ipv6: Create percpu rt6_info

After the patch
'ipv6: Only create RTF_CACHE routes after encountering pmtu exception',
we need to compensate the performance hit (bouncing dst->__refcnt).

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Cc: Hannes Frederic Sowa <hannes@stressinduktion.org>
Cc: Steffen Klassert <steffen.klassert@secunet.com>
Cc: Julian Anastasov <ja@ssi.bg>
Signed-off-by: David S. Miller <davem@davemloft.net>
This commit is contained in:
Martin KaFai Lau 2015-05-22 20:56:06 -07:00 committed by David S. Miller
parent 83a09abd1a
commit d52d3997f8
4 changed files with 142 additions and 18 deletions

View File

@ -124,6 +124,7 @@ struct rt6_info {
struct uncached_list *rt6i_uncached_list;
struct inet6_dev *rt6i_idev;
struct rt6_info * __percpu *rt6i_pcpu;
u32 rt6i_metric;
u32 rt6i_pmtu;
@ -164,7 +165,7 @@ static inline void rt6_update_expires(struct rt6_info *rt0, int timeout)
static inline u32 rt6_get_cookie(const struct rt6_info *rt)
{
if (unlikely(rt->dst.flags & DST_NOCACHE))
if (rt->rt6i_flags & RTF_PCPU || unlikely(rt->dst.flags & DST_NOCACHE))
rt = (struct rt6_info *)(rt->dst.from);
return rt->rt6i_node ? rt->rt6i_node->fn_sernum : 0;

View File

@ -34,6 +34,7 @@
#define RTF_PREF(pref) ((pref) << 27)
#define RTF_PREF_MASK 0x18000000
#define RTF_PCPU 0x40000000
#define RTF_LOCAL 0x80000000

View File

@ -154,10 +154,32 @@ static void node_free(struct fib6_node *fn)
kmem_cache_free(fib6_node_kmem, fn);
}
static void rt6_free_pcpu(struct rt6_info *non_pcpu_rt)
{
int cpu;
if (!non_pcpu_rt->rt6i_pcpu)
return;
for_each_possible_cpu(cpu) {
struct rt6_info **ppcpu_rt;
struct rt6_info *pcpu_rt;
ppcpu_rt = per_cpu_ptr(non_pcpu_rt->rt6i_pcpu, cpu);
pcpu_rt = *ppcpu_rt;
if (pcpu_rt) {
dst_free(&pcpu_rt->dst);
*ppcpu_rt = NULL;
}
}
}
static void rt6_release(struct rt6_info *rt)
{
if (atomic_dec_and_test(&rt->rt6i_ref))
if (atomic_dec_and_test(&rt->rt6i_ref)) {
rt6_free_pcpu(rt);
dst_free(&rt->dst);
}
}
static void fib6_link_table(struct net *net, struct fib6_table *tb)

View File

@ -165,11 +165,18 @@ static void rt6_uncached_list_flush_dev(struct net *net, struct net_device *dev)
}
}
static u32 *rt6_pcpu_cow_metrics(struct rt6_info *rt)
{
return dst_metrics_write_ptr(rt->dst.from);
}
static u32 *ipv6_cow_metrics(struct dst_entry *dst, unsigned long old)
{
struct rt6_info *rt = (struct rt6_info *)dst;
if (rt->rt6i_flags & RTF_CACHE)
if (rt->rt6i_flags & RTF_PCPU)
return rt6_pcpu_cow_metrics(rt);
else if (rt->rt6i_flags & RTF_CACHE)
return NULL;
else
return dst_cow_metrics_generic(dst, old);
@ -309,10 +316,10 @@ static const struct rt6_info ip6_blk_hole_entry_template = {
#endif
/* allocate dst with ip6_dst_ops */
static inline struct rt6_info *ip6_dst_alloc(struct net *net,
struct net_device *dev,
int flags,
struct fib6_table *table)
static struct rt6_info *__ip6_dst_alloc(struct net *net,
struct net_device *dev,
int flags,
struct fib6_table *table)
{
struct rt6_info *rt = dst_alloc(&net->ipv6.ip6_dst_ops, dev,
0, DST_OBSOLETE_FORCE_CHK, flags);
@ -327,6 +334,34 @@ static inline struct rt6_info *ip6_dst_alloc(struct net *net,
return rt;
}
static struct rt6_info *ip6_dst_alloc(struct net *net,
struct net_device *dev,
int flags,
struct fib6_table *table)
{
struct rt6_info *rt = __ip6_dst_alloc(net, dev, flags, table);
if (rt) {
rt->rt6i_pcpu = alloc_percpu_gfp(struct rt6_info *, GFP_ATOMIC);
if (rt->rt6i_pcpu) {
int cpu;
for_each_possible_cpu(cpu) {
struct rt6_info **p;
p = per_cpu_ptr(rt->rt6i_pcpu, cpu);
/* no one shares rt */
*p = NULL;
}
} else {
dst_destroy((struct dst_entry *)rt);
return NULL;
}
}
return rt;
}
static void ip6_dst_destroy(struct dst_entry *dst)
{
struct rt6_info *rt = (struct rt6_info *)dst;
@ -335,6 +370,9 @@ static void ip6_dst_destroy(struct dst_entry *dst)
dst_destroy_metrics_generic(dst);
if (rt->rt6i_pcpu)
free_percpu(rt->rt6i_pcpu);
rt6_uncached_list_del(rt);
idev = rt->rt6i_idev;
@ -912,11 +950,11 @@ static struct rt6_info *ip6_rt_cache_alloc(struct rt6_info *ort,
* Clone the route.
*/
if (ort->rt6i_flags & RTF_CACHE)
if (ort->rt6i_flags & (RTF_CACHE | RTF_PCPU))
ort = (struct rt6_info *)ort->dst.from;
rt = ip6_dst_alloc(dev_net(ort->dst.dev), ort->dst.dev,
0, ort->rt6i_table);
rt = __ip6_dst_alloc(dev_net(ort->dst.dev), ort->dst.dev,
0, ort->rt6i_table);
if (!rt)
return NULL;
@ -943,6 +981,54 @@ static struct rt6_info *ip6_rt_cache_alloc(struct rt6_info *ort,
return rt;
}
static struct rt6_info *ip6_rt_pcpu_alloc(struct rt6_info *rt)
{
struct rt6_info *pcpu_rt;
pcpu_rt = __ip6_dst_alloc(dev_net(rt->dst.dev),
rt->dst.dev, rt->dst.flags,
rt->rt6i_table);
if (!pcpu_rt)
return NULL;
ip6_rt_copy_init(pcpu_rt, rt);
pcpu_rt->rt6i_protocol = rt->rt6i_protocol;
pcpu_rt->rt6i_flags |= RTF_PCPU;
return pcpu_rt;
}
/* It should be called with read_lock_bh(&tb6_lock) acquired */
static struct rt6_info *rt6_get_pcpu_route(struct rt6_info *rt)
{
struct rt6_info *pcpu_rt, *prev, **p;
p = this_cpu_ptr(rt->rt6i_pcpu);
pcpu_rt = *p;
if (pcpu_rt)
goto done;
pcpu_rt = ip6_rt_pcpu_alloc(rt);
if (!pcpu_rt) {
struct net *net = dev_net(rt->dst.dev);
pcpu_rt = net->ipv6.ip6_null_entry;
goto done;
}
prev = cmpxchg(p, NULL, pcpu_rt);
if (prev) {
/* If someone did it before us, return prev instead */
dst_destroy(&pcpu_rt->dst);
pcpu_rt = prev;
}
done:
dst_hold(&pcpu_rt->dst);
rt6_dst_from_metrics_check(pcpu_rt);
return pcpu_rt;
}
static struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, int oif,
struct flowi6 *fl6, int flags)
{
@ -975,11 +1061,13 @@ redo_rt6_select:
}
}
dst_use(&rt->dst, jiffies);
read_unlock_bh(&table->tb6_lock);
if (rt == net->ipv6.ip6_null_entry || (rt->rt6i_flags & RTF_CACHE)) {
goto done;
dst_use(&rt->dst, jiffies);
read_unlock_bh(&table->tb6_lock);
rt6_dst_from_metrics_check(rt);
return rt;
} else if (unlikely((fl6->flowi6_flags & FLOWI_FLAG_KNOWN_NH) &&
!(rt->rt6i_flags & RTF_GATEWAY))) {
/* Create a RTF_CACHE clone which will not be
@ -990,6 +1078,9 @@ redo_rt6_select:
struct rt6_info *uncached_rt;
dst_use(&rt->dst, jiffies);
read_unlock_bh(&table->tb6_lock);
uncached_rt = ip6_rt_cache_alloc(rt, &fl6->daddr, NULL);
dst_release(&rt->dst);
@ -997,13 +1088,22 @@ redo_rt6_select:
rt6_uncached_list_add(uncached_rt);
else
uncached_rt = net->ipv6.ip6_null_entry;
dst_hold(&uncached_rt->dst);
return uncached_rt;
}
done:
rt6_dst_from_metrics_check(rt);
return rt;
} else {
/* Get a percpu copy */
struct rt6_info *pcpu_rt;
rt->dst.lastuse = jiffies;
rt->dst.__use++;
pcpu_rt = rt6_get_pcpu_route(rt);
read_unlock_bh(&table->tb6_lock);
return pcpu_rt;
}
}
static struct rt6_info *ip6_pol_route_input(struct net *net, struct fib6_table *table,
@ -1147,7 +1247,7 @@ static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie)
rt6_dst_from_metrics_check(rt);
if (unlikely(dst->flags & DST_NOCACHE))
if ((rt->rt6i_flags & RTF_PCPU) || unlikely(dst->flags & DST_NOCACHE))
return rt6_dst_from_check(rt, cookie);
else
return rt6_check(rt, cookie);