aboutsummaryrefslogtreecommitdiffstats
path: root/net/core
diff options
context:
space:
mode:
Diffstat (limited to 'net/core')
-rw-r--r--net/core/dev.c53
-rw-r--r--net/core/filter.c2
-rw-r--r--net/core/flow.c132
-rw-r--r--net/core/flow_dissector.c24
-rw-r--r--net/core/neighbour.c9
-rw-r--r--net/core/net-sysfs.c11
-rw-r--r--net/core/netpoll.c585
-rw-r--r--net/core/pktgen.c32
-rw-r--r--net/core/request_sock.c1
-rw-r--r--net/core/rtnetlink.c107
-rw-r--r--net/core/skbuff.c166
11 files changed, 321 insertions, 801 deletions
diff --git a/net/core/dev.c b/net/core/dev.c
index 45fa2f11f84d..cf92139b229c 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1245,7 +1245,7 @@ static int __dev_open(struct net_device *dev)
* If we don't do this there is a chance ndo_poll_controller
* or ndo_poll may be running while we open the device
*/
- netpoll_rx_disable(dev);
+ netpoll_poll_disable(dev);
ret = call_netdevice_notifiers(NETDEV_PRE_UP, dev);
ret = notifier_to_errno(ret);
@@ -1260,7 +1260,7 @@ static int __dev_open(struct net_device *dev)
if (!ret && ops->ndo_open)
ret = ops->ndo_open(dev);
- netpoll_rx_enable(dev);
+ netpoll_poll_enable(dev);
if (ret)
clear_bit(__LINK_STATE_START, &dev->state);
@@ -1313,6 +1313,9 @@ static int __dev_close_many(struct list_head *head)
might_sleep();
list_for_each_entry(dev, head, close_list) {
+ /* Temporarily disable netpoll until the interface is down */
+ netpoll_poll_disable(dev);
+
call_netdevice_notifiers(NETDEV_GOING_DOWN, dev);
clear_bit(__LINK_STATE_START, &dev->state);
@@ -1343,6 +1346,7 @@ static int __dev_close_many(struct list_head *head)
dev->flags &= ~IFF_UP;
net_dmaengine_put();
+ netpoll_poll_enable(dev);
}
return 0;
@@ -1353,14 +1357,10 @@ static int __dev_close(struct net_device *dev)
int retval;
LIST_HEAD(single);
- /* Temporarily disable netpoll until the interface is down */
- netpoll_rx_disable(dev);
-
list_add(&dev->close_list, &single);
retval = __dev_close_many(&single);
list_del(&single);
- netpoll_rx_enable(dev);
return retval;
}
@@ -1398,14 +1398,9 @@ int dev_close(struct net_device *dev)
if (dev->flags & IFF_UP) {
LIST_HEAD(single);
- /* Block netpoll rx while the interface is going down */
- netpoll_rx_disable(dev);
-
list_add(&dev->close_list, &single);
dev_close_many(&single);
list_del(&single);
-
- netpoll_rx_enable(dev);
}
return 0;
}
@@ -2885,6 +2880,7 @@ recursion_alert:
rc = -ENETDOWN;
rcu_read_unlock_bh();
+ atomic_long_inc(&dev->tx_dropped);
kfree_skb(skb);
return rc;
out:
@@ -2957,7 +2953,7 @@ set_rps_cpu(struct net_device *dev, struct sk_buff *skb,
flow_table = rcu_dereference(rxqueue->rps_flow_table);
if (!flow_table)
goto out;
- flow_id = skb->rxhash & flow_table->mask;
+ flow_id = skb_get_hash(skb) & flow_table->mask;
rc = dev->netdev_ops->ndo_rx_flow_steer(dev, skb,
rxq_index, flow_id);
if (rc < 0)
@@ -2991,6 +2987,7 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb,
struct rps_sock_flow_table *sock_flow_table;
int cpu = -1;
u16 tcpu;
+ u32 hash;
if (skb_rx_queue_recorded(skb)) {
u16 index = skb_get_rx_queue(skb);
@@ -3019,7 +3016,8 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb,
}
skb_reset_network_header(skb);
- if (!skb_get_hash(skb))
+ hash = skb_get_hash(skb);
+ if (!hash)
goto done;
flow_table = rcu_dereference(rxqueue->rps_flow_table);
@@ -3028,11 +3026,10 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb,
u16 next_cpu;
struct rps_dev_flow *rflow;
- rflow = &flow_table->flows[skb->rxhash & flow_table->mask];
+ rflow = &flow_table->flows[hash & flow_table->mask];
tcpu = rflow->cpu;
- next_cpu = sock_flow_table->ents[skb->rxhash &
- sock_flow_table->mask];
+ next_cpu = sock_flow_table->ents[hash & sock_flow_table->mask];
/*
* If the desired CPU (where last recvmsg was done) is
@@ -3061,7 +3058,7 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb,
}
if (map) {
- tcpu = map->cpus[((u64) skb->rxhash * map->len) >> 32];
+ tcpu = map->cpus[((u64) hash * map->len) >> 32];
if (cpu_online(tcpu)) {
cpu = tcpu;
@@ -3236,10 +3233,6 @@ static int netif_rx_internal(struct sk_buff *skb)
{
int ret;
- /* if netpoll wants it, pretend we never saw it */
- if (netpoll_rx(skb))
- return NET_RX_DROP;
-
net_timestamp_check(netdev_tstamp_prequeue, skb);
trace_netif_rx(skb);
@@ -3500,11 +3493,11 @@ EXPORT_SYMBOL_GPL(netdev_rx_handler_unregister);
static bool skb_pfmemalloc_protocol(struct sk_buff *skb)
{
switch (skb->protocol) {
- case __constant_htons(ETH_P_ARP):
- case __constant_htons(ETH_P_IP):
- case __constant_htons(ETH_P_IPV6):
- case __constant_htons(ETH_P_8021Q):
- case __constant_htons(ETH_P_8021AD):
+ case htons(ETH_P_ARP):
+ case htons(ETH_P_IP):
+ case htons(ETH_P_IPV6):
+ case htons(ETH_P_8021Q):
+ case htons(ETH_P_8021AD):
return true;
default:
return false;
@@ -3525,10 +3518,6 @@ static int __netif_receive_skb_core(struct sk_buff *skb, bool pfmemalloc)
trace_netif_receive_skb(skb);
- /* if we've gotten here through NAPI, check netpoll */
- if (netpoll_receive_skb(skb))
- goto out;
-
orig_dev = skb->dev;
skb_reset_network_header(skb);
@@ -3655,7 +3644,6 @@ drop:
unlock:
rcu_read_unlock();
-out:
return ret;
}
@@ -3880,7 +3868,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
int same_flow;
enum gro_result ret;
- if (!(skb->dev->features & NETIF_F_GRO) || netpoll_rx_on(skb))
+ if (!(skb->dev->features & NETIF_F_GRO))
goto normal;
if (skb_is_gso(skb) || skb_has_frag_list(skb))
@@ -6251,6 +6239,7 @@ struct rtnl_link_stats64 *dev_get_stats(struct net_device *dev,
netdev_stats_to_stats64(storage, &dev->stats);
}
storage->rx_dropped += atomic_long_read(&dev->rx_dropped);
+ storage->tx_dropped += atomic_long_read(&dev->tx_dropped);
return storage;
}
EXPORT_SYMBOL(dev_get_stats);
diff --git a/net/core/filter.c b/net/core/filter.c
index ad30d626a5bd..65b75966e206 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -336,7 +336,7 @@ load_b:
A = skb->dev->type;
continue;
case BPF_S_ANC_RXHASH:
- A = skb->rxhash;
+ A = skb->hash;
continue;
case BPF_S_ANC_CPU:
A = raw_smp_processor_id();
diff --git a/net/core/flow.c b/net/core/flow.c
index dfa602ceb8cd..31cfb365e0c6 100644
--- a/net/core/flow.c
+++ b/net/core/flow.c
@@ -24,6 +24,7 @@
#include <net/flow.h>
#include <linux/atomic.h>
#include <linux/security.h>
+#include <net/net_namespace.h>
struct flow_cache_entry {
union {
@@ -38,37 +39,14 @@ struct flow_cache_entry {
struct flow_cache_object *object;
};
-struct flow_cache_percpu {
- struct hlist_head *hash_table;
- int hash_count;
- u32 hash_rnd;
- int hash_rnd_recalc;
- struct tasklet_struct flush_tasklet;
-};
-
struct flow_flush_info {
struct flow_cache *cache;
atomic_t cpuleft;
struct completion completion;
};
-struct flow_cache {
- u32 hash_shift;
- struct flow_cache_percpu __percpu *percpu;
- struct notifier_block hotcpu_notifier;
- int low_watermark;
- int high_watermark;
- struct timer_list rnd_timer;
-};
-
-atomic_t flow_cache_genid = ATOMIC_INIT(0);
-EXPORT_SYMBOL(flow_cache_genid);
-static struct flow_cache flow_cache_global;
static struct kmem_cache *flow_cachep __read_mostly;
-static DEFINE_SPINLOCK(flow_cache_gc_lock);
-static LIST_HEAD(flow_cache_gc_list);
-
#define flow_cache_hash_size(cache) (1 << (cache)->hash_shift)
#define FLOW_HASH_RND_PERIOD (10 * 60 * HZ)
@@ -84,16 +62,18 @@ static void flow_cache_new_hashrnd(unsigned long arg)
add_timer(&fc->rnd_timer);
}
-static int flow_entry_valid(struct flow_cache_entry *fle)
+static int flow_entry_valid(struct flow_cache_entry *fle,
+ struct netns_xfrm *xfrm)
{
- if (atomic_read(&flow_cache_genid) != fle->genid)
+ if (atomic_read(&xfrm->flow_cache_genid) != fle->genid)
return 0;
if (fle->object && !fle->object->ops->check(fle->object))
return 0;
return 1;
}
-static void flow_entry_kill(struct flow_cache_entry *fle)
+static void flow_entry_kill(struct flow_cache_entry *fle,
+ struct netns_xfrm *xfrm)
{
if (fle->object)
fle->object->ops->delete(fle->object);
@@ -104,26 +84,28 @@ static void flow_cache_gc_task(struct work_struct *work)
{
struct list_head gc_list;
struct flow_cache_entry *fce, *n;
+ struct netns_xfrm *xfrm = container_of(work, struct netns_xfrm,
+ flow_cache_gc_work);
INIT_LIST_HEAD(&gc_list);
- spin_lock_bh(&flow_cache_gc_lock);
- list_splice_tail_init(&flow_cache_gc_list, &gc_list);
- spin_unlock_bh(&flow_cache_gc_lock);
+ spin_lock_bh(&xfrm->flow_cache_gc_lock);
+ list_splice_tail_init(&xfrm->flow_cache_gc_list, &gc_list);
+ spin_unlock_bh(&xfrm->flow_cache_gc_lock);
list_for_each_entry_safe(fce, n, &gc_list, u.gc_list)
- flow_entry_kill(fce);
+ flow_entry_kill(fce, xfrm);
}
-static DECLARE_WORK(flow_cache_gc_work, flow_cache_gc_task);
static void flow_cache_queue_garbage(struct flow_cache_percpu *fcp,
- int deleted, struct list_head *gc_list)
+ int deleted, struct list_head *gc_list,
+ struct netns_xfrm *xfrm)
{
if (deleted) {
fcp->hash_count -= deleted;
- spin_lock_bh(&flow_cache_gc_lock);
- list_splice_tail(gc_list, &flow_cache_gc_list);
- spin_unlock_bh(&flow_cache_gc_lock);
- schedule_work(&flow_cache_gc_work);
+ spin_lock_bh(&xfrm->flow_cache_gc_lock);
+ list_splice_tail(gc_list, &xfrm->flow_cache_gc_list);
+ spin_unlock_bh(&xfrm->flow_cache_gc_lock);
+ schedule_work(&xfrm->flow_cache_gc_work);
}
}
@@ -135,6 +117,8 @@ static void __flow_cache_shrink(struct flow_cache *fc,
struct hlist_node *tmp;
LIST_HEAD(gc_list);
int i, deleted = 0;
+ struct netns_xfrm *xfrm = container_of(fc, struct netns_xfrm,
+ flow_cache_global);
for (i = 0; i < flow_cache_hash_size(fc); i++) {
int saved = 0;
@@ -142,7 +126,7 @@ static void __flow_cache_shrink(struct flow_cache *fc,
hlist_for_each_entry_safe(fle, tmp,
&fcp->hash_table[i], u.hlist) {
if (saved < shrink_to &&
- flow_entry_valid(fle)) {
+ flow_entry_valid(fle, xfrm)) {
saved++;
} else {
deleted++;
@@ -152,7 +136,7 @@ static void __flow_cache_shrink(struct flow_cache *fc,
}
}
- flow_cache_queue_garbage(fcp, deleted, &gc_list);
+ flow_cache_queue_garbage(fcp, deleted, &gc_list, xfrm);
}
static void flow_cache_shrink(struct flow_cache *fc,
@@ -208,7 +192,7 @@ struct flow_cache_object *
flow_cache_lookup(struct net *net, const struct flowi *key, u16 family, u8 dir,
flow_resolve_t resolver, void *ctx)
{
- struct flow_cache *fc = &flow_cache_global;
+ struct flow_cache *fc = &net->xfrm.flow_cache_global;
struct flow_cache_percpu *fcp;
struct flow_cache_entry *fle, *tfle;
struct flow_cache_object *flo;
@@ -258,7 +242,7 @@ flow_cache_lookup(struct net *net, const struct flowi *key, u16 family, u8 dir,
hlist_add_head(&fle->u.hlist, &fcp->hash_table[hash]);
fcp->hash_count++;
}
- } else if (likely(fle->genid == atomic_read(&flow_cache_genid))) {
+ } else if (likely(fle->genid == atomic_read(&net->xfrm.flow_cache_genid))) {
flo = fle->object;
if (!flo)
goto ret_object;
@@ -279,7 +263,7 @@ nocache:
}
flo = resolver(net, key, family, dir, flo, ctx);
if (fle) {
- fle->genid = atomic_read(&flow_cache_genid);
+ fle->genid = atomic_read(&net->xfrm.flow_cache_genid);
if (!IS_ERR(flo))
fle->object = flo;
else
@@ -303,12 +287,14 @@ static void flow_cache_flush_tasklet(unsigned long data)
struct hlist_node *tmp;
LIST_HEAD(gc_list);
int i, deleted = 0;
+ struct netns_xfrm *xfrm = container_of(fc, struct netns_xfrm,
+ flow_cache_global);
fcp = this_cpu_ptr(fc->percpu);
for (i = 0; i < flow_cache_hash_size(fc); i++) {
hlist_for_each_entry_safe(fle, tmp,
&fcp->hash_table[i], u.hlist) {
- if (flow_entry_valid(fle))
+ if (flow_entry_valid(fle, xfrm))
continue;
deleted++;
@@ -317,7 +303,7 @@ static void flow_cache_flush_tasklet(unsigned long data)
}
}
- flow_cache_queue_garbage(fcp, deleted, &gc_list);
+ flow_cache_queue_garbage(fcp, deleted, &gc_list, xfrm);
if (atomic_dec_and_test(&info->cpuleft))
complete(&info->completion);
@@ -351,10 +337,9 @@ static void flow_cache_flush_per_cpu(void *data)
tasklet_schedule(tasklet);
}
-void flow_cache_flush(void)
+void flow_cache_flush(struct net *net)
{
struct flow_flush_info info;
- static DEFINE_MUTEX(flow_flush_sem);
cpumask_var_t mask;
int i, self;
@@ -365,8 +350,8 @@ void flow_cache_flush(void)
/* Don't want cpus going down or up during this. */
get_online_cpus();
- mutex_lock(&flow_flush_sem);
- info.cache = &flow_cache_global;
+ mutex_lock(&net->xfrm.flow_flush_sem);
+ info.cache = &net->xfrm.flow_cache_global;
for_each_online_cpu(i)
if (!flow_cache_percpu_empty(info.cache, i))
cpumask_set_cpu(i, mask);
@@ -386,21 +371,23 @@ void flow_cache_flush(void)
wait_for_completion(&info.completion);
done:
- mutex_unlock(&flow_flush_sem);
+ mutex_unlock(&net->xfrm.flow_flush_sem);
put_online_cpus();
free_cpumask_var(mask);
}
static void flow_cache_flush_task(struct work_struct *work)
{
- flow_cache_flush();
-}
+ struct netns_xfrm *xfrm = container_of(work, struct netns_xfrm,
+ flow_cache_gc_work);
+ struct net *net = container_of(xfrm, struct net, xfrm);
-static DECLARE_WORK(flow_cache_flush_work, flow_cache_flush_task);
+ flow_cache_flush(net);
+}
-void flow_cache_flush_deferred(void)
+void flow_cache_flush_deferred(struct net *net)
{
- schedule_work(&flow_cache_flush_work);
+ schedule_work(&net->xfrm.flow_cache_flush_work);
}
static int flow_cache_cpu_prepare(struct flow_cache *fc, int cpu)
@@ -425,7 +412,8 @@ static int flow_cache_cpu(struct notifier_block *nfb,
unsigned long action,
void *hcpu)
{
- struct flow_cache *fc = container_of(nfb, struct flow_cache, hotcpu_notifier);
+ struct flow_cache *fc = container_of(nfb, struct flow_cache,
+ hotcpu_notifier);
int res, cpu = (unsigned long) hcpu;
struct flow_cache_percpu *fcp = per_cpu_ptr(fc->percpu, cpu);
@@ -444,9 +432,20 @@ static int flow_cache_cpu(struct notifier_block *nfb,
return NOTIFY_OK;
}
-static int __init flow_cache_init(struct flow_cache *fc)
+int flow_cache_init(struct net *net)
{
int i;
+ struct flow_cache *fc = &net->xfrm.flow_cache_global;
+
+ if (!flow_cachep)
+ flow_cachep = kmem_cache_create("flow_cache",
+ sizeof(struct flow_cache_entry),
+ 0, SLAB_PANIC, NULL);
+ spin_lock_init(&net->xfrm.flow_cache_gc_lock);
+ INIT_LIST_HEAD(&net->xfrm.flow_cache_gc_list);
+ INIT_WORK(&net->xfrm.flow_cache_gc_work, flow_cache_gc_task);
+ INIT_WORK(&net->xfrm.flow_cache_flush_work, flow_cache_flush_task);
+ mutex_init(&net->xfrm.flow_flush_sem);
fc->hash_shift = 10;
fc->low_watermark = 2 * flow_cache_hash_size(fc);
@@ -484,14 +483,23 @@ err:
return -ENOMEM;
}
+EXPORT_SYMBOL(flow_cache_init);
-static int __init flow_cache_init_global(void)
+void flow_cache_fini(struct net *net)
{
- flow_cachep = kmem_cache_create("flow_cache",
- sizeof(struct flow_cache_entry),
- 0, SLAB_PANIC, NULL);
+ int i;
+ struct flow_cache *fc = &net->xfrm.flow_cache_global;
- return flow_cache_init(&flow_cache_global);
-}
+ del_timer_sync(&fc->rnd_timer);
+ unregister_hotcpu_notifier(&fc->hotcpu_notifier);
-module_init(flow_cache_init_global);
+ 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;
+}
+EXPORT_SYMBOL(flow_cache_fini);
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index e29e810663d7..107ed12a5323 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -61,7 +61,7 @@ bool skb_flow_dissect(const struct sk_buff *skb, struct flow_keys *flow)
again:
switch (proto) {
- case __constant_htons(ETH_P_IP): {
+ case htons(ETH_P_IP): {
const struct iphdr *iph;
struct iphdr _iph;
ip:
@@ -77,7 +77,7 @@ ip:
iph_to_flow_copy_addrs(flow, iph);
break;
}
- case __constant_htons(ETH_P_IPV6): {
+ case htons(ETH_P_IPV6): {
const struct ipv6hdr *iph;
struct ipv6hdr _iph;
ipv6:
@@ -91,8 +91,8 @@ ipv6:
nhoff += sizeof(struct ipv6hdr);
break;
}
- case __constant_htons(ETH_P_8021AD):
- case __constant_htons(ETH_P_8021Q): {
+ case htons(ETH_P_8021AD):
+ case htons(ETH_P_8021Q): {
const struct vlan_hdr *vlan;
struct vlan_hdr _vlan;
@@ -104,7 +104,7 @@ ipv6:
nhoff += sizeof(*vlan);
goto again;
}
- case __constant_htons(ETH_P_PPP_SES): {
+ case htons(ETH_P_PPP_SES): {
struct {
struct pppoe_hdr hdr;
__be16 proto;
@@ -115,9 +115,9 @@ ipv6:
proto = hdr->proto;
nhoff += PPPOE_SES_HLEN;
switch (proto) {
- case __constant_htons(PPP_IP):
+ case htons(PPP_IP):
goto ip;
- case __constant_htons(PPP_IPV6):
+ case htons(PPP_IPV6):
goto ipv6;
default:
return false;
@@ -203,8 +203,8 @@ static __always_inline u32 __flow_hash_1word(u32 a)
/*
* __skb_get_hash: calculate a flow hash based on src/dst addresses
- * and src/dst port numbers. Sets rxhash in skb to non-zero hash value
- * on success, zero indicates no valid hash. Also, sets l4_rxhash in skb
+ * and src/dst port numbers. Sets hash in skb to non-zero hash value
+ * on success, zero indicates no valid hash. Also, sets l4_hash in skb
* if hash is a canonical 4-tuple hash over transport ports.
*/
void __skb_get_hash(struct sk_buff *skb)
@@ -216,7 +216,7 @@ void __skb_get_hash(struct sk_buff *skb)
return;
if (keys.ports)
- skb->l4_rxhash = 1;
+ skb->l4_hash = 1;
/* get a consistent hash (same value on both flow directions) */
if (((__force u32)keys.dst < (__force u32)keys.src) ||
@@ -232,7 +232,7 @@ void __skb_get_hash(struct sk_buff *skb)
if (!hash)
hash = 1;
- skb->rxhash = hash;
+ skb->hash = hash;
}
EXPORT_SYMBOL(__skb_get_hash);
@@ -344,7 +344,7 @@ static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb)
hash = skb->sk->sk_hash;
else
hash = (__force u16) skb->protocol ^
- skb->rxhash;
+ skb->hash;
hash = __flow_hash_1word(hash);
queue_index = map->queues[
((u64)hash * map->len) >> 32];
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index e16129019c66..8f8a96ef9f3f 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -836,10 +836,10 @@ out:
static __inline__ int neigh_max_probes(struct neighbour *n)
{
struct neigh_parms *p = n->parms;
- return (n->nud_state & NUD_PROBE) ?
- NEIGH_VAR(p, UCAST_PROBES) :
- NEIGH_VAR(p, UCAST_PROBES) + NEIGH_VAR(p, APP_PROBES) +
- NEIGH_VAR(p, MCAST_PROBES);
+ int max_probes = NEIGH_VAR(p, UCAST_PROBES) + NEIGH_VAR(p, APP_PROBES);
+ if (!(n->nud_state & NUD_PROBE))
+ max_probes += NEIGH_VAR(p, MCAST_PROBES);
+ return max_probes;
}
static void neigh_invalidate(struct neighbour *neigh)
@@ -945,6 +945,7 @@ static void neigh_timer_handler(unsigned long arg)
neigh->nud_state = NUD_FAILED;
notify = 1;
neigh_invalidate(neigh);
+ goto out;
}
if (neigh->nud_state & NUD_IN_TIMER) {
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 93886246a0b4..daed9a64c6f6 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -104,6 +104,7 @@ static ssize_t netdev_store(struct device *dev, struct device_attribute *attr,
}
NETDEVICE_SHOW_RO(dev_id, fmt_hex);
+NETDEVICE_SHOW_RO(dev_port, fmt_dec);
NETDEVICE_SHOW_RO(addr_assign_type, fmt_dec);
NETDEVICE_SHOW_RO(addr_len, fmt_dec);
NETDEVICE_SHOW_RO(iflink, fmt_dec);
@@ -373,6 +374,7 @@ static struct attribute *net_class_attrs[] = {
&dev_attr_netdev_group.attr,
&dev_attr_type.attr,
&dev_attr_dev_id.attr,
+ &dev_attr_dev_port.attr,
&dev_attr_iflink.attr,
&dev_attr_ifindex.attr,
&dev_attr_addr_assign_type.attr,
@@ -996,15 +998,12 @@ static struct attribute_group dql_group = {
#endif /* CONFIG_BQL */
#ifdef CONFIG_XPS
-static inline unsigned int get_netdev_queue_index(struct netdev_queue *queue)
+static unsigned int get_netdev_queue_index(struct netdev_queue *queue)
{
struct net_device *dev = queue->dev;
- int i;
-
- for (i = 0; i < dev->num_tx_queues; i++)
- if (queue == &dev->_tx[i])
- break;
+ unsigned int i;
+ i = queue - dev->_tx;
BUG_ON(i >= dev->num_tx_queues);
return i;
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index df9e6b1a9759..ed7740f7a94d 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -46,13 +46,9 @@
static struct sk_buff_head skb_pool;
-static atomic_t trapped;
-
DEFINE_STATIC_SRCU(netpoll_srcu);
#define USEC_PER_POLL 50
-#define NETPOLL_RX_ENABLED 1
-#define NETPOLL_RX_DROP 2
#define MAX_SKB_SIZE \
(sizeof(struct ethhdr) + \
@@ -61,7 +57,6 @@ DEFINE_STATIC_SRCU(netpoll_srcu);
MAX_UDP_CHUNK)
static void zap_completion_queue(void);
-static void netpoll_neigh_reply(struct sk_buff *skb, struct netpoll_info *npinfo);
static void netpoll_async_cleanup(struct work_struct *work);
static unsigned int carrier_timeout = 4;
@@ -74,6 +69,37 @@ module_param(carrier_timeout, uint, 0644);
#define np_notice(np, fmt, ...) \
pr_notice("%s: " fmt, np->name, ##__VA_ARGS__)
+static int netpoll_start_xmit(struct sk_buff *skb, struct net_device *dev,
+ struct netdev_queue *txq)
+{
+ const struct net_device_ops *ops = dev->netdev_ops;
+ int status = NETDEV_TX_OK;
+ netdev_features_t features;
+
+ features = netif_skb_features(skb);
+
+ if (vlan_tx_tag_present(skb) &&
+ !vlan_hw_offload_capable(features, skb->vlan_proto)) {
+ skb = __vlan_put_tag(skb, skb->vlan_proto,
+ vlan_tx_tag_get(skb));
+ if (unlikely(!skb)) {
+ /* This is actually a packet drop, but we
+ * don't want the code that calls this
+ * function to try and operate on a NULL skb.
+ */
+ goto out;
+ }
+ skb->vlan_tci = 0;
+ }
+
+ status = ops->ndo_start_xmit(skb, dev);
+ if (status == NETDEV_TX_OK)
+ txq_trans_update(txq);
+
+out:
+ return status;
+}
+
static void queue_process(struct work_struct *work)
{
struct netpoll_info *npinfo =
@@ -83,51 +109,31 @@ static void queue_process(struct work_struct *work)
while ((skb = skb_dequeue(&npinfo->txq))) {
struct net_device *dev = skb->dev;
- const struct net_device_ops *ops = dev->netdev_ops;
struct netdev_queue *txq;
if (!netif_device_present(dev) || !netif_running(dev)) {
- __kfree_skb(skb);
+ kfree_skb(skb);
continue;
}
txq = netdev_get_tx_queue(dev, skb_get_queue_mapping(skb));
local_irq_save(flags);
- __netif_tx_lock(txq, smp_processor_id());
+ HARD_TX_LOCK(dev, txq, smp_processor_id());
if (netif_xmit_frozen_or_stopped(txq) ||
- ops->ndo_start_xmit(skb, dev) != NETDEV_TX_OK) {
+ netpoll_start_xmit(skb, dev, txq) != NETDEV_TX_OK) {
skb_queue_head(&npinfo->txq, skb);
- __netif_tx_unlock(txq);
+ HARD_TX_UNLOCK(dev, txq);
local_irq_restore(flags);
schedule_delayed_work(&npinfo->tx_work, HZ/10);
return;
}
- __netif_tx_unlock(txq);
+ HARD_TX_UNLOCK(dev, txq);
local_irq_restore(flags);
}
}
-static __sum16 checksum_udp(struct sk_buff *skb, struct udphdr *uh,
- unsigned short ulen, __be32 saddr, __be32 daddr)
-{
- __wsum psum;
-
- if (uh->check == 0 || skb_csum_unnecessary(skb))
- return 0;
-
- psum = csum_tcpudp_nofold(saddr, daddr, ulen, IPPROTO_UDP, 0);
-
- if (skb->ip_summed == CHECKSUM_COMPLETE &&
- !csum_fold(csum_add(psum, skb->csum)))
- return 0;
-
- skb->csum = psum;
-
- return __skb_checksum_complete(skb);
-}
-
/*
* Check whether delayed processing was scheduled for our NIC. If so,
* we attempt to grab the poll lock and use ->poll() to pump the card.
@@ -138,14 +144,8 @@ static __sum16 checksum_udp(struct sk_buff *skb, struct udphdr *uh,
* trylock here and interrupts are already disabled in the softirq
* case. Further, we test the poll_owner to avoid recursion on UP
* systems where the lock doesn't exist.
- *
- * In cases where there is bi-directional communications, reading only
- * one message at a time can lead to packets being dropped by the
- * network adapter, forcing superfluous retries and possibly timeouts.
- * Thus, we set our budget to greater than 1.
*/
-static int poll_one_napi(struct netpoll_info *npinfo,
- struct napi_struct *napi, int budget)
+static int poll_one_napi(struct napi_struct *napi, int budget)
{
int work;
@@ -156,52 +156,35 @@ static int poll_one_napi(struct netpoll_info *npinfo,
if (!test_bit(NAPI_STATE_SCHED, &napi->state))
return budget;
- npinfo->rx_flags |= NETPOLL_RX_DROP;
- atomic_inc(&trapped);
set_bit(NAPI_STATE_NPSVC, &napi->state);
work = napi->poll(napi, budget);
+ WARN_ONCE(work > budget, "%pF exceeded budget in poll\n", napi->poll);
trace_napi_poll(napi);
clear_bit(NAPI_STATE_NPSVC, &napi->state);
- atomic_dec(&trapped);
- npinfo->rx_flags &= ~NETPOLL_RX_DROP;
return budget - work;
}
-static void poll_napi(struct net_device *dev)
+static void poll_napi(struct net_device *dev, int budget)
{
struct napi_struct *napi;
- int budget = 16;
list_for_each_entry(napi, &dev->napi_list, dev_list) {
if (napi->poll_owner != smp_processor_id() &&
spin_trylock(&napi->poll_lock)) {
- budget = poll_one_napi(rcu_dereference_bh(dev->npinfo),
- napi, budget);
+ budget = poll_one_napi(napi, budget);
spin_unlock(&napi->poll_lock);
-
- if (!budget)
- break;
}
}
}
-static void service_neigh_queue(struct netpoll_info *npi)
-{
- if (npi) {
- struct sk_buff *skb;
-
- while ((skb = skb_dequeue(&npi->neigh_tx)))
- netpoll_neigh_reply(skb, npi);
- }
-}
-
static void netpoll_poll_dev(struct net_device *dev)
{
const struct net_device_ops *ops;
struct netpoll_info *ni = rcu_dereference_bh(dev->npinfo);
+ int budget = 0;
/* Don't do any rx activity if the dev_lock mutex is held
* the dev_open/close paths use this to block netpoll activity
@@ -224,31 +207,14 @@ static void netpoll_poll_dev(struct net_device *dev)
/* Process pending work on NIC */
ops->ndo_poll_controller(dev);
- poll_napi(dev);
+ poll_napi(dev, budget);
up(&ni->dev_lock);
- if (dev->flags & IFF_SLAVE) {
- if (ni) {
- struct net_device *bond_dev;
- struct sk_buff *skb;
- struct netpoll_info *bond_ni;
-
- bond_dev = netdev_master_upper_dev_get_rcu(dev);
- bond_ni = rcu_dereference_bh(bond_dev->npinfo);
- while ((skb = skb_dequeue(&ni->neigh_tx))) {
- skb->dev = bond_dev;
- skb_queue_tail(&bond_ni->neigh_tx, skb);
- }
- }
- }
-
- service_neigh_queue(ni);
-
zap_completion_queue();
}
-void netpoll_rx_disable(struct net_device *dev)
+void netpoll_poll_disable(struct net_device *dev)
{
struct netpoll_info *ni;
int idx;
@@ -259,9 +225,9 @@ void netpoll_rx_disable(struct net_device *dev)
down(&ni->dev_lock);
srcu_read_unlock(&netpoll_srcu, idx);
}
-EXPORT_SYMBOL(netpoll_rx_disable);
+EXPORT_SYMBOL(netpoll_poll_disable);
-void netpoll_rx_enable(struct net_device *dev)
+void netpoll_poll_enable(struct net_device *dev)
{
struct netpoll_info *ni;
rcu_read_lock();
@@ -270,7 +236,7 @@ void netpoll_rx_enable(struct net_device *dev)
up(&ni->dev_lock);
rcu_read_unlock();
}
-EXPORT_SYMBOL(netpoll_rx_enable);
+EXPORT_SYMBOL(netpoll_poll_enable);
static void refill_skbs(void)
{
@@ -359,7 +325,6 @@ void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb,
{
int status = NETDEV_TX_BUSY;
unsigned long tries;
- const struct net_device_ops *ops = dev->netdev_ops;
/* It is up to the caller to keep npinfo alive. */
struct netpoll_info *npinfo;
@@ -367,7 +332,7 @@ void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb,
npinfo = rcu_dereference_bh(np->dev->npinfo);
if (!npinfo || !netif_running(dev) || !netif_device_present(dev)) {
- __kfree_skb(skb);
+ dev_kfree_skb_irq(skb);
return;
}
@@ -380,29 +345,11 @@ void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb,
/* try until next clock tick */
for (tries = jiffies_to_usecs(1)/USEC_PER_POLL;
tries > 0; --tries) {
- if (__netif_tx_trylock(txq)) {
- if (!netif_xmit_stopped(txq)) {
- if (vlan_tx_tag_present(skb) &&
- !vlan_hw_offload_capable(netif_skb_features(skb),
- skb->vlan_proto)) {
- skb = __vlan_put_tag(skb, skb->vlan_proto, vlan_tx_tag_get(skb));
- if (unlikely(!skb)) {
- /* This is actually a packet drop, but we
- * don't want the code at the end of this
- * function to try and re-queue a NULL skb.
- */
- status = NETDEV_TX_OK;
- goto unlock_txq;
- }
- skb->vlan_tci = 0;
- }
-
- status = ops->ndo_start_xmit(skb, dev);
- if (status == NETDEV_TX_OK)
- txq_trans_update(txq);
- }
- unlock_txq:
- __netif_tx_unlock(txq);
+ if (HARD_TX_TRYLOCK(dev, txq)) {
+ if (!netif_xmit_stopped(txq))
+ status = netpoll_start_xmit(skb, dev, txq);
+
+ HARD_TX_UNLOCK(dev, txq);
if (status == NETDEV_TX_OK)
break;
@@ -417,7 +364,7 @@ void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb,
WARN_ONCE(!irqs_disabled(),
"netpoll_send_skb_on_dev(): %s enabled interrupts in poll (%pF)\n",
- dev->name, ops->ndo_start_xmit);
+ dev->name, dev->netdev_ops->ndo_start_xmit);
}
@@ -529,384 +476,6 @@ void netpoll_send_udp(struct netpoll *np, const char *msg, int len)
}
EXPORT_SYMBOL(netpoll_send_udp);
-static void netpoll_neigh_reply(struct sk_buff *skb, struct netpoll_info *npinfo)
-{
- int size, type = ARPOP_REPLY;
- __be32 sip, tip;
- unsigned char *sha;
- struct sk_buff *send_skb;
- struct netpoll *np, *tmp;
- unsigned long flags;
- int hlen, tlen;
- int hits = 0, proto;
-
- if (list_empty(&npinfo->rx_np))
- return;
-
- /* Before checking the packet, we do some early
- inspection whether this is interesting at all */
- spin_lock_irqsave(&npinfo->rx_lock, flags);
- list_for_each_entry_safe(np, tmp, &npinfo->rx_np, rx) {
- if (np->dev == skb->dev)
- hits++;
- }
- spin_unlock_irqrestore(&npinfo->rx_lock, flags);
-
- /* No netpoll struct is using this dev */
- if (!hits)
- return;
-
- proto = ntohs(eth_hdr(skb)->h_proto);
- if (proto == ETH_P_ARP) {
- struct arphdr *arp;
- unsigned char *arp_ptr;
- /* No arp on this interface */
- if (skb->dev->flags & IFF_NOARP)
- return;
-
- if (!pskb_may_pull(skb, arp_hdr_len(skb->dev)))
- return;
-
- skb_reset_network_header(skb);
- skb_reset_transport_header(skb);
- arp = arp_hdr(skb);
-
- if ((arp->ar_hrd != htons(ARPHRD_ETHER) &&
- arp->ar_hrd != htons(ARPHRD_IEEE802)) ||
- arp->ar_pro != htons(ETH_P_IP) ||
- arp->ar_op != htons(ARPOP_REQUEST))
- return;
-
- arp_ptr = (unsigned char *)(arp+1);
- /* save the location of the src hw addr */
- sha = arp_ptr;
- arp_ptr += skb->dev->addr_len;
- memcpy(&sip, arp_ptr, 4);
- arp_ptr += 4;
- /* If we actually cared about dst hw addr,
- it would get copied here */
- arp_ptr += skb->dev->addr_len;
- memcpy(&tip, arp_ptr, 4);
-
- /* Should we ignore arp? */
- if (ipv4_is_loopback(tip) || ipv4_is_multicast(tip))
- return;
-
- size = arp_hdr_len(skb->dev);
-
- spin_lock_irqsave(&npinfo->rx_lock, flags);
- list_for_each_entry_safe(np, tmp, &npinfo->rx_np, rx) {
- if (tip != np->local_ip.ip)
- continue;
-
- hlen = LL_RESERVED_SPACE(np->dev);
- tlen = np->dev->needed_tailroom;
- send_skb = find_skb(np, size + hlen + tlen, hlen);
- if (!send_skb)
- continue;
-
- skb_reset_network_header(send_skb);
- arp = (struct arphdr *) skb_put(send_skb, size);
- send_skb->dev = skb->dev;
- send_skb->protocol = htons(ETH_P_ARP);
-
- /* Fill the device header for the ARP frame */
- if (dev_hard_header(send_skb, skb->dev, ETH_P_ARP,
- sha, np->dev->dev_addr,
- send_skb->len) < 0) {
- kfree_skb(send_skb);
- continue;
- }
-
- /*
- * Fill out the arp protocol part.
- *
- * we only support ethernet device type,
- * which (according to RFC 1390) should
- * always equal 1 (Ethernet).
- */
-
- arp->ar_hrd = htons(np->dev->type);
- arp->ar_pro = htons(ETH_P_IP);
- arp->ar_hln = np->dev->addr_len;
- arp->ar_pln = 4;
- arp->ar_op = htons(type);
-
- arp_ptr = (unsigned char *)(arp + 1);
- memcpy(arp_ptr, np->dev->dev_addr, np->dev->addr_len);
- arp_ptr += np->dev->addr_len;
- memcpy(arp_ptr, &tip, 4);
- arp_ptr += 4;
- memcpy(arp_ptr, sha, np->dev->addr_len);
- arp_ptr += np->dev->addr_len;
- memcpy(arp_ptr, &sip, 4);
-
- netpoll_send_skb(np, send_skb);
-
- /* If there are several rx_skb_hooks for the same
- * address we're fine by sending a single reply
- */
- break;
- }
- spin_unlock_irqrestore(&npinfo->rx_lock, flags);
- } else if( proto == ETH_P_IPV6) {
-#if IS_ENABLED(CONFIG_IPV6)
- struct nd_msg *msg;
- u8 *lladdr = NULL;
- struct ipv6hdr *hdr;
- struct icmp6hdr *icmp6h;
- const struct in6_addr *saddr;
- const struct in6_addr *daddr;
- struct inet6_dev *in6_dev = NULL;
- struct in6_addr *target;
-
- in6_dev = in6_dev_get(skb->dev);
- if (!in6_dev || !in6_dev->cnf.accept_ra)
- return;
-
- if (!pskb_may_pull(skb, skb->len))
- return;
-
- msg = (struct nd_msg *)skb_transport_header(skb);
-
- __skb_push(skb, skb->data - skb_transport_header(skb));
-
- if (ipv6_hdr(skb)->hop_limit != 255)
- return;
- if (msg->icmph.icmp6_code != 0)
- return;
- if (msg->icmph.icmp6_type != NDISC_NEIGHBOUR_SOLICITATION)
- return;
-
- saddr = &ipv6_hdr(skb)->saddr;
- daddr = &ipv6_hdr(skb)->daddr;
-
- size = sizeof(struct icmp6hdr) + sizeof(struct in6_addr);
-
- spin_lock_irqsave(&npinfo->rx_lock, flags);
- list_for_each_entry_safe(np, tmp, &npinfo->rx_np, rx) {
- if (!ipv6_addr_equal(daddr, &np->local_ip.in6))
- continue;
-
- hlen = LL_RESERVED_SPACE(np->dev);
- tlen = np->dev->needed_tailroom;
- send_skb = find_skb(np, size + hlen + tlen, hlen);
- if (!send_skb)
- continue;
-
- send_skb->protocol = htons(ETH_P_IPV6);
- send_skb->dev = skb->dev;
-
- skb_reset_network_header(send_skb);
- hdr = (struct ipv6hdr *) skb_put(send_skb, sizeof(struct ipv6hdr));
- *(__be32*)hdr = htonl(0x60000000);
- hdr->payload_len = htons(size);
- hdr->nexthdr = IPPROTO_ICMPV6;
- hdr->hop_limit = 255;
- hdr->saddr = *saddr;
- hdr->daddr = *daddr;
-
- icmp6h = (struct icmp6hdr *) skb_put(send_skb, sizeof(struct icmp6hdr));
- icmp6h->icmp6_type = NDISC_NEIGHBOUR_ADVERTISEMENT;
- icmp6h->icmp6_router = 0;
- icmp6h->icmp6_solicited = 1;
-
- target = (struct in6_addr *) skb_put(send_skb, sizeof(struct in6_addr));
- *target = msg->target;
- icmp6h->icmp6_cksum = csum_ipv6_magic(saddr, daddr, size,
- IPPROTO_ICMPV6,
- csum_partial(icmp6h,
- size, 0));
-
- if (dev_hard_header(send_skb, skb->dev, ETH_P_IPV6,
- lladdr, np->dev->dev_addr,
- send_skb->len) < 0) {
- kfree_skb(send_skb);
- continue;
- }
-
- netpoll_send_skb(np, send_skb);
-
- /* If there are several rx_skb_hooks for the same
- * address, we're fine by sending a single reply
- */
- break;
- }
- spin_unlock_irqrestore(&npinfo->rx_lock, flags);
-#endif
- }
-}
-
-static bool pkt_is_ns(struct sk_buff *skb)
-{
- struct nd_msg *msg;
- struct ipv6hdr *hdr;
-
- if (skb->protocol != htons(ETH_P_IPV6))
- return false;
- if (!pskb_may_pull(skb, sizeof(struct ipv6hdr) + sizeof(struct nd_msg)))
- return false;
-
- msg = (struct nd_msg *)skb_transport_header(skb);
- __skb_push(skb, skb->data - skb_transport_header(skb));
- hdr = ipv6_hdr(skb);
-
- if (hdr->nexthdr != IPPROTO_ICMPV6)
- return false;
- if (hdr->hop_limit != 255)
- return false;
- if (msg->icmph.icmp6_code != 0)
- return false;
- if (msg->icmph.icmp6_type != NDISC_NEIGHBOUR_SOLICITATION)
- return false;
-
- return true;
-}
-
-int __netpoll_rx(struct sk_buff *skb, struct netpoll_info *npinfo)
-{
- int proto, len, ulen, data_len;
- int hits = 0, offset;
- const struct iphdr *iph;
- struct udphdr *uh;
- struct netpoll *np, *tmp;
- uint16_t source;
-
- if (list_empty(&npinfo->rx_np))
- goto out;
-
- if (skb->dev->type != ARPHRD_ETHER)
- goto out;
-
- /* check if netpoll clients need ARP */
- if (skb->protocol == htons(ETH_P_ARP) && atomic_read(&trapped)) {
- skb_queue_tail(&npinfo->neigh_tx, skb);
- return 1;
- } else if (pkt_is_ns(skb) && atomic_read(&trapped)) {
- skb_queue_tail(&npinfo->neigh_tx, skb);
- return 1;
- }
-
- if (skb->protocol == cpu_to_be16(ETH_P_8021Q)) {
- skb = vlan_untag(skb);
- if (unlikely(!skb))
- goto out;
- }
-
- proto = ntohs(eth_hdr(skb)->h_proto);
- if (proto != ETH_P_IP && proto != ETH_P_IPV6)
- goto out;
- if (skb->pkt_type == PACKET_OTHERHOST)
- goto out;
- if (skb_shared(skb))
- goto out;
-
- if (proto == ETH_P_IP) {
- if (!pskb_may_pull(skb, sizeof(struct iphdr)))
- goto out;
- iph = (struct iphdr *)skb->data;
- if (iph->ihl < 5 || iph->version != 4)
- goto out;
- if (!pskb_may_pull(skb, iph->ihl*4))
- goto out;
- iph = (struct iphdr *)skb->data;
- if (ip_fast_csum((u8 *)iph, iph->ihl) != 0)
- goto out;
-
- len = ntohs(iph->tot_len);
- if (skb->len < len || len < iph->ihl*4)
- goto out;
-
- /*
- * Our transport medium may have padded the buffer out.
- * Now We trim to the true length of the frame.
- */
- if (pskb_trim_rcsum(skb, len))
- goto out;
-
- iph = (struct iphdr *)skb->data;
- if (iph->protocol != IPPROTO_UDP)
- goto out;
-
- len -= iph->ihl*4;
- uh = (struct udphdr *)(((char *)iph) + iph->ihl*4);
- offset = (unsigned char *)(uh + 1) - skb->data;
- ulen = ntohs(uh->len);
- data_len = skb->len - offset;
- source = ntohs(uh->source);
-
- if (ulen != len)
- goto out;
- if (checksum_udp(skb, uh, ulen, iph->saddr, iph->daddr))
- goto out;
- list_for_each_entry_safe(np, tmp, &npinfo->rx_np, rx) {
- if (np->local_ip.ip && np->local_ip.ip != iph->daddr)
- continue;
- if (np->remote_ip.ip && np->remote_ip.ip != iph->saddr)
- continue;
- if (np->local_port && np->local_port != ntohs(uh->dest))
- continue;
-
- np->rx_skb_hook(np, source, skb, offset, data_len);
- hits++;
- }
- } else {
-#if IS_ENABLED(CONFIG_IPV6)
- const struct ipv6hdr *ip6h;
-
- if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
- goto out;
- ip6h = (struct ipv6hdr *)skb->data;
- if (ip6h->version != 6)
- goto out;
- len = ntohs(ip6h->payload_len);
- if (!len)
- goto out;
- if (len + sizeof(struct ipv6hdr) > skb->len)
- goto out;
- if (pskb_trim_rcsum(skb, len + sizeof(struct ipv6hdr)))
- goto out;
- ip6h = ipv6_hdr(skb);
- if (!pskb_may_pull(skb, sizeof(struct udphdr)))
- goto out;
- uh = udp_hdr(skb);
- offset = (unsigned char *)(uh + 1) - skb->data;
- ulen = ntohs(uh->len);
- data_len = skb->len - offset;
- source = ntohs(uh->source);
- if (ulen != skb->len)
- goto out;
- if (udp6_csum_init(skb, uh, IPPROTO_UDP))
- goto out;
- list_for_each_entry_safe(np, tmp, &npinfo->rx_np, rx) {
- if (!ipv6_addr_equal(&np->local_ip.in6, &ip6h->daddr))
- continue;
- if (!ipv6_addr_equal(&np->remote_ip.in6, &ip6h->saddr))
- continue;
- if (np->local_port && np->local_port != ntohs(uh->dest))
- continue;
-
- np->rx_skb_hook(np, source, skb, offset, data_len);
- hits++;
- }
-#endif
- }
-
- if (!hits)
- goto out;
-
- kfree_skb(skb);
- return 1;
-
-out:
- if (atomic_read(&trapped)) {
- kfree_skb(skb);
- return 1;
- }
-
- return 0;
-}
-
void netpoll_print_options(struct netpoll *np)
{
np_info(np, "local port %d\n", np->local_port);
@@ -1026,11 +595,10 @@ int netpoll_parse_options(struct netpoll *np, char *opt)
}
EXPORT_SYMBOL(netpoll_parse_options);
-int __netpoll_setup(struct netpoll *np, struct net_device *ndev, gfp_t gfp)
+int __netpoll_setup(struct netpoll *np, struct net_device *ndev)
{
struct netpoll_info *npinfo;
const struct net_device_ops *ops;
- unsigned long flags;
int err;
np->dev = ndev;
@@ -1046,18 +614,13 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev, gfp_t gfp)
}
if (!ndev->npinfo) {
- npinfo = kmalloc(sizeof(*npinfo), gfp);
+ npinfo = kmalloc(sizeof(*npinfo), GFP_KERNEL);
if (!npinfo) {
err = -ENOMEM;
goto out;
}
- npinfo->rx_flags = 0;
- INIT_LIST_HEAD(&npinfo->rx_np);
-
- spin_lock_init(&npinfo->rx_lock);
sema_init(&npinfo->dev_lock, 1);
- skb_queue_head_init(&npinfo->neigh_tx);
skb_queue_head_init(&npinfo->txq);
INIT_DELAYED_WORK(&npinfo->tx_work, queue_process);
@@ -1065,7 +628,7 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev, gfp_t gfp)
ops = np->dev->netdev_ops;
if (ops->ndo_netpoll_setup) {
- err = ops->ndo_netpoll_setup(ndev, npinfo, gfp);
+ err = ops->ndo_netpoll_setup(ndev, npinfo);
if (err)
goto free_npinfo;
}
@@ -1076,13 +639,6 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev, gfp_t gfp)
npinfo->netpoll = np;
- if (np->rx_skb_hook) {
- spin_lock_irqsave(&npinfo->rx_lock, flags);
- npinfo->rx_flags |= NETPOLL_RX_ENABLED;
- list_add_tail(&np->rx, &npinfo->rx_np);
- spin_unlock_irqrestore(&npinfo->rx_lock, flags);
- }
-
/* last thing to do is link it to the net device structure */
rcu_assign_pointer(ndev->npinfo, npinfo);
@@ -1204,7 +760,7 @@ int netpoll_setup(struct netpoll *np)
/* fill up the skb queue */
refill_skbs();
- err = __netpoll_setup(np, ndev, GFP_KERNEL);
+ err = __netpoll_setup(np, ndev);
if (err)
goto put;
@@ -1231,7 +787,6 @@ static void rcu_cleanup_netpoll_info(struct rcu_head *rcu_head)
struct netpoll_info *npinfo =
container_of(rcu_head, struct netpoll_info, rcu);
- skb_queue_purge(&npinfo->neigh_tx);
skb_queue_purge(&npinfo->txq);
/* we can't call cancel_delayed_work_sync here, as we are in softirq */
@@ -1247,7 +802,6 @@ static void rcu_cleanup_netpoll_info(struct rcu_head *rcu_head)
void __netpoll_cleanup(struct netpoll *np)
{
struct netpoll_info *npinfo;
- unsigned long flags;
/* rtnl_dereference would be preferable here but
* rcu_cleanup_netpoll path can put us in here safely without
@@ -1257,14 +811,6 @@ void __netpoll_cleanup(struct netpoll *np)
if (!npinfo)
return;
- if (!list_empty(&npinfo->rx_np)) {
- spin_lock_irqsave(&npinfo->rx_lock, flags);
- list_del(&np->rx);
- if (list_empty(&npinfo->rx_np))
- npinfo->rx_flags &= ~NETPOLL_RX_ENABLED;
- spin_unlock_irqrestore(&npinfo->rx_lock, flags);
- }
-
synchronize_srcu(&netpoll_srcu);
if (atomic_dec_and_test(&npinfo->refcnt)) {
@@ -1274,7 +820,7 @@ 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);
call_rcu_bh(&npinfo->rcu, rcu_cleanup_netpoll_info);
}
}
@@ -1308,18 +854,3 @@ out:
rtnl_unlock();
}
EXPORT_SYMBOL(netpoll_cleanup);
-
-int netpoll_trap(void)
-{
- return atomic_read(&trapped);
-}
-EXPORT_SYMBOL(netpoll_trap);
-
-void netpoll_set_trap(int trap)
-{
- if (trap)
- atomic_inc(&trapped);
- else
- atomic_dec(&trapped);
-}
-EXPORT_SYMBOL(netpoll_set_trap);
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index fdac61cac1bd..d0dac57291af 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -476,23 +476,22 @@ static int pgctrl_show(struct seq_file *seq, void *v)
static ssize_t pgctrl_write(struct file *file, const char __user *buf,
size_t count, loff_t *ppos)
{
- int err = 0;
char data[128];
struct pktgen_net *pn = net_generic(current->nsproxy->net_ns, pg_net_id);
- if (!capable(CAP_NET_ADMIN)) {
- err = -EPERM;
- goto out;
- }
+ if (!capable(CAP_NET_ADMIN))
+ return -EPERM;
+
+ if (count == 0)
+ return -EINVAL;
if (count > sizeof(data))
count = sizeof(data);
- if (copy_from_user(data, buf, count)) {
- err = -EFAULT;
- goto out;
- }
- data[count - 1] = 0; /* Make string */
+ if (copy_from_user(data, buf, count))
+ return -EFAULT;
+
+ data[count - 1] = 0; /* Strip trailing '\n' and terminate string */
if (!strcmp(data, "stop"))
pktgen_stop_all_threads_ifs(pn);
@@ -506,10 +505,7 @@ static ssize_t pgctrl_write(struct file *file, const char __user *buf,
else
pr_warning("Unknown command: %s\n", data);
- err = count;
-
-out:
- return err;
+ return count;
}
static int pgctrl_open(struct inode *inode, struct file *file)
@@ -1251,7 +1247,13 @@ static ssize_t pktgen_if_write(struct file *file,
"Flag -:%s:- unknown\nAvailable flags, (prepend ! to un-set flag):\n%s",
f,
"IPSRC_RND, IPDST_RND, UDPSRC_RND, UDPDST_RND, "
- "MACSRC_RND, MACDST_RND, TXSIZE_RND, IPV6, MPLS_RND, VID_RND, SVID_RND, FLOW_SEQ, IPSEC, NODE_ALLOC\n");
+ "MACSRC_RND, MACDST_RND, TXSIZE_RND, IPV6, "
+ "MPLS_RND, VID_RND, SVID_RND, FLOW_SEQ, "
+ "QUEUE_MAP_RND, QUEUE_MAP_CPU, UDPCSUM, "
+#ifdef CONFIG_XFRM
+ "IPSEC, "
+#endif
+ "NODE_ALLOC\n");
return count;
}
sprintf(pg_result, "OK: flags=0x%x", pkt_dev->flags);
diff --git a/net/core/request_sock.c b/net/core/request_sock.c
index 4425148d2b51..467f326126e0 100644
--- a/net/core/request_sock.c
+++ b/net/core/request_sock.c
@@ -221,5 +221,4 @@ void reqsk_fastopen_remove(struct sock *sk, struct request_sock *req,
out:
spin_unlock_bh(&fastopenq->lock);
sock_put(lsk);
- return;
}
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 120eecc0f5a4..e7c6006bc3ea 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1121,56 +1121,7 @@ nla_put_failure:
return -EMSGSIZE;
}
-static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
-{
- struct net *net = sock_net(skb->sk);
- int h, s_h;
- int idx = 0, s_idx;
- struct net_device *dev;
- struct hlist_head *head;
- struct nlattr *tb[IFLA_MAX+1];
- u32 ext_filter_mask = 0;
-
- s_h = cb->args[0];
- s_idx = cb->args[1];
-
- rcu_read_lock();
- cb->seq = net->dev_base_seq;
-
- if (nlmsg_parse(cb->nlh, sizeof(struct ifinfomsg), tb, IFLA_MAX,
- ifla_policy) >= 0) {
-
- if (tb[IFLA_EXT_MASK])
- ext_filter_mask = nla_get_u32(tb[IFLA_EXT_MASK]);
- }
-
- for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) {
- idx = 0;
- head = &net->dev_index_head[h];
- hlist_for_each_entry_rcu(dev, head, index_hlist) {
- if (idx < s_idx)
- goto cont;
- if (rtnl_fill_ifinfo(skb, dev, RTM_NEWLINK,
- NETLINK_CB(cb->skb).portid,
- cb->nlh->nlmsg_seq, 0,
- NLM_F_MULTI,
- ext_filter_mask) <= 0)
- goto out;
-
- nl_dump_check_consistent(cb, nlmsg_hdr(skb));
-cont:
- idx++;
- }
- }
-out:
- rcu_read_unlock();
- cb->args[1] = idx;
- cb->args[0] = h;
-
- return skb->len;
-}
-
-const struct nla_policy ifla_policy[IFLA_MAX+1] = {
+static const struct nla_policy ifla_policy[IFLA_MAX+1] = {
[IFLA_IFNAME] = { .type = NLA_STRING, .len = IFNAMSIZ-1 },
[IFLA_ADDRESS] = { .type = NLA_BINARY, .len = MAX_ADDR_LEN },
[IFLA_BROADCAST] = { .type = NLA_BINARY, .len = MAX_ADDR_LEN },
@@ -1197,7 +1148,6 @@ const struct nla_policy ifla_policy[IFLA_MAX+1] = {
[IFLA_NUM_RX_QUEUES] = { .type = NLA_U32 },
[IFLA_PHYS_PORT_ID] = { .type = NLA_BINARY, .len = MAX_PHYS_PORT_ID_LEN },
};
-EXPORT_SYMBOL(ifla_policy);
static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = {
[IFLA_INFO_KIND] = { .type = NLA_STRING },
@@ -1235,6 +1185,61 @@ static const struct nla_policy ifla_port_policy[IFLA_PORT_MAX+1] = {
[IFLA_PORT_RESPONSE] = { .type = NLA_U16, },
};
+static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
+{
+ struct net *net = sock_net(skb->sk);
+ int h, s_h;
+ int idx = 0, s_idx;
+ struct net_device *dev;
+ struct hlist_head *head;
+ struct nlattr *tb[IFLA_MAX+1];
+ u32 ext_filter_mask = 0;
+
+ s_h = cb->args[0];
+ s_idx = cb->args[1];
+
+ rcu_read_lock();
+ cb->seq = net->dev_base_seq;
+
+ if (nlmsg_parse(cb->nlh, sizeof(struct ifinfomsg), tb, IFLA_MAX,
+ ifla_policy) >= 0) {
+
+ if (tb[IFLA_EXT_MASK])
+ ext_filter_mask = nla_get_u32(tb[IFLA_EXT_MASK]);
+ }
+
+ for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) {
+ idx = 0;
+ head = &net->dev_index_head[h];
+ hlist_for_each_entry_rcu(dev, head, index_hlist) {
+ if (idx < s_idx)
+ goto cont;
+ if (rtnl_fill_ifinfo(skb, dev, RTM_NEWLINK,
+ NETLINK_CB(cb->skb).portid,
+ cb->nlh->nlmsg_seq, 0,
+ NLM_F_MULTI,
+ ext_filter_mask) <= 0)
+ goto out;
+
+ nl_dump_check_consistent(cb, nlmsg_hdr(skb));
+cont:
+ idx++;
+ }
+ }
+out:
+ rcu_read_unlock();
+ cb->args[1] = idx;
+ cb->args[0] = h;
+
+ return skb->len;
+}
+
+int rtnl_nla_parse_ifla(struct nlattr **tb, const struct nlattr *head, int len)
+{
+ return nla_parse(tb, IFLA_MAX, head, len, ifla_policy);
+}
+EXPORT_SYMBOL(rtnl_nla_parse_ifla);
+
struct net *rtnl_link_get_net(struct net *src_net, struct nlattr *tb[])
{
struct net *net;
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 90b96a11b974..30c7d35dd862 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3300,6 +3300,32 @@ __skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len)
return elt;
}
+/* As compared with skb_to_sgvec, skb_to_sgvec_nomark only map skb to given
+ * sglist without mark the sg which contain last skb data as the end.
+ * So the caller can mannipulate sg list as will when padding new data after
+ * the first call without calling sg_unmark_end to expend sg list.
+ *
+ * Scenario to use skb_to_sgvec_nomark:
+ * 1. sg_init_table
+ * 2. skb_to_sgvec_nomark(payload1)
+ * 3. skb_to_sgvec_nomark(payload2)
+ *
+ * This is equivalent to:
+ * 1. sg_init_table
+ * 2. skb_to_sgvec(payload1)
+ * 3. sg_unmark_end
+ * 4. skb_to_sgvec(payload2)
+ *
+ * When mapping mutilple payload conditionally, skb_to_sgvec_nomark
+ * is more preferable.
+ */
+int skb_to_sgvec_nomark(struct sk_buff *skb, struct scatterlist *sg,
+ int offset, int len)
+{
+ return __skb_to_sgvec(skb, sg, offset, len);
+}
+EXPORT_SYMBOL_GPL(skb_to_sgvec_nomark);
+
int skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len)
{
int nsg = __skb_to_sgvec(skb, sg, offset, len);
@@ -3562,15 +3588,47 @@ static int skb_maybe_pull_tail(struct sk_buff *skb, unsigned int len,
return 0;
}
+#define MAX_TCP_HDR_LEN (15 * 4)
+
+static __sum16 *skb_checksum_setup_ip(struct sk_buff *skb,
+ typeof(IPPROTO_IP) proto,
+ unsigned int off)
+{
+ switch (proto) {
+ int err;
+
+ case IPPROTO_TCP:
+ err = skb_maybe_pull_tail(skb, off + sizeof(struct tcphdr),
+ off + MAX_TCP_HDR_LEN);
+ if (!err && !skb_partial_csum_set(skb, off,
+ offsetof(struct tcphdr,
+ check)))
+ err = -EPROTO;
+ return err ? ERR_PTR(err) : &tcp_hdr(skb)->check;
+
+ case IPPROTO_UDP:
+ err = skb_maybe_pull_tail(skb, off + sizeof(struct udphdr),
+ off + sizeof(struct udphdr));
+ if (!err && !skb_partial_csum_set(skb, off,
+ offsetof(struct udphdr,
+ check)))
+ err = -EPROTO;
+ return err ? ERR_PTR(err) : &udp_hdr(skb)->check;
+ }
+
+ return ERR_PTR(-EPROTO);
+}
+
/* This value should be large enough to cover a tagged ethernet header plus
* maximally sized IP and TCP or UDP headers.
*/
#define MAX_IP_HDR_LEN 128
-static int skb_checksum_setup_ip(struct sk_buff *skb, bool recalculate)
+static int skb_checksum_setup_ipv4(struct sk_buff *skb, bool recalculate)
{
unsigned int off;
bool fragment;
+ __sum16 *csum;
int err;
fragment = false;
@@ -3591,51 +3649,15 @@ static int skb_checksum_setup_ip(struct sk_buff *skb, bool recalculate)
if (fragment)
goto out;
- switch (ip_hdr(skb)->protocol) {
- case IPPROTO_TCP:
- err = skb_maybe_pull_tail(skb,
- off + sizeof(struct tcphdr),
- MAX_IP_HDR_LEN);
- if (err < 0)
- goto out;
-
- if (!skb_partial_csum_set(skb, off,
- offsetof(struct tcphdr, check))) {
- err = -EPROTO;
- goto out;
- }
-
- if (recalculate)
- tcp_hdr(skb)->check =
- ~csum_tcpudp_magic(ip_hdr(skb)->saddr,
- ip_hdr(skb)->daddr,
- skb->len - off,
- IPPROTO_TCP, 0);
- break;
- case IPPROTO_UDP:
- err = skb_maybe_pull_tail(skb,
- off + sizeof(struct udphdr),
- MAX_IP_HDR_LEN);
- if (err < 0)
- goto out;
-
- if (!skb_partial_csum_set(skb, off,
- offsetof(struct udphdr, check))) {
- err = -EPROTO;
- goto out;
- }
-
- if (recalculate)
- udp_hdr(skb)->check =
- ~csum_tcpudp_magic(ip_hdr(skb)->saddr,
- ip_hdr(skb)->daddr,
- skb->len - off,
- IPPROTO_UDP, 0);
- break;
- default:
- goto out;
- }
+ csum = skb_checksum_setup_ip(skb, ip_hdr(skb)->protocol, off);
+ if (IS_ERR(csum))
+ return PTR_ERR(csum);
+ if (recalculate)
+ *csum = ~csum_tcpudp_magic(ip_hdr(skb)->saddr,
+ ip_hdr(skb)->daddr,
+ skb->len - off,
+ ip_hdr(skb)->protocol, 0);
err = 0;
out:
@@ -3658,6 +3680,7 @@ static int skb_checksum_setup_ipv6(struct sk_buff *skb, bool recalculate)
unsigned int len;
bool fragment;
bool done;
+ __sum16 *csum;
fragment = false;
done = false;
@@ -3735,51 +3758,14 @@ static int skb_checksum_setup_ipv6(struct sk_buff *skb, bool recalculate)
if (!done || fragment)
goto out;
- switch (nexthdr) {
- case IPPROTO_TCP:
- err = skb_maybe_pull_tail(skb,
- off + sizeof(struct tcphdr),
- MAX_IPV6_HDR_LEN);
- if (err < 0)
- goto out;
-
- if (!skb_partial_csum_set(skb, off,
- offsetof(struct tcphdr, check))) {
- err = -EPROTO;
- goto out;
- }
-
- if (recalculate)
- tcp_hdr(skb)->check =
- ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr,
- &ipv6_hdr(skb)->daddr,
- skb->len - off,
- IPPROTO_TCP, 0);
- break;
- case IPPROTO_UDP:
- err = skb_maybe_pull_tail(skb,
- off + sizeof(struct udphdr),
- MAX_IPV6_HDR_LEN);
- if (err < 0)
- goto out;
-
- if (!skb_partial_csum_set(skb, off,
- offsetof(struct udphdr, check))) {
- err = -EPROTO;
- goto out;
- }
-
- if (recalculate)
- udp_hdr(skb)->check =
- ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr,
- &ipv6_hdr(skb)->daddr,
- skb->len - off,
- IPPROTO_UDP, 0);
- break;
- default:
- goto out;
- }
+ csum = skb_checksum_setup_ip(skb, nexthdr, off);
+ if (IS_ERR(csum))
+ return PTR_ERR(csum);
+ if (recalculate)
+ *csum = ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr,
+ &ipv6_hdr(skb)->daddr,
+ skb->len - off, nexthdr, 0);
err = 0;
out:
@@ -3797,7 +3783,7 @@ int skb_checksum_setup(struct sk_buff *skb, bool recalculate)
switch (skb->protocol) {
case htons(ETH_P_IP):
- err = skb_checksum_setup_ip(skb, recalculate);
+ err = skb_checksum_setup_ipv4(skb, recalculate);
break;
case htons(ETH_P_IPV6):
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.