summaryrefslogtreecommitdiff
path: root/net/core
diff options
context:
space:
mode:
Diffstat (limited to 'net/core')
-rw-r--r--net/core/dev.c8
-rw-r--r--net/core/page_pool.c28
-rw-r--r--net/core/rtnetlink.c54
-rw-r--r--net/core/skbuff.c4
-rw-r--r--net/core/skmsg.c82
-rw-r--r--net/core/sock.c8
-rw-r--r--net/core/sock_map.c3
7 files changed, 114 insertions, 73 deletions
diff --git a/net/core/dev.c b/net/core/dev.c
index b3c13e041935..c29f3e1db3ca 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4471,8 +4471,10 @@ 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;
@@ -10541,7 +10543,7 @@ struct netdev_queue *dev_ingress_queue_create(struct net_device *dev)
return NULL;
netdev_init_one_queue(dev, queue, NULL);
RCU_INIT_POINTER(queue->qdisc, &noop_qdisc);
- queue->qdisc_sleeping = &noop_qdisc;
+ RCU_INIT_POINTER(queue->qdisc_sleeping, &noop_qdisc);
rcu_assign_pointer(dev->ingress_queue, queue);
#endif
return queue;
diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index e212e9d7edcb..a3e12a61d456 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -134,6 +134,29 @@ EXPORT_SYMBOL(page_pool_ethtool_stats_get);
#define recycle_stat_add(pool, __stat, val)
#endif
+static bool page_pool_producer_lock(struct page_pool *pool)
+ __acquires(&pool->ring.producer_lock)
+{
+ bool in_softirq = in_softirq();
+
+ if (in_softirq)
+ spin_lock(&pool->ring.producer_lock);
+ else
+ spin_lock_bh(&pool->ring.producer_lock);
+
+ return in_softirq;
+}
+
+static void page_pool_producer_unlock(struct page_pool *pool,
+ bool in_softirq)
+ __releases(&pool->ring.producer_lock)
+{
+ if (in_softirq)
+ spin_unlock(&pool->ring.producer_lock);
+ else
+ spin_unlock_bh(&pool->ring.producer_lock);
+}
+
static int page_pool_init(struct page_pool *pool,
const struct page_pool_params *params)
{
@@ -617,6 +640,7 @@ void page_pool_put_page_bulk(struct page_pool *pool, void **data,
int count)
{
int i, bulk_len = 0;
+ bool in_softirq;
for (i = 0; i < count; i++) {
struct page *page = virt_to_head_page(data[i]);
@@ -635,7 +659,7 @@ void page_pool_put_page_bulk(struct page_pool *pool, void **data,
return;
/* Bulk producer into ptr_ring page_pool cache */
- page_pool_ring_lock(pool);
+ in_softirq = page_pool_producer_lock(pool);
for (i = 0; i < bulk_len; i++) {
if (__ptr_ring_produce(&pool->ring, data[i])) {
/* ring full */
@@ -644,7 +668,7 @@ void page_pool_put_page_bulk(struct page_pool *pool, void **data,
}
}
recycle_stat_add(pool, ring, i);
- page_pool_ring_unlock(pool);
+ page_pool_producer_unlock(pool, in_softirq);
/* Hopefully all pages was return into ptr_ring */
if (likely(i == bulk_len))
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 653901a1bf75..41de3a2f29e1 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -2385,6 +2385,37 @@ static int validate_linkmsg(struct net_device *dev, struct nlattr *tb[],
if (tb[IFLA_BROADCAST] &&
nla_len(tb[IFLA_BROADCAST]) < dev->addr_len)
return -EINVAL;
+
+ if (tb[IFLA_GSO_MAX_SIZE] &&
+ nla_get_u32(tb[IFLA_GSO_MAX_SIZE]) > dev->tso_max_size) {
+ NL_SET_ERR_MSG(extack, "too big gso_max_size");
+ return -EINVAL;
+ }
+
+ if (tb[IFLA_GSO_MAX_SEGS] &&
+ (nla_get_u32(tb[IFLA_GSO_MAX_SEGS]) > GSO_MAX_SEGS ||
+ nla_get_u32(tb[IFLA_GSO_MAX_SEGS]) > dev->tso_max_segs)) {
+ NL_SET_ERR_MSG(extack, "too big gso_max_segs");
+ return -EINVAL;
+ }
+
+ if (tb[IFLA_GRO_MAX_SIZE] &&
+ nla_get_u32(tb[IFLA_GRO_MAX_SIZE]) > GRO_MAX_SIZE) {
+ NL_SET_ERR_MSG(extack, "too big gro_max_size");
+ return -EINVAL;
+ }
+
+ if (tb[IFLA_GSO_IPV4_MAX_SIZE] &&
+ nla_get_u32(tb[IFLA_GSO_IPV4_MAX_SIZE]) > dev->tso_max_size) {
+ NL_SET_ERR_MSG(extack, "too big gso_ipv4_max_size");
+ return -EINVAL;
+ }
+
+ if (tb[IFLA_GRO_IPV4_MAX_SIZE] &&
+ nla_get_u32(tb[IFLA_GRO_IPV4_MAX_SIZE]) > GRO_MAX_SIZE) {
+ NL_SET_ERR_MSG(extack, "too big gro_ipv4_max_size");
+ return -EINVAL;
+ }
}
if (tb[IFLA_AF_SPEC]) {
@@ -2858,11 +2889,6 @@ static int do_setlink(const struct sk_buff *skb,
if (tb[IFLA_GSO_MAX_SIZE]) {
u32 max_size = nla_get_u32(tb[IFLA_GSO_MAX_SIZE]);
- if (max_size > dev->tso_max_size) {
- err = -EINVAL;
- goto errout;
- }
-
if (dev->gso_max_size ^ max_size) {
netif_set_gso_max_size(dev, max_size);
status |= DO_SETLINK_MODIFIED;
@@ -2872,11 +2898,6 @@ static int do_setlink(const struct sk_buff *skb,
if (tb[IFLA_GSO_MAX_SEGS]) {
u32 max_segs = nla_get_u32(tb[IFLA_GSO_MAX_SEGS]);
- if (max_segs > GSO_MAX_SEGS || max_segs > dev->tso_max_segs) {
- err = -EINVAL;
- goto errout;
- }
-
if (dev->gso_max_segs ^ max_segs) {
netif_set_gso_max_segs(dev, max_segs);
status |= DO_SETLINK_MODIFIED;
@@ -2895,11 +2916,6 @@ static int do_setlink(const struct sk_buff *skb,
if (tb[IFLA_GSO_IPV4_MAX_SIZE]) {
u32 max_size = nla_get_u32(tb[IFLA_GSO_IPV4_MAX_SIZE]);
- if (max_size > dev->tso_max_size) {
- err = -EINVAL;
- goto errout;
- }
-
if (dev->gso_ipv4_max_size ^ max_size) {
netif_set_gso_ipv4_max_size(dev, max_size);
status |= DO_SETLINK_MODIFIED;
@@ -3285,6 +3301,7 @@ struct net_device *rtnl_create_link(struct net *net, const char *ifname,
struct net_device *dev;
unsigned int num_tx_queues = 1;
unsigned int num_rx_queues = 1;
+ int err;
if (tb[IFLA_NUM_TX_QUEUES])
num_tx_queues = nla_get_u32(tb[IFLA_NUM_TX_QUEUES]);
@@ -3320,13 +3337,18 @@ struct net_device *rtnl_create_link(struct net *net, const char *ifname,
if (!dev)
return ERR_PTR(-ENOMEM);
+ err = validate_linkmsg(dev, tb, extack);
+ if (err < 0) {
+ free_netdev(dev);
+ return ERR_PTR(err);
+ }
+
dev_net_set(dev, net);
dev->rtnl_link_ops = ops;
dev->rtnl_link_state = RTNL_LINK_INITIALIZING;
if (tb[IFLA_MTU]) {
u32 mtu = nla_get_u32(tb[IFLA_MTU]);
- int err;
err = dev_validate_mtu(dev, mtu, extack);
if (err) {
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 515ec5cdc79c..cea28d30abb5 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -5224,8 +5224,10 @@ void __skb_tstamp_tx(struct sk_buff *orig_skb,
} else {
skb = skb_clone(orig_skb, GFP_ATOMIC);
- if (skb_orphan_frags_rx(skb, GFP_ATOMIC))
+ if (skb_orphan_frags_rx(skb, GFP_ATOMIC)) {
+ kfree_skb(skb);
return;
+ }
}
if (!skb)
return;
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index f81883759d38..a29508e1ff35 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -481,8 +481,6 @@ int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg,
msg_rx = sk_psock_peek_msg(psock);
}
out:
- if (psock->work_state.skb && copied > 0)
- schedule_work(&psock->work);
return copied;
}
EXPORT_SYMBOL_GPL(sk_msg_recvmsg);
@@ -624,42 +622,33 @@ static int sk_psock_handle_skb(struct sk_psock *psock, struct sk_buff *skb,
static void sk_psock_skb_state(struct sk_psock *psock,
struct sk_psock_work_state *state,
- struct sk_buff *skb,
int len, int off)
{
spin_lock_bh(&psock->ingress_lock);
if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) {
- state->skb = skb;
state->len = len;
state->off = off;
- } else {
- sock_drop(psock->sk, skb);
}
spin_unlock_bh(&psock->ingress_lock);
}
static void sk_psock_backlog(struct work_struct *work)
{
- struct sk_psock *psock = container_of(work, struct sk_psock, work);
+ struct delayed_work *dwork = to_delayed_work(work);
+ struct sk_psock *psock = container_of(dwork, struct sk_psock, work);
struct sk_psock_work_state *state = &psock->work_state;
struct sk_buff *skb = NULL;
+ u32 len = 0, off = 0;
bool ingress;
- u32 len, off;
int ret;
mutex_lock(&psock->work_mutex);
- if (unlikely(state->skb)) {
- spin_lock_bh(&psock->ingress_lock);
- skb = state->skb;
+ if (unlikely(state->len)) {
len = state->len;
off = state->off;
- state->skb = NULL;
- spin_unlock_bh(&psock->ingress_lock);
}
- if (skb)
- goto start;
- while ((skb = skb_dequeue(&psock->ingress_skb))) {
+ while ((skb = skb_peek(&psock->ingress_skb))) {
len = skb->len;
off = 0;
if (skb_bpf_strparser(skb)) {
@@ -668,7 +657,6 @@ static void sk_psock_backlog(struct work_struct *work)
off = stm->offset;
len = stm->full_len;
}
-start:
ingress = skb_bpf_ingress(skb);
skb_bpf_redirect_clear(skb);
do {
@@ -678,22 +666,28 @@ start:
len, ingress);
if (ret <= 0) {
if (ret == -EAGAIN) {
- sk_psock_skb_state(psock, state, skb,
- len, off);
+ sk_psock_skb_state(psock, state, len, off);
+
+ /* Delay slightly to prioritize any
+ * other work that might be here.
+ */
+ if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED))
+ schedule_delayed_work(&psock->work, 1);
goto end;
}
/* Hard errors break pipe and stop xmit. */
sk_psock_report_error(psock, ret ? -ret : EPIPE);
sk_psock_clear_state(psock, SK_PSOCK_TX_ENABLED);
- sock_drop(psock->sk, skb);
goto end;
}
off += ret;
len -= ret;
} while (len);
- if (!ingress)
+ skb = skb_dequeue(&psock->ingress_skb);
+ if (!ingress) {
kfree_skb(skb);
+ }
}
end:
mutex_unlock(&psock->work_mutex);
@@ -734,7 +728,7 @@ struct sk_psock *sk_psock_init(struct sock *sk, int node)
INIT_LIST_HEAD(&psock->link);
spin_lock_init(&psock->link_lock);
- INIT_WORK(&psock->work, sk_psock_backlog);
+ INIT_DELAYED_WORK(&psock->work, sk_psock_backlog);
mutex_init(&psock->work_mutex);
INIT_LIST_HEAD(&psock->ingress_msg);
spin_lock_init(&psock->ingress_lock);
@@ -786,11 +780,6 @@ static void __sk_psock_zap_ingress(struct sk_psock *psock)
skb_bpf_redirect_clear(skb);
sock_drop(psock->sk, skb);
}
- kfree_skb(psock->work_state.skb);
- /* We null the skb here to ensure that calls to sk_psock_backlog
- * do not pick up the free'd skb.
- */
- psock->work_state.skb = NULL;
__sk_psock_purge_ingress_msg(psock);
}
@@ -809,7 +798,6 @@ void sk_psock_stop(struct sk_psock *psock)
spin_lock_bh(&psock->ingress_lock);
sk_psock_clear_state(psock, SK_PSOCK_TX_ENABLED);
sk_psock_cork_free(psock);
- __sk_psock_zap_ingress(psock);
spin_unlock_bh(&psock->ingress_lock);
}
@@ -823,7 +811,8 @@ static void sk_psock_destroy(struct work_struct *work)
sk_psock_done_strp(psock);
- cancel_work_sync(&psock->work);
+ cancel_delayed_work_sync(&psock->work);
+ __sk_psock_zap_ingress(psock);
mutex_destroy(&psock->work_mutex);
psock_progs_drop(&psock->progs);
@@ -938,7 +927,7 @@ static int sk_psock_skb_redirect(struct sk_psock *from, struct sk_buff *skb)
}
skb_queue_tail(&psock_other->ingress_skb, skb);
- schedule_work(&psock_other->work);
+ schedule_delayed_work(&psock_other->work, 0);
spin_unlock_bh(&psock_other->ingress_lock);
return 0;
}
@@ -990,10 +979,8 @@ static int sk_psock_verdict_apply(struct sk_psock *psock, struct sk_buff *skb,
err = -EIO;
sk_other = psock->sk;
if (sock_flag(sk_other, SOCK_DEAD) ||
- !sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) {
- skb_bpf_redirect_clear(skb);
+ !sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED))
goto out_free;
- }
skb_bpf_set_ingress(skb);
@@ -1018,22 +1005,23 @@ static int sk_psock_verdict_apply(struct sk_psock *psock, struct sk_buff *skb,
spin_lock_bh(&psock->ingress_lock);
if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) {
skb_queue_tail(&psock->ingress_skb, skb);
- schedule_work(&psock->work);
+ schedule_delayed_work(&psock->work, 0);
err = 0;
}
spin_unlock_bh(&psock->ingress_lock);
- if (err < 0) {
- skb_bpf_redirect_clear(skb);
+ if (err < 0)
goto out_free;
- }
}
break;
case __SK_REDIRECT:
+ tcp_eat_skb(psock->sk, skb);
err = sk_psock_skb_redirect(psock, skb);
break;
case __SK_DROP:
default:
out_free:
+ skb_bpf_redirect_clear(skb);
+ tcp_eat_skb(psock->sk, skb);
sock_drop(psock->sk, skb);
}
@@ -1049,7 +1037,7 @@ static void sk_psock_write_space(struct sock *sk)
psock = sk_psock(sk);
if (likely(psock)) {
if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED))
- schedule_work(&psock->work);
+ schedule_delayed_work(&psock->work, 0);
write_space = psock->saved_write_space;
}
rcu_read_unlock();
@@ -1078,8 +1066,7 @@ static void sk_psock_strp_read(struct strparser *strp, struct sk_buff *skb)
skb_dst_drop(skb);
skb_bpf_redirect_clear(skb);
ret = bpf_prog_run_pin_on_cpu(prog, skb);
- if (ret == SK_PASS)
- skb_bpf_set_strparser(skb);
+ skb_bpf_set_strparser(skb);
ret = sk_psock_map_verd(ret, skb_bpf_redirect_fetch(skb));
skb->sk = NULL;
}
@@ -1183,12 +1170,11 @@ static int sk_psock_verdict_recv(struct sock *sk, struct sk_buff *skb)
int ret = __SK_DROP;
int len = skb->len;
- skb_get(skb);
-
rcu_read_lock();
psock = sk_psock(sk);
if (unlikely(!psock)) {
len = 0;
+ tcp_eat_skb(sk, skb);
sock_drop(sk, skb);
goto out;
}
@@ -1212,12 +1198,22 @@ out:
static void sk_psock_verdict_data_ready(struct sock *sk)
{
struct socket *sock = sk->sk_socket;
+ int copied;
trace_sk_data_ready(sk);
if (unlikely(!sock || !sock->ops || !sock->ops->read_skb))
return;
- sock->ops->read_skb(sk, sk_psock_verdict_recv);
+ copied = sock->ops->read_skb(sk, sk_psock_verdict_recv);
+ if (copied >= 0) {
+ struct sk_psock *psock;
+
+ rcu_read_lock();
+ psock = sk_psock(sk);
+ if (psock)
+ psock->saved_data_ready(sk);
+ rcu_read_unlock();
+ }
}
void sk_psock_start_verdict(struct sock *sk, struct sk_psock *psock)
diff --git a/net/core/sock.c b/net/core/sock.c
index 5440e67bcfe3..6e5662ca00fe 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1362,12 +1362,6 @@ set_sndbuf:
__sock_set_mark(sk, val);
break;
case SO_RCVMARK:
- if (!sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) &&
- !sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) {
- ret = -EPERM;
- break;
- }
-
sock_valbool_flag(sk, SOCK_RCVMARK, valbool);
break;
@@ -2381,7 +2375,6 @@ 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;
if (sk_is_tcp(sk))
sk->sk_route_caps |= NETIF_F_GSO;
@@ -2400,6 +2393,7 @@ 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);
diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index 7c189c2e2fbf..00afb66cd095 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -1644,9 +1644,10 @@ void sock_map_close(struct sock *sk, long timeout)
rcu_read_unlock();
sk_psock_stop(psock);
release_sock(sk);
- cancel_work_sync(&psock->work);
+ cancel_delayed_work_sync(&psock->work);
sk_psock_put(sk, psock);
}
+
/* Make sure we do not recurse. This is a bug.
* Leak the socket instead of crashing on a stack overflow.
*/
generated by cgit (git 2.34.1) at 2025-03-24 19:07:21 +0000