summaryrefslogtreecommitdiffstats
path: root/net/core
diff options
context:
space:
mode:
Diffstat (limited to 'net/core')
-rw-r--r--net/core/dev.c51
-rw-r--r--net/core/ethtool.c1
-rw-r--r--net/core/flow_dissector.c57
-rw-r--r--net/core/net_namespace.c2
-rw-r--r--net/core/skbuff.c15
-rw-r--r--net/core/sock.c55
6 files changed, 161 insertions, 20 deletions
diff --git a/net/core/dev.c b/net/core/dev.c
index b0eee49a2489..2eb66c0d9cdb 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1542,6 +1542,23 @@ void dev_disable_lro(struct net_device *dev)
}
EXPORT_SYMBOL(dev_disable_lro);
+/**
+ * dev_disable_gro_hw - disable HW Generic Receive Offload on a device
+ * @dev: device
+ *
+ * Disable HW Generic Receive Offload (GRO_HW) on a net device. Must be
+ * called under RTNL. This is needed if Generic XDP is installed on
+ * the device.
+ */
+static void dev_disable_gro_hw(struct net_device *dev)
+{
+ dev->wanted_features &= ~NETIF_F_GRO_HW;
+ netdev_update_features(dev);
+
+ if (unlikely(dev->features & NETIF_F_GRO_HW))
+ netdev_WARN(dev, "failed to disable GRO_HW!\n");
+}
+
static int call_netdevice_notifier(struct notifier_block *nb, unsigned long val,
struct net_device *dev)
{
@@ -3042,7 +3059,7 @@ int skb_csum_hwoffload_help(struct sk_buff *skb,
}
EXPORT_SYMBOL(skb_csum_hwoffload_help);
-static struct sk_buff *validate_xmit_skb(struct sk_buff *skb, struct net_device *dev)
+static struct sk_buff *validate_xmit_skb(struct sk_buff *skb, struct net_device *dev, bool *again)
{
netdev_features_t features;
@@ -3066,9 +3083,6 @@ static struct sk_buff *validate_xmit_skb(struct sk_buff *skb, struct net_device
__skb_linearize(skb))
goto out_kfree_skb;
- if (validate_xmit_xfrm(skb, features))
- goto out_kfree_skb;
-
/* If packet is not checksummed and device does not
* support checksumming for this protocol, complete
* checksumming here.
@@ -3085,6 +3099,8 @@ static struct sk_buff *validate_xmit_skb(struct sk_buff *skb, struct net_device
}
}
+ skb = validate_xmit_xfrm(skb, features, again);
+
return skb;
out_kfree_skb:
@@ -3094,7 +3110,7 @@ out_null:
return NULL;
}
-struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *dev)
+struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *dev, bool *again)
{
struct sk_buff *next, *head = NULL, *tail;
@@ -3105,7 +3121,7 @@ struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *d
/* in case skb wont be segmented, point to itself */
skb->prev = skb;
- skb = validate_xmit_skb(skb, dev);
+ skb = validate_xmit_skb(skb, dev, again);
if (!skb)
continue;
@@ -3432,6 +3448,7 @@ static int __dev_queue_xmit(struct sk_buff *skb, void *accel_priv)
struct netdev_queue *txq;
struct Qdisc *q;
int rc = -ENOMEM;
+ bool again = false;
skb_reset_mac_header(skb);
@@ -3493,7 +3510,7 @@ static int __dev_queue_xmit(struct sk_buff *skb, void *accel_priv)
XMIT_RECURSION_LIMIT))
goto recursion_alert;
- skb = validate_xmit_skb(skb, dev);
+ skb = validate_xmit_skb(skb, dev, &again);
if (!skb)
goto out;
@@ -3920,7 +3937,7 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb,
hroom > 0 ? ALIGN(hroom, NET_SKB_PAD) : 0,
troom > 0 ? troom + 128 : 0, GFP_ATOMIC))
goto do_drop;
- if (troom > 0 && __skb_linearize(skb))
+ if (skb_linearize(skb))
goto do_drop;
}
@@ -4177,6 +4194,8 @@ static __latent_entropy void net_tx_action(struct softirq_action *h)
spin_unlock(root_lock);
}
}
+
+ xfrm_dev_backlog(sd);
}
#if IS_ENABLED(CONFIG_BRIDGE) && IS_ENABLED(CONFIG_ATM_LANE)
@@ -4564,6 +4583,7 @@ static int generic_xdp_install(struct net_device *dev, struct netdev_bpf *xdp)
} else if (new && !old) {
static_key_slow_inc(&generic_xdp_needed);
dev_disable_lro(dev);
+ dev_disable_gro_hw(dev);
}
break;
@@ -7424,6 +7444,18 @@ static netdev_features_t netdev_fix_features(struct net_device *dev,
features &= ~dev->gso_partial_features;
}
+ if (!(features & NETIF_F_RXCSUM)) {
+ /* NETIF_F_GRO_HW implies doing RXCSUM since every packet
+ * successfully merged by hardware must also have the
+ * checksum verified by hardware. If the user does not
+ * want to enable RXCSUM, logically, we should disable GRO_HW.
+ */
+ if (features & NETIF_F_GRO_HW) {
+ netdev_dbg(dev, "Dropping NETIF_F_GRO_HW since no RXCSUM feature.\n");
+ features &= ~NETIF_F_GRO_HW;
+ }
+ }
+
return features;
}
@@ -8845,6 +8877,9 @@ static int __init net_dev_init(void)
skb_queue_head_init(&sd->input_pkt_queue);
skb_queue_head_init(&sd->process_queue);
+#ifdef CONFIG_XFRM_OFFLOAD
+ skb_queue_head_init(&sd->xfrm_backlog);
+#endif
INIT_LIST_HEAD(&sd->poll_list);
sd->output_queue_tailp = &sd->output_queue;
#ifdef CONFIG_RPS
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index f8fcf450a36e..50a79203043b 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -73,6 +73,7 @@ static const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN]
[NETIF_F_LLTX_BIT] = "tx-lockless",
[NETIF_F_NETNS_LOCAL_BIT] = "netns-local",
[NETIF_F_GRO_BIT] = "rx-gro",
+ [NETIF_F_GRO_HW_BIT] = "rx-gro-hw",
[NETIF_F_LRO_BIT] = "rx-lro",
[NETIF_F_TSO_BIT] = "tx-tcp-segmentation",
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index cc75488d3653..02db7b122a73 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -24,6 +24,7 @@
#include <linux/tcp.h>
#include <net/flow_dissector.h>
#include <scsi/fc/fc_fcoe.h>
+#include <uapi/linux/batadv_packet.h>
static void dissector_set_key(struct flow_dissector *flow_dissector,
enum flow_dissector_key_id key_id)
@@ -437,6 +438,57 @@ __skb_flow_dissect_gre(const struct sk_buff *skb,
return FLOW_DISSECT_RET_PROTO_AGAIN;
}
+/**
+ * __skb_flow_dissect_batadv() - dissect batman-adv header
+ * @skb: sk_buff to with the batman-adv header
+ * @key_control: flow dissectors control key
+ * @data: raw buffer pointer to the packet, if NULL use skb->data
+ * @p_proto: pointer used to update the protocol to process next
+ * @p_nhoff: pointer used to update inner network header offset
+ * @hlen: packet header length
+ * @flags: any combination of FLOW_DISSECTOR_F_*
+ *
+ * ETH_P_BATMAN packets are tried to be dissected. Only
+ * &struct batadv_unicast packets are actually processed because they contain an
+ * inner ethernet header and are usually followed by actual network header. This
+ * allows the flow dissector to continue processing the packet.
+ *
+ * Return: FLOW_DISSECT_RET_PROTO_AGAIN when &struct batadv_unicast was found,
+ * FLOW_DISSECT_RET_OUT_GOOD when dissector should stop after encapsulation,
+ * otherwise FLOW_DISSECT_RET_OUT_BAD
+ */
+static enum flow_dissect_ret
+__skb_flow_dissect_batadv(const struct sk_buff *skb,
+ struct flow_dissector_key_control *key_control,
+ void *data, __be16 *p_proto, int *p_nhoff, int hlen,
+ unsigned int flags)
+{
+ struct {
+ struct batadv_unicast_packet batadv_unicast;
+ struct ethhdr eth;
+ } *hdr, _hdr;
+
+ hdr = __skb_header_pointer(skb, *p_nhoff, sizeof(_hdr), data, hlen,
+ &_hdr);
+ if (!hdr)
+ return FLOW_DISSECT_RET_OUT_BAD;
+
+ if (hdr->batadv_unicast.version != BATADV_COMPAT_VERSION)
+ return FLOW_DISSECT_RET_OUT_BAD;
+
+ if (hdr->batadv_unicast.packet_type != BATADV_UNICAST)
+ return FLOW_DISSECT_RET_OUT_BAD;
+
+ *p_proto = hdr->eth.h_proto;
+ *p_nhoff += sizeof(*hdr);
+
+ key_control->flags |= FLOW_DIS_ENCAPSULATION;
+ if (flags & FLOW_DISSECTOR_F_STOP_AT_ENCAP)
+ return FLOW_DISSECT_RET_OUT_GOOD;
+
+ return FLOW_DISSECT_RET_PROTO_AGAIN;
+}
+
static void
__skb_flow_dissect_tcp(const struct sk_buff *skb,
struct flow_dissector *flow_dissector,
@@ -815,6 +867,11 @@ proto_again:
nhoff, hlen);
break;
+ case htons(ETH_P_BATMAN):
+ fdret = __skb_flow_dissect_batadv(skb, key_control, data,
+ &proto, &nhoff, hlen, flags);
+ break;
+
default:
fdret = FLOW_DISSECT_RET_OUT_BAD;
break;
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index b797832565d3..60a71be75aea 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -267,7 +267,7 @@ struct net *get_net_ns_by_id(struct net *net, int id)
spin_lock_bh(&net->nsid_lock);
peer = idr_find(&net->netns_ids, id);
if (peer)
- get_net(peer);
+ peer = maybe_get_net(peer);
spin_unlock_bh(&net->nsid_lock);
rcu_read_unlock();
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index a592ca025fc4..00b0757830e2 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -1178,7 +1178,7 @@ int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask)
u32 d_off;
if (!num_frags)
- return 0;
+ goto release;
if (skb_shared(skb) || skb_unclone(skb, gfp_mask))
return -EINVAL;
@@ -1238,6 +1238,7 @@ int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask)
__skb_fill_page_desc(skb, new_frags - 1, head, 0, d_off);
skb_shinfo(skb)->nr_frags = new_frags;
+release:
skb_zcopy_clear(skb, false);
return 0;
}
@@ -3654,7 +3655,9 @@ normal:
skb_shinfo(nskb)->tx_flags |= skb_shinfo(head_skb)->tx_flags &
SKBTX_SHARED_FRAG;
- if (skb_zerocopy_clone(nskb, head_skb, GFP_ATOMIC))
+
+ if (skb_orphan_frags(frag_skb, GFP_ATOMIC) ||
+ skb_zerocopy_clone(nskb, frag_skb, GFP_ATOMIC))
goto err;
while (pos < offset + len) {
@@ -3668,6 +3671,11 @@ normal:
BUG_ON(!nfrags);
+ if (skb_orphan_frags(frag_skb, GFP_ATOMIC) ||
+ skb_zerocopy_clone(nskb, frag_skb,
+ GFP_ATOMIC))
+ goto err;
+
list_skb = list_skb->next;
}
@@ -3679,9 +3687,6 @@ normal:
goto err;
}
- if (unlikely(skb_orphan_frags(frag_skb, GFP_ATOMIC)))
- goto err;
-
*nskb_frag = *frag;
__skb_frag_ref(nskb_frag);
size = skb_frag_size(nskb_frag);
diff --git a/net/core/sock.c b/net/core/sock.c
index c0b5b2f17412..72d14b221784 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -145,6 +145,8 @@
static DEFINE_MUTEX(proto_list_mutex);
static LIST_HEAD(proto_list);
+static void sock_inuse_add(struct net *net, int val);
+
/**
* sk_ns_capable - General socket capability test
* @sk: Socket to use a capability on or through
@@ -1531,8 +1533,11 @@ struct sock *sk_alloc(struct net *net, int family, gfp_t priority,
sk->sk_kern_sock = kern;
sock_lock_init(sk);
sk->sk_net_refcnt = kern ? 0 : 1;
- if (likely(sk->sk_net_refcnt))
+ if (likely(sk->sk_net_refcnt)) {
get_net(net);
+ sock_inuse_add(net, 1);
+ }
+
sock_net_set(sk, net);
refcount_set(&sk->sk_wmem_alloc, 1);
@@ -1595,6 +1600,9 @@ void sk_destruct(struct sock *sk)
static void __sk_free(struct sock *sk)
{
+ if (likely(sk->sk_net_refcnt))
+ sock_inuse_add(sock_net(sk), -1);
+
if (unlikely(sock_diag_has_destroy_listeners(sk) && sk->sk_net_refcnt))
sock_diag_broadcast_destroy(sk);
else
@@ -1716,6 +1724,8 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
newsk->sk_priority = 0;
newsk->sk_incoming_cpu = raw_smp_processor_id();
atomic64_set(&newsk->sk_cookie, 0);
+ if (likely(newsk->sk_net_refcnt))
+ sock_inuse_add(sock_net(newsk), 1);
/*
* Before updating sk_refcnt, we must commit prior changes to memory
@@ -3045,7 +3055,7 @@ static DECLARE_BITMAP(proto_inuse_idx, PROTO_INUSE_NR);
void sock_prot_inuse_add(struct net *net, struct proto *prot, int val)
{
- __this_cpu_add(net->core.inuse->val[prot->inuse_idx], val);
+ __this_cpu_add(net->core.prot_inuse->val[prot->inuse_idx], val);
}
EXPORT_SYMBOL_GPL(sock_prot_inuse_add);
@@ -3055,21 +3065,50 @@ int sock_prot_inuse_get(struct net *net, struct proto *prot)
int res = 0;
for_each_possible_cpu(cpu)
- res += per_cpu_ptr(net->core.inuse, cpu)->val[idx];
+ res += per_cpu_ptr(net->core.prot_inuse, cpu)->val[idx];
return res >= 0 ? res : 0;
}
EXPORT_SYMBOL_GPL(sock_prot_inuse_get);
+static void sock_inuse_add(struct net *net, int val)
+{
+ this_cpu_add(*net->core.sock_inuse, val);
+}
+
+int sock_inuse_get(struct net *net)
+{
+ int cpu, res = 0;
+
+ for_each_possible_cpu(cpu)
+ res += *per_cpu_ptr(net->core.sock_inuse, cpu);
+
+ return res;
+}
+
+EXPORT_SYMBOL_GPL(sock_inuse_get);
+
static int __net_init sock_inuse_init_net(struct net *net)
{
- net->core.inuse = alloc_percpu(struct prot_inuse);
- return net->core.inuse ? 0 : -ENOMEM;
+ net->core.prot_inuse = alloc_percpu(struct prot_inuse);
+ if (net->core.prot_inuse == NULL)
+ return -ENOMEM;
+
+ net->core.sock_inuse = alloc_percpu(int);
+ if (net->core.sock_inuse == NULL)
+ goto out;
+
+ return 0;
+
+out:
+ free_percpu(net->core.prot_inuse);
+ return -ENOMEM;
}
static void __net_exit sock_inuse_exit_net(struct net *net)
{
- free_percpu(net->core.inuse);
+ free_percpu(net->core.prot_inuse);
+ free_percpu(net->core.sock_inuse);
}
static struct pernet_operations net_inuse_ops = {
@@ -3112,6 +3151,10 @@ static inline void assign_proto_idx(struct proto *prot)
static inline void release_proto_idx(struct proto *prot)
{
}
+
+static void sock_inuse_add(struct net *net, int val)
+{
+}
#endif
static void req_prot_cleanup(struct request_sock_ops *rsk_prot)
generated by cgit v1.2.3 (git 2.39.1) at 2025-04-25 09:18:45 +0000