summaryrefslogtreecommitdiffstats
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/af_inet.c12
-rw-r--r--net/ipv4/gre_offload.c14
-rw-r--r--net/ipv4/inetpeer.c428
-rw-r--r--net/ipv4/ip_output.c76
-rw-r--r--net/ipv4/ip_vti.c31
-rw-r--r--net/ipv4/tcp_output.c17
-rw-r--r--net/ipv4/tcp_recovery.c2
-rw-r--r--net/ipv4/udp_offload.c64
-rw-r--r--net/ipv4/xfrm4_policy.c11
9 files changed, 111 insertions, 544 deletions
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 76c2077c3f5b..5ce44fb7d498 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1219,10 +1219,9 @@ EXPORT_SYMBOL(inet_sk_rebuild_header);
struct sk_buff *inet_gso_segment(struct sk_buff *skb,
netdev_features_t features)
{
- bool udpfrag = false, fixedid = false, gso_partial, encap;
+ bool fixedid = false, gso_partial, encap;
struct sk_buff *segs = ERR_PTR(-EINVAL);
const struct net_offload *ops;
- unsigned int offset = 0;
struct iphdr *iph;
int proto, tot_len;
int nhoff;
@@ -1257,7 +1256,6 @@ struct sk_buff *inet_gso_segment(struct sk_buff *skb,
segs = ERR_PTR(-EPROTONOSUPPORT);
if (!skb->encapsulation || encap) {
- udpfrag = !!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP);
fixedid = !!(skb_shinfo(skb)->gso_type & SKB_GSO_TCP_FIXEDID);
/* fixed ID is invalid if DF bit is not set */
@@ -1277,13 +1275,7 @@ struct sk_buff *inet_gso_segment(struct sk_buff *skb,
skb = segs;
do {
iph = (struct iphdr *)(skb_mac_header(skb) + nhoff);
- if (udpfrag) {
- iph->frag_off = htons(offset >> 3);
- if (skb->next)
- iph->frag_off |= htons(IP_MF);
- offset += skb->len - nhoff - ihl;
- tot_len = skb->len - nhoff;
- } else if (skb_is_gso(skb)) {
+ if (skb_is_gso(skb)) {
if (!fixedid) {
iph->id = htons(id);
id += skb_shinfo(skb)->gso_segs;
diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c
index d5cac99170b1..416bb304a281 100644
--- a/net/ipv4/gre_offload.c
+++ b/net/ipv4/gre_offload.c
@@ -24,7 +24,7 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
__be16 protocol = skb->protocol;
u16 mac_len = skb->mac_len;
int gre_offset, outer_hlen;
- bool need_csum, ufo, gso_partial;
+ bool need_csum, gso_partial;
if (!skb->encapsulation)
goto out;
@@ -47,20 +47,8 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
need_csum = !!(skb_shinfo(skb)->gso_type & SKB_GSO_GRE_CSUM);
skb->encap_hdr_csum = need_csum;
- ufo = !!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP);
-
features &= skb->dev->hw_enc_features;
- /* The only checksum offload we care about from here on out is the
- * outer one so strip the existing checksum feature flags based
- * on the fact that we will be computing our checksum in software.
- */
- if (ufo) {
- features &= ~NETIF_F_CSUM_MASK;
- if (!need_csum)
- features |= NETIF_F_HW_CSUM;
- }
-
/* segment inner packet. */
segs = skb_mac_gso_segment(skb, features);
if (IS_ERR_OR_NULL(segs)) {
diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c
index c5a117cc6619..337ad41bb80a 100644
--- a/net/ipv4/inetpeer.c
+++ b/net/ipv4/inetpeer.c
@@ -33,7 +33,7 @@
* also be removed if the pool is overloaded i.e. if the total amount of
* entries is greater-or-equal than the threshold.
*
- * Node pool is organised as an AVL tree.
+ * Node pool is organised as an RB tree.
* Such an implementation has been chosen not just for fun. It's a way to
* prevent easy and efficient DoS attacks by creating hash collisions. A huge
* amount of long living nodes in a single hash slot would significantly delay
@@ -45,7 +45,7 @@
* AND reference count being 0.
* 3. Global variable peer_total is modified under the pool lock.
* 4. struct inet_peer fields modification:
- * avl_left, avl_right, avl_parent, avl_height: pool lock
+ * rb_node: pool lock
* refcnt: atomically against modifications on other CPU;
* usually under some other lock to prevent node disappearing
* daddr: unchangeable
@@ -53,30 +53,15 @@
static struct kmem_cache *peer_cachep __read_mostly;
-static LIST_HEAD(gc_list);
-static const int gc_delay = 60 * HZ;
-static struct delayed_work gc_work;
-static DEFINE_SPINLOCK(gc_lock);
-
-#define node_height(x) x->avl_height
-
-#define peer_avl_empty ((struct inet_peer *)&peer_fake_node)
-#define peer_avl_empty_rcu ((struct inet_peer __rcu __force *)&peer_fake_node)
-static const struct inet_peer peer_fake_node = {
- .avl_left = peer_avl_empty_rcu,
- .avl_right = peer_avl_empty_rcu,
- .avl_height = 0
-};
-
void inet_peer_base_init(struct inet_peer_base *bp)
{
- bp->root = peer_avl_empty_rcu;
+ bp->rb_root = RB_ROOT;
seqlock_init(&bp->lock);
bp->total = 0;
}
EXPORT_SYMBOL_GPL(inet_peer_base_init);
-#define PEER_MAXDEPTH 40 /* sufficient for about 2^27 nodes */
+#define PEER_MAX_GC 32
/* Exported for sysctl_net_ipv4. */
int inet_peer_threshold __read_mostly = 65536 + 128; /* start to throw entries more
@@ -84,53 +69,6 @@ int inet_peer_threshold __read_mostly = 65536 + 128; /* start to throw entries m
int inet_peer_minttl __read_mostly = 120 * HZ; /* TTL under high load: 120 sec */
int inet_peer_maxttl __read_mostly = 10 * 60 * HZ; /* usual time to live: 10 min */
-static void inetpeer_gc_worker(struct work_struct *work)
-{
- struct inet_peer *p, *n, *c;
- struct list_head list;
-
- spin_lock_bh(&gc_lock);
- list_replace_init(&gc_list, &list);
- spin_unlock_bh(&gc_lock);
-
- if (list_empty(&list))
- return;
-
- list_for_each_entry_safe(p, n, &list, gc_list) {
-
- if (need_resched())
- cond_resched();
-
- c = rcu_dereference_protected(p->avl_left, 1);
- if (c != peer_avl_empty) {
- list_add_tail(&c->gc_list, &list);
- p->avl_left = peer_avl_empty_rcu;
- }
-
- c = rcu_dereference_protected(p->avl_right, 1);
- if (c != peer_avl_empty) {
- list_add_tail(&c->gc_list, &list);
- p->avl_right = peer_avl_empty_rcu;
- }
-
- n = list_entry(p->gc_list.next, struct inet_peer, gc_list);
-
- if (refcount_read(&p->refcnt) == 1) {
- list_del(&p->gc_list);
- kmem_cache_free(peer_cachep, p);
- }
- }
-
- if (list_empty(&list))
- return;
-
- spin_lock_bh(&gc_lock);
- list_splice(&list, &gc_list);
- spin_unlock_bh(&gc_lock);
-
- schedule_delayed_work(&gc_work, gc_delay);
-}
-
/* Called from ip_output.c:ip_init */
void __init inet_initpeers(void)
{
@@ -153,225 +91,62 @@ void __init inet_initpeers(void)
sizeof(struct inet_peer),
0, SLAB_HWCACHE_ALIGN | SLAB_PANIC,
NULL);
-
- INIT_DEFERRABLE_WORK(&gc_work, inetpeer_gc_worker);
}
-#define rcu_deref_locked(X, BASE) \
- rcu_dereference_protected(X, lockdep_is_held(&(BASE)->lock.lock))
-
-/*
- * Called with local BH disabled and the pool lock held.
- */
-#define lookup(_daddr, _stack, _base) \
-({ \
- struct inet_peer *u; \
- struct inet_peer __rcu **v; \
- \
- stackptr = _stack; \
- *stackptr++ = &_base->root; \
- for (u = rcu_deref_locked(_base->root, _base); \
- u != peer_avl_empty;) { \
- int cmp = inetpeer_addr_cmp(_daddr, &u->daddr); \
- if (cmp == 0) \
- break; \
- if (cmp == -1) \
- v = &u->avl_left; \
- else \
- v = &u->avl_right; \
- *stackptr++ = v; \
- u = rcu_deref_locked(*v, _base); \
- } \
- u; \
-})
-
-/*
- * Called with rcu_read_lock()
- * Because we hold no lock against a writer, its quite possible we fall
- * in an endless loop.
- * But every pointer we follow is guaranteed to be valid thanks to RCU.
- * We exit from this function if number of links exceeds PEER_MAXDEPTH
- */
-static struct inet_peer *lookup_rcu(const struct inetpeer_addr *daddr,
- struct inet_peer_base *base)
+/* Called with rcu_read_lock() or base->lock held */
+static struct inet_peer *lookup(const struct inetpeer_addr *daddr,
+ struct inet_peer_base *base,
+ unsigned int seq,
+ struct inet_peer *gc_stack[],
+ unsigned int *gc_cnt,
+ struct rb_node **parent_p,
+ struct rb_node ***pp_p)
{
- struct inet_peer *u = rcu_dereference(base->root);
- int count = 0;
+ struct rb_node **pp, *parent;
+ struct inet_peer *p;
+
+ pp = &base->rb_root.rb_node;
+ parent = NULL;
+ while (*pp) {
+ int cmp;
- while (u != peer_avl_empty) {
- int cmp = inetpeer_addr_cmp(daddr, &u->daddr);
+ parent = rcu_dereference_raw(*pp);
+ p = rb_entry(parent, struct inet_peer, rb_node);
+ cmp = inetpeer_addr_cmp(daddr, &p->daddr);
if (cmp == 0) {
- /* Before taking a reference, check if this entry was
- * deleted (refcnt=0)
- */
- if (!refcount_inc_not_zero(&u->refcnt)) {
- u = NULL;
- }
- return u;
+ if (!refcount_inc_not_zero(&p->refcnt))
+ break;
+ return p;
+ }
+ if (gc_stack) {
+ if (*gc_cnt < PEER_MAX_GC)
+ gc_stack[(*gc_cnt)++] = p;
+ } else if (unlikely(read_seqretry(&base->lock, seq))) {
+ break;
}
if (cmp == -1)
- u = rcu_dereference(u->avl_left);
+ pp = &(*pp)->rb_left;
else
- u = rcu_dereference(u->avl_right);
- if (unlikely(++count == PEER_MAXDEPTH))
- break;
+ pp = &(*pp)->rb_right;
}
+ *parent_p = parent;
+ *pp_p = pp;
return NULL;
}
-/* Called with local BH disabled and the pool lock held. */
-#define lookup_rightempty(start, base) \
-({ \
- struct inet_peer *u; \
- struct inet_peer __rcu **v; \
- *stackptr++ = &start->avl_left; \
- v = &start->avl_left; \
- for (u = rcu_deref_locked(*v, base); \
- u->avl_right != peer_avl_empty_rcu;) { \
- v = &u->avl_right; \
- *stackptr++ = v; \
- u = rcu_deref_locked(*v, base); \
- } \
- u; \
-})
-
-/* Called with local BH disabled and the pool lock held.
- * Variable names are the proof of operation correctness.
- * Look into mm/map_avl.c for more detail description of the ideas.
- */
-static void peer_avl_rebalance(struct inet_peer __rcu **stack[],
- struct inet_peer __rcu ***stackend,
- struct inet_peer_base *base)
-{
- struct inet_peer __rcu **nodep;
- struct inet_peer *node, *l, *r;
- int lh, rh;
-
- while (stackend > stack) {
- nodep = *--stackend;
- node = rcu_deref_locked(*nodep, base);
- l = rcu_deref_locked(node->avl_left, base);
- r = rcu_deref_locked(node->avl_right, base);
- lh = node_height(l);
- rh = node_height(r);
- if (lh > rh + 1) { /* l: RH+2 */
- struct inet_peer *ll, *lr, *lrl, *lrr;
- int lrh;
- ll = rcu_deref_locked(l->avl_left, base);
- lr = rcu_deref_locked(l->avl_right, base);
- lrh = node_height(lr);
- if (lrh <= node_height(ll)) { /* ll: RH+1 */
- RCU_INIT_POINTER(node->avl_left, lr); /* lr: RH or RH+1 */
- RCU_INIT_POINTER(node->avl_right, r); /* r: RH */
- node->avl_height = lrh + 1; /* RH+1 or RH+2 */
- RCU_INIT_POINTER(l->avl_left, ll); /* ll: RH+1 */
- RCU_INIT_POINTER(l->avl_right, node); /* node: RH+1 or RH+2 */
- l->avl_height = node->avl_height + 1;
- RCU_INIT_POINTER(*nodep, l);
- } else { /* ll: RH, lr: RH+1 */
- lrl = rcu_deref_locked(lr->avl_left, base);/* lrl: RH or RH-1 */
- lrr = rcu_deref_locked(lr->avl_right, base);/* lrr: RH or RH-1 */
- RCU_INIT_POINTER(node->avl_left, lrr); /* lrr: RH or RH-1 */
- RCU_INIT_POINTER(node->avl_right, r); /* r: RH */
- node->avl_height = rh + 1; /* node: RH+1 */
- RCU_INIT_POINTER(l->avl_left, ll); /* ll: RH */
- RCU_INIT_POINTER(l->avl_right, lrl); /* lrl: RH or RH-1 */
- l->avl_height = rh + 1; /* l: RH+1 */
- RCU_INIT_POINTER(lr->avl_left, l); /* l: RH+1 */
- RCU_INIT_POINTER(lr->avl_right, node); /* node: RH+1 */
- lr->avl_height = rh + 2;
- RCU_INIT_POINTER(*nodep, lr);
- }
- } else if (rh > lh + 1) { /* r: LH+2 */
- struct inet_peer *rr, *rl, *rlr, *rll;
- int rlh;
- rr = rcu_deref_locked(r->avl_right, base);
- rl = rcu_deref_locked(r->avl_left, base);
- rlh = node_height(rl);
- if (rlh <= node_height(rr)) { /* rr: LH+1 */
- RCU_INIT_POINTER(node->avl_right, rl); /* rl: LH or LH+1 */
- RCU_INIT_POINTER(node->avl_left, l); /* l: LH */
- node->avl_height = rlh + 1; /* LH+1 or LH+2 */
- RCU_INIT_POINTER(r->avl_right, rr); /* rr: LH+1 */
- RCU_INIT_POINTER(r->avl_left, node); /* node: LH+1 or LH+2 */
- r->avl_height = node->avl_height + 1;
- RCU_INIT_POINTER(*nodep, r);
- } else { /* rr: RH, rl: RH+1 */
- rlr = rcu_deref_locked(rl->avl_right, base);/* rlr: LH or LH-1 */
- rll = rcu_deref_locked(rl->avl_left, base);/* rll: LH or LH-1 */
- RCU_INIT_POINTER(node->avl_right, rll); /* rll: LH or LH-1 */
- RCU_INIT_POINTER(node->avl_left, l); /* l: LH */
- node->avl_height = lh + 1; /* node: LH+1 */
- RCU_INIT_POINTER(r->avl_right, rr); /* rr: LH */
- RCU_INIT_POINTER(r->avl_left, rlr); /* rlr: LH or LH-1 */
- r->avl_height = lh + 1; /* r: LH+1 */
- RCU_INIT_POINTER(rl->avl_right, r); /* r: LH+1 */
- RCU_INIT_POINTER(rl->avl_left, node); /* node: LH+1 */
- rl->avl_height = lh + 2;
- RCU_INIT_POINTER(*nodep, rl);
- }
- } else {
- node->avl_height = (lh > rh ? lh : rh) + 1;
- }
- }
-}
-
-/* Called with local BH disabled and the pool lock held. */
-#define link_to_pool(n, base) \
-do { \
- n->avl_height = 1; \
- n->avl_left = peer_avl_empty_rcu; \
- n->avl_right = peer_avl_empty_rcu; \
- /* lockless readers can catch us now */ \
- rcu_assign_pointer(**--stackptr, n); \
- peer_avl_rebalance(stack, stackptr, base); \
-} while (0)
-
static void inetpeer_free_rcu(struct rcu_head *head)
{
kmem_cache_free(peer_cachep, container_of(head, struct inet_peer, rcu));
}
-static void unlink_from_pool(struct inet_peer *p, struct inet_peer_base *base,
- struct inet_peer __rcu **stack[PEER_MAXDEPTH])
-{
- struct inet_peer __rcu ***stackptr, ***delp;
-
- if (lookup(&p->daddr, stack, base) != p)
- BUG();
- delp = stackptr - 1; /* *delp[0] == p */
- if (p->avl_left == peer_avl_empty_rcu) {
- *delp[0] = p->avl_right;
- --stackptr;
- } else {
- /* look for a node to insert instead of p */
- struct inet_peer *t;
- t = lookup_rightempty(p, base);
- BUG_ON(rcu_deref_locked(*stackptr[-1], base) != t);
- **--stackptr = t->avl_left;
- /* t is removed, t->daddr > x->daddr for any
- * x in p->avl_left subtree.
- * Put t in the old place of p. */
- RCU_INIT_POINTER(*delp[0], t);
- t->avl_left = p->avl_left;
- t->avl_right = p->avl_right;
- t->avl_height = p->avl_height;
- BUG_ON(delp[1] != &p->avl_left);
- delp[1] = &t->avl_left; /* was &p->avl_left */
- }
- peer_avl_rebalance(stack, stackptr, base);
- base->total--;
- call_rcu(&p->rcu, inetpeer_free_rcu);
-}
-
/* perform garbage collect on all items stacked during a lookup */
-static int inet_peer_gc(struct inet_peer_base *base,
- struct inet_peer __rcu **stack[PEER_MAXDEPTH],
- struct inet_peer __rcu ***stackptr)
+static void inet_peer_gc(struct inet_peer_base *base,
+ struct inet_peer *gc_stack[],
+ unsigned int gc_cnt)
{
- struct inet_peer *p, *gchead = NULL;
+ struct inet_peer *p;
__u32 delta, ttl;
- int cnt = 0;
+ int i;
if (base->total >= inet_peer_threshold)
ttl = 0; /* be aggressive */
@@ -379,43 +154,38 @@ static int inet_peer_gc(struct inet_peer_base *base,
ttl = inet_peer_maxttl
- (inet_peer_maxttl - inet_peer_minttl) / HZ *
base->total / inet_peer_threshold * HZ;
- stackptr--; /* last stack slot is peer_avl_empty */
- while (stackptr > stack) {
- stackptr--;
- p = rcu_deref_locked(**stackptr, base);
- if (refcount_read(&p->refcnt) == 1) {
- smp_rmb();
- delta = (__u32)jiffies - p->dtime;
- if (delta >= ttl && refcount_dec_if_one(&p->refcnt)) {
- p->gc_next = gchead;
- gchead = p;
- }
- }
+ for (i = 0; i < gc_cnt; i++) {
+ p = gc_stack[i];
+ delta = (__u32)jiffies - p->dtime;
+ if (delta < ttl || !refcount_dec_if_one(&p->refcnt))
+ gc_stack[i] = NULL;
}
- while ((p = gchead) != NULL) {
- gchead = p->gc_next;
- cnt++;
- unlink_from_pool(p, base, stack);
+ for (i = 0; i < gc_cnt; i++) {
+ p = gc_stack[i];
+ if (p) {
+ rb_erase(&p->rb_node, &base->rb_root);
+ base->total--;
+ call_rcu(&p->rcu, inetpeer_free_rcu);
+ }
}
- return cnt;
}
struct inet_peer *inet_getpeer(struct inet_peer_base *base,
const struct inetpeer_addr *daddr,
int create)
{
- struct inet_peer __rcu **stack[PEER_MAXDEPTH], ***stackptr;
- struct inet_peer *p;
- unsigned int sequence;
- int invalidated, gccnt = 0;
+ struct inet_peer *p, *gc_stack[PEER_MAX_GC];
+ struct rb_node **pp, *parent;
+ unsigned int gc_cnt, seq;
+ int invalidated;
/* Attempt a lockless lookup first.
* Because of a concurrent writer, we might not find an existing entry.
*/
rcu_read_lock();
- sequence = read_seqbegin(&base->lock);
- p = lookup_rcu(daddr, base);
- invalidated = read_seqretry(&base->lock, sequence);
+ seq = read_seqbegin(&base->lock);
+ p = lookup(daddr, base, seq, NULL, &gc_cnt, &parent, &pp);
+ invalidated = read_seqretry(&base->lock, seq);
rcu_read_unlock();
if (p)
@@ -428,36 +198,31 @@ struct inet_peer *inet_getpeer(struct inet_peer_base *base,
/* retry an exact lookup, taking the lock before.
* At least, nodes should be hot in our cache.
*/
+ parent = NULL;
write_seqlock_bh(&base->lock);
-relookup:
- p = lookup(daddr, stack, base);
- if (p != peer_avl_empty) {
- refcount_inc(&p->refcnt);
- write_sequnlock_bh(&base->lock);
- return p;
- }
- if (!gccnt) {
- gccnt = inet_peer_gc(base, stack, stackptr);
- if (gccnt && create)
- goto relookup;
- }
- p = create ? kmem_cache_alloc(peer_cachep, GFP_ATOMIC) : NULL;
- if (p) {
- p->daddr = *daddr;
- refcount_set(&p->refcnt, 2);
- atomic_set(&p->rid, 0);
- p->metrics[RTAX_LOCK-1] = INETPEER_METRICS_NEW;
- p->rate_tokens = 0;
- /* 60*HZ is arbitrary, but chosen enough high so that the first
- * calculation of tokens is at its maximum.
- */
- p->rate_last = jiffies - 60*HZ;
- INIT_LIST_HEAD(&p->gc_list);
- /* Link the node. */
- link_to_pool(p, base);
- base->total++;
+ gc_cnt = 0;
+ p = lookup(daddr, base, seq, gc_stack, &gc_cnt, &parent, &pp);
+ if (!p && create) {
+ p = kmem_cache_alloc(peer_cachep, GFP_ATOMIC);
+ if (p) {
+ p->daddr = *daddr;
+ refcount_set(&p->refcnt, 2);
+ atomic_set(&p->rid, 0);
+ p->metrics[RTAX_LOCK-1] = INETPEER_METRICS_NEW;
+ p->rate_tokens = 0;
+ /* 60*HZ is arbitrary, but chosen enough high so that the first
+ * calculation of tokens is at its maximum.
+ */
+ p->rate_last = jiffies - 60*HZ;
+
+ rb_link_node(&p->rb_node, parent, pp);
+ rb_insert_color(&p->rb_node, &base->rb_root);
+ base->total++;
+ }
}
+ if (gc_cnt)
+ inet_peer_gc(base, gc_stack, gc_cnt);
write_sequnlock_bh(&base->lock);
return p;
@@ -467,8 +232,9 @@ EXPORT_SYMBOL_GPL(inet_getpeer);
void inet_putpeer(struct inet_peer *p)
{
p->dtime = (__u32)jiffies;
- smp_mb__before_atomic();
- refcount_dec(&p->refcnt);
+
+ if (refcount_dec_and_test(&p->refcnt))
+ call_rcu(&p->rcu, inetpeer_free_rcu);
}
EXPORT_SYMBOL_GPL(inet_putpeer);
@@ -513,30 +279,16 @@ bool inet_peer_xrlim_allow(struct inet_peer *peer, int timeout)
}
EXPORT_SYMBOL(inet_peer_xrlim_allow);
-static void inetpeer_inval_rcu(struct rcu_head *head)
-{
- struct inet_peer *p = container_of(head, struct inet_peer, gc_rcu);
-
- spin_lock_bh(&gc_lock);
- list_add_tail(&p->gc_list, &gc_list);
- spin_unlock_bh(&gc_lock);
-
- schedule_delayed_work(&gc_work, gc_delay);
-}
-
void inetpeer_invalidate_tree(struct inet_peer_base *base)
{
- struct inet_peer *root;
-
- write_seqlock_bh(&base->lock);
+ struct inet_peer *p, *n;
- root = rcu_deref_locked(base->root, base);
- if (root != peer_avl_empty) {
- base->root = peer_avl_empty_rcu;
- base->total = 0;
- call_rcu(&root->gc_rcu, inetpeer_inval_rcu);
+ rbtree_postorder_for_each_entry_safe(p, n, &base->rb_root, rb_node) {
+ inet_putpeer(p);
+ cond_resched();
}
- write_sequnlock_bh(&base->lock);
+ base->rb_root = RB_ROOT;
+ base->total = 0;
}
EXPORT_SYMBOL(inetpeer_invalidate_tree);
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 50c74cd890bc..b631ec685d77 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -853,61 +853,6 @@ csum_page(struct page *page, int offset, int copy)
return csum;
}
-static inline int ip_ufo_append_data(struct sock *sk,
- struct sk_buff_head *queue,
- int getfrag(void *from, char *to, int offset, int len,
- int odd, struct sk_buff *skb),
- void *from, int length, int hh_len, int fragheaderlen,
- int transhdrlen, int maxfraglen, unsigned int flags)
-{
- struct sk_buff *skb;
- int err;
-
- /* There is support for UDP fragmentation offload by network
- * device, so create one single skb packet containing complete
- * udp datagram
- */
- skb = skb_peek_tail(queue);
- if (!skb) {
- skb = sock_alloc_send_skb(sk,
- hh_len + fragheaderlen + transhdrlen + 20,
- (flags & MSG_DONTWAIT), &err);
-
- if (!skb)
- return err;
-
- /* reserve space for Hardware header */
- skb_reserve(skb, hh_len);
-
- /* create space for UDP/IP header */
- skb_put(skb, fragheaderlen + transhdrlen);
-
- /* initialize network header pointer */
- skb_reset_network_header(skb);
-
- /* initialize protocol header pointer */
- skb->transport_header = skb->network_header + fragheaderlen;
-
- skb->csum = 0;
-
- if (flags & MSG_CONFIRM)
- skb_set_dst_pending_confirm(skb, 1);
-
- __skb_queue_tail(queue, skb);
- } else if (skb_is_gso(skb)) {
- goto append;
- }
-
- skb->ip_summed = CHECKSUM_PARTIAL;
- /* specify the length of each IP datagram fragment */
- skb_shinfo(skb)->gso_size = maxfraglen - fragheaderlen;
- skb_shinfo(skb)->gso_type = SKB_GSO_UDP;
-
-append:
- return skb_append_datato_frags(sk, skb, getfrag, from,
- (length - transhdrlen));
-}
-
static int __ip_append_data(struct sock *sk,
struct flowi4 *fl4,
struct sk_buff_head *queue,
@@ -965,18 +910,6 @@ static int __ip_append_data(struct sock *sk,
csummode = CHECKSUM_PARTIAL;
cork->length += length;
- if ((((length + (skb ? skb->len : fragheaderlen)) > mtu) ||
- (skb && skb_is_gso(skb))) &&
- (sk->sk_protocol == IPPROTO_UDP) &&
- (rt->dst.dev->features & NETIF_F_UFO) && !dst_xfrm(&rt->dst) &&
- (sk->sk_type == SOCK_DGRAM) && !sk->sk_no_check_tx) {
- err = ip_ufo_append_data(sk, queue, getfrag, from, length,
- hh_len, fragheaderlen, transhdrlen,
- maxfraglen, flags);
- if (err)
- goto error;
- return 0;
- }
/* So, what's going on in the loop below?
*
@@ -1287,15 +1220,6 @@ ssize_t ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page,
if (!skb)
return -EINVAL;
- if ((size + skb->len > mtu) &&
- (sk->sk_protocol == IPPROTO_UDP) &&
- (rt->dst.dev->features & NETIF_F_UFO)) {
- if (skb->ip_summed != CHECKSUM_PARTIAL)
- return -EOPNOTSUPP;
-
- skb_shinfo(skb)->gso_size = mtu - fragheaderlen;
- skb_shinfo(skb)->gso_type = SKB_GSO_UDP;
- }
cork->length += size;
while (size > 0) {
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index 0192c255e508..5ed63d250950 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -584,33 +584,6 @@ static struct rtnl_link_ops vti_link_ops __read_mostly = {
.get_link_net = ip_tunnel_get_link_net,
};
-static bool is_vti_tunnel(const struct net_device *dev)
-{
- return dev->netdev_ops == &vti_netdev_ops;
-}
-
-static int vti_device_event(struct notifier_block *unused,
- unsigned long event, void *ptr)
-{
- struct net_device *dev = netdev_notifier_info_to_dev(ptr);
- struct ip_tunnel *tunnel = netdev_priv(dev);
-
- if (!is_vti_tunnel(dev))
- return NOTIFY_DONE;
-
- switch (event) {
- case NETDEV_DOWN:
- if (!net_eq(tunnel->net, dev_net(dev)))
- xfrm_garbage_collect(tunnel->net);
- break;
- }
- return NOTIFY_DONE;
-}
-
-static struct notifier_block vti_notifier_block __read_mostly = {
- .notifier_call = vti_device_event,
-};
-
static int __init vti_init(void)
{
const char *msg;
@@ -618,8 +591,6 @@ static int __init vti_init(void)
pr_info("IPv4 over IPsec tunneling driver\n");
- register_netdevice_notifier(&vti_notifier_block);
-
msg = "tunnel device";
err = register_pernet_device(&vti_net_ops);
if (err < 0)
@@ -652,7 +623,6 @@ xfrm_proto_ah_failed:
xfrm_proto_esp_failed:
unregister_pernet_device(&vti_net_ops);
pernet_dev_failed:
- unregister_netdevice_notifier(&vti_notifier_block);
pr_err("vti init: failed to register %s\n", msg);
return err;
}
@@ -664,7 +634,6 @@ static void __exit vti_fini(void)
xfrm4_protocol_deregister(&vti_ah4_protocol, IPPROTO_AH);
xfrm4_protocol_deregister(&vti_esp4_protocol, IPPROTO_ESP);
unregister_pernet_device(&vti_net_ops);
- unregister_netdevice_notifier(&vti_notifier_block);
}
module_init(vti_init);
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 4e985dea1dd2..886d874775df 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2377,7 +2377,6 @@ bool tcp_schedule_loss_probe(struct sock *sk)
struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
u32 timeout, tlp_time_stamp, rto_time_stamp;
- u32 rtt = usecs_to_jiffies(tp->srtt_us >> 3);
/* No consecutive loss probes. */
if (WARN_ON(icsk->icsk_pending == ICSK_TIME_LOSS_PROBE)) {
@@ -2406,15 +2405,19 @@ bool tcp_schedule_loss_probe(struct sock *sk)
tcp_send_head(sk))
return false;
- /* Probe timeout is at least 1.5*rtt + TCP_DELACK_MAX to account
+ /* Probe timeout is 2*rtt. Add minimum RTO to account
* for delayed ack when there's one outstanding packet. If no RTT
* sample is available then probe after TCP_TIMEOUT_INIT.
*/
- timeout = rtt << 1 ? : TCP_TIMEOUT_INIT;
- if (tp->packets_out == 1)
- timeout = max_t(u32, timeout,
- (rtt + (rtt >> 1) + TCP_DELACK_MAX));
- timeout = max_t(u32, timeout, msecs_to_jiffies(10));
+ if (tp->srtt_us) {
+ timeout = usecs_to_jiffies(tp->srtt_us >> 2);
+ if (tp->packets_out == 1)
+ timeout += TCP_RTO_MIN;
+ else
+ timeout += TCP_TIMEOUT_MIN;
+ } else {
+ timeout = TCP_TIMEOUT_INIT;
+ }
/* If RTO is shorter, just schedule TLP in its place. */
tlp_time_stamp = tcp_jiffies32 + timeout;
diff --git a/net/ipv4/tcp_recovery.c b/net/ipv4/tcp_recovery.c
index fe9a493d0208..449cd914d58e 100644
--- a/net/ipv4/tcp_recovery.c
+++ b/net/ipv4/tcp_recovery.c
@@ -113,7 +113,7 @@ void tcp_rack_mark_lost(struct sock *sk)
tp->rack.advanced = 0;
tcp_rack_detect_loss(sk, &timeout);
if (timeout) {
- timeout = usecs_to_jiffies(timeout + TCP_REO_TIMEOUT_MIN);
+ timeout = usecs_to_jiffies(timeout) + TCP_TIMEOUT_MIN;
inet_csk_reset_xmit_timer(sk, ICSK_TIME_REO_TIMEOUT,
timeout, inet_csk(sk)->icsk_rto);
}
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 781250151d40..97658bfc1b58 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -21,7 +21,7 @@ static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb,
__be16 new_protocol, bool is_ipv6)
{
int tnl_hlen = skb_inner_mac_header(skb) - skb_transport_header(skb);
- bool remcsum, need_csum, offload_csum, ufo, gso_partial;
+ bool remcsum, need_csum, offload_csum, gso_partial;
struct sk_buff *segs = ERR_PTR(-EINVAL);
struct udphdr *uh = udp_hdr(skb);
u16 mac_offset = skb->mac_header;
@@ -61,8 +61,6 @@ static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb,
remcsum = !!(skb_shinfo(skb)->gso_type & SKB_GSO_TUNNEL_REMCSUM);
skb->remcsum_offload = remcsum;
- ufo = !!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP);
-
need_ipsec = skb_dst(skb) && dst_xfrm(skb_dst(skb));
/* Try to offload checksum if possible */
offload_csum = !!(need_csum &&
@@ -77,7 +75,7 @@ static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb,
* outer one so strip the existing checksum feature flags and
* instead set the flag based on our outer checksum offload value.
*/
- if (remcsum || ufo) {
+ if (remcsum) {
features &= ~NETIF_F_CSUM_MASK;
if (!need_csum || offload_csum)
features |= NETIF_F_HW_CSUM;
@@ -189,66 +187,16 @@ out_unlock:
}
EXPORT_SYMBOL(skb_udp_tunnel_segment);
-static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb,
- netdev_features_t features)
+static struct sk_buff *udp4_tunnel_segment(struct sk_buff *skb,
+ netdev_features_t features)
{
struct sk_buff *segs = ERR_PTR(-EINVAL);
- unsigned int mss;
- __wsum csum;
- struct udphdr *uh;
- struct iphdr *iph;
if (skb->encapsulation &&
(skb_shinfo(skb)->gso_type &
- (SKB_GSO_UDP_TUNNEL|SKB_GSO_UDP_TUNNEL_CSUM))) {
+ (SKB_GSO_UDP_TUNNEL|SKB_GSO_UDP_TUNNEL_CSUM)))
segs = skb_udp_tunnel_segment(skb, features, false);
- goto out;
- }
- if (!pskb_may_pull(skb, sizeof(struct udphdr)))
- goto out;
-
- mss = skb_shinfo(skb)->gso_size;
- if (unlikely(skb->len <= mss))
- goto out;
-
- if (skb_gso_ok(skb, features | NETIF_F_GSO_ROBUST)) {
- /* Packet is from an untrusted source, reset gso_segs. */
-
- skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(skb->len, mss);
-
- segs = NULL;
- goto out;
- }
-
- /* Do software UFO. Complete and fill in the UDP checksum as
- * HW cannot do checksum of UDP packets sent as multiple
- * IP fragments.
- */
-
- uh = udp_hdr(skb);
- iph = ip_hdr(skb);
-
- uh->check = 0;
- csum = skb_checksum(skb, 0, skb->len, 0);
- uh->check = udp_v4_check(skb->len, iph->saddr, iph->daddr, csum);
- if (uh->check == 0)
- uh->check = CSUM_MANGLED_0;
-
- skb->ip_summed = CHECKSUM_NONE;
-
- /* If there is no outer header we can fake a checksum offload
- * due to the fact that we have already done the checksum in
- * software prior to segmenting the frame.
- */
- if (!skb->encap_hdr_csum)
- features |= NETIF_F_HW_CSUM;
-
- /* Fragment the skb. IP headers of the fragments are updated in
- * inet_gso_segment()
- */
- segs = skb_segment(skb, features);
-out:
return segs;
}
@@ -382,7 +330,7 @@ static int udp4_gro_complete(struct sk_buff *skb, int nhoff)
static const struct net_offload udpv4_offload = {
.callbacks = {
- .gso_segment = udp4_ufo_fragment,
+ .gso_segment = udp4_tunnel_segment,
.gro_receive = udp4_gro_receive,
.gro_complete = udp4_gro_complete,
},
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index 71b4ecc195c7..4aefb149fe0a 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -213,14 +213,6 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse)
fl4->flowi4_tos = iph->tos;
}
-static inline int xfrm4_garbage_collect(struct dst_ops *ops)
-{
- struct net *net = container_of(ops, struct net, xfrm.xfrm4_dst_ops);
-
- xfrm_garbage_collect_deferred(net);
- return (dst_entries_get_slow(ops) > ops->gc_thresh * 2);
-}
-
static void xfrm4_update_pmtu(struct dst_entry *dst, struct sock *sk,
struct sk_buff *skb, u32 mtu)
{
@@ -259,14 +251,13 @@ static void xfrm4_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
static struct dst_ops xfrm4_dst_ops_template = {
.family = AF_INET,
- .gc = xfrm4_garbage_collect,
.update_pmtu = xfrm4_update_pmtu,
.redirect = xfrm4_redirect,
.cow_metrics = dst_cow_metrics_generic,
.destroy = xfrm4_dst_destroy,
.ifdown = xfrm4_dst_ifdown,
.local_out = __ip_local_out,
- .gc_thresh = INT_MAX,
+ .gc_thresh = 32768,
};
static const struct xfrm_policy_afinfo xfrm4_policy_afinfo = {
OpenPOWER on IntegriCloud