summaryrefslogtreecommitdiff
path: root/net/core
diff options
context:
space:
mode:
authorH. Peter Anvin <hpa@linux.intel.com>2013-04-20 20:16:44 +0400
committerH. Peter Anvin <hpa@linux.intel.com>2013-04-20 20:16:44 +0400
commitf53f292eeaa234615c31a1306babe703fc4263f2 (patch)
tree707b0933a20f7dc05495e974243a23b5c9f8c918 /net/core
parent15b9c359f288b09003cb70f7ed204affc0c6614d (diff)
parenta9499fa7cd3fd4824a7202d00c766b269fa3bda6 (diff)
downloadlinux-f53f292eeaa234615c31a1306babe703fc4263f2.tar.xz
Merge remote-tracking branch 'efi/chainsaw' into x86/efi
Resolved Conflicts: drivers/firmware/efivars.c fs/efivarsfs/file.c Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Diffstat (limited to 'net/core')
-rw-r--r--net/core/Makefile3
-rw-r--r--net/core/datagram.c2
-rw-r--r--net/core/dev.c1736
-rw-r--r--net/core/dev_addr_lists.c74
-rw-r--r--net/core/dev_ioctl.c576
-rw-r--r--net/core/dst.c1
-rw-r--r--net/core/ethtool.c46
-rw-r--r--net/core/filter.c13
-rw-r--r--net/core/flow.c13
-rw-r--r--net/core/flow_dissector.c175
-rw-r--r--net/core/neighbour.c20
-rw-r--r--net/core/net-procfs.c411
-rw-r--r--net/core/net-sysfs.c180
-rw-r--r--net/core/net_namespace.c2
-rw-r--r--net/core/netpoll.c721
-rw-r--r--net/core/netprio_cgroup.c4
-rw-r--r--net/core/pktgen.c205
-rw-r--r--net/core/rtnetlink.c220
-rw-r--r--net/core/scm.c4
-rw-r--r--net/core/skbuff.c113
-rw-r--r--net/core/sock.c26
-rw-r--r--net/core/sock_diag.c27
-rw-r--r--net/core/sysctl_net_core.c14
23 files changed, 2708 insertions, 1878 deletions
diff --git a/net/core/Makefile b/net/core/Makefile
index 674641b13aea..b33b996f5dd6 100644
--- a/net/core/Makefile
+++ b/net/core/Makefile
@@ -9,10 +9,11 @@ obj-$(CONFIG_SYSCTL) += sysctl_net_core.o
obj-y += dev.o ethtool.o dev_addr_lists.o dst.o netevent.o \
neighbour.o rtnetlink.o utils.o link_watch.o filter.o \
- sock_diag.o
+ sock_diag.o dev_ioctl.o
obj-$(CONFIG_XFRM) += flow.o
obj-y += net-sysfs.o
+obj-$(CONFIG_PROC_FS) += net-procfs.o
obj-$(CONFIG_NET_PKTGEN) += pktgen.o
obj-$(CONFIG_NETPOLL) += netpoll.o
obj-$(CONFIG_NET_DMA) += user_dma.o
diff --git a/net/core/datagram.c b/net/core/datagram.c
index 0337e2b76862..368f9c3f9dc6 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -187,7 +187,7 @@ struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned int flags,
skb_queue_walk(queue, skb) {
*peeked = skb->peeked;
if (flags & MSG_PEEK) {
- if (*off >= skb->len) {
+ if (*off >= skb->len && skb->len) {
*off -= skb->len;
continue;
}
diff --git a/net/core/dev.c b/net/core/dev.c
index f64e439b4a00..b13e5c766c11 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -97,8 +97,6 @@
#include <net/net_namespace.h>
#include <net/sock.h>
#include <linux/rtnetlink.h>
-#include <linux/proc_fs.h>
-#include <linux/seq_file.h>
#include <linux/stat.h>
#include <net/dst.h>
#include <net/pkt_sched.h>
@@ -106,12 +104,10 @@
#include <net/xfrm.h>
#include <linux/highmem.h>
#include <linux/init.h>
-#include <linux/kmod.h>
#include <linux/module.h>
#include <linux/netpoll.h>
#include <linux/rcupdate.h>
#include <linux/delay.h>
-#include <net/wext.h>
#include <net/iw_handler.h>
#include <asm/current.h>
#include <linux/audit.h>
@@ -132,9 +128,7 @@
#include <linux/pci.h>
#include <linux/inetdevice.h>
#include <linux/cpu_rmap.h>
-#include <linux/net_tstamp.h>
#include <linux/static_key.h>
-#include <net/flow_keys.h>
#include "net-sysfs.h"
@@ -144,41 +138,10 @@
/* This should be increased if a protocol with a bigger head is added. */
#define GRO_MAX_HEAD (MAX_HEADER + 128)
-/*
- * The list of packet types we will receive (as opposed to discard)
- * and the routines to invoke.
- *
- * Why 16. Because with 16 the only overlap we get on a hash of the
- * low nibble of the protocol value is RARP/SNAP/X.25.
- *
- * NOTE: That is no longer true with the addition of VLAN tags. Not
- * sure which should go first, but I bet it won't make much
- * difference if we are running VLANs. The good news is that
- * this protocol won't be in the list unless compiled in, so
- * the average user (w/out VLANs) will not be adversely affected.
- * --BLG
- *
- * 0800 IP
- * 8100 802.1Q VLAN
- * 0001 802.3
- * 0002 AX.25
- * 0004 802.2
- * 8035 RARP
- * 0005 SNAP
- * 0805 X.25
- * 0806 ARP
- * 8137 IPX
- * 0009 Localtalk
- * 86DD IPv6
- */
-
-#define PTYPE_HASH_SIZE (16)
-#define PTYPE_HASH_MASK (PTYPE_HASH_SIZE - 1)
-
static DEFINE_SPINLOCK(ptype_lock);
static DEFINE_SPINLOCK(offload_lock);
-static struct list_head ptype_base[PTYPE_HASH_SIZE] __read_mostly;
-static struct list_head ptype_all __read_mostly; /* Taps */
+struct list_head ptype_base[PTYPE_HASH_SIZE] __read_mostly;
+struct list_head ptype_all __read_mostly; /* Taps */
static struct list_head offload_base __read_mostly;
/*
@@ -695,11 +658,10 @@ __setup("netdev=", netdev_boot_setup);
struct net_device *__dev_get_by_name(struct net *net, const char *name)
{
- struct hlist_node *p;
struct net_device *dev;
struct hlist_head *head = dev_name_hash(net, name);
- hlist_for_each_entry(dev, p, head, name_hlist)
+ hlist_for_each_entry(dev, head, name_hlist)
if (!strncmp(dev->name, name, IFNAMSIZ))
return dev;
@@ -721,11 +683,10 @@ EXPORT_SYMBOL(__dev_get_by_name);
struct net_device *dev_get_by_name_rcu(struct net *net, const char *name)
{
- struct hlist_node *p;
struct net_device *dev;
struct hlist_head *head = dev_name_hash(net, name);
- hlist_for_each_entry_rcu(dev, p, head, name_hlist)
+ hlist_for_each_entry_rcu(dev, head, name_hlist)
if (!strncmp(dev->name, name, IFNAMSIZ))
return dev;
@@ -772,11 +733,10 @@ EXPORT_SYMBOL(dev_get_by_name);
struct net_device *__dev_get_by_index(struct net *net, int ifindex)
{
- struct hlist_node *p;
struct net_device *dev;
struct hlist_head *head = dev_index_hash(net, ifindex);
- hlist_for_each_entry(dev, p, head, index_hlist)
+ hlist_for_each_entry(dev, head, index_hlist)
if (dev->ifindex == ifindex)
return dev;
@@ -797,11 +757,10 @@ EXPORT_SYMBOL(__dev_get_by_index);
struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex)
{
- struct hlist_node *p;
struct net_device *dev;
struct hlist_head *head = dev_index_hash(net, ifindex);
- hlist_for_each_entry_rcu(dev, p, head, index_hlist)
+ hlist_for_each_entry_rcu(dev, head, index_hlist)
if (dev->ifindex == ifindex)
return dev;
@@ -1227,36 +1186,6 @@ void netdev_notify_peers(struct net_device *dev)
}
EXPORT_SYMBOL(netdev_notify_peers);
-/**
- * dev_load - load a network module
- * @net: the applicable net namespace
- * @name: name of interface
- *
- * If a network interface is not present and the process has suitable
- * privileges this function loads the module. If module loading is not
- * available in this kernel then it becomes a nop.
- */
-
-void dev_load(struct net *net, const char *name)
-{
- struct net_device *dev;
- int no_module;
-
- rcu_read_lock();
- dev = dev_get_by_name_rcu(net, name);
- rcu_read_unlock();
-
- no_module = !dev;
- if (no_module && capable(CAP_NET_ADMIN))
- no_module = request_module("netdev-%s", name);
- if (no_module && capable(CAP_SYS_MODULE)) {
- if (!request_module("%s", name))
- pr_warn("Loading kernel module for a network device with CAP_SYS_MODULE (deprecated). Use CAP_NET_ADMIN and alias netdev-%s instead.\n",
- name);
- }
-}
-EXPORT_SYMBOL(dev_load);
-
static int __dev_open(struct net_device *dev)
{
const struct net_device_ops *ops = dev->netdev_ops;
@@ -1267,6 +1196,14 @@ static int __dev_open(struct net_device *dev)
if (!netif_device_present(dev))
return -ENODEV;
+ /* Block netpoll from trying to do any rx path servicing.
+ * If we don't do this there is a chance ndo_poll_controller
+ * or ndo_poll may be running while we open the device
+ */
+ ret = netpoll_rx_disable(dev);
+ if (ret)
+ return ret;
+
ret = call_netdevice_notifiers(NETDEV_PRE_UP, dev);
ret = notifier_to_errno(ret);
if (ret)
@@ -1280,6 +1217,8 @@ static int __dev_open(struct net_device *dev)
if (!ret && ops->ndo_open)
ret = ops->ndo_open(dev);
+ netpoll_rx_enable(dev);
+
if (ret)
clear_bit(__LINK_STATE_START, &dev->state);
else {
@@ -1371,9 +1310,16 @@ static int __dev_close(struct net_device *dev)
int retval;
LIST_HEAD(single);
+ /* Temporarily disable netpoll until the interface is down */
+ retval = netpoll_rx_disable(dev);
+ if (retval)
+ return retval;
+
list_add(&dev->unreg_list, &single);
retval = __dev_close_many(&single);
list_del(&single);
+
+ netpoll_rx_enable(dev);
return retval;
}
@@ -1409,14 +1355,22 @@ static int dev_close_many(struct list_head *head)
*/
int dev_close(struct net_device *dev)
{
+ int ret = 0;
if (dev->flags & IFF_UP) {
LIST_HEAD(single);
+ /* Block netpoll rx while the interface is going down */
+ ret = netpoll_rx_disable(dev);
+ if (ret)
+ return ret;
+
list_add(&dev->unreg_list, &single);
dev_close_many(&single);
list_del(&single);
+
+ netpoll_rx_enable(dev);
}
- return 0;
+ return ret;
}
EXPORT_SYMBOL(dev_close);
@@ -1591,7 +1545,6 @@ void net_enable_timestamp(void)
return;
}
#endif
- WARN_ON(in_interrupt());
static_key_slow_inc(&netstamp_needed);
}
EXPORT_SYMBOL(net_enable_timestamp);
@@ -1621,57 +1574,6 @@ static inline void net_timestamp_set(struct sk_buff *skb)
__net_timestamp(SKB); \
} \
-static int net_hwtstamp_validate(struct ifreq *ifr)
-{
- struct hwtstamp_config cfg;
- enum hwtstamp_tx_types tx_type;
- enum hwtstamp_rx_filters rx_filter;
- int tx_type_valid = 0;
- int rx_filter_valid = 0;
-
- if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg)))
- return -EFAULT;
-
- if (cfg.flags) /* reserved for future extensions */
- return -EINVAL;
-
- tx_type = cfg.tx_type;
- rx_filter = cfg.rx_filter;
-
- switch (tx_type) {
- case HWTSTAMP_TX_OFF:
- case HWTSTAMP_TX_ON:
- case HWTSTAMP_TX_ONESTEP_SYNC:
- tx_type_valid = 1;
- break;
- }
-
- switch (rx_filter) {
- case HWTSTAMP_FILTER_NONE:
- case HWTSTAMP_FILTER_ALL:
- case HWTSTAMP_FILTER_SOME:
- case HWTSTAMP_FILTER_PTP_V1_L4_EVENT:
- case HWTSTAMP_FILTER_PTP_V1_L4_SYNC:
- case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ:
- case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
- case HWTSTAMP_FILTER_PTP_V2_L4_SYNC:
- case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ:
- case HWTSTAMP_FILTER_PTP_V2_L2_EVENT:
- case HWTSTAMP_FILTER_PTP_V2_L2_SYNC:
- case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ:
- case HWTSTAMP_FILTER_PTP_V2_EVENT:
- case HWTSTAMP_FILTER_PTP_V2_SYNC:
- case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
- rx_filter_valid = 1;
- break;
- }
-
- if (!tx_type_valid || !rx_filter_valid)
- return -ERANGE;
-
- return 0;
-}
-
static inline bool is_skb_forwardable(struct net_device *dev,
struct sk_buff *skb)
{
@@ -1857,6 +1759,230 @@ static void netif_setup_tc(struct net_device *dev, unsigned int txq)
}
}
+#ifdef CONFIG_XPS
+static DEFINE_MUTEX(xps_map_mutex);
+#define xmap_dereference(P) \
+ rcu_dereference_protected((P), lockdep_is_held(&xps_map_mutex))
+
+static struct xps_map *remove_xps_queue(struct xps_dev_maps *dev_maps,
+ int cpu, u16 index)
+{
+ struct xps_map *map = NULL;
+ int pos;
+
+ if (dev_maps)
+ map = xmap_dereference(dev_maps->cpu_map[cpu]);
+
+ for (pos = 0; map && pos < map->len; pos++) {
+ if (map->queues[pos] == index) {
+ if (map->len > 1) {
+ map->queues[pos] = map->queues[--map->len];
+ } else {
+ RCU_INIT_POINTER(dev_maps->cpu_map[cpu], NULL);
+ kfree_rcu(map, rcu);
+ map = NULL;
+ }
+ break;
+ }
+ }
+
+ return map;
+}
+
+static void netif_reset_xps_queues_gt(struct net_device *dev, u16 index)
+{
+ struct xps_dev_maps *dev_maps;
+ int cpu, i;
+ bool active = false;
+
+ mutex_lock(&xps_map_mutex);
+ dev_maps = xmap_dereference(dev->xps_maps);
+
+ if (!dev_maps)
+ goto out_no_maps;
+
+ for_each_possible_cpu(cpu) {
+ for (i = index; i < dev->num_tx_queues; i++) {
+ if (!remove_xps_queue(dev_maps, cpu, i))
+ break;
+ }
+ if (i == dev->num_tx_queues)
+ active = true;
+ }
+
+ if (!active) {
+ RCU_INIT_POINTER(dev->xps_maps, NULL);
+ kfree_rcu(dev_maps, rcu);
+ }
+
+ for (i = index; i < dev->num_tx_queues; i++)
+ netdev_queue_numa_node_write(netdev_get_tx_queue(dev, i),
+ NUMA_NO_NODE);
+
+out_no_maps:
+ mutex_unlock(&xps_map_mutex);
+}
+
+static struct xps_map *expand_xps_map(struct xps_map *map,
+ int cpu, u16 index)
+{
+ struct xps_map *new_map;
+ int alloc_len = XPS_MIN_MAP_ALLOC;
+ int i, pos;
+
+ for (pos = 0; map && pos < map->len; pos++) {
+ if (map->queues[pos] != index)
+ continue;
+ return map;
+ }
+
+ /* Need to add queue to this CPU's existing map */
+ if (map) {
+ if (pos < map->alloc_len)
+ return map;
+
+ alloc_len = map->alloc_len * 2;
+ }
+
+ /* Need to allocate new map to store queue on this CPU's map */
+ new_map = kzalloc_node(XPS_MAP_SIZE(alloc_len), GFP_KERNEL,
+ cpu_to_node(cpu));
+ if (!new_map)
+ return NULL;
+
+ for (i = 0; i < pos; i++)
+ new_map->queues[i] = map->queues[i];
+ new_map->alloc_len = alloc_len;
+ new_map->len = pos;
+
+ return new_map;
+}
+
+int netif_set_xps_queue(struct net_device *dev, struct cpumask *mask, u16 index)
+{
+ struct xps_dev_maps *dev_maps, *new_dev_maps = NULL;
+ struct xps_map *map, *new_map;
+ int maps_sz = max_t(unsigned int, XPS_DEV_MAPS_SIZE, L1_CACHE_BYTES);
+ int cpu, numa_node_id = -2;
+ bool active = false;
+
+ mutex_lock(&xps_map_mutex);
+
+ dev_maps = xmap_dereference(dev->xps_maps);
+
+ /* allocate memory for queue storage */
+ for_each_online_cpu(cpu) {
+ if (!cpumask_test_cpu(cpu, mask))
+ continue;
+
+ if (!new_dev_maps)
+ new_dev_maps = kzalloc(maps_sz, GFP_KERNEL);
+ if (!new_dev_maps) {
+ mutex_unlock(&xps_map_mutex);
+ return -ENOMEM;
+ }
+
+ map = dev_maps ? xmap_dereference(dev_maps->cpu_map[cpu]) :
+ NULL;
+
+ map = expand_xps_map(map, cpu, index);
+ if (!map)
+ goto error;
+
+ RCU_INIT_POINTER(new_dev_maps->cpu_map[cpu], map);
+ }
+
+ if (!new_dev_maps)
+ goto out_no_new_maps;
+
+ for_each_possible_cpu(cpu) {
+ if (cpumask_test_cpu(cpu, mask) && cpu_online(cpu)) {
+ /* add queue to CPU maps */
+ int pos = 0;
+
+ map = xmap_dereference(new_dev_maps->cpu_map[cpu]);
+ while ((pos < map->len) && (map->queues[pos] != index))
+ pos++;
+
+ if (pos == map->len)
+ map->queues[map->len++] = index;
+#ifdef CONFIG_NUMA
+ if (numa_node_id == -2)
+ numa_node_id = cpu_to_node(cpu);
+ else if (numa_node_id != cpu_to_node(cpu))
+ numa_node_id = -1;
+#endif
+ } else if (dev_maps) {
+ /* fill in the new device map from the old device map */
+ map = xmap_dereference(dev_maps->cpu_map[cpu]);
+ RCU_INIT_POINTER(new_dev_maps->cpu_map[cpu], map);
+ }
+
+ }
+
+ rcu_assign_pointer(dev->xps_maps, new_dev_maps);
+
+ /* Cleanup old maps */
+ if (dev_maps) {
+ for_each_possible_cpu(cpu) {
+ new_map = xmap_dereference(new_dev_maps->cpu_map[cpu]);
+ map = xmap_dereference(dev_maps->cpu_map[cpu]);
+ if (map && map != new_map)
+ kfree_rcu(map, rcu);
+ }
+
+ kfree_rcu(dev_maps, rcu);
+ }
+
+ dev_maps = new_dev_maps;
+ active = true;
+
+out_no_new_maps:
+ /* update Tx queue numa node */
+ netdev_queue_numa_node_write(netdev_get_tx_queue(dev, index),
+ (numa_node_id >= 0) ? numa_node_id :
+ NUMA_NO_NODE);
+
+ if (!dev_maps)
+ goto out_no_maps;
+
+ /* removes queue from unused CPUs */
+ for_each_possible_cpu(cpu) {
+ if (cpumask_test_cpu(cpu, mask) && cpu_online(cpu))
+ continue;
+
+ if (remove_xps_queue(dev_maps, cpu, index))
+ active = true;
+ }
+
+ /* free map if not active */
+ if (!active) {
+ RCU_INIT_POINTER(dev->xps_maps, NULL);
+ kfree_rcu(dev_maps, rcu);
+ }
+
+out_no_maps:
+ mutex_unlock(&xps_map_mutex);
+
+ return 0;
+error:
+ /* remove any maps that we added */
+ for_each_possible_cpu(cpu) {
+ new_map = xmap_dereference(new_dev_maps->cpu_map[cpu]);
+ map = dev_maps ? xmap_dereference(dev_maps->cpu_map[cpu]) :
+ NULL;
+ if (new_map && new_map != map)
+ kfree(new_map);
+ }
+
+ mutex_unlock(&xps_map_mutex);
+
+ kfree(new_dev_maps);
+ return -ENOMEM;
+}
+EXPORT_SYMBOL(netif_set_xps_queue);
+
+#endif
/*
* Routine to help set real_num_tx_queues. To avoid skbs mapped to queues
* greater then real_num_tx_queues stale skbs on the qdisc must be flushed.
@@ -1880,8 +2006,12 @@ int netif_set_real_num_tx_queues(struct net_device *dev, unsigned int txq)
if (dev->num_tc)
netif_setup_tc(dev, txq);
- if (txq < dev->real_num_tx_queues)
+ if (txq < dev->real_num_tx_queues) {
qdisc_reset_all_tx_gt(dev, txq);
+#ifdef CONFIG_XPS
+ netif_reset_xps_queues_gt(dev, txq);
+#endif
+ }
}
dev->real_num_tx_queues = txq;
@@ -2046,6 +2176,15 @@ int skb_checksum_help(struct sk_buff *skb)
return -EINVAL;
}
+ /* Before computing a checksum, we should make sure no frag could
+ * be modified by an external entity : checksum could be wrong.
+ */
+ if (skb_has_shared_frag(skb)) {
+ ret = __skb_linearize(skb);
+ if (ret)
+ goto out;
+ }
+
offset = skb_checksum_start_offset(skb);
BUG_ON(offset >= skb_headlen(skb));
csum = skb_checksum(skb, offset, skb->len - offset, 0);
@@ -2069,23 +2208,17 @@ out:
EXPORT_SYMBOL(skb_checksum_help);
/**
- * skb_gso_segment - Perform segmentation on skb.
+ * skb_mac_gso_segment - mac layer segmentation handler.
* @skb: buffer to segment
* @features: features for the output path (see dev->features)
- *
- * This function segments the given skb and returns a list of segments.
- *
- * It may return NULL if the skb requires no segmentation. This is
- * only possible when GSO is used for verifying header integrity.
*/
-struct sk_buff *skb_gso_segment(struct sk_buff *skb,
- netdev_features_t features)
+struct sk_buff *skb_mac_gso_segment(struct sk_buff *skb,
+ netdev_features_t features)
{
struct sk_buff *segs = ERR_PTR(-EPROTONOSUPPORT);
struct packet_offload *ptype;
__be16 type = skb->protocol;
int vlan_depth = ETH_HLEN;
- int err;
while (type == htons(ETH_P_8021Q)) {
struct vlan_hdr *vh;
@@ -2098,22 +2231,14 @@ struct sk_buff *skb_gso_segment(struct sk_buff *skb,
vlan_depth += VLAN_HLEN;
}
- skb_reset_mac_header(skb);
- skb->mac_len = skb->network_header - skb->mac_header;
__skb_pull(skb, skb->mac_len);
- if (unlikely(skb->ip_summed != CHECKSUM_PARTIAL)) {
- skb_warn_bad_offload(skb);
-
- if (skb_header_cloned(skb) &&
- (err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC)))
- return ERR_PTR(err);
- }
-
rcu_read_lock();
list_for_each_entry_rcu(ptype, &offload_base, list) {
if (ptype->type == type && ptype->callbacks.gso_segment) {
if (unlikely(skb->ip_summed != CHECKSUM_PARTIAL)) {
+ int err;
+
err = ptype->callbacks.gso_send_check(skb);
segs = ERR_PTR(err);
if (err || skb_gso_ok(skb, features))
@@ -2131,7 +2256,50 @@ struct sk_buff *skb_gso_segment(struct sk_buff *skb,
return segs;
}
-EXPORT_SYMBOL(skb_gso_segment);
+EXPORT_SYMBOL(skb_mac_gso_segment);
+
+
+/* openvswitch calls this on rx path, so we need a different check.
+ */
+static inline bool skb_needs_check(struct sk_buff *skb, bool tx_path)
+{
+ if (tx_path)
+ return skb->ip_summed != CHECKSUM_PARTIAL;
+ else
+ return skb->ip_summed == CHECKSUM_NONE;
+}
+
+/**
+ * __skb_gso_segment - Perform segmentation on skb.
+ * @skb: buffer to segment
+ * @features: features for the output path (see dev->features)
+ * @tx_path: whether it is called in TX path
+ *
+ * This function segments the given skb and returns a list of segments.
+ *
+ * It may return NULL if the skb requires no segmentation. This is
+ * only possible when GSO is used for verifying header integrity.
+ */
+struct sk_buff *__skb_gso_segment(struct sk_buff *skb,
+ netdev_features_t features, bool tx_path)
+{
+ if (unlikely(skb_needs_check(skb, tx_path))) {
+ int err;
+
+ skb_warn_bad_offload(skb);
+
+ if (skb_header_cloned(skb) &&
+ (err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC)))
+ return ERR_PTR(err);
+ }
+
+ SKB_GSO_CB(skb)->mac_offset = skb_headroom(skb);
+ skb_reset_mac_header(skb);
+ skb_reset_mac_len(skb);
+
+ return skb_mac_gso_segment(skb, features);
+}
+EXPORT_SYMBOL(__skb_gso_segment);
/* Take action when hardware reception checksum errors are detected. */
#ifdef CONFIG_BUG
@@ -2410,126 +2578,28 @@ out:
return rc;
}
-static u32 hashrnd __read_mostly;
-
-/*
- * Returns a Tx hash based on the given packet descriptor a Tx queues' number
- * to be used as a distribution range.
- */
-u16 __skb_tx_hash(const struct net_device *dev, const struct sk_buff *skb,
- unsigned int num_tx_queues)
-{
- u32 hash;
- u16 qoffset = 0;
- u16 qcount = num_tx_queues;
-
- if (skb_rx_queue_recorded(skb)) {
- hash = skb_get_rx_queue(skb);
- while (unlikely(hash >= num_tx_queues))
- hash -= num_tx_queues;
- return hash;
- }
-
- if (dev->num_tc) {
- u8 tc = netdev_get_prio_tc_map(dev, skb->priority);
- qoffset = dev->tc_to_txq[tc].offset;
- qcount = dev->tc_to_txq[tc].count;
- }
-
- if (skb->sk && skb->sk->sk_hash)
- hash = skb->sk->sk_hash;
- else
- hash = (__force u16) skb->protocol;
- hash = jhash_1word(hash, hashrnd);
-
- return (u16) (((u64) hash * qcount) >> 32) + qoffset;
-}
-EXPORT_SYMBOL(__skb_tx_hash);
-
-static inline u16 dev_cap_txqueue(struct net_device *dev, u16 queue_index)
-{
- if (unlikely(queue_index >= dev->real_num_tx_queues)) {
- net_warn_ratelimited("%s selects TX queue %d, but real number of TX queues is %d\n",
- dev->name, queue_index,
- dev->real_num_tx_queues);
- return 0;
- }
- return queue_index;
-}
-
-static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb)
-{
-#ifdef CONFIG_XPS
- struct xps_dev_maps *dev_maps;
- struct xps_map *map;
- int queue_index = -1;
-
- rcu_read_lock();
- dev_maps = rcu_dereference(dev->xps_maps);
- if (dev_maps) {
- map = rcu_dereference(
- dev_maps->cpu_map[raw_smp_processor_id()]);
- if (map) {
- if (map->len == 1)
- queue_index = map->queues[0];
- else {
- u32 hash;
- if (skb->sk && skb->sk->sk_hash)
- hash = skb->sk->sk_hash;
- else
- hash = (__force u16) skb->protocol ^
- skb->rxhash;
- hash = jhash_1word(hash, hashrnd);
- queue_index = map->queues[
- ((u64)hash * map->len) >> 32];
- }
- if (unlikely(queue_index >= dev->real_num_tx_queues))
- queue_index = -1;
- }
- }
- rcu_read_unlock();
-
- return queue_index;
-#else
- return -1;
-#endif
-}
-
-struct netdev_queue *netdev_pick_tx(struct net_device *dev,
- struct sk_buff *skb)
+static void qdisc_pkt_len_init(struct sk_buff *skb)
{
- int queue_index;
- const struct net_device_ops *ops = dev->netdev_ops;
+ const struct skb_shared_info *shinfo = skb_shinfo(skb);
- if (dev->real_num_tx_queues == 1)
- queue_index = 0;
- else if (ops->ndo_select_queue) {
- queue_index = ops->ndo_select_queue(dev, skb);
- queue_index = dev_cap_txqueue(dev, queue_index);
- } else {
- struct sock *sk = skb->sk;
- queue_index = sk_tx_queue_get(sk);
-
- if (queue_index < 0 || skb->ooo_okay ||
- queue_index >= dev->real_num_tx_queues) {
- int old_index = queue_index;
+ qdisc_skb_cb(skb)->pkt_len = skb->len;
- queue_index = get_xps_queue(dev, skb);
- if (queue_index < 0)
- queue_index = skb_tx_hash(dev, skb);
+ /* To get more precise estimation of bytes sent on wire,
+ * we add to pkt_len the headers size of all segments
+ */
+ if (shinfo->gso_size) {
+ unsigned int hdr_len;
- if (queue_index != old_index && sk) {
- struct dst_entry *dst =
- rcu_dereference_check(sk->sk_dst_cache, 1);
+ /* mac layer + network layer */
+ hdr_len = skb_transport_header(skb) - skb_mac_header(skb);
- if (dst && skb_dst(skb) == dst)
- sk_tx_queue_set(sk, queue_index);
- }
- }
+ /* + transport layer */
+ if (likely(shinfo->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6)))
+ hdr_len += tcp_hdrlen(skb);
+ else
+ hdr_len += sizeof(struct udphdr);
+ qdisc_skb_cb(skb)->pkt_len += (shinfo->gso_segs - 1) * hdr_len;
}
-
- skb_set_queue_mapping(skb, queue_index);
- return netdev_get_tx_queue(dev, queue_index);
}
static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
@@ -2540,7 +2610,7 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
bool contended;
int rc;
- qdisc_skb_cb(skb)->pkt_len = skb->len;
+ qdisc_pkt_len_init(skb);
qdisc_calculate_pkt_len(skb, q);
/*
* Heuristic to force contended enqueues to serialize on a
@@ -2663,6 +2733,8 @@ int dev_queue_xmit(struct sk_buff *skb)
struct Qdisc *q;
int rc = -ENOMEM;
+ skb_reset_mac_header(skb);
+
/* Disable soft irqs for various locks below. Also
* stops preemption for RCU.
*/
@@ -2757,41 +2829,6 @@ static inline void ____napi_schedule(struct softnet_data *sd,
__raise_softirq_irqoff(NET_RX_SOFTIRQ);
}
-/*
- * __skb_get_rxhash: calculate a flow hash based on src/dst addresses
- * and src/dst port numbers. Sets rxhash in skb to non-zero hash value
- * on success, zero indicates no valid hash. Also, sets l4_rxhash in skb
- * if hash is a canonical 4-tuple hash over transport ports.
- */
-void __skb_get_rxhash(struct sk_buff *skb)
-{
- struct flow_keys keys;
- u32 hash;
-
- if (!skb_flow_dissect(skb, &keys))
- return;
-
- if (keys.ports)
- skb->l4_rxhash = 1;
-
- /* get a consistent hash (same value on both flow directions) */
- if (((__force u32)keys.dst < (__force u32)keys.src) ||
- (((__force u32)keys.dst == (__force u32)keys.src) &&
- ((__force u16)keys.port16[1] < (__force u16)keys.port16[0]))) {
- swap(keys.dst, keys.src);
- swap(keys.port16[0], keys.port16[1]);
- }
-
- hash = jhash_3words((__force u32)keys.dst,
- (__force u32)keys.src,
- (__force u32)keys.ports, hashrnd);
- if (!hash)
- hash = 1;
-
- skb->rxhash = hash;
-}
-EXPORT_SYMBOL(__skb_get_rxhash);
-
#ifdef CONFIG_RPS
/* One global table that all flow-based protocols share. */
@@ -3318,7 +3355,7 @@ static bool skb_pfmemalloc_protocol(struct sk_buff *skb)
}
}
-static int __netif_receive_skb(struct sk_buff *skb)
+static int __netif_receive_skb_core(struct sk_buff *skb, bool pfmemalloc)
{
struct packet_type *ptype, *pt_prev;
rx_handler_func_t *rx_handler;
@@ -3327,24 +3364,11 @@ static int __netif_receive_skb(struct sk_buff *skb)
bool deliver_exact = false;
int ret = NET_RX_DROP;
__be16 type;
- unsigned long pflags = current->flags;
net_timestamp_check(!netdev_tstamp_prequeue, skb);
trace_netif_receive_skb(skb);
- /*
- * PFMEMALLOC skbs are special, they should
- * - be delivered to SOCK_MEMALLOC sockets only
- * - stay away from userspace
- * - have bounded memory usage
- *
- * Use PF_MEMALLOC as this saves us from propagating the allocation
- * context down to all allocation sites.
- */
- if (sk_memalloc_socks() && skb_pfmemalloc(skb))
- current->flags |= PF_MEMALLOC;
-
/* if we've gotten here through NAPI, check netpoll */
if (netpoll_receive_skb(skb))
goto out;
@@ -3352,7 +3376,8 @@ static int __netif_receive_skb(struct sk_buff *skb)
orig_dev = skb->dev;
skb_reset_network_header(skb);
- skb_reset_transport_header(skb);
+ if (!skb_transport_header_was_set(skb))
+ skb_reset_transport_header(skb);
skb_reset_mac_len(skb);
pt_prev = NULL;
@@ -3377,7 +3402,7 @@ another_round:
}
#endif
- if (sk_memalloc_socks() && skb_pfmemalloc(skb))
+ if (pfmemalloc)
goto skip_taps;
list_for_each_entry_rcu(ptype, &ptype_all, list) {
@@ -3396,8 +3421,7 @@ skip_taps:
ncls:
#endif
- if (sk_memalloc_socks() && skb_pfmemalloc(skb)
- && !skb_pfmemalloc_protocol(skb))
+ if (pfmemalloc && !skb_pfmemalloc_protocol(skb))
goto drop;
if (vlan_tx_tag_present(skb)) {
@@ -3419,6 +3443,7 @@ ncls:
}
switch (rx_handler(&skb)) {
case RX_HANDLER_CONSUMED:
+ ret = NET_RX_SUCCESS;
goto unlock;
case RX_HANDLER_ANOTHER:
goto another_round;
@@ -3467,7 +3492,31 @@ drop:
unlock:
rcu_read_unlock();
out:
- tsk_restore_flags(current, pflags, PF_MEMALLOC);
+ return ret;
+}
+
+static int __netif_receive_skb(struct sk_buff *skb)
+{
+ int ret;
+
+ if (sk_memalloc_socks() && skb_pfmemalloc(skb)) {
+ unsigned long pflags = current->flags;
+
+ /*
+ * PFMEMALLOC skbs are special, they should
+ * - be delivered to SOCK_MEMALLOC sockets only
+ * - stay away from userspace
+ * - have bounded memory usage
+ *
+ * Use PF_MEMALLOC as this saves us from propagating the allocation
+ * context down to all allocation sites.
+ */
+ current->flags |= PF_MEMALLOC;
+ ret = __netif_receive_skb_core(skb, true);
+ tsk_restore_flags(current, pflags, PF_MEMALLOC);
+ } else
+ ret = __netif_receive_skb_core(skb, false);
+
return ret;
}
@@ -3634,7 +3683,6 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
__be16 type = skb->protocol;
struct list_head *head = &offload_base;
int same_flow;
- int mac_len;
enum gro_result ret;
if (!(skb->dev->features & NETIF_F_GRO) || netpoll_rx_on(skb))
@@ -3651,8 +3699,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
continue;
skb_set_network_header(skb, skb_gro_offset(skb));
- mac_len = skb->network_header - skb->mac_header;
- skb->mac_len = mac_len;
+ skb_reset_mac_len(skb);
NAPI_GRO_CB(skb)->same_flow = 0;
NAPI_GRO_CB(skb)->flush = 0;
NAPI_GRO_CB(skb)->free = 0;
@@ -4056,7 +4103,7 @@ static void net_rx_action(struct softirq_action *h)
* Allow this to run for 2 jiffies since which will allow
* an average latency of 1.5/HZ.
*/
- if (unlikely(budget <= 0 || time_after(jiffies, time_limit)))
+ if (unlikely(budget <= 0 || time_after_eq(jiffies, time_limit)))
goto softnet_break;
local_irq_enable();
@@ -4134,530 +4181,231 @@ softnet_break:
goto out;
}
-static gifconf_func_t *gifconf_list[NPROTO];
-
-/**
- * register_gifconf - register a SIOCGIF handler
- * @family: Address family
- * @gifconf: Function handler
- *
- * Register protocol dependent address dumping routines. The handler
- * that is passed must not be freed or reused until it has been replaced
- * by another handler.
- */
-int register_gifconf(unsigned int family, gifconf_func_t *gifconf)
-{
- if (family >= NPROTO)
- return -EINVAL;
- gifconf_list[family] = gifconf;
- return 0;
-}
-EXPORT_SYMBOL(register_gifconf);
-
-
-/*
- * Map an interface index to its name (SIOCGIFNAME)
- */
-
-/*
- * We need this ioctl for efficient implementation of the
- * if_indextoname() function required by the IPv6 API. Without
- * it, we would have to search all the interfaces to find a
- * match. --pb
- */
-
-static int dev_ifname(struct net *net, struct ifreq __user *arg)
-{
+struct netdev_upper {
struct net_device *dev;
- struct ifreq ifr;
- unsigned seq;
-
- /*
- * Fetch the caller's info block.
- */
+ bool master;
+ struct list_head list;
+ struct rcu_head rcu;
+ struct list_head search_list;
+};
- if (copy_from_user(&ifr, arg, sizeof(struct ifreq)))
- return -EFAULT;
+static void __append_search_uppers(struct list_head *search_list,
+ struct net_device *dev)
+{
+ struct netdev_upper *upper;
-retry:
- seq = read_seqcount_begin(&devnet_rename_seq);
- rcu_read_lock();
- dev = dev_get_by_index_rcu(net, ifr.ifr_ifindex);
- if (!dev) {
- rcu_read_unlock();
- return -ENODEV;
+ list_for_each_entry(upper, &dev->upper_dev_list, list) {
+ /* check if this upper is not already in search list */
+ if (list_empty(&upper->search_list))
+ list_add_tail(&upper->search_list, search_list);
}
-
- strcpy(ifr.ifr_name, dev->name);
- rcu_read_unlock();
- if (read_seqcount_retry(&devnet_rename_seq, seq))
- goto retry;
-
- if (copy_to_user(arg, &ifr, sizeof(struct ifreq)))
- return -EFAULT;
- return 0;
}
-/*
- * Perform a SIOCGIFCONF call. This structure will change
- * size eventually, and there is nothing I can do about it.
- * Thus we will need a 'compatibility mode'.
- */
-
-static int dev_ifconf(struct net *net, char __user *arg)
+static bool __netdev_search_upper_dev(struct net_device *dev,
+ struct net_device *upper_dev)
{
- struct ifconf ifc;
- struct net_device *dev;
- char __user *pos;
- int len;
- int total;
- int i;
-
- /*
- * Fetch the caller's info block.
- */
-
- if (copy_from_user(&ifc, arg, sizeof(struct ifconf)))
- return -EFAULT;
+ LIST_HEAD(search_list);
+ struct netdev_upper *upper;
+ struct netdev_upper *tmp;
+ bool ret = false;
- pos = ifc.ifc_buf;
- len = ifc.ifc_len;
-
- /*
- * Loop over the interfaces, and write an info block for each.
- */
-
- total = 0;
- for_each_netdev(net, dev) {
- for (i = 0; i < NPROTO; i++) {
- if (gifconf_list[i]) {
- int done;
- if (!pos)
- done = gifconf_list[i](dev, NULL, 0);
- else
- done = gifconf_list[i](dev, pos + total,
- len - total);
- if (done < 0)
- return -EFAULT;
- total += done;
- }
+ __append_search_uppers(&search_list, dev);
+ list_for_each_entry(upper, &search_list, search_list) {
+ if (upper->dev == upper_dev) {
+ ret = true;
+ break;
}
+ __append_search_uppers(&search_list, upper->dev);
}
-
- /*
- * All done. Write the updated control block back to the caller.
- */
- ifc.ifc_len = total;
-
- /*
- * Both BSD and Solaris return 0 here, so we do too.
- */
- return copy_to_user(arg, &ifc, sizeof(struct ifconf)) ? -EFAULT : 0;
+ list_for_each_entry_safe(upper, tmp, &search_list, search_list)
+ INIT_LIST_HEAD(&upper->search_list);
+ return ret;
}
-#ifdef CONFIG_PROC_FS
-
-#define BUCKET_SPACE (32 - NETDEV_HASHBITS - 1)
-
-#define get_bucket(x) ((x) >> BUCKET_SPACE)
-#define get_offset(x) ((x) & ((1 << BUCKET_SPACE) - 1))
-#define set_bucket_offset(b, o) ((b) << BUCKET_SPACE | (o))
-
-static inline struct net_device *dev_from_same_bucket(struct seq_file *seq, loff_t *pos)
+static struct netdev_upper *__netdev_find_upper(struct net_device *dev,
+ struct net_device *upper_dev)
{
- struct net *net = seq_file_net(seq);
- struct net_device *dev;
- struct hlist_node *p;
- struct hlist_head *h;
- unsigned int count = 0, offset = get_offset(*pos);
+ struct netdev_upper *upper;
- h = &net->dev_name_head[get_bucket(*pos)];
- hlist_for_each_entry_rcu(dev, p, h, name_hlist) {
- if (++count == offset)
- return dev;
+ list_for_each_entry(upper, &dev->upper_dev_list, list) {
+ if (upper->dev == upper_dev)
+ return upper;
}
-
return NULL;
}
-static inline struct net_device *dev_from_bucket(struct seq_file *seq, loff_t *pos)
-{
- struct net_device *dev;
- unsigned int bucket;
-
- do {
- dev = dev_from_same_bucket(seq, pos);
- if (dev)
- return dev;
-
- bucket = get_bucket(*pos) + 1;
- *pos = set_bucket_offset(bucket, 1);
- } while (bucket < NETDEV_HASHENTRIES);
-
- return NULL;
-}
-
-/*
- * This is invoked by the /proc filesystem handler to display a device
- * in detail.
+/**
+ * netdev_has_upper_dev - Check if device is linked to an upper device
+ * @dev: device
+ * @upper_dev: upper device to check
+ *
+ * Find out if a device is linked to specified upper device and return true
+ * in case it is. Note that this checks only immediate upper device,
+ * not through a complete stack of devices. The caller must hold the RTNL lock.
*/
-void *dev_seq_start(struct seq_file *seq, loff_t *pos)
- __acquires(RCU)
+bool netdev_has_upper_dev(struct net_device *dev,
+ struct net_device *upper_dev)
{
- rcu_read_lock();
- if (!*pos)
- return SEQ_START_TOKEN;
-
- if (get_bucket(*pos) >= NETDEV_HASHENTRIES)
- return NULL;
-
- return dev_from_bucket(seq, pos);
-}
-
-void *dev_seq_next(struct seq_file *seq, void *v, loff_t *pos)
-{
- ++*pos;
- return dev_from_bucket(seq, pos);
-}
-
-void dev_seq_stop(struct seq_file *seq, void *v)
- __releases(RCU)
-{
- rcu_read_unlock();
-}
-
-static void dev_seq_printf_stats(struct seq_file *seq, struct net_device *dev)
-{
- struct rtnl_link_stats64 temp;
- const struct rtnl_link_stats64 *stats = dev_get_stats(dev, &temp);
+ ASSERT_RTNL();
- seq_printf(seq, "%6s: %7llu %7llu %4llu %4llu %4llu %5llu %10llu %9llu "
- "%8llu %7llu %4llu %4llu %4llu %5llu %7llu %10llu\n",
- dev->name, stats->rx_bytes, stats->rx_packets,
- stats->rx_errors,
- stats->rx_dropped + stats->rx_missed_errors,
- stats->rx_fifo_errors,
- stats->rx_length_errors + stats->rx_over_errors +
- stats->rx_crc_errors + stats->rx_frame_errors,
- stats->rx_compressed, stats->multicast,
- stats->tx_bytes, stats->tx_packets,
- stats->tx_errors, stats->tx_dropped,
- stats->tx_fifo_errors, stats->collisions,
- stats->tx_carrier_errors +
- stats->tx_aborted_errors +
- stats->tx_window_errors +
- stats->tx_heartbeat_errors,
- stats->tx_compressed);
+ return __netdev_find_upper(dev, upper_dev);
}
+EXPORT_SYMBOL(netdev_has_upper_dev);
-/*
- * Called from the PROCfs module. This now uses the new arbitrary sized
- * /proc/net interface to create /proc/net/dev
+/**
+ * netdev_has_any_upper_dev - Check if device is linked to some device
+ * @dev: device
+ *
+ * Find out if a device is linked to an upper device and return true in case
+ * it is. The caller must hold the RTNL lock.
*/
-static int dev_seq_show(struct seq_file *seq, void *v)
-{
- if (v == SEQ_START_TOKEN)
- seq_puts(seq, "Inter-| Receive "
- " | Transmit\n"
- " face |bytes packets errs drop fifo frame "
- "compressed multicast|bytes packets errs "
- "drop fifo colls carrier compressed\n");
- else
- dev_seq_printf_stats(seq, v);
- return 0;
-}
-
-static struct softnet_data *softnet_get_online(loff_t *pos)
-{
- struct softnet_data *sd = NULL;
-
- while (*pos < nr_cpu_ids)
- if (cpu_online(*pos)) {
- sd = &per_cpu(softnet_data, *pos);
- break;
- } else
- ++*pos;
- return sd;
-}
-
-static void *softnet_seq_start(struct seq_file *seq, loff_t *pos)
-{
- return softnet_get_online(pos);
-}
-
-static void *softnet_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+bool netdev_has_any_upper_dev(struct net_device *dev)
{
- ++*pos;
- return softnet_get_online(pos);
-}
-
-static void softnet_seq_stop(struct seq_file *seq, void *v)
-{
-}
-
-static int softnet_seq_show(struct seq_file *seq, void *v)
-{
- struct softnet_data *sd = v;
+ ASSERT_RTNL();
- seq_printf(seq, "%08x %08x %08x %08x %08x %08x %08x %08x %08x %08x\n",
- sd->processed, sd->dropped, sd->time_squeeze, 0,
- 0, 0, 0, 0, /* was fastroute */
- sd->cpu_collision, sd->received_rps);
- return 0;
+ return !list_empty(&dev->upper_dev_list);
}
+EXPORT_SYMBOL(netdev_has_any_upper_dev);
-static const struct seq_operations dev_seq_ops = {
- .start = dev_seq_start,
- .next = dev_seq_next,
- .stop = dev_seq_stop,
- .show = dev_seq_show,
-};
-
-static int dev_seq_open(struct inode *inode, struct file *file)
+/**
+ * netdev_master_upper_dev_get - Get master upper device
+ * @dev: device
+ *
+ * Find a master upper device and return pointer to it or NULL in case
+ * it's not there. The caller must hold the RTNL lock.
+ */
+struct net_device *netdev_master_upper_dev_get(struct net_device *dev)
{
- return seq_open_net(inode, file, &dev_seq_ops,
- sizeof(struct seq_net_private));
-}
+ struct netdev_upper *upper;
-static const struct file_operations dev_seq_fops = {
- .owner = THIS_MODULE,
- .open = dev_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release_net,
-};
+ ASSERT_RTNL();
-static const struct seq_operations softnet_seq_ops = {
- .start = softnet_seq_start,
- .next = softnet_seq_next,
- .stop = softnet_seq_stop,
- .show = softnet_seq_show,
-};
+ if (list_empty(&dev->upper_dev_list))
+ return NULL;
-static int softnet_seq_open(struct inode *inode, struct file *file)
-{
- return seq_open(file, &softnet_seq_ops);
+ upper = list_first_entry(&dev->upper_dev_list,
+ struct netdev_upper, list);
+ if (likely(upper->master))
+ return upper->dev;
+ return NULL;
}
+EXPORT_SYMBOL(netdev_master_upper_dev_get);
-static const struct file_operations softnet_seq_fops = {
- .owner = THIS_MODULE,
- .open = softnet_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
-
-static void *ptype_get_idx(loff_t pos)
+/**
+ * netdev_master_upper_dev_get_rcu - Get master upper device
+ * @dev: device
+ *
+ * Find a master upper device and return pointer to it or NULL in case
+ * it's not there. The caller must hold the RCU read lock.
+ */
+struct net_device *netdev_master_upper_dev_get_rcu(struct net_device *dev)
{
- struct packet_type *pt = NULL;
- loff_t i = 0;
- int t;
+ struct netdev_upper *upper;
- list_for_each_entry_rcu(pt, &ptype_all, list) {
- if (i == pos)
- return pt;
- ++i;
- }
-
- for (t = 0; t < PTYPE_HASH_SIZE; t++) {
- list_for_each_entry_rcu(pt, &ptype_base[t], list) {
- if (i == pos)
- return pt;
- ++i;
- }
- }
+ upper = list_first_or_null_rcu(&dev->upper_dev_list,
+ struct netdev_upper, list);
+ if (upper && likely(upper->master))
+ return upper->dev;
return NULL;
}
+EXPORT_SYMBOL(netdev_master_upper_dev_get_rcu);
-static void *ptype_seq_start(struct seq_file *seq, loff_t *pos)
- __acquires(RCU)
+static int __netdev_upper_dev_link(struct net_device *dev,
+ struct net_device *upper_dev, bool master)
{
- rcu_read_lock();
- return *pos ? ptype_get_idx(*pos - 1) : SEQ_START_TOKEN;
-}
+ struct netdev_upper *upper;
-static void *ptype_seq_next(struct seq_file *seq, void *v, loff_t *pos)
-{
- struct packet_type *pt;
- struct list_head *nxt;
- int hash;
+ ASSERT_RTNL();
- ++*pos;
- if (v == SEQ_START_TOKEN)
- return ptype_get_idx(0);
+ if (dev == upper_dev)
+ return -EBUSY;
- pt = v;
- nxt = pt->list.next;
- if (pt->type == htons(ETH_P_ALL)) {
- if (nxt != &ptype_all)
- goto found;
- hash = 0;
- nxt = ptype_base[0].next;
- } else
- hash = ntohs(pt->type) & PTYPE_HASH_MASK;
+ /* To prevent loops, check if dev is not upper device to upper_dev. */
+ if (__netdev_search_upper_dev(upper_dev, dev))
+ return -EBUSY;
- while (nxt == &ptype_base[hash]) {
- if (++hash >= PTYPE_HASH_SIZE)
- return NULL;
- nxt = ptype_base[hash].next;
- }
-found:
- return list_entry(nxt, struct packet_type, list);
-}
+ if (__netdev_find_upper(dev, upper_dev))
+ return -EEXIST;
-static void ptype_seq_stop(struct seq_file *seq, void *v)
- __releases(RCU)
-{
- rcu_read_unlock();
-}
+ if (master && netdev_master_upper_dev_get(dev))
+ return -EBUSY;
-static int ptype_seq_show(struct seq_file *seq, void *v)
-{
- struct packet_type *pt = v;
+ upper = kmalloc(sizeof(*upper), GFP_KERNEL);
+ if (!upper)
+ return -ENOMEM;
- if (v == SEQ_START_TOKEN)
- seq_puts(seq, "Type Device Function\n");
- else if (pt->dev == NULL || dev_net(pt->dev) == seq_file_net(seq)) {
- if (pt->type == htons(ETH_P_ALL))
- seq_puts(seq, "ALL ");
- else
- seq_printf(seq, "%04x", ntohs(pt->type));
+ upper->dev = upper_dev;
+ upper->master = master;
+ INIT_LIST_HEAD(&upper->search_list);
- seq_printf(seq, " %-8s %pF\n",
- pt->dev ? pt->dev->name : "", pt->func);
- }
+ /* Ensure that master upper link is always the first item in list. */
+ if (master)
+ list_add_rcu(&upper->list, &dev->upper_dev_list);
+ else
+ list_add_tail_rcu(&upper->list, &dev->upper_dev_list);
+ dev_hold(upper_dev);
return 0;
}
-static const struct seq_operations ptype_seq_ops = {
- .start = ptype_seq_start,
- .next = ptype_seq_next,
- .stop = ptype_seq_stop,
- .show = ptype_seq_show,
-};
-
-static int ptype_seq_open(struct inode *inode, struct file *file)
-{
- return seq_open_net(inode, file, &ptype_seq_ops,
- sizeof(struct seq_net_private));
-}
-
-static const struct file_operations ptype_seq_fops = {
- .owner = THIS_MODULE,
- .open = ptype_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release_net,
-};
-
-
-static int __net_init dev_proc_net_init(struct net *net)
-{
- int rc = -ENOMEM;
-
- if (!proc_net_fops_create(net, "dev", S_IRUGO, &dev_seq_fops))
- goto out;
- if (!proc_net_fops_create(net, "softnet_stat", S_IRUGO, &softnet_seq_fops))
- goto out_dev;
- if (!proc_net_fops_create(net, "ptype", S_IRUGO, &ptype_seq_fops))
- goto out_softnet;
-
- if (wext_proc_init(net))
- goto out_ptype;
- rc = 0;
-out:
- return rc;
-out_ptype:
- proc_net_remove(net, "ptype");
-out_softnet:
- proc_net_remove(net, "softnet_stat");
-out_dev:
- proc_net_remove(net, "dev");
- goto out;
-}
-
-static void __net_exit dev_proc_net_exit(struct net *net)
-{
- wext_proc_exit(net);
-
- proc_net_remove(net, "ptype");
- proc_net_remove(net, "softnet_stat");
- proc_net_remove(net, "dev");
-}
-
-static struct pernet_operations __net_initdata dev_proc_ops = {
- .init = dev_proc_net_init,
- .exit = dev_proc_net_exit,
-};
-
-static int __init dev_proc_init(void)
+/**
+ * netdev_upper_dev_link - Add a link to the upper device
+ * @dev: device
+ * @upper_dev: new upper device
+ *
+ * Adds a link to device which is upper to this one. The caller must hold
+ * the RTNL lock. On a failure a negative errno code is returned.
+ * On success the reference counts are adjusted and the function
+ * returns zero.
+ */
+int netdev_upper_dev_link(struct net_device *dev,
+ struct net_device *upper_dev)
{
- return register_pernet_subsys(&dev_proc_ops);
+ return __netdev_upper_dev_link(dev, upper_dev, false);
}
-#else
-#define dev_proc_init() 0
-#endif /* CONFIG_PROC_FS */
-
+EXPORT_SYMBOL(netdev_upper_dev_link);
/**
- * netdev_set_master - set up master pointer
- * @slave: slave device
- * @master: new master device
+ * netdev_master_upper_dev_link - Add a master link to the upper device
+ * @dev: device
+ * @upper_dev: new upper device
*
- * Changes the master device of the slave. Pass %NULL to break the
- * bonding. The caller must hold the RTNL semaphore. On a failure
- * a negative errno code is returned. On success the reference counts
- * are adjusted and the function returns zero.
+ * 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
+ * might be linked as well. The caller must hold the RTNL lock.
+ * On a failure a negative errno code is returned. On success the reference
+ * counts are adjusted and the function returns zero.
*/
-int netdev_set_master(struct net_device *slave, struct net_device *master)
+int netdev_master_upper_dev_link(struct net_device *dev,
+ struct net_device *upper_dev)
{
- struct net_device *old = slave->master;
-
- ASSERT_RTNL();
-
- if (master) {
- if (old)
- return -EBUSY;
- dev_hold(master);
- }
-
- slave->master = master;
-
- if (old)
- dev_put(old);
- return 0;
+ return __netdev_upper_dev_link(dev, upper_dev, true);
}
-EXPORT_SYMBOL(netdev_set_master);
+EXPORT_SYMBOL(netdev_master_upper_dev_link);
/**
- * netdev_set_bond_master - set up bonding master/slave pair
- * @slave: slave device
- * @master: new master device
+ * netdev_upper_dev_unlink - Removes a link to upper device
+ * @dev: device
+ * @upper_dev: new upper device
*
- * Changes the master device of the slave. Pass %NULL to break the
- * bonding. The caller must hold the RTNL semaphore. On a failure
- * a negative errno code is returned. On success %RTM_NEWLINK is sent
- * to the routing socket and the function returns zero.
+ * Removes a link to device which is upper to this one. The caller must hold
+ * the RTNL lock.
*/
-int netdev_set_bond_master(struct net_device *slave, struct net_device *master)
+void netdev_upper_dev_unlink(struct net_device *dev,
+ struct net_device *upper_dev)
{
- int err;
+ struct netdev_upper *upper;
ASSERT_RTNL();
- err = netdev_set_master(slave, master);
- if (err)
- return err;
- if (master)
- slave->flags |= IFF_SLAVE;
- else
- slave->flags &= ~IFF_SLAVE;
-
- rtmsg_ifinfo(RTM_NEWLINK, slave, IFF_SLAVE);
- return 0;
+ upper = __netdev_find_upper(dev, upper_dev);
+ if (!upper)
+ return;
+ list_del_rcu(&upper->list);
+ dev_put(upper_dev);
+ kfree_rcu(upper, rcu);
}
-EXPORT_SYMBOL(netdev_set_bond_master);
+EXPORT_SYMBOL(netdev_upper_dev_unlink);
static void dev_change_rx_flags(struct net_device *dev, int flags)
{
@@ -5020,381 +4768,33 @@ int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa)
if (!netif_device_present(dev))
return -ENODEV;
err = ops->ndo_set_mac_address(dev, sa);
- if (!err)
- call_netdevice_notifiers(NETDEV_CHANGEADDR, dev);
+ if (err)
+ return err;
+ dev->addr_assign_type = NET_ADDR_SET;
+ call_netdevice_notifiers(NETDEV_CHANGEADDR, dev);
add_device_randomness(dev->dev_addr, dev->addr_len);
- return err;
+ return 0;
}
EXPORT_SYMBOL(dev_set_mac_address);
-/*
- * Perform the SIOCxIFxxx calls, inside rcu_read_lock()
- */
-static int dev_ifsioc_locked(struct net *net, struct ifreq *ifr, unsigned int cmd)
-{
- int err;
- struct net_device *dev = dev_get_by_name_rcu(net, ifr->ifr_name);
-
- if (!dev)
- return -ENODEV;
-
- switch (cmd) {
- case SIOCGIFFLAGS: /* Get interface flags */
- ifr->ifr_flags = (short) dev_get_flags(dev);
- return 0;
-
- case SIOCGIFMETRIC: /* Get the metric on the interface
- (currently unused) */
- ifr->ifr_metric = 0;
- return 0;
-
- case SIOCGIFMTU: /* Get the MTU of a device */
- ifr->ifr_mtu = dev->mtu;
- return 0;
-
- case SIOCGIFHWADDR:
- if (!dev->addr_len)
- memset(ifr->ifr_hwaddr.sa_data, 0, sizeof ifr->ifr_hwaddr.sa_data);
- else
- memcpy(ifr->ifr_hwaddr.sa_data, dev->dev_addr,
- min(sizeof ifr->ifr_hwaddr.sa_data, (size_t) dev->addr_len));
- ifr->ifr_hwaddr.sa_family = dev->type;
- return 0;
-
- case SIOCGIFSLAVE:
- err = -EINVAL;
- break;
-
- case SIOCGIFMAP:
- ifr->ifr_map.mem_start = dev->mem_start;
- ifr->ifr_map.mem_end = dev->mem_end;
- ifr->ifr_map.base_addr = dev->base_addr;
- ifr->ifr_map.irq = dev->irq;
- ifr->ifr_map.dma = dev->dma;
- ifr->ifr_map.port = dev->if_port;
- return 0;
-
- case SIOCGIFINDEX:
- ifr->ifr_ifindex = dev->ifindex;
- return 0;
-
- case SIOCGIFTXQLEN:
- ifr->ifr_qlen = dev->tx_queue_len;
- return 0;
-
- default:
- /* dev_ioctl() should ensure this case
- * is never reached
- */
- WARN_ON(1);
- err = -ENOTTY;
- break;
-
- }
- return err;
-}
-
-/*
- * Perform the SIOCxIFxxx calls, inside rtnl_lock()
- */
-static int dev_ifsioc(struct net *net, struct ifreq *ifr, unsigned int cmd)
-{
- int err;
- struct net_device *dev = __dev_get_by_name(net, ifr->ifr_name);
- const struct net_device_ops *ops;
-
- if (!dev)
- return -ENODEV;
-
- ops = dev->netdev_ops;
-
- switch (cmd) {
- case SIOCSIFFLAGS: /* Set interface flags */
- return dev_change_flags(dev, ifr->ifr_flags);
-
- case SIOCSIFMETRIC: /* Set the metric on the interface
- (currently unused) */
- return -EOPNOTSUPP;
-
- case SIOCSIFMTU: /* Set the MTU of a device */
- return dev_set_mtu(dev, ifr->ifr_mtu);
-
- case SIOCSIFHWADDR:
- return dev_set_mac_address(dev, &ifr->ifr_hwaddr);
-
- case SIOCSIFHWBROADCAST:
- if (ifr->ifr_hwaddr.sa_family != dev->type)
- return -EINVAL;
- memcpy(dev->broadcast, ifr->ifr_hwaddr.sa_data,
- min(sizeof ifr->ifr_hwaddr.sa_data, (size_t) dev->addr_len));
- call_netdevice_notifiers(NETDEV_CHANGEADDR, dev);
- return 0;
-
- case SIOCSIFMAP:
- if (ops->ndo_set_config) {
- if (!netif_device_present(dev))
- return -ENODEV;
- return ops->ndo_set_config(dev, &ifr->ifr_map);
- }
- return -EOPNOTSUPP;
-
- case SIOCADDMULTI:
- if (!ops->ndo_set_rx_mode ||
- ifr->ifr_hwaddr.sa_family != AF_UNSPEC)
- return -EINVAL;
- if (!netif_device_present(dev))
- return -ENODEV;
- return dev_mc_add_global(dev, ifr->ifr_hwaddr.sa_data);
-
- case SIOCDELMULTI:
- if (!ops->ndo_set_rx_mode ||
- ifr->ifr_hwaddr.sa_family != AF_UNSPEC)
- return -EINVAL;
- if (!netif_device_present(dev))
- return -ENODEV;
- return dev_mc_del_global(dev, ifr->ifr_hwaddr.sa_data);
-
- case SIOCSIFTXQLEN:
- if (ifr->ifr_qlen < 0)
- return -EINVAL;
- dev->tx_queue_len = ifr->ifr_qlen;
- return 0;
-
- case SIOCSIFNAME:
- ifr->ifr_newname[IFNAMSIZ-1] = '\0';
- return dev_change_name(dev, ifr->ifr_newname);
-
- case SIOCSHWTSTAMP:
- err = net_hwtstamp_validate(ifr);
- if (err)
- return err;
- /* fall through */
-
- /*
- * Unknown or private ioctl
- */
- default:
- if ((cmd >= SIOCDEVPRIVATE &&
- cmd <= SIOCDEVPRIVATE + 15) ||
- cmd == SIOCBONDENSLAVE ||
- cmd == SIOCBONDRELEASE ||
- cmd == SIOCBONDSETHWADDR ||
- cmd == SIOCBONDSLAVEINFOQUERY ||
- cmd == SIOCBONDINFOQUERY ||
- cmd == SIOCBONDCHANGEACTIVE ||
- cmd == SIOCGMIIPHY ||
- cmd == SIOCGMIIREG ||
- cmd == SIOCSMIIREG ||
- cmd == SIOCBRADDIF ||
- cmd == SIOCBRDELIF ||
- cmd == SIOCSHWTSTAMP ||
- cmd == SIOCWANDEV) {
- err = -EOPNOTSUPP;
- if (ops->ndo_do_ioctl) {
- if (netif_device_present(dev))
- err = ops->ndo_do_ioctl(dev, ifr, cmd);
- else
- err = -ENODEV;
- }
- } else
- err = -EINVAL;
-
- }
- return err;
-}
-
-/*
- * This function handles all "interface"-type I/O control requests. The actual
- * 'doing' part of this is dev_ifsioc above.
- */
-
/**
- * dev_ioctl - network device ioctl
- * @net: the applicable net namespace
- * @cmd: command to issue
- * @arg: pointer to a struct ifreq in user space
+ * dev_change_carrier - Change device carrier
+ * @dev: device
+ * @new_carrier: new value
*
- * Issue ioctl functions to devices. This is normally called by the
- * user space syscall interfaces but can sometimes be useful for
- * other purposes. The return value is the return from the syscall if
- * positive or a negative errno code on error.
+ * Change device carrier
*/
-
-int dev_ioctl(struct net *net, unsigned int cmd, void __user *arg)
+int dev_change_carrier(struct net_device *dev, bool new_carrier)
{
- struct ifreq ifr;
- int ret;
- char *colon;
-
- /* One special case: SIOCGIFCONF takes ifconf argument
- and requires shared lock, because it sleeps writing
- to user space.
- */
-
- if (cmd == SIOCGIFCONF) {
- rtnl_lock();
- ret = dev_ifconf(net, (char __user *) arg);
- rtnl_unlock();
- return ret;
- }
- if (cmd == SIOCGIFNAME)
- return dev_ifname(net, (struct ifreq __user *)arg);
-
- if (copy_from_user(&ifr, arg, sizeof(struct ifreq)))
- return -EFAULT;
-
- ifr.ifr_name[IFNAMSIZ-1] = 0;
-
- colon = strchr(ifr.ifr_name, ':');
- if (colon)
- *colon = 0;
-
- /*
- * See which interface the caller is talking about.
- */
-
- switch (cmd) {
- /*
- * These ioctl calls:
- * - can be done by all.
- * - atomic and do not require locking.
- * - return a value
- */
- case SIOCGIFFLAGS:
- case SIOCGIFMETRIC:
- case SIOCGIFMTU:
- case SIOCGIFHWADDR:
- case SIOCGIFSLAVE:
- case SIOCGIFMAP:
- case SIOCGIFINDEX:
- case SIOCGIFTXQLEN:
- dev_load(net, ifr.ifr_name);
- rcu_read_lock();
- ret = dev_ifsioc_locked(net, &ifr, cmd);
- rcu_read_unlock();
- if (!ret) {
- if (colon)
- *colon = ':';
- if (copy_to_user(arg, &ifr,
- sizeof(struct ifreq)))
- ret = -EFAULT;
- }
- return ret;
-
- case SIOCETHTOOL:
- dev_load(net, ifr.ifr_name);
- rtnl_lock();
- ret = dev_ethtool(net, &ifr);
- rtnl_unlock();
- if (!ret) {
- if (colon)
- *colon = ':';
- if (copy_to_user(arg, &ifr,
- sizeof(struct ifreq)))
- ret = -EFAULT;
- }
- return ret;
-
- /*
- * These ioctl calls:
- * - require superuser power.
- * - require strict serialization.
- * - return a value
- */
- case SIOCGMIIPHY:
- case SIOCGMIIREG:
- case SIOCSIFNAME:
- if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
- return -EPERM;
- dev_load(net, ifr.ifr_name);
- rtnl_lock();
- ret = dev_ifsioc(net, &ifr, cmd);
- rtnl_unlock();
- if (!ret) {
- if (colon)
- *colon = ':';
- if (copy_to_user(arg, &ifr,
- sizeof(struct ifreq)))
- ret = -EFAULT;
- }
- return ret;
-
- /*
- * These ioctl calls:
- * - require superuser power.
- * - require strict serialization.
- * - do not return a value
- */
- case SIOCSIFMAP:
- case SIOCSIFTXQLEN:
- if (!capable(CAP_NET_ADMIN))
- return -EPERM;
- /* fall through */
- /*
- * These ioctl calls:
- * - require local superuser power.
- * - require strict serialization.
- * - do not return a value
- */
- case SIOCSIFFLAGS:
- case SIOCSIFMETRIC:
- case SIOCSIFMTU:
- case SIOCSIFHWADDR:
- case SIOCSIFSLAVE:
- case SIOCADDMULTI:
- case SIOCDELMULTI:
- case SIOCSIFHWBROADCAST:
- case SIOCSMIIREG:
- case SIOCBONDENSLAVE:
- case SIOCBONDRELEASE:
- case SIOCBONDSETHWADDR:
- case SIOCBONDCHANGEACTIVE:
- case SIOCBRADDIF:
- case SIOCBRDELIF:
- case SIOCSHWTSTAMP:
- if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
- return -EPERM;
- /* fall through */
- case SIOCBONDSLAVEINFOQUERY:
- case SIOCBONDINFOQUERY:
- dev_load(net, ifr.ifr_name);
- rtnl_lock();
- ret = dev_ifsioc(net, &ifr, cmd);
- rtnl_unlock();
- return ret;
-
- case SIOCGIFMEM:
- /* Get the per device memory space. We can add this but
- * currently do not support it */
- case SIOCSIFMEM:
- /* Set the per device memory buffer space.
- * Not applicable in our case */
- case SIOCSIFLINK:
- return -ENOTTY;
+ const struct net_device_ops *ops = dev->netdev_ops;
- /*
- * Unknown or private ioctl.
- */
- default:
- if (cmd == SIOCWANDEV ||
- (cmd >= SIOCDEVPRIVATE &&
- cmd <= SIOCDEVPRIVATE + 15)) {
- dev_load(net, ifr.ifr_name);
- rtnl_lock();
- ret = dev_ifsioc(net, &ifr, cmd);
- rtnl_unlock();
- if (!ret && copy_to_user(arg, &ifr,
- sizeof(struct ifreq)))
- ret = -EFAULT;
- return ret;
- }
- /* Take care of Wireless Extensions */
- if (cmd >= SIOCIWFIRST && cmd <= SIOCIWLAST)
- return wext_handle_ioctl(net, &ifr, cmd, arg);
- return -ENOTTY;
- }
+ if (!ops->ndo_change_carrier)
+ return -EOPNOTSUPP;
+ if (!netif_device_present(dev))
+ return -ENODEV;
+ return ops->ndo_change_carrier(dev, new_carrier);
}
-
+EXPORT_SYMBOL(dev_change_carrier);
/**
* dev_new_index - allocate an ifindex
@@ -5482,11 +4882,15 @@ static void rollback_registered_many(struct list_head *head)
if (dev->netdev_ops->ndo_uninit)
dev->netdev_ops->ndo_uninit(dev);
- /* Notifier chain MUST detach us from master device. */
- WARN_ON(dev->master);
+ /* Notifier chain MUST detach us all upper devices. */
+ WARN_ON(netdev_has_any_upper_dev(dev));
/* Remove entries from kobject tree */
netdev_unregister_kobject(dev);
+#ifdef CONFIG_XPS
+ /* Remove XPS queueing entries */
+ netif_reset_xps_queues_gt(dev, 0);
+#endif
}
synchronize_net();
@@ -5664,10 +5068,9 @@ static int netif_alloc_rx_queues(struct net_device *dev)
BUG_ON(count < 1);
rx = kcalloc(count, sizeof(struct netdev_rx_queue), GFP_KERNEL);
- if (!rx) {
- pr_err("netdev: Unable to allocate %u rx queues\n", count);
+ if (!rx)
return -ENOMEM;
- }
+
dev->_rx = rx;
for (i = 0; i < count; i++)
@@ -5698,10 +5101,9 @@ static int netif_alloc_netdev_queues(struct net_device *dev)
BUG_ON(count < 1);
tx = kcalloc(count, sizeof(struct netdev_queue), GFP_KERNEL);
- if (!tx) {
- pr_err("netdev: Unable to allocate %u tx queues\n", count);
+ if (!tx)
return -ENOMEM;
- }
+
dev->_tx = tx;
netdev_for_each_tx_queue(dev, netdev_init_one_queue, NULL);
@@ -5760,6 +5162,14 @@ int register_netdevice(struct net_device *dev)
}
}
+ if (((dev->hw_features | dev->features) & NETIF_F_HW_VLAN_FILTER) &&
+ (!dev->netdev_ops->ndo_vlan_rx_add_vid ||
+ !dev->netdev_ops->ndo_vlan_rx_kill_vid)) {
+ netdev_WARN(dev, "Buggy VLAN acceleration in driver!\n");
+ ret = -EINVAL;
+ goto err_uninit;
+ }
+
ret = -EBUSY;
if (!dev->ifindex)
dev->ifindex = dev_new_index(net);
@@ -5815,6 +5225,13 @@ int register_netdevice(struct net_device *dev)
list_netdevice(dev);
add_device_randomness(dev->dev_addr, dev->addr_len);
+ /* If the device has permanent device address, driver should
+ * set dev_addr and also addr_assign_type should be set to
+ * NET_ADDR_PERM (default value).
+ */
+ if (dev->addr_assign_type == NET_ADDR_PERM)
+ memcpy(dev->perm_addr, dev->dev_addr, dev->addr_len);
+
/* Notify protocols, that a new device appeared. */
ret = call_netdevice_notifiers(NETDEV_REGISTER, dev);
ret = notifier_to_errno(ret);
@@ -6173,10 +5590,8 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
alloc_size += NETDEV_ALIGN - 1;
p = kzalloc(alloc_size, GFP_KERNEL);
- if (!p) {
- pr_err("alloc_netdev: Unable to allocate device\n");
+ if (!p)
return NULL;
- }
dev = PTR_ALIGN(p, NETDEV_ALIGN);
dev->padded = (char *)dev - (char *)p;
@@ -6199,6 +5614,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
INIT_LIST_HEAD(&dev->napi_list);
INIT_LIST_HEAD(&dev->unreg_list);
INIT_LIST_HEAD(&dev->link_watch_list);
+ INIT_LIST_HEAD(&dev->upper_dev_list);
dev->priv_flags = IFF_XMIT_DST_RELEASE;
setup(dev);
@@ -6842,19 +6258,9 @@ static int __init net_dev_init(void)
hotcpu_notifier(dev_cpu_callback, 0);
dst_init();
- dev_mcast_init();
rc = 0;
out:
return rc;
}
subsys_initcall(net_dev_init);
-
-static int __init initialize_hashrnd(void)
-{
- get_random_bytes(&hashrnd, sizeof(hashrnd));
- return 0;
-}
-
-late_initcall_sync(initialize_hashrnd);
-
diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c
index b079c7bbc157..bd2eb9d3e369 100644
--- a/net/core/dev_addr_lists.c
+++ b/net/core/dev_addr_lists.c
@@ -15,7 +15,6 @@
#include <linux/rtnetlink.h>
#include <linux/export.h>
#include <linux/list.h>
-#include <linux/proc_fs.h>
/*
* General list handling functions
@@ -727,76 +726,3 @@ void dev_mc_init(struct net_device *dev)
__hw_addr_init(&dev->mc);
}
EXPORT_SYMBOL(dev_mc_init);
-
-#ifdef CONFIG_PROC_FS
-#include <linux/seq_file.h>
-
-static int dev_mc_seq_show(struct seq_file *seq, void *v)
-{
- struct netdev_hw_addr *ha;
- struct net_device *dev = v;
-
- if (v == SEQ_START_TOKEN)
- return 0;
-
- 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');
- }
- netif_addr_unlock_bh(dev);
- return 0;
-}
-
-static const struct seq_operations dev_mc_seq_ops = {
- .start = dev_seq_start,
- .next = dev_seq_next,
- .stop = dev_seq_stop,
- .show = dev_mc_seq_show,
-};
-
-static int dev_mc_seq_open(struct inode *inode, struct file *file)
-{
- return seq_open_net(inode, file, &dev_mc_seq_ops,
- sizeof(struct seq_net_private));
-}
-
-static const struct file_operations dev_mc_seq_fops = {
- .owner = THIS_MODULE,
- .open = dev_mc_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release_net,
-};
-
-#endif
-
-static int __net_init dev_mc_net_init(struct net *net)
-{
- if (!proc_net_fops_create(net, "dev_mcast", 0, &dev_mc_seq_fops))
- return -ENOMEM;
- return 0;
-}
-
-static void __net_exit dev_mc_net_exit(struct net *net)
-{
- proc_net_remove(net, "dev_mcast");
-}
-
-static struct pernet_operations __net_initdata dev_mc_net_ops = {
- .init = dev_mc_net_init,
- .exit = dev_mc_net_exit,
-};
-
-void __init dev_mcast_init(void)
-{
- register_pernet_subsys(&dev_mc_net_ops);
-}
-
diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c
new file mode 100644
index 000000000000..6cc0481faade
--- /dev/null
+++ b/net/core/dev_ioctl.c
@@ -0,0 +1,576 @@
+#include <linux/kmod.h>
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/rtnetlink.h>
+#include <linux/net_tstamp.h>
+#include <linux/wireless.h>
+#include <net/wext.h>
+
+/*
+ * Map an interface index to its name (SIOCGIFNAME)
+ */
+
+/*
+ * We need this ioctl for efficient implementation of the
+ * if_indextoname() function required by the IPv6 API. Without
+ * it, we would have to search all the interfaces to find a
+ * match. --pb
+ */
+
+static int dev_ifname(struct net *net, struct ifreq __user *arg)
+{
+ struct net_device *dev;
+ struct ifreq ifr;
+ unsigned seq;
+
+ /*
+ * Fetch the caller's info block.
+ */
+
+ if (copy_from_user(&ifr, arg, sizeof(struct ifreq)))
+ return -EFAULT;
+
+retry:
+ seq = read_seqcount_begin(&devnet_rename_seq);
+ rcu_read_lock();
+ dev = dev_get_by_index_rcu(net, ifr.ifr_ifindex);
+ if (!dev) {
+ rcu_read_unlock();
+ return -ENODEV;
+ }
+
+ strcpy(ifr.ifr_name, dev->name);
+ rcu_read_unlock();
+ if (read_seqcount_retry(&devnet_rename_seq, seq))
+ goto retry;
+
+ if (copy_to_user(arg, &ifr, sizeof(struct ifreq)))
+ return -EFAULT;
+ return 0;
+}
+
+static gifconf_func_t *gifconf_list[NPROTO];
+
+/**
+ * register_gifconf - register a SIOCGIF handler
+ * @family: Address family
+ * @gifconf: Function handler
+ *
+ * Register protocol dependent address dumping routines. The handler
+ * that is passed must not be freed or reused until it has been replaced
+ * by another handler.
+ */
+int register_gifconf(unsigned int family, gifconf_func_t *gifconf)
+{
+ if (family >= NPROTO)
+ return -EINVAL;
+ gifconf_list[family] = gifconf;
+ return 0;
+}
+EXPORT_SYMBOL(register_gifconf);
+
+/*
+ * Perform a SIOCGIFCONF call. This structure will change
+ * size eventually, and there is nothing I can do about it.
+ * Thus we will need a 'compatibility mode'.
+ */
+
+static int dev_ifconf(struct net *net, char __user *arg)
+{
+ struct ifconf ifc;
+ struct net_device *dev;
+ char __user *pos;
+ int len;
+ int total;
+ int i;
+
+ /*
+ * Fetch the caller's info block.
+ */
+
+ if (copy_from_user(&ifc, arg, sizeof(struct ifconf)))
+ return -EFAULT;
+
+ pos = ifc.ifc_buf;
+ len = ifc.ifc_len;
+
+ /*
+ * Loop over the interfaces, and write an info block for each.
+ */
+
+ total = 0;
+ for_each_netdev(net, dev) {
+ for (i = 0; i < NPROTO; i++) {
+ if (gifconf_list[i]) {
+ int done;
+ if (!pos)
+ done = gifconf_list[i](dev, NULL, 0);
+ else
+ done = gifconf_list[i](dev, pos + total,
+ len - total);
+ if (done < 0)
+ return -EFAULT;
+ total += done;
+ }
+ }
+ }
+
+ /*
+ * All done. Write the updated control block back to the caller.
+ */
+ ifc.ifc_len = total;
+
+ /*
+ * Both BSD and Solaris return 0 here, so we do too.
+ */
+ return copy_to_user(arg, &ifc, sizeof(struct ifconf)) ? -EFAULT : 0;
+}
+
+/*
+ * Perform the SIOCxIFxxx calls, inside rcu_read_lock()
+ */
+static int dev_ifsioc_locked(struct net *net, struct ifreq *ifr, unsigned int cmd)
+{
+ int err;
+ struct net_device *dev = dev_get_by_name_rcu(net, ifr->ifr_name);
+
+ if (!dev)
+ return -ENODEV;
+
+ switch (cmd) {
+ case SIOCGIFFLAGS: /* Get interface flags */
+ ifr->ifr_flags = (short) dev_get_flags(dev);
+ return 0;
+
+ case SIOCGIFMETRIC: /* Get the metric on the interface
+ (currently unused) */
+ ifr->ifr_metric = 0;
+ return 0;
+
+ case SIOCGIFMTU: /* Get the MTU of a device */
+ ifr->ifr_mtu = dev->mtu;
+ return 0;
+
+ case SIOCGIFHWADDR:
+ if (!dev->addr_len)
+ memset(ifr->ifr_hwaddr.sa_data, 0, sizeof ifr->ifr_hwaddr.sa_data);
+ else
+ memcpy(ifr->ifr_hwaddr.sa_data, dev->dev_addr,
+ min(sizeof ifr->ifr_hwaddr.sa_data, (size_t) dev->addr_len));
+ ifr->ifr_hwaddr.sa_family = dev->type;
+ return 0;
+
+ case SIOCGIFSLAVE:
+ err = -EINVAL;
+ break;
+
+ case SIOCGIFMAP:
+ ifr->ifr_map.mem_start = dev->mem_start;
+ ifr->ifr_map.mem_end = dev->mem_end;
+ ifr->ifr_map.base_addr = dev->base_addr;
+ ifr->ifr_map.irq = dev->irq;
+ ifr->ifr_map.dma = dev->dma;
+ ifr->ifr_map.port = dev->if_port;
+ return 0;
+
+ case SIOCGIFINDEX:
+ ifr->ifr_ifindex = dev->ifindex;
+ return 0;
+
+ case SIOCGIFTXQLEN:
+ ifr->ifr_qlen = dev->tx_queue_len;
+ return 0;
+
+ default:
+ /* dev_ioctl() should ensure this case
+ * is never reached
+ */
+ WARN_ON(1);
+ err = -ENOTTY;
+ break;
+
+ }
+ return err;
+}
+
+static int net_hwtstamp_validate(struct ifreq *ifr)
+{
+ struct hwtstamp_config cfg;
+ enum hwtstamp_tx_types tx_type;
+ enum hwtstamp_rx_filters rx_filter;
+ int tx_type_valid = 0;
+ int rx_filter_valid = 0;
+
+ if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg)))
+ return -EFAULT;
+
+ if (cfg.flags) /* reserved for future extensions */
+ return -EINVAL;
+
+ tx_type = cfg.tx_type;
+ rx_filter = cfg.rx_filter;
+
+ switch (tx_type) {
+ case HWTSTAMP_TX_OFF:
+ case HWTSTAMP_TX_ON:
+ case HWTSTAMP_TX_ONESTEP_SYNC:
+ tx_type_valid = 1;
+ break;
+ }
+
+ switch (rx_filter) {
+ case HWTSTAMP_FILTER_NONE:
+ case HWTSTAMP_FILTER_ALL:
+ case HWTSTAMP_FILTER_SOME:
+ case HWTSTAMP_FILTER_PTP_V1_L4_EVENT:
+ case HWTSTAMP_FILTER_PTP_V1_L4_SYNC:
+ case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ:
+ case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
+ case HWTSTAMP_FILTER_PTP_V2_L4_SYNC:
+ case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ:
+ case HWTSTAMP_FILTER_PTP_V2_L2_EVENT:
+ case HWTSTAMP_FILTER_PTP_V2_L2_SYNC:
+ case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ:
+ case HWTSTAMP_FILTER_PTP_V2_EVENT:
+ case HWTSTAMP_FILTER_PTP_V2_SYNC:
+ case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
+ rx_filter_valid = 1;
+ break;
+ }
+
+ if (!tx_type_valid || !rx_filter_valid)
+ return -ERANGE;
+
+ return 0;
+}
+
+/*
+ * Perform the SIOCxIFxxx calls, inside rtnl_lock()
+ */
+static int dev_ifsioc(struct net *net, struct ifreq *ifr, unsigned int cmd)
+{
+ int err;
+ struct net_device *dev = __dev_get_by_name(net, ifr->ifr_name);
+ const struct net_device_ops *ops;
+
+ if (!dev)
+ return -ENODEV;
+
+ ops = dev->netdev_ops;
+
+ switch (cmd) {
+ case SIOCSIFFLAGS: /* Set interface flags */
+ return dev_change_flags(dev, ifr->ifr_flags);
+
+ case SIOCSIFMETRIC: /* Set the metric on the interface
+ (currently unused) */
+ return -EOPNOTSUPP;
+
+ case SIOCSIFMTU: /* Set the MTU of a device */
+ return dev_set_mtu(dev, ifr->ifr_mtu);
+
+ case SIOCSIFHWADDR:
+ return dev_set_mac_address(dev, &ifr->ifr_hwaddr);
+
+ case SIOCSIFHWBROADCAST:
+ if (ifr->ifr_hwaddr.sa_family != dev->type)
+ return -EINVAL;
+ memcpy(dev->broadcast, ifr->ifr_hwaddr.sa_data,
+ min(sizeof ifr->ifr_hwaddr.sa_data, (size_t) dev->addr_len));
+ call_netdevice_notifiers(NETDEV_CHANGEADDR, dev);
+ return 0;
+
+ case SIOCSIFMAP:
+ if (ops->ndo_set_config) {
+ if (!netif_device_present(dev))
+ return -ENODEV;
+ return ops->ndo_set_config(dev, &ifr->ifr_map);
+ }
+ return -EOPNOTSUPP;
+
+ case SIOCADDMULTI:
+ if (!ops->ndo_set_rx_mode ||
+ ifr->ifr_hwaddr.sa_family != AF_UNSPEC)
+ return -EINVAL;
+ if (!netif_device_present(dev))
+ return -ENODEV;
+ return dev_mc_add_global(dev, ifr->ifr_hwaddr.sa_data);
+
+ case SIOCDELMULTI:
+ if (!ops->ndo_set_rx_mode ||
+ ifr->ifr_hwaddr.sa_family != AF_UNSPEC)
+ return -EINVAL;
+ if (!netif_device_present(dev))
+ return -ENODEV;
+ return dev_mc_del_global(dev, ifr->ifr_hwaddr.sa_data);
+
+ case SIOCSIFTXQLEN:
+ if (ifr->ifr_qlen < 0)
+ return -EINVAL;
+ dev->tx_queue_len = ifr->ifr_qlen;
+ return 0;
+
+ case SIOCSIFNAME:
+ ifr->ifr_newname[IFNAMSIZ-1] = '\0';
+ return dev_change_name(dev, ifr->ifr_newname);
+
+ case SIOCSHWTSTAMP:
+ err = net_hwtstamp_validate(ifr);
+ if (err)
+ return err;
+ /* fall through */
+
+ /*
+ * Unknown or private ioctl
+ */
+ default:
+ if ((cmd >= SIOCDEVPRIVATE &&
+ cmd <= SIOCDEVPRIVATE + 15) ||
+ cmd == SIOCBONDENSLAVE ||
+ cmd == SIOCBONDRELEASE ||
+ cmd == SIOCBONDSETHWADDR ||
+ cmd == SIOCBONDSLAVEINFOQUERY ||
+ cmd == SIOCBONDINFOQUERY ||
+ cmd == SIOCBONDCHANGEACTIVE ||
+ cmd == SIOCGMIIPHY ||
+ cmd == SIOCGMIIREG ||
+ cmd == SIOCSMIIREG ||
+ cmd == SIOCBRADDIF ||
+ cmd == SIOCBRDELIF ||
+ cmd == SIOCSHWTSTAMP ||
+ cmd == SIOCWANDEV) {
+ err = -EOPNOTSUPP;
+ if (ops->ndo_do_ioctl) {
+ if (netif_device_present(dev))
+ err = ops->ndo_do_ioctl(dev, ifr, cmd);
+ else
+ err = -ENODEV;
+ }
+ } else
+ err = -EINVAL;
+
+ }
+ return err;
+}
+
+/**
+ * dev_load - load a network module
+ * @net: the applicable net namespace
+ * @name: name of interface
+ *
+ * If a network interface is not present and the process has suitable
+ * privileges this function loads the module. If module loading is not
+ * available in this kernel then it becomes a nop.
+ */
+
+void dev_load(struct net *net, const char *name)
+{
+ struct net_device *dev;
+ int no_module;
+
+ rcu_read_lock();
+ dev = dev_get_by_name_rcu(net, name);
+ rcu_read_unlock();
+
+ no_module = !dev;
+ if (no_module && capable(CAP_NET_ADMIN))
+ no_module = request_module("netdev-%s", name);
+ if (no_module && capable(CAP_SYS_MODULE)) {
+ if (!request_module("%s", name))
+ pr_warn("Loading kernel module for a network device with CAP_SYS_MODULE (deprecated). Use CAP_NET_ADMIN and alias netdev-%s instead.\n",
+ name);
+ }
+}
+EXPORT_SYMBOL(dev_load);
+
+/*
+ * This function handles all "interface"-type I/O control requests. The actual
+ * 'doing' part of this is dev_ifsioc above.
+ */
+
+/**
+ * dev_ioctl - network device ioctl
+ * @net: the applicable net namespace
+ * @cmd: command to issue
+ * @arg: pointer to a struct ifreq in user space
+ *
+ * Issue ioctl functions to devices. This is normally called by the
+ * user space syscall interfaces but can sometimes be useful for
+ * other purposes. The return value is the return from the syscall if
+ * positive or a negative errno code on error.
+ */
+
+int dev_ioctl(struct net *net, unsigned int cmd, void __user *arg)
+{
+ struct ifreq ifr;
+ int ret;
+ char *colon;
+
+ /* One special case: SIOCGIFCONF takes ifconf argument
+ and requires shared lock, because it sleeps writing
+ to user space.
+ */
+
+ if (cmd == SIOCGIFCONF) {
+ rtnl_lock();
+ ret = dev_ifconf(net, (char __user *) arg);
+ rtnl_unlock();
+ return ret;
+ }
+ if (cmd == SIOCGIFNAME)
+ return dev_ifname(net, (struct ifreq __user *)arg);
+
+ if (copy_from_user(&ifr, arg, sizeof(struct ifreq)))
+ return -EFAULT;
+
+ ifr.ifr_name[IFNAMSIZ-1] = 0;
+
+ colon = strchr(ifr.ifr_name, ':');
+ if (colon)
+ *colon = 0;
+
+ /*
+ * See which interface the caller is talking about.
+ */
+
+ switch (cmd) {
+ /*
+ * These ioctl calls:
+ * - can be done by all.
+ * - atomic and do not require locking.
+ * - return a value
+ */
+ case SIOCGIFFLAGS:
+ case SIOCGIFMETRIC:
+ case SIOCGIFMTU:
+ case SIOCGIFHWADDR:
+ case SIOCGIFSLAVE:
+ case SIOCGIFMAP:
+ case SIOCGIFINDEX:
+ case SIOCGIFTXQLEN:
+ dev_load(net, ifr.ifr_name);
+ rcu_read_lock();
+ ret = dev_ifsioc_locked(net, &ifr, cmd);
+ rcu_read_unlock();
+ if (!ret) {
+ if (colon)
+ *colon = ':';
+ if (copy_to_user(arg, &ifr,
+ sizeof(struct ifreq)))
+ ret = -EFAULT;
+ }
+ return ret;
+
+ case SIOCETHTOOL:
+ dev_load(net, ifr.ifr_name);
+ rtnl_lock();
+ ret = dev_ethtool(net, &ifr);
+ rtnl_unlock();
+ if (!ret) {
+ if (colon)
+ *colon = ':';
+ if (copy_to_user(arg, &ifr,
+ sizeof(struct ifreq)))
+ ret = -EFAULT;
+ }
+ return ret;
+
+ /*
+ * These ioctl calls:
+ * - require superuser power.
+ * - require strict serialization.
+ * - return a value
+ */
+ case SIOCGMIIPHY:
+ case SIOCGMIIREG:
+ case SIOCSIFNAME:
+ if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
+ return -EPERM;
+ dev_load(net, ifr.ifr_name);
+ rtnl_lock();
+ ret = dev_ifsioc(net, &ifr, cmd);
+ rtnl_unlock();
+ if (!ret) {
+ if (colon)
+ *colon = ':';
+ if (copy_to_user(arg, &ifr,
+ sizeof(struct ifreq)))
+ ret = -EFAULT;
+ }
+ return ret;
+
+ /*
+ * These ioctl calls:
+ * - require superuser power.
+ * - require strict serialization.
+ * - do not return a value
+ */
+ case SIOCSIFMAP:
+ case SIOCSIFTXQLEN:
+ if (!capable(CAP_NET_ADMIN))
+ return -EPERM;
+ /* fall through */
+ /*
+ * These ioctl calls:
+ * - require local superuser power.
+ * - require strict serialization.
+ * - do not return a value
+ */
+ case SIOCSIFFLAGS:
+ case SIOCSIFMETRIC:
+ case SIOCSIFMTU:
+ case SIOCSIFHWADDR:
+ case SIOCSIFSLAVE:
+ case SIOCADDMULTI:
+ case SIOCDELMULTI:
+ case SIOCSIFHWBROADCAST:
+ case SIOCSMIIREG:
+ case SIOCBONDENSLAVE:
+ case SIOCBONDRELEASE:
+ case SIOCBONDSETHWADDR:
+ case SIOCBONDCHANGEACTIVE:
+ case SIOCBRADDIF:
+ case SIOCBRDELIF:
+ case SIOCSHWTSTAMP:
+ if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
+ return -EPERM;
+ /* fall through */
+ case SIOCBONDSLAVEINFOQUERY:
+ case SIOCBONDINFOQUERY:
+ dev_load(net, ifr.ifr_name);
+ rtnl_lock();
+ ret = dev_ifsioc(net, &ifr, cmd);
+ rtnl_unlock();
+ return ret;
+
+ case SIOCGIFMEM:
+ /* Get the per device memory space. We can add this but
+ * currently do not support it */
+ case SIOCSIFMEM:
+ /* Set the per device memory buffer space.
+ * Not applicable in our case */
+ case SIOCSIFLINK:
+ return -ENOTTY;
+
+ /*
+ * Unknown or private ioctl.
+ */
+ default:
+ if (cmd == SIOCWANDEV ||
+ (cmd >= SIOCDEVPRIVATE &&
+ cmd <= SIOCDEVPRIVATE + 15)) {
+ dev_load(net, ifr.ifr_name);
+ rtnl_lock();
+ ret = dev_ifsioc(net, &ifr, cmd);
+ rtnl_unlock();
+ if (!ret && copy_to_user(arg, &ifr,
+ sizeof(struct ifreq)))
+ ret = -EFAULT;
+ return ret;
+ }
+ /* Take care of Wireless Extensions */
+ if (cmd >= SIOCIWFIRST && cmd <= SIOCIWLAST)
+ return wext_handle_ioctl(net, &ifr, cmd, arg);
+ return -ENOTTY;
+ }
+}
diff --git a/net/core/dst.c b/net/core/dst.c
index ee6153e2cf43..35fd12f1a69c 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -179,6 +179,7 @@ void *dst_alloc(struct dst_ops *ops, struct net_device *dev,
dst_init_metrics(dst, dst_default_metrics, true);
dst->expires = 0UL;
dst->path = dst;
+ dst->from = NULL;
#ifdef CONFIG_XFRM
dst->xfrm = NULL;
#endif
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index a8705432e4b1..3e9b2c3e30f0 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -77,6 +77,7 @@ static const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN]
[NETIF_F_TSO_ECN_BIT] = "tx-tcp-ecn-segmentation",
[NETIF_F_TSO6_BIT] = "tx-tcp6-segmentation",
[NETIF_F_FSO_BIT] = "tx-fcoe-segmentation",
+ [NETIF_F_GSO_GRE_BIT] = "tx-gre-segmentation",
[NETIF_F_FCOE_CRC_BIT] = "tx-checksum-fcoe-crc",
[NETIF_F_SCTP_CSUM_BIT] = "tx-checksum-sctp",
@@ -175,7 +176,7 @@ static int __ethtool_get_sset_count(struct net_device *dev, int sset)
if (sset == ETH_SS_FEATURES)
return ARRAY_SIZE(netdev_features_strings);
- if (ops && ops->get_sset_count && ops->get_strings)
+ if (ops->get_sset_count && ops->get_strings)
return ops->get_sset_count(dev, sset);
else
return -EOPNOTSUPP;
@@ -311,7 +312,7 @@ int __ethtool_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
{
ASSERT_RTNL();
- if (!dev->ethtool_ops || !dev->ethtool_ops->get_settings)
+ if (!dev->ethtool_ops->get_settings)
return -EOPNOTSUPP;
memset(cmd, 0, sizeof(struct ethtool_cmd));
@@ -355,7 +356,7 @@ static noinline_for_stack int ethtool_get_drvinfo(struct net_device *dev,
memset(&info, 0, sizeof(info));
info.cmd = ETHTOOL_GDRVINFO;
- if (ops && ops->get_drvinfo) {
+ if (ops->get_drvinfo) {
ops->get_drvinfo(dev, &info);
} else if (dev->dev.parent && dev->dev.parent->driver) {
strlcpy(info.bus_info, dev_name(dev->dev.parent),
@@ -370,7 +371,7 @@ static noinline_for_stack int ethtool_get_drvinfo(struct net_device *dev,
* this method of obtaining string set info is deprecated;
* Use ETHTOOL_GSSET_INFO instead.
*/
- if (ops && ops->get_sset_count) {
+ if (ops->get_sset_count) {
int rc;
rc = ops->get_sset_count(dev, ETH_SS_TEST);
@@ -383,9 +384,9 @@ static noinline_for_stack int ethtool_get_drvinfo(struct net_device *dev,
if (rc >= 0)
info.n_priv_flags = rc;
}
- if (ops && ops->get_regs_len)
+ if (ops->get_regs_len)
info.regdump_len = ops->get_regs_len(dev);
- if (ops && ops->get_eeprom_len)
+ if (ops->get_eeprom_len)
info.eedump_len = ops->get_eeprom_len(dev);
if (copy_to_user(useraddr, &info, sizeof(info)))
@@ -590,13 +591,14 @@ static noinline_for_stack int ethtool_set_rxfh_indir(struct net_device *dev,
struct ethtool_rxnfc rx_rings;
u32 user_size, dev_size, i;
u32 *indir;
+ const struct ethtool_ops *ops = dev->ethtool_ops;
int ret;
- if (!dev->ethtool_ops->get_rxfh_indir_size ||
- !dev->ethtool_ops->set_rxfh_indir ||
- !dev->ethtool_ops->get_rxnfc)
+ if (!ops->get_rxfh_indir_size || !ops->set_rxfh_indir ||
+ !ops->get_rxnfc)
return -EOPNOTSUPP;
- dev_size = dev->ethtool_ops->get_rxfh_indir_size(dev);
+
+ dev_size = ops->get_rxfh_indir_size(dev);
if (dev_size == 0)
return -EOPNOTSUPP;
@@ -613,7 +615,7 @@ static noinline_for_stack int ethtool_set_rxfh_indir(struct net_device *dev,
return -ENOMEM;
rx_rings.cmd = ETHTOOL_GRXRINGS;
- ret = dev->ethtool_ops->get_rxnfc(dev, &rx_rings, NULL);
+ ret = ops->get_rxnfc(dev, &rx_rings, NULL);
if (ret)
goto out;
@@ -639,7 +641,7 @@ static noinline_for_stack int ethtool_set_rxfh_indir(struct net_device *dev,
}
}
- ret = dev->ethtool_ops->set_rxfh_indir(dev, indir);
+ ret = ops->set_rxfh_indir(dev, indir);
out:
kfree(indir);
@@ -1082,9 +1084,10 @@ static int ethtool_phys_id(struct net_device *dev, void __user *useraddr)
{
struct ethtool_value id;
static bool busy;
+ const struct ethtool_ops *ops = dev->ethtool_ops;
int rc;
- if (!dev->ethtool_ops->set_phys_id)
+ if (!ops->set_phys_id)
return -EOPNOTSUPP;
if (busy)
@@ -1093,7 +1096,7 @@ static int ethtool_phys_id(struct net_device *dev, void __user *useraddr)
if (copy_from_user(&id, useraddr, sizeof(id)))
return -EFAULT;
- rc = dev->ethtool_ops->set_phys_id(dev, ETHTOOL_ID_ACTIVE);
+ rc = ops->set_phys_id(dev, ETHTOOL_ID_ACTIVE);
if (rc < 0)
return rc;
@@ -1118,7 +1121,7 @@ static int ethtool_phys_id(struct net_device *dev, void __user *useraddr)
i = n;
do {
rtnl_lock();
- rc = dev->ethtool_ops->set_phys_id(dev,
+ rc = ops->set_phys_id(dev,
(i & 1) ? ETHTOOL_ID_OFF : ETHTOOL_ID_ON);
rtnl_unlock();
if (rc)
@@ -1133,7 +1136,7 @@ static int ethtool_phys_id(struct net_device *dev, void __user *useraddr)
dev_put(dev);
busy = false;
- (void)dev->ethtool_ops->set_phys_id(dev, ETHTOOL_ID_INACTIVE);
+ (void) ops->set_phys_id(dev, ETHTOOL_ID_INACTIVE);
return rc;
}
@@ -1275,7 +1278,7 @@ static int ethtool_get_dump_flag(struct net_device *dev,
struct ethtool_dump dump;
const struct ethtool_ops *ops = dev->ethtool_ops;
- if (!dev->ethtool_ops->get_dump_flag)
+ if (!ops->get_dump_flag)
return -EOPNOTSUPP;
if (copy_from_user(&dump, useraddr, sizeof(dump)))
@@ -1299,8 +1302,7 @@ static int ethtool_get_dump_data(struct net_device *dev,
const struct ethtool_ops *ops = dev->ethtool_ops;
void *data = NULL;
- if (!dev->ethtool_ops->get_dump_data ||
- !dev->ethtool_ops->get_dump_flag)
+ if (!ops->get_dump_data || !ops->get_dump_flag)
return -EOPNOTSUPP;
if (copy_from_user(&dump, useraddr, sizeof(dump)))
@@ -1346,13 +1348,9 @@ static int ethtool_get_ts_info(struct net_device *dev, void __user *useraddr)
info.cmd = ETHTOOL_GET_TS_INFO;
if (phydev && phydev->drv && phydev->drv->ts_info) {
-
err = phydev->drv->ts_info(phydev, &info);
-
- } else if (dev->ethtool_ops && dev->ethtool_ops->get_ts_info) {
-
+ } else if (ops->get_ts_info) {
err = ops->get_ts_info(dev, &info);
-
} else {
info.so_timestamping =
SOF_TIMESTAMPING_RX_SOFTWARE |
diff --git a/net/core/filter.c b/net/core/filter.c
index c23543cba132..2e20b55a7830 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -532,6 +532,7 @@ int sk_chk_filter(struct sock_filter *filter, unsigned int flen)
[BPF_JMP|BPF_JSET|BPF_X] = BPF_S_JMP_JSET_X,
};
int pc;
+ bool anc_found;
if (flen == 0 || flen > BPF_MAXINSNS)
return -EINVAL;
@@ -592,8 +593,10 @@ int sk_chk_filter(struct sock_filter *filter, unsigned int flen)
case BPF_S_LD_W_ABS:
case BPF_S_LD_H_ABS:
case BPF_S_LD_B_ABS:
+ anc_found = false;
#define ANCILLARY(CODE) case SKF_AD_OFF + SKF_AD_##CODE: \
code = BPF_S_ANC_##CODE; \
+ anc_found = true; \
break
switch (ftest->k) {
ANCILLARY(PROTOCOL);
@@ -610,6 +613,10 @@ int sk_chk_filter(struct sock_filter *filter, unsigned int flen)
ANCILLARY(VLAN_TAG);
ANCILLARY(VLAN_TAG_PRESENT);
}
+
+ /* ancillary operation unknown or unsupported */
+ if (anc_found == false && ftest->k >= SKF_AD_OFF)
+ return -EINVAL;
}
ftest->code = code;
}
@@ -714,6 +721,9 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk)
unsigned int fsize = sizeof(struct sock_filter) * fprog->len;
int err;
+ if (sock_flag(sk, SOCK_FILTER_LOCKED))
+ return -EPERM;
+
/* Make sure new filter is there and in the right amounts. */
if (fprog->filter == NULL)
return -EINVAL;
@@ -750,6 +760,9 @@ int sk_detach_filter(struct sock *sk)
int ret = -ENOENT;
struct sk_filter *filter;
+ if (sock_flag(sk, SOCK_FILTER_LOCKED))
+ return -EPERM;
+
filter = rcu_dereference_protected(sk->sk_filter,
sock_owned_by_user(sk));
if (filter) {
diff --git a/net/core/flow.c b/net/core/flow.c
index b0901ee5a002..c56ea6f7f6c7 100644
--- a/net/core/flow.c
+++ b/net/core/flow.c
@@ -132,14 +132,14 @@ static void __flow_cache_shrink(struct flow_cache *fc,
int shrink_to)
{
struct flow_cache_entry *fle;
- struct hlist_node *entry, *tmp;
+ struct hlist_node *tmp;
LIST_HEAD(gc_list);
int i, deleted = 0;
for (i = 0; i < flow_cache_hash_size(fc); i++) {
int saved = 0;
- hlist_for_each_entry_safe(fle, entry, tmp,
+ hlist_for_each_entry_safe(fle, tmp,
&fcp->hash_table[i], u.hlist) {
if (saved < shrink_to &&
flow_entry_valid(fle)) {
@@ -211,7 +211,6 @@ flow_cache_lookup(struct net *net, const struct flowi *key, u16 family, u8 dir,
struct flow_cache *fc = &flow_cache_global;
struct flow_cache_percpu *fcp;
struct flow_cache_entry *fle, *tfle;
- struct hlist_node *entry;
struct flow_cache_object *flo;
size_t keysize;
unsigned int hash;
@@ -235,7 +234,7 @@ flow_cache_lookup(struct net *net, const struct flowi *key, u16 family, u8 dir,
flow_new_hash_rnd(fc, fcp);
hash = flow_hash_code(fc, fcp, key, keysize);
- hlist_for_each_entry(tfle, entry, &fcp->hash_table[hash], u.hlist) {
+ hlist_for_each_entry(tfle, &fcp->hash_table[hash], u.hlist) {
if (tfle->net == net &&
tfle->family == family &&
tfle->dir == dir &&
@@ -286,7 +285,7 @@ nocache:
else
fle->genid--;
} else {
- if (flo && !IS_ERR(flo))
+ if (!IS_ERR_OR_NULL(flo))
flo->ops->delete(flo);
}
ret_object:
@@ -301,13 +300,13 @@ static void flow_cache_flush_tasklet(unsigned long data)
struct flow_cache *fc = info->cache;
struct flow_cache_percpu *fcp;
struct flow_cache_entry *fle;
- struct hlist_node *entry, *tmp;
+ struct hlist_node *tmp;
LIST_HEAD(gc_list);
int i, deleted = 0;
fcp = this_cpu_ptr(fc->percpu);
for (i = 0; i < flow_cache_hash_size(fc); i++) {
- hlist_for_each_entry_safe(fle, entry, tmp,
+ hlist_for_each_entry_safe(fle, tmp,
&fcp->hash_table[i], u.hlist) {
if (flow_entry_valid(fle))
continue;
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 466820b6e344..e187bf06d673 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -140,6 +140,181 @@ ipv6:
flow->ports = *ports;
}
+ flow->thoff = (u16) nhoff;
+
return true;
}
EXPORT_SYMBOL(skb_flow_dissect);
+
+static u32 hashrnd __read_mostly;
+
+/*
+ * __skb_get_rxhash: calculate a flow hash based on src/dst addresses
+ * and src/dst port numbers. Sets rxhash in skb to non-zero hash value
+ * on success, zero indicates no valid hash. Also, sets l4_rxhash in skb
+ * if hash is a canonical 4-tuple hash over transport ports.
+ */
+void __skb_get_rxhash(struct sk_buff *skb)
+{
+ struct flow_keys keys;
+ u32 hash;
+
+ if (!skb_flow_dissect(skb, &keys))
+ return;
+
+ if (keys.ports)
+ skb->l4_rxhash = 1;
+
+ /* get a consistent hash (same value on both flow directions) */
+ if (((__force u32)keys.dst < (__force u32)keys.src) ||
+ (((__force u32)keys.dst == (__force u32)keys.src) &&
+ ((__force u16)keys.port16[1] < (__force u16)keys.port16[0]))) {
+ swap(keys.dst, keys.src);
+ swap(keys.port16[0], keys.port16[1]);
+ }
+
+ hash = jhash_3words((__force u32)keys.dst,
+ (__force u32)keys.src,
+ (__force u32)keys.ports, hashrnd);
+ if (!hash)
+ hash = 1;
+
+ skb->rxhash = hash;
+}
+EXPORT_SYMBOL(__skb_get_rxhash);
+
+/*
+ * Returns a Tx hash based on the given packet descriptor a Tx queues' number
+ * to be used as a distribution range.
+ */
+u16 __skb_tx_hash(const struct net_device *dev, const struct sk_buff *skb,
+ unsigned int num_tx_queues)
+{
+ u32 hash;
+ u16 qoffset = 0;
+ u16 qcount = num_tx_queues;
+
+ if (skb_rx_queue_recorded(skb)) {
+ hash = skb_get_rx_queue(skb);
+ while (unlikely(hash >= num_tx_queues))
+ hash -= num_tx_queues;
+ return hash;
+ }
+
+ if (dev->num_tc) {
+ u8 tc = netdev_get_prio_tc_map(dev, skb->priority);
+ qoffset = dev->tc_to_txq[tc].offset;
+ qcount = dev->tc_to_txq[tc].count;
+ }
+
+ if (skb->sk && skb->sk->sk_hash)
+ hash = skb->sk->sk_hash;
+ else
+ hash = (__force u16) skb->protocol;
+ hash = jhash_1word(hash, hashrnd);
+
+ return (u16) (((u64) hash * qcount) >> 32) + qoffset;
+}
+EXPORT_SYMBOL(__skb_tx_hash);
+
+static inline u16 dev_cap_txqueue(struct net_device *dev, u16 queue_index)
+{
+ if (unlikely(queue_index >= dev->real_num_tx_queues)) {
+ net_warn_ratelimited("%s selects TX queue %d, but real number of TX queues is %d\n",
+ dev->name, queue_index,
+ dev->real_num_tx_queues);
+ return 0;
+ }
+ return queue_index;
+}
+
+static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb)
+{
+#ifdef CONFIG_XPS
+ struct xps_dev_maps *dev_maps;
+ struct xps_map *map;
+ int queue_index = -1;
+
+ rcu_read_lock();
+ dev_maps = rcu_dereference(dev->xps_maps);
+ if (dev_maps) {
+ map = rcu_dereference(
+ dev_maps->cpu_map[raw_smp_processor_id()]);
+ if (map) {
+ if (map->len == 1)
+ queue_index = map->queues[0];
+ else {
+ u32 hash;
+ if (skb->sk && skb->sk->sk_hash)
+ hash = skb->sk->sk_hash;
+ else
+ hash = (__force u16) skb->protocol ^
+ skb->rxhash;
+ hash = jhash_1word(hash, hashrnd);
+ queue_index = map->queues[
+ ((u64)hash * map->len) >> 32];
+ }
+ if (unlikely(queue_index >= dev->real_num_tx_queues))
+ queue_index = -1;
+ }
+ }
+ rcu_read_unlock();
+
+ return queue_index;
+#else
+ return -1;
+#endif
+}
+
+u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb)
+{
+ struct sock *sk = skb->sk;
+ int queue_index = sk_tx_queue_get(sk);
+
+ if (queue_index < 0 || skb->ooo_okay ||
+ queue_index >= dev->real_num_tx_queues) {
+ int new_index = get_xps_queue(dev, skb);
+ if (new_index < 0)
+ new_index = skb_tx_hash(dev, skb);
+
+ if (queue_index != new_index && sk) {
+ struct dst_entry *dst =
+ rcu_dereference_check(sk->sk_dst_cache, 1);
+
+ if (dst && skb_dst(skb) == dst)
+ sk_tx_queue_set(sk, queue_index);
+
+ }
+
+ queue_index = new_index;
+ }
+
+ return queue_index;
+}
+EXPORT_SYMBOL(__netdev_pick_tx);
+
+struct netdev_queue *netdev_pick_tx(struct net_device *dev,
+ struct sk_buff *skb)
+{
+ int queue_index = 0;
+
+ if (dev->real_num_tx_queues != 1) {
+ const struct net_device_ops *ops = dev->netdev_ops;
+ if (ops->ndo_select_queue)
+ queue_index = ops->ndo_select_queue(dev, skb);
+ else
+ queue_index = __netdev_pick_tx(dev, skb);
+ queue_index = dev_cap_txqueue(dev, queue_index);
+ }
+
+ skb_set_queue_mapping(skb, queue_index);
+ return netdev_get_tx_queue(dev, queue_index);
+}
+
+static int __init initialize_hashrnd(void)
+{
+ get_random_bytes(&hashrnd, sizeof(hashrnd));
+ return 0;
+}
+
+late_initcall_sync(initialize_hashrnd);
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index c815f285e5ab..3863b8f639c5 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -290,15 +290,7 @@ static struct neighbour *neigh_alloc(struct neigh_table *tbl, struct net_device
goto out_entries;
}
- if (tbl->entry_size)
- n = kzalloc(tbl->entry_size, GFP_ATOMIC);
- else {
- int sz = sizeof(*n) + tbl->key_len;
-
- sz = ALIGN(sz, NEIGH_PRIV_ALIGN);
- sz += dev->neigh_priv_len;
- n = kzalloc(sz, GFP_ATOMIC);
- }
+ n = kzalloc(tbl->entry_size + dev->neigh_priv_len, GFP_ATOMIC);
if (!n)
goto out_entries;
@@ -778,6 +770,9 @@ static void neigh_periodic_work(struct work_struct *work)
nht = rcu_dereference_protected(tbl->nht,
lockdep_is_held(&tbl->lock));
+ if (atomic_read(&tbl->entries) < tbl->gc_thresh1)
+ goto out;
+
/*
* periodically recompute ReachableTime from random function
*/
@@ -832,6 +827,7 @@ next_elt:
nht = rcu_dereference_protected(tbl->nht,
lockdep_is_held(&tbl->lock));
}
+out:
/* Cycle through all hash buckets every base_reachable_time/2 ticks.
* ARP entry timeouts range from 1/2 base_reachable_time to 3/2
* base_reachable_time.
@@ -1542,6 +1538,12 @@ static void neigh_table_init_no_netlink(struct neigh_table *tbl)
if (!tbl->nht || !tbl->phash_buckets)
panic("cannot allocate neighbour cache hashes");
+ if (!tbl->entry_size)
+ tbl->entry_size = ALIGN(offsetof(struct neighbour, primary_key) +
+ tbl->key_len, NEIGH_PRIV_ALIGN);
+ else
+ WARN_ON(tbl->entry_size % NEIGH_PRIV_ALIGN);
+
rwlock_init(&tbl->lock);
INIT_DEFERRABLE_WORK(&tbl->gc_work, neigh_periodic_work);
schedule_delayed_work(&tbl->gc_work, tbl->parms.reachable_time);
diff --git a/net/core/net-procfs.c b/net/core/net-procfs.c
new file mode 100644
index 000000000000..3174f1998ee6
--- /dev/null
+++ b/net/core/net-procfs.c
@@ -0,0 +1,411 @@
+#include <linux/netdevice.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include <net/wext.h>
+
+#define BUCKET_SPACE (32 - NETDEV_HASHBITS - 1)
+
+#define get_bucket(x) ((x) >> BUCKET_SPACE)
+#define get_offset(x) ((x) & ((1 << BUCKET_SPACE) - 1))
+#define set_bucket_offset(b, o) ((b) << BUCKET_SPACE | (o))
+
+extern struct list_head ptype_all __read_mostly;
+extern struct list_head ptype_base[PTYPE_HASH_SIZE] __read_mostly;
+
+static inline struct net_device *dev_from_same_bucket(struct seq_file *seq, loff_t *pos)
+{
+ struct net *net = seq_file_net(seq);
+ struct net_device *dev;
+ struct hlist_head *h;
+ unsigned int count = 0, offset = get_offset(*pos);
+
+ h = &net->dev_name_head[get_bucket(*pos)];
+ hlist_for_each_entry_rcu(dev, h, name_hlist) {
+ if (++count == offset)
+ return dev;
+ }
+
+ return NULL;
+}
+
+static inline struct net_device *dev_from_bucket(struct seq_file *seq, loff_t *pos)
+{
+ struct net_device *dev;
+ unsigned int bucket;
+
+ do {
+ dev = dev_from_same_bucket(seq, pos);
+ if (dev)
+ return dev;
+
+ bucket = get_bucket(*pos) + 1;
+ *pos = set_bucket_offset(bucket, 1);
+ } while (bucket < NETDEV_HASHENTRIES);
+
+ return NULL;
+}
+
+/*
+ * This is invoked by the /proc filesystem handler to display a device
+ * in detail.
+ */
+static void *dev_seq_start(struct seq_file *seq, loff_t *pos)
+ __acquires(RCU)
+{
+ rcu_read_lock();
+ if (!*pos)
+ return SEQ_START_TOKEN;
+
+ if (get_bucket(*pos) >= NETDEV_HASHENTRIES)
+ return NULL;
+
+ return dev_from_bucket(seq, pos);
+}
+
+static void *dev_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+ ++*pos;
+ return dev_from_bucket(seq, pos);
+}
+
+static void dev_seq_stop(struct seq_file *seq, void *v)
+ __releases(RCU)
+{
+ rcu_read_unlock();
+}
+
+static void dev_seq_printf_stats(struct seq_file *seq, struct net_device *dev)
+{
+ struct rtnl_link_stats64 temp;
+ const struct rtnl_link_stats64 *stats = dev_get_stats(dev, &temp);
+
+ seq_printf(seq, "%6s: %7llu %7llu %4llu %4llu %4llu %5llu %10llu %9llu "
+ "%8llu %7llu %4llu %4llu %4llu %5llu %7llu %10llu\n",
+ dev->name, stats->rx_bytes, stats->rx_packets,
+ stats->rx_errors,
+ stats->rx_dropped + stats->rx_missed_errors,
+ stats->rx_fifo_errors,
+ stats->rx_length_errors + stats->rx_over_errors +
+ stats->rx_crc_errors + stats->rx_frame_errors,
+ stats->rx_compressed, stats->multicast,
+ stats->tx_bytes, stats->tx_packets,
+ stats->tx_errors, stats->tx_dropped,
+ stats->tx_fifo_errors, stats->collisions,
+ stats->tx_carrier_errors +
+ stats->tx_aborted_errors +
+ stats->tx_window_errors +
+ stats->tx_heartbeat_errors,
+ stats->tx_compressed);
+}
+
+/*
+ * Called from the PROCfs module. This now uses the new arbitrary sized
+ * /proc/net interface to create /proc/net/dev
+ */
+static int dev_seq_show(struct seq_file *seq, void *v)
+{
+ if (v == SEQ_START_TOKEN)
+ seq_puts(seq, "Inter-| Receive "
+ " | Transmit\n"
+ " face |bytes packets errs drop fifo frame "
+ "compressed multicast|bytes packets errs "
+ "drop fifo colls carrier compressed\n");
+ else
+ dev_seq_printf_stats(seq, v);
+ return 0;
+}
+
+static struct softnet_data *softnet_get_online(loff_t *pos)
+{
+ struct softnet_data *sd = NULL;
+
+ while (*pos < nr_cpu_ids)
+ if (cpu_online(*pos)) {
+ sd = &per_cpu(softnet_data, *pos);
+ break;
+ } else
+ ++*pos;
+ return sd;
+}
+
+static void *softnet_seq_start(struct seq_file *seq, loff_t *pos)
+{
+ return softnet_get_online(pos);
+}
+
+static void *softnet_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+ ++*pos;
+ return softnet_get_online(pos);
+}
+
+static void softnet_seq_stop(struct seq_file *seq, void *v)
+{
+}
+
+static int softnet_seq_show(struct seq_file *seq, void *v)
+{
+ struct softnet_data *sd = v;
+
+ seq_printf(seq, "%08x %08x %08x %08x %08x %08x %08x %08x %08x %08x\n",
+ sd->processed, sd->dropped, sd->time_squeeze, 0,
+ 0, 0, 0, 0, /* was fastroute */
+ sd->cpu_collision, sd->received_rps);
+ return 0;
+}
+
+static const struct seq_operations dev_seq_ops = {
+ .start = dev_seq_start,
+ .next = dev_seq_next,
+ .stop = dev_seq_stop,
+ .show = dev_seq_show,
+};
+
+static int dev_seq_open(struct inode *inode, struct file *file)
+{
+ return seq_open_net(inode, file, &dev_seq_ops,
+ sizeof(struct seq_net_private));
+}
+
+static const struct file_operations dev_seq_fops = {
+ .owner = THIS_MODULE,
+ .open = dev_seq_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = seq_release_net,
+};
+
+static const struct seq_operations softnet_seq_ops = {
+ .start = softnet_seq_start,
+ .next = softnet_seq_next,
+ .stop = softnet_seq_stop,
+ .show = softnet_seq_show,
+};
+
+static int softnet_seq_open(struct inode *inode, struct file *file)
+{
+ return seq_open(file, &softnet_seq_ops);
+}
+
+static const struct file_operations softnet_seq_fops = {
+ .owner = THIS_MODULE,
+ .open = softnet_seq_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = seq_release,
+};
+
+static void *ptype_get_idx(loff_t pos)
+{
+ struct packet_type *pt = NULL;
+ loff_t i = 0;
+ int t;
+
+ list_for_each_entry_rcu(pt, &ptype_all, list) {
+ if (i == pos)
+ return pt;
+ ++i;
+ }
+
+ for (t = 0; t < PTYPE_HASH_SIZE; t++) {
+ list_for_each_entry_rcu(pt, &ptype_base[t], list) {
+ if (i == pos)
+ return pt;
+ ++i;
+ }
+ }
+ return NULL;
+}
+
+static void *ptype_seq_start(struct seq_file *seq, loff_t *pos)
+ __acquires(RCU)
+{
+ rcu_read_lock();
+ return *pos ? ptype_get_idx(*pos - 1) : SEQ_START_TOKEN;
+}
+
+static void *ptype_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+ struct packet_type *pt;
+ struct list_head *nxt;
+ int hash;
+
+ ++*pos;
+ if (v == SEQ_START_TOKEN)
+ return ptype_get_idx(0);
+
+ pt = v;
+ nxt = pt->list.next;
+ if (pt->type == htons(ETH_P_ALL)) {
+ if (nxt != &ptype_all)
+ goto found;
+ hash = 0;
+ nxt = ptype_base[0].next;
+ } else
+ hash = ntohs(pt->type) & PTYPE_HASH_MASK;
+
+ while (nxt == &ptype_base[hash]) {
+ if (++hash >= PTYPE_HASH_SIZE)
+ return NULL;
+ nxt = ptype_base[hash].next;
+ }
+found:
+ return list_entry(nxt, struct packet_type, list);
+}
+
+static void ptype_seq_stop(struct seq_file *seq, void *v)
+ __releases(RCU)
+{
+ rcu_read_unlock();
+}
+
+static int ptype_seq_show(struct seq_file *seq, void *v)
+{
+ struct packet_type *pt = v;
+
+ if (v == SEQ_START_TOKEN)
+ seq_puts(seq, "Type Device Function\n");
+ else if (pt->dev == NULL || dev_net(pt->dev) == seq_file_net(seq)) {
+ if (pt->type == htons(ETH_P_ALL))
+ seq_puts(seq, "ALL ");
+ else
+ seq_printf(seq, "%04x", ntohs(pt->type));
+
+ seq_printf(seq, " %-8s %pF\n",
+ pt->dev ? pt->dev->name : "", pt->func);
+ }
+
+ return 0;
+}
+
+static const struct seq_operations ptype_seq_ops = {
+ .start = ptype_seq_start,
+ .next = ptype_seq_next,
+ .stop = ptype_seq_stop,
+ .show = ptype_seq_show,
+};
+
+static int ptype_seq_open(struct inode *inode, struct file *file)
+{
+ return seq_open_net(inode, file, &ptype_seq_ops,
+ sizeof(struct seq_net_private));
+}
+
+static const struct file_operations ptype_seq_fops = {
+ .owner = THIS_MODULE,
+ .open = ptype_seq_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = seq_release_net,
+};
+
+
+static int __net_init dev_proc_net_init(struct net *net)
+{
+ int rc = -ENOMEM;
+
+ if (!proc_create("dev", S_IRUGO, net->proc_net, &dev_seq_fops))
+ goto out;
+ if (!proc_create("softnet_stat", S_IRUGO, net->proc_net,
+ &softnet_seq_fops))
+ goto out_dev;
+ if (!proc_create("ptype", S_IRUGO, net->proc_net, &ptype_seq_fops))
+ goto out_softnet;
+
+ if (wext_proc_init(net))
+ goto out_ptype;
+ rc = 0;
+out:
+ return rc;
+out_ptype:
+ remove_proc_entry("ptype", net->proc_net);
+out_softnet:
+ remove_proc_entry("softnet_stat", net->proc_net);
+out_dev:
+ remove_proc_entry("dev", net->proc_net);
+ goto out;
+}
+
+static void __net_exit dev_proc_net_exit(struct net *net)
+{
+ wext_proc_exit(net);
+
+ remove_proc_entry("ptype", net->proc_net);
+ remove_proc_entry("softnet_stat", net->proc_net);
+ remove_proc_entry("dev", net->proc_net);
+}
+
+static struct pernet_operations __net_initdata dev_proc_ops = {
+ .init = dev_proc_net_init,
+ .exit = dev_proc_net_exit,
+};
+
+static int dev_mc_seq_show(struct seq_file *seq, void *v)
+{
+ struct netdev_hw_addr *ha;
+ struct net_device *dev = v;
+
+ if (v == SEQ_START_TOKEN)
+ return 0;
+
+ 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');
+ }
+ netif_addr_unlock_bh(dev);
+ return 0;
+}
+
+static const struct seq_operations dev_mc_seq_ops = {
+ .start = dev_seq_start,
+ .next = dev_seq_next,
+ .stop = dev_seq_stop,
+ .show = dev_mc_seq_show,
+};
+
+static int dev_mc_seq_open(struct inode *inode, struct file *file)
+{
+ return seq_open_net(inode, file, &dev_mc_seq_ops,
+ sizeof(struct seq_net_private));
+}
+
+static const struct file_operations dev_mc_seq_fops = {
+ .owner = THIS_MODULE,
+ .open = dev_mc_seq_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = seq_release_net,
+};
+
+static int __net_init dev_mc_net_init(struct net *net)
+{
+ if (!proc_create("dev_mcast", 0, net->proc_net, &dev_mc_seq_fops))
+ return -ENOMEM;
+ return 0;
+}
+
+static void __net_exit dev_mc_net_exit(struct net *net)
+{
+ remove_proc_entry("dev_mcast", net->proc_net);
+}
+
+static struct pernet_operations __net_initdata dev_mc_net_ops = {
+ .init = dev_mc_net_init,
+ .exit = dev_mc_net_exit,
+};
+
+int __init dev_proc_init(void)
+{
+ int ret = register_pernet_subsys(&dev_proc_ops);
+ if (!ret)
+ return register_pernet_subsys(&dev_mc_net_ops);
+ return ret;
+}
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 28c5f5aa7ca7..7427ab5e27d8 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -21,6 +21,7 @@
#include <linux/vmalloc.h>
#include <linux/export.h>
#include <linux/jiffies.h>
+#include <linux/pm_runtime.h>
#include "net-sysfs.h"
@@ -126,6 +127,19 @@ static ssize_t show_broadcast(struct device *dev,
return -EINVAL;
}
+static int change_carrier(struct net_device *net, unsigned long new_carrier)
+{
+ if (!netif_running(net))
+ return -EINVAL;
+ return dev_change_carrier(net, (bool) new_carrier);
+}
+
+static ssize_t store_carrier(struct device *dev, struct device_attribute *attr,
+ const char *buf, size_t len)
+{
+ return netdev_store(dev, attr, buf, len, change_carrier);
+}
+
static ssize_t show_carrier(struct device *dev,
struct device_attribute *attr, char *buf)
{
@@ -331,7 +345,7 @@ static struct device_attribute net_class_attributes[] = {
__ATTR(link_mode, S_IRUGO, show_link_mode, NULL),
__ATTR(address, S_IRUGO, show_address, NULL),
__ATTR(broadcast, S_IRUGO, show_broadcast, NULL),
- __ATTR(carrier, S_IRUGO, show_carrier, NULL),
+ __ATTR(carrier, S_IRUGO | S_IWUSR, show_carrier, store_carrier),
__ATTR(speed, S_IRUGO, show_speed, NULL),
__ATTR(duplex, S_IRUGO, show_duplex, NULL),
__ATTR(dormant, S_IRUGO, show_dormant, NULL),
@@ -989,68 +1003,14 @@ static ssize_t show_xps_map(struct netdev_queue *queue,
return len;
}
-static DEFINE_MUTEX(xps_map_mutex);
-#define xmap_dereference(P) \
- rcu_dereference_protected((P), lockdep_is_held(&xps_map_mutex))
-
-static void xps_queue_release(struct netdev_queue *queue)
-{
- struct net_device *dev = queue->dev;
- struct xps_dev_maps *dev_maps;
- struct xps_map *map;
- unsigned long index;
- int i, pos, nonempty = 0;
-
- index = get_netdev_queue_index(queue);
-
- mutex_lock(&xps_map_mutex);
- dev_maps = xmap_dereference(dev->xps_maps);
-
- if (dev_maps) {
- for_each_possible_cpu(i) {
- map = xmap_dereference(dev_maps->cpu_map[i]);
- if (!map)
- continue;
-
- for (pos = 0; pos < map->len; pos++)
- if (map->queues[pos] == index)
- break;
-
- if (pos < map->len) {
- if (map->len > 1)
- map->queues[pos] =
- map->queues[--map->len];
- else {
- RCU_INIT_POINTER(dev_maps->cpu_map[i],
- NULL);
- kfree_rcu(map, rcu);
- map = NULL;
- }
- }
- if (map)
- nonempty = 1;
- }
-
- if (!nonempty) {
- RCU_INIT_POINTER(dev->xps_maps, NULL);
- kfree_rcu(dev_maps, rcu);
- }
- }
- mutex_unlock(&xps_map_mutex);
-}
-
static ssize_t store_xps_map(struct netdev_queue *queue,
struct netdev_queue_attribute *attribute,
const char *buf, size_t len)
{
struct net_device *dev = queue->dev;
- cpumask_var_t mask;
- int err, i, cpu, pos, map_len, alloc_len, need_set;
unsigned long index;
- struct xps_map *map, *new_map;
- struct xps_dev_maps *dev_maps, *new_dev_maps;
- int nonempty = 0;
- int numa_node_id = -2;
+ cpumask_var_t mask;
+ int err;
if (!capable(CAP_NET_ADMIN))
return -EPERM;
@@ -1066,105 +1026,11 @@ static ssize_t store_xps_map(struct netdev_queue *queue,
return err;
}
- new_dev_maps = kzalloc(max_t(unsigned int,
- XPS_DEV_MAPS_SIZE, L1_CACHE_BYTES), GFP_KERNEL);
- if (!new_dev_maps) {
- free_cpumask_var(mask);
- return -ENOMEM;
- }
-
- mutex_lock(&xps_map_mutex);
-
- dev_maps = xmap_dereference(dev->xps_maps);
-
- for_each_possible_cpu(cpu) {
- map = dev_maps ?
- xmap_dereference(dev_maps->cpu_map[cpu]) : NULL;
- new_map = map;
- if (map) {
- for (pos = 0; pos < map->len; pos++)
- if (map->queues[pos] == index)
- break;
- map_len = map->len;
- alloc_len = map->alloc_len;
- } else
- pos = map_len = alloc_len = 0;
-
- need_set = cpumask_test_cpu(cpu, mask) && cpu_online(cpu);
-#ifdef CONFIG_NUMA
- if (need_set) {
- if (numa_node_id == -2)
- numa_node_id = cpu_to_node(cpu);
- else if (numa_node_id != cpu_to_node(cpu))
- numa_node_id = -1;
- }
-#endif
- if (need_set && pos >= map_len) {
- /* Need to add queue to this CPU's map */
- if (map_len >= alloc_len) {
- alloc_len = alloc_len ?
- 2 * alloc_len : XPS_MIN_MAP_ALLOC;
- new_map = kzalloc_node(XPS_MAP_SIZE(alloc_len),
- GFP_KERNEL,
- cpu_to_node(cpu));
- if (!new_map)
- goto error;
- new_map->alloc_len = alloc_len;
- for (i = 0; i < map_len; i++)
- new_map->queues[i] = map->queues[i];
- new_map->len = map_len;
- }
- new_map->queues[new_map->len++] = index;
- } else if (!need_set && pos < map_len) {
- /* Need to remove queue from this CPU's map */
- if (map_len > 1)
- new_map->queues[pos] =
- new_map->queues[--new_map->len];
- else
- new_map = NULL;
- }
- RCU_INIT_POINTER(new_dev_maps->cpu_map[cpu], new_map);
- }
-
- /* Cleanup old maps */
- for_each_possible_cpu(cpu) {
- map = dev_maps ?
- xmap_dereference(dev_maps->cpu_map[cpu]) : NULL;
- if (map && xmap_dereference(new_dev_maps->cpu_map[cpu]) != map)
- kfree_rcu(map, rcu);
- if (new_dev_maps->cpu_map[cpu])
- nonempty = 1;
- }
-
- if (nonempty) {
- rcu_assign_pointer(dev->xps_maps, new_dev_maps);
- } else {
- kfree(new_dev_maps);
- RCU_INIT_POINTER(dev->xps_maps, NULL);
- }
-
- if (dev_maps)
- kfree_rcu(dev_maps, rcu);
-
- netdev_queue_numa_node_write(queue, (numa_node_id >= 0) ? numa_node_id :
- NUMA_NO_NODE);
-
- mutex_unlock(&xps_map_mutex);
+ err = netif_set_xps_queue(dev, mask, index);
free_cpumask_var(mask);
- return len;
-error:
- mutex_unlock(&xps_map_mutex);
-
- if (new_dev_maps)
- for_each_possible_cpu(i)
- kfree(rcu_dereference_protected(
- new_dev_maps->cpu_map[i],
- 1));
- kfree(new_dev_maps);
- free_cpumask_var(mask);
- return -ENOMEM;
+ return err ? : len;
}
static struct netdev_queue_attribute xps_cpus_attribute =
@@ -1183,10 +1049,6 @@ static void netdev_queue_release(struct kobject *kobj)
{
struct netdev_queue *queue = to_netdev_queue(kobj);
-#ifdef CONFIG_XPS
- xps_queue_release(queue);
-#endif
-
memset(kobj, 0, sizeof(*kobj));
dev_put(queue->dev);
}
@@ -1396,6 +1258,8 @@ void netdev_unregister_kobject(struct net_device * net)
remove_queue_kobjects(net);
+ pm_runtime_set_memalloc_noio(dev, false);
+
device_del(dev);
}
@@ -1440,6 +1304,8 @@ int netdev_register_kobject(struct net_device *net)
return error;
}
+ pm_runtime_set_memalloc_noio(dev, true);
+
return error;
}
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 8acce01b6dab..80e271d9e64b 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -344,7 +344,7 @@ struct net *get_net_ns_by_fd(int fd)
if (IS_ERR(file))
return ERR_CAST(file);
- ei = PROC_I(file->f_dentry->d_inode);
+ ei = PROC_I(file_inode(file));
if (ei->ns_ops == &netns_operations)
net = get_net(ei->ns);
else
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index 3151acf5ec13..fa32899006a2 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -29,6 +29,9 @@
#include <linux/if_vlan.h>
#include <net/tcp.h>
#include <net/udp.h>
+#include <net/addrconf.h>
+#include <net/ndisc.h>
+#include <net/ip6_checksum.h>
#include <asm/unaligned.h>
#include <trace/events/napi.h>
@@ -44,6 +47,8 @@ static struct sk_buff_head skb_pool;
static atomic_t trapped;
+static struct srcu_struct netpoll_srcu;
+
#define USEC_PER_POLL 50
#define NETPOLL_RX_ENABLED 1
#define NETPOLL_RX_DROP 2
@@ -55,7 +60,8 @@ static atomic_t trapped;
MAX_UDP_CHUNK)
static void zap_completion_queue(void);
-static void netpoll_arp_reply(struct sk_buff *skb, struct netpoll_info *npinfo);
+static void netpoll_neigh_reply(struct sk_buff *skb, struct netpoll_info *npinfo);
+static void netpoll_async_cleanup(struct work_struct *work);
static unsigned int carrier_timeout = 4;
module_param(carrier_timeout, uint, 0644);
@@ -181,13 +187,13 @@ static void poll_napi(struct net_device *dev)
}
}
-static void service_arp_queue(struct netpoll_info *npi)
+static void service_neigh_queue(struct netpoll_info *npi)
{
if (npi) {
struct sk_buff *skb;
- while ((skb = skb_dequeue(&npi->arp_tx)))
- netpoll_arp_reply(skb, npi);
+ while ((skb = skb_dequeue(&npi->neigh_tx)))
+ netpoll_neigh_reply(skb, npi);
}
}
@@ -196,35 +202,76 @@ static void netpoll_poll_dev(struct net_device *dev)
const struct net_device_ops *ops;
struct netpoll_info *ni = rcu_dereference_bh(dev->npinfo);
- if (!dev || !netif_running(dev))
+ /* Don't do any rx activity if the dev_lock mutex is held
+ * the dev_open/close paths use this to block netpoll activity
+ * while changing device state
+ */
+ if (!mutex_trylock(&ni->dev_lock))
return;
+ if (!netif_running(dev)) {
+ mutex_unlock(&ni->dev_lock);
+ return;
+ }
+
ops = dev->netdev_ops;
- if (!ops->ndo_poll_controller)
+ if (!ops->ndo_poll_controller) {
+ mutex_unlock(&ni->dev_lock);
return;
+ }
/* Process pending work on NIC */
ops->ndo_poll_controller(dev);
poll_napi(dev);
+ mutex_unlock(&ni->dev_lock);
+
if (dev->flags & IFF_SLAVE) {
if (ni) {
- struct net_device *bond_dev = dev->master;
+ struct net_device *bond_dev;
struct sk_buff *skb;
- struct netpoll_info *bond_ni = rcu_dereference_bh(bond_dev->npinfo);
- while ((skb = skb_dequeue(&ni->arp_tx))) {
+ struct netpoll_info *bond_ni;
+
+ bond_dev = netdev_master_upper_dev_get_rcu(dev);
+ bond_ni = rcu_dereference_bh(bond_dev->npinfo);
+ while ((skb = skb_dequeue(&ni->neigh_tx))) {
skb->dev = bond_dev;
- skb_queue_tail(&bond_ni->arp_tx, skb);
+ skb_queue_tail(&bond_ni->neigh_tx, skb);
}
}
}
- service_arp_queue(ni);
+ service_neigh_queue(ni);
zap_completion_queue();
}
+int netpoll_rx_disable(struct net_device *dev)
+{
+ struct netpoll_info *ni;
+ int idx;
+ might_sleep();
+ idx = srcu_read_lock(&netpoll_srcu);
+ ni = srcu_dereference(dev->npinfo, &netpoll_srcu);
+ if (ni)
+ mutex_lock(&ni->dev_lock);
+ srcu_read_unlock(&netpoll_srcu, idx);
+ return 0;
+}
+EXPORT_SYMBOL(netpoll_rx_disable);
+
+void netpoll_rx_enable(struct net_device *dev)
+{
+ struct netpoll_info *ni;
+ rcu_read_lock();
+ ni = rcu_dereference(dev->npinfo);
+ if (ni)
+ mutex_unlock(&ni->dev_lock);
+ rcu_read_unlock();
+}
+EXPORT_SYMBOL(netpoll_rx_enable);
+
static void refill_skbs(void)
{
struct sk_buff *skb;
@@ -381,9 +428,14 @@ void netpoll_send_udp(struct netpoll *np, const char *msg, int len)
struct iphdr *iph;
struct ethhdr *eth;
static atomic_t ip_ident;
+ struct ipv6hdr *ip6h;
udp_len = len + sizeof(*udph);
- ip_len = udp_len + sizeof(*iph);
+ if (np->ipv6)
+ ip_len = udp_len + sizeof(*ip6h);
+ else
+ ip_len = udp_len + sizeof(*iph);
+
total_len = ip_len + LL_RESERVED_SPACE(np->dev);
skb = find_skb(np, total_len + np->dev->needed_tailroom,
@@ -400,34 +452,66 @@ void netpoll_send_udp(struct netpoll *np, const char *msg, int len)
udph->source = htons(np->local_port);
udph->dest = htons(np->remote_port);
udph->len = htons(udp_len);
- udph->check = 0;
- udph->check = csum_tcpudp_magic(np->local_ip,
- np->remote_ip,
- udp_len, IPPROTO_UDP,
- csum_partial(udph, udp_len, 0));
- if (udph->check == 0)
- udph->check = CSUM_MANGLED_0;
-
- skb_push(skb, sizeof(*iph));
- skb_reset_network_header(skb);
- iph = ip_hdr(skb);
-
- /* iph->version = 4; iph->ihl = 5; */
- put_unaligned(0x45, (unsigned char *)iph);
- iph->tos = 0;
- put_unaligned(htons(ip_len), &(iph->tot_len));
- iph->id = htons(atomic_inc_return(&ip_ident));
- iph->frag_off = 0;
- iph->ttl = 64;
- iph->protocol = IPPROTO_UDP;
- iph->check = 0;
- put_unaligned(np->local_ip, &(iph->saddr));
- put_unaligned(np->remote_ip, &(iph->daddr));
- iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl);
-
- eth = (struct ethhdr *) skb_push(skb, ETH_HLEN);
- skb_reset_mac_header(skb);
- skb->protocol = eth->h_proto = htons(ETH_P_IP);
+
+ if (np->ipv6) {
+ udph->check = 0;
+ udph->check = csum_ipv6_magic(&np->local_ip.in6,
+ &np->remote_ip.in6,
+ udp_len, IPPROTO_UDP,
+ csum_partial(udph, udp_len, 0));
+ if (udph->check == 0)
+ udph->check = CSUM_MANGLED_0;
+
+ skb_push(skb, sizeof(*ip6h));
+ skb_reset_network_header(skb);
+ ip6h = ipv6_hdr(skb);
+
+ /* ip6h->version = 6; ip6h->priority = 0; */
+ put_unaligned(0x60, (unsigned char *)ip6h);
+ ip6h->flow_lbl[0] = 0;
+ ip6h->flow_lbl[1] = 0;
+ ip6h->flow_lbl[2] = 0;
+
+ ip6h->payload_len = htons(sizeof(struct udphdr) + len);
+ ip6h->nexthdr = IPPROTO_UDP;
+ ip6h->hop_limit = 32;
+ ip6h->saddr = np->local_ip.in6;
+ ip6h->daddr = np->remote_ip.in6;
+
+ eth = (struct ethhdr *) skb_push(skb, ETH_HLEN);
+ skb_reset_mac_header(skb);
+ skb->protocol = eth->h_proto = htons(ETH_P_IPV6);
+ } else {
+ udph->check = 0;
+ udph->check = csum_tcpudp_magic(np->local_ip.ip,
+ np->remote_ip.ip,
+ udp_len, IPPROTO_UDP,
+ csum_partial(udph, udp_len, 0));
+ if (udph->check == 0)
+ udph->check = CSUM_MANGLED_0;
+
+ skb_push(skb, sizeof(*iph));
+ skb_reset_network_header(skb);
+ iph = ip_hdr(skb);
+
+ /* iph->version = 4; iph->ihl = 5; */
+ put_unaligned(0x45, (unsigned char *)iph);
+ iph->tos = 0;
+ put_unaligned(htons(ip_len), &(iph->tot_len));
+ iph->id = htons(atomic_inc_return(&ip_ident));
+ iph->frag_off = 0;
+ iph->ttl = 64;
+ iph->protocol = IPPROTO_UDP;
+ iph->check = 0;
+ put_unaligned(np->local_ip.ip, &(iph->saddr));
+ put_unaligned(np->remote_ip.ip, &(iph->daddr));
+ iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl);
+
+ eth = (struct ethhdr *) skb_push(skb, ETH_HLEN);
+ skb_reset_mac_header(skb);
+ skb->protocol = eth->h_proto = htons(ETH_P_IP);
+ }
+
memcpy(eth->h_source, np->dev->dev_addr, ETH_ALEN);
memcpy(eth->h_dest, np->remote_mac, ETH_ALEN);
@@ -437,18 +521,16 @@ void netpoll_send_udp(struct netpoll *np, const char *msg, int len)
}
EXPORT_SYMBOL(netpoll_send_udp);
-static void netpoll_arp_reply(struct sk_buff *skb, struct netpoll_info *npinfo)
+static void netpoll_neigh_reply(struct sk_buff *skb, struct netpoll_info *npinfo)
{
- struct arphdr *arp;
- unsigned char *arp_ptr;
- int size, type = ARPOP_REPLY, ptype = ETH_P_ARP;
+ int size, type = ARPOP_REPLY;
__be32 sip, tip;
unsigned char *sha;
struct sk_buff *send_skb;
struct netpoll *np, *tmp;
unsigned long flags;
int hlen, tlen;
- int hits = 0;
+ int hits = 0, proto;
if (list_empty(&npinfo->rx_np))
return;
@@ -466,94 +548,214 @@ static void netpoll_arp_reply(struct sk_buff *skb, struct netpoll_info *npinfo)
if (!hits)
return;
- /* No arp on this interface */
- if (skb->dev->flags & IFF_NOARP)
- return;
-
- if (!pskb_may_pull(skb, arp_hdr_len(skb->dev)))
- return;
+ proto = ntohs(eth_hdr(skb)->h_proto);
+ if (proto == ETH_P_IP) {
+ struct arphdr *arp;
+ unsigned char *arp_ptr;
+ /* No arp on this interface */
+ if (skb->dev->flags & IFF_NOARP)
+ return;
- skb_reset_network_header(skb);
- skb_reset_transport_header(skb);
- arp = arp_hdr(skb);
+ if (!pskb_may_pull(skb, arp_hdr_len(skb->dev)))
+ return;
- if ((arp->ar_hrd != htons(ARPHRD_ETHER) &&
- arp->ar_hrd != htons(ARPHRD_IEEE802)) ||
- arp->ar_pro != htons(ETH_P_IP) ||
- arp->ar_op != htons(ARPOP_REQUEST))
- return;
+ skb_reset_network_header(skb);
+ skb_reset_transport_header(skb);
+ arp = arp_hdr(skb);
- arp_ptr = (unsigned char *)(arp+1);
- /* save the location of the src hw addr */
- sha = arp_ptr;
- arp_ptr += skb->dev->addr_len;
- memcpy(&sip, arp_ptr, 4);
- arp_ptr += 4;
- /* If we actually cared about dst hw addr,
- it would get copied here */
- arp_ptr += skb->dev->addr_len;
- memcpy(&tip, arp_ptr, 4);
-
- /* Should we ignore arp? */
- if (ipv4_is_loopback(tip) || ipv4_is_multicast(tip))
- return;
+ if ((arp->ar_hrd != htons(ARPHRD_ETHER) &&
+ arp->ar_hrd != htons(ARPHRD_IEEE802)) ||
+ arp->ar_pro != htons(ETH_P_IP) ||
+ arp->ar_op != htons(ARPOP_REQUEST))
+ return;
- size = arp_hdr_len(skb->dev);
+ arp_ptr = (unsigned char *)(arp+1);
+ /* save the location of the src hw addr */
+ sha = arp_ptr;
+ arp_ptr += skb->dev->addr_len;
+ memcpy(&sip, arp_ptr, 4);
+ arp_ptr += 4;
+ /* If we actually cared about dst hw addr,
+ it would get copied here */
+ arp_ptr += skb->dev->addr_len;
+ memcpy(&tip, arp_ptr, 4);
- spin_lock_irqsave(&npinfo->rx_lock, flags);
- list_for_each_entry_safe(np, tmp, &npinfo->rx_np, rx) {
- if (tip != np->local_ip)
- continue;
+ /* Should we ignore arp? */
+ if (ipv4_is_loopback(tip) || ipv4_is_multicast(tip))
+ return;
- hlen = LL_RESERVED_SPACE(np->dev);
- tlen = np->dev->needed_tailroom;
- send_skb = find_skb(np, size + hlen + tlen, hlen);
- if (!send_skb)
- continue;
+ size = arp_hdr_len(skb->dev);
- skb_reset_network_header(send_skb);
- arp = (struct arphdr *) skb_put(send_skb, size);
- send_skb->dev = skb->dev;
- send_skb->protocol = htons(ETH_P_ARP);
+ spin_lock_irqsave(&npinfo->rx_lock, flags);
+ list_for_each_entry_safe(np, tmp, &npinfo->rx_np, rx) {
+ if (tip != np->local_ip.ip)
+ continue;
+
+ hlen = LL_RESERVED_SPACE(np->dev);
+ tlen = np->dev->needed_tailroom;
+ send_skb = find_skb(np, size + hlen + tlen, hlen);
+ if (!send_skb)
+ continue;
+
+ skb_reset_network_header(send_skb);
+ arp = (struct arphdr *) skb_put(send_skb, size);
+ send_skb->dev = skb->dev;
+ send_skb->protocol = htons(ETH_P_ARP);
+
+ /* Fill the device header for the ARP frame */
+ if (dev_hard_header(send_skb, skb->dev, ETH_P_ARP,
+ sha, np->dev->dev_addr,
+ send_skb->len) < 0) {
+ kfree_skb(send_skb);
+ continue;
+ }
- /* Fill the device header for the ARP frame */
- if (dev_hard_header(send_skb, skb->dev, ptype,
- sha, np->dev->dev_addr,
- send_skb->len) < 0) {
- kfree_skb(send_skb);
- continue;
+ /*
+ * Fill out the arp protocol part.
+ *
+ * we only support ethernet device type,
+ * which (according to RFC 1390) should
+ * always equal 1 (Ethernet).
+ */
+
+ arp->ar_hrd = htons(np->dev->type);
+ arp->ar_pro = htons(ETH_P_IP);
+ arp->ar_hln = np->dev->addr_len;
+ arp->ar_pln = 4;
+ arp->ar_op = htons(type);
+
+ arp_ptr = (unsigned char *)(arp + 1);
+ memcpy(arp_ptr, np->dev->dev_addr, np->dev->addr_len);
+ arp_ptr += np->dev->addr_len;
+ memcpy(arp_ptr, &tip, 4);
+ arp_ptr += 4;
+ memcpy(arp_ptr, sha, np->dev->addr_len);
+ arp_ptr += np->dev->addr_len;
+ memcpy(arp_ptr, &sip, 4);
+
+ netpoll_send_skb(np, send_skb);
+
+ /* If there are several rx_hooks for the same address,
+ we're fine by sending a single reply */
+ break;
}
+ spin_unlock_irqrestore(&npinfo->rx_lock, flags);
+ } else if( proto == ETH_P_IPV6) {
+#if IS_ENABLED(CONFIG_IPV6)
+ struct nd_msg *msg;
+ u8 *lladdr = NULL;
+ struct ipv6hdr *hdr;
+ struct icmp6hdr *icmp6h;
+ const struct in6_addr *saddr;
+ const struct in6_addr *daddr;
+ struct inet6_dev *in6_dev = NULL;
+ struct in6_addr *target;
+
+ in6_dev = in6_dev_get(skb->dev);
+ if (!in6_dev || !in6_dev->cnf.accept_ra)
+ return;
- /*
- * Fill out the arp protocol part.
- *
- * we only support ethernet device type,
- * which (according to RFC 1390) should
- * always equal 1 (Ethernet).
- */
+ if (!pskb_may_pull(skb, skb->len))
+ return;
- arp->ar_hrd = htons(np->dev->type);
- arp->ar_pro = htons(ETH_P_IP);
- arp->ar_hln = np->dev->addr_len;
- arp->ar_pln = 4;
- arp->ar_op = htons(type);
+ msg = (struct nd_msg *)skb_transport_header(skb);
- arp_ptr = (unsigned char *)(arp + 1);
- memcpy(arp_ptr, np->dev->dev_addr, np->dev->addr_len);
- arp_ptr += np->dev->addr_len;
- memcpy(arp_ptr, &tip, 4);
- arp_ptr += 4;
- memcpy(arp_ptr, sha, np->dev->addr_len);
- arp_ptr += np->dev->addr_len;
- memcpy(arp_ptr, &sip, 4);
+ __skb_push(skb, skb->data - skb_transport_header(skb));
- netpoll_send_skb(np, send_skb);
+ if (ipv6_hdr(skb)->hop_limit != 255)
+ return;
+ if (msg->icmph.icmp6_code != 0)
+ return;
+ if (msg->icmph.icmp6_type != NDISC_NEIGHBOUR_SOLICITATION)
+ return;
+
+ saddr = &ipv6_hdr(skb)->saddr;
+ daddr = &ipv6_hdr(skb)->daddr;
- /* If there are several rx_hooks for the same address,
- we're fine by sending a single reply */
- break;
+ size = sizeof(struct icmp6hdr) + sizeof(struct in6_addr);
+
+ spin_lock_irqsave(&npinfo->rx_lock, flags);
+ list_for_each_entry_safe(np, tmp, &npinfo->rx_np, rx) {
+ if (!ipv6_addr_equal(daddr, &np->local_ip.in6))
+ continue;
+
+ hlen = LL_RESERVED_SPACE(np->dev);
+ tlen = np->dev->needed_tailroom;
+ send_skb = find_skb(np, size + hlen + tlen, hlen);
+ if (!send_skb)
+ continue;
+
+ send_skb->protocol = htons(ETH_P_IPV6);
+ send_skb->dev = skb->dev;
+
+ skb_reset_network_header(send_skb);
+ skb_put(send_skb, sizeof(struct ipv6hdr));
+ hdr = ipv6_hdr(send_skb);
+
+ *(__be32*)hdr = htonl(0x60000000);
+
+ hdr->payload_len = htons(size);
+ hdr->nexthdr = IPPROTO_ICMPV6;
+ hdr->hop_limit = 255;
+ hdr->saddr = *saddr;
+ hdr->daddr = *daddr;
+
+ send_skb->transport_header = send_skb->tail;
+ skb_put(send_skb, size);
+
+ icmp6h = (struct icmp6hdr *)skb_transport_header(skb);
+ icmp6h->icmp6_type = NDISC_NEIGHBOUR_ADVERTISEMENT;
+ icmp6h->icmp6_router = 0;
+ icmp6h->icmp6_solicited = 1;
+ target = (struct in6_addr *)(skb_transport_header(send_skb) + sizeof(struct icmp6hdr));
+ *target = msg->target;
+ icmp6h->icmp6_cksum = csum_ipv6_magic(saddr, daddr, size,
+ IPPROTO_ICMPV6,
+ csum_partial(icmp6h,
+ size, 0));
+
+ if (dev_hard_header(send_skb, skb->dev, ETH_P_IPV6,
+ lladdr, np->dev->dev_addr,
+ send_skb->len) < 0) {
+ kfree_skb(send_skb);
+ continue;
+ }
+
+ netpoll_send_skb(np, send_skb);
+
+ /* If there are several rx_hooks for the same address,
+ we're fine by sending a single reply */
+ break;
+ }
+ spin_unlock_irqrestore(&npinfo->rx_lock, flags);
+#endif
}
- spin_unlock_irqrestore(&npinfo->rx_lock, flags);
+}
+
+static bool pkt_is_ns(struct sk_buff *skb)
+{
+ struct nd_msg *msg;
+ struct ipv6hdr *hdr;
+
+ if (skb->protocol != htons(ETH_P_ARP))
+ return false;
+ if (!pskb_may_pull(skb, sizeof(struct ipv6hdr) + sizeof(struct nd_msg)))
+ return false;
+
+ msg = (struct nd_msg *)skb_transport_header(skb);
+ __skb_push(skb, skb->data - skb_transport_header(skb));
+ hdr = ipv6_hdr(skb);
+
+ if (hdr->nexthdr != IPPROTO_ICMPV6)
+ return false;
+ if (hdr->hop_limit != 255)
+ return false;
+ if (msg->icmph.icmp6_code != 0)
+ return false;
+ if (msg->icmph.icmp6_type != NDISC_NEIGHBOUR_SOLICITATION)
+ return false;
+
+ return true;
}
int __netpoll_rx(struct sk_buff *skb, struct netpoll_info *npinfo)
@@ -571,9 +773,11 @@ int __netpoll_rx(struct sk_buff *skb, struct netpoll_info *npinfo)
goto out;
/* check if netpoll clients need ARP */
- if (skb->protocol == htons(ETH_P_ARP) &&
- atomic_read(&trapped)) {
- skb_queue_tail(&npinfo->arp_tx, skb);
+ if (skb->protocol == htons(ETH_P_ARP) && atomic_read(&trapped)) {
+ skb_queue_tail(&npinfo->neigh_tx, skb);
+ return 1;
+ } else if (pkt_is_ns(skb) && atomic_read(&trapped)) {
+ skb_queue_tail(&npinfo->neigh_tx, skb);
return 1;
}
@@ -584,60 +788,100 @@ int __netpoll_rx(struct sk_buff *skb, struct netpoll_info *npinfo)
}
proto = ntohs(eth_hdr(skb)->h_proto);
- if (proto != ETH_P_IP)
+ if (proto != ETH_P_IP && proto != ETH_P_IPV6)
goto out;
if (skb->pkt_type == PACKET_OTHERHOST)
goto out;
if (skb_shared(skb))
goto out;
- if (!pskb_may_pull(skb, sizeof(struct iphdr)))
- goto out;
- iph = (struct iphdr *)skb->data;
- if (iph->ihl < 5 || iph->version != 4)
- goto out;
- if (!pskb_may_pull(skb, iph->ihl*4))
- goto out;
- iph = (struct iphdr *)skb->data;
- if (ip_fast_csum((u8 *)iph, iph->ihl) != 0)
- goto out;
-
- len = ntohs(iph->tot_len);
- if (skb->len < len || len < iph->ihl*4)
- goto out;
+ if (proto == ETH_P_IP) {
+ if (!pskb_may_pull(skb, sizeof(struct iphdr)))
+ goto out;
+ iph = (struct iphdr *)skb->data;
+ if (iph->ihl < 5 || iph->version != 4)
+ goto out;
+ if (!pskb_may_pull(skb, iph->ihl*4))
+ goto out;
+ iph = (struct iphdr *)skb->data;
+ if (ip_fast_csum((u8 *)iph, iph->ihl) != 0)
+ goto out;
- /*
- * Our transport medium may have padded the buffer out.
- * Now We trim to the true length of the frame.
- */
- if (pskb_trim_rcsum(skb, len))
- goto out;
+ len = ntohs(iph->tot_len);
+ if (skb->len < len || len < iph->ihl*4)
+ goto out;
- iph = (struct iphdr *)skb->data;
- if (iph->protocol != IPPROTO_UDP)
- goto out;
+ /*
+ * Our transport medium may have padded the buffer out.
+ * Now We trim to the true length of the frame.
+ */
+ if (pskb_trim_rcsum(skb, len))
+ goto out;
- len -= iph->ihl*4;
- uh = (struct udphdr *)(((char *)iph) + iph->ihl*4);
- ulen = ntohs(uh->len);
+ iph = (struct iphdr *)skb->data;
+ if (iph->protocol != IPPROTO_UDP)
+ goto out;
- if (ulen != len)
- goto out;
- if (checksum_udp(skb, uh, ulen, iph->saddr, iph->daddr))
- goto out;
+ len -= iph->ihl*4;
+ uh = (struct udphdr *)(((char *)iph) + iph->ihl*4);
+ ulen = ntohs(uh->len);
- list_for_each_entry_safe(np, tmp, &npinfo->rx_np, rx) {
- if (np->local_ip && np->local_ip != iph->daddr)
- continue;
- if (np->remote_ip && np->remote_ip != iph->saddr)
- continue;
- if (np->local_port && np->local_port != ntohs(uh->dest))
- continue;
+ if (ulen != len)
+ goto out;
+ if (checksum_udp(skb, uh, ulen, iph->saddr, iph->daddr))
+ goto out;
+ list_for_each_entry_safe(np, tmp, &npinfo->rx_np, rx) {
+ if (np->local_ip.ip && np->local_ip.ip != iph->daddr)
+ continue;
+ if (np->remote_ip.ip && np->remote_ip.ip != iph->saddr)
+ continue;
+ if (np->local_port && np->local_port != ntohs(uh->dest))
+ continue;
+
+ np->rx_hook(np, ntohs(uh->source),
+ (char *)(uh+1),
+ ulen - sizeof(struct udphdr));
+ hits++;
+ }
+ } else {
+#if IS_ENABLED(CONFIG_IPV6)
+ const struct ipv6hdr *ip6h;
- np->rx_hook(np, ntohs(uh->source),
- (char *)(uh+1),
- ulen - sizeof(struct udphdr));
- hits++;
+ if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
+ goto out;
+ ip6h = (struct ipv6hdr *)skb->data;
+ if (ip6h->version != 6)
+ goto out;
+ len = ntohs(ip6h->payload_len);
+ if (!len)
+ goto out;
+ if (len + sizeof(struct ipv6hdr) > skb->len)
+ goto out;
+ if (pskb_trim_rcsum(skb, len + sizeof(struct ipv6hdr)))
+ goto out;
+ ip6h = ipv6_hdr(skb);
+ if (!pskb_may_pull(skb, sizeof(struct udphdr)))
+ goto out;
+ uh = udp_hdr(skb);
+ ulen = ntohs(uh->len);
+ if (ulen != skb->len)
+ goto out;
+ if (udp6_csum_init(skb, uh, IPPROTO_UDP))
+ goto out;
+ list_for_each_entry_safe(np, tmp, &npinfo->rx_np, rx) {
+ if (!ipv6_addr_equal(&np->local_ip.in6, &ip6h->daddr))
+ continue;
+ if (!ipv6_addr_equal(&np->remote_ip.in6, &ip6h->saddr))
+ continue;
+ if (np->local_port && np->local_port != ntohs(uh->dest))
+ continue;
+
+ np->rx_hook(np, ntohs(uh->source),
+ (char *)(uh+1),
+ ulen - sizeof(struct udphdr));
+ hits++;
+ }
+#endif
}
if (!hits)
@@ -658,17 +902,44 @@ out:
void netpoll_print_options(struct netpoll *np)
{
np_info(np, "local port %d\n", np->local_port);
- np_info(np, "local IP %pI4\n", &np->local_ip);
+ if (np->ipv6)
+ np_info(np, "local IPv6 address %pI6c\n", &np->local_ip.in6);
+ else
+ np_info(np, "local IPv4 address %pI4\n", &np->local_ip.ip);
np_info(np, "interface '%s'\n", np->dev_name);
np_info(np, "remote port %d\n", np->remote_port);
- np_info(np, "remote IP %pI4\n", &np->remote_ip);
+ if (np->ipv6)
+ np_info(np, "remote IPv6 address %pI6c\n", &np->remote_ip.in6);
+ else
+ np_info(np, "remote IPv4 address %pI4\n", &np->remote_ip.ip);
np_info(np, "remote ethernet address %pM\n", np->remote_mac);
}
EXPORT_SYMBOL(netpoll_print_options);
+static int netpoll_parse_ip_addr(const char *str, union inet_addr *addr)
+{
+ const char *end;
+
+ if (!strchr(str, ':') &&
+ in4_pton(str, -1, (void *)addr, -1, &end) > 0) {
+ if (!*end)
+ return 0;
+ }
+ if (in6_pton(str, -1, addr->in6.s6_addr, -1, &end) > 0) {
+#if IS_ENABLED(CONFIG_IPV6)
+ if (!*end)
+ return 1;
+#else
+ return -1;
+#endif
+ }
+ return -1;
+}
+
int netpoll_parse_options(struct netpoll *np, char *opt)
{
char *cur=opt, *delim;
+ int ipv6;
if (*cur != '@') {
if ((delim = strchr(cur, '@')) == NULL)
@@ -684,7 +955,11 @@ int netpoll_parse_options(struct netpoll *np, char *opt)
if ((delim = strchr(cur, '/')) == NULL)
goto parse_failed;
*delim = 0;
- np->local_ip = in_aton(cur);
+ ipv6 = netpoll_parse_ip_addr(cur, &np->local_ip);
+ if (ipv6 < 0)
+ goto parse_failed;
+ else
+ np->ipv6 = (bool)ipv6;
cur = delim;
}
cur++;
@@ -716,7 +991,13 @@ int netpoll_parse_options(struct netpoll *np, char *opt)
if ((delim = strchr(cur, '/')) == NULL)
goto parse_failed;
*delim = 0;
- np->remote_ip = in_aton(cur);
+ ipv6 = netpoll_parse_ip_addr(cur, &np->remote_ip);
+ if (ipv6 < 0)
+ goto parse_failed;
+ else if (np->ipv6 != (bool)ipv6)
+ goto parse_failed;
+ else
+ np->ipv6 = (bool)ipv6;
cur = delim + 1;
if (*cur != 0) {
@@ -744,6 +1025,7 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev, gfp_t gfp)
np->dev = ndev;
strlcpy(np->dev_name, ndev->name, IFNAMSIZ);
+ INIT_WORK(&np->cleanup_work, netpoll_async_cleanup);
if ((ndev->priv_flags & IFF_DISABLE_NETPOLL) ||
!ndev->netdev_ops->ndo_poll_controller) {
@@ -764,7 +1046,8 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev, gfp_t gfp)
INIT_LIST_HEAD(&npinfo->rx_np);
spin_lock_init(&npinfo->rx_lock);
- skb_queue_head_init(&npinfo->arp_tx);
+ mutex_init(&npinfo->dev_lock);
+ skb_queue_head_init(&npinfo->neigh_tx);
skb_queue_head_init(&npinfo->txq);
INIT_DELAYED_WORK(&npinfo->tx_work, queue_process);
@@ -777,7 +1060,7 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev, gfp_t gfp)
goto free_npinfo;
}
} else {
- npinfo = ndev->npinfo;
+ npinfo = rtnl_dereference(ndev->npinfo);
atomic_inc(&npinfo->refcnt);
}
@@ -808,14 +1091,19 @@ int netpoll_setup(struct netpoll *np)
struct in_device *in_dev;
int err;
- if (np->dev_name)
- ndev = dev_get_by_name(&init_net, np->dev_name);
+ rtnl_lock();
+ if (np->dev_name) {
+ struct net *net = current->nsproxy->net_ns;
+ ndev = __dev_get_by_name(net, np->dev_name);
+ }
if (!ndev) {
np_err(np, "%s doesn't exist, aborting\n", np->dev_name);
- return -ENODEV;
+ err = -ENODEV;
+ goto unlock;
}
+ dev_hold(ndev);
- if (ndev->master) {
+ if (netdev_master_upper_dev_get(ndev)) {
np_err(np, "%s is a slave device, aborting\n", np->dev_name);
err = -EBUSY;
goto put;
@@ -826,15 +1114,14 @@ int netpoll_setup(struct netpoll *np)
np_info(np, "device %s not up yet, forcing it\n", np->dev_name);
- rtnl_lock();
err = dev_open(ndev);
- rtnl_unlock();
if (err) {
np_err(np, "failed to open %s\n", ndev->name);
goto put;
}
+ rtnl_unlock();
atleast = jiffies + HZ/10;
atmost = jiffies + carrier_timeout * HZ;
while (!netif_carrier_ok(ndev)) {
@@ -854,39 +1141,70 @@ int netpoll_setup(struct netpoll *np)
np_notice(np, "carrier detect appears untrustworthy, waiting 4 seconds\n");
msleep(4000);
}
+ rtnl_lock();
}
- if (!np->local_ip) {
- rcu_read_lock();
- in_dev = __in_dev_get_rcu(ndev);
+ if (!np->local_ip.ip) {
+ if (!np->ipv6) {
+ in_dev = __in_dev_get_rtnl(ndev);
+
+ if (!in_dev || !in_dev->ifa_list) {
+ np_err(np, "no IP address for %s, aborting\n",
+ np->dev_name);
+ err = -EDESTADDRREQ;
+ goto put;
+ }
+
+ np->local_ip.ip = in_dev->ifa_list->ifa_local;
+ np_info(np, "local IP %pI4\n", &np->local_ip.ip);
+ } else {
+#if IS_ENABLED(CONFIG_IPV6)
+ struct inet6_dev *idev;
- if (!in_dev || !in_dev->ifa_list) {
- rcu_read_unlock();
- np_err(np, "no IP address for %s, aborting\n",
- np->dev_name);
err = -EDESTADDRREQ;
+ idev = __in6_dev_get(ndev);
+ if (idev) {
+ struct inet6_ifaddr *ifp;
+
+ read_lock_bh(&idev->lock);
+ list_for_each_entry(ifp, &idev->addr_list, if_list) {
+ if (ipv6_addr_type(&ifp->addr) & IPV6_ADDR_LINKLOCAL)
+ continue;
+ np->local_ip.in6 = ifp->addr;
+ err = 0;
+ break;
+ }
+ read_unlock_bh(&idev->lock);
+ }
+ if (err) {
+ np_err(np, "no IPv6 address for %s, aborting\n",
+ np->dev_name);
+ goto put;
+ } else
+ np_info(np, "local IPv6 %pI6c\n", &np->local_ip.in6);
+#else
+ np_err(np, "IPv6 is not supported %s, aborting\n",
+ np->dev_name);
+ err = -EINVAL;
goto put;
+#endif
}
-
- np->local_ip = in_dev->ifa_list->ifa_local;
- rcu_read_unlock();
- np_info(np, "local IP %pI4\n", &np->local_ip);
}
/* fill up the skb queue */
refill_skbs();
- rtnl_lock();
err = __netpoll_setup(np, ndev, GFP_KERNEL);
- rtnl_unlock();
-
if (err)
goto put;
+ rtnl_unlock();
return 0;
put:
dev_put(ndev);
+unlock:
+ rtnl_unlock();
return err;
}
EXPORT_SYMBOL(netpoll_setup);
@@ -894,6 +1212,7 @@ EXPORT_SYMBOL(netpoll_setup);
static int __init netpoll_init(void)
{
skb_queue_head_init(&skb_pool);
+ init_srcu_struct(&netpoll_srcu);
return 0;
}
core_initcall(netpoll_init);
@@ -903,7 +1222,7 @@ static void rcu_cleanup_netpoll_info(struct rcu_head *rcu_head)
struct netpoll_info *npinfo =
container_of(rcu_head, struct netpoll_info, rcu);
- skb_queue_purge(&npinfo->arp_tx);
+ skb_queue_purge(&npinfo->neigh_tx);
skb_queue_purge(&npinfo->txq);
/* we can't call cancel_delayed_work_sync here, as we are in softirq */
@@ -921,7 +1240,11 @@ void __netpoll_cleanup(struct netpoll *np)
struct netpoll_info *npinfo;
unsigned long flags;
- npinfo = np->dev->npinfo;
+ /* rtnl_dereference would be preferable here but
+ * rcu_cleanup_netpoll path can put us in here safely without
+ * holding the rtnl, so plain rcu_dereference it is
+ */
+ npinfo = rtnl_dereference(np->dev->npinfo);
if (!npinfo)
return;
@@ -933,6 +1256,8 @@ void __netpoll_cleanup(struct netpoll *np)
spin_unlock_irqrestore(&npinfo->rx_lock, flags);
}
+ synchronize_srcu(&netpoll_srcu);
+
if (atomic_dec_and_test(&npinfo->refcnt)) {
const struct net_device_ops *ops;
@@ -940,25 +1265,27 @@ void __netpoll_cleanup(struct netpoll *np)
if (ops->ndo_netpoll_cleanup)
ops->ndo_netpoll_cleanup(np->dev);
- RCU_INIT_POINTER(np->dev->npinfo, NULL);
+ rcu_assign_pointer(np->dev->npinfo, NULL);
call_rcu_bh(&npinfo->rcu, rcu_cleanup_netpoll_info);
}
}
EXPORT_SYMBOL_GPL(__netpoll_cleanup);
-static void rcu_cleanup_netpoll(struct rcu_head *rcu_head)
+static void netpoll_async_cleanup(struct work_struct *work)
{
- struct netpoll *np = container_of(rcu_head, struct netpoll, rcu);
+ struct netpoll *np = container_of(work, struct netpoll, cleanup_work);
+ rtnl_lock();
__netpoll_cleanup(np);
+ rtnl_unlock();
kfree(np);
}
-void __netpoll_free_rcu(struct netpoll *np)
+void __netpoll_free_async(struct netpoll *np)
{
- call_rcu_bh(&np->rcu, rcu_cleanup_netpoll);
+ schedule_work(&np->cleanup_work);
}
-EXPORT_SYMBOL_GPL(__netpoll_free_rcu);
+EXPORT_SYMBOL_GPL(__netpoll_free_async);
void netpoll_cleanup(struct netpoll *np)
{
diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c
index 5e67defe2cb0..0777d0aa18c3 100644
--- a/net/core/netprio_cgroup.c
+++ b/net/core/netprio_cgroup.c
@@ -69,10 +69,8 @@ static int extend_netdev_table(struct net_device *dev, u32 target_idx)
/* allocate & copy */
new = kzalloc(new_sz, GFP_KERNEL);
- if (!new) {
- pr_warn("Unable to alloc new priomap!\n");
+ if (!new)
return -ENOMEM;
- }
if (old)
memcpy(new->priomap, old->priomap,
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index b29dacf900f9..6048fc1da1c2 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -164,6 +164,7 @@
#ifdef CONFIG_XFRM
#include <net/xfrm.h>
#endif
+#include <net/netns/generic.h>
#include <asm/byteorder.h>
#include <linux/rcupdate.h>
#include <linux/bitops.h>
@@ -212,7 +213,6 @@
#define PKTGEN_MAGIC 0xbe9be955
#define PG_PROC_DIR "pktgen"
#define PGCTRL "pgctrl"
-static struct proc_dir_entry *pg_proc_dir;
#define MAX_CFLOWS 65536
@@ -397,7 +397,15 @@ struct pktgen_hdr {
__be32 tv_usec;
};
-static bool pktgen_exiting __read_mostly;
+
+static int pg_net_id __read_mostly;
+
+struct pktgen_net {
+ struct net *net;
+ struct proc_dir_entry *proc_dir;
+ struct list_head pktgen_threads;
+ bool pktgen_exiting;
+};
struct pktgen_thread {
spinlock_t if_lock; /* for list of devices */
@@ -414,6 +422,7 @@ struct pktgen_thread {
wait_queue_head_t queue;
struct completion start_done;
+ struct pktgen_net *net;
};
#define REMOVE 1
@@ -428,9 +437,9 @@ static int pktgen_add_device(struct pktgen_thread *t, const char *ifname);
static struct pktgen_dev *pktgen_find_dev(struct pktgen_thread *t,
const char *ifname, bool exact);
static int pktgen_device_event(struct notifier_block *, unsigned long, void *);
-static void pktgen_run_all_threads(void);
-static void pktgen_reset_all_threads(void);
-static void pktgen_stop_all_threads_ifs(void);
+static void pktgen_run_all_threads(struct pktgen_net *pn);
+static void pktgen_reset_all_threads(struct pktgen_net *pn);
+static void pktgen_stop_all_threads_ifs(struct pktgen_net *pn);
static void pktgen_stop(struct pktgen_thread *t);
static void pktgen_clear_counters(struct pktgen_dev *pkt_dev);
@@ -442,7 +451,6 @@ static int pg_clone_skb_d __read_mostly;
static int debug __read_mostly;
static DEFINE_MUTEX(pktgen_thread_lock);
-static LIST_HEAD(pktgen_threads);
static struct notifier_block pktgen_notifier_block = {
.notifier_call = pktgen_device_event,
@@ -464,6 +472,7 @@ static ssize_t pgctrl_write(struct file *file, const char __user *buf,
{
int err = 0;
char data[128];
+ struct pktgen_net *pn = net_generic(current->nsproxy->net_ns, pg_net_id);
if (!capable(CAP_NET_ADMIN)) {
err = -EPERM;
@@ -480,13 +489,13 @@ static ssize_t pgctrl_write(struct file *file, const char __user *buf,
data[count - 1] = 0; /* Make string */
if (!strcmp(data, "stop"))
- pktgen_stop_all_threads_ifs();
+ pktgen_stop_all_threads_ifs(pn);
else if (!strcmp(data, "start"))
- pktgen_run_all_threads();
+ pktgen_run_all_threads(pn);
else if (!strcmp(data, "reset"))
- pktgen_reset_all_threads();
+ pktgen_reset_all_threads(pn);
else
pr_warning("Unknown command: %s\n", data);
@@ -1781,10 +1790,13 @@ static ssize_t pktgen_thread_write(struct file *file,
return -EFAULT;
i += len;
mutex_lock(&pktgen_thread_lock);
- pktgen_add_device(t, f);
+ ret = pktgen_add_device(t, f);
mutex_unlock(&pktgen_thread_lock);
- ret = count;
- sprintf(pg_result, "OK: add_device=%s", f);
+ if (!ret) {
+ ret = count;
+ sprintf(pg_result, "OK: add_device=%s", f);
+ } else
+ sprintf(pg_result, "ERROR: can not add device %s", f);
goto out;
}
@@ -1824,13 +1836,14 @@ static const struct file_operations pktgen_thread_fops = {
};
/* Think find or remove for NN */
-static struct pktgen_dev *__pktgen_NN_threads(const char *ifname, int remove)
+static struct pktgen_dev *__pktgen_NN_threads(const struct pktgen_net *pn,
+ const char *ifname, int remove)
{
struct pktgen_thread *t;
struct pktgen_dev *pkt_dev = NULL;
bool exact = (remove == FIND);
- list_for_each_entry(t, &pktgen_threads, th_list) {
+ list_for_each_entry(t, &pn->pktgen_threads, th_list) {
pkt_dev = pktgen_find_dev(t, ifname, exact);
if (pkt_dev) {
if (remove) {
@@ -1848,7 +1861,7 @@ static struct pktgen_dev *__pktgen_NN_threads(const char *ifname, int remove)
/*
* mark a device for removal
*/
-static void pktgen_mark_device(const char *ifname)
+static void pktgen_mark_device(const struct pktgen_net *pn, const char *ifname)
{
struct pktgen_dev *pkt_dev = NULL;
const int max_tries = 10, msec_per_try = 125;
@@ -1859,7 +1872,7 @@ static void pktgen_mark_device(const char *ifname)
while (1) {
- pkt_dev = __pktgen_NN_threads(ifname, REMOVE);
+ pkt_dev = __pktgen_NN_threads(pn, ifname, REMOVE);
if (pkt_dev == NULL)
break; /* success */
@@ -1880,21 +1893,21 @@ static void pktgen_mark_device(const char *ifname)
mutex_unlock(&pktgen_thread_lock);
}
-static void pktgen_change_name(struct net_device *dev)
+static void pktgen_change_name(const struct pktgen_net *pn, struct net_device *dev)
{
struct pktgen_thread *t;
- list_for_each_entry(t, &pktgen_threads, th_list) {
+ list_for_each_entry(t, &pn->pktgen_threads, th_list) {
struct pktgen_dev *pkt_dev;
list_for_each_entry(pkt_dev, &t->if_list, list) {
if (pkt_dev->odev != dev)
continue;
- remove_proc_entry(pkt_dev->entry->name, pg_proc_dir);
+ remove_proc_entry(pkt_dev->entry->name, pn->proc_dir);
pkt_dev->entry = proc_create_data(dev->name, 0600,
- pg_proc_dir,
+ pn->proc_dir,
&pktgen_if_fops,
pkt_dev);
if (!pkt_dev->entry)
@@ -1909,8 +1922,9 @@ static int pktgen_device_event(struct notifier_block *unused,
unsigned long event, void *ptr)
{
struct net_device *dev = ptr;
+ struct pktgen_net *pn = net_generic(dev_net(dev), pg_net_id);
- if (!net_eq(dev_net(dev), &init_net) || pktgen_exiting)
+ if (pn->pktgen_exiting)
return NOTIFY_DONE;
/* It is OK that we do not hold the group lock right now,
@@ -1919,18 +1933,19 @@ static int pktgen_device_event(struct notifier_block *unused,
switch (event) {
case NETDEV_CHANGENAME:
- pktgen_change_name(dev);
+ pktgen_change_name(pn, dev);
break;
case NETDEV_UNREGISTER:
- pktgen_mark_device(dev->name);
+ pktgen_mark_device(pn, dev->name);
break;
}
return NOTIFY_DONE;
}
-static struct net_device *pktgen_dev_get_by_name(struct pktgen_dev *pkt_dev,
+static struct net_device *pktgen_dev_get_by_name(const struct pktgen_net *pn,
+ struct pktgen_dev *pkt_dev,
const char *ifname)
{
char b[IFNAMSIZ+5];
@@ -1944,13 +1959,14 @@ static struct net_device *pktgen_dev_get_by_name(struct pktgen_dev *pkt_dev,
}
b[i] = 0;
- return dev_get_by_name(&init_net, b);
+ return dev_get_by_name(pn->net, b);
}
/* Associate pktgen_dev with a device. */
-static int pktgen_setup_dev(struct pktgen_dev *pkt_dev, const char *ifname)
+static int pktgen_setup_dev(const struct pktgen_net *pn,
+ struct pktgen_dev *pkt_dev, const char *ifname)
{
struct net_device *odev;
int err;
@@ -1961,7 +1977,7 @@ static int pktgen_setup_dev(struct pktgen_dev *pkt_dev, const char *ifname)
pkt_dev->odev = NULL;
}
- odev = pktgen_dev_get_by_name(pkt_dev, ifname);
+ odev = pktgen_dev_get_by_name(pn, pkt_dev, ifname);
if (!odev) {
pr_err("no such netdevice: \"%s\"\n", ifname);
return -ENODEV;
@@ -2203,9 +2219,10 @@ static inline int f_pick(struct pktgen_dev *pkt_dev)
static void get_ipsec_sa(struct pktgen_dev *pkt_dev, int flow)
{
struct xfrm_state *x = pkt_dev->flows[flow].x;
+ struct pktgen_net *pn = net_generic(dev_net(pkt_dev->odev), pg_net_id);
if (!x) {
/*slow path: we dont already have xfrm_state*/
- x = xfrm_stateonly_find(&init_net, DUMMY_MARK,
+ x = xfrm_stateonly_find(pn->net, DUMMY_MARK,
(xfrm_address_t *)&pkt_dev->cur_daddr,
(xfrm_address_t *)&pkt_dev->cur_saddr,
AF_INET,
@@ -2912,7 +2929,7 @@ static void pktgen_run(struct pktgen_thread *t)
t->control &= ~(T_STOP);
}
-static void pktgen_stop_all_threads_ifs(void)
+static void pktgen_stop_all_threads_ifs(struct pktgen_net *pn)
{
struct pktgen_thread *t;
@@ -2920,7 +2937,7 @@ static void pktgen_stop_all_threads_ifs(void)
mutex_lock(&pktgen_thread_lock);
- list_for_each_entry(t, &pktgen_threads, th_list)
+ list_for_each_entry(t, &pn->pktgen_threads, th_list)
t->control |= T_STOP;
mutex_unlock(&pktgen_thread_lock);
@@ -2956,28 +2973,28 @@ signal:
return 0;
}
-static int pktgen_wait_all_threads_run(void)
+static int pktgen_wait_all_threads_run(struct pktgen_net *pn)
{
struct pktgen_thread *t;
int sig = 1;
mutex_lock(&pktgen_thread_lock);
- list_for_each_entry(t, &pktgen_threads, th_list) {
+ list_for_each_entry(t, &pn->pktgen_threads, th_list) {
sig = pktgen_wait_thread_run(t);
if (sig == 0)
break;
}
if (sig == 0)
- list_for_each_entry(t, &pktgen_threads, th_list)
+ list_for_each_entry(t, &pn->pktgen_threads, th_list)
t->control |= (T_STOP);
mutex_unlock(&pktgen_thread_lock);
return sig;
}
-static void pktgen_run_all_threads(void)
+static void pktgen_run_all_threads(struct pktgen_net *pn)
{
struct pktgen_thread *t;
@@ -2985,7 +3002,7 @@ static void pktgen_run_all_threads(void)
mutex_lock(&pktgen_thread_lock);
- list_for_each_entry(t, &pktgen_threads, th_list)
+ list_for_each_entry(t, &pn->pktgen_threads, th_list)
t->control |= (T_RUN);
mutex_unlock(&pktgen_thread_lock);
@@ -2993,10 +3010,10 @@ static void pktgen_run_all_threads(void)
/* Propagate thread->control */
schedule_timeout_interruptible(msecs_to_jiffies(125));
- pktgen_wait_all_threads_run();
+ pktgen_wait_all_threads_run(pn);
}
-static void pktgen_reset_all_threads(void)
+static void pktgen_reset_all_threads(struct pktgen_net *pn)
{
struct pktgen_thread *t;
@@ -3004,7 +3021,7 @@ static void pktgen_reset_all_threads(void)
mutex_lock(&pktgen_thread_lock);
- list_for_each_entry(t, &pktgen_threads, th_list)
+ list_for_each_entry(t, &pn->pktgen_threads, th_list)
t->control |= (T_REMDEVALL);
mutex_unlock(&pktgen_thread_lock);
@@ -3012,7 +3029,7 @@ static void pktgen_reset_all_threads(void)
/* Propagate thread->control */
schedule_timeout_interruptible(msecs_to_jiffies(125));
- pktgen_wait_all_threads_run();
+ pktgen_wait_all_threads_run(pn);
}
static void show_results(struct pktgen_dev *pkt_dev, int nr_frags)
@@ -3154,9 +3171,7 @@ static void pktgen_rem_all_ifs(struct pktgen_thread *t)
static void pktgen_rem_thread(struct pktgen_thread *t)
{
/* Remove from the thread list */
-
- remove_proc_entry(t->tsk->comm, pg_proc_dir);
-
+ remove_proc_entry(t->tsk->comm, t->net->proc_dir);
}
static void pktgen_resched(struct pktgen_dev *pkt_dev)
@@ -3302,7 +3317,7 @@ static int pktgen_thread_worker(void *arg)
pkt_dev = next_to_run(t);
if (unlikely(!pkt_dev && t->control == 0)) {
- if (pktgen_exiting)
+ if (t->net->pktgen_exiting)
break;
wait_event_interruptible_timeout(t->queue,
t->control != 0,
@@ -3424,7 +3439,7 @@ static int pktgen_add_device(struct pktgen_thread *t, const char *ifname)
/* We don't allow a device to be on several threads */
- pkt_dev = __pktgen_NN_threads(ifname, FIND);
+ pkt_dev = __pktgen_NN_threads(t->net, ifname, FIND);
if (pkt_dev) {
pr_err("ERROR: interface already used\n");
return -EBUSY;
@@ -3459,13 +3474,13 @@ static int pktgen_add_device(struct pktgen_thread *t, const char *ifname)
pkt_dev->svlan_id = 0xffff;
pkt_dev->node = -1;
- err = pktgen_setup_dev(pkt_dev, ifname);
+ err = pktgen_setup_dev(t->net, pkt_dev, ifname);
if (err)
goto out1;
if (pkt_dev->odev->priv_flags & IFF_TX_SKB_SHARING)
pkt_dev->clone_skb = pg_clone_skb_d;
- pkt_dev->entry = proc_create_data(ifname, 0600, pg_proc_dir,
+ pkt_dev->entry = proc_create_data(ifname, 0600, t->net->proc_dir,
&pktgen_if_fops, pkt_dev);
if (!pkt_dev->entry) {
pr_err("cannot create %s/%s procfs entry\n",
@@ -3490,7 +3505,7 @@ out1:
return err;
}
-static int __init pktgen_create_thread(int cpu)
+static int __net_init pktgen_create_thread(int cpu, struct pktgen_net *pn)
{
struct pktgen_thread *t;
struct proc_dir_entry *pe;
@@ -3508,7 +3523,7 @@ static int __init pktgen_create_thread(int cpu)
INIT_LIST_HEAD(&t->if_list);
- list_add_tail(&t->th_list, &pktgen_threads);
+ list_add_tail(&t->th_list, &pn->pktgen_threads);
init_completion(&t->start_done);
p = kthread_create_on_node(pktgen_thread_worker,
@@ -3524,7 +3539,7 @@ static int __init pktgen_create_thread(int cpu)
kthread_bind(p, cpu);
t->tsk = p;
- pe = proc_create_data(t->tsk->comm, 0600, pg_proc_dir,
+ pe = proc_create_data(t->tsk->comm, 0600, pn->proc_dir,
&pktgen_thread_fops, t);
if (!pe) {
pr_err("cannot create %s/%s procfs entry\n",
@@ -3535,6 +3550,7 @@ static int __init pktgen_create_thread(int cpu)
return -EINVAL;
}
+ t->net = pn;
wake_up_process(p);
wait_for_completion(&t->start_done);
@@ -3560,6 +3576,7 @@ static void _rem_dev_from_if_list(struct pktgen_thread *t,
static int pktgen_remove_device(struct pktgen_thread *t,
struct pktgen_dev *pkt_dev)
{
+ struct pktgen_net *pn = t->net;
pr_debug("remove_device pkt_dev=%p\n", pkt_dev);
@@ -3580,7 +3597,7 @@ static int pktgen_remove_device(struct pktgen_thread *t,
_rem_dev_from_if_list(t, pkt_dev);
if (pkt_dev->entry)
- remove_proc_entry(pkt_dev->entry->name, pg_proc_dir);
+ remove_proc_entry(pkt_dev->entry->name, pn->proc_dir);
#ifdef CONFIG_XFRM
free_SAs(pkt_dev);
@@ -3592,63 +3609,63 @@ static int pktgen_remove_device(struct pktgen_thread *t,
return 0;
}
-static int __init pg_init(void)
+static int __net_init pg_net_init(struct net *net)
{
- int cpu;
+ struct pktgen_net *pn = net_generic(net, pg_net_id);
struct proc_dir_entry *pe;
- int ret = 0;
-
- pr_info("%s", version);
-
- pg_proc_dir = proc_mkdir(PG_PROC_DIR, init_net.proc_net);
- if (!pg_proc_dir)
+ int cpu, ret = 0;
+
+ pn->net = net;
+ INIT_LIST_HEAD(&pn->pktgen_threads);
+ pn->pktgen_exiting = false;
+ pn->proc_dir = proc_mkdir(PG_PROC_DIR, pn->net->proc_net);
+ if (!pn->proc_dir) {
+ pr_warn("cannot create /proc/net/%s\n", PG_PROC_DIR);
return -ENODEV;
-
- pe = proc_create(PGCTRL, 0600, pg_proc_dir, &pktgen_fops);
+ }
+ pe = proc_create(PGCTRL, 0600, pn->proc_dir, &pktgen_fops);
if (pe == NULL) {
- pr_err("ERROR: cannot create %s procfs entry\n", PGCTRL);
+ pr_err("cannot create %s procfs entry\n", PGCTRL);
ret = -EINVAL;
- goto remove_dir;
+ goto remove;
}
- register_netdevice_notifier(&pktgen_notifier_block);
-
for_each_online_cpu(cpu) {
int err;
- err = pktgen_create_thread(cpu);
+ err = pktgen_create_thread(cpu, pn);
if (err)
- pr_warning("WARNING: Cannot create thread for cpu %d (%d)\n",
+ pr_warn("Cannot create thread for cpu %d (%d)\n",
cpu, err);
}
- if (list_empty(&pktgen_threads)) {
- pr_err("ERROR: Initialization failed for all threads\n");
+ if (list_empty(&pn->pktgen_threads)) {
+ pr_err("Initialization failed for all threads\n");
ret = -ENODEV;
- goto unregister;
+ goto remove_entry;
}
return 0;
- unregister:
- unregister_netdevice_notifier(&pktgen_notifier_block);
- remove_proc_entry(PGCTRL, pg_proc_dir);
- remove_dir:
- proc_net_remove(&init_net, PG_PROC_DIR);
+remove_entry:
+ remove_proc_entry(PGCTRL, pn->proc_dir);
+remove:
+ remove_proc_entry(PG_PROC_DIR, pn->net->proc_net);
return ret;
}
-static void __exit pg_cleanup(void)
+static void __net_exit pg_net_exit(struct net *net)
{
+ struct pktgen_net *pn = net_generic(net, pg_net_id);
struct pktgen_thread *t;
struct list_head *q, *n;
LIST_HEAD(list);
/* Stop all interfaces & threads */
- pktgen_exiting = true;
+ pn->pktgen_exiting = true;
mutex_lock(&pktgen_thread_lock);
- list_splice_init(&pktgen_threads, &list);
+ list_splice_init(&pn->pktgen_threads, &list);
mutex_unlock(&pktgen_thread_lock);
list_for_each_safe(q, n, &list) {
@@ -3658,12 +3675,36 @@ static void __exit pg_cleanup(void)
kfree(t);
}
- /* Un-register us from receiving netdevice events */
- unregister_netdevice_notifier(&pktgen_notifier_block);
+ remove_proc_entry(PGCTRL, pn->proc_dir);
+ remove_proc_entry(PG_PROC_DIR, pn->net->proc_net);
+}
+
+static struct pernet_operations pg_net_ops = {
+ .init = pg_net_init,
+ .exit = pg_net_exit,
+ .id = &pg_net_id,
+ .size = sizeof(struct pktgen_net),
+};
+
+static int __init pg_init(void)
+{
+ int ret = 0;
- /* Clean up proc file system */
- remove_proc_entry(PGCTRL, pg_proc_dir);
- proc_net_remove(&init_net, PG_PROC_DIR);
+ pr_info("%s", version);
+ ret = register_pernet_subsys(&pg_net_ops);
+ if (ret)
+ return ret;
+ ret = register_netdevice_notifier(&pktgen_notifier_block);
+ if (ret)
+ unregister_pernet_subsys(&pg_net_ops);
+
+ return ret;
+}
+
+static void __exit pg_cleanup(void)
+{
+ unregister_netdevice_notifier(&pktgen_notifier_block);
+ unregister_pernet_subsys(&pg_net_ops);
}
module_init(pg_init);
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 1868625af25e..5fb8d7e47294 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -780,6 +780,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev,
+ nla_total_size(4) /* IFLA_MTU */
+ nla_total_size(4) /* IFLA_LINK */
+ nla_total_size(4) /* IFLA_MASTER */
+ + nla_total_size(1) /* IFLA_CARRIER */
+ nla_total_size(4) /* IFLA_PROMISCUITY */
+ nla_total_size(4) /* IFLA_NUM_TX_QUEUES */
+ nla_total_size(4) /* IFLA_NUM_RX_QUEUES */
@@ -879,6 +880,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
const struct rtnl_link_stats64 *stats;
struct nlattr *attr, *af_spec;
struct rtnl_af_ops *af_ops;
+ struct net_device *upper_dev = netdev_master_upper_dev_get(dev);
ASSERT_RTNL();
nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ifm), flags);
@@ -907,8 +909,9 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
#endif
(dev->ifindex != dev->iflink &&
nla_put_u32(skb, IFLA_LINK, dev->iflink)) ||
- (dev->master &&
- nla_put_u32(skb, IFLA_MASTER, dev->master->ifindex)) ||
+ (upper_dev &&
+ nla_put_u32(skb, IFLA_MASTER, upper_dev->ifindex)) ||
+ nla_put_u8(skb, IFLA_CARRIER, netif_carrier_ok(dev)) ||
(dev->qdisc &&
nla_put_string(skb, IFLA_QDISC, dev->qdisc->ops->id)) ||
(dev->ifalias &&
@@ -976,6 +979,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
* report anything.
*/
ivi.spoofchk = -1;
+ memset(ivi.mac, 0, sizeof(ivi.mac));
if (dev->netdev_ops->ndo_get_vf_config(dev, i, &ivi))
break;
vf_mac.vf =
@@ -1057,7 +1061,6 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
int idx = 0, s_idx;
struct net_device *dev;
struct hlist_head *head;
- struct hlist_node *node;
struct nlattr *tb[IFLA_MAX+1];
u32 ext_filter_mask = 0;
@@ -1077,7 +1080,7 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) {
idx = 0;
head = &net->dev_index_head[h];
- hlist_for_each_entry_rcu(dev, node, head, index_hlist) {
+ hlist_for_each_entry_rcu(dev, head, index_hlist) {
if (idx < s_idx)
goto cont;
if (rtnl_fill_ifinfo(skb, dev, RTM_NEWLINK,
@@ -1108,6 +1111,7 @@ const struct nla_policy ifla_policy[IFLA_MAX+1] = {
[IFLA_MTU] = { .type = NLA_U32 },
[IFLA_LINK] = { .type = NLA_U32 },
[IFLA_MASTER] = { .type = NLA_U32 },
+ [IFLA_CARRIER] = { .type = NLA_U8 },
[IFLA_TXQLEN] = { .type = NLA_U32 },
[IFLA_WEIGHT] = { .type = NLA_U32 },
[IFLA_OPERSTATE] = { .type = NLA_U8 },
@@ -1270,16 +1274,16 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr *attr)
static int do_set_master(struct net_device *dev, int ifindex)
{
- struct net_device *master_dev;
+ struct net_device *upper_dev = netdev_master_upper_dev_get(dev);
const struct net_device_ops *ops;
int err;
- if (dev->master) {
- if (dev->master->ifindex == ifindex)
+ if (upper_dev) {
+ if (upper_dev->ifindex == ifindex)
return 0;
- ops = dev->master->netdev_ops;
+ ops = upper_dev->netdev_ops;
if (ops->ndo_del_slave) {
- err = ops->ndo_del_slave(dev->master, dev);
+ err = ops->ndo_del_slave(upper_dev, dev);
if (err)
return err;
} else {
@@ -1288,12 +1292,12 @@ static int do_set_master(struct net_device *dev, int ifindex)
}
if (ifindex) {
- master_dev = __dev_get_by_index(dev_net(dev), ifindex);
- if (!master_dev)
+ upper_dev = __dev_get_by_index(dev_net(dev), ifindex);
+ if (!upper_dev)
return -EINVAL;
- ops = master_dev->netdev_ops;
+ ops = upper_dev->netdev_ops;
if (ops->ndo_add_slave) {
- err = ops->ndo_add_slave(master_dev, dev);
+ err = ops->ndo_add_slave(upper_dev, dev);
if (err)
return err;
} else {
@@ -1307,7 +1311,6 @@ static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm,
struct nlattr **tb, char *ifname, int modified)
{
const struct net_device_ops *ops = dev->netdev_ops;
- int send_addr_notify = 0;
int err;
if (tb[IFLA_NET_NS_PID] || tb[IFLA_NET_NS_FD]) {
@@ -1360,16 +1363,6 @@ static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm,
struct sockaddr *sa;
int len;
- if (!ops->ndo_set_mac_address) {
- err = -EOPNOTSUPP;
- goto errout;
- }
-
- if (!netif_device_present(dev)) {
- err = -ENODEV;
- goto errout;
- }
-
len = sizeof(sa_family_t) + dev->addr_len;
sa = kmalloc(len, GFP_KERNEL);
if (!sa) {
@@ -1379,13 +1372,11 @@ static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm,
sa->sa_family = dev->type;
memcpy(sa->sa_data, nla_data(tb[IFLA_ADDRESS]),
dev->addr_len);
- err = ops->ndo_set_mac_address(dev, sa);
+ err = dev_set_mac_address(dev, sa);
kfree(sa);
if (err)
goto errout;
- send_addr_notify = 1;
modified = 1;
- add_device_randomness(dev->dev_addr, dev->addr_len);
}
if (tb[IFLA_MTU]) {
@@ -1422,7 +1413,7 @@ static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm,
if (tb[IFLA_BROADCAST]) {
nla_memcpy(dev->broadcast, tb[IFLA_BROADCAST], dev->addr_len);
- send_addr_notify = 1;
+ call_netdevice_notifiers(NETDEV_CHANGEADDR, dev);
}
if (ifm->ifi_flags || ifm->ifi_change) {
@@ -1438,6 +1429,13 @@ static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm,
modified = 1;
}
+ if (tb[IFLA_CARRIER]) {
+ err = dev_change_carrier(dev, nla_get_u8(tb[IFLA_CARRIER]));
+ if (err)
+ goto errout;
+ modified = 1;
+ }
+
if (tb[IFLA_TXQLEN])
dev->tx_queue_len = nla_get_u32(tb[IFLA_TXQLEN]);
@@ -1536,9 +1534,6 @@ errout:
net_warn_ratelimited("A link change request failed with some changes committed already. Interface %s may have been left with an inconsistent configuration, please check.\n",
dev->name);
- if (send_addr_notify)
- call_netdevice_notifiers(NETDEV_CHANGEADDR, dev);
-
return err;
}
@@ -1672,9 +1667,11 @@ struct net_device *rtnl_create_link(struct net *net,
if (tb[IFLA_MTU])
dev->mtu = nla_get_u32(tb[IFLA_MTU]);
- if (tb[IFLA_ADDRESS])
+ if (tb[IFLA_ADDRESS]) {
memcpy(dev->dev_addr, nla_data(tb[IFLA_ADDRESS]),
nla_len(tb[IFLA_ADDRESS]));
+ dev->addr_assign_type = NET_ADDR_SET;
+ }
if (tb[IFLA_BROADCAST])
memcpy(dev->broadcast, nla_data(tb[IFLA_BROADCAST]),
nla_len(tb[IFLA_BROADCAST]));
@@ -1992,6 +1989,7 @@ errout:
if (err < 0)
rtnl_set_sk_err(net, RTNLGRP_LINK, err);
}
+EXPORT_SYMBOL(rtmsg_ifinfo);
static int nlmsg_populate_fdb_fill(struct sk_buff *skb,
struct net_device *dev,
@@ -2054,16 +2052,12 @@ errout:
static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
{
struct net *net = sock_net(skb->sk);
- struct net_device *master = NULL;
struct ndmsg *ndm;
struct nlattr *tb[NDA_MAX+1];
struct net_device *dev;
u8 *addr;
int err;
- if (!capable(CAP_NET_ADMIN))
- return -EPERM;
-
err = nlmsg_parse(nlh, sizeof(*ndm), tb, NDA_MAX, NULL);
if (err < 0)
return err;
@@ -2096,10 +2090,10 @@ static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
/* Support fdb on master device the net/bridge default case */
if ((!ndm->ndm_flags || ndm->ndm_flags & NTF_MASTER) &&
(dev->priv_flags & IFF_BRIDGE_PORT)) {
- master = dev->master;
- err = master->netdev_ops->ndo_fdb_add(ndm, tb,
- dev, addr,
- nlh->nlmsg_flags);
+ struct net_device *br_dev = netdev_master_upper_dev_get(dev);
+ const struct net_device_ops *ops = br_dev->netdev_ops;
+
+ err = ops->ndo_fdb_add(ndm, tb, dev, addr, nlh->nlmsg_flags);
if (err)
goto out;
else
@@ -2125,7 +2119,7 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
{
struct net *net = sock_net(skb->sk);
struct ndmsg *ndm;
- struct nlattr *llattr;
+ struct nlattr *tb[NDA_MAX+1];
struct net_device *dev;
int err = -EINVAL;
__u8 *addr;
@@ -2133,8 +2127,9 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
if (!capable(CAP_NET_ADMIN))
return -EPERM;
- if (nlmsg_len(nlh) < sizeof(*ndm))
- return -EINVAL;
+ err = nlmsg_parse(nlh, sizeof(*ndm), tb, NDA_MAX, NULL);
+ if (err < 0)
+ return err;
ndm = nlmsg_data(nlh);
if (ndm->ndm_ifindex == 0) {
@@ -2148,22 +2143,27 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
return -ENODEV;
}
- llattr = nlmsg_find_attr(nlh, sizeof(*ndm), NDA_LLADDR);
- if (llattr == NULL || nla_len(llattr) != ETH_ALEN) {
- pr_info("PF_BRIGDE: RTM_DELNEIGH with invalid address\n");
+ if (!tb[NDA_LLADDR] || nla_len(tb[NDA_LLADDR]) != ETH_ALEN) {
+ pr_info("PF_BRIDGE: RTM_DELNEIGH with invalid address\n");
+ return -EINVAL;
+ }
+
+ addr = nla_data(tb[NDA_LLADDR]);
+ if (!is_valid_ether_addr(addr)) {
+ pr_info("PF_BRIDGE: RTM_DELNEIGH with invalid ether address\n");
return -EINVAL;
}
- addr = nla_data(llattr);
err = -EOPNOTSUPP;
/* Support fdb on master device the net/bridge default case */
if ((!ndm->ndm_flags || ndm->ndm_flags & NTF_MASTER) &&
(dev->priv_flags & IFF_BRIDGE_PORT)) {
- struct net_device *master = dev->master;
+ struct net_device *br_dev = netdev_master_upper_dev_get(dev);
+ const struct net_device_ops *ops = br_dev->netdev_ops;
- if (master->netdev_ops->ndo_fdb_del)
- err = master->netdev_ops->ndo_fdb_del(ndm, dev, addr);
+ if (ops->ndo_fdb_del)
+ err = ops->ndo_fdb_del(ndm, tb, dev, addr);
if (err)
goto out;
@@ -2173,7 +2173,7 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
/* Embedded bridge, macvlan, and any other device support */
if ((ndm->ndm_flags & NTF_SELF) && dev->netdev_ops->ndo_fdb_del) {
- err = dev->netdev_ops->ndo_fdb_del(ndm, dev, addr);
+ err = dev->netdev_ops->ndo_fdb_del(ndm, tb, dev, addr);
if (!err) {
rtnl_fdb_notify(dev, addr, RTM_DELNEIGH);
@@ -2247,9 +2247,11 @@ static int rtnl_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb)
rcu_read_lock();
for_each_netdev_rcu(net, dev) {
if (dev->priv_flags & IFF_BRIDGE_PORT) {
- struct net_device *master = dev->master;
- const struct net_device_ops *ops = master->netdev_ops;
+ struct net_device *br_dev;
+ const struct net_device_ops *ops;
+ br_dev = netdev_master_upper_dev_get(dev);
+ ops = br_dev->netdev_ops;
if (ops->ndo_fdb_dump)
idx = ops->ndo_fdb_dump(skb, cb, dev, idx);
}
@@ -2270,6 +2272,7 @@ int ndo_dflt_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
struct ifinfomsg *ifm;
struct nlattr *br_afspec;
u8 operstate = netif_running(dev) ? dev->operstate : IF_OPER_DOWN;
+ struct net_device *br_dev = netdev_master_upper_dev_get(dev);
nlh = nlmsg_put(skb, pid, seq, RTM_NEWLINK, sizeof(*ifm), NLM_F_MULTI);
if (nlh == NULL)
@@ -2287,8 +2290,8 @@ int ndo_dflt_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
if (nla_put_string(skb, IFLA_IFNAME, dev->name) ||
nla_put_u32(skb, IFLA_MTU, dev->mtu) ||
nla_put_u8(skb, IFLA_OPERSTATE, operstate) ||
- (dev->master &&
- nla_put_u32(skb, IFLA_MASTER, dev->master->ifindex)) ||
+ (br_dev &&
+ nla_put_u32(skb, IFLA_MASTER, br_dev->ifindex)) ||
(dev->addr_len &&
nla_put(skb, IFLA_ADDRESS, dev->addr_len, dev->dev_addr)) ||
(dev->ifindex != dev->iflink &&
@@ -2320,23 +2323,31 @@ static int rtnl_bridge_getlink(struct sk_buff *skb, struct netlink_callback *cb)
int idx = 0;
u32 portid = NETLINK_CB(cb->skb).portid;
u32 seq = cb->nlh->nlmsg_seq;
+ struct nlattr *extfilt;
+ u32 filter_mask = 0;
+
+ extfilt = nlmsg_find_attr(cb->nlh, sizeof(struct rtgenmsg),
+ IFLA_EXT_MASK);
+ if (extfilt)
+ filter_mask = nla_get_u32(extfilt);
rcu_read_lock();
for_each_netdev_rcu(net, dev) {
const struct net_device_ops *ops = dev->netdev_ops;
- struct net_device *master = dev->master;
+ struct net_device *br_dev = netdev_master_upper_dev_get(dev);
- if (master && master->netdev_ops->ndo_bridge_getlink) {
+ if (br_dev && br_dev->netdev_ops->ndo_bridge_getlink) {
if (idx >= cb->args[0] &&
- master->netdev_ops->ndo_bridge_getlink(
- skb, portid, seq, dev) < 0)
+ br_dev->netdev_ops->ndo_bridge_getlink(
+ skb, portid, seq, dev, filter_mask) < 0)
break;
idx++;
}
if (ops->ndo_bridge_getlink) {
if (idx >= cb->args[0] &&
- ops->ndo_bridge_getlink(skb, portid, seq, dev) < 0)
+ ops->ndo_bridge_getlink(skb, portid, seq, dev,
+ filter_mask) < 0)
break;
idx++;
}
@@ -2365,7 +2376,7 @@ static inline size_t bridge_nlmsg_size(void)
static int rtnl_bridge_notify(struct net_device *dev, u16 flags)
{
struct net *net = dev_net(dev);
- struct net_device *master = dev->master;
+ struct net_device *br_dev = netdev_master_upper_dev_get(dev);
struct sk_buff *skb;
int err = -EOPNOTSUPP;
@@ -2376,15 +2387,15 @@ static int rtnl_bridge_notify(struct net_device *dev, u16 flags)
}
if ((!flags || (flags & BRIDGE_FLAGS_MASTER)) &&
- master && master->netdev_ops->ndo_bridge_getlink) {
- err = master->netdev_ops->ndo_bridge_getlink(skb, 0, 0, dev);
+ br_dev && br_dev->netdev_ops->ndo_bridge_getlink) {
+ err = br_dev->netdev_ops->ndo_bridge_getlink(skb, 0, 0, dev, 0);
if (err < 0)
goto errout;
}
if ((flags & BRIDGE_FLAGS_SELF) &&
dev->netdev_ops->ndo_bridge_getlink) {
- err = dev->netdev_ops->ndo_bridge_getlink(skb, 0, 0, dev);
+ err = dev->netdev_ops->ndo_bridge_getlink(skb, 0, 0, dev, 0);
if (err < 0)
goto errout;
}
@@ -2436,13 +2447,14 @@ static int rtnl_bridge_setlink(struct sk_buff *skb, struct nlmsghdr *nlh,
oflags = flags;
if (!flags || (flags & BRIDGE_FLAGS_MASTER)) {
- if (!dev->master ||
- !dev->master->netdev_ops->ndo_bridge_setlink) {
+ struct net_device *br_dev = netdev_master_upper_dev_get(dev);
+
+ if (!br_dev || !br_dev->netdev_ops->ndo_bridge_setlink) {
err = -EOPNOTSUPP;
goto out;
}
- err = dev->master->netdev_ops->ndo_bridge_setlink(dev, nlh);
+ err = br_dev->netdev_ops->ndo_bridge_setlink(dev, nlh);
if (err)
goto out;
@@ -2468,6 +2480,77 @@ out:
return err;
}
+static int rtnl_bridge_dellink(struct sk_buff *skb, struct nlmsghdr *nlh,
+ void *arg)
+{
+ struct net *net = sock_net(skb->sk);
+ struct ifinfomsg *ifm;
+ struct net_device *dev;
+ struct nlattr *br_spec, *attr = NULL;
+ int rem, err = -EOPNOTSUPP;
+ u16 oflags, flags = 0;
+ bool have_flags = false;
+
+ if (nlmsg_len(nlh) < sizeof(*ifm))
+ return -EINVAL;
+
+ ifm = nlmsg_data(nlh);
+ if (ifm->ifi_family != AF_BRIDGE)
+ return -EPFNOSUPPORT;
+
+ dev = __dev_get_by_index(net, ifm->ifi_index);
+ if (!dev) {
+ pr_info("PF_BRIDGE: RTM_SETLINK with unknown ifindex\n");
+ return -ENODEV;
+ }
+
+ br_spec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC);
+ if (br_spec) {
+ nla_for_each_nested(attr, br_spec, rem) {
+ if (nla_type(attr) == IFLA_BRIDGE_FLAGS) {
+ have_flags = true;
+ flags = nla_get_u16(attr);
+ break;
+ }
+ }
+ }
+
+ oflags = flags;
+
+ if (!flags || (flags & BRIDGE_FLAGS_MASTER)) {
+ struct net_device *br_dev = netdev_master_upper_dev_get(dev);
+
+ if (!br_dev || !br_dev->netdev_ops->ndo_bridge_dellink) {
+ err = -EOPNOTSUPP;
+ goto out;
+ }
+
+ err = br_dev->netdev_ops->ndo_bridge_dellink(dev, nlh);
+ if (err)
+ goto out;
+
+ flags &= ~BRIDGE_FLAGS_MASTER;
+ }
+
+ if ((flags & BRIDGE_FLAGS_SELF)) {
+ if (!dev->netdev_ops->ndo_bridge_dellink)
+ err = -EOPNOTSUPP;
+ else
+ err = dev->netdev_ops->ndo_bridge_dellink(dev, nlh);
+
+ if (!err)
+ flags &= ~BRIDGE_FLAGS_SELF;
+ }
+
+ if (have_flags)
+ memcpy(nla_data(attr), &flags, sizeof(flags));
+ /* Generate event to notify upper layer of bridge change */
+ if (!err)
+ err = rtnl_bridge_notify(dev, oflags);
+out:
+ return err;
+}
+
/* Protected by RTNL sempahore. */
static struct rtattr **rta_buf;
static int rtattr_max;
@@ -2538,7 +2621,7 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
struct rtattr *attr = (void *)nlh + NLMSG_ALIGN(min_len);
while (RTA_OK(attr, attrlen)) {
- unsigned int flavor = attr->rta_type;
+ unsigned int flavor = attr->rta_type & NLA_TYPE_MASK;
if (flavor) {
if (flavor > rta_max[sz_idx])
return -EINVAL;
@@ -2651,6 +2734,7 @@ void __init rtnetlink_init(void)
rtnl_register(PF_BRIDGE, RTM_GETNEIGH, NULL, rtnl_fdb_dump, NULL);
rtnl_register(PF_BRIDGE, RTM_GETLINK, NULL, rtnl_bridge_getlink, NULL);
+ rtnl_register(PF_BRIDGE, RTM_DELLINK, rtnl_bridge_dellink, NULL, NULL);
rtnl_register(PF_BRIDGE, RTM_SETLINK, rtnl_bridge_setlink, NULL, NULL);
}
diff --git a/net/core/scm.c b/net/core/scm.c
index 905dcc6ad1e3..2dc6cdaaae8a 100644
--- a/net/core/scm.c
+++ b/net/core/scm.c
@@ -24,6 +24,7 @@
#include <linux/interrupt.h>
#include <linux/netdevice.h>
#include <linux/security.h>
+#include <linux/pid_namespace.h>
#include <linux/pid.h>
#include <linux/nsproxy.h>
#include <linux/slab.h>
@@ -52,7 +53,8 @@ static __inline__ int scm_check_creds(struct ucred *creds)
if (!uid_valid(uid) || !gid_valid(gid))
return -EINVAL;
- if ((creds->pid == task_tgid_vnr(current) || nsown_capable(CAP_SYS_ADMIN)) &&
+ if ((creds->pid == task_tgid_vnr(current) ||
+ ns_capable(current->nsproxy->pid_ns->user_ns, CAP_SYS_ADMIN)) &&
((uid_eq(uid, cred->uid) || uid_eq(uid, cred->euid) ||
uid_eq(uid, cred->suid)) || nsown_capable(CAP_SETUID)) &&
((gid_eq(gid, cred->gid) || gid_eq(gid, cred->egid) ||
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index a9a2ae3e2213..33245ef54c3b 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -104,47 +104,37 @@ static const struct pipe_buf_operations sock_pipe_buf_ops = {
.get = sock_pipe_buf_get,
};
-/*
- * Keep out-of-line to prevent kernel bloat.
- * __builtin_return_address is not used because it is not always
- * reliable.
- */
-
/**
- * skb_over_panic - private function
- * @skb: buffer
- * @sz: size
- * @here: address
- *
- * Out of line support code for skb_put(). Not user callable.
+ * skb_panic - private function for out-of-line support
+ * @skb: buffer
+ * @sz: size
+ * @addr: address
+ * @msg: skb_over_panic or skb_under_panic
+ *
+ * Out-of-line support for skb_put() and skb_push().
+ * Called via the wrapper skb_over_panic() or skb_under_panic().
+ * Keep out of line to prevent kernel bloat.
+ * __builtin_return_address is not used because it is not always reliable.
*/
-static void skb_over_panic(struct sk_buff *skb, int sz, void *here)
+static void skb_panic(struct sk_buff *skb, unsigned int sz, void *addr,
+ const char msg[])
{
pr_emerg("%s: text:%p len:%d put:%d head:%p data:%p tail:%#lx end:%#lx dev:%s\n",
- __func__, here, skb->len, sz, skb->head, skb->data,
+ msg, addr, skb->len, sz, skb->head, skb->data,
(unsigned long)skb->tail, (unsigned long)skb->end,
skb->dev ? skb->dev->name : "<NULL>");
BUG();
}
-/**
- * skb_under_panic - private function
- * @skb: buffer
- * @sz: size
- * @here: address
- *
- * Out of line support code for skb_push(). Not user callable.
- */
-
-static void skb_under_panic(struct sk_buff *skb, int sz, void *here)
+static void skb_over_panic(struct sk_buff *skb, unsigned int sz, void *addr)
{
- pr_emerg("%s: text:%p len:%d put:%d head:%p data:%p tail:%#lx end:%#lx dev:%s\n",
- __func__, here, skb->len, sz, skb->head, skb->data,
- (unsigned long)skb->tail, (unsigned long)skb->end,
- skb->dev ? skb->dev->name : "<NULL>");
- BUG();
+ skb_panic(skb, sz, addr, __func__);
}
+static void skb_under_panic(struct sk_buff *skb, unsigned int sz, void *addr)
+{
+ skb_panic(skb, sz, addr, __func__);
+}
/*
* kmalloc_reserve is a wrapper around kmalloc_node_track_caller that tells
@@ -155,8 +145,9 @@ static void skb_under_panic(struct sk_buff *skb, int sz, void *here)
*/
#define kmalloc_reserve(size, gfp, node, pfmemalloc) \
__kmalloc_reserve(size, gfp, node, _RET_IP_, pfmemalloc)
-void *__kmalloc_reserve(size_t size, gfp_t flags, int node, unsigned long ip,
- bool *pfmemalloc)
+
+static void *__kmalloc_reserve(size_t size, gfp_t flags, int node,
+ unsigned long ip, bool *pfmemalloc)
{
void *obj;
bool ret_pfmemalloc = false;
@@ -259,6 +250,7 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask,
skb->end = skb->tail + size;
#ifdef NET_SKBUFF_DATA_USES_OFFSET
skb->mac_header = ~0U;
+ skb->transport_header = ~0U;
#endif
/* make sure we initialize shinfo sequentially */
@@ -327,6 +319,7 @@ struct sk_buff *build_skb(void *data, unsigned int frag_size)
skb->end = skb->tail + size;
#ifdef NET_SKBUFF_DATA_USES_OFFSET
skb->mac_header = ~0U;
+ skb->transport_header = ~0U;
#endif
/* make sure we initialize shinfo sequentially */
@@ -348,10 +341,6 @@ struct netdev_alloc_cache {
};
static DEFINE_PER_CPU(struct netdev_alloc_cache, netdev_alloc_cache);
-#define NETDEV_FRAG_PAGE_MAX_ORDER get_order(32768)
-#define NETDEV_FRAG_PAGE_MAX_SIZE (PAGE_SIZE << NETDEV_FRAG_PAGE_MAX_ORDER)
-#define NETDEV_PAGECNT_MAX_BIAS NETDEV_FRAG_PAGE_MAX_SIZE
-
static void *__netdev_alloc_frag(unsigned int fragsz, gfp_t gfp_mask)
{
struct netdev_alloc_cache *nc;
@@ -683,7 +672,7 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old)
new->network_header = old->network_header;
new->mac_header = old->mac_header;
new->inner_transport_header = old->inner_transport_header;
- new->inner_network_header = old->inner_transport_header;
+ new->inner_network_header = old->inner_network_header;
skb_dst_copy(new, old);
new->rxhash = old->rxhash;
new->ooo_okay = old->ooo_okay;
@@ -2337,6 +2326,7 @@ void skb_split(struct sk_buff *skb, struct sk_buff *skb1, const u32 len)
{
int pos = skb_headlen(skb);
+ skb_shinfo(skb1)->tx_flags = skb_shinfo(skb)->tx_flags & SKBTX_SHARED_FRAG;
if (len < pos) /* Split line is inside header. */
skb_split_inside_header(skb, skb1, len, pos);
else /* Second chunk has no header, nothing to copy. */
@@ -2668,48 +2658,37 @@ int skb_append_datato_frags(struct sock *sk, struct sk_buff *skb,
int len, int odd, struct sk_buff *skb),
void *from, int length)
{
- int frg_cnt = 0;
- skb_frag_t *frag = NULL;
- struct page *page = NULL;
- int copy, left;
+ int frg_cnt = skb_shinfo(skb)->nr_frags;
+ int copy;
int offset = 0;
int ret;
+ struct page_frag *pfrag = &current->task_frag;
do {
/* Return error if we don't have space for new frag */
- frg_cnt = skb_shinfo(skb)->nr_frags;
if (frg_cnt >= MAX_SKB_FRAGS)
- return -EFAULT;
+ return -EMSGSIZE;
- /* allocate a new page for next frag */
- page = alloc_pages(sk->sk_allocation, 0);
-
- /* If alloc_page fails just return failure and caller will
- * free previous allocated pages by doing kfree_skb()
- */
- if (page == NULL)
+ if (!sk_page_frag_refill(sk, pfrag))
return -ENOMEM;
- /* initialize the next frag */
- skb_fill_page_desc(skb, frg_cnt, page, 0, 0);
- skb->truesize += PAGE_SIZE;
- atomic_add(PAGE_SIZE, &sk->sk_wmem_alloc);
-
- /* get the new initialized frag */
- frg_cnt = skb_shinfo(skb)->nr_frags;
- frag = &skb_shinfo(skb)->frags[frg_cnt - 1];
-
/* copy the user data to page */
- left = PAGE_SIZE - frag->page_offset;
- copy = (length > left)? left : length;
+ copy = min_t(int, length, pfrag->size - pfrag->offset);
- ret = getfrag(from, skb_frag_address(frag) + skb_frag_size(frag),
- offset, copy, 0, skb);
+ ret = getfrag(from, page_address(pfrag->page) + pfrag->offset,
+ offset, copy, 0, skb);
if (ret < 0)
return -EFAULT;
/* copy was successful so update the size parameters */
- skb_frag_size_add(frag, copy);
+ skb_fill_page_desc(skb, frg_cnt, pfrag->page, pfrag->offset,
+ copy);
+ frg_cnt++;
+ pfrag->offset += copy;
+ get_page(pfrag->page);
+
+ skb->truesize += copy;
+ atomic_add(copy, &sk->sk_wmem_alloc);
skb->len += copy;
skb->data_len += copy;
offset += copy;
@@ -2759,6 +2738,7 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features)
unsigned int mss = skb_shinfo(skb)->gso_size;
unsigned int doffset = skb->data - skb_mac_header(skb);
unsigned int offset = doffset;
+ unsigned int tnl_hlen = skb_tnl_header_len(skb);
unsigned int headroom;
unsigned int len;
int sg = !!(features & NETIF_F_SG);
@@ -2835,7 +2815,10 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features)
skb_set_network_header(nskb, skb->mac_len);
nskb->transport_header = (nskb->network_header +
skb_network_header_len(skb));
- skb_copy_from_linear_data(skb, nskb->data, doffset);
+
+ skb_copy_from_linear_data_offset(skb, -tnl_hlen,
+ nskb->data - tnl_hlen,
+ doffset + tnl_hlen);
if (fskb != skb_shinfo(skb)->frag_list)
continue;
@@ -2853,6 +2836,8 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features)
skb_copy_from_linear_data_offset(skb, offset,
skb_put(nskb, hsize), hsize);
+ skb_shinfo(nskb)->tx_flags = skb_shinfo(skb)->tx_flags & SKBTX_SHARED_FRAG;
+
while (pos < offset + len && i < nfrags) {
*frag = skb_shinfo(skb)->frags[i];
__skb_frag_ref(frag);
diff --git a/net/core/sock.c b/net/core/sock.c
index bc131d419683..b261a7977746 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -186,8 +186,10 @@ void mem_cgroup_sockets_destroy(struct mem_cgroup *memcg)
static struct lock_class_key af_family_keys[AF_MAX];
static struct lock_class_key af_family_slock_keys[AF_MAX];
+#if defined(CONFIG_MEMCG_KMEM)
struct static_key memcg_socket_limit_enabled;
EXPORT_SYMBOL(memcg_socket_limit_enabled);
+#endif
/*
* Make lock validator output more readable. (we pre-construct these
@@ -665,6 +667,9 @@ int sock_setsockopt(struct socket *sock, int level, int optname,
case SO_REUSEADDR:
sk->sk_reuse = (valbool ? SK_CAN_REUSE : SK_NO_REUSE);
break;
+ case SO_REUSEPORT:
+ sk->sk_reuseport = valbool;
+ break;
case SO_TYPE:
case SO_PROTOCOL:
case SO_DOMAIN:
@@ -861,6 +866,13 @@ set_rcvbuf:
ret = sk_detach_filter(sk);
break;
+ case SO_LOCK_FILTER:
+ if (sock_flag(sk, SOCK_FILTER_LOCKED) && !valbool)
+ ret = -EPERM;
+ else
+ sock_valbool_flag(sk, SOCK_FILTER_LOCKED, valbool);
+ break;
+
case SO_PASSSEC:
if (valbool)
set_bit(SOCK_PASSSEC, &sock->flags);
@@ -965,6 +977,10 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
v.val = sk->sk_reuse;
break;
+ case SO_REUSEPORT:
+ v.val = sk->sk_reuseport;
+ break;
+
case SO_KEEPALIVE:
v.val = sock_flag(sk, SOCK_KEEPOPEN);
break;
@@ -1140,6 +1156,10 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
goto lenout;
+ case SO_LOCK_FILTER:
+ v.val = sock_flag(sk, SOCK_FILTER_LOCKED);
+ break;
+
default:
return -ENOPROTOOPT;
}
@@ -2212,7 +2232,7 @@ EXPORT_SYMBOL(sk_reset_timer);
void sk_stop_timer(struct sock *sk, struct timer_list* timer)
{
- if (timer_pending(timer) && del_timer(timer))
+ if (del_timer(timer))
__sock_put(sk);
}
EXPORT_SYMBOL(sk_stop_timer);
@@ -2818,7 +2838,7 @@ static const struct file_operations proto_seq_fops = {
static __net_init int proto_init_net(struct net *net)
{
- if (!proc_net_fops_create(net, "protocols", S_IRUGO, &proto_seq_fops))
+ if (!proc_create("protocols", S_IRUGO, net->proc_net, &proto_seq_fops))
return -ENOMEM;
return 0;
@@ -2826,7 +2846,7 @@ static __net_init int proto_init_net(struct net *net)
static __net_exit void proto_exit_net(struct net *net)
{
- proc_net_remove(net, "protocols");
+ remove_proc_entry("protocols", net->proc_net);
}
diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c
index 602cd637182e..a29e90cf36b7 100644
--- a/net/core/sock_diag.c
+++ b/net/core/sock_diag.c
@@ -97,21 +97,6 @@ void sock_diag_unregister(const struct sock_diag_handler *hnld)
}
EXPORT_SYMBOL_GPL(sock_diag_unregister);
-static const inline struct sock_diag_handler *sock_diag_lock_handler(int family)
-{
- if (sock_diag_handlers[family] == NULL)
- request_module("net-pf-%d-proto-%d-type-%d", PF_NETLINK,
- NETLINK_SOCK_DIAG, family);
-
- mutex_lock(&sock_diag_table_mutex);
- return sock_diag_handlers[family];
-}
-
-static inline void sock_diag_unlock_handler(const struct sock_diag_handler *h)
-{
- mutex_unlock(&sock_diag_table_mutex);
-}
-
static int __sock_diag_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
{
int err;
@@ -121,12 +106,20 @@ static int __sock_diag_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
if (nlmsg_len(nlh) < sizeof(*req))
return -EINVAL;
- hndl = sock_diag_lock_handler(req->sdiag_family);
+ if (req->sdiag_family >= AF_MAX)
+ return -EINVAL;
+
+ if (sock_diag_handlers[req->sdiag_family] == NULL)
+ request_module("net-pf-%d-proto-%d-type-%d", PF_NETLINK,
+ NETLINK_SOCK_DIAG, req->sdiag_family);
+
+ mutex_lock(&sock_diag_table_mutex);
+ hndl = sock_diag_handlers[req->sdiag_family];
if (hndl == NULL)
err = -ENOENT;
else
err = hndl->dump(skb, nlh);
- sock_diag_unlock_handler(hndl);
+ mutex_unlock(&sock_diag_table_mutex);
return err;
}
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index d1b08045a9df..cfdb46ab3a7f 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -20,6 +20,8 @@
#include <net/sock.h>
#include <net/net_ratelimit.h>
+static int one = 1;
+
#ifdef CONFIG_RPS
static int rps_sock_flow_sysctl(ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
@@ -92,28 +94,32 @@ static struct ctl_table net_core_table[] = {
.data = &sysctl_wmem_max,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = proc_dointvec
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &one,
},
{
.procname = "rmem_max",
.data = &sysctl_rmem_max,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = proc_dointvec
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &one,
},
{
.procname = "wmem_default",
.data = &sysctl_wmem_default,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = proc_dointvec
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &one,
},
{
.procname = "rmem_default",
.data = &sysctl_rmem_default,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = proc_dointvec
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &one,
},
{
.procname = "dev_weight",