_t *frag;
__be16 proto;
bool csum, sg;
- int nfrags = skb_shinfo(head_skb)->nr_frags;
int err = -ENOMEM;
int i = 0;
- int pos;
+ int nfrags, pos;
int dummy;
if ((skb_shinfo(head_skb)->gso_type & SKB_GSO_DODGY) &&
@@ -3635,6 +3637,13 @@ normal:
headroom = skb_headroom(head_skb);
pos = skb_headlen(head_skb);
+ if (skb_orphan_frags(head_skb, GFP_ATOMIC))
+ return ERR_PTR(-ENOMEM);
+
+ nfrags = skb_shinfo(head_skb)->nr_frags;
+ frag = skb_shinfo(head_skb)->frags;
+ frag_skb = head_skb;
+
do {
struct sk_buff *nskb;
skb_frag_t *nskb_frag;
@@ -3659,6 +3668,10 @@ normal:
(skb_headlen(list_skb) == len || sg)) {
BUG_ON(skb_headlen(list_skb) > len);
+ nskb = skb_clone(list_skb, GFP_ATOMIC);
+ if (unlikely(!nskb))
+ goto err;
+
i = 0;
nfrags = skb_shinfo(list_skb)->nr_frags;
frag = skb_shinfo(list_skb)->frags;
@@ -3677,12 +3690,8 @@ normal:
frag++;
}
- nskb = skb_clone(list_skb, GFP_ATOMIC);
list_skb = list_skb->next;
- if (unlikely(!nskb))
- goto err;
-
if (unlikely(pskb_trim(nskb, len))) {
kfree_skb(nskb);
goto err;
@@ -3747,12 +3756,16 @@ normal:
skb_shinfo(nskb)->tx_flags |= skb_shinfo(head_skb)->tx_flags &
SKBTX_SHARED_FRAG;
- if (skb_orphan_frags(frag_skb, GFP_ATOMIC) ||
- skb_zerocopy_clone(nskb, frag_skb, GFP_ATOMIC))
+ if (skb_zerocopy_clone(nskb, frag_skb, GFP_ATOMIC))
goto err;
while (pos < offset + len) {
if (i >= nfrags) {
+ if (skb_orphan_frags(list_skb, GFP_ATOMIC) ||
+ skb_zerocopy_clone(nskb, list_skb,
+ GFP_ATOMIC))
+ goto err;
+
i = 0;
nfrags = skb_shinfo(list_skb)->nr_frags;
frag = skb_shinfo(list_skb)->frags;
@@ -3766,10 +3779,6 @@ normal:
i--;
frag--;
}
- if (skb_orphan_frags(frag_skb, GFP_ATOMIC) ||
- skb_zerocopy_clone(nskb, frag_skb,
- GFP_ATOMIC))
- goto err;
list_skb = list_skb->next;
}
@@ -4442,6 +4451,11 @@ void __skb_tstamp_tx(struct sk_buff *orig_skb,
skb = alloc_skb(0, GFP_ATOMIC);
} else {
skb = skb_clone(orig_skb, GFP_ATOMIC);
+
+ if (skb_orphan_frags_rx(skb, GFP_ATOMIC)) {
+ kfree_skb(skb);
+ return;
+ }
}
if (!skb)
return;
diff --git a/net/core/sock.c b/net/core/sock.c
index cd23a8e4556c..62d169bcfcfa 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -496,7 +496,7 @@ struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie)
if (dst && dst->obsolete && dst->ops->check(dst, cookie) == NULL) {
sk_tx_queue_clear(sk);
- sk->sk_dst_pending_confirm = 0;
+ WRITE_ONCE(sk->sk_dst_pending_confirm, 0);
RCU_INIT_POINTER(sk->sk_dst_cache, NULL);
dst_release(dst);
return NULL;
@@ -632,7 +632,8 @@ bool sk_mc_loop(struct sock *sk)
return false;
if (!sk)
return true;
- switch (sk->sk_family) {
+ /* IPV6_ADDRFORM can change sk->sk_family under us. */
+ switch (READ_ONCE(sk->sk_family)) {
case AF_INET:
return inet_sk(sk)->mc_loop;
#if IS_ENABLED(CONFIG_IPV6)
@@ -1319,7 +1320,7 @@ int sock_getsockopt(struct socket *sock, 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);
@@ -1349,7 +1350,7 @@ int sock_getsockopt(struct socket *sock, 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;
#endif
@@ -1795,7 +1796,6 @@ void sk_setup_caps(struct sock *sk, struct dst_entry *dst)
{
u32 max_segs = 1;
- sk_dst_set(sk, dst);
sk->sk_route_caps = dst->dev->features | sk->sk_route_forced_caps;
if (sk->sk_route_caps & NETIF_F_GSO)
sk->sk_route_caps |= NETIF_F_GSO_SOFTWARE;
@@ -1810,6 +1810,7 @@ void sk_setup_caps(struct sock *sk, struct dst_entry *dst)
}
}
sk->sk_gso_max_segs = max_segs;
+ sk_dst_set(sk, dst);
}
EXPORT_SYMBOL_GPL(sk_setup_caps);
@@ -1939,13 +1940,24 @@ kuid_t sock_i_uid(struct sock *sk)
}
EXPORT_SYMBOL(sock_i_uid);
-unsigned long sock_i_ino(struct sock *sk)
+unsigned long __sock_i_ino(struct sock *sk)
{
unsigned long ino;
- read_lock_bh(&sk->sk_callback_lock);
+ read_lock(&sk->sk_callback_lock);
ino = sk->sk_socket ? SOCK_INODE(sk->sk_socket)->i_ino : 0;
- read_unlock_bh(&sk->sk_callback_lock);
+ read_unlock(&sk->sk_callback_lock);
+ return ino;
+}
+EXPORT_SYMBOL(__sock_i_ino);
+
+unsigned long sock_i_ino(struct sock *sk)
+{
+ unsigned long ino;
+
+ local_bh_disable();
+ ino = __sock_i_ino(sk);
+ local_bh_enable();
return ino;
}
EXPORT_SYMBOL(sock_i_ino);
@@ -2060,9 +2072,9 @@ static long sock_wait_for_wmem(struct sock *sk, long timeo)
prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
if (refcount_read(&sk->sk_wmem_alloc) < sk->sk_sndbuf)
break;
- if (sk->sk_shutdown & SEND_SHUTDOWN)
+ if (READ_ONCE(sk->sk_shutdown) & SEND_SHUTDOWN)
break;
- if (sk->sk_err)
+ if (READ_ONCE(sk->sk_err))
break;
timeo = schedule_timeout(timeo);
}
@@ -2090,7 +2102,7 @@ struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len,
goto failure;
err = -EPIPE;
- if (sk->sk_shutdown & SEND_SHUTDOWN)
+ if (READ_ONCE(sk->sk_shutdown) & SEND_SHUTDOWN)
goto failure;
if (sk_wmem_alloc_get(sk) < sk->sk_sndbuf)
@@ -2527,7 +2539,7 @@ void __sk_mem_reduce_allocated(struct sock *sk, int amount)
if (mem_cgroup_sockets_enabled && sk->sk_memcg)
mem_cgroup_uncharge_skmem(sk->sk_memcg, amount);
- if (sk_under_memory_pressure(sk) &&
+ if (sk_under_global_memory_pressure(sk) &&
(sk_memory_allocated(sk) < sk_prot_mem_limits(sk, 0)))
sk_leave_memory_pressure(sk);
}
@@ -2548,7 +2560,7 @@ 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/stream.c b/net/core/stream.c
index 7b411a91a81c..cd60746877b1 100644
--- a/net/core/stream.c
+++ b/net/core/stream.c
@@ -32,7 +32,7 @@ void sk_stream_write_space(struct sock *sk)
struct socket *sock = sk->sk_socket;
struct socket_wq *wq;
- if (sk_stream_is_writeable(sk) && sock) {
+ if (__sk_stream_is_writeable(sk, 1) && sock) {
clear_bit(SOCK_NOSPACE, &sock->flags);
rcu_read_lock();
@@ -196,6 +196,12 @@ void sk_stream_kill_queues(struct sock *sk)
/* First the read buffer. */
__skb_queue_purge(&sk->sk_receive_queue);
+ /* Next, the error queue.
+ * We need to use queue lock, because other threads might
+ * add packets to the queue without socket lock being held.
+ */
+ skb_queue_purge(&sk->sk_error_queue);
+
/* Next, the write queue. */
WARN_ON(!skb_queue_empty(&sk->sk_write_queue));
@@ -203,7 +209,6 @@ void sk_stream_kill_queues(struct sock *sk)
sk_mem_reclaim(sk);
WARN_ON(sk->sk_wmem_queued);
- WARN_ON(sk->sk_forward_alloc);
/* It is _impossible_ for the backlog to contain anything
* when we get here. All user references to this socket
generated by cgit 1.2.3-korg (git 2.39.0) at 2024-05-02 03:50:50 +0000