summaryrefslogtreecommitdiff
path: root/net/core
diff options
context:
space:
mode:
Diffstat (limited to 'net/core')
-rw-r--r--net/core/Makefile2
-rw-r--r--net/core/dev.c102
-rw-r--r--net/core/ethtool.c28
-rw-r--r--net/core/filter.c24
-rw-r--r--net/core/rtnetlink.c20
-rw-r--r--net/core/skbuff.c20
-rw-r--r--net/core/xdp.c73
7 files changed, 219 insertions, 50 deletions
diff --git a/net/core/Makefile b/net/core/Makefile
index 1fd0a9c88b1b..6dbbba8c57ae 100644
--- a/net/core/Makefile
+++ b/net/core/Makefile
@@ -11,7 +11,7 @@ obj-$(CONFIG_SYSCTL) += sysctl_net_core.o
obj-y += dev.o ethtool.o dev_addr_lists.o dst.o netevent.o \
neighbour.o rtnetlink.o utils.o link_watch.o filter.o \
sock_diag.o dev_ioctl.o tso.o sock_reuseport.o \
- fib_notifier.o
+ fib_notifier.o xdp.o
obj-y += net-sysfs.o
obj-$(CONFIG_PROC_FS) += net-procfs.o
diff --git a/net/core/dev.c b/net/core/dev.c
index 59ead3910ab7..5cb782f074d7 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1146,7 +1146,19 @@ EXPORT_SYMBOL(dev_alloc_name);
int dev_get_valid_name(struct net *net, struct net_device *dev,
const char *name)
{
- return dev_alloc_name_ns(net, dev, name);
+ BUG_ON(!net);
+
+ if (!dev_valid_name(name))
+ return -EINVAL;
+
+ if (strchr(name, '%'))
+ return dev_alloc_name_ns(net, dev, name);
+ else if (__dev_get_by_name(net, name))
+ return -EEXIST;
+ else if (dev->name != name)
+ strlcpy(dev->name, name, IFNAMSIZ);
+
+ return 0;
}
EXPORT_SYMBOL(dev_get_valid_name);
@@ -3059,7 +3071,7 @@ 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;
@@ -3083,9 +3095,6 @@ 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.
@@ -3102,6 +3111,8 @@ 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:
@@ -3111,7 +3122,7 @@ 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;
@@ -3122,7 +3133,7 @@ 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;
@@ -3449,6 +3460,7 @@ 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);
@@ -3510,7 +3522,7 @@ 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;
@@ -3906,9 +3918,33 @@ drop:
return NET_RX_DROP;
}
+static struct netdev_rx_queue *netif_get_rxqueue(struct sk_buff *skb)
+{
+ struct net_device *dev = skb->dev;
+ struct netdev_rx_queue *rxqueue;
+
+ rxqueue = dev->_rx;
+
+ if (skb_rx_queue_recorded(skb)) {
+ u16 index = skb_get_rx_queue(skb);
+
+ if (unlikely(index >= dev->real_num_rx_queues)) {
+ WARN_ONCE(dev->real_num_rx_queues > 1,
+ "%s received packet on queue %u, but number "
+ "of RX queues is %u\n",
+ dev->name, index, dev->real_num_rx_queues);
+
+ return rxqueue; /* Return first rxqueue */
+ }
+ rxqueue += index;
+ }
+ return rxqueue;
+}
+
static u32 netif_receive_generic_xdp(struct sk_buff *skb,
struct bpf_prog *xdp_prog)
{
+ struct netdev_rx_queue *rxqueue;
u32 metalen, act = XDP_DROP;
struct xdp_buff xdp;
void *orig_data;
@@ -3952,6 +3988,9 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb,
xdp.data_hard_start = skb->data - skb_headroom(skb);
orig_data = xdp.data;
+ rxqueue = netif_get_rxqueue(skb);
+ xdp.rxq = &rxqueue->xdp_rxq;
+
act = bpf_prog_run_xdp(xdp_prog, &xdp);
off = xdp.data - orig_data;
@@ -4194,6 +4233,8 @@ 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)
@@ -7587,12 +7628,12 @@ void netif_stacked_transfer_operstate(const struct net_device *rootdev,
}
EXPORT_SYMBOL(netif_stacked_transfer_operstate);
-#ifdef CONFIG_SYSFS
static int netif_alloc_rx_queues(struct net_device *dev)
{
unsigned int i, count = dev->num_rx_queues;
struct netdev_rx_queue *rx;
size_t sz = count * sizeof(*rx);
+ int err = 0;
BUG_ON(count < 1);
@@ -7602,11 +7643,39 @@ static int netif_alloc_rx_queues(struct net_device *dev)
dev->_rx = rx;
- for (i = 0; i < count; i++)
+ for (i = 0; i < count; i++) {
rx[i].dev = dev;
+
+ /* XDP RX-queue setup */
+ err = xdp_rxq_info_reg(&rx[i].xdp_rxq, dev, i);
+ if (err < 0)
+ goto err_rxq_info;
+ }
return 0;
+
+err_rxq_info:
+ /* Rollback successful reg's and free other resources */
+ while (i--)
+ xdp_rxq_info_unreg(&rx[i].xdp_rxq);
+ kfree(dev->_rx);
+ dev->_rx = NULL;
+ return err;
+}
+
+static void netif_free_rx_queues(struct net_device *dev)
+{
+ unsigned int i, count = dev->num_rx_queues;
+ struct netdev_rx_queue *rx;
+
+ /* netif_alloc_rx_queues alloc failed, resources have been unreg'ed */
+ if (!dev->_rx)
+ return;
+
+ rx = dev->_rx;
+
+ for (i = 0; i < count; i++)
+ xdp_rxq_info_unreg(&rx[i].xdp_rxq);
}
-#endif
static void netdev_init_one_queue(struct net_device *dev,
struct netdev_queue *queue, void *_unused)
@@ -8167,12 +8236,10 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
return NULL;
}
-#ifdef CONFIG_SYSFS
if (rxqs < 1) {
pr_err("alloc_netdev: Unable to allocate device with zero RX queues\n");
return NULL;
}
-#endif
alloc_size = sizeof(struct net_device);
if (sizeof_priv) {
@@ -8229,12 +8296,10 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
if (netif_alloc_netdev_queues(dev))
goto free_all;
-#ifdef CONFIG_SYSFS
dev->num_rx_queues = rxqs;
dev->real_num_rx_queues = rxqs;
if (netif_alloc_rx_queues(dev))
goto free_all;
-#endif
strcpy(dev->name, name);
dev->name_assign_type = name_assign_type;
@@ -8273,9 +8338,7 @@ void free_netdev(struct net_device *dev)
might_sleep();
netif_free_tx_queues(dev);
-#ifdef CONFIG_SYSFS
- kvfree(dev->_rx);
-#endif
+ netif_free_rx_queues(dev);
kfree(rcu_dereference_protected(dev->ingress_queue, 1));
@@ -8875,6 +8938,9 @@ 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 50a79203043b..107b122c8969 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -771,15 +771,6 @@ static int ethtool_set_link_ksettings(struct net_device *dev,
return dev->ethtool_ops->set_link_ksettings(dev, &link_ksettings);
}
-static void
-warn_incomplete_ethtool_legacy_settings_conversion(const char *details)
-{
- char name[sizeof(current->comm)];
-
- pr_info_once("warning: `%s' uses legacy ethtool link settings API, %s\n",
- get_task_comm(name, current), details);
-}
-
/* Query device for its ethtool_cmd settings.
*
* Backward compatibility note: for compatibility with legacy ethtool,
@@ -806,10 +797,8 @@ static int ethtool_get_settings(struct net_device *dev, void __user *useraddr)
&link_ksettings);
if (err < 0)
return err;
- if (!convert_link_ksettings_to_legacy_settings(&cmd,
- &link_ksettings))
- warn_incomplete_ethtool_legacy_settings_conversion(
- "link modes are only partially reported");
+ convert_link_ksettings_to_legacy_settings(&cmd,
+ &link_ksettings);
/* send a sensible cmd tag back to user */
cmd.cmd = ETHTOOL_GSET;
@@ -1704,14 +1693,23 @@ static int ethtool_get_ringparam(struct net_device *dev, void __user *useraddr)
static int ethtool_set_ringparam(struct net_device *dev, void __user *useraddr)
{
- struct ethtool_ringparam ringparam;
+ struct ethtool_ringparam ringparam, max = { .cmd = ETHTOOL_GRINGPARAM };
- if (!dev->ethtool_ops->set_ringparam)
+ if (!dev->ethtool_ops->set_ringparam || !dev->ethtool_ops->get_ringparam)
return -EOPNOTSUPP;
if (copy_from_user(&ringparam, useraddr, sizeof(ringparam)))
return -EFAULT;
+ dev->ethtool_ops->get_ringparam(dev, &max);
+
+ /* ensure new ring parameters are within the maximums */
+ if (ringparam.rx_pending > max.rx_max_pending ||
+ ringparam.rx_mini_pending > max.rx_mini_max_pending ||
+ ringparam.rx_jumbo_pending > max.rx_jumbo_max_pending ||
+ ringparam.tx_pending > max.tx_max_pending)
+ return -EINVAL;
+
return dev->ethtool_ops->set_ringparam(dev, &ringparam);
}
diff --git a/net/core/filter.c b/net/core/filter.c
index 754abe1041b7..acdb94c0e97f 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2684,8 +2684,9 @@ static int __xdp_generic_ok_fwd_dev(struct sk_buff *skb, struct net_device *fwd)
return 0;
}
-int xdp_do_generic_redirect_map(struct net_device *dev, struct sk_buff *skb,
- struct bpf_prog *xdp_prog)
+static int xdp_do_generic_redirect_map(struct net_device *dev,
+ struct sk_buff *skb,
+ struct bpf_prog *xdp_prog)
{
struct redirect_info *ri = this_cpu_ptr(&redirect_info);
unsigned long map_owner = ri->map_owner;
@@ -4303,6 +4304,25 @@ static u32 xdp_convert_ctx_access(enum bpf_access_type type,
si->dst_reg, si->src_reg,
offsetof(struct xdp_buff, data_end));
break;
+ case offsetof(struct xdp_md, ingress_ifindex):
+ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_buff, rxq),
+ si->dst_reg, si->src_reg,
+ offsetof(struct xdp_buff, rxq));
+ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_rxq_info, dev),
+ si->dst_reg, si->dst_reg,
+ offsetof(struct xdp_rxq_info, dev));
+ *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg,
+ bpf_target_off(struct net_device,
+ ifindex, 4, target_size));
+ break;
+ case offsetof(struct xdp_md, rx_queue_index):
+ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_buff, rxq),
+ si->dst_reg, si->src_reg,
+ offsetof(struct xdp_buff, rxq));
+ *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg,
+ bpf_target_off(struct xdp_rxq_info,
+ queue_index, 4, target_size));
+ break;
}
return insn - insn_buf;
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index c688dc564b11..16d644a4f974 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -904,6 +904,10 @@ static inline int rtnl_vfinfo_size(const struct net_device *dev,
nla_total_size_64bit(sizeof(__u64)) +
/* IFLA_VF_STATS_MULTICAST */
nla_total_size_64bit(sizeof(__u64)) +
+ /* IFLA_VF_STATS_RX_DROPPED */
+ nla_total_size_64bit(sizeof(__u64)) +
+ /* IFLA_VF_STATS_TX_DROPPED */
+ nla_total_size_64bit(sizeof(__u64)) +
nla_total_size(sizeof(struct ifla_vf_trust)));
return size;
} else
@@ -1258,7 +1262,11 @@ static noinline_for_stack int rtnl_fill_vfinfo(struct sk_buff *skb,
nla_put_u64_64bit(skb, IFLA_VF_STATS_BROADCAST,
vf_stats.broadcast, IFLA_VF_STATS_PAD) ||
nla_put_u64_64bit(skb, IFLA_VF_STATS_MULTICAST,
- vf_stats.multicast, IFLA_VF_STATS_PAD)) {
+ vf_stats.multicast, IFLA_VF_STATS_PAD) ||
+ nla_put_u64_64bit(skb, IFLA_VF_STATS_RX_DROPPED,
+ vf_stats.rx_dropped, IFLA_VF_STATS_PAD) ||
+ nla_put_u64_64bit(skb, IFLA_VF_STATS_TX_DROPPED,
+ vf_stats.tx_dropped, IFLA_VF_STATS_PAD)) {
nla_nest_cancel(skb, vfstats);
goto nla_put_vf_failure;
}
@@ -1751,18 +1759,18 @@ static bool link_dump_filtered(struct net_device *dev,
return false;
}
-static struct net *get_target_net(struct sk_buff *skb, int netnsid)
+static struct net *get_target_net(struct sock *sk, int netnsid)
{
struct net *net;
- net = get_net_ns_by_id(sock_net(skb->sk), netnsid);
+ net = get_net_ns_by_id(sock_net(sk), netnsid);
if (!net)
return ERR_PTR(-EINVAL);
/* For now, the caller is required to have CAP_NET_ADMIN in
* the user namespace owning the target net ns.
*/
- if (!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN)) {
+ if (!sk_ns_capable(sk, net->user_ns, CAP_NET_ADMIN)) {
put_net(net);
return ERR_PTR(-EACCES);
}
@@ -1803,7 +1811,7 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
ifla_policy, NULL) >= 0) {
if (tb[IFLA_IF_NETNSID]) {
netnsid = nla_get_s32(tb[IFLA_IF_NETNSID]);
- tgt_net = get_target_net(skb, netnsid);
+ tgt_net = get_target_net(skb->sk, netnsid);
if (IS_ERR(tgt_net)) {
tgt_net = net;
netnsid = -1;
@@ -2985,7 +2993,7 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr *nlh,
if (tb[IFLA_IF_NETNSID]) {
netnsid = nla_get_s32(tb[IFLA_IF_NETNSID]);
- tgt_net = get_target_net(skb, netnsid);
+ tgt_net = get_target_net(NETLINK_CB(skb).sk, netnsid);
if (IS_ERR(tgt_net))
return PTR_ERR(tgt_net);
}
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index a3cb0be4c6f3..01e8285aea73 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -1177,12 +1177,12 @@ int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask)
int i, new_frags;
u32 d_off;
- if (!num_frags)
- goto release;
-
if (skb_shared(skb) || skb_unclone(skb, gfp_mask))
return -EINVAL;
+ if (!num_frags)
+ goto release;
+
new_frags = (__skb_pagelen(skb) + PAGE_SIZE - 1) >> PAGE_SHIFT;
for (i = 0; i < new_frags; i++) {
page = alloc_page(gfp_mask);
@@ -3656,6 +3656,10 @@ 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))
+ goto err;
+
while (pos < offset + len) {
if (i >= nfrags) {
BUG_ON(skb_headlen(list_skb));
@@ -3667,6 +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;
}
@@ -3678,11 +3687,6 @@ normal:
goto err;
}
- if (unlikely(skb_orphan_frags(frag_skb, GFP_ATOMIC)))
- goto err;
- if (skb_zerocopy_clone(nskb, 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/xdp.c b/net/core/xdp.c
new file mode 100644
index 000000000000..097a0f74e004
--- /dev/null
+++ b/net/core/xdp.c
@@ -0,0 +1,73 @@
+/* net/core/xdp.c
+ *
+ * Copyright (c) 2017 Jesper Dangaard Brouer, Red Hat Inc.
+ * Released under terms in GPL version 2. See COPYING.
+ */
+#include <linux/types.h>
+#include <linux/mm.h>
+
+#include <net/xdp.h>
+
+#define REG_STATE_NEW 0x0
+#define REG_STATE_REGISTERED 0x1
+#define REG_STATE_UNREGISTERED 0x2
+#define REG_STATE_UNUSED 0x3
+
+void xdp_rxq_info_unreg(struct xdp_rxq_info *xdp_rxq)
+{
+ /* Simplify driver cleanup code paths, allow unreg "unused" */
+ if (xdp_rxq->reg_state == REG_STATE_UNUSED)
+ return;
+
+ WARN(!(xdp_rxq->reg_state == REG_STATE_REGISTERED), "Driver BUG");
+
+ xdp_rxq->reg_state = REG_STATE_UNREGISTERED;
+ xdp_rxq->dev = NULL;
+}
+EXPORT_SYMBOL_GPL(xdp_rxq_info_unreg);
+
+static void xdp_rxq_info_init(struct xdp_rxq_info *xdp_rxq)
+{
+ memset(xdp_rxq, 0, sizeof(*xdp_rxq));
+}
+
+/* Returns 0 on success, negative on failure */
+int xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq,
+ struct net_device *dev, u32 queue_index)
+{
+ if (xdp_rxq->reg_state == REG_STATE_UNUSED) {
+ WARN(1, "Driver promised not to register this");
+ return -EINVAL;
+ }
+
+ if (xdp_rxq->reg_state == REG_STATE_REGISTERED) {
+ WARN(1, "Missing unregister, handled but fix driver");
+ xdp_rxq_info_unreg(xdp_rxq);
+ }
+
+ if (!dev) {
+ WARN(1, "Missing net_device from driver");
+ return -ENODEV;
+ }
+
+ /* State either UNREGISTERED or NEW */
+ xdp_rxq_info_init(xdp_rxq);
+ xdp_rxq->dev = dev;
+ xdp_rxq->queue_index = queue_index;
+
+ xdp_rxq->reg_state = REG_STATE_REGISTERED;
+ return 0;
+}
+EXPORT_SYMBOL_GPL(xdp_rxq_info_reg);
+
+void xdp_rxq_info_unused(struct xdp_rxq_info *xdp_rxq)
+{
+ xdp_rxq->reg_state = REG_STATE_UNUSED;
+}
+EXPORT_SYMBOL_GPL(xdp_rxq_info_unused);
+
+bool xdp_rxq_info_is_reg(struct xdp_rxq_info *xdp_rxq)
+{
+ return (xdp_rxq->reg_state == REG_STATE_REGISTERED);
+}
+EXPORT_SYMBOL_GPL(xdp_rxq_info_is_reg);
generated by cgit v1.2.3 (git 2.46.0) at 2025-11-06 13:49:03 +0000