summaryrefslogtreecommitdiff
path: root/net/core
diff options
context:
space:
mode:
Diffstat (limited to 'net/core')
-rw-r--r--net/core/Makefile2
-rw-r--r--net/core/datagram.c24
-rw-r--r--net/core/dev.c377
-rw-r--r--net/core/dev_addr_lists.c5
-rw-r--r--net/core/dst.c22
-rw-r--r--net/core/ethtool.c333
-rw-r--r--net/core/fib_rules.c20
-rw-r--r--net/core/filter.c4
-rw-r--r--net/core/flow.c52
-rw-r--r--net/core/kmap_skb.h2
-rw-r--r--net/core/link_watch.c11
-rw-r--r--net/core/neighbour.c249
-rw-r--r--net/core/net-sysfs.c15
-rw-r--r--net/core/net-traces.c3
-rw-r--r--net/core/net_namespace.c2
-rw-r--r--net/core/netevent.c1
-rw-r--r--net/core/netpoll.c22
-rw-r--r--net/core/pktgen.c33
-rw-r--r--net/core/rtnetlink.c98
-rw-r--r--net/core/scm.c12
-rw-r--r--net/core/secure_seq.c184
-rw-r--r--net/core/skbuff.c272
-rw-r--r--net/core/sock.c35
-rw-r--r--net/core/timestamping.c15
-rw-r--r--net/core/user_dma.c7
25 files changed, 1022 insertions, 778 deletions
diff --git a/net/core/Makefile b/net/core/Makefile
index 8a04dd22cf77..0d357b1c4e57 100644
--- a/net/core/Makefile
+++ b/net/core/Makefile
@@ -3,7 +3,7 @@
#
obj-y := sock.o request_sock.o skbuff.o iovec.o datagram.o stream.o scm.o \
- gen_stats.o gen_estimator.o net_namespace.o
+ gen_stats.o gen_estimator.o net_namespace.o secure_seq.o
obj-$(CONFIG_SYSCTL) += sysctl_net_core.o
diff --git a/net/core/datagram.c b/net/core/datagram.c
index 18ac112ea7ae..68bbf9f65cb0 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -324,15 +324,15 @@ int skb_copy_datagram_iovec(const struct sk_buff *skb, int offset,
/* Copy paged appendix. Hmm... why does this look so complicated? */
for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
int end;
+ const skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
WARN_ON(start > offset + len);
- end = start + skb_shinfo(skb)->frags[i].size;
+ end = start + skb_frag_size(frag);
if ((copy = end - offset) > 0) {
int err;
u8 *vaddr;
- skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
- struct page *page = frag->page;
+ struct page *page = skb_frag_page(frag);
if (copy > len)
copy = len;
@@ -410,15 +410,15 @@ int skb_copy_datagram_const_iovec(const struct sk_buff *skb, int offset,
/* Copy paged appendix. Hmm... why does this look so complicated? */
for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
int end;
+ const skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
WARN_ON(start > offset + len);
- end = start + skb_shinfo(skb)->frags[i].size;
+ end = start + skb_frag_size(frag);
if ((copy = end - offset) > 0) {
int err;
u8 *vaddr;
- skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
- struct page *page = frag->page;
+ struct page *page = skb_frag_page(frag);
if (copy > len)
copy = len;
@@ -500,15 +500,15 @@ int skb_copy_datagram_from_iovec(struct sk_buff *skb, int offset,
/* Copy paged appendix. Hmm... why does this look so complicated? */
for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
int end;
+ const skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
WARN_ON(start > offset + len);
- end = start + skb_shinfo(skb)->frags[i].size;
+ end = start + skb_frag_size(frag);
if ((copy = end - offset) > 0) {
int err;
u8 *vaddr;
- skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
- struct page *page = frag->page;
+ struct page *page = skb_frag_page(frag);
if (copy > len)
copy = len;
@@ -585,16 +585,16 @@ static int skb_copy_and_csum_datagram(const struct sk_buff *skb, int offset,
for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
int end;
+ const skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
WARN_ON(start > offset + len);
- end = start + skb_shinfo(skb)->frags[i].size;
+ end = start + skb_frag_size(frag);
if ((copy = end - offset) > 0) {
__wsum csum2;
int err = 0;
u8 *vaddr;
- skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
- struct page *page = frag->page;
+ struct page *page = skb_frag_page(frag);
if (copy > len)
copy = len;
diff --git a/net/core/dev.c b/net/core/dev.c
index 9c58c1ec41a9..6ba50a1e404c 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -133,6 +133,10 @@
#include <linux/pci.h>
#include <linux/inetdevice.h>
#include <linux/cpu_rmap.h>
+#include <linux/if_tunnel.h>
+#include <linux/if_pppox.h>
+#include <linux/ppp_defs.h>
+#include <linux/net_tstamp.h>
#include "net-sysfs.h"
@@ -199,6 +203,11 @@ static struct list_head ptype_all __read_mostly; /* Taps */
DEFINE_RWLOCK(dev_base_lock);
EXPORT_SYMBOL(dev_base_lock);
+static inline void dev_base_seq_inc(struct net *net)
+{
+ while (++net->dev_base_seq == 0);
+}
+
static inline struct hlist_head *dev_name_hash(struct net *net, const char *name)
{
unsigned hash = full_name_hash(name, strnlen(name, IFNAMSIZ));
@@ -237,6 +246,9 @@ static int list_netdevice(struct net_device *dev)
hlist_add_head_rcu(&dev->index_hlist,
dev_index_hash(net, dev->ifindex));
write_unlock_bh(&dev_base_lock);
+
+ dev_base_seq_inc(net);
+
return 0;
}
@@ -253,6 +265,8 @@ static void unlist_netdevice(struct net_device *dev)
hlist_del_rcu(&dev->name_hlist);
hlist_del_rcu(&dev->index_hlist);
write_unlock_bh(&dev_base_lock);
+
+ dev_base_seq_inc(dev_net(dev));
}
/*
@@ -1464,6 +1478,57 @@ static inline void net_timestamp_check(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)
{
@@ -1505,6 +1570,14 @@ static inline bool is_skb_forwardable(struct net_device *dev,
*/
int dev_forward_skb(struct net_device *dev, struct sk_buff *skb)
{
+ if (skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY) {
+ if (skb_copy_ubufs(skb, GFP_ATOMIC)) {
+ atomic_long_inc(&dev->rx_dropped);
+ kfree_skb(skb);
+ return NET_RX_DROP;
+ }
+ }
+
skb_orphan(skb);
nf_reset(skb);
@@ -1937,9 +2010,11 @@ static int illegal_highdma(struct net_device *dev, struct sk_buff *skb)
#ifdef CONFIG_HIGHMEM
int i;
if (!(dev->features & NETIF_F_HIGHDMA)) {
- for (i = 0; i < skb_shinfo(skb)->nr_frags; i++)
- if (PageHighMem(skb_shinfo(skb)->frags[i].page))
+ for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+ skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
+ if (PageHighMem(skb_frag_page(frag)))
return 1;
+ }
}
if (PCI_DMA_BUS_IS_PHYS) {
@@ -1948,7 +2023,8 @@ static int illegal_highdma(struct net_device *dev, struct sk_buff *skb)
if (!pdev)
return 0;
for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
- dma_addr_t addr = page_to_phys(skb_shinfo(skb)->frags[i].page);
+ skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
+ dma_addr_t addr = page_to_phys(skb_frag_page(frag));
if (!pdev->dma_mask || addr + PAGE_SIZE - 1 > *pdev->dma_mask)
return 1;
}
@@ -2509,38 +2585,45 @@ static inline void ____napi_schedule(struct softnet_data *sd,
/*
* __skb_get_rxhash: calculate a flow hash based on src/dst addresses
- * and src/dst port numbers. Returns a non-zero hash number on success
- * and 0 on failure.
+ * 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.
*/
-__u32 __skb_get_rxhash(struct sk_buff *skb)
+void __skb_get_rxhash(struct sk_buff *skb)
{
int nhoff, hash = 0, poff;
const struct ipv6hdr *ip6;
const struct iphdr *ip;
+ const struct vlan_hdr *vlan;
u8 ip_proto;
- u32 addr1, addr2, ihl;
+ u32 addr1, addr2;
+ u16 proto;
union {
u32 v32;
u16 v16[2];
} ports;
nhoff = skb_network_offset(skb);
+ proto = skb->protocol;
- switch (skb->protocol) {
+again:
+ switch (proto) {
case __constant_htons(ETH_P_IP):
+ip:
if (!pskb_may_pull(skb, sizeof(*ip) + nhoff))
goto done;
ip = (const struct iphdr *) (skb->data + nhoff);
- if (ip->frag_off & htons(IP_MF | IP_OFFSET))
+ if (ip_is_fragment(ip))
ip_proto = 0;
else
ip_proto = ip->protocol;
addr1 = (__force u32) ip->saddr;
addr2 = (__force u32) ip->daddr;
- ihl = ip->ihl;
+ nhoff += ip->ihl * 4;
break;
case __constant_htons(ETH_P_IPV6):
+ipv6:
if (!pskb_may_pull(skb, sizeof(*ip6) + nhoff))
goto done;
@@ -2548,20 +2631,71 @@ __u32 __skb_get_rxhash(struct sk_buff *skb)
ip_proto = ip6->nexthdr;
addr1 = (__force u32) ip6->saddr.s6_addr32[3];
addr2 = (__force u32) ip6->daddr.s6_addr32[3];
- ihl = (40 >> 2);
+ nhoff += 40;
break;
+ case __constant_htons(ETH_P_8021Q):
+ if (!pskb_may_pull(skb, sizeof(*vlan) + nhoff))
+ goto done;
+ vlan = (const struct vlan_hdr *) (skb->data + nhoff);
+ proto = vlan->h_vlan_encapsulated_proto;
+ nhoff += sizeof(*vlan);
+ goto again;
+ case __constant_htons(ETH_P_PPP_SES):
+ if (!pskb_may_pull(skb, PPPOE_SES_HLEN + nhoff))
+ goto done;
+ proto = *((__be16 *) (skb->data + nhoff +
+ sizeof(struct pppoe_hdr)));
+ nhoff += PPPOE_SES_HLEN;
+ switch (proto) {
+ case __constant_htons(PPP_IP):
+ goto ip;
+ case __constant_htons(PPP_IPV6):
+ goto ipv6;
+ default:
+ goto done;
+ }
default:
goto done;
}
+ switch (ip_proto) {
+ case IPPROTO_GRE:
+ if (pskb_may_pull(skb, nhoff + 16)) {
+ u8 *h = skb->data + nhoff;
+ __be16 flags = *(__be16 *)h;
+
+ /*
+ * Only look inside GRE if version zero and no
+ * routing
+ */
+ if (!(flags & (GRE_VERSION|GRE_ROUTING))) {
+ proto = *(__be16 *)(h + 2);
+ nhoff += 4;
+ if (flags & GRE_CSUM)
+ nhoff += 4;
+ if (flags & GRE_KEY)
+ nhoff += 4;
+ if (flags & GRE_SEQ)
+ nhoff += 4;
+ goto again;
+ }
+ }
+ break;
+ case IPPROTO_IPIP:
+ goto again;
+ default:
+ break;
+ }
+
ports.v32 = 0;
poff = proto_ports_offset(ip_proto);
if (poff >= 0) {
- nhoff += ihl * 4 + poff;
+ nhoff += poff;
if (pskb_may_pull(skb, nhoff + 4)) {
ports.v32 = * (__force u32 *) (skb->data + nhoff);
if (ports.v16[1] < ports.v16[0])
swap(ports.v16[0], ports.v16[1]);
+ skb->l4_rxhash = 1;
}
}
@@ -2574,7 +2708,7 @@ __u32 __skb_get_rxhash(struct sk_buff *skb)
hash = 1;
done:
- return hash;
+ skb->rxhash = hash;
}
EXPORT_SYMBOL(__skb_get_rxhash);
@@ -2588,10 +2722,7 @@ static struct rps_dev_flow *
set_rps_cpu(struct net_device *dev, struct sk_buff *skb,
struct rps_dev_flow *rflow, u16 next_cpu)
{
- u16 tcpu;
-
- tcpu = rflow->cpu = next_cpu;
- if (tcpu != RPS_NO_CPU) {
+ if (next_cpu != RPS_NO_CPU) {
#ifdef CONFIG_RFS_ACCEL
struct netdev_rx_queue *rxqueue;
struct rps_dev_flow_table *flow_table;
@@ -2619,16 +2750,16 @@ set_rps_cpu(struct net_device *dev, struct sk_buff *skb,
goto out;
old_rflow = rflow;
rflow = &flow_table->flows[flow_id];
- rflow->cpu = next_cpu;
rflow->filter = rc;
if (old_rflow->filter == rflow->filter)
old_rflow->filter = RPS_NO_FILTER;
out:
#endif
rflow->last_qtail =
- per_cpu(softnet_data, tcpu).input_queue_head;
+ per_cpu(softnet_data, next_cpu).input_queue_head;
}
+ rflow->cpu = next_cpu;
return rflow;
}
@@ -2663,13 +2794,13 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb,
map = rcu_dereference(rxqueue->rps_map);
if (map) {
if (map->len == 1 &&
- !rcu_dereference_raw(rxqueue->rps_flow_table)) {
+ !rcu_access_pointer(rxqueue->rps_flow_table)) {
tcpu = map->cpus[0];
if (cpu_online(tcpu))
cpu = tcpu;
goto done;
}
- } else if (!rcu_dereference_raw(rxqueue->rps_flow_table)) {
+ } else if (!rcu_access_pointer(rxqueue->rps_flow_table)) {
goto done;
}
@@ -3084,8 +3215,8 @@ void netdev_rx_handler_unregister(struct net_device *dev)
{
ASSERT_RTNL();
- rcu_assign_pointer(dev->rx_handler, NULL);
- rcu_assign_pointer(dev->rx_handler_data, NULL);
+ RCU_INIT_POINTER(dev->rx_handler, NULL);
+ RCU_INIT_POINTER(dev->rx_handler_data, NULL);
}
EXPORT_SYMBOL_GPL(netdev_rx_handler_unregister);
@@ -3153,6 +3284,17 @@ ncls:
#endif
rx_handler = rcu_dereference(skb->dev->rx_handler);
+ if (vlan_tx_tag_present(skb)) {
+ if (pt_prev) {
+ ret = deliver_skb(skb, pt_prev, orig_dev);
+ pt_prev = NULL;
+ }
+ if (vlan_do_receive(&skb, !rx_handler))
+ goto another_round;
+ else if (unlikely(!skb))
+ goto out;
+ }
+
if (rx_handler) {
if (pt_prev) {
ret = deliver_skb(skb, pt_prev, orig_dev);
@@ -3172,18 +3314,6 @@ ncls:
}
}
- if (vlan_tx_tag_present(skb)) {
- if (pt_prev) {
- ret = deliver_skb(skb, pt_prev, orig_dev);
- pt_prev = NULL;
- }
- if (vlan_do_receive(&skb)) {
- ret = __netif_receive_skb(skb);
- goto out;
- } else if (unlikely(!skb))
- goto out;
- }
-
/* deliver only exact match when indicated */
null_or_dev = deliver_exact ? skb->dev : NULL;
@@ -3411,10 +3541,10 @@ pull:
skb->data_len -= grow;
skb_shinfo(skb)->frags[0].page_offset += grow;
- skb_shinfo(skb)->frags[0].size -= grow;
+ skb_frag_size_sub(&skb_shinfo(skb)->frags[0], grow);
- if (unlikely(!skb_shinfo(skb)->frags[0].size)) {
- put_page(skb_shinfo(skb)->frags[0].page);
+ if (unlikely(!skb_frag_size(&skb_shinfo(skb)->frags[0]))) {
+ skb_frag_unref(skb, 0);
memmove(skb_shinfo(skb)->frags,
skb_shinfo(skb)->frags + 1,
--skb_shinfo(skb)->nr_frags * sizeof(skb_frag_t));
@@ -3478,11 +3608,10 @@ void skb_gro_reset_offset(struct sk_buff *skb)
NAPI_GRO_CB(skb)->frag0_len = 0;
if (skb->mac_header == skb->tail &&
- !PageHighMem(skb_shinfo(skb)->frags[0].page)) {
+ !PageHighMem(skb_frag_page(&skb_shinfo(skb)->frags[0]))) {
NAPI_GRO_CB(skb)->frag0 =
- page_address(skb_shinfo(skb)->frags[0].page) +
- skb_shinfo(skb)->frags[0].page_offset;
- NAPI_GRO_CB(skb)->frag0_len = skb_shinfo(skb)->frags[0].size;
+ skb_frag_address(&skb_shinfo(skb)->frags[0]);
+ NAPI_GRO_CB(skb)->frag0_len = skb_frag_size(&skb_shinfo(skb)->frags[0]);
}
}
EXPORT_SYMBOL(skb_gro_reset_offset);
@@ -3964,6 +4093,60 @@ static int dev_ifconf(struct net *net, char __user *arg)
}
#ifdef CONFIG_PROC_FS
+
+#define BUCKET_SPACE (32 - NETDEV_HASHBITS)
+
+struct dev_iter_state {
+ struct seq_net_private p;
+ unsigned int pos; /* bucket << BUCKET_SPACE + offset */
+};
+
+#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)
+{
+ struct dev_iter_state *state = seq->private;
+ struct net *net = seq_file_net(seq);
+ struct net_device *dev;
+ struct hlist_node *p;
+ struct hlist_head *h;
+ unsigned int count, bucket, offset;
+
+ bucket = get_bucket(state->pos);
+ offset = get_offset(state->pos);
+ h = &net->dev_name_head[bucket];
+ count = 0;
+ hlist_for_each_entry_rcu(dev, p, h, name_hlist) {
+ if (count++ == offset) {
+ state->pos = set_bucket_offset(bucket, count);
+ return dev;
+ }
+ }
+
+ return NULL;
+}
+
+static inline struct net_device *dev_from_new_bucket(struct seq_file *seq)
+{
+ struct dev_iter_state *state = seq->private;
+ struct net_device *dev;
+ unsigned int bucket;
+
+ bucket = get_bucket(state->pos);
+ do {
+ dev = dev_from_same_bucket(seq);
+ if (dev)
+ return dev;
+
+ bucket++;
+ state->pos = set_bucket_offset(bucket, 0);
+ } while (bucket < NETDEV_HASHENTRIES);
+
+ return NULL;
+}
+
/*
* This is invoked by the /proc filesystem handler to display a device
* in detail.
@@ -3971,33 +4154,33 @@ static int dev_ifconf(struct net *net, char __user *arg)
void *dev_seq_start(struct seq_file *seq, loff_t *pos)
__acquires(RCU)
{
- struct net *net = seq_file_net(seq);
- loff_t off;
- struct net_device *dev;
+ struct dev_iter_state *state = seq->private;
rcu_read_lock();
if (!*pos)
return SEQ_START_TOKEN;
- off = 1;
- for_each_netdev_rcu(net, dev)
- if (off++ == *pos)
- return dev;
+ /* check for end of the hash */
+ if (state->pos == 0 && *pos > 1)
+ return NULL;
- return NULL;
+ return dev_from_new_bucket(seq);
}
void *dev_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
- struct net_device *dev = v;
+ struct net_device *dev;
+
+ ++*pos;
if (v == SEQ_START_TOKEN)
- dev = first_net_device_rcu(seq_file_net(seq));
- else
- dev = next_net_device_rcu(dev);
+ return dev_from_new_bucket(seq);
- ++*pos;
- return dev;
+ dev = dev_from_same_bucket(seq);
+ if (dev)
+ return dev;
+
+ return dev_from_new_bucket(seq);
}
void dev_seq_stop(struct seq_file *seq, void *v)
@@ -4096,7 +4279,7 @@ static const struct seq_operations dev_seq_ops = {
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));
+ sizeof(struct dev_iter_state));
}
static const struct file_operations dev_seq_fops = {
@@ -4479,23 +4662,21 @@ void __dev_set_rx_mode(struct net_device *dev)
if (!netif_device_present(dev))
return;
- if (ops->ndo_set_rx_mode)
- ops->ndo_set_rx_mode(dev);
- else {
+ if (!(dev->priv_flags & IFF_UNICAST_FLT)) {
/* Unicast addresses changes may only happen under the rtnl,
* therefore calling __dev_set_promiscuity here is safe.
*/
if (!netdev_uc_empty(dev) && !dev->uc_promisc) {
__dev_set_promiscuity(dev, 1);
- dev->uc_promisc = 1;
+ dev->uc_promisc = true;
} else if (netdev_uc_empty(dev) && dev->uc_promisc) {
__dev_set_promiscuity(dev, -1);
- dev->uc_promisc = 0;
+ dev->uc_promisc = false;
}
-
- if (ops->ndo_set_multicast_list)
- ops->ndo_set_multicast_list(dev);
}
+
+ if (ops->ndo_set_rx_mode)
+ ops->ndo_set_rx_mode(dev);
}
void dev_set_rx_mode(struct net_device *dev)
@@ -4506,30 +4687,6 @@ void dev_set_rx_mode(struct net_device *dev)
}
/**
- * dev_ethtool_get_settings - call device's ethtool_ops::get_settings()
- * @dev: device
- * @cmd: memory area for ethtool_ops::get_settings() result
- *
- * The cmd arg is initialized properly (cleared and
- * ethtool_cmd::cmd field set to ETHTOOL_GSET).
- *
- * Return device's ethtool_ops::get_settings() result value or
- * -EOPNOTSUPP when device doesn't expose
- * ethtool_ops::get_settings() operation.
- */
-int dev_ethtool_get_settings(struct net_device *dev,
- struct ethtool_cmd *cmd)
-{
- if (!dev->ethtool_ops || !dev->ethtool_ops->get_settings)
- return -EOPNOTSUPP;
-
- memset(cmd, 0, sizeof(struct ethtool_cmd));
- cmd->cmd = ETHTOOL_GSET;
- return dev->ethtool_ops->get_settings(dev, cmd);
-}
-EXPORT_SYMBOL(dev_ethtool_get_settings);
-
-/**
* dev_get_flags - get flags reported to userspace
* @dev: device
*
@@ -4845,7 +5002,7 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, unsigned int cmd)
return -EOPNOTSUPP;
case SIOCADDMULTI:
- if ((!ops->ndo_set_multicast_list && !ops->ndo_set_rx_mode) ||
+ if (!ops->ndo_set_rx_mode ||
ifr->ifr_hwaddr.sa_family != AF_UNSPEC)
return -EINVAL;
if (!netif_device_present(dev))
@@ -4853,7 +5010,7 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, unsigned int cmd)
return dev_mc_add_global(dev, ifr->ifr_hwaddr.sa_data);
case SIOCDELMULTI:
- if ((!ops->ndo_set_multicast_list && !ops->ndo_set_rx_mode) ||
+ if (!ops->ndo_set_rx_mode ||
ifr->ifr_hwaddr.sa_family != AF_UNSPEC)
return -EINVAL;
if (!netif_device_present(dev))
@@ -4870,6 +5027,12 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, unsigned int cmd)
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
*/
@@ -5184,7 +5347,7 @@ static void rollback_registered_many(struct list_head *head)
dev = list_first_entry(head, struct net_device, unreg_list);
call_netdevice_notifiers(NETDEV_UNREGISTER_BATCH, dev);
- rcu_barrier();
+ synchronize_net();
list_for_each_entry(dev, head, unreg_list)
dev_put(dev);
@@ -5199,7 +5362,7 @@ static void rollback_registered(struct net_device *dev)
list_del(&single);
}
-u32 netdev_fix_features(struct net_device *dev, u32 features)
+static u32 netdev_fix_features(struct net_device *dev, u32 features)
{
/* Fix illegal checksum combinations */
if ((features & NETIF_F_HW_CSUM) &&
@@ -5258,7 +5421,6 @@ u32 netdev_fix_features(struct net_device *dev, u32 features)
return features;
}
-EXPORT_SYMBOL(netdev_fix_features);
int __netdev_update_features(struct net_device *dev)
{
@@ -5478,11 +5640,9 @@ int register_netdevice(struct net_device *dev)
dev->features |= NETIF_F_NOCACHE_COPY;
}
- /* Enable GRO and NETIF_F_HIGHDMA for vlans by default,
- * vlan_dev_init() will do the dev->features check, so these features
- * are enabled only if supported by underlying device.
+ /* Make NETIF_F_HIGHDMA inheritable to VLAN devices.
*/
- dev->vlan_features |= (NETIF_F_GRO | NETIF_F_HIGHDMA);
+ dev->vlan_features |= NETIF_F_HIGHDMA;
ret = call_netdevice_notifiers(NETDEV_POST_INIT, dev);
ret = notifier_to_errno(ret);
@@ -5700,6 +5860,12 @@ void netdev_run_todo(void)
__rtnl_unlock();
+ /* Wait for rcu callbacks to finish before attempting to drain
+ * the device list. This usually avoids a 250ms wait.
+ */
+ if (!list_empty(&list))
+ rcu_barrier();
+
while (!list_empty(&list)) {
struct net_device *dev
= list_first_entry(&list, struct net_device, todo_list);
@@ -5720,8 +5886,8 @@ void netdev_run_todo(void)
/* paranoia */
BUG_ON(netdev_refcnt_read(dev));
- WARN_ON(rcu_dereference_raw(dev->ip_ptr));
- WARN_ON(rcu_dereference_raw(dev->ip6_ptr));
+ WARN_ON(rcu_access_pointer(dev->ip_ptr));
+ WARN_ON(rcu_access_pointer(dev->ip6_ptr));
WARN_ON(dev->dn_ptr);
if (dev->destructor)
@@ -5867,8 +6033,6 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
dev->gso_max_size = GSO_MAX_SIZE;
- INIT_LIST_HEAD(&dev->ethtool_ntuple_list.list);
- dev->ethtool_ntuple_list.count = 0;
INIT_LIST_HEAD(&dev->napi_list);
INIT_LIST_HEAD(&dev->unreg_list);
INIT_LIST_HEAD(&dev->link_watch_list);
@@ -5927,14 +6091,11 @@ void free_netdev(struct net_device *dev)
kfree(dev->_rx);
#endif
- kfree(rcu_dereference_raw(dev->ingress_queue));
+ kfree(rcu_dereference_protected(dev->ingress_queue, 1));
/* Flush device addresses */
dev_addr_flush(dev);
- /* Clear ethtool n-tuple list */
- ethtool_ntuple_flush(dev);
-
list_for_each_entry_safe(p, n, &dev->napi_list, dev_list)
netif_napi_del(p);
@@ -6105,6 +6266,7 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char
*/
call_netdevice_notifiers(NETDEV_UNREGISTER, dev);
call_netdevice_notifiers(NETDEV_UNREGISTER_BATCH, dev);
+ rtmsg_ifinfo(RTM_DELLINK, dev, ~0U);
/*
* Flush the unicast and multicast chains
@@ -6288,7 +6450,7 @@ const char *netdev_drivername(const struct net_device *dev)
return empty;
}
-static int __netdev_printk(const char *level, const struct net_device *dev,
+int __netdev_printk(const char *level, const struct net_device *dev,
struct va_format *vaf)
{
int r;
@@ -6303,6 +6465,7 @@ static int __netdev_printk(const char *level, const struct net_device *dev,
return r;
}
+EXPORT_SYMBOL(__netdev_printk);
int netdev_printk(const char *level, const struct net_device *dev,
const char *format, ...)
diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c
index e2e66939ed00..277faef9148d 100644
--- a/net/core/dev_addr_lists.c
+++ b/net/core/dev_addr_lists.c
@@ -13,6 +13,7 @@
#include <linux/netdevice.h>
#include <linux/rtnetlink.h>
+#include <linux/export.h>
#include <linux/list.h>
#include <linux/proc_fs.h>
@@ -591,8 +592,8 @@ EXPORT_SYMBOL(dev_mc_del_global);
* addresses that have no users left. The source device must be
* locked by netif_tx_lock_bh.
*
- * This function is intended to be called from the dev->set_multicast_list
- * or dev->set_rx_mode function of layered software devices.
+ * This function is intended to be called from the ndo_set_rx_mode
+ * function of layered software devices.
*/
int dev_mc_sync(struct net_device *to, struct net_device *from)
{
diff --git a/net/core/dst.c b/net/core/dst.c
index 6135f3671692..d5e2c4c09107 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -171,8 +171,7 @@ 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->neighbour = NULL;
- dst->hh = NULL;
+ RCU_INIT_POINTER(dst->_neighbour, NULL);
#ifdef CONFIG_XFRM
dst->xfrm = NULL;
#endif
@@ -226,21 +225,15 @@ struct dst_entry *dst_destroy(struct dst_entry * dst)
{
struct dst_entry *child;
struct neighbour *neigh;
- struct hh_cache *hh;
smp_rmb();
again:
- neigh = dst->neighbour;
- hh = dst->hh;
+ neigh = rcu_dereference_protected(dst->_neighbour, 1);
child = dst->child;
- dst->hh = NULL;
- if (hh)
- hh_cache_put(hh);
-
if (neigh) {
- dst->neighbour = NULL;
+ RCU_INIT_POINTER(dst->_neighbour, NULL);
neigh_release(neigh);
}
@@ -367,14 +360,19 @@ static void dst_ifdown(struct dst_entry *dst, struct net_device *dev,
if (!unregister) {
dst->input = dst->output = dst_discard;
} else {
+ struct neighbour *neigh;
+
dst->dev = dev_net(dst->dev)->loopback_dev;
dev_hold(dst->dev);
dev_put(dev);
- if (dst->neighbour && dst->neighbour->dev == dev) {
- dst->neighbour->dev = dst->dev;
+ rcu_read_lock();
+ neigh = dst_get_neighbour(dst);
+ if (neigh && neigh->dev == dev) {
+ neigh->dev = dst->dev;
dev_hold(dst->dev);
dev_put(dev);
}
+ rcu_read_unlock();
}
}
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index fd14116ad7f0..f44481707124 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -169,18 +169,6 @@ int ethtool_op_set_flags(struct net_device *dev, u32 data, u32 supported)
}
EXPORT_SYMBOL(ethtool_op_set_flags);
-void ethtool_ntuple_flush(struct net_device *dev)
-{
- struct ethtool_rx_ntuple_flow_spec_container *fsc, *f;
-
- list_for_each_entry_safe(fsc, f, &dev->ethtool_ntuple_list.list, list) {
- list_del(&fsc->list);
- kfree(fsc);
- }
- dev->ethtool_ntuple_list.count = 0;
-}
-EXPORT_SYMBOL(ethtool_ntuple_flush);
-
/* Handlers for each ethtool command */
#define ETHTOOL_DEV_FEATURE_WORDS 1
@@ -581,15 +569,25 @@ int __ethtool_set_flags(struct net_device *dev, u32 data)
return 0;
}
-static int ethtool_get_settings(struct net_device *dev, void __user *useraddr)
+int __ethtool_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
{
- struct ethtool_cmd cmd = { .cmd = ETHTOOL_GSET };
- int err;
+ ASSERT_RTNL();
- if (!dev->ethtool_ops->get_settings)
+ if (!dev->ethtool_ops || !dev->ethtool_ops->get_settings)
return -EOPNOTSUPP;
- err = dev->ethtool_ops->get_settings(dev, &cmd);
+ memset(cmd, 0, sizeof(struct ethtool_cmd));
+ cmd->cmd = ETHTOOL_GSET;
+ return dev->ethtool_ops->get_settings(dev, cmd);
+}
+EXPORT_SYMBOL(__ethtool_get_settings);
+
+static int ethtool_get_settings(struct net_device *dev, void __user *useraddr)
+{
+ int err;
+ struct ethtool_cmd cmd;
+
+ err = __ethtool_get_settings(dev, &cmd);
if (err < 0)
return err;
@@ -865,34 +863,6 @@ out:
return ret;
}
-static void __rx_ntuple_filter_add(struct ethtool_rx_ntuple_list *list,
- struct ethtool_rx_ntuple_flow_spec *spec,
- struct ethtool_rx_ntuple_flow_spec_container *fsc)
-{
-
- /* don't add filters forever */
- if (list->count >= ETHTOOL_MAX_NTUPLE_LIST_ENTRY) {
- /* free the container */
- kfree(fsc);
- return;
- }
-
- /* Copy the whole filter over */
- fsc->fs.flow_type = spec->flow_type;
- memcpy(&fsc->fs.h_u, &spec->h_u, sizeof(spec->h_u));
- memcpy(&fsc->fs.m_u, &spec->m_u, sizeof(spec->m_u));
-
- fsc->fs.vlan_tag = spec->vlan_tag;
- fsc->fs.vlan_tag_mask = spec->vlan_tag_mask;
- fsc->fs.data = spec->data;
- fsc->fs.data_mask = spec->data_mask;
- fsc->fs.action = spec->action;
-
- /* add to the list */
- list_add_tail_rcu(&fsc->list, &list->list);
- list->count++;
-}
-
/*
* ethtool does not (or did not) set masks for flow parameters that are
* not specified, so if both value and mask are 0 then this must be
@@ -930,8 +900,6 @@ static noinline_for_stack int ethtool_set_rx_ntuple(struct net_device *dev,
{
struct ethtool_rx_ntuple cmd;
const struct ethtool_ops *ops = dev->ethtool_ops;
- struct ethtool_rx_ntuple_flow_spec_container *fsc = NULL;
- int ret;
if (!ops->set_rx_ntuple)
return -EOPNOTSUPP;
@@ -944,269 +912,7 @@ static noinline_for_stack int ethtool_set_rx_ntuple(struct net_device *dev,
rx_ntuple_fix_masks(&cmd.fs);
- /*
- * Cache filter in dev struct for GET operation only if
- * the underlying driver doesn't have its own GET operation, and
- * only if the filter was added successfully. First make sure we
- * can allocate the filter, then continue if successful.
- */
- if (!ops->get_rx_ntuple) {
- fsc = kmalloc(sizeof(*fsc), GFP_ATOMIC);
- if (!fsc)
- return -ENOMEM;
- }
-
- ret = ops->set_rx_ntuple(dev, &cmd);
- if (ret) {
- kfree(fsc);
- return ret;
- }
-
- if (!ops->get_rx_ntuple)
- __rx_ntuple_filter_add(&dev->ethtool_ntuple_list, &cmd.fs, fsc);
-
- return ret;
-}
-
-static int ethtool_get_rx_ntuple(struct net_device *dev, void __user *useraddr)
-{
- struct ethtool_gstrings gstrings;
- const struct ethtool_ops *ops = dev->ethtool_ops;
- struct ethtool_rx_ntuple_flow_spec_container *fsc;
- u8 *data;
- char *p;
- int ret, i, num_strings = 0;
-
- if (!ops->get_sset_count)
- return -EOPNOTSUPP;
-
- if (copy_from_user(&gstrings, useraddr, sizeof(gstrings)))
- return -EFAULT;
-
- ret = ops->get_sset_count(dev, gstrings.string_set);
- if (ret < 0)
- return ret;
-
- gstrings.len = ret;
-
- data = kzalloc(gstrings.len * ETH_GSTRING_LEN, GFP_USER);
- if (!data)
- return -ENOMEM;
-
- if (ops->get_rx_ntuple) {
- /* driver-specific filter grab */
- ret = ops->get_rx_ntuple(dev, gstrings.string_set, data);
- goto copy;
- }
-
- /* default ethtool filter grab */
- i = 0;
- p = (char *)data;
- list_for_each_entry(fsc, &dev->ethtool_ntuple_list.list, list) {
- sprintf(p, "Filter %d:\n", i);
- p += ETH_GSTRING_LEN;
- num_strings++;
-
- switch (fsc->fs.flow_type) {
- case TCP_V4_FLOW:
- sprintf(p, "\tFlow Type: TCP\n");
- p += ETH_GSTRING_LEN;
- num_strings++;
- break;
- case UDP_V4_FLOW:
- sprintf(p, "\tFlow Type: UDP\n");
- p += ETH_GSTRING_LEN;
- num_strings++;
- break;
- case SCTP_V4_FLOW:
- sprintf(p, "\tFlow Type: SCTP\n");
- p += ETH_GSTRING_LEN;
- num_strings++;
- break;
- case AH_ESP_V4_FLOW:
- sprintf(p, "\tFlow Type: AH ESP\n");
- p += ETH_GSTRING_LEN;
- num_strings++;
- break;
- case ESP_V4_FLOW:
- sprintf(p, "\tFlow Type: ESP\n");
- p += ETH_GSTRING_LEN;
- num_strings++;
- break;
- case IP_USER_FLOW:
- sprintf(p, "\tFlow Type: Raw IP\n");
- p += ETH_GSTRING_LEN;
- num_strings++;
- break;
- case IPV4_FLOW:
- sprintf(p, "\tFlow Type: IPv4\n");
- p += ETH_GSTRING_LEN;
- num_strings++;
- break;
- default:
- sprintf(p, "\tFlow Type: Unknown\n");
- p += ETH_GSTRING_LEN;
- num_strings++;
- goto unknown_filter;
- }
-
- /* now the rest of the filters */
- switch (fsc->fs.flow_type) {
- case TCP_V4_FLOW:
- case UDP_V4_FLOW:
- case SCTP_V4_FLOW:
- sprintf(p, "\tSrc IP addr: 0x%x\n",
- fsc->fs.h_u.tcp_ip4_spec.ip4src);
- p += ETH_GSTRING_LEN;
- num_strings++;
- sprintf(p, "\tSrc IP mask: 0x%x\n",
- fsc->fs.m_u.tcp_ip4_spec.ip4src);
- p += ETH_GSTRING_LEN;
- num_strings++;
- sprintf(p, "\tDest IP addr: 0x%x\n",
- fsc->fs.h_u.tcp_ip4_spec.ip4dst);
- p += ETH_GSTRING_LEN;
- num_strings++;
- sprintf(p, "\tDest IP mask: 0x%x\n",
- fsc->fs.m_u.tcp_ip4_spec.ip4dst);
- p += ETH_GSTRING_LEN;
- num_strings++;
- sprintf(p, "\tSrc Port: %d, mask: 0x%x\n",
- fsc->fs.h_u.tcp_ip4_spec.psrc,
- fsc->fs.m_u.tcp_ip4_spec.psrc);
- p += ETH_GSTRING_LEN;
- num_strings++;
- sprintf(p, "\tDest Port: %d, mask: 0x%x\n",
- fsc->fs.h_u.tcp_ip4_spec.pdst,
- fsc->fs.m_u.tcp_ip4_spec.pdst);
- p += ETH_GSTRING_LEN;
- num_strings++;
- sprintf(p, "\tTOS: %d, mask: 0x%x\n",
- fsc->fs.h_u.tcp_ip4_spec.tos,
- fsc->fs.m_u.tcp_ip4_spec.tos);
- p += ETH_GSTRING_LEN;
- num_strings++;
- break;
- case AH_ESP_V4_FLOW:
- case ESP_V4_FLOW:
- sprintf(p, "\tSrc IP addr: 0x%x\n",
- fsc->fs.h_u.ah_ip4_spec.ip4src);
- p += ETH_GSTRING_LEN;
- num_strings++;
- sprintf(p, "\tSrc IP mask: 0x%x\n",
- fsc->fs.m_u.ah_ip4_spec.ip4src);
- p += ETH_GSTRING_LEN;
- num_strings++;
- sprintf(p, "\tDest IP addr: 0x%x\n",
- fsc->fs.h_u.ah_ip4_spec.ip4dst);
- p += ETH_GSTRING_LEN;
- num_strings++;
- sprintf(p, "\tDest IP mask: 0x%x\n",
- fsc->fs.m_u.ah_ip4_spec.ip4dst);
- p += ETH_GSTRING_LEN;
- num_strings++;
- sprintf(p, "\tSPI: %d, mask: 0x%x\n",
- fsc->fs.h_u.ah_ip4_spec.spi,
- fsc->fs.m_u.ah_ip4_spec.spi);
- p += ETH_GSTRING_LEN;
- num_strings++;
- sprintf(p, "\tTOS: %d, mask: 0x%x\n",
- fsc->fs.h_u.ah_ip4_spec.tos,
- fsc->fs.m_u.ah_ip4_spec.tos);
- p += ETH_GSTRING_LEN;
- num_strings++;
- break;
- case IP_USER_FLOW:
- sprintf(p, "\tSrc IP addr: 0x%x\n",
- fsc->fs.h_u.usr_ip4_spec.ip4src);
- p += ETH_GSTRING_LEN;
- num_strings++;
- sprintf(p, "\tSrc IP mask: 0x%x\n",
- fsc->fs.m_u.usr_ip4_spec.ip4src);
- p += ETH_GSTRING_LEN;
- num_strings++;
- sprintf(p, "\tDest IP addr: 0x%x\n",
- fsc->fs.h_u.usr_ip4_spec.ip4dst);
- p += ETH_GSTRING_LEN;
- num_strings++;
- sprintf(p, "\tDest IP mask: 0x%x\n",
- fsc->fs.m_u.usr_ip4_spec.ip4dst);
- p += ETH_GSTRING_LEN;
- num_strings++;
- break;
- case IPV4_FLOW:
- sprintf(p, "\tSrc IP addr: 0x%x\n",
- fsc->fs.h_u.usr_ip4_spec.ip4src);
- p += ETH_GSTRING_LEN;
- num_strings++;
- sprintf(p, "\tSrc IP mask: 0x%x\n",
- fsc->fs.m_u.usr_ip4_spec.ip4src);
- p += ETH_GSTRING_LEN;
- num_strings++;
- sprintf(p, "\tDest IP addr: 0x%x\n",
- fsc->fs.h_u.usr_ip4_spec.ip4dst);
- p += ETH_GSTRING_LEN;
- num_strings++;
- sprintf(p, "\tDest IP mask: 0x%x\n",
- fsc->fs.m_u.usr_ip4_spec.ip4dst);
- p += ETH_GSTRING_LEN;
- num_strings++;
- sprintf(p, "\tL4 bytes: 0x%x, mask: 0x%x\n",
- fsc->fs.h_u.usr_ip4_spec.l4_4_bytes,
- fsc->fs.m_u.usr_ip4_spec.l4_4_bytes);
- p += ETH_GSTRING_LEN;
- num_strings++;
- sprintf(p, "\tTOS: %d, mask: 0x%x\n",
- fsc->fs.h_u.usr_ip4_spec.tos,
- fsc->fs.m_u.usr_ip4_spec.tos);
- p += ETH_GSTRING_LEN;
- num_strings++;
- sprintf(p, "\tIP Version: %d, mask: 0x%x\n",
- fsc->fs.h_u.usr_ip4_spec.ip_ver,
- fsc->fs.m_u.usr_ip4_spec.ip_ver);
- p += ETH_GSTRING_LEN;
- num_strings++;
- sprintf(p, "\tProtocol: %d, mask: 0x%x\n",
- fsc->fs.h_u.usr_ip4_spec.proto,
- fsc->fs.m_u.usr_ip4_spec.proto);
- p += ETH_GSTRING_LEN;
- num_strings++;
- break;
- }
- sprintf(p, "\tVLAN: %d, mask: 0x%x\n",
- fsc->fs.vlan_tag, fsc->fs.vlan_tag_mask);
- p += ETH_GSTRING_LEN;
- num_strings++;
- sprintf(p, "\tUser-defined: 0x%Lx\n", fsc->fs.data);
- p += ETH_GSTRING_LEN;
- num_strings++;
- sprintf(p, "\tUser-defined mask: 0x%Lx\n", fsc->fs.data_mask);
- p += ETH_GSTRING_LEN;
- num_strings++;
- if (fsc->fs.action == ETHTOOL_RXNTUPLE_ACTION_DROP)
- sprintf(p, "\tAction: Drop\n");
- else
- sprintf(p, "\tAction: Direct to queue %d\n",
- fsc->fs.action);
- p += ETH_GSTRING_LEN;
- num_strings++;
-unknown_filter:
- i++;
- }
-copy:
- /* indicate to userspace how many strings we actually have */
- gstrings.len = num_strings;
- ret = -EFAULT;
- if (copy_to_user(useraddr, &gstrings, sizeof(gstrings)))
- goto out;
- useraddr += sizeof(gstrings);
- if (copy_to_user(useraddr, data, gstrings.len * ETH_GSTRING_LEN))
- goto out;
- ret = 0;
-
-out:
- kfree(data);
- return ret;
+ return ops->set_rx_ntuple(dev, &cmd);
}
static int ethtool_get_regs(struct net_device *dev, char __user *useraddr)
@@ -1227,7 +933,7 @@ static int ethtool_get_regs(struct net_device *dev, char __user *useraddr)
regs.len = reglen;
regbuf = vzalloc(reglen);
- if (!regbuf)
+ if (reglen && !regbuf)
return -ENOMEM;
ops->get_regs(dev, &regs, regbuf);
@@ -1236,7 +942,7 @@ static int ethtool_get_regs(struct net_device *dev, char __user *useraddr)
if (copy_to_user(useraddr, &regs, sizeof(regs)))
goto out;
useraddr += offsetof(struct ethtool_regs, data);
- if (copy_to_user(useraddr, regbuf, regs.len))
+ if (regbuf && copy_to_user(useraddr, regbuf, regs.len))
goto out;
ret = 0;
@@ -2101,9 +1807,6 @@ int dev_ethtool(struct net *net, struct ifreq *ifr)
case ETHTOOL_SRXNTUPLE:
rc = ethtool_set_rx_ntuple(dev, useraddr);
break;
- case ETHTOOL_GRXNTUPLE:
- rc = ethtool_get_rx_ntuple(dev, useraddr);
- break;
case ETHTOOL_GSSET_INFO:
rc = ethtool_get_sset_info(dev, useraddr);
break;
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index 008dc70b064b..c02e63c908da 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -12,6 +12,7 @@
#include <linux/kernel.h>
#include <linux/slab.h>
#include <linux/list.h>
+#include <linux/module.h>
#include <net/net_namespace.h>
#include <net/sock.h>
#include <net/fib_rules.h>
@@ -384,8 +385,8 @@ static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
*/
list_for_each_entry(r, &ops->rules_list, list) {
if (r->action == FR_ACT_GOTO &&
- r->target == rule->pref) {
- BUG_ON(rtnl_dereference(r->ctarget) != NULL);
+ r->target == rule->pref &&
+ rtnl_dereference(r->ctarget) == NULL) {
rcu_assign_pointer(r->ctarget, rule);
if (--ops->unresolved_rules == 0)
break;
@@ -475,8 +476,11 @@ static int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
list_del_rcu(&rule->list);
- if (rule->action == FR_ACT_GOTO)
+ if (rule->action == FR_ACT_GOTO) {
ops->nr_goto_rules--;
+ if (rtnl_dereference(rule->ctarget) == NULL)
+ ops->unresolved_rules--;
+ }
/*
* Check if this rule is a target to any of them. If so,
@@ -487,7 +491,7 @@ static int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
if (ops->nr_goto_rules > 0) {
list_for_each_entry(tmp, &ops->rules_list, list) {
if (rtnl_dereference(tmp->ctarget) == rule) {
- rcu_assign_pointer(tmp->ctarget, NULL);
+ RCU_INIT_POINTER(tmp->ctarget, NULL);
ops->unresolved_rules++;
}
}
@@ -545,7 +549,7 @@ static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule,
frh->flags = rule->flags;
if (rule->action == FR_ACT_GOTO &&
- rcu_dereference_raw(rule->ctarget) == NULL)
+ rcu_access_pointer(rule->ctarget) == NULL)
frh->flags |= FIB_RULE_UNRESOLVED;
if (rule->iifname[0]) {
@@ -740,9 +744,9 @@ static struct pernet_operations fib_rules_net_ops = {
static int __init fib_rules_init(void)
{
int err;
- rtnl_register(PF_UNSPEC, RTM_NEWRULE, fib_nl_newrule, NULL);
- rtnl_register(PF_UNSPEC, RTM_DELRULE, fib_nl_delrule, NULL);
- rtnl_register(PF_UNSPEC, RTM_GETRULE, NULL, fib_nl_dumprule);
+ rtnl_register(PF_UNSPEC, RTM_NEWRULE, fib_nl_newrule, NULL, NULL);
+ rtnl_register(PF_UNSPEC, RTM_DELRULE, fib_nl_delrule, NULL, NULL);
+ rtnl_register(PF_UNSPEC, RTM_GETRULE, NULL, fib_nl_dumprule, NULL);
err = register_pernet_subsys(&fib_rules_net_ops);
if (err < 0)
diff --git a/net/core/filter.c b/net/core/filter.c
index 36f975fa87cb..5dea45279215 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -436,7 +436,7 @@ error:
*
* Returns 0 if the rule set is legal or -EINVAL if not.
*/
-int sk_chk_filter(struct sock_filter *filter, int flen)
+int sk_chk_filter(struct sock_filter *filter, unsigned int flen)
{
/*
* Valid instructions are initialized to non-0.
@@ -645,7 +645,7 @@ int sk_detach_filter(struct sock *sk)
filter = rcu_dereference_protected(sk->sk_filter,
sock_owned_by_user(sk));
if (filter) {
- rcu_assign_pointer(sk->sk_filter, NULL);
+ RCU_INIT_POINTER(sk->sk_filter, NULL);
sk_filter_uncharge(sk, filter);
ret = 0;
}
diff --git a/net/core/flow.c b/net/core/flow.c
index 990703b8863b..8ae42de9c79e 100644
--- a/net/core/flow.c
+++ b/net/core/flow.c
@@ -22,7 +22,7 @@
#include <linux/cpumask.h>
#include <linux/mutex.h>
#include <net/flow.h>
-#include <asm/atomic.h>
+#include <linux/atomic.h>
#include <linux/security.h>
struct flow_cache_entry {
@@ -30,6 +30,7 @@ struct flow_cache_entry {
struct hlist_node hlist;
struct list_head gc_list;
} u;
+ struct net *net;
u16 family;
u8 dir;
u32 genid;
@@ -172,29 +173,26 @@ static void flow_new_hash_rnd(struct flow_cache *fc,
static u32 flow_hash_code(struct flow_cache *fc,
struct flow_cache_percpu *fcp,
- const struct flowi *key)
+ const struct flowi *key,
+ size_t keysize)
{
const u32 *k = (const u32 *) key;
+ const u32 length = keysize * sizeof(flow_compare_t) / sizeof(u32);
- return jhash2(k, (sizeof(*key) / sizeof(u32)), fcp->hash_rnd)
+ return jhash2(k, length, fcp->hash_rnd)
& (flow_cache_hash_size(fc) - 1);
}
-typedef unsigned long flow_compare_t;
-
/* I hear what you're saying, use memcmp. But memcmp cannot make
- * important assumptions that we can here, such as alignment and
- * constant size.
+ * important assumptions that we can here, such as alignment.
*/
-static int flow_key_compare(const struct flowi *key1, const struct flowi *key2)
+static int flow_key_compare(const struct flowi *key1, const struct flowi *key2,
+ size_t keysize)
{
const flow_compare_t *k1, *k1_lim, *k2;
- const int n_elem = sizeof(struct flowi) / sizeof(flow_compare_t);
-
- BUILD_BUG_ON(sizeof(struct flowi) % sizeof(flow_compare_t));
k1 = (const flow_compare_t *) key1;
- k1_lim = k1 + n_elem;
+ k1_lim = k1 + keysize;
k2 = (const flow_compare_t *) key2;
@@ -215,6 +213,7 @@ flow_cache_lookup(struct net *net, const struct flowi *key, u16 family, u8 dir,
struct flow_cache_entry *fle, *tfle;
struct hlist_node *entry;
struct flow_cache_object *flo;
+ size_t keysize;
unsigned int hash;
local_bh_disable();
@@ -222,6 +221,11 @@ flow_cache_lookup(struct net *net, const struct flowi *key, u16 family, u8 dir,
fle = NULL;
flo = NULL;
+
+ keysize = flow_key_size(family);
+ if (!keysize)
+ goto nocache;
+
/* Packet really early in init? Making flow_cache_init a
* pre-smp initcall would solve this. --RR */
if (!fcp->hash_table)
@@ -230,11 +234,12 @@ flow_cache_lookup(struct net *net, const struct flowi *key, u16 family, u8 dir,
if (fcp->hash_rnd_recalc)
flow_new_hash_rnd(fc, fcp);
- hash = flow_hash_code(fc, fcp, key);
+ hash = flow_hash_code(fc, fcp, key, keysize);
hlist_for_each_entry(tfle, entry, &fcp->hash_table[hash], u.hlist) {
- if (tfle->family == family &&
+ if (tfle->net == net &&
+ tfle->family == family &&
tfle->dir == dir &&
- flow_key_compare(key, &tfle->key) == 0) {
+ flow_key_compare(key, &tfle->key, keysize) == 0) {
fle = tfle;
break;
}
@@ -246,9 +251,10 @@ flow_cache_lookup(struct net *net, const struct flowi *key, u16 family, u8 dir,
fle = kmem_cache_alloc(flow_cachep, GFP_ATOMIC);
if (fle) {
+ fle->net = net;
fle->family = family;
fle->dir = dir;
- memcpy(&fle->key, key, sizeof(*key));
+ memcpy(&fle->key, key, keysize * sizeof(flow_compare_t));
fle->object = NULL;
hlist_add_head(&fle->u.hlist, &fcp->hash_table[hash]);
fcp->hash_count++;
@@ -407,7 +413,7 @@ static int __init flow_cache_init(struct flow_cache *fc)
for_each_online_cpu(i) {
if (flow_cache_cpu_prepare(fc, i))
- return -ENOMEM;
+ goto err;
}
fc->hotcpu_notifier = (struct notifier_block){
.notifier_call = flow_cache_cpu,
@@ -420,6 +426,18 @@ static int __init flow_cache_init(struct flow_cache *fc)
add_timer(&fc->rnd_timer);
return 0;
+
+err:
+ for_each_possible_cpu(i) {
+ struct flow_cache_percpu *fcp = per_cpu_ptr(fc->percpu, i);
+ kfree(fcp->hash_table);
+ fcp->hash_table = NULL;
+ }
+
+ free_percpu(fc->percpu);
+ fc->percpu = NULL;
+
+ return -ENOMEM;
}
static int __init flow_cache_init_global(void)
diff --git a/net/core/kmap_skb.h b/net/core/kmap_skb.h
index 283c2b993fb8..81e1ed7c8383 100644
--- a/net/core/kmap_skb.h
+++ b/net/core/kmap_skb.h
@@ -7,7 +7,7 @@ static inline void *kmap_skb_frag(const skb_frag_t *frag)
local_bh_disable();
#endif
- return kmap_atomic(frag->page, KM_SKB_DATA_SOFTIRQ);
+ return kmap_atomic(skb_frag_page(frag), KM_SKB_DATA_SOFTIRQ);
}
static inline void kunmap_skb_frag(void *vaddr)
diff --git a/net/core/link_watch.c b/net/core/link_watch.c
index a7b342131869..c3519c6d1b16 100644
--- a/net/core/link_watch.c
+++ b/net/core/link_watch.c
@@ -78,8 +78,13 @@ static void rfc2863_policy(struct net_device *dev)
static bool linkwatch_urgent_event(struct net_device *dev)
{
- return netif_running(dev) && netif_carrier_ok(dev) &&
- qdisc_tx_changing(dev);
+ if (!netif_running(dev))
+ return false;
+
+ if (dev->ifindex != dev->iflink)
+ return true;
+
+ return netif_carrier_ok(dev) && qdisc_tx_changing(dev);
}
@@ -126,7 +131,7 @@ static void linkwatch_schedule_work(int urgent)
return;
/* It's already running which is good enough. */
- if (!cancel_delayed_work(&linkwatch_work))
+ if (!__cancel_delayed_work(&linkwatch_work))
return;
/* Otherwise we reschedule it again for immediate execution. */
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 799f06e03a22..039d51e6c284 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -98,7 +98,7 @@ static const struct file_operations neigh_stat_seq_fops;
static DEFINE_RWLOCK(neigh_tbl_lock);
-static int neigh_blackhole(struct sk_buff *skb)
+static int neigh_blackhole(struct neighbour *neigh, struct sk_buff *skb)
{
kfree_skb(skb);
return -ENETDOWN;
@@ -137,7 +137,7 @@ static int neigh_forced_gc(struct neigh_table *tbl)
write_lock_bh(&tbl->lock);
nht = rcu_dereference_protected(tbl->nht,
lockdep_is_held(&tbl->lock));
- for (i = 0; i <= nht->hash_mask; i++) {
+ for (i = 0; i < (1 << nht->hash_shift); i++) {
struct neighbour *n;
struct neighbour __rcu **np;
@@ -210,7 +210,7 @@ static void neigh_flush_dev(struct neigh_table *tbl, struct net_device *dev)
nht = rcu_dereference_protected(tbl->nht,
lockdep_is_held(&tbl->lock));
- for (i = 0; i <= nht->hash_mask; i++) {
+ for (i = 0; i < (1 << nht->hash_shift); i++) {
struct neighbour *n;
struct neighbour __rcu **np = &nht->hash_buckets[i];
@@ -297,6 +297,7 @@ static struct neighbour *neigh_alloc(struct neigh_table *tbl)
n->updated = n->used = now;
n->nud_state = NUD_NONE;
n->output = neigh_blackhole;
+ seqlock_init(&n->hh.hh_lock);
n->parms = neigh_parms_clone(&tbl->parms);
setup_timer(&n->timer, neigh_timer_handler, (unsigned long)n);
@@ -312,9 +313,9 @@ out_entries:
goto out;
}
-static struct neigh_hash_table *neigh_hash_alloc(unsigned int entries)
+static struct neigh_hash_table *neigh_hash_alloc(unsigned int shift)
{
- size_t size = entries * sizeof(struct neighbour *);
+ size_t size = (1 << shift) * sizeof(struct neighbour *);
struct neigh_hash_table *ret;
struct neighbour __rcu **buckets;
@@ -332,8 +333,9 @@ static struct neigh_hash_table *neigh_hash_alloc(unsigned int entries)
return NULL;
}
ret->hash_buckets = buckets;
- ret->hash_mask = entries - 1;
+ ret->hash_shift = shift;
get_random_bytes(&ret->hash_rnd, sizeof(ret->hash_rnd));
+ ret->hash_rnd |= 1;
return ret;
}
@@ -342,7 +344,7 @@ static void neigh_hash_free_rcu(struct rcu_head *head)
struct neigh_hash_table *nht = container_of(head,
struct neigh_hash_table,
rcu);
- size_t size = (nht->hash_mask + 1) * sizeof(struct neighbour *);
+ size_t size = (1 << nht->hash_shift) * sizeof(struct neighbour *);
struct neighbour __rcu **buckets = nht->hash_buckets;
if (size <= PAGE_SIZE)
@@ -353,21 +355,20 @@ static void neigh_hash_free_rcu(struct rcu_head *head)
}
static struct neigh_hash_table *neigh_hash_grow(struct neigh_table *tbl,
- unsigned long new_entries)
+ unsigned long new_shift)
{
unsigned int i, hash;
struct neigh_hash_table *new_nht, *old_nht;
NEIGH_CACHE_STAT_INC(tbl, hash_grows);
- BUG_ON(!is_power_of_2(new_entries));
old_nht = rcu_dereference_protected(tbl->nht,
lockdep_is_held(&tbl->lock));
- new_nht = neigh_hash_alloc(new_entries);
+ new_nht = neigh_hash_alloc(new_shift);
if (!new_nht)
return old_nht;
- for (i = 0; i <= old_nht->hash_mask; i++) {
+ for (i = 0; i < (1 << old_nht->hash_shift); i++) {
struct neighbour *n, *next;
for (n = rcu_dereference_protected(old_nht->hash_buckets[i],
@@ -377,7 +378,7 @@ static struct neigh_hash_table *neigh_hash_grow(struct neigh_table *tbl,
hash = tbl->hash(n->primary_key, n->dev,
new_nht->hash_rnd);
- hash &= new_nht->hash_mask;
+ hash >>= (32 - new_nht->hash_shift);
next = rcu_dereference_protected(n->next,
lockdep_is_held(&tbl->lock));
@@ -406,7 +407,7 @@ struct neighbour *neigh_lookup(struct neigh_table *tbl, const void *pkey,
rcu_read_lock_bh();
nht = rcu_dereference_bh(tbl->nht);
- hash_val = tbl->hash(pkey, dev, nht->hash_rnd) & nht->hash_mask;
+ hash_val = tbl->hash(pkey, dev, nht->hash_rnd) >> (32 - nht->hash_shift);
for (n = rcu_dereference_bh(nht->hash_buckets[hash_val]);
n != NULL;
@@ -436,7 +437,7 @@ struct neighbour *neigh_lookup_nodev(struct neigh_table *tbl, struct net *net,
rcu_read_lock_bh();
nht = rcu_dereference_bh(tbl->nht);
- hash_val = tbl->hash(pkey, NULL, nht->hash_rnd) & nht->hash_mask;
+ hash_val = tbl->hash(pkey, NULL, nht->hash_rnd) >> (32 - nht->hash_shift);
for (n = rcu_dereference_bh(nht->hash_buckets[hash_val]);
n != NULL;
@@ -492,10 +493,10 @@ struct neighbour *neigh_create(struct neigh_table *tbl, const void *pkey,
nht = rcu_dereference_protected(tbl->nht,
lockdep_is_held(&tbl->lock));
- if (atomic_read(&tbl->entries) > (nht->hash_mask + 1))
- nht = neigh_hash_grow(tbl, (nht->hash_mask + 1) << 1);
+ if (atomic_read(&tbl->entries) > (1 << nht->hash_shift))
+ nht = neigh_hash_grow(tbl, nht->hash_shift + 1);
- hash_val = tbl->hash(pkey, dev, nht->hash_rnd) & nht->hash_mask;
+ hash_val = tbl->hash(pkey, dev, nht->hash_rnd) >> (32 - nht->hash_shift);
if (n->parms->dead) {
rc = ERR_PTR(-EINVAL);
@@ -688,8 +689,6 @@ static void neigh_destroy_rcu(struct rcu_head *head)
*/
void neigh_destroy(struct neighbour *neigh)
{
- struct hh_cache *hh;
-
NEIGH_CACHE_STAT_INC(neigh->tbl, destroys);
if (!neigh->dead) {
@@ -702,16 +701,6 @@ void neigh_destroy(struct neighbour *neigh)
if (neigh_del_timer(neigh))
printk(KERN_WARNING "Impossible event.\n");
- while ((hh = neigh->hh) != NULL) {
- neigh->hh = hh->hh_next;
- hh->hh_next = NULL;
-
- write_seqlock_bh(&hh->hh_lock);
- hh->hh_output = neigh_blackhole;
- write_sequnlock_bh(&hh->hh_lock);
- hh_cache_put(hh);
- }
-
skb_queue_purge(&neigh->arp_queue);
dev_put(neigh->dev);
@@ -731,14 +720,9 @@ EXPORT_SYMBOL(neigh_destroy);
*/
static void neigh_suspect(struct neighbour *neigh)
{
- struct hh_cache *hh;
-
NEIGH_PRINTK2("neigh %p is suspected.\n", neigh);
neigh->output = neigh->ops->output;
-
- for (hh = neigh->hh; hh; hh = hh->hh_next)
- hh->hh_output = neigh->ops->output;
}
/* Neighbour state is OK;
@@ -748,14 +732,9 @@ static void neigh_suspect(struct neighbour *neigh)
*/
static void neigh_connect(struct neighbour *neigh)
{
- struct hh_cache *hh;
-
NEIGH_PRINTK2("neigh %p is connected.\n", neigh);
neigh->output = neigh->ops->connected_output;
-
- for (hh = neigh->hh; hh; hh = hh->hh_next)
- hh->hh_output = neigh->ops->hh_output;
}
static void neigh_periodic_work(struct work_struct *work)
@@ -784,7 +763,7 @@ static void neigh_periodic_work(struct work_struct *work)
neigh_rand_reach_time(p->base_reachable_time);
}
- for (i = 0 ; i <= nht->hash_mask; i++) {
+ for (i = 0 ; i < (1 << nht->hash_shift); i++) {
np = &nht->hash_buckets[i];
while ((n = rcu_dereference_protected(*np,
@@ -865,6 +844,19 @@ static void neigh_invalidate(struct neighbour *neigh)
skb_queue_purge(&neigh->arp_queue);
}
+static void neigh_probe(struct neighbour *neigh)
+ __releases(neigh->lock)
+{
+ struct sk_buff *skb = skb_peek(&neigh->arp_queue);
+ /* keep skb alive even if arp_queue overflows */
+ if (skb)
+ skb = skb_copy(skb, GFP_ATOMIC);
+ write_unlock(&neigh->lock);
+ neigh->ops->solicit(neigh, skb);
+ atomic_inc(&neigh->probes);
+ kfree_skb(skb);
+}
+
/* Called when a timer expires for a neighbour entry. */
static void neigh_timer_handler(unsigned long arg)
@@ -880,12 +872,8 @@ static void neigh_timer_handler(unsigned long arg)
now = jiffies;
next = now + HZ;
- if (!(state & NUD_IN_TIMER)) {
-#ifndef CONFIG_SMP
- printk(KERN_WARNING "neigh: timer & !nud_in_timer\n");
-#endif
+ if (!(state & NUD_IN_TIMER))
goto out;
- }
if (state & NUD_REACHABLE) {
if (time_before_eq(now,
@@ -941,14 +929,7 @@ static void neigh_timer_handler(unsigned long arg)
neigh_hold(neigh);
}
if (neigh->nud_state & (NUD_INCOMPLETE | NUD_PROBE)) {
- struct sk_buff *skb = skb_peek(&neigh->arp_queue);
- /* keep skb alive even if arp_queue overflows */
- if (skb)
- skb = skb_copy(skb, GFP_ATOMIC);
- write_unlock(&neigh->lock);
- neigh->ops->solicit(neigh, skb);
- atomic_inc(&neigh->probes);
- kfree_skb(skb);
+ neigh_probe(neigh);
} else {
out:
write_unlock(&neigh->lock);
@@ -963,7 +944,7 @@ out:
int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb)
{
int rc;
- unsigned long now;
+ bool immediate_probe = false;
write_lock_bh(&neigh->lock);
@@ -971,14 +952,16 @@ int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb)
if (neigh->nud_state & (NUD_CONNECTED | NUD_DELAY | NUD_PROBE))
goto out_unlock_bh;
- now = jiffies;
-
if (!(neigh->nud_state & (NUD_STALE | NUD_INCOMPLETE))) {
if (neigh->parms->mcast_probes + neigh->parms->app_probes) {
+ unsigned long next, now = jiffies;
+
atomic_set(&neigh->probes, neigh->parms->ucast_probes);
neigh->nud_state = NUD_INCOMPLETE;
- neigh->updated = jiffies;
- neigh_add_timer(neigh, now + 1);
+ neigh->updated = now;
+ next = now + max(neigh->parms->retrans_time, HZ/2);
+ neigh_add_timer(neigh, next);
+ immediate_probe = true;
} else {
neigh->nud_state = NUD_FAILED;
neigh->updated = jiffies;
@@ -1010,12 +993,16 @@ int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb)
rc = 1;
}
out_unlock_bh:
- write_unlock_bh(&neigh->lock);
+ if (immediate_probe)
+ neigh_probe(neigh);
+ else
+ write_unlock(&neigh->lock);
+ local_bh_enable();
return rc;
}
EXPORT_SYMBOL(__neigh_event_send);
-static void neigh_update_hhs(const struct neighbour *neigh)
+static void neigh_update_hhs(struct neighbour *neigh)
{
struct hh_cache *hh;
void (*update)(struct hh_cache*, const struct net_device*, const unsigned char *)
@@ -1025,7 +1012,8 @@ static void neigh_update_hhs(const struct neighbour *neigh)
update = neigh->dev->header_ops->cache_update;
if (update) {
- for (hh = neigh->hh; hh; hh = hh->hh_next) {
+ hh = &neigh->hh;
+ if (hh->hh_len) {
write_seqlock_bh(&hh->hh_lock);
update(hh, neigh->dev, neigh->ha);
write_sequnlock_bh(&hh->hh_lock);
@@ -1173,12 +1161,17 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new,
while (neigh->nud_state & NUD_VALID &&
(skb = __skb_dequeue(&neigh->arp_queue)) != NULL) {
- struct neighbour *n1 = neigh;
+ struct dst_entry *dst = skb_dst(skb);
+ struct neighbour *n2, *n1 = neigh;
write_unlock_bh(&neigh->lock);
+
+ rcu_read_lock();
/* On shaper/eql skb->dst->neighbour != neigh :( */
- if (skb_dst(skb) && skb_dst(skb)->neighbour)
- n1 = skb_dst(skb)->neighbour;
- n1->output(skb);
+ if (dst && (n2 = dst_get_neighbour(dst)) != NULL)
+ n1 = n2;
+ n1->output(n1, skb);
+ rcu_read_unlock();
+
write_lock_bh(&neigh->lock);
}
skb_queue_purge(&neigh->arp_queue);
@@ -1211,67 +1204,21 @@ struct neighbour *neigh_event_ns(struct neigh_table *tbl,
}
EXPORT_SYMBOL(neigh_event_ns);
-static inline bool neigh_hh_lookup(struct neighbour *n, struct dst_entry *dst,
- __be16 protocol)
-{
- struct hh_cache *hh;
-
- smp_rmb(); /* paired with smp_wmb() in neigh_hh_init() */
- for (hh = n->hh; hh; hh = hh->hh_next) {
- if (hh->hh_type == protocol) {
- atomic_inc(&hh->hh_refcnt);
- if (unlikely(cmpxchg(&dst->hh, NULL, hh) != NULL))
- hh_cache_put(hh);
- return true;
- }
- }
- return false;
-}
-
/* called with read_lock_bh(&n->lock); */
-static void neigh_hh_init(struct neighbour *n, struct dst_entry *dst,
- __be16 protocol)
+static void neigh_hh_init(struct neighbour *n, struct dst_entry *dst)
{
- struct hh_cache *hh;
struct net_device *dev = dst->dev;
-
- if (likely(neigh_hh_lookup(n, dst, protocol)))
- return;
-
- /* slow path */
- hh = kzalloc(sizeof(*hh), GFP_ATOMIC);
- if (!hh)
- return;
-
- seqlock_init(&hh->hh_lock);
- hh->hh_type = protocol;
- atomic_set(&hh->hh_refcnt, 2);
-
- if (dev->header_ops->cache(n, hh)) {
- kfree(hh);
- return;
- }
+ __be16 prot = dst->ops->protocol;
+ struct hh_cache *hh = &n->hh;
write_lock_bh(&n->lock);
- /* must check if another thread already did the insert */
- if (neigh_hh_lookup(n, dst, protocol)) {
- kfree(hh);
- goto end;
- }
-
- if (n->nud_state & NUD_CONNECTED)
- hh->hh_output = n->ops->hh_output;
- else
- hh->hh_output = n->ops->output;
-
- hh->hh_next = n->hh;
- smp_wmb(); /* paired with smp_rmb() in neigh_hh_lookup() */
- n->hh = hh;
+ /* Only one thread can come in here and initialize the
+ * hh_cache entry.
+ */
+ if (!hh->hh_len)
+ dev->header_ops->cache(n, hh, prot);
- if (unlikely(cmpxchg(&dst->hh, NULL, hh) != NULL))
- hh_cache_put(hh);
-end:
write_unlock_bh(&n->lock);
}
@@ -1280,7 +1227,7 @@ end:
* but resolution is not made yet.
*/
-int neigh_compat_output(struct sk_buff *skb)
+int neigh_compat_output(struct neighbour *neigh, struct sk_buff *skb)
{
struct net_device *dev = skb->dev;
@@ -1297,13 +1244,12 @@ EXPORT_SYMBOL(neigh_compat_output);
/* Slow and careful. */
-int neigh_resolve_output(struct sk_buff *skb)
+int neigh_resolve_output(struct neighbour *neigh, struct sk_buff *skb)
{
struct dst_entry *dst = skb_dst(skb);
- struct neighbour *neigh;
int rc = 0;
- if (!dst || !(neigh = dst->neighbour))
+ if (!dst)
goto discard;
__skb_pull(skb, skb_network_offset(skb));
@@ -1313,10 +1259,8 @@ int neigh_resolve_output(struct sk_buff *skb)
struct net_device *dev = neigh->dev;
unsigned int seq;
- if (dev->header_ops->cache &&
- !dst->hh &&
- !(dst->flags & DST_NOCACHE))
- neigh_hh_init(neigh, dst, dst->ops->protocol);
+ if (dev->header_ops->cache && !neigh->hh.hh_len)
+ neigh_hh_init(neigh, dst);
do {
seq = read_seqbegin(&neigh->ha_lock);
@@ -1325,7 +1269,7 @@ int neigh_resolve_output(struct sk_buff *skb)
} while (read_seqretry(&neigh->ha_lock, seq));
if (err >= 0)
- rc = neigh->ops->queue_xmit(skb);
+ rc = dev_queue_xmit(skb);
else
goto out_kfree_skb;
}
@@ -1333,7 +1277,7 @@ out:
return rc;
discard:
NEIGH_PRINTK1("neigh_resolve_output: dst=%p neigh=%p\n",
- dst, dst ? dst->neighbour : NULL);
+ dst, neigh);
out_kfree_skb:
rc = -EINVAL;
kfree_skb(skb);
@@ -1343,13 +1287,11 @@ EXPORT_SYMBOL(neigh_resolve_output);
/* As fast as possible without hh cache */
-int neigh_connected_output(struct sk_buff *skb)
+int neigh_connected_output(struct neighbour *neigh, struct sk_buff *skb)
{
- int err;
- struct dst_entry *dst = skb_dst(skb);
- struct neighbour *neigh = dst->neighbour;
struct net_device *dev = neigh->dev;
unsigned int seq;
+ int err;
__skb_pull(skb, skb_network_offset(skb));
@@ -1360,7 +1302,7 @@ int neigh_connected_output(struct sk_buff *skb)
} while (read_seqretry(&neigh->ha_lock, seq));
if (err >= 0)
- err = neigh->ops->queue_xmit(skb);
+ err = dev_queue_xmit(skb);
else {
err = -EINVAL;
kfree_skb(skb);
@@ -1369,6 +1311,12 @@ int neigh_connected_output(struct sk_buff *skb)
}
EXPORT_SYMBOL(neigh_connected_output);
+int neigh_direct_output(struct neighbour *neigh, struct sk_buff *skb)
+{
+ return dev_queue_xmit(skb);
+}
+EXPORT_SYMBOL(neigh_direct_output);
+
static void neigh_proxy_process(unsigned long arg)
{
struct neigh_table *tbl = (struct neigh_table *)arg;
@@ -1383,11 +1331,15 @@ static void neigh_proxy_process(unsigned long arg)
if (tdif <= 0) {
struct net_device *dev = skb->dev;
+
__skb_unlink(skb, &tbl->proxy_queue);
- if (tbl->proxy_redo && netif_running(dev))
+ if (tbl->proxy_redo && netif_running(dev)) {
+ rcu_read_lock();
tbl->proxy_redo(skb);
- else
+ rcu_read_unlock();
+ } else {
kfree_skb(skb);
+ }
dev_put(dev);
} else if (!sched_next || tdif < sched_next)
@@ -1540,7 +1492,7 @@ void neigh_table_init_no_netlink(struct neigh_table *tbl)
panic("cannot create neighbour proc dir entry");
#endif
- RCU_INIT_POINTER(tbl->nht, neigh_hash_alloc(8));
+ RCU_INIT_POINTER(tbl->nht, neigh_hash_alloc(3));
phsize = (PNEIGH_HASHMASK + 1) * sizeof(struct pneigh_entry *);
tbl->phash_buckets = kzalloc(phsize, GFP_KERNEL);
@@ -1857,7 +1809,7 @@ static int neightbl_fill_info(struct sk_buff *skb, struct neigh_table *tbl,
rcu_read_lock_bh();
nht = rcu_dereference_bh(tbl->nht);
ndc.ndtc_hash_rnd = nht->hash_rnd;
- ndc.ndtc_hash_mask = nht->hash_mask;
+ ndc.ndtc_hash_mask = ((1 << nht->hash_shift) - 1);
rcu_read_unlock_bh();
NLA_PUT(skb, NDTA_CONFIG, sizeof(ndc), &ndc);
@@ -2200,7 +2152,7 @@ static int neigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb,
rcu_read_lock_bh();
nht = rcu_dereference_bh(tbl->nht);
- for (h = 0; h <= nht->hash_mask; h++) {
+ for (h = 0; h < (1 << nht->hash_shift); h++) {
if (h < s_h)
continue;
if (h > s_h)
@@ -2264,7 +2216,7 @@ void neigh_for_each(struct neigh_table *tbl, void (*cb)(struct neighbour *, void
nht = rcu_dereference_bh(tbl->nht);
read_lock(&tbl->lock); /* avoid resizes */
- for (chain = 0; chain <= nht->hash_mask; chain++) {
+ for (chain = 0; chain < (1 << nht->hash_shift); chain++) {
struct neighbour *n;
for (n = rcu_dereference_bh(nht->hash_buckets[chain]);
@@ -2286,7 +2238,7 @@ void __neigh_for_each_release(struct neigh_table *tbl,
nht = rcu_dereference_protected(tbl->nht,
lockdep_is_held(&tbl->lock));
- for (chain = 0; chain <= nht->hash_mask; chain++) {
+ for (chain = 0; chain < (1 << nht->hash_shift); chain++) {
struct neighbour *n;
struct neighbour __rcu **np;
@@ -2323,7 +2275,7 @@ static struct neighbour *neigh_get_first(struct seq_file *seq)
int bucket = state->bucket;
state->flags &= ~NEIGH_SEQ_IS_PNEIGH;
- for (bucket = 0; bucket <= nht->hash_mask; bucket++) {
+ for (bucket = 0; bucket < (1 << nht->hash_shift); bucket++) {
n = rcu_dereference_bh(nht->hash_buckets[bucket]);
while (n) {
@@ -2390,7 +2342,7 @@ next:
if (n)
break;
- if (++state->bucket > nht->hash_mask)
+ if (++state->bucket >= (1 << nht->hash_shift))
break;
n = rcu_dereference_bh(nht->hash_buckets[state->bucket]);
@@ -2909,12 +2861,13 @@ EXPORT_SYMBOL(neigh_sysctl_unregister);
static int __init neigh_init(void)
{
- rtnl_register(PF_UNSPEC, RTM_NEWNEIGH, neigh_add, NULL);
- rtnl_register(PF_UNSPEC, RTM_DELNEIGH, neigh_delete, NULL);
- rtnl_register(PF_UNSPEC, RTM_GETNEIGH, NULL, neigh_dump_info);
+ rtnl_register(PF_UNSPEC, RTM_NEWNEIGH, neigh_add, NULL, NULL);
+ rtnl_register(PF_UNSPEC, RTM_DELNEIGH, neigh_delete, NULL, NULL);
+ rtnl_register(PF_UNSPEC, RTM_GETNEIGH, NULL, neigh_dump_info, NULL);
- rtnl_register(PF_UNSPEC, RTM_GETNEIGHTBL, NULL, neightbl_dump_info);
- rtnl_register(PF_UNSPEC, RTM_SETNEIGHTBL, neightbl_set, NULL);
+ rtnl_register(PF_UNSPEC, RTM_GETNEIGHTBL, NULL, neightbl_dump_info,
+ NULL);
+ rtnl_register(PF_UNSPEC, RTM_SETNEIGHTBL, neightbl_set, NULL, NULL);
return 0;
}
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 33d2a1fba131..c71c434a4c05 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -20,6 +20,7 @@
#include <linux/rtnetlink.h>
#include <linux/wireless.h>
#include <linux/vmalloc.h>
+#include <linux/export.h>
#include <net/wext.h>
#include "net-sysfs.h"
@@ -100,7 +101,6 @@ NETDEVICE_SHOW(addr_assign_type, fmt_dec);
NETDEVICE_SHOW(addr_len, fmt_dec);
NETDEVICE_SHOW(iflink, fmt_dec);
NETDEVICE_SHOW(ifindex, fmt_dec);
-NETDEVICE_SHOW(features, fmt_hex);
NETDEVICE_SHOW(type, fmt_dec);
NETDEVICE_SHOW(link_mode, fmt_dec);
@@ -148,7 +148,7 @@ static ssize_t show_speed(struct device *dev,
if (netif_running(netdev)) {
struct ethtool_cmd cmd;
- if (!dev_ethtool_get_settings(netdev, &cmd))
+ if (!__ethtool_get_settings(netdev, &cmd))
ret = sprintf(buf, fmt_udec, ethtool_cmd_speed(&cmd));
}
rtnl_unlock();
@@ -166,7 +166,7 @@ static ssize_t show_duplex(struct device *dev,
if (netif_running(netdev)) {
struct ethtool_cmd cmd;
- if (!dev_ethtool_get_settings(netdev, &cmd))
+ if (!__ethtool_get_settings(netdev, &cmd))
ret = sprintf(buf, "%s\n",
cmd.duplex ? "full" : "half");
}
@@ -312,7 +312,6 @@ static struct device_attribute net_class_attributes[] = {
__ATTR(ifalias, S_IRUGO | S_IWUSR, show_ifalias, store_ifalias),
__ATTR(iflink, S_IRUGO, show_iflink, NULL),
__ATTR(ifindex, S_IRUGO, show_ifindex, NULL),
- __ATTR(features, S_IRUGO, show_features, NULL),
__ATTR(type, S_IRUGO, show_type, NULL),
__ATTR(link_mode, S_IRUGO, show_link_mode, NULL),
__ATTR(address, S_IRUGO, show_address, NULL),
@@ -714,13 +713,13 @@ static void rx_queue_release(struct kobject *kobj)
struct rps_dev_flow_table *flow_table;
- map = rcu_dereference_raw(queue->rps_map);
+ map = rcu_dereference_protected(queue->rps_map, 1);
if (map) {
RCU_INIT_POINTER(queue->rps_map, NULL);
kfree_rcu(map, rcu);
}
- flow_table = rcu_dereference_raw(queue->rps_flow_table);
+ flow_table = rcu_dereference_protected(queue->rps_flow_table, 1);
if (flow_table) {
RCU_INIT_POINTER(queue->rps_flow_table, NULL);
call_rcu(&flow_table->rcu, rps_dev_flow_table_release);
@@ -989,10 +988,10 @@ static ssize_t store_xps_map(struct netdev_queue *queue,
}
if (nonempty)
- rcu_assign_pointer(dev->xps_maps, new_dev_maps);
+ RCU_INIT_POINTER(dev->xps_maps, new_dev_maps);
else {
kfree(new_dev_maps);
- rcu_assign_pointer(dev->xps_maps, NULL);
+ RCU_INIT_POINTER(dev->xps_maps, NULL);
}
if (dev_maps)
diff --git a/net/core/net-traces.c b/net/core/net-traces.c
index 7f1bb2aba03b..ba3c0120786c 100644
--- a/net/core/net-traces.c
+++ b/net/core/net-traces.c
@@ -11,6 +11,7 @@
#include <linux/inetdevice.h>
#include <linux/inet.h>
#include <linux/interrupt.h>
+#include <linux/export.h>
#include <linux/netpoll.h>
#include <linux/sched.h>
#include <linux/delay.h>
@@ -28,6 +29,8 @@
#include <trace/events/skb.h>
#include <trace/events/net.h>
#include <trace/events/napi.h>
+#include <trace/events/sock.h>
+#include <trace/events/udp.h>
EXPORT_TRACEPOINT_SYMBOL_GPL(kfree_skb);
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index ea489db1bc23..aefcd7acbffa 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -10,6 +10,7 @@
#include <linux/nsproxy.h>
#include <linux/proc_fs.h>
#include <linux/file.h>
+#include <linux/export.h>
#include <net/net_namespace.h>
#include <net/netns/generic.h>
@@ -129,6 +130,7 @@ static __net_init int setup_net(struct net *net)
atomic_set(&net->count, 1);
atomic_set(&net->passive, 1);
+ net->dev_base_seq = 1;
#ifdef NETNS_REFCNT_DEBUG
atomic_set(&net->use_count, 0);
diff --git a/net/core/netevent.c b/net/core/netevent.c
index 865f0ceb81fb..f17ccd291d39 100644
--- a/net/core/netevent.c
+++ b/net/core/netevent.c
@@ -15,6 +15,7 @@
#include <linux/rtnetlink.h>
#include <linux/notifier.h>
+#include <linux/export.h>
#include <net/netevent.h>
static ATOMIC_NOTIFIER_HEAD(netevent_notif_chain);
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index 18d9cbda3a39..cf64c1ffa4cd 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -23,6 +23,7 @@
#include <linux/rcupdate.h>
#include <linux/workqueue.h>
#include <linux/slab.h>
+#include <linux/export.h>
#include <net/tcp.h>
#include <net/udp.h>
#include <asm/unaligned.h>
@@ -177,7 +178,7 @@ static void service_arp_queue(struct netpoll_info *npi)
}
}
-void netpoll_poll_dev(struct net_device *dev)
+static void netpoll_poll_dev(struct net_device *dev)
{
const struct net_device_ops *ops;
@@ -208,13 +209,6 @@ void netpoll_poll_dev(struct net_device *dev)
zap_completion_queue();
}
-EXPORT_SYMBOL(netpoll_poll_dev);
-
-void netpoll_poll(struct netpoll *np)
-{
- netpoll_poll_dev(np->dev);
-}
-EXPORT_SYMBOL(netpoll_poll);
static void refill_skbs(void)
{
@@ -275,7 +269,7 @@ repeat:
if (!skb) {
if (++count < 10) {
- netpoll_poll(np);
+ netpoll_poll_dev(np->dev);
goto repeat;
}
return NULL;
@@ -336,7 +330,7 @@ void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb,
}
/* tickle device maybe there is some cleanup */
- netpoll_poll(np);
+ netpoll_poll_dev(np->dev);
udelay(USEC_PER_POLL);
}
@@ -565,13 +559,14 @@ int __netpoll_rx(struct sk_buff *skb)
if (skb_shared(skb))
goto out;
- iph = (struct iphdr *)skb->data;
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;
@@ -586,6 +581,7 @@ int __netpoll_rx(struct sk_buff *skb)
if (pskb_trim_rcsum(skb, len))
goto out;
+ iph = (struct iphdr *)skb->data;
if (iph->protocol != IPPROTO_UDP)
goto out;
@@ -767,7 +763,7 @@ int __netpoll_setup(struct netpoll *np)
}
/* last thing to do is link it to the net device structure */
- rcu_assign_pointer(ndev->npinfo, npinfo);
+ RCU_INIT_POINTER(ndev->npinfo, npinfo);
return 0;
@@ -908,7 +904,7 @@ void __netpoll_cleanup(struct netpoll *np)
if (ops->ndo_netpoll_cleanup)
ops->ndo_netpoll_cleanup(np->dev);
- rcu_assign_pointer(np->dev->npinfo, NULL);
+ RCU_INIT_POINTER(np->dev->npinfo, NULL);
/* avoid racing with NAPI reading npinfo */
synchronize_rcu_bh();
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index f76079cd750c..0001c243b35c 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -1070,7 +1070,9 @@ static ssize_t pktgen_if_write(struct file *file,
len = num_arg(&user_buffer[i], 10, &value);
if (len < 0)
return len;
-
+ if ((value > 0) &&
+ (!(pkt_dev->odev->priv_flags & IFF_TX_SKB_SHARING)))
+ return -ENOTSUPP;
i += len;
pkt_dev->clone_skb = value;
@@ -2143,9 +2145,12 @@ static void spin(struct pktgen_dev *pkt_dev, ktime_t spin_until)
}
start_time = ktime_now();
- if (remaining < 100000)
- ndelay(remaining); /* really small just spin */
- else {
+ if (remaining < 100000) {
+ /* for small delays (<100us), just loop until limit is reached */
+ do {
+ end_time = ktime_now();
+ } while (ktime_lt(end_time, spin_until));
+ } else {
/* see do_nanosleep */
hrtimer_init_sleeper(&t, current);
do {
@@ -2160,8 +2165,8 @@ static void spin(struct pktgen_dev *pkt_dev, ktime_t spin_until)
hrtimer_cancel(&t.timer);
} while (t.task && pkt_dev->running && !signal_pending(current));
__set_current_state(TASK_RUNNING);
+ end_time = ktime_now();
}
- end_time = ktime_now();
pkt_dev->idle_acc += ktime_to_ns(ktime_sub(end_time, start_time));
pkt_dev->next_tx = ktime_add_ns(spin_until, pkt_dev->delay);
@@ -2600,18 +2605,18 @@ static void pktgen_finalize_skb(struct pktgen_dev *pkt_dev, struct sk_buff *skb,
if (!pkt_dev->page)
break;
}
- skb_shinfo(skb)->frags[i].page = pkt_dev->page;
get_page(pkt_dev->page);
+ skb_frag_set_page(skb, i, pkt_dev->page);
skb_shinfo(skb)->frags[i].page_offset = 0;
/*last fragment, fill rest of data*/
if (i == (frags - 1))
- skb_shinfo(skb)->frags[i].size =
- (datalen < PAGE_SIZE ? datalen : PAGE_SIZE);
+ skb_frag_size_set(&skb_shinfo(skb)->frags[i],
+ (datalen < PAGE_SIZE ? datalen : PAGE_SIZE));
else
- skb_shinfo(skb)->frags[i].size = frag_len;
- datalen -= skb_shinfo(skb)->frags[i].size;
- skb->len += skb_shinfo(skb)->frags[i].size;
- skb->data_len += skb_shinfo(skb)->frags[i].size;
+ skb_frag_size_set(&skb_shinfo(skb)->frags[i], frag_len);
+ datalen -= skb_frag_size(&skb_shinfo(skb)->frags[i]);
+ skb->len += skb_frag_size(&skb_shinfo(skb)->frags[i]);
+ skb->data_len += skb_frag_size(&skb_shinfo(skb)->frags[i]);
i++;
skb_shinfo(skb)->nr_frags = i;
}
@@ -3555,7 +3560,6 @@ static int pktgen_add_device(struct pktgen_thread *t, const char *ifname)
pkt_dev->min_pkt_size = ETH_ZLEN;
pkt_dev->max_pkt_size = ETH_ZLEN;
pkt_dev->nfrags = 0;
- pkt_dev->clone_skb = pg_clone_skb_d;
pkt_dev->delay = pg_delay_d;
pkt_dev->count = pg_count_d;
pkt_dev->sofar = 0;
@@ -3563,7 +3567,6 @@ static int pktgen_add_device(struct pktgen_thread *t, const char *ifname)
pkt_dev->udp_src_max = 9;
pkt_dev->udp_dst_min = 9;
pkt_dev->udp_dst_max = 9;
-
pkt_dev->vlan_p = 0;
pkt_dev->vlan_cfi = 0;
pkt_dev->vlan_id = 0xffff;
@@ -3575,6 +3578,8 @@ static int pktgen_add_device(struct pktgen_thread *t, const char *ifname)
err = pktgen_setup_dev(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,
&pktgen_if_fops, pkt_dev);
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index abd936d8a716..9083e82bdae5 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -56,9 +56,11 @@
struct rtnl_link {
rtnl_doit_func doit;
rtnl_dumpit_func dumpit;
+ rtnl_calcit_func calcit;
};
static DEFINE_MUTEX(rtnl_mutex);
+static u16 min_ifinfo_dump_size;
void rtnl_lock(void)
{
@@ -144,12 +146,28 @@ static rtnl_dumpit_func rtnl_get_dumpit(int protocol, int msgindex)
return tab ? tab[msgindex].dumpit : NULL;
}
+static rtnl_calcit_func rtnl_get_calcit(int protocol, int msgindex)
+{
+ struct rtnl_link *tab;
+
+ if (protocol <= RTNL_FAMILY_MAX)
+ tab = rtnl_msg_handlers[protocol];
+ else
+ tab = NULL;
+
+ if (tab == NULL || tab[msgindex].calcit == NULL)
+ tab = rtnl_msg_handlers[PF_UNSPEC];
+
+ return tab ? tab[msgindex].calcit : NULL;
+}
+
/**
* __rtnl_register - Register a rtnetlink message type
* @protocol: Protocol family or PF_UNSPEC
* @msgtype: rtnetlink message type
* @doit: Function pointer called for each request message
* @dumpit: Function pointer called for each dump request (NLM_F_DUMP) message
+ * @calcit: Function pointer to calc size of dump message
*
* Registers the specified function pointers (at least one of them has
* to be non-NULL) to be called whenever a request message for the
@@ -162,7 +180,8 @@ static rtnl_dumpit_func rtnl_get_dumpit(int protocol, int msgindex)
* Returns 0 on success or a negative error code.
*/
int __rtnl_register(int protocol, int msgtype,
- rtnl_doit_func doit, rtnl_dumpit_func dumpit)
+ rtnl_doit_func doit, rtnl_dumpit_func dumpit,
+ rtnl_calcit_func calcit)
{
struct rtnl_link *tab;
int msgindex;
@@ -185,6 +204,9 @@ int __rtnl_register(int protocol, int msgtype,
if (dumpit)
tab[msgindex].dumpit = dumpit;
+ if (calcit)
+ tab[msgindex].calcit = calcit;
+
return 0;
}
EXPORT_SYMBOL_GPL(__rtnl_register);
@@ -199,9 +221,10 @@ EXPORT_SYMBOL_GPL(__rtnl_register);
* of memory implies no sense in continuing.
*/
void rtnl_register(int protocol, int msgtype,
- rtnl_doit_func doit, rtnl_dumpit_func dumpit)
+ rtnl_doit_func doit, rtnl_dumpit_func dumpit,
+ rtnl_calcit_func calcit)
{
- if (__rtnl_register(protocol, msgtype, doit, dumpit) < 0)
+ if (__rtnl_register(protocol, msgtype, doit, dumpit, calcit) < 0)
panic("Unable to register rtnetlink message handler, "
"protocol = %d, message type = %d\n",
protocol, msgtype);
@@ -708,7 +731,8 @@ static inline int rtnl_vfinfo_size(const struct net_device *dev)
size += num_vfs *
(nla_total_size(sizeof(struct ifla_vf_mac)) +
nla_total_size(sizeof(struct ifla_vf_vlan)) +
- nla_total_size(sizeof(struct ifla_vf_tx_rate)));
+ nla_total_size(sizeof(struct ifla_vf_tx_rate)) +
+ nla_total_size(sizeof(struct ifla_vf_spoofchk)));
return size;
} else
return 0;
@@ -931,13 +955,27 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
struct ifla_vf_mac vf_mac;
struct ifla_vf_vlan vf_vlan;
struct ifla_vf_tx_rate vf_tx_rate;
+ struct ifla_vf_spoofchk vf_spoofchk;
+
+ /*
+ * Not all SR-IOV capable drivers support the
+ * spoofcheck query. Preset to -1 so the user
+ * space tool can detect that the driver didn't
+ * report anything.
+ */
+ ivi.spoofchk = -1;
if (dev->netdev_ops->ndo_get_vf_config(dev, i, &ivi))
break;
- vf_mac.vf = vf_vlan.vf = vf_tx_rate.vf = ivi.vf;
+ vf_mac.vf =
+ vf_vlan.vf =
+ vf_tx_rate.vf =
+ vf_spoofchk.vf = ivi.vf;
+
memcpy(vf_mac.mac, ivi.mac, sizeof(ivi.mac));
vf_vlan.vlan = ivi.vlan;
vf_vlan.qos = ivi.qos;
vf_tx_rate.rate = ivi.tx_rate;
+ vf_spoofchk.setting = ivi.spoofchk;
vf = nla_nest_start(skb, IFLA_VF_INFO);
if (!vf) {
nla_nest_cancel(skb, vfinfo);
@@ -945,7 +983,10 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
}
NLA_PUT(skb, IFLA_VF_MAC, sizeof(vf_mac), &vf_mac);
NLA_PUT(skb, IFLA_VF_VLAN, sizeof(vf_vlan), &vf_vlan);
- NLA_PUT(skb, IFLA_VF_TX_RATE, sizeof(vf_tx_rate), &vf_tx_rate);
+ NLA_PUT(skb, IFLA_VF_TX_RATE, sizeof(vf_tx_rate),
+ &vf_tx_rate);
+ NLA_PUT(skb, IFLA_VF_SPOOFCHK, sizeof(vf_spoofchk),
+ &vf_spoofchk);
nla_nest_end(skb, vf);
}
nla_nest_end(skb, vfinfo);
@@ -1009,6 +1050,8 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
s_idx = cb->args[1];
rcu_read_lock();
+ cb->seq = net->dev_base_seq;
+
for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) {
idx = 0;
head = &net->dev_index_head[h];
@@ -1020,6 +1063,8 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
cb->nlh->nlmsg_seq, 0,
NLM_F_MULTI) <= 0)
goto out;
+
+ nl_dump_check_consistent(cb, nlmsg_hdr(skb));
cont:
idx++;
}
@@ -1175,6 +1220,15 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr *attr)
ivt->rate);
break;
}
+ case IFLA_VF_SPOOFCHK: {
+ struct ifla_vf_spoofchk *ivs;
+ ivs = nla_data(vf);
+ err = -EOPNOTSUPP;
+ if (ops->ndo_set_vf_spoofchk)
+ err = ops->ndo_set_vf_spoofchk(dev, ivs->vf,
+ ivs->setting);
+ break;
+ }
default:
err = -EINVAL;
break;
@@ -1577,7 +1631,6 @@ struct net_device *rtnl_create_link(struct net *src_net, struct net *net,
dev_net_set(dev, net);
dev->rtnl_link_ops = ops;
dev->rtnl_link_state = RTNL_LINK_INITIALIZING;
- dev->real_num_tx_queues = real_num_queues;
if (tb[IFLA_MTU])
dev->mtu = nla_get_u32(tb[IFLA_MTU]);
@@ -1818,6 +1871,11 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
return err;
}
+static u16 rtnl_calcit(struct sk_buff *skb)
+{
+ return min_ifinfo_dump_size;
+}
+
static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb)
{
int idx;
@@ -1847,11 +1905,14 @@ void rtmsg_ifinfo(int type, struct net_device *dev, unsigned change)
struct net *net = dev_net(dev);
struct sk_buff *skb;
int err = -ENOBUFS;
+ size_t if_info_size;
- skb = nlmsg_new(if_nlmsg_size(dev), GFP_KERNEL);
+ skb = nlmsg_new((if_info_size = if_nlmsg_size(dev)), GFP_KERNEL);
if (skb == NULL)
goto errout;
+ min_ifinfo_dump_size = max_t(u16, if_info_size, min_ifinfo_dump_size);
+
err = rtnl_fill_ifinfo(skb, dev, type, 0, 0, change, 0);
if (err < 0) {
/* -EMSGSIZE implies BUG in if_nlmsg_size() */
@@ -1902,14 +1963,20 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
if (kind == 2 && nlh->nlmsg_flags&NLM_F_DUMP) {
struct sock *rtnl;
rtnl_dumpit_func dumpit;
+ rtnl_calcit_func calcit;
+ u16 min_dump_alloc = 0;
dumpit = rtnl_get_dumpit(family, type);
if (dumpit == NULL)
return -EOPNOTSUPP;
+ calcit = rtnl_get_calcit(family, type);
+ if (calcit)
+ min_dump_alloc = calcit(skb);
__rtnl_unlock();
rtnl = net->rtnl;
- err = netlink_dump_start(rtnl, skb, nlh, dumpit, NULL);
+ err = netlink_dump_start(rtnl, skb, nlh, dumpit,
+ NULL, min_dump_alloc);
rtnl_lock();
return err;
}
@@ -2019,12 +2086,13 @@ void __init rtnetlink_init(void)
netlink_set_nonroot(NETLINK_ROUTE, NL_NONROOT_RECV);
register_netdevice_notifier(&rtnetlink_dev_notifier);
- rtnl_register(PF_UNSPEC, RTM_GETLINK, rtnl_getlink, rtnl_dump_ifinfo);
- rtnl_register(PF_UNSPEC, RTM_SETLINK, rtnl_setlink, NULL);
- rtnl_register(PF_UNSPEC, RTM_NEWLINK, rtnl_newlink, NULL);
- rtnl_register(PF_UNSPEC, RTM_DELLINK, rtnl_dellink, NULL);
+ rtnl_register(PF_UNSPEC, RTM_GETLINK, rtnl_getlink,
+ rtnl_dump_ifinfo, rtnl_calcit);
+ rtnl_register(PF_UNSPEC, RTM_SETLINK, rtnl_setlink, NULL, NULL);
+ rtnl_register(PF_UNSPEC, RTM_NEWLINK, rtnl_newlink, NULL, NULL);
+ rtnl_register(PF_UNSPEC, RTM_DELLINK, rtnl_dellink, NULL, NULL);
- rtnl_register(PF_UNSPEC, RTM_GETADDR, NULL, rtnl_dump_all);
- rtnl_register(PF_UNSPEC, RTM_GETROUTE, NULL, rtnl_dump_all);
+ rtnl_register(PF_UNSPEC, RTM_GETADDR, NULL, rtnl_dump_all, NULL);
+ rtnl_register(PF_UNSPEC, RTM_GETROUTE, NULL, rtnl_dump_all, NULL);
}
diff --git a/net/core/scm.c b/net/core/scm.c
index 4c1ef026d695..ff52ad0a5150 100644
--- a/net/core/scm.c
+++ b/net/core/scm.c
@@ -173,7 +173,7 @@ int __scm_send(struct socket *sock, struct msghdr *msg, struct scm_cookie *p)
if (err)
goto error;
- if (pid_vnr(p->pid) != p->creds.pid) {
+ if (!p->pid || pid_vnr(p->pid) != p->creds.pid) {
struct pid *pid;
err = -ESRCH;
pid = find_get_pid(p->creds.pid);
@@ -183,8 +183,9 @@ int __scm_send(struct socket *sock, struct msghdr *msg, struct scm_cookie *p)
p->pid = pid;
}
- if ((p->cred->euid != p->creds.uid) ||
- (p->cred->egid != p->creds.gid)) {
+ if (!p->cred ||
+ (p->cred->euid != p->creds.uid) ||
+ (p->cred->egid != p->creds.gid)) {
struct cred *cred;
err = -ENOMEM;
cred = prepare_creds();
@@ -192,8 +193,9 @@ int __scm_send(struct socket *sock, struct msghdr *msg, struct scm_cookie *p)
goto error;
cred->uid = cred->euid = p->creds.uid;
- cred->gid = cred->egid = p->creds.uid;
- put_cred(p->cred);
+ cred->gid = cred->egid = p->creds.gid;
+ if (p->cred)
+ put_cred(p->cred);
p->cred = cred;
}
break;
diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c
new file mode 100644
index 000000000000..025233de25f9
--- /dev/null
+++ b/net/core/secure_seq.c
@@ -0,0 +1,184 @@
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/cryptohash.h>
+#include <linux/module.h>
+#include <linux/cache.h>
+#include <linux/random.h>
+#include <linux/hrtimer.h>
+#include <linux/ktime.h>
+#include <linux/string.h>
+
+#include <net/secure_seq.h>
+
+static u32 net_secret[MD5_MESSAGE_BYTES / 4] ____cacheline_aligned;
+
+static int __init net_secret_init(void)
+{
+ get_random_bytes(net_secret, sizeof(net_secret));
+ return 0;
+}
+late_initcall(net_secret_init);
+
+static u32 seq_scale(u32 seq)
+{
+ /*
+ * As close as possible to RFC 793, which
+ * suggests using a 250 kHz clock.
+ * Further reading shows this assumes 2 Mb/s networks.
+ * For 10 Mb/s Ethernet, a 1 MHz clock is appropriate.
+ * For 10 Gb/s Ethernet, a 1 GHz clock should be ok, but
+ * we also need to limit the resolution so that the u32 seq
+ * overlaps less than one time per MSL (2 minutes).
+ * Choosing a clock of 64 ns period is OK. (period of 274 s)
+ */
+ return seq + (ktime_to_ns(ktime_get_real()) >> 6);
+}
+
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+__u32 secure_tcpv6_sequence_number(const __be32 *saddr, const __be32 *daddr,
+ __be16 sport, __be16 dport)
+{
+ u32 secret[MD5_MESSAGE_BYTES / 4];
+ u32 hash[MD5_DIGEST_WORDS];
+ u32 i;
+
+ memcpy(hash, saddr, 16);
+ for (i = 0; i < 4; i++)
+ secret[i] = net_secret[i] + daddr[i];
+ secret[4] = net_secret[4] +
+ (((__force u16)sport << 16) + (__force u16)dport);
+ for (i = 5; i < MD5_MESSAGE_BYTES / 4; i++)
+ secret[i] = net_secret[i];
+
+ md5_transform(hash, secret);
+
+ return seq_scale(hash[0]);
+}
+EXPORT_SYMBOL(secure_tcpv6_sequence_number);
+
+u32 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr,
+ __be16 dport)
+{
+ u32 secret[MD5_MESSAGE_BYTES / 4];
+ u32 hash[MD5_DIGEST_WORDS];
+ u32 i;
+
+ memcpy(hash, saddr, 16);
+ for (i = 0; i < 4; i++)
+ secret[i] = net_secret[i] + (__force u32) daddr[i];
+ secret[4] = net_secret[4] + (__force u32)dport;
+ for (i = 5; i < MD5_MESSAGE_BYTES / 4; i++)
+ secret[i] = net_secret[i];
+
+ md5_transform(hash, secret);
+
+ return hash[0];
+}
+#endif
+
+#ifdef CONFIG_INET
+__u32 secure_ip_id(__be32 daddr)
+{
+ u32 hash[MD5_DIGEST_WORDS];
+
+ hash[0] = (__force __u32) daddr;
+ hash[1] = net_secret[13];
+ hash[2] = net_secret[14];
+ hash[3] = net_secret[15];
+
+ md5_transform(hash, net_secret);
+
+ return hash[0];
+}
+
+__u32 secure_ipv6_id(const __be32 daddr[4])
+{
+ __u32 hash[4];
+
+ memcpy(hash, daddr, 16);
+ md5_transform(hash, net_secret);
+
+ return hash[0];
+}
+
+__u32 secure_tcp_sequence_number(__be32 saddr, __be32 daddr,
+ __be16 sport, __be16 dport)
+{
+ u32 hash[MD5_DIGEST_WORDS];
+
+ hash[0] = (__force u32)saddr;
+ hash[1] = (__force u32)daddr;
+ hash[2] = ((__force u16)sport << 16) + (__force u16)dport;
+ hash[3] = net_secret[15];
+
+ md5_transform(hash, net_secret);
+
+ return seq_scale(hash[0]);
+}
+
+u32 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport)
+{
+ u32 hash[MD5_DIGEST_WORDS];
+
+ hash[0] = (__force u32)saddr;
+ hash[1] = (__force u32)daddr;
+ hash[2] = (__force u32)dport ^ net_secret[14];
+ hash[3] = net_secret[15];
+
+ md5_transform(hash, net_secret);
+
+ return hash[0];
+}
+EXPORT_SYMBOL_GPL(secure_ipv4_port_ephemeral);
+#endif
+
+#if defined(CONFIG_IP_DCCP) || defined(CONFIG_IP_DCCP_MODULE)
+u64 secure_dccp_sequence_number(__be32 saddr, __be32 daddr,
+ __be16 sport, __be16 dport)
+{
+ u32 hash[MD5_DIGEST_WORDS];
+ u64 seq;
+
+ hash[0] = (__force u32)saddr;
+ hash[1] = (__force u32)daddr;
+ hash[2] = ((__force u16)sport << 16) + (__force u16)dport;
+ hash[3] = net_secret[15];
+
+ md5_transform(hash, net_secret);
+
+ seq = hash[0] | (((u64)hash[1]) << 32);
+ seq += ktime_to_ns(ktime_get_real());
+ seq &= (1ull << 48) - 1;
+
+ return seq;
+}
+EXPORT_SYMBOL(secure_dccp_sequence_number);
+
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+u64 secure_dccpv6_sequence_number(__be32 *saddr, __be32 *daddr,
+ __be16 sport, __be16 dport)
+{
+ u32 secret[MD5_MESSAGE_BYTES / 4];
+ u32 hash[MD5_DIGEST_WORDS];
+ u64 seq;
+ u32 i;
+
+ memcpy(hash, saddr, 16);
+ for (i = 0; i < 4; i++)
+ secret[i] = net_secret[i] + daddr[i];
+ secret[4] = net_secret[4] +
+ (((__force u16)sport << 16) + (__force u16)dport);
+ for (i = 5; i < MD5_MESSAGE_BYTES / 4; i++)
+ secret[i] = net_secret[i];
+
+ md5_transform(hash, secret);
+
+ seq = hash[0] | (((u64)hash[1]) << 32);
+ seq += ktime_to_ns(ktime_get_real());
+ seq &= (1ull << 48) - 1;
+
+ return seq;
+}
+EXPORT_SYMBOL(secure_dccpv6_sequence_number);
+#endif
+#endif
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 46cbd28f40f9..18a3cebb753d 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -184,11 +184,21 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask,
goto out;
prefetchw(skb);
+ /* We do our best to align skb_shared_info on a separate cache
+ * line. It usually works because kmalloc(X > SMP_CACHE_BYTES) gives
+ * aligned memory blocks, unless SLUB/SLAB debug is enabled.
+ * Both skb->head and skb_shared_info are cache line aligned.
+ */
size = SKB_DATA_ALIGN(size);
- data = kmalloc_node_track_caller(size + sizeof(struct skb_shared_info),
- gfp_mask, node);
+ size += SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+ data = kmalloc_node_track_caller(size, gfp_mask, node);
if (!data)
goto nodata;
+ /* kmalloc(size) might give us more room than requested.
+ * Put skb_shared_info exactly at the end of allocated zone,
+ * to allow max possible filling before reallocation.
+ */
+ size = SKB_WITH_OVERHEAD(ksize(data));
prefetchw(data + size);
/*
@@ -197,7 +207,8 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask,
* the tail pointer in struct sk_buff!
*/
memset(skb, 0, offsetof(struct sk_buff, tail));
- skb->truesize = size + sizeof(struct sk_buff);
+ /* Account for allocated memory : skb + skb->head */
+ skb->truesize = SKB_TRUESIZE(size);
atomic_set(&skb->users, 1);
skb->head = data;
skb->data = data;
@@ -326,7 +337,19 @@ static void skb_release_data(struct sk_buff *skb)
if (skb_shinfo(skb)->nr_frags) {
int i;
for (i = 0; i < skb_shinfo(skb)->nr_frags; i++)
- put_page(skb_shinfo(skb)->frags[i].page);
+ skb_frag_unref(skb, i);
+ }
+
+ /*
+ * If skb buf is from userspace, we need to notify the caller
+ * the lower device DMA has done;
+ */
+ if (skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY) {
+ struct ubuf_info *uarg;
+
+ uarg = skb_shinfo(skb)->destructor_arg;
+ if (uarg->callback)
+ uarg->callback(uarg);
}
if (skb_has_frag_list(skb))
@@ -463,6 +486,30 @@ void consume_skb(struct sk_buff *skb)
EXPORT_SYMBOL(consume_skb);
/**
+ * skb_recycle - clean up an skb for reuse
+ * @skb: buffer
+ *
+ * Recycles the skb to be reused as a receive buffer. This
+ * function does any necessary reference count dropping, and
+ * cleans up the skbuff as if it just came from __alloc_skb().
+ */
+void skb_recycle(struct sk_buff *skb)
+{
+ struct skb_shared_info *shinfo;
+
+ skb_release_head_state(skb);
+
+ shinfo = skb_shinfo(skb);
+ memset(shinfo, 0, offsetof(struct skb_shared_info, dataref));
+ atomic_set(&shinfo->dataref, 1);
+
+ memset(skb, 0, offsetof(struct sk_buff, tail));
+ skb->data = skb->head + NET_SKB_PAD;
+ skb_reset_tail_pointer(skb);
+}
+EXPORT_SYMBOL(skb_recycle);
+
+/**
* skb_recycle_check - check if skb can be reused for receive
* @skb: buffer
* @skb_size: minimum receive buffer size
@@ -476,30 +523,10 @@ EXPORT_SYMBOL(consume_skb);
*/
bool skb_recycle_check(struct sk_buff *skb, int skb_size)
{
- struct skb_shared_info *shinfo;
-
- if (irqs_disabled())
- return false;
-
- if (skb_is_nonlinear(skb) || skb->fclone != SKB_FCLONE_UNAVAILABLE)
- return false;
-
- skb_size = SKB_DATA_ALIGN(skb_size + NET_SKB_PAD);
- if (skb_end_pointer(skb) - skb->head < skb_size)
- return false;
-
- if (skb_shared(skb) || skb_cloned(skb))
+ if (!skb_is_recycleable(skb, skb_size))
return false;
- skb_release_head_state(skb);
-
- shinfo = skb_shinfo(skb);
- memset(shinfo, 0, offsetof(struct skb_shared_info, dataref));
- atomic_set(&shinfo->dataref, 1);
-
- memset(skb, 0, offsetof(struct sk_buff, tail));
- skb->data = skb->head + NET_SKB_PAD;
- skb_reset_tail_pointer(skb);
+ skb_recycle(skb);
return true;
}
@@ -514,6 +541,8 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old)
new->mac_header = old->mac_header;
skb_dst_copy(new, old);
new->rxhash = old->rxhash;
+ new->ooo_okay = old->ooo_okay;
+ new->l4_rxhash = old->l4_rxhash;
#ifdef CONFIG_XFRM
new->sp = secpath_get(old->sp);
#endif
@@ -596,6 +625,66 @@ struct sk_buff *skb_morph(struct sk_buff *dst, struct sk_buff *src)
}
EXPORT_SYMBOL_GPL(skb_morph);
+/* skb_copy_ubufs - copy userspace skb frags buffers to kernel
+ * @skb: the skb to modify
+ * @gfp_mask: allocation priority
+ *
+ * This must be called on SKBTX_DEV_ZEROCOPY skb.
+ * It will copy all frags into kernel and drop the reference
+ * to userspace pages.
+ *
+ * If this function is called from an interrupt gfp_mask() must be
+ * %GFP_ATOMIC.
+ *
+ * Returns 0 on success or a negative error code on failure
+ * to allocate kernel memory to copy to.
+ */
+int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask)
+{
+ int i;
+ int num_frags = skb_shinfo(skb)->nr_frags;
+ struct page *page, *head = NULL;
+ struct ubuf_info *uarg = skb_shinfo(skb)->destructor_arg;
+
+ for (i = 0; i < num_frags; i++) {
+ u8 *vaddr;
+ skb_frag_t *f = &skb_shinfo(skb)->frags[i];
+
+ page = alloc_page(GFP_ATOMIC);
+ if (!page) {
+ while (head) {
+ struct page *next = (struct page *)head->private;
+ put_page(head);
+ head = next;
+ }
+ return -ENOMEM;
+ }
+ vaddr = kmap_skb_frag(&skb_shinfo(skb)->frags[i]);
+ memcpy(page_address(page),
+ vaddr + f->page_offset, skb_frag_size(f));
+ kunmap_skb_frag(vaddr);
+ page->private = (unsigned long)head;
+ head = page;
+ }
+
+ /* skb frags release userspace buffers */
+ for (i = 0; i < skb_shinfo(skb)->nr_frags; i++)
+ skb_frag_unref(skb, i);
+
+ uarg->callback(uarg);
+
+ /* skb frags point to kernel buffers */
+ for (i = skb_shinfo(skb)->nr_frags; i > 0; i--) {
+ __skb_fill_page_desc(skb, i-1, head, 0,
+ skb_shinfo(skb)->frags[i - 1].size);
+ head = (struct page *)head->private;
+ }
+
+ skb_shinfo(skb)->tx_flags &= ~SKBTX_DEV_ZEROCOPY;
+ return 0;
+}
+
+
/**
* skb_clone - duplicate an sk_buff
* @skb: buffer to clone
@@ -614,6 +703,11 @@ struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t gfp_mask)
{
struct sk_buff *n;
+ if (skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY) {
+ if (skb_copy_ubufs(skb, gfp_mask))
+ return NULL;
+ }
+
n = skb + 1;
if (skb->fclone == SKB_FCLONE_ORIG &&
n->fclone == SKB_FCLONE_UNAVAILABLE) {
@@ -731,9 +825,16 @@ struct sk_buff *pskb_copy(struct sk_buff *skb, gfp_t gfp_mask)
if (skb_shinfo(skb)->nr_frags) {
int i;
+ if (skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY) {
+ if (skb_copy_ubufs(skb, gfp_mask)) {
+ kfree_skb(n);
+ n = NULL;
+ goto out;
+ }
+ }
for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
skb_shinfo(n)->frags[i] = skb_shinfo(skb)->frags[i];
- get_page(skb_shinfo(n)->frags[i].page);
+ skb_frag_ref(skb, i);
}
skb_shinfo(n)->nr_frags = i;
}
@@ -788,7 +889,6 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail,
fastpath = true;
else {
int delta = skb->nohdr ? (1 << SKB_DATAREF_SHIFT) + 1 : 1;
-
fastpath = atomic_read(&skb_shinfo(skb)->dataref) == delta;
}
@@ -819,8 +919,13 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail,
if (fastpath) {
kfree(skb->head);
} else {
+ /* copy this zero copy skb frags */
+ if (skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY) {
+ if (skb_copy_ubufs(skb, gfp_mask))
+ goto nofrags;
+ }
for (i = 0; i < skb_shinfo(skb)->nr_frags; i++)
- get_page(skb_shinfo(skb)->frags[i].page);
+ skb_frag_ref(skb, i);
if (skb_has_frag_list(skb))
skb_clone_fraglist(skb);
@@ -853,6 +958,8 @@ adjust_others:
atomic_set(&skb_shinfo(skb)->dataref, 1);
return 0;
+nofrags:
+ kfree(data);
nodata:
return -ENOMEM;
}
@@ -1085,20 +1192,20 @@ int ___pskb_trim(struct sk_buff *skb, unsigned int len)
goto drop_pages;
for (; i < nfrags; i++) {
- int end = offset + skb_shinfo(skb)->frags[i].size;
+ int end = offset + skb_frag_size(&skb_shinfo(skb)->frags[i]);
if (end < len) {
offset = end;
continue;
}
- skb_shinfo(skb)->frags[i++].size = len - offset;
+ skb_frag_size_set(&skb_shinfo(skb)->frags[i++], len - offset);
drop_pages:
skb_shinfo(skb)->nr_frags = i;
for (; i < nfrags; i++)
- put_page(skb_shinfo(skb)->frags[i].page);
+ skb_frag_unref(skb, i);
if (skb_has_frag_list(skb))
skb_drop_fraglist(skb);
@@ -1201,9 +1308,11 @@ unsigned char *__pskb_pull_tail(struct sk_buff *skb, int delta)
/* Estimate size of pulled pages. */
eat = delta;
for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
- if (skb_shinfo(skb)->frags[i].size >= eat)
+ int size = skb_frag_size(&skb_shinfo(skb)->frags[i]);
+
+ if (size >= eat)
goto pull_pages;
- eat -= skb_shinfo(skb)->frags[i].size;
+ eat -= size;
}
/* If we need update frag list, we are in troubles.
@@ -1266,14 +1375,16 @@ pull_pages:
eat = delta;
k = 0;
for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
- if (skb_shinfo(skb)->frags[i].size <= eat) {
- put_page(skb_shinfo(skb)->frags[i].page);
- eat -= skb_shinfo(skb)->frags[i].size;
+ int size = skb_frag_size(&skb_shinfo(skb)->frags[i]);
+
+ if (size <= eat) {
+ skb_frag_unref(skb, i);
+ eat -= size;
} else {
skb_shinfo(skb)->frags[k] = skb_shinfo(skb)->frags[i];
if (eat) {
skb_shinfo(skb)->frags[k].page_offset += eat;
- skb_shinfo(skb)->frags[k].size -= eat;
+ skb_frag_size_sub(&skb_shinfo(skb)->frags[k], eat);
eat = 0;
}
k++;
@@ -1288,8 +1399,21 @@ pull_pages:
}
EXPORT_SYMBOL(__pskb_pull_tail);
-/* Copy some data bits from skb to kernel buffer. */
-
+/**
+ * skb_copy_bits - copy bits from skb to kernel buffer
+ * @skb: source skb
+ * @offset: offset in source
+ * @to: destination buffer
+ * @len: number of bytes to copy
+ *
+ * Copy the specified number of bytes from the source skb to the
+ * destination buffer.
+ *
+ * CAUTION ! :
+ * If its prototype is ever changed,
+ * check arch/{*}/net/{*}.S files,
+ * since it is called from BPF assembly code.
+ */
int skb_copy_bits(const struct sk_buff *skb, int offset, void *to, int len)
{
int start = skb_headlen(skb);
@@ -1315,7 +1439,7 @@ int skb_copy_bits(const struct sk_buff *skb, int offset, void *to, int len)
WARN_ON(start > offset + len);
- end = start + skb_shinfo(skb)->frags[i].size;
+ end = start + skb_frag_size(&skb_shinfo(skb)->frags[i]);
if ((copy = end - offset) > 0) {
u8 *vaddr;
@@ -1354,6 +1478,7 @@ int skb_copy_bits(const struct sk_buff *skb, int offset, void *to, int len)
}
start = end;
}
+
if (!len)
return 0;
@@ -1512,7 +1637,8 @@ static int __skb_splice_bits(struct sk_buff *skb, struct pipe_inode_info *pipe,
for (seg = 0; seg < skb_shinfo(skb)->nr_frags; seg++) {
const skb_frag_t *f = &skb_shinfo(skb)->frags[seg];
- if (__splice_segment(f->page, f->page_offset, f->size,
+ if (__splice_segment(skb_frag_page(f),
+ f->page_offset, skb_frag_size(f),
offset, len, skb, spd, 0, sk, pipe))
return 1;
}
@@ -1622,7 +1748,7 @@ int skb_store_bits(struct sk_buff *skb, int offset, const void *from, int len)
WARN_ON(start > offset + len);
- end = start + frag->size;
+ end = start + skb_frag_size(frag);
if ((copy = end - offset) > 0) {
u8 *vaddr;
@@ -1695,7 +1821,7 @@ __wsum skb_checksum(const struct sk_buff *skb, int offset,
WARN_ON(start > offset + len);
- end = start + skb_shinfo(skb)->frags[i].size;
+ end = start + skb_frag_size(&skb_shinfo(skb)->frags[i]);
if ((copy = end - offset) > 0) {
__wsum csum2;
u8 *vaddr;
@@ -1770,7 +1896,7 @@ __wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset,
WARN_ON(start > offset + len);
- end = start + skb_shinfo(skb)->frags[i].size;
+ end = start + skb_frag_size(&skb_shinfo(skb)->frags[i]);
if ((copy = end - offset) > 0) {
__wsum csum2;
u8 *vaddr;
@@ -2043,7 +2169,7 @@ static inline void skb_split_no_header(struct sk_buff *skb,
skb->data_len = len - pos;
for (i = 0; i < nfrags; i++) {
- int size = skb_shinfo(skb)->frags[i].size;
+ int size = skb_frag_size(&skb_shinfo(skb)->frags[i]);
if (pos + size > len) {
skb_shinfo(skb1)->frags[k] = skb_shinfo(skb)->frags[i];
@@ -2057,10 +2183,10 @@ static inline void skb_split_no_header(struct sk_buff *skb,
* where splitting is expensive.
* 2. Split is accurately. We make this.
*/
- get_page(skb_shinfo(skb)->frags[i].page);
+ skb_frag_ref(skb, i);
skb_shinfo(skb1)->frags[0].page_offset += len - pos;
- skb_shinfo(skb1)->frags[0].size -= len - pos;
- skb_shinfo(skb)->frags[i].size = len - pos;
+ skb_frag_size_sub(&skb_shinfo(skb1)->frags[0], len - pos);
+ skb_frag_size_set(&skb_shinfo(skb)->frags[i], len - pos);
skb_shinfo(skb)->nr_frags++;
}
k++;
@@ -2132,12 +2258,13 @@ int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen)
* commit all, so that we don't have to undo partial changes
*/
if (!to ||
- !skb_can_coalesce(tgt, to, fragfrom->page, fragfrom->page_offset)) {
+ !skb_can_coalesce(tgt, to, skb_frag_page(fragfrom),
+ fragfrom->page_offset)) {
merge = -1;
} else {
merge = to - 1;
- todo -= fragfrom->size;
+ todo -= skb_frag_size(fragfrom);
if (todo < 0) {
if (skb_prepare_for_shift(skb) ||
skb_prepare_for_shift(tgt))
@@ -2147,8 +2274,8 @@ int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen)
fragfrom = &skb_shinfo(skb)->frags[from];
fragto = &skb_shinfo(tgt)->frags[merge];
- fragto->size += shiftlen;
- fragfrom->size -= shiftlen;
+ skb_frag_size_add(fragto, shiftlen);
+ skb_frag_size_sub(fragfrom, shiftlen);
fragfrom->page_offset += shiftlen;
goto onlymerged;
@@ -2172,20 +2299,20 @@ int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen)
fragfrom = &skb_shinfo(skb)->frags[from];
fragto = &skb_shinfo(tgt)->frags[to];
- if (todo >= fragfrom->size) {
+ if (todo >= skb_frag_size(fragfrom)) {
*fragto = *fragfrom;
- todo -= fragfrom->size;
+ todo -= skb_frag_size(fragfrom);
from++;
to++;
} else {
- get_page(fragfrom->page);
+ __skb_frag_ref(fragfrom);
fragto->page = fragfrom->page;
fragto->page_offset = fragfrom->page_offset;
- fragto->size = todo;
+ skb_frag_size_set(fragto, todo);
fragfrom->page_offset += todo;
- fragfrom->size -= todo;
+ skb_frag_size_sub(fragfrom, todo);
todo = 0;
to++;
@@ -2200,8 +2327,8 @@ int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen)
fragfrom = &skb_shinfo(skb)->frags[0];
fragto = &skb_shinfo(tgt)->frags[merge];
- fragto->size += fragfrom->size;
- put_page(fragfrom->page);
+ skb_frag_size_add(fragto, skb_frag_size(fragfrom));
+ __skb_frag_unref(fragfrom);
}
/* Reposition in the original skb */
@@ -2298,7 +2425,7 @@ next_skb:
while (st->frag_idx < skb_shinfo(st->cur_skb)->nr_frags) {
frag = &skb_shinfo(st->cur_skb)->frags[st->frag_idx];
- block_limit = frag->size + st->stepped_offset;
+ block_limit = skb_frag_size(frag) + st->stepped_offset;
if (abs_offset < block_limit) {
if (!st->frag_data)
@@ -2316,7 +2443,7 @@ next_skb:
}
st->frag_idx++;
- st->stepped_offset += frag->size;
+ st->stepped_offset += skb_frag_size(frag);
}
if (st->frag_data) {
@@ -2446,14 +2573,13 @@ int skb_append_datato_frags(struct sock *sk, struct sk_buff *skb,
left = PAGE_SIZE - frag->page_offset;
copy = (length > left)? left : length;
- ret = getfrag(from, (page_address(frag->page) +
- frag->page_offset + frag->size),
+ ret = getfrag(from, skb_frag_address(frag) + skb_frag_size(frag),
offset, copy, 0, skb);
if (ret < 0)
return -EFAULT;
/* copy was successful so update the size parameters */
- frag->size += copy;
+ skb_frag_size_add(frag, copy);
skb->len += copy;
skb->data_len += copy;
offset += copy;
@@ -2599,12 +2725,12 @@ struct sk_buff *skb_segment(struct sk_buff *skb, u32 features)
while (pos < offset + len && i < nfrags) {
*frag = skb_shinfo(skb)->frags[i];
- get_page(frag->page);
- size = frag->size;
+ __skb_frag_ref(frag);
+ size = skb_frag_size(frag);
if (pos < offset) {
frag->page_offset += offset - pos;
- frag->size -= offset - pos;
+ skb_frag_size_sub(frag, offset - pos);
}
skb_shinfo(nskb)->nr_frags++;
@@ -2613,7 +2739,7 @@ struct sk_buff *skb_segment(struct sk_buff *skb, u32 features)
i++;
pos += size;
} else {
- frag->size -= pos + size - (offset + len);
+ skb_frag_size_sub(frag, pos + size - (offset + len));
goto skip_fraglist;
}
@@ -2693,7 +2819,7 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb)
} while (--i);
frag->page_offset += offset;
- frag->size -= offset;
+ skb_frag_size_sub(frag, offset);
skb->truesize -= skb->data_len;
skb->len -= skb->data_len;
@@ -2745,7 +2871,7 @@ merge:
unsigned int eat = offset - headlen;
skbinfo->frags[0].page_offset += eat;
- skbinfo->frags[0].size -= eat;
+ skb_frag_size_sub(&skbinfo->frags[0], eat);
skb->data_len -= eat;
skb->len -= eat;
offset = headlen;
@@ -2816,13 +2942,13 @@ __skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len)
WARN_ON(start > offset + len);
- end = start + skb_shinfo(skb)->frags[i].size;
+ end = start + skb_frag_size(&skb_shinfo(skb)->frags[i]);
if ((copy = end - offset) > 0) {
skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
if (copy > len)
copy = len;
- sg_set_page(&sg[elt], frag->page, copy,
+ sg_set_page(&sg[elt], skb_frag_page(frag), copy,
frag->page_offset+offset-start);
elt++;
if (!(len -= copy))
diff --git a/net/core/sock.c b/net/core/sock.c
index 6e819780c232..4ed7b1d12f5e 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -128,6 +128,8 @@
#include <linux/filter.h>
+#include <trace/events/sock.h>
+
#ifdef CONFIG_INET
#include <net/tcp.h>
#endif
@@ -158,7 +160,7 @@ static const char *const af_family_key_strings[AF_MAX+1] = {
"sk_lock-AF_TIPC" , "sk_lock-AF_BLUETOOTH", "sk_lock-IUCV" ,
"sk_lock-AF_RXRPC" , "sk_lock-AF_ISDN" , "sk_lock-AF_PHONET" ,
"sk_lock-AF_IEEE802154", "sk_lock-AF_CAIF" , "sk_lock-AF_ALG" ,
- "sk_lock-AF_MAX"
+ "sk_lock-AF_NFC" , "sk_lock-AF_MAX"
};
static const char *const af_family_slock_key_strings[AF_MAX+1] = {
"slock-AF_UNSPEC", "slock-AF_UNIX" , "slock-AF_INET" ,
@@ -174,7 +176,7 @@ static const char *const af_family_slock_key_strings[AF_MAX+1] = {
"slock-AF_TIPC" , "slock-AF_BLUETOOTH", "slock-AF_IUCV" ,
"slock-AF_RXRPC" , "slock-AF_ISDN" , "slock-AF_PHONET" ,
"slock-AF_IEEE802154", "slock-AF_CAIF" , "slock-AF_ALG" ,
- "slock-AF_MAX"
+ "slock-AF_NFC" , "slock-AF_MAX"
};
static const char *const af_family_clock_key_strings[AF_MAX+1] = {
"clock-AF_UNSPEC", "clock-AF_UNIX" , "clock-AF_INET" ,
@@ -190,7 +192,7 @@ static const char *const af_family_clock_key_strings[AF_MAX+1] = {
"clock-AF_TIPC" , "clock-AF_BLUETOOTH", "clock-AF_IUCV" ,
"clock-AF_RXRPC" , "clock-AF_ISDN" , "clock-AF_PHONET" ,
"clock-AF_IEEE802154", "clock-AF_CAIF" , "clock-AF_ALG" ,
- "clock-AF_MAX"
+ "clock-AF_NFC" , "clock-AF_MAX"
};
/*
@@ -205,7 +207,7 @@ static struct lock_class_key af_callback_keys[AF_MAX];
* not depend upon such differences.
*/
#define _SK_MEM_PACKETS 256
-#define _SK_MEM_OVERHEAD (sizeof(struct sk_buff) + 256)
+#define _SK_MEM_OVERHEAD SKB_TRUESIZE(256)
#define SK_WMEM_MAX (_SK_MEM_OVERHEAD * _SK_MEM_PACKETS)
#define SK_RMEM_MAX (_SK_MEM_OVERHEAD * _SK_MEM_PACKETS)
@@ -292,6 +294,7 @@ int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
if (atomic_read(&sk->sk_rmem_alloc) + skb->truesize >=
(unsigned)sk->sk_rcvbuf) {
atomic_inc(&sk->sk_drops);
+ trace_sock_rcvqueue_full(sk, skb);
return -ENOMEM;
}
@@ -384,7 +387,7 @@ struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie)
if (dst && dst->obsolete && dst->ops->check(dst, cookie) == NULL) {
sk_tx_queue_clear(sk);
- rcu_assign_pointer(sk->sk_dst_cache, NULL);
+ RCU_INIT_POINTER(sk->sk_dst_cache, NULL);
dst_release(dst);
return NULL;
}
@@ -735,10 +738,7 @@ set_rcvbuf:
/* We implement the SO_SNDLOWAT etc to
not be settable (1003.1g 5.3) */
case SO_RXQ_OVFL:
- if (valbool)
- sock_set_flag(sk, SOCK_RXQ_OVFL);
- else
- sock_reset_flag(sk, SOCK_RXQ_OVFL);
+ sock_valbool_flag(sk, SOCK_RXQ_OVFL, valbool);
break;
default:
ret = -ENOPROTOOPT;
@@ -1155,7 +1155,7 @@ static void __sk_free(struct sock *sk)
atomic_read(&sk->sk_wmem_alloc) == 0);
if (filter) {
sk_filter_uncharge(sk, filter);
- rcu_assign_pointer(sk->sk_filter, NULL);
+ RCU_INIT_POINTER(sk->sk_filter, NULL);
}
sock_disable_timestamp(sk, SOCK_TIMESTAMP);
@@ -1257,6 +1257,7 @@ struct sock *sk_clone(const struct sock *sk, const gfp_t priority)
/* It is still raw copy of parent, so invalidate
* destructor and make plain sk_free() */
newsk->sk_destruct = NULL;
+ bh_unlock_sock(newsk);
sk_free(newsk);
newsk = NULL;
goto out;
@@ -1530,7 +1531,6 @@ struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len,
skb_shinfo(skb)->nr_frags = npages;
for (i = 0; i < npages; i++) {
struct page *page;
- skb_frag_t *frag;
page = alloc_pages(sk->sk_allocation, 0);
if (!page) {
@@ -1540,12 +1540,11 @@ struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len,
goto failure;
}
- frag = &skb_shinfo(skb)->frags[i];
- frag->page = page;
- frag->page_offset = 0;
- frag->size = (data_len >= PAGE_SIZE ?
- PAGE_SIZE :
- data_len);
+ __skb_fill_page_desc(skb, i,
+ page, 0,
+ (data_len >= PAGE_SIZE ?
+ PAGE_SIZE :
+ data_len));
data_len -= PAGE_SIZE;
}
@@ -1736,6 +1735,8 @@ suppress_allocation:
return 1;
}
+ trace_sock_exceed_buf_limit(sk, prot, allocated);
+
/* Alas. Undo changes. */
sk->sk_forward_alloc -= amt * SK_MEM_QUANTUM;
atomic_long_sub(amt, prot->memory_allocated);
diff --git a/net/core/timestamping.c b/net/core/timestamping.c
index 7e7ca375d431..661b5a40ec10 100644
--- a/net/core/timestamping.c
+++ b/net/core/timestamping.c
@@ -21,6 +21,7 @@
#include <linux/phy.h>
#include <linux/ptp_classify.h>
#include <linux/skbuff.h>
+#include <linux/export.h>
static struct sock_filter ptp_filter[] = {
PTP_FILTER
@@ -57,9 +58,13 @@ void skb_clone_tx_timestamp(struct sk_buff *skb)
case PTP_CLASS_V2_VLAN:
phydev = skb->dev->phydev;
if (likely(phydev->drv->txtstamp)) {
+ if (!atomic_inc_not_zero(&sk->sk_refcnt))
+ return;
clone = skb_clone(skb, GFP_ATOMIC);
- if (!clone)
+ if (!clone) {
+ sock_put(sk);
return;
+ }
clone->sk = sk;
phydev->drv->txtstamp(phydev, clone, type);
}
@@ -68,6 +73,7 @@ void skb_clone_tx_timestamp(struct sk_buff *skb)
break;
}
}
+EXPORT_SYMBOL_GPL(skb_clone_tx_timestamp);
void skb_complete_tx_timestamp(struct sk_buff *skb,
struct skb_shared_hwtstamps *hwtstamps)
@@ -76,8 +82,11 @@ void skb_complete_tx_timestamp(struct sk_buff *skb,
struct sock_exterr_skb *serr;
int err;
- if (!hwtstamps)
+ if (!hwtstamps) {
+ sock_put(sk);
+ kfree_skb(skb);
return;
+ }
*skb_hwtstamps(skb) = *hwtstamps;
serr = SKB_EXT_ERR(skb);
@@ -86,6 +95,7 @@ void skb_complete_tx_timestamp(struct sk_buff *skb,
serr->ee.ee_origin = SO_EE_ORIGIN_TIMESTAMPING;
skb->sk = NULL;
err = sock_queue_err_skb(sk, skb);
+ sock_put(sk);
if (err)
kfree_skb(skb);
}
@@ -121,6 +131,7 @@ bool skb_defer_rx_timestamp(struct sk_buff *skb)
return false;
}
+EXPORT_SYMBOL_GPL(skb_defer_rx_timestamp);
void __init skb_timestamping_init(void)
{
diff --git a/net/core/user_dma.c b/net/core/user_dma.c
index 25d717ebc92e..1b5fefdb8198 100644
--- a/net/core/user_dma.c
+++ b/net/core/user_dma.c
@@ -27,6 +27,7 @@
#include <linux/dmaengine.h>
#include <linux/socket.h>
+#include <linux/export.h>
#include <net/tcp.h>
#include <net/netdma.h>
@@ -71,14 +72,14 @@ int dma_skb_copy_datagram_iovec(struct dma_chan *chan,
/* Copy paged appendix. Hmm... why does this look so complicated? */
for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
int end;
+ const skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
WARN_ON(start > offset + len);
- end = start + skb_shinfo(skb)->frags[i].size;
+ end = start + skb_frag_size(frag);
copy = end - offset;
if (copy > 0) {
- skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
- struct page *page = frag->page;
+ struct page *page = skb_frag_page(frag);
if (copy > len)
copy = len;
generated by cgit v1.2.3 (git 2.51.0) at 2025-09-25 04:34:29 +0000