summaryrefslogtreecommitdiff
path: root/net/core
diff options
context:
space:
mode:
Diffstat (limited to 'net/core')
-rw-r--r--net/core/datagram.c77
-rw-r--r--net/core/dev.c332
-rw-r--r--net/core/ethtool.c4
-rw-r--r--net/core/net-sysfs.c1
-rw-r--r--net/core/net-traces.c4
-rw-r--r--net/core/netclassid_cgroup.c11
-rw-r--r--net/core/netprio_cgroup.c19
-rw-r--r--net/core/pktgen.c4
-rw-r--r--net/core/rtnetlink.c18
-rw-r--r--net/core/scm.c4
-rw-r--r--net/core/sock.c25
-rw-r--r--net/core/sock_diag.c23
-rw-r--r--net/core/stream.c2
13 files changed, 405 insertions, 119 deletions
diff --git a/net/core/datagram.c b/net/core/datagram.c
index d62af69ad844..fa9dc6450b08 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -83,8 +83,8 @@ static int receiver_wake_function(wait_queue_t *wait, unsigned int mode, int syn
/*
* Wait for the last received packet to be different from skb
*/
-static int wait_for_more_packets(struct sock *sk, int *err, long *timeo_p,
- const struct sk_buff *skb)
+int __skb_wait_for_more_packets(struct sock *sk, int *err, long *timeo_p,
+ const struct sk_buff *skb)
{
int error;
DEFINE_WAIT_FUNC(wait, receiver_wake_function);
@@ -130,6 +130,7 @@ out_noerr:
error = 1;
goto out;
}
+EXPORT_SYMBOL(__skb_wait_for_more_packets);
static struct sk_buff *skb_set_peeked(struct sk_buff *skb)
{
@@ -161,13 +162,15 @@ done:
}
/**
- * __skb_recv_datagram - Receive a datagram skbuff
+ * __skb_try_recv_datagram - Receive a datagram skbuff
* @sk: socket
* @flags: MSG_ flags
* @peeked: returns non-zero if this packet has been seen before
* @off: an offset in bytes to peek skb from. Returns an offset
* within an skb where data actually starts
* @err: error code returned
+ * @last: set to last peeked message to inform the wait function
+ * what to look for when peeking
*
* Get a datagram skbuff, understands the peeking, nonblocking wakeups
* and possible races. This replaces identical code in packet, raw and
@@ -175,9 +178,11 @@ done:
* the long standing peek and read race for datagram sockets. If you
* alter this routine remember it must be re-entrant.
*
- * This function will lock the socket if a skb is returned, so the caller
- * needs to unlock the socket in that case (usually by calling
- * skb_free_datagram)
+ * This function will lock the socket if a skb is returned, so
+ * the caller needs to unlock the socket in that case (usually by
+ * calling skb_free_datagram). Returns NULL with *err set to
+ * -EAGAIN if no data was available or to some other value if an
+ * error was detected.
*
* * It does not lock socket since today. This function is
* * free of race conditions. This measure should/can improve
@@ -191,13 +196,13 @@ done:
* quite explicitly by POSIX 1003.1g, don't change them without having
* the standard around please.
*/
-struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned int flags,
- int *peeked, int *off, int *err)
+struct sk_buff *__skb_try_recv_datagram(struct sock *sk, unsigned int flags,
+ int *peeked, int *off, int *err,
+ struct sk_buff **last)
{
struct sk_buff_head *queue = &sk->sk_receive_queue;
- struct sk_buff *skb, *last;
+ struct sk_buff *skb;
unsigned long cpu_flags;
- long timeo;
/*
* Caller is allowed not to check sk->sk_err before skb_recv_datagram()
*/
@@ -206,8 +211,6 @@ struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned int flags,
if (error)
goto no_packet;
- timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
-
do {
/* Again only user level code calls this function, so nothing
* interrupt level will suddenly eat the receive_queue.
@@ -217,10 +220,10 @@ struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned int flags,
*/
int _off = *off;
- last = (struct sk_buff *)queue;
+ *last = (struct sk_buff *)queue;
spin_lock_irqsave(&queue->lock, cpu_flags);
skb_queue_walk(queue, skb) {
- last = skb;
+ *last = skb;
*peeked = skb->peeked;
if (flags & MSG_PEEK) {
if (_off >= skb->len && (skb->len || _off ||
@@ -231,8 +234,11 @@ struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned int flags,
skb = skb_set_peeked(skb);
error = PTR_ERR(skb);
- if (IS_ERR(skb))
- goto unlock_err;
+ if (IS_ERR(skb)) {
+ spin_unlock_irqrestore(&queue->lock,
+ cpu_flags);
+ goto no_packet;
+ }
atomic_inc(&skb->users);
} else
@@ -242,25 +248,38 @@ struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned int flags,
*off = _off;
return skb;
}
+
spin_unlock_irqrestore(&queue->lock, cpu_flags);
+ } while (sk_can_busy_loop(sk) &&
+ sk_busy_loop(sk, flags & MSG_DONTWAIT));
- if (sk_can_busy_loop(sk) &&
- sk_busy_loop(sk, flags & MSG_DONTWAIT))
- continue;
+ error = -EAGAIN;
- /* User doesn't want to wait */
- error = -EAGAIN;
- if (!timeo)
- goto no_packet;
+no_packet:
+ *err = error;
+ return NULL;
+}
+EXPORT_SYMBOL(__skb_try_recv_datagram);
- } while (!wait_for_more_packets(sk, err, &timeo, last));
+struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned int flags,
+ int *peeked, int *off, int *err)
+{
+ struct sk_buff *skb, *last;
+ long timeo;
- return NULL;
+ timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
+
+ do {
+ skb = __skb_try_recv_datagram(sk, flags, peeked, off, err,
+ &last);
+ if (skb)
+ return skb;
+
+ if (*err != -EAGAIN)
+ break;
+ } while (timeo &&
+ !__skb_wait_for_more_packets(sk, err, &timeo, last));
-unlock_err:
- spin_unlock_irqrestore(&queue->lock, cpu_flags);
-no_packet:
- *err = error;
return NULL;
}
EXPORT_SYMBOL(__skb_recv_datagram);
diff --git a/net/core/dev.c b/net/core/dev.c
index ae00b894e675..914b4a24c654 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -96,6 +96,7 @@
#include <linux/skbuff.h>
#include <net/net_namespace.h>
#include <net/sock.h>
+#include <net/busy_poll.h>
#include <linux/rtnetlink.h>
#include <linux/stat.h>
#include <net/dst.h>
@@ -137,6 +138,7 @@
#include <linux/errqueue.h>
#include <linux/hrtimer.h>
#include <linux/netfilter_ingress.h>
+#include <linux/sctp.h>
#include "net-sysfs.h"
@@ -182,8 +184,8 @@ EXPORT_SYMBOL(dev_base_lock);
/* protects napi_hash addition/deletion and napi_gen_id */
static DEFINE_SPINLOCK(napi_hash_lock);
-static unsigned int napi_gen_id;
-static DEFINE_HASHTABLE(napi_hash, 8);
+static unsigned int napi_gen_id = NR_CPUS;
+static DEFINE_READ_MOSTLY_HASHTABLE(napi_hash, 8);
static seqcount_t devnet_rename_seq;
@@ -2470,6 +2472,141 @@ out:
}
EXPORT_SYMBOL(skb_checksum_help);
+/* skb_csum_offload_check - Driver helper function to determine if a device
+ * with limited checksum offload capabilities is able to offload the checksum
+ * for a given packet.
+ *
+ * Arguments:
+ * skb - sk_buff for the packet in question
+ * spec - contains the description of what device can offload
+ * csum_encapped - returns true if the checksum being offloaded is
+ * encpasulated. That is it is checksum for the transport header
+ * in the inner headers.
+ * checksum_help - when set indicates that helper function should
+ * call skb_checksum_help if offload checks fail
+ *
+ * Returns:
+ * true: Packet has passed the checksum checks and should be offloadable to
+ * the device (a driver may still need to check for additional
+ * restrictions of its device)
+ * false: Checksum is not offloadable. If checksum_help was set then
+ * skb_checksum_help was called to resolve checksum for non-GSO
+ * packets and when IP protocol is not SCTP
+ */
+bool __skb_csum_offload_chk(struct sk_buff *skb,
+ const struct skb_csum_offl_spec *spec,
+ bool *csum_encapped,
+ bool csum_help)
+{
+ struct iphdr *iph;
+ struct ipv6hdr *ipv6;
+ void *nhdr;
+ int protocol;
+ u8 ip_proto;
+
+ if (skb->protocol == htons(ETH_P_8021Q) ||
+ skb->protocol == htons(ETH_P_8021AD)) {
+ if (!spec->vlan_okay)
+ goto need_help;
+ }
+
+ /* We check whether the checksum refers to a transport layer checksum in
+ * the outermost header or an encapsulated transport layer checksum that
+ * corresponds to the inner headers of the skb. If the checksum is for
+ * something else in the packet we need help.
+ */
+ if (skb_checksum_start_offset(skb) == skb_transport_offset(skb)) {
+ /* Non-encapsulated checksum */
+ protocol = eproto_to_ipproto(vlan_get_protocol(skb));
+ nhdr = skb_network_header(skb);
+ *csum_encapped = false;
+ if (spec->no_not_encapped)
+ goto need_help;
+ } else if (skb->encapsulation && spec->encap_okay &&
+ skb_checksum_start_offset(skb) ==
+ skb_inner_transport_offset(skb)) {
+ /* Encapsulated checksum */
+ *csum_encapped = true;
+ switch (skb->inner_protocol_type) {
+ case ENCAP_TYPE_ETHER:
+ protocol = eproto_to_ipproto(skb->inner_protocol);
+ break;
+ case ENCAP_TYPE_IPPROTO:
+ protocol = skb->inner_protocol;
+ break;
+ }
+ nhdr = skb_inner_network_header(skb);
+ } else {
+ goto need_help;
+ }
+
+ switch (protocol) {
+ case IPPROTO_IP:
+ if (!spec->ipv4_okay)
+ goto need_help;
+ iph = nhdr;
+ ip_proto = iph->protocol;
+ if (iph->ihl != 5 && !spec->ip_options_okay)
+ goto need_help;
+ break;
+ case IPPROTO_IPV6:
+ if (!spec->ipv6_okay)
+ goto need_help;
+ if (spec->no_encapped_ipv6 && *csum_encapped)
+ goto need_help;
+ ipv6 = nhdr;
+ nhdr += sizeof(*ipv6);
+ ip_proto = ipv6->nexthdr;
+ break;
+ default:
+ goto need_help;
+ }
+
+ip_proto_again:
+ switch (ip_proto) {
+ case IPPROTO_TCP:
+ if (!spec->tcp_okay ||
+ skb->csum_offset != offsetof(struct tcphdr, check))
+ goto need_help;
+ break;
+ case IPPROTO_UDP:
+ if (!spec->udp_okay ||
+ skb->csum_offset != offsetof(struct udphdr, check))
+ goto need_help;
+ break;
+ case IPPROTO_SCTP:
+ if (!spec->sctp_okay ||
+ skb->csum_offset != offsetof(struct sctphdr, checksum))
+ goto cant_help;
+ break;
+ case NEXTHDR_HOP:
+ case NEXTHDR_ROUTING:
+ case NEXTHDR_DEST: {
+ u8 *opthdr = nhdr;
+
+ if (protocol != IPPROTO_IPV6 || !spec->ext_hdrs_okay)
+ goto need_help;
+
+ ip_proto = opthdr[0];
+ nhdr += (opthdr[1] + 1) << 3;
+
+ goto ip_proto_again;
+ }
+ default:
+ goto need_help;
+ }
+
+ /* Passed the tests for offloading checksum */
+ return true;
+
+need_help:
+ if (csum_help && !skb_shinfo(skb)->gso_size)
+ skb_checksum_help(skb);
+cant_help:
+ return false;
+}
+EXPORT_SYMBOL(__skb_csum_offload_chk);
+
__be16 skb_network_protocol(struct sk_buff *skb, int *depth)
{
__be16 type = skb->protocol;
@@ -2644,7 +2781,7 @@ static netdev_features_t harmonize_features(struct sk_buff *skb,
if (skb->ip_summed != CHECKSUM_NONE &&
!can_checksum_protocol(features, type)) {
- features &= ~NETIF_F_ALL_CSUM;
+ features &= ~NETIF_F_CSUM_MASK;
} else if (illegal_highdma(skb->dev, skb)) {
features &= ~NETIF_F_SG;
}
@@ -2791,7 +2928,7 @@ 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_ALL_CSUM) &&
+ if (!(features & NETIF_F_CSUM_MASK) &&
skb_checksum_help(skb))
goto out_kfree_skb;
}
@@ -2928,7 +3065,8 @@ static void skb_update_prio(struct sk_buff *skb)
struct netprio_map *map = rcu_dereference_bh(skb->dev->priomap);
if (!skb->priority && skb->sk && map) {
- unsigned int prioidx = skb->sk->sk_cgrp_prioidx;
+ unsigned int prioidx =
+ sock_cgroup_prioidx(&skb->sk->sk_cgrp_data);
if (prioidx < map->priomap_len)
skb->priority = map->priomap[prioidx];
@@ -3021,7 +3159,9 @@ struct netdev_queue *netdev_pick_tx(struct net_device *dev,
int queue_index = 0;
#ifdef CONFIG_XPS
- if (skb->sender_cpu == 0)
+ u32 sender_cpu = skb->sender_cpu - 1;
+
+ if (sender_cpu >= (u32)NR_CPUS)
skb->sender_cpu = raw_smp_processor_id() + 1;
#endif
@@ -4353,6 +4493,7 @@ static gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb)
gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
{
+ skb_mark_napi_id(skb, napi);
trace_napi_gro_receive_entry(skb);
skb_gro_reset_offset(skb);
@@ -4386,7 +4527,10 @@ struct sk_buff *napi_get_frags(struct napi_struct *napi)
if (!skb) {
skb = napi_alloc_skb(napi, GRO_MAX_HEAD);
- napi->skb = skb;
+ if (skb) {
+ napi->skb = skb;
+ skb_mark_napi_id(skb, napi);
+ }
}
return skb;
}
@@ -4661,7 +4805,7 @@ void napi_complete_done(struct napi_struct *n, int work_done)
EXPORT_SYMBOL(napi_complete_done);
/* must be called under rcu_read_lock(), as we dont take a reference */
-struct napi_struct *napi_by_id(unsigned int napi_id)
+static struct napi_struct *napi_by_id(unsigned int napi_id)
{
unsigned int hash = napi_id % HASH_SIZE(napi_hash);
struct napi_struct *napi;
@@ -4672,43 +4816,101 @@ struct napi_struct *napi_by_id(unsigned int napi_id)
return NULL;
}
-EXPORT_SYMBOL_GPL(napi_by_id);
-void napi_hash_add(struct napi_struct *napi)
+#if defined(CONFIG_NET_RX_BUSY_POLL)
+#define BUSY_POLL_BUDGET 8
+bool sk_busy_loop(struct sock *sk, int nonblock)
{
- if (!test_and_set_bit(NAPI_STATE_HASHED, &napi->state)) {
+ unsigned long end_time = !nonblock ? sk_busy_loop_end_time(sk) : 0;
+ int (*busy_poll)(struct napi_struct *dev);
+ struct napi_struct *napi;
+ int rc = false;
- spin_lock(&napi_hash_lock);
+ rcu_read_lock();
- /* 0 is not a valid id, we also skip an id that is taken
- * we expect both events to be extremely rare
- */
- napi->napi_id = 0;
- while (!napi->napi_id) {
- napi->napi_id = ++napi_gen_id;
- if (napi_by_id(napi->napi_id))
- napi->napi_id = 0;
+ napi = napi_by_id(sk->sk_napi_id);
+ if (!napi)
+ goto out;
+
+ /* Note: ndo_busy_poll method is optional in linux-4.5 */
+ busy_poll = napi->dev->netdev_ops->ndo_busy_poll;
+
+ do {
+ rc = 0;
+ local_bh_disable();
+ if (busy_poll) {
+ rc = busy_poll(napi);
+ } else if (napi_schedule_prep(napi)) {
+ void *have = netpoll_poll_lock(napi);
+
+ if (test_bit(NAPI_STATE_SCHED, &napi->state)) {
+ rc = napi->poll(napi, BUSY_POLL_BUDGET);
+ trace_napi_poll(napi);
+ if (rc == BUSY_POLL_BUDGET) {
+ napi_complete_done(napi, rc);
+ napi_schedule(napi);
+ }
+ }
+ netpoll_poll_unlock(have);
}
+ if (rc > 0)
+ NET_ADD_STATS_BH(sock_net(sk),
+ LINUX_MIB_BUSYPOLLRXPACKETS, rc);
+ local_bh_enable();
- hlist_add_head_rcu(&napi->napi_hash_node,
- &napi_hash[napi->napi_id % HASH_SIZE(napi_hash)]);
+ if (rc == LL_FLUSH_FAILED)
+ break; /* permanent failure */
- spin_unlock(&napi_hash_lock);
- }
+ cpu_relax();
+ } while (!nonblock && skb_queue_empty(&sk->sk_receive_queue) &&
+ !need_resched() && !busy_loop_timeout(end_time));
+
+ rc = !skb_queue_empty(&sk->sk_receive_queue);
+out:
+ rcu_read_unlock();
+ return rc;
+}
+EXPORT_SYMBOL(sk_busy_loop);
+
+#endif /* CONFIG_NET_RX_BUSY_POLL */
+
+void napi_hash_add(struct napi_struct *napi)
+{
+ if (test_bit(NAPI_STATE_NO_BUSY_POLL, &napi->state) ||
+ test_and_set_bit(NAPI_STATE_HASHED, &napi->state))
+ return;
+
+ spin_lock(&napi_hash_lock);
+
+ /* 0..NR_CPUS+1 range is reserved for sender_cpu use */
+ do {
+ if (unlikely(++napi_gen_id < NR_CPUS + 1))
+ napi_gen_id = NR_CPUS + 1;
+ } while (napi_by_id(napi_gen_id));
+ napi->napi_id = napi_gen_id;
+
+ hlist_add_head_rcu(&napi->napi_hash_node,
+ &napi_hash[napi->napi_id % HASH_SIZE(napi_hash)]);
+
+ spin_unlock(&napi_hash_lock);
}
EXPORT_SYMBOL_GPL(napi_hash_add);
/* Warning : caller is responsible to make sure rcu grace period
* is respected before freeing memory containing @napi
*/
-void napi_hash_del(struct napi_struct *napi)
+bool napi_hash_del(struct napi_struct *napi)
{
+ bool rcu_sync_needed = false;
+
spin_lock(&napi_hash_lock);
- if (test_and_clear_bit(NAPI_STATE_HASHED, &napi->state))
+ if (test_and_clear_bit(NAPI_STATE_HASHED, &napi->state)) {
+ rcu_sync_needed = true;
hlist_del_rcu(&napi->napi_hash_node);
-
+ }
spin_unlock(&napi_hash_lock);
+ return rcu_sync_needed;
}
EXPORT_SYMBOL_GPL(napi_hash_del);
@@ -4744,6 +4946,7 @@ void netif_napi_add(struct net_device *dev, struct napi_struct *napi,
napi->poll_owner = -1;
#endif
set_bit(NAPI_STATE_SCHED, &napi->state);
+ napi_hash_add(napi);
}
EXPORT_SYMBOL(netif_napi_add);
@@ -4763,8 +4966,12 @@ void napi_disable(struct napi_struct *n)
}
EXPORT_SYMBOL(napi_disable);
+/* Must be called in process context */
void netif_napi_del(struct napi_struct *napi)
{
+ might_sleep();
+ if (napi_hash_del(napi))
+ synchronize_net();
list_del_init(&napi->dev_list);
napi_free_frags(napi);
@@ -5351,7 +5558,7 @@ static void __netdev_adjacent_dev_unlink_neighbour(struct net_device *dev,
static int __netdev_upper_dev_link(struct net_device *dev,
struct net_device *upper_dev, bool master,
- void *private)
+ void *upper_priv, void *upper_info)
{
struct netdev_notifier_changeupper_info changeupper_info;
struct netdev_adjacent *i, *j, *to_i, *to_j;
@@ -5375,6 +5582,7 @@ static int __netdev_upper_dev_link(struct net_device *dev,
changeupper_info.upper_dev = upper_dev;
changeupper_info.master = master;
changeupper_info.linking = true;
+ changeupper_info.upper_info = upper_info;
ret = call_netdevice_notifiers_info(NETDEV_PRECHANGEUPPER, dev,
&changeupper_info.info);
@@ -5382,7 +5590,7 @@ static int __netdev_upper_dev_link(struct net_device *dev,
if (ret)
return ret;
- ret = __netdev_adjacent_dev_link_neighbour(dev, upper_dev, private,
+ ret = __netdev_adjacent_dev_link_neighbour(dev, upper_dev, upper_priv,
master);
if (ret)
return ret;
@@ -5420,8 +5628,12 @@ static int __netdev_upper_dev_link(struct net_device *dev,
goto rollback_lower_mesh;
}
- call_netdevice_notifiers_info(NETDEV_CHANGEUPPER, dev,
- &changeupper_info.info);
+ ret = call_netdevice_notifiers_info(NETDEV_CHANGEUPPER, dev,
+ &changeupper_info.info);
+ ret = notifier_to_errno(ret);
+ if (ret)
+ goto rollback_lower_mesh;
+
return 0;
rollback_lower_mesh:
@@ -5475,7 +5687,7 @@ rollback_mesh:
int netdev_upper_dev_link(struct net_device *dev,
struct net_device *upper_dev)
{
- return __netdev_upper_dev_link(dev, upper_dev, false, NULL);
+ return __netdev_upper_dev_link(dev, upper_dev, false, NULL, NULL);
}
EXPORT_SYMBOL(netdev_upper_dev_link);
@@ -5483,6 +5695,8 @@ EXPORT_SYMBOL(netdev_upper_dev_link);
* netdev_master_upper_dev_link - Add a master link to the upper device
* @dev: device
* @upper_dev: new upper device
+ * @upper_priv: upper device private
+ * @upper_info: upper info to be passed down via notifier
*
* Adds a link to device which is upper to this one. In this case, only
* one master upper device can be linked, although other non-master devices
@@ -5491,20 +5705,14 @@ EXPORT_SYMBOL(netdev_upper_dev_link);
* counts are adjusted and the function returns zero.
*/
int netdev_master_upper_dev_link(struct net_device *dev,
- struct net_device *upper_dev)
+ struct net_device *upper_dev,
+ void *upper_priv, void *upper_info)
{
- return __netdev_upper_dev_link(dev, upper_dev, true, NULL);
+ return __netdev_upper_dev_link(dev, upper_dev, true,
+ upper_priv, upper_info);
}
EXPORT_SYMBOL(netdev_master_upper_dev_link);
-int netdev_master_upper_dev_link_private(struct net_device *dev,
- struct net_device *upper_dev,
- void *private)
-{
- return __netdev_upper_dev_link(dev, upper_dev, true, private);
-}
-EXPORT_SYMBOL(netdev_master_upper_dev_link_private);
-
/**
* netdev_upper_dev_unlink - Removes a link to upper device
* @dev: device
@@ -5663,7 +5871,7 @@ EXPORT_SYMBOL(netdev_lower_dev_get_private);
int dev_get_nest_level(struct net_device *dev,
- bool (*type_check)(struct net_device *dev))
+ bool (*type_check)(const struct net_device *dev))
{
struct net_device *lower = NULL;
struct list_head *iter;
@@ -5685,6 +5893,26 @@ int dev_get_nest_level(struct net_device *dev,
}
EXPORT_SYMBOL(dev_get_nest_level);
+/**
+ * netdev_lower_change - Dispatch event about lower device state change
+ * @lower_dev: device
+ * @lower_state_info: state to dispatch
+ *
+ * Send NETDEV_CHANGELOWERSTATE to netdev notifiers with info.
+ * The caller must hold the RTNL lock.
+ */
+void netdev_lower_state_changed(struct net_device *lower_dev,
+ void *lower_state_info)
+{
+ struct netdev_notifier_changelowerstate_info changelowerstate_info;
+
+ ASSERT_RTNL();
+ changelowerstate_info.lower_state_info = lower_state_info;
+ call_netdevice_notifiers_info(NETDEV_CHANGELOWERSTATE, lower_dev,
+ &changelowerstate_info.info);
+}
+EXPORT_SYMBOL(netdev_lower_state_changed);
+
static void dev_change_rx_flags(struct net_device *dev, int flags)
{
const struct net_device_ops *ops = dev->netdev_ops;
@@ -6375,9 +6603,9 @@ static netdev_features_t netdev_fix_features(struct net_device *dev,
/* UFO needs SG and checksumming */
if (features & NETIF_F_UFO) {
/* maybe split UFO into V4 and V6? */
- if (!((features & NETIF_F_GEN_CSUM) ||
- (features & (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM))
- == (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM))) {
+ if (!(features & NETIF_F_HW_CSUM) &&
+ ((features & (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM)) !=
+ (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM))) {
netdev_dbg(dev,
"Dropping NETIF_F_UFO since no checksum offload features.\n");
features &= ~NETIF_F_UFO;
@@ -7164,11 +7392,13 @@ EXPORT_SYMBOL(alloc_netdev_mqs);
* This function does the last stage of destroying an allocated device
* interface. The reference to the device object is released.
* If this is the last reference then it will be freed.
+ * Must be called in process context.
*/
void free_netdev(struct net_device *dev)
{
struct napi_struct *p, *n;
+ might_sleep();
netif_free_tx_queues(dev);
#ifdef CONFIG_SYSFS
kvfree(dev->_rx);
@@ -7477,16 +7707,16 @@ static int dev_cpu_callback(struct notifier_block *nfb,
netdev_features_t netdev_increment_features(netdev_features_t all,
netdev_features_t one, netdev_features_t mask)
{
- if (mask & NETIF_F_GEN_CSUM)
- mask |= NETIF_F_ALL_CSUM;
+ if (mask & NETIF_F_HW_CSUM)
+ mask |= NETIF_F_CSUM_MASK;
mask |= NETIF_F_VLAN_CHALLENGED;
- all |= one & (NETIF_F_ONE_FOR_ALL|NETIF_F_ALL_CSUM) & mask;
+ all |= one & (NETIF_F_ONE_FOR_ALL | NETIF_F_CSUM_MASK) & mask;
all &= one | ~NETIF_F_ALL_FOR_ALL;
/* If one device supports hw checksumming, set for all. */
- if (all & NETIF_F_GEN_CSUM)
- all &= ~(NETIF_F_ALL_CSUM & ~NETIF_F_GEN_CSUM);
+ if (all & NETIF_F_HW_CSUM)
+ all &= ~(NETIF_F_CSUM_MASK & ~NETIF_F_HW_CSUM);
return all;
}
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index 29edf74846fc..09948a726347 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -87,7 +87,7 @@ static const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN]
[NETIF_F_GSO_UDP_TUNNEL_BIT] = "tx-udp_tnl-segmentation",
[NETIF_F_FCOE_CRC_BIT] = "tx-checksum-fcoe-crc",
- [NETIF_F_SCTP_CSUM_BIT] = "tx-checksum-sctp",
+ [NETIF_F_SCTP_CRC_BIT] = "tx-checksum-sctp",
[NETIF_F_FCOE_MTU_BIT] = "fcoe-mtu",
[NETIF_F_NTUPLE_BIT] = "rx-ntuple-filter",
[NETIF_F_RXHASH_BIT] = "rx-hashing",
@@ -235,7 +235,7 @@ static netdev_features_t ethtool_get_feature_mask(u32 eth_cmd)
switch (eth_cmd) {
case ETHTOOL_GTXCSUM:
case ETHTOOL_STXCSUM:
- return NETIF_F_ALL_CSUM | NETIF_F_SCTP_CSUM;
+ return NETIF_F_CSUM_MASK | NETIF_F_SCTP_CRC;
case ETHTOOL_GRXCSUM:
case ETHTOOL_SRXCSUM:
return NETIF_F_RXCSUM;
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index f88a62ab019d..bca8c350e7f3 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -471,6 +471,7 @@ static ssize_t phys_switch_id_show(struct device *dev,
if (dev_isalive(netdev)) {
struct switchdev_attr attr = {
+ .orig_dev = netdev,
.id = SWITCHDEV_ATTR_ID_PORT_PARENT_ID,
.flags = SWITCHDEV_F_NO_RECURSE,
};
diff --git a/net/core/net-traces.c b/net/core/net-traces.c
index adef015b2f41..92da5e4ceb4f 100644
--- a/net/core/net-traces.c
+++ b/net/core/net-traces.c
@@ -32,6 +32,10 @@
#include <trace/events/sock.h>
#include <trace/events/udp.h>
#include <trace/events/fib.h>
+#if IS_ENABLED(CONFIG_IPV6)
+#include <trace/events/fib6.h>
+EXPORT_TRACEPOINT_SYMBOL_GPL(fib6_table_lookup);
+#endif
EXPORT_TRACEPOINT_SYMBOL_GPL(kfree_skb);
diff --git a/net/core/netclassid_cgroup.c b/net/core/netclassid_cgroup.c
index d9ee8d08a3a6..0260c84ed83c 100644
--- a/net/core/netclassid_cgroup.c
+++ b/net/core/netclassid_cgroup.c
@@ -61,9 +61,12 @@ static int update_classid_sock(const void *v, struct file *file, unsigned n)
int err;
struct socket *sock = sock_from_file(file, &err);
- if (sock)
- sock->sk->sk_classid = (u32)(unsigned long)v;
-
+ if (sock) {
+ spin_lock(&cgroup_sk_update_lock);
+ sock_cgroup_set_classid(&sock->sk->sk_cgrp_data,
+ (unsigned long)v);
+ spin_unlock(&cgroup_sk_update_lock);
+ }
return 0;
}
@@ -100,6 +103,8 @@ static int write_classid(struct cgroup_subsys_state *css, struct cftype *cft,
{
struct cgroup_cls_state *cs = css_cls_state(css);
+ cgroup_sk_alloc_disable();
+
cs->classid = (u32)value;
update_classid(css, (void *)(unsigned long)cs->classid);
diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c
index 40fd09fe06ae..f1efbc39ef6b 100644
--- a/net/core/netprio_cgroup.c
+++ b/net/core/netprio_cgroup.c
@@ -27,6 +27,12 @@
#include <linux/fdtable.h>
+/*
+ * netprio allocates per-net_device priomap array which is indexed by
+ * css->id. Limiting css ID to 16bits doesn't lose anything.
+ */
+#define NETPRIO_ID_MAX USHRT_MAX
+
#define PRIOMAP_MIN_SZ 128
/*
@@ -144,6 +150,9 @@ static int cgrp_css_online(struct cgroup_subsys_state *css)
struct net_device *dev;
int ret = 0;
+ if (css->id > NETPRIO_ID_MAX)
+ return -ENOSPC;
+
if (!parent_css)
return 0;
@@ -200,6 +209,8 @@ static ssize_t write_priomap(struct kernfs_open_file *of,
if (!dev)
return -ENODEV;
+ cgroup_sk_alloc_disable();
+
rtnl_lock();
ret = netprio_set_prio(of_css(of), dev, prio);
@@ -213,8 +224,12 @@ static int update_netprio(const void *v, struct file *file, unsigned n)
{
int err;
struct socket *sock = sock_from_file(file, &err);
- if (sock)
- sock->sk->sk_cgrp_prioidx = (u32)(unsigned long)v;
+ if (sock) {
+ spin_lock(&cgroup_sk_update_lock);
+ sock_cgroup_set_prioidx(&sock->sk->sk_cgrp_data,
+ (unsigned long)v);
+ spin_unlock(&cgroup_sk_update_lock);
+ }
return 0;
}
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index de8d5cc5eb24..2be144498bcf 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -2898,7 +2898,7 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev,
if (!(pkt_dev->flags & F_UDPCSUM)) {
skb->ip_summed = CHECKSUM_NONE;
- } else if (odev->features & NETIF_F_V4_CSUM) {
+ } else if (odev->features & (NETIF_F_HW_CSUM | NETIF_F_IP_CSUM)) {
skb->ip_summed = CHECKSUM_PARTIAL;
skb->csum = 0;
udp4_hwcsum(skb, iph->saddr, iph->daddr);
@@ -3032,7 +3032,7 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev,
if (!(pkt_dev->flags & F_UDPCSUM)) {
skb->ip_summed = CHECKSUM_NONE;
- } else if (odev->features & NETIF_F_V6_CSUM) {
+ } else if (odev->features & (NETIF_F_HW_CSUM | NETIF_F_IPV6_CSUM)) {
skb->ip_summed = CHECKSUM_PARTIAL;
skb->csum_start = skb_transport_header(skb) - skb->head;
skb->csum_offset = offsetof(struct udphdr, check);
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 34ba7a08876d..baf49cb2f23d 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1027,6 +1027,7 @@ static int rtnl_phys_switch_id_fill(struct sk_buff *skb, struct net_device *dev)
{
int err;
struct switchdev_attr attr = {
+ .orig_dev = dev,
.id = SWITCHDEV_ATTR_ID_PORT_PARENT_ID,
.flags = SWITCHDEV_F_NO_RECURSE,
};
@@ -2563,7 +2564,7 @@ static int nlmsg_populate_fdb_fill(struct sk_buff *skb,
struct net_device *dev,
u8 *addr, u16 vid, u32 pid, u32 seq,
int type, unsigned int flags,
- int nlflags)
+ int nlflags, u16 ndm_state)
{
struct nlmsghdr *nlh;
struct ndmsg *ndm;
@@ -2579,7 +2580,7 @@ static int nlmsg_populate_fdb_fill(struct sk_buff *skb,
ndm->ndm_flags = flags;
ndm->ndm_type = 0;
ndm->ndm_ifindex = dev->ifindex;
- ndm->ndm_state = NUD_PERMANENT;
+ ndm->ndm_state = ndm_state;
if (nla_put(skb, NDA_LLADDR, ETH_ALEN, addr))
goto nla_put_failure;
@@ -2600,7 +2601,8 @@ static inline size_t rtnl_fdb_nlmsg_size(void)
return NLMSG_ALIGN(sizeof(struct ndmsg)) + nla_total_size(ETH_ALEN);
}
-static void rtnl_fdb_notify(struct net_device *dev, u8 *addr, u16 vid, int type)
+static void rtnl_fdb_notify(struct net_device *dev, u8 *addr, u16 vid, int type,
+ u16 ndm_state)
{
struct net *net = dev_net(dev);
struct sk_buff *skb;
@@ -2611,7 +2613,7 @@ static void rtnl_fdb_notify(struct net_device *dev, u8 *addr, u16 vid, int type)
goto errout;
err = nlmsg_populate_fdb_fill(skb, dev, addr, vid,
- 0, 0, type, NTF_SELF, 0);
+ 0, 0, type, NTF_SELF, 0, ndm_state);
if (err < 0) {
kfree_skb(skb);
goto errout;
@@ -2746,7 +2748,8 @@ static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh)
nlh->nlmsg_flags);
if (!err) {
- rtnl_fdb_notify(dev, addr, vid, RTM_NEWNEIGH);
+ rtnl_fdb_notify(dev, addr, vid, RTM_NEWNEIGH,
+ ndm->ndm_state);
ndm->ndm_flags &= ~NTF_SELF;
}
}
@@ -2847,7 +2850,8 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh)
err = ndo_dflt_fdb_del(ndm, tb, dev, addr, vid);
if (!err) {
- rtnl_fdb_notify(dev, addr, vid, RTM_DELNEIGH);
+ rtnl_fdb_notify(dev, addr, vid, RTM_DELNEIGH,
+ ndm->ndm_state);
ndm->ndm_flags &= ~NTF_SELF;
}
}
@@ -2875,7 +2879,7 @@ static int nlmsg_populate_fdb(struct sk_buff *skb,
err = nlmsg_populate_fdb_fill(skb, dev, ha->addr, 0,
portid, seq,
RTM_NEWNEIGH, NTF_SELF,
- NLM_F_MULTI);
+ NLM_F_MULTI, NUD_PERMANENT);
if (err < 0)
return err;
skip:
diff --git a/net/core/scm.c b/net/core/scm.c
index 8a1741b14302..14596fb37172 100644
--- a/net/core/scm.c
+++ b/net/core/scm.c
@@ -289,8 +289,8 @@ void scm_detach_fds(struct msghdr *msg, struct scm_cookie *scm)
/* Bump the usage count and install the file. */
sock = sock_from_file(fp[i], &err);
if (sock) {
- sock_update_netprioidx(sock->sk);
- sock_update_classid(sock->sk);
+ sock_update_netprioidx(&sock->sk->sk_cgrp_data);
+ sock_update_classid(&sock->sk->sk_cgrp_data);
}
fd_install(new_fd, get_file(fp[i]));
}
diff --git a/net/core/sock.c b/net/core/sock.c
index 0d91f7dca751..565bab7baca9 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1362,6 +1362,7 @@ static struct sock *sk_prot_alloc(struct proto *prot, gfp_t priority,
if (!try_module_get(prot->owner))
goto out_free_sec;
sk_tx_queue_clear(sk);
+ cgroup_sk_alloc(&sk->sk_cgrp_data);
}
return sk;
@@ -1384,6 +1385,7 @@ static void sk_prot_free(struct proto *prot, struct sock *sk)
owner = prot->owner;
slab = prot->slab;
+ cgroup_sk_free(&sk->sk_cgrp_data);
security_sk_free(sk);
if (slab != NULL)
kmem_cache_free(slab, sk);
@@ -1392,17 +1394,6 @@ static void sk_prot_free(struct proto *prot, struct sock *sk)
module_put(owner);
}
-#if IS_ENABLED(CONFIG_CGROUP_NET_PRIO)
-void sock_update_netprioidx(struct sock *sk)
-{
- if (in_interrupt())
- return;
-
- sk->sk_cgrp_prioidx = task_netprioidx(current);
-}
-EXPORT_SYMBOL_GPL(sock_update_netprioidx);
-#endif
-
/**
* sk_alloc - All socket objects are allocated here
* @net: the applicable net namespace
@@ -1431,8 +1422,8 @@ struct sock *sk_alloc(struct net *net, int family, gfp_t priority,
sock_net_set(sk, net);
atomic_set(&sk->sk_wmem_alloc, 1);
- sock_update_classid(sk);
- sock_update_netprioidx(sk);
+ sock_update_classid(&sk->sk_cgrp_data);
+ sock_update_netprioidx(&sk->sk_cgrp_data);
}
return sk;
@@ -2281,7 +2272,7 @@ static void sock_def_wakeup(struct sock *sk)
rcu_read_lock();
wq = rcu_dereference(sk->sk_wq);
- if (wq_has_sleeper(wq))
+ if (skwq_has_sleeper(wq))
wake_up_interruptible_all(&wq->wait);
rcu_read_unlock();
}
@@ -2292,7 +2283,7 @@ static void sock_def_error_report(struct sock *sk)
rcu_read_lock();
wq = rcu_dereference(sk->sk_wq);
- if (wq_has_sleeper(wq))
+ if (skwq_has_sleeper(wq))
wake_up_interruptible_poll(&wq->wait, POLLERR);
sk_wake_async(sk, SOCK_WAKE_IO, POLL_ERR);
rcu_read_unlock();
@@ -2304,7 +2295,7 @@ static void sock_def_readable(struct sock *sk)
rcu_read_lock();
wq = rcu_dereference(sk->sk_wq);
- if (wq_has_sleeper(wq))
+ if (skwq_has_sleeper(wq))
wake_up_interruptible_sync_poll(&wq->wait, POLLIN | POLLPRI |
POLLRDNORM | POLLRDBAND);
sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN);
@@ -2322,7 +2313,7 @@ static void sock_def_write_space(struct sock *sk)
*/
if ((atomic_read(&sk->sk_wmem_alloc) << 1) <= sk->sk_sndbuf) {
wq = rcu_dereference(sk->sk_wq);
- if (wq_has_sleeper(wq))
+ if (skwq_has_sleeper(wq))
wake_up_interruptible_sync_poll(&wq->wait, POLLOUT |
POLLWRNORM | POLLWRBAND);
diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c
index 0c1d58d43f67..a996ce8c8fb2 100644
--- a/net/core/sock_diag.c
+++ b/net/core/sock_diag.c
@@ -214,7 +214,7 @@ void sock_diag_unregister(const struct sock_diag_handler *hnld)
}
EXPORT_SYMBOL_GPL(sock_diag_unregister);
-static int __sock_diag_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
+static int __sock_diag_cmd(struct sk_buff *skb, struct nlmsghdr *nlh)
{
int err;
struct sock_diag_req *req = nlmsg_data(nlh);
@@ -234,8 +234,12 @@ static int __sock_diag_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
hndl = sock_diag_handlers[req->sdiag_family];
if (hndl == NULL)
err = -ENOENT;
- else
+ else if (nlh->nlmsg_type == SOCK_DIAG_BY_FAMILY)
err = hndl->dump(skb, nlh);
+ else if (nlh->nlmsg_type == SOCK_DESTROY && hndl->destroy)
+ err = hndl->destroy(skb, nlh);
+ else
+ err = -EOPNOTSUPP;
mutex_unlock(&sock_diag_table_mutex);
return err;
@@ -261,7 +265,8 @@ static int sock_diag_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
return ret;
case SOCK_DIAG_BY_FAMILY:
- return __sock_diag_rcv_msg(skb, nlh);
+ case SOCK_DESTROY:
+ return __sock_diag_cmd(skb, nlh);
default:
return -EINVAL;
}
@@ -295,6 +300,18 @@ static int sock_diag_bind(struct net *net, int group)
return 0;
}
+int sock_diag_destroy(struct sock *sk, int err)
+{
+ if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))
+ return -EPERM;
+
+ if (!sk->sk_prot->diag_destroy)
+ return -EOPNOTSUPP;
+
+ return sk->sk_prot->diag_destroy(sk, err);
+}
+EXPORT_SYMBOL_GPL(sock_diag_destroy);
+
static int __net_init diag_net_init(struct net *net)
{
struct netlink_kernel_cfg cfg = {
diff --git a/net/core/stream.c b/net/core/stream.c
index b96f7a79e544..159516a11b7e 100644
--- a/net/core/stream.c
+++ b/net/core/stream.c
@@ -35,7 +35,7 @@ void sk_stream_write_space(struct sock *sk)
rcu_read_lock();
wq = rcu_dereference(sk->sk_wq);
- if (wq_has_sleeper(wq))
+ if (skwq_has_sleeper(wq))
wake_up_interruptible_poll(&wq->wait, POLLOUT |
POLLWRNORM | POLLWRBAND);
if (wq && wq->fasync_list && !(sk->sk_shutdown & SEND_SHUTDOWN))
generated by cgit v1.2.3-58-ga151 (git 2.39.0) at 2024-12-27 06:59:51 +0000