summaryrefslogtreecommitdiffstats
path: root/net/core
diff options
context:
space:
mode:
Diffstat (limited to 'net/core')
-rw-r--r--net/core/datagram.c92
-rw-r--r--net/core/dev.c94
-rw-r--r--net/core/dev_ioctl.c1
-rw-r--r--net/core/filter.c36
-rw-r--r--net/core/flow_dissector.c69
-rw-r--r--net/core/lwt_bpf.c5
-rw-r--r--net/core/lwtunnel.c38
-rw-r--r--net/core/neighbour.c60
-rw-r--r--net/core/net-procfs.c13
-rw-r--r--net/core/net-sysfs.c8
-rw-r--r--net/core/rtnetlink.c69
-rw-r--r--net/core/skbuff.c95
-rw-r--r--net/core/sock.c4
13 files changed, 457 insertions, 127 deletions
diff --git a/net/core/datagram.c b/net/core/datagram.c
index db1866f2ffcf..bc46118486fe 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -161,6 +161,45 @@ done:
return skb;
}
+struct sk_buff *__skb_try_recv_from_queue(struct sock *sk,
+ struct sk_buff_head *queue,
+ unsigned int flags,
+ void (*destructor)(struct sock *sk,
+ struct sk_buff *skb),
+ int *peeked, int *off, int *err,
+ struct sk_buff **last)
+{
+ struct sk_buff *skb;
+ int _off = *off;
+
+ *last = queue->prev;
+ skb_queue_walk(queue, skb) {
+ if (flags & MSG_PEEK) {
+ if (_off >= skb->len && (skb->len || _off ||
+ skb->peeked)) {
+ _off -= skb->len;
+ continue;
+ }
+ if (!skb->len) {
+ skb = skb_set_peeked(skb);
+ if (unlikely(IS_ERR(skb))) {
+ *err = PTR_ERR(skb);
+ return NULL;
+ }
+ }
+ *peeked = 1;
+ atomic_inc(&skb->users);
+ } else {
+ __skb_unlink(skb, queue);
+ if (destructor)
+ destructor(sk, skb);
+ }
+ *off = _off;
+ return skb;
+ }
+ return NULL;
+}
+
/**
* __skb_try_recv_datagram - Receive a datagram skbuff
* @sk: socket
@@ -222,40 +261,14 @@ struct sk_buff *__skb_try_recv_datagram(struct sock *sk, unsigned int flags,
* Look at current nfs client by the way...
* However, this function was correct in any case. 8)
*/
- int _off = *off;
-
- *last = (struct sk_buff *)queue;
spin_lock_irqsave(&queue->lock, cpu_flags);
- skb_queue_walk(queue, skb) {
- *last = skb;
- if (flags & MSG_PEEK) {
- if (_off >= skb->len && (skb->len || _off ||
- skb->peeked)) {
- _off -= skb->len;
- continue;
- }
- if (!skb->len) {
- skb = skb_set_peeked(skb);
- if (IS_ERR(skb)) {
- error = PTR_ERR(skb);
- spin_unlock_irqrestore(&queue->lock,
- cpu_flags);
- goto no_packet;
- }
- }
- *peeked = 1;
- atomic_inc(&skb->users);
- } else {
- __skb_unlink(skb, queue);
- if (destructor)
- destructor(sk, skb);
- }
- spin_unlock_irqrestore(&queue->lock, cpu_flags);
- *off = _off;
- return skb;
- }
-
+ skb = __skb_try_recv_from_queue(sk, queue, flags, destructor,
+ peeked, off, &error, last);
spin_unlock_irqrestore(&queue->lock, cpu_flags);
+ if (error)
+ goto no_packet;
+ if (skb)
+ return skb;
if (!sk_can_busy_loop(sk))
break;
@@ -335,8 +348,8 @@ void __skb_free_datagram_locked(struct sock *sk, struct sk_buff *skb, int len)
}
EXPORT_SYMBOL(__skb_free_datagram_locked);
-int __sk_queue_drop_skb(struct sock *sk, struct sk_buff *skb,
- unsigned int flags,
+int __sk_queue_drop_skb(struct sock *sk, struct sk_buff_head *sk_queue,
+ struct sk_buff *skb, unsigned int flags,
void (*destructor)(struct sock *sk,
struct sk_buff *skb))
{
@@ -344,15 +357,15 @@ int __sk_queue_drop_skb(struct sock *sk, struct sk_buff *skb,
if (flags & MSG_PEEK) {
err = -ENOENT;
- spin_lock_bh(&sk->sk_receive_queue.lock);
- if (skb == skb_peek(&sk->sk_receive_queue)) {
- __skb_unlink(skb, &sk->sk_receive_queue);
+ spin_lock_bh(&sk_queue->lock);
+ if (skb == skb_peek(sk_queue)) {
+ __skb_unlink(skb, sk_queue);
atomic_dec(&skb->users);
if (destructor)
destructor(sk, skb);
err = 0;
}
- spin_unlock_bh(&sk->sk_receive_queue.lock);
+ spin_unlock_bh(&sk_queue->lock);
}
atomic_inc(&sk->sk_drops);
@@ -383,7 +396,8 @@ EXPORT_SYMBOL(__sk_queue_drop_skb);
int skb_kill_datagram(struct sock *sk, struct sk_buff *skb, unsigned int flags)
{
- int err = __sk_queue_drop_skb(sk, skb, flags, NULL);
+ int err = __sk_queue_drop_skb(sk, &sk->sk_receive_queue, skb, flags,
+ NULL);
kfree_skb(skb);
sk_mem_reclaim_partial(sk);
diff --git a/net/core/dev.c b/net/core/dev.c
index fca407b4a6ea..8f72f4a9c6ac 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -105,6 +105,7 @@
#include <net/dst.h>
#include <net/dst_metadata.h>
#include <net/pkt_sched.h>
+#include <net/pkt_cls.h>
#include <net/checksum.h>
#include <net/xfrm.h>
#include <linux/highmem.h>
@@ -142,6 +143,7 @@
#include <linux/hrtimer.h>
#include <linux/netfilter_ingress.h>
#include <linux/crash_dump.h>
+#include <linux/sctp.h>
#include "net-sysfs.h"
@@ -161,6 +163,7 @@ static int netif_rx_internal(struct sk_buff *skb);
static int call_netdevice_notifiers_info(unsigned long val,
struct net_device *dev,
struct netdev_notifier_info *info);
+static struct napi_struct *napi_by_id(unsigned int napi_id);
/*
* The @dev_base_head list is protected by @dev_base_lock and the rtnl
@@ -865,6 +868,31 @@ struct net_device *dev_get_by_index(struct net *net, int ifindex)
EXPORT_SYMBOL(dev_get_by_index);
/**
+ * dev_get_by_napi_id - find a device by napi_id
+ * @napi_id: ID of the NAPI struct
+ *
+ * Search for an interface by NAPI ID. Returns %NULL if the device
+ * is not found or a pointer to the device. The device has not had
+ * its reference counter increased so the caller must be careful
+ * about locking. The caller must hold RCU lock.
+ */
+
+struct net_device *dev_get_by_napi_id(unsigned int napi_id)
+{
+ struct napi_struct *napi;
+
+ WARN_ON_ONCE(!rcu_read_lock_held());
+
+ if (napi_id < MIN_NAPI_ID)
+ return NULL;
+
+ napi = napi_by_id(napi_id);
+
+ return napi ? napi->dev : NULL;
+}
+EXPORT_SYMBOL(dev_get_by_napi_id);
+
+/**
* netdev_get_name - get a netdevice name, knowing its ifindex.
* @net: network namespace
* @name: a pointer to the buffer where the name will be stored.
@@ -2611,6 +2639,47 @@ out:
}
EXPORT_SYMBOL(skb_checksum_help);
+int skb_crc32c_csum_help(struct sk_buff *skb)
+{
+ __le32 crc32c_csum;
+ int ret = 0, offset, start;
+
+ if (skb->ip_summed != CHECKSUM_PARTIAL)
+ goto out;
+
+ if (unlikely(skb_is_gso(skb)))
+ goto out;
+
+ /* Before computing a checksum, we should make sure no frag could
+ * be modified by an external entity : checksum could be wrong.
+ */
+ if (unlikely(skb_has_shared_frag(skb))) {
+ ret = __skb_linearize(skb);
+ if (ret)
+ goto out;
+ }
+ start = skb_checksum_start_offset(skb);
+ offset = start + offsetof(struct sctphdr, checksum);
+ if (WARN_ON_ONCE(offset >= skb_headlen(skb))) {
+ ret = -EINVAL;
+ goto out;
+ }
+ if (skb_cloned(skb) &&
+ !skb_clone_writable(skb, offset + sizeof(__le32))) {
+ ret = pskb_expand_head(skb, 0, 0, GFP_ATOMIC);
+ if (ret)
+ goto out;
+ }
+ crc32c_csum = cpu_to_le32(~__skb_checksum(skb, start,
+ skb->len - start, ~(__u32)0,
+ crc32c_csum_stub));
+ *(__le32 *)(skb->data + offset) = crc32c_csum;
+ skb->ip_summed = CHECKSUM_NONE;
+ skb->csum_not_inet = 0;
+out:
+ return ret;
+}
+
__be16 skb_network_protocol(struct sk_buff *skb, int *depth)
{
__be16 type = skb->protocol;
@@ -2953,6 +3022,17 @@ static struct sk_buff *validate_xmit_vlan(struct sk_buff *skb,
return skb;
}
+int skb_csum_hwoffload_help(struct sk_buff *skb,
+ const netdev_features_t features)
+{
+ if (unlikely(skb->csum_not_inet))
+ return !!(features & NETIF_F_SCTP_CRC) ? 0 :
+ skb_crc32c_csum_help(skb);
+
+ return !!(features & NETIF_F_CSUM_MASK) ? 0 : skb_checksum_help(skb);
+}
+EXPORT_SYMBOL(skb_csum_hwoffload_help);
+
static struct sk_buff *validate_xmit_skb(struct sk_buff *skb, struct net_device *dev)
{
netdev_features_t features;
@@ -2991,8 +3071,7 @@ static struct sk_buff *validate_xmit_skb(struct sk_buff *skb, struct net_device
else
skb_set_transport_header(skb,
skb_checksum_start_offset(skb));
- if (!(features & NETIF_F_CSUM_MASK) &&
- skb_checksum_help(skb))
+ if (skb_csum_hwoffload_help(skb, features))
goto out_kfree_skb;
}
}
@@ -3178,7 +3257,7 @@ sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev)
/* qdisc_skb_cb(skb)->pkt_len was already set by the caller. */
qdisc_bstats_cpu_update(cl->q, skb);
- switch (tc_classify(skb, cl, &cl_res, false)) {
+ switch (tcf_classify(skb, cl, &cl_res, false)) {
case TC_ACT_OK:
case TC_ACT_RECLASSIFY:
skb->tc_index = TC_H_MIN(cl_res.classid);
@@ -3190,6 +3269,7 @@ sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev)
return NULL;
case TC_ACT_STOLEN:
case TC_ACT_QUEUED:
+ case TC_ACT_TRAP:
*ret = NET_XMIT_SUCCESS;
consume_skb(skb);
return NULL;
@@ -3948,7 +4028,7 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret,
skb->tc_at_ingress = 1;
qdisc_bstats_cpu_update(cl->q, skb);
- switch (tc_classify(skb, cl, &cl_res, false)) {
+ switch (tcf_classify(skb, cl, &cl_res, false)) {
case TC_ACT_OK:
case TC_ACT_RECLASSIFY:
skb->tc_index = TC_H_MIN(cl_res.classid);
@@ -3959,6 +4039,7 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret,
return NULL;
case TC_ACT_STOLEN:
case TC_ACT_QUEUED:
+ case TC_ACT_TRAP:
consume_skb(skb);
return NULL;
case TC_ACT_REDIRECT:
@@ -4636,9 +4717,6 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
if (netif_elide_gro(skb->dev))
goto normal;
- if (skb->csum_bad)
- goto normal;
-
gro_list_prepare(napi, skb);
rcu_read_lock();
@@ -7008,7 +7086,7 @@ static void rollback_registered_many(struct list_head *head)
if (!dev->rtnl_link_ops ||
dev->rtnl_link_state == RTNL_LINK_INITIALIZED)
- skb = rtmsg_ifinfo_build_skb(RTM_DELLINK, dev, ~0U,
+ skb = rtmsg_ifinfo_build_skb(RTM_DELLINK, dev, ~0U, 0,
GFP_KERNEL);
/*
diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c
index b94b1d293506..77f04e71100f 100644
--- a/net/core/dev_ioctl.c
+++ b/net/core/dev_ioctl.c
@@ -225,6 +225,7 @@ static int net_hwtstamp_validate(struct ifreq *ifr)
case HWTSTAMP_FILTER_PTP_V2_EVENT:
case HWTSTAMP_FILTER_PTP_V2_SYNC:
case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
+ case HWTSTAMP_FILTER_NTP_ALL:
rx_filter_valid = 1;
break;
}
diff --git a/net/core/filter.c b/net/core/filter.c
index a6bb95fa87b2..946f758d44f2 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -352,7 +352,7 @@ static bool convert_bpf_extensions(struct sock_filter *fp,
* bpf_convert_filter - convert filter program
* @prog: the user passed filter program
* @len: the length of the user passed filter program
- * @new_prog: buffer where converted program will be stored
+ * @new_prog: allocated 'struct bpf_prog' or NULL
* @new_len: pointer to store length of converted program
*
* Remap 'sock_filter' style classic BPF (cBPF) instruction set to 'bpf_insn'
@@ -364,14 +364,13 @@ static bool convert_bpf_extensions(struct sock_filter *fp,
*
* 2) 2nd pass to remap in two passes: 1st pass finds new
* jump offsets, 2nd pass remapping:
- * new_prog = kmalloc(sizeof(struct bpf_insn) * new_len);
* bpf_convert_filter(old_prog, old_len, new_prog, &new_len);
*/
static int bpf_convert_filter(struct sock_filter *prog, int len,
- struct bpf_insn *new_prog, int *new_len)
+ struct bpf_prog *new_prog, int *new_len)
{
- int new_flen = 0, pass = 0, target, i;
- struct bpf_insn *new_insn;
+ int new_flen = 0, pass = 0, target, i, stack_off;
+ struct bpf_insn *new_insn, *first_insn = NULL;
struct sock_filter *fp;
int *addrs = NULL;
u8 bpf_src;
@@ -383,6 +382,7 @@ static int bpf_convert_filter(struct sock_filter *prog, int len,
return -EINVAL;
if (new_prog) {
+ first_insn = new_prog->insnsi;
addrs = kcalloc(len, sizeof(*addrs),
GFP_KERNEL | __GFP_NOWARN);
if (!addrs)
@@ -390,11 +390,11 @@ static int bpf_convert_filter(struct sock_filter *prog, int len,
}
do_pass:
- new_insn = new_prog;
+ new_insn = first_insn;
fp = prog;
/* Classic BPF related prologue emission. */
- if (new_insn) {
+ if (new_prog) {
/* Classic BPF expects A and X to be reset first. These need
* to be guaranteed to be the first two instructions.
*/
@@ -415,7 +415,7 @@ do_pass:
struct bpf_insn *insn = tmp_insns;
if (addrs)
- addrs[i] = new_insn - new_prog;
+ addrs[i] = new_insn - first_insn;
switch (fp->code) {
/* All arithmetic insns and skb loads map as-is. */
@@ -561,17 +561,25 @@ do_pass:
/* Store to stack. */
case BPF_ST:
case BPF_STX:
+ stack_off = fp->k * 4 + 4;
*insn = BPF_STX_MEM(BPF_W, BPF_REG_FP, BPF_CLASS(fp->code) ==
BPF_ST ? BPF_REG_A : BPF_REG_X,
- -(BPF_MEMWORDS - fp->k) * 4);
+ -stack_off);
+ /* check_load_and_stores() verifies that classic BPF can
+ * load from stack only after write, so tracking
+ * stack_depth for ST|STX insns is enough
+ */
+ if (new_prog && new_prog->aux->stack_depth < stack_off)
+ new_prog->aux->stack_depth = stack_off;
break;
/* Load from stack. */
case BPF_LD | BPF_MEM:
case BPF_LDX | BPF_MEM:
+ stack_off = fp->k * 4 + 4;
*insn = BPF_LDX_MEM(BPF_W, BPF_CLASS(fp->code) == BPF_LD ?
BPF_REG_A : BPF_REG_X, BPF_REG_FP,
- -(BPF_MEMWORDS - fp->k) * 4);
+ -stack_off);
break;
/* A = K or X = K */
@@ -619,13 +627,13 @@ do_pass:
if (!new_prog) {
/* Only calculating new length. */
- *new_len = new_insn - new_prog;
+ *new_len = new_insn - first_insn;
return 0;
}
pass++;
- if (new_flen != new_insn - new_prog) {
- new_flen = new_insn - new_prog;
+ if (new_flen != new_insn - first_insn) {
+ new_flen = new_insn - first_insn;
if (pass > 2)
goto err;
goto do_pass;
@@ -1017,7 +1025,7 @@ static struct bpf_prog *bpf_migrate_filter(struct bpf_prog *fp)
fp->len = new_len;
/* 2nd pass: remap sock_filter insns into bpf_insn insns. */
- err = bpf_convert_filter(old_prog, old_len, fp->insnsi, &new_len);
+ err = bpf_convert_filter(old_prog, old_len, fp, &new_len);
if (err)
/* 2nd bpf_convert_filter() can fail only if it fails
* to allocate memory, remapping must succeed. Note,
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 28d94bce4df8..fc5fc4594c90 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -18,6 +18,7 @@
#include <linux/stddef.h>
#include <linux/if_ether.h>
#include <linux/mpls.h>
+#include <linux/tcp.h>
#include <net/flow_dissector.h>
#include <scsi/fc/fc_fcoe.h>
@@ -342,6 +343,64 @@ __skb_flow_dissect_gre(const struct sk_buff *skb,
return FLOW_DISSECT_RET_OUT_PROTO_AGAIN;
}
+static void
+__skb_flow_dissect_tcp(const struct sk_buff *skb,
+ struct flow_dissector *flow_dissector,
+ void *target_container, void *data, int thoff, int hlen)
+{
+ struct flow_dissector_key_tcp *key_tcp;
+ struct tcphdr *th, _th;
+
+ if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_TCP))
+ return;
+
+ th = __skb_header_pointer(skb, thoff, sizeof(_th), data, hlen, &_th);
+ if (!th)
+ return;
+
+ if (unlikely(__tcp_hdrlen(th) < sizeof(_th)))
+ return;
+
+ key_tcp = skb_flow_dissector_target(flow_dissector,
+ FLOW_DISSECTOR_KEY_TCP,
+ target_container);
+ key_tcp->flags = (*(__be16 *) &tcp_flag_word(th) & htons(0x0FFF));
+}
+
+static void
+__skb_flow_dissect_ipv4(const struct sk_buff *skb,
+ struct flow_dissector *flow_dissector,
+ void *target_container, void *data, const struct iphdr *iph)
+{
+ struct flow_dissector_key_ip *key_ip;
+
+ if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_IP))
+ return;
+
+ key_ip = skb_flow_dissector_target(flow_dissector,
+ FLOW_DISSECTOR_KEY_IP,
+ target_container);
+ key_ip->tos = iph->tos;
+ key_ip->ttl = iph->ttl;
+}
+
+static void
+__skb_flow_dissect_ipv6(const struct sk_buff *skb,
+ struct flow_dissector *flow_dissector,
+ void *target_container, void *data, const struct ipv6hdr *iph)
+{
+ struct flow_dissector_key_ip *key_ip;
+
+ if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_IP))
+ return;
+
+ key_ip = skb_flow_dissector_target(flow_dissector,
+ FLOW_DISSECTOR_KEY_IP,
+ target_container);
+ key_ip->tos = ipv6_get_dsfield(iph);
+ key_ip->ttl = iph->hop_limit;
+}
+
/**
* __skb_flow_dissect - extract the flow_keys struct and return it
* @skb: sk_buff to extract the flow from, can be NULL if the rest are specified
@@ -444,6 +503,9 @@ ip:
}
}
+ __skb_flow_dissect_ipv4(skb, flow_dissector,
+ target_container, data, iph);
+
if (flags & FLOW_DISSECTOR_F_STOP_AT_L3)
goto out_good;
@@ -489,6 +551,9 @@ ipv6:
goto out_good;
}
+ __skb_flow_dissect_ipv6(skb, flow_dissector,
+ target_container, data, iph);
+
if (flags & FLOW_DISSECTOR_F_STOP_AT_L3)
goto out_good;
@@ -683,6 +748,10 @@ ip_proto_again:
case IPPROTO_MPLS:
proto = htons(ETH_P_MPLS_UC);
goto mpls;
+ case IPPROTO_TCP:
+ __skb_flow_dissect_tcp(skb, flow_dissector, target_container,
+ data, nhoff, hlen);
+ break;
default:
break;
}
diff --git a/net/core/lwt_bpf.c b/net/core/lwt_bpf.c
index b3bc0a31af9f..1307731ddfe4 100644
--- a/net/core/lwt_bpf.c
+++ b/net/core/lwt_bpf.c
@@ -240,7 +240,8 @@ static const struct nla_policy bpf_nl_policy[LWT_BPF_MAX + 1] = {
static int bpf_build_state(struct nlattr *nla,
unsigned int family, const void *cfg,
- struct lwtunnel_state **ts)
+ struct lwtunnel_state **ts,
+ struct netlink_ext_ack *extack)
{
struct nlattr *tb[LWT_BPF_MAX + 1];
struct lwtunnel_state *newts;
@@ -250,7 +251,7 @@ static int bpf_build_state(struct nlattr *nla,
if (family != AF_INET && family != AF_INET6)
return -EAFNOSUPPORT;
- ret = nla_parse_nested(tb, LWT_BPF_MAX, nla, bpf_nl_policy, NULL);
+ ret = nla_parse_nested(tb, LWT_BPF_MAX, nla, bpf_nl_policy, extack);
if (ret < 0)
return ret;
diff --git a/net/core/lwtunnel.c b/net/core/lwtunnel.c
index cfae3d5fe11f..d9cb3532f1dd 100644
--- a/net/core/lwtunnel.c
+++ b/net/core/lwtunnel.c
@@ -103,37 +103,53 @@ EXPORT_SYMBOL(lwtunnel_encap_del_ops);
int lwtunnel_build_state(u16 encap_type,
struct nlattr *encap, unsigned int family,
- const void *cfg, struct lwtunnel_state **lws)
+ const void *cfg, struct lwtunnel_state **lws,
+ struct netlink_ext_ack *extack)
{
const struct lwtunnel_encap_ops *ops;
+ bool found = false;
int ret = -EINVAL;
if (encap_type == LWTUNNEL_ENCAP_NONE ||
- encap_type > LWTUNNEL_ENCAP_MAX)
+ encap_type > LWTUNNEL_ENCAP_MAX) {
+ NL_SET_ERR_MSG_ATTR(extack, encap,
+ "Unknown LWT encapsulation type");
return ret;
+ }
ret = -EOPNOTSUPP;
rcu_read_lock();
ops = rcu_dereference(lwtun_encaps[encap_type]);
if (likely(ops && ops->build_state && try_module_get(ops->owner))) {
- ret = ops->build_state(encap, family, cfg, lws);
+ found = true;
+ ret = ops->build_state(encap, family, cfg, lws, extack);
if (ret)
module_put(ops->owner);
}
rcu_read_unlock();
+ /* don't rely on -EOPNOTSUPP to detect match as build_state
+ * handlers could return it
+ */
+ if (!found) {
+ NL_SET_ERR_MSG_ATTR(extack, encap,
+ "LWT encapsulation type not supported");
+ }
+
return ret;
}
EXPORT_SYMBOL(lwtunnel_build_state);
-int lwtunnel_valid_encap_type(u16 encap_type)
+int lwtunnel_valid_encap_type(u16 encap_type, struct netlink_ext_ack *extack)
{
const struct lwtunnel_encap_ops *ops;
int ret = -EINVAL;
if (encap_type == LWTUNNEL_ENCAP_NONE ||
- encap_type > LWTUNNEL_ENCAP_MAX)
+ encap_type > LWTUNNEL_ENCAP_MAX) {
+ NL_SET_ERR_MSG(extack, "Unknown lwt encapsulation type");
return ret;
+ }
rcu_read_lock();
ops = rcu_dereference(lwtun_encaps[encap_type]);
@@ -153,11 +169,16 @@ int lwtunnel_valid_encap_type(u16 encap_type)
}
}
#endif
- return ops ? 0 : -EOPNOTSUPP;
+ ret = ops ? 0 : -EOPNOTSUPP;
+ if (ret < 0)
+ NL_SET_ERR_MSG(extack, "lwt encapsulation type not supported");
+
+ return ret;
}
EXPORT_SYMBOL(lwtunnel_valid_encap_type);
-int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int remaining)
+int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int remaining,
+ struct netlink_ext_ack *extack)
{
struct rtnexthop *rtnh = (struct rtnexthop *)attr;
struct nlattr *nla_entype;
@@ -174,7 +195,8 @@ int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int remaining)
if (nla_entype) {
encap_type = nla_get_u16(nla_entype);
- if (lwtunnel_valid_encap_type(encap_type) != 0)
+ if (lwtunnel_valid_encap_type(encap_type,
+ extack) != 0)
return -EOPNOTSUPP;
}
}
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index d274f81fcc2c..dadb5eef91c3 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -118,6 +118,50 @@ unsigned long neigh_rand_reach_time(unsigned long base)
EXPORT_SYMBOL(neigh_rand_reach_time);
+static bool neigh_del(struct neighbour *n, __u8 state,
+ struct neighbour __rcu **np, struct neigh_table *tbl)
+{
+ bool retval = false;
+
+ write_lock(&n->lock);
+ if (atomic_read(&n->refcnt) == 1 && !(n->nud_state & state)) {
+ struct neighbour *neigh;
+
+ neigh = rcu_dereference_protected(n->next,
+ lockdep_is_held(&tbl->lock));
+ rcu_assign_pointer(*np, neigh);
+ n->dead = 1;
+ retval = true;
+ }
+ write_unlock(&n->lock);
+ if (retval)
+ neigh_cleanup_and_release(n);
+ return retval;
+}
+
+bool neigh_remove_one(struct neighbour *ndel, struct neigh_table *tbl)
+{
+ struct neigh_hash_table *nht;
+ void *pkey = ndel->primary_key;
+ u32 hash_val;
+ struct neighbour *n;
+ struct neighbour __rcu **np;
+
+ nht = rcu_dereference_protected(tbl->nht,
+ lockdep_is_held(&tbl->lock));
+ hash_val = tbl->hash(pkey, ndel->dev, nht->hash_rnd);
+ hash_val = hash_val >> (32 - nht->hash_shift);
+
+ np = &nht->hash_buckets[hash_val];
+ while ((n = rcu_dereference_protected(*np,
+ lockdep_is_held(&tbl->lock)))) {
+ if (n == ndel)
+ return neigh_del(n, 0, np, tbl);
+ np = &n->next;
+ }
+ return false;
+}
+
static int neigh_forced_gc(struct neigh_table *tbl)
{
int shrunk = 0;
@@ -140,19 +184,10 @@ static int neigh_forced_gc(struct neigh_table *tbl)
* - nobody refers to it.
* - it is not permanent
*/
- write_lock(&n->lock);
- if (atomic_read(&n->refcnt) == 1 &&
- !(n->nud_state & NUD_PERMANENT)) {
- rcu_assign_pointer(*np,
- rcu_dereference_protected(n->next,
- lockdep_is_held(&tbl->lock)));
- n->dead = 1;
- shrunk = 1;
- write_unlock(&n->lock);
- neigh_cleanup_and_release(n);
+ if (neigh_del(n, NUD_PERMANENT, np, tbl)) {
+ shrunk = 1;
continue;
}
- write_unlock(&n->lock);
np = &n->next;
}
}
@@ -1649,7 +1684,10 @@ static int neigh_delete(struct sk_buff *skb, struct nlmsghdr *nlh,
NEIGH_UPDATE_F_OVERRIDE |
NEIGH_UPDATE_F_ADMIN,
NETLINK_CB(skb).portid);
+ write_lock_bh(&tbl->lock);
neigh_release(neigh);
+ neigh_remove_one(neigh, tbl);
+ write_unlock_bh(&tbl->lock);
out:
return err;
diff --git a/net/core/net-procfs.c b/net/core/net-procfs.c
index 14d09345f00d..4847964931df 100644
--- a/net/core/net-procfs.c
+++ b/net/core/net-procfs.c
@@ -363,15 +363,10 @@ static int dev_mc_seq_show(struct seq_file *seq, void *v)
netif_addr_lock_bh(dev);
netdev_for_each_mc_addr(ha, dev) {
- int i;
-
- seq_printf(seq, "%-4d %-15s %-5d %-5d ", dev->ifindex,
- dev->name, ha->refcount, ha->global_use);
-
- for (i = 0; i < dev->addr_len; i++)
- seq_printf(seq, "%02x", ha->addr[i]);
-
- seq_putc(seq, '\n');
+ seq_printf(seq, "%-4d %-15s %-5d %-5d %*phN\n",
+ dev->ifindex, dev->name,
+ ha->refcount, ha->global_use,
+ (int)dev->addr_len, ha->addr);
}
netif_addr_unlock_bh(dev);
return 0;
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 65ea0ff4017c..58e6cc70500d 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -323,7 +323,11 @@ NETDEVICE_SHOW_RW(flags, fmt_hex);
static int change_tx_queue_len(struct net_device *dev, unsigned long new_len)
{
- int res, orig_len = dev->tx_queue_len;
+ unsigned int orig_len = dev->tx_queue_len;
+ int res;
+
+ if (new_len != (unsigned int)new_len)
+ return -ERANGE;
if (new_len != orig_len) {
dev->tx_queue_len = new_len;
@@ -349,7 +353,7 @@ static ssize_t tx_queue_len_store(struct device *dev,
return netdev_store(dev, attr, buf, len, change_tx_queue_len);
}
-NETDEVICE_SHOW_RW(tx_queue_len, fmt_ulong);
+NETDEVICE_SHOW_RW(tx_queue_len, fmt_dec);
static int change_gro_flush_timeout(struct net_device *dev, unsigned long val)
{
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 9e2c0a7cb325..7084f1db2446 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -941,6 +941,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev,
+ nla_total_size(MAX_PHYS_ITEM_ID_LEN) /* IFLA_PHYS_SWITCH_ID */
+ nla_total_size(IFNAMSIZ) /* IFLA_PHYS_PORT_NAME */
+ rtnl_xdp_size() /* IFLA_XDP */
+ + nla_total_size(4) /* IFLA_EVENT */
+ nla_total_size(1); /* IFLA_PROTO_DOWN */
}
@@ -1282,9 +1283,40 @@ err_cancel:
return err;
}
+static u32 rtnl_get_event(unsigned long event)
+{
+ u32 rtnl_event_type = IFLA_EVENT_NONE;
+
+ switch (event) {
+ case NETDEV_REBOOT:
+ rtnl_event_type = IFLA_EVENT_REBOOT;
+ break;
+ case NETDEV_FEAT_CHANGE:
+ rtnl_event_type = IFLA_EVENT_FEATURES;
+ break;
+ case NETDEV_BONDING_FAILOVER:
+ rtnl_event_type = IFLA_EVENT_BONDING_FAILOVER;
+ break;
+ case NETDEV_NOTIFY_PEERS:
+ rtnl_event_type = IFLA_EVENT_NOTIFY_PEERS;
+ break;
+ case NETDEV_RESEND_IGMP:
+ rtnl_event_type = IFLA_EVENT_IGMP_RESEND;
+ break;
+ case NETDEV_CHANGEINFODATA:
+ rtnl_event_type = IFLA_EVENT_BONDING_OPTIONS;
+ break;
+ default:
+ break;
+ }
+
+ return rtnl_event_type;
+}
+
static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
int type, u32 pid, u32 seq, u32 change,
- unsigned int flags, u32 ext_filter_mask)
+ unsigned int flags, u32 ext_filter_mask,
+ u32 event)
{
struct ifinfomsg *ifm;
struct nlmsghdr *nlh;
@@ -1333,6 +1365,11 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
nla_put_u8(skb, IFLA_PROTO_DOWN, dev->proto_down))
goto nla_put_failure;
+ if (event != IFLA_EVENT_NONE) {
+ if (nla_put_u32(skb, IFLA_EVENT, event))
+ goto nla_put_failure;
+ }
+
if (rtnl_fill_link_ifmap(skb, dev))
goto nla_put_failure;
@@ -1467,6 +1504,7 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = {
[IFLA_LINK_NETNSID] = { .type = NLA_S32 },
[IFLA_PROTO_DOWN] = { .type = NLA_U8 },
[IFLA_XDP] = { .type = NLA_NESTED },
+ [IFLA_EVENT] = { .type = NLA_U32 },
};
static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = {
@@ -1626,7 +1664,7 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq, 0,
flags,
- ext_filter_mask);
+ ext_filter_mask, 0);
if (err < 0) {
if (likely(skb->len))
@@ -2048,8 +2086,8 @@ static int do_setlink(const struct sk_buff *skb,
}
if (tb[IFLA_TXQLEN]) {
- unsigned long value = nla_get_u32(tb[IFLA_TXQLEN]);
- unsigned long orig_len = dev->tx_queue_len;
+ unsigned int value = nla_get_u32(tb[IFLA_TXQLEN]);
+ unsigned int orig_len = dev->tx_queue_len;
if (dev->tx_queue_len ^ value) {
dev->tx_queue_len = value;
@@ -2736,7 +2774,7 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr *nlh,
return -ENOBUFS;
err = rtnl_fill_ifinfo(nskb, dev, RTM_NEWLINK, NETLINK_CB(skb).portid,
- nlh->nlmsg_seq, 0, 0, ext_filter_mask);
+ nlh->nlmsg_seq, 0, 0, ext_filter_mask, 0);
if (err < 0) {
/* -EMSGSIZE implies BUG in if_nlmsg_size */
WARN_ON(err == -EMSGSIZE);
@@ -2808,7 +2846,8 @@ static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb)
}
struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev,
- unsigned int change, gfp_t flags)
+ unsigned int change,
+ u32 event, gfp_t flags)
{
struct net *net = dev_net(dev);
struct sk_buff *skb;
@@ -2819,7 +2858,7 @@ struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev,
if (skb == NULL)
goto errout;
- err = rtnl_fill_ifinfo(skb, dev, type, 0, 0, change, 0, 0);
+ err = rtnl_fill_ifinfo(skb, dev, type, 0, 0, change, 0, 0, event);
if (err < 0) {
/* -EMSGSIZE implies BUG in if_nlmsg_size() */
WARN_ON(err == -EMSGSIZE);
@@ -2840,18 +2879,25 @@ void rtmsg_ifinfo_send(struct sk_buff *skb, struct net_device *dev, gfp_t flags)
rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, flags);
}
-void rtmsg_ifinfo(int type, struct net_device *dev, unsigned int change,
- gfp_t flags)
+static void rtmsg_ifinfo_event(int type, struct net_device *dev,
+ unsigned int change, u32 event,
+ gfp_t flags)
{
struct sk_buff *skb;
if (dev->reg_state != NETREG_REGISTERED)
return;
- skb = rtmsg_ifinfo_build_skb(type, dev, change, flags);
+ skb = rtmsg_ifinfo_build_skb(type, dev, change, event, flags);
if (skb)
rtmsg_ifinfo_send(skb, dev, flags);
}
+
+void rtmsg_ifinfo(int type, struct net_device *dev, unsigned int change,
+ gfp_t flags)
+{
+ rtmsg_ifinfo_event(type, dev, change, rtnl_get_event(0), flags);
+}
EXPORT_SYMBOL(rtmsg_ifinfo);
static int nlmsg_populate_fdb_fill(struct sk_buff *skb,
@@ -4168,7 +4214,8 @@ static int rtnetlink_event(struct notifier_block *this, unsigned long event, voi
case NETDEV_NOTIFY_PEERS:
case NETDEV_RESEND_IGMP:
case NETDEV_CHANGEINFODATA:
- rtmsg_ifinfo(RTM_NEWLINK, dev, 0, GFP_KERNEL);
+ rtmsg_ifinfo_event(RTM_NEWLINK, dev, 0, rtnl_get_event(event),
+ GFP_KERNEL);
break;
default:
break;
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index b1be7c01efe2..82cfc9c7a090 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -2243,6 +2243,32 @@ __wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset,
}
EXPORT_SYMBOL(skb_copy_and_csum_bits);
+static __wsum warn_crc32c_csum_update(const void *buff, int len, __wsum sum)
+{
+ net_warn_ratelimited(
+ "%s: attempt to compute crc32c without libcrc32c.ko\n",
+ __func__);
+ return 0;
+}
+
+static __wsum warn_crc32c_csum_combine(__wsum csum, __wsum csum2,
+ int offset, int len)
+{
+ net_warn_ratelimited(
+ "%s: attempt to compute crc32c without libcrc32c.ko\n",
+ __func__);
+ return 0;
+}
+
+static const struct skb_checksum_ops default_crc32c_ops = {
+ .update = warn_crc32c_csum_update,
+ .combine = warn_crc32c_csum_combine,
+};
+
+const struct skb_checksum_ops *crc32c_csum_stub __read_mostly =
+ &default_crc32c_ops;
+EXPORT_SYMBOL(crc32c_csum_stub);
+
/**
* skb_zerocopy_headlen - Calculate headroom needed for skb_zerocopy()
* @from: source buffer
@@ -3482,24 +3508,18 @@ void __init skb_init(void)
NULL);
}
-/**
- * skb_to_sgvec - Fill a scatter-gather list from a socket buffer
- * @skb: Socket buffer containing the buffers to be mapped
- * @sg: The scatter-gather list to map into
- * @offset: The offset into the buffer's contents to start mapping
- * @len: Length of buffer space to be mapped
- *
- * Fill the specified scatter-gather list with mappings/pointers into a
- * region of the buffer space attached to a socket buffer.
- */
static int
-__skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len)
+__skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len,
+ unsigned int recursion_level)
{
int start = skb_headlen(skb);
int i, copy = start - offset;
struct sk_buff *frag_iter;
int elt = 0;
+ if (unlikely(recursion_level >= 24))
+ return -EMSGSIZE;
+
if (copy > 0) {
if (copy > len)
copy = len;
@@ -3518,6 +3538,8 @@ __skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len)
end = start + skb_frag_size(&skb_shinfo(skb)->frags[i]);
if ((copy = end - offset) > 0) {
skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
+ if (unlikely(elt && sg_is_last(&sg[elt - 1])))
+ return -EMSGSIZE;
if (copy > len)
copy = len;
@@ -3532,16 +3554,22 @@ __skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len)
}
skb_walk_frags(skb, frag_iter) {
- int end;
+ int end, ret;
WARN_ON(start > offset + len);
end = start + frag_iter->len;
if ((copy = end - offset) > 0) {
+ if (unlikely(elt && sg_is_last(&sg[elt - 1])))
+ return -EMSGSIZE;
+
if (copy > len)
copy = len;
- elt += __skb_to_sgvec(frag_iter, sg+elt, offset - start,
- copy);
+ ret = __skb_to_sgvec(frag_iter, sg+elt, offset - start,
+ copy, recursion_level + 1);
+ if (unlikely(ret < 0))
+ return ret;
+ elt += ret;
if ((len -= copy) == 0)
return elt;
offset += copy;
@@ -3552,6 +3580,31 @@ __skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len)
return elt;
}
+/**
+ * skb_to_sgvec - Fill a scatter-gather list from a socket buffer
+ * @skb: Socket buffer containing the buffers to be mapped
+ * @sg: The scatter-gather list to map into
+ * @offset: The offset into the buffer's contents to start mapping
+ * @len: Length of buffer space to be mapped
+ *
+ * Fill the specified scatter-gather list with mappings/pointers into a
+ * region of the buffer space attached to a socket buffer. Returns either
+ * the number of scatterlist items used, or -EMSGSIZE if the contents
+ * could not fit.
+ */
+int skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len)
+{
+ int nsg = __skb_to_sgvec(skb, sg, offset, len, 0);
+
+ if (nsg <= 0)
+ return nsg;
+
+ sg_mark_end(&sg[nsg - 1]);
+
+ return nsg;
+}
+EXPORT_SYMBOL_GPL(skb_to_sgvec);
+
/* As compared with skb_to_sgvec, skb_to_sgvec_nomark only map skb to given
* sglist without mark the sg which contain last skb data as the end.
* So the caller can mannipulate sg list as will when padding new data after
@@ -3574,19 +3627,11 @@ __skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len)
int skb_to_sgvec_nomark(struct sk_buff *skb, struct scatterlist *sg,
int offset, int len)
{
- return __skb_to_sgvec(skb, sg, offset, len);
+ return __skb_to_sgvec(skb, sg, offset, len, 0);
}
EXPORT_SYMBOL_GPL(skb_to_sgvec_nomark);
-int skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len)
-{
- int nsg = __skb_to_sgvec(skb, sg, offset, len);
- sg_mark_end(&sg[nsg - 1]);
-
- return nsg;
-}
-EXPORT_SYMBOL_GPL(skb_to_sgvec);
/**
* skb_cow_data - Check that a socket buffer's data buffers are writable
@@ -3878,6 +3923,10 @@ void __skb_tstamp_tx(struct sk_buff *orig_skb,
if (!sk)
return;
+ if (!hwtstamps && !(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_TX_SWHW) &&
+ skb_shinfo(orig_skb)->tx_flags & SKBTX_IN_PROGRESS)
+ return;
+
tsonly = sk->sk_tsflags & SOF_TIMESTAMPING_OPT_TSONLY;
if (!skb_may_tx_timestamp(sk, tsonly))
return;
diff --git a/net/core/sock.c b/net/core/sock.c
index 727f924b7f91..bef844127e01 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1038,6 +1038,10 @@ set_rcvbuf:
#endif
case SO_MAX_PACING_RATE:
+ if (val != ~0U)
+ cmpxchg(&sk->sk_pacing_status,
+ SK_PACING_NONE,
+ SK_PACING_NEEDED);
sk->sk_max_pacing_rate = val;
sk->sk_pacing_rate = min(sk->sk_pacing_rate,
sk->sk_max_pacing_rate);
generated by cgit v1.2.3 (git 2.39.1) at 2024-11-23 08:45:48 +0000